Search

Digital technologies can be used to gather accurate information about the behavior of structural components for improving systems design, as well as for enabling advanced Structural Health Monitoring (SHM) strategies. New avenues for achieving automated and continuous structural assessment are opened up via development of virtualization approaches delivering so-called Digital Twins (DTs), i.e., digital mirrored representations of physical systems relying on fusion of simulation models and real-time monitoring data. In this framework, the main motivation of the work presented in this paper stems from the existing challenges in the implementation and deployment of a real-time predictive framework for virtualization of dynamic systems. Kalman-based filters are usually employed in this context to address the task of joint input-state prediction in structural dynamics. A Gaussian Process Latent Force Model (GPLFM) approach is exploited in this work to construct flexible data-driven a priori models for the unknown inputs, which are then coupled with a combined deterministic-stochastic state-space model of the structural component under study for Kalman-based input-state estimation. The use of Gaussian Process (GP) regression for this task overcomes the limitations of the conventionally adopted random-walk model, thus limiting the necessity of offline user-dependent calibration of this type of data assimilation methods. This paper proposes the use of alternative covariance functions for GP regression in structural dynamics. A theoretical analysis of the GPLFMs linked to the investigated covariance functions is offered. The outcome of this study provides insights into the applicability of each covariance type for GP-based input-state estimation. The proposed framework is validated via an illustrative simulated example, namely a 3 Degrees of Freedom (DOF) system subjected to an array of different loading scenarios. Additionally, the performance of the method is experimentally assessed on the task of joint input-state estimation during testing of a 3D-printed scaled Wind Turbine (WT) blade. [ABSTRACT FROM AUTHOR]

• A reinforced concrete moment-resisting frame was tested on a shaking table. • Table excitations and frame response accelerations with increasing intensities of the table motion were acquired. • Crack images and three damage-sensitive features are compared in various stages of the damage. • The results explore the dependence of the damage-sensitive features on horizontal peak table velocities. Methods of early warning in damage detection of civil engineering structures represent a particular challenge in Structural Health Monitoring (SHM). To investigate these problems, vibration records of a full-size, reinforced concrete frame subjected to seismic damages on a shaking table, were investigated. The seismic recordings of excitations and response were accompanied by images of cracks associated with each state of the damage. This paper presents the results of the damage identification from non-linear response during the damaging phases of the shaking table tests. Time-dependent base shear forces were observed, together with wavelet spectral analyses of the responses. Three damage-sensitive features accounting for decreasing stiffness, energy dissipation, and the wavelet changes during inelastic seismic responses were analyzed as functions of horizontal peak table velocities. The paper aims to study seismic response records of moment-resisting reinforced concrete structure frames in search of prospective simple online damage indicators which could be applied to start alarms, right after excessive damage loads, e.g., in instantaneous earthquake rapid damage assessments of buildings. [ABSTRACT FROM AUTHOR]

• IE models and AGs are used to describe and compare a set of six real bridge decks bridges. • Modal responses from each of the six bridges are identified and subsequently compared using the Modal Assurance Criterion. • increasing number of elements making up the beam and slab bridge decks results in a consistent decreasing similarity metric • Similarity metrics from Fig. 7 appear largely reflective of the meaningful similarities between the bridges Bridges are valuable infrastructure assets that are challenging and expensive to maintain. State-of-the-art data-based bridge SHM solutions look to use bridge response data for condition assessment and damage detection. Data-based SHM methods can be limited in their application as they require large datasets to train models effectively, and most bridges lack the available data for the approaches to work. Further, it would be expensive and unrealistic to collect the required datasets to employ data-based methods to entire bridge networks. Recently, a population-based structural health monitoring (PBSHM) approach was proposed that seeks to leverage the data available for SHM problems by pooling together similar structures with their datasets. The PBSHM approach could be valuable in bridge SHM, enhancing the datasets available for 'populations of bridges. The PBSHM approach for assessing the similarity of bridges has been considered before and was shown to be useful for identifying similar and different bridge types. However, no data were considered in the previous work, and similarity metrics were only qualified using engineering judgement. For the PBSHM approach to be useful in bridge SHM, there is still a need to check that 'similar' bridges have similar responses for transfer learning to be feasible. This paper expands upon previous work and provides originality by investigating if bridges identified as similar also exhibit similar responses. The PBSHM derived similarity metrics convey the topological similarity between structures, and mode shapes are identified as being a topologically sensitive bridge response. Therefore, a modal test campaign is carried out for a set of six real bridges, and Operational Modal Analysis is used to identify modal responses from each of the bridge decks. The Modal Assurance Criterion is used to evaluate the similarity between the mode shapes from pairs of bridges and is subsequently compared to the similarity metrics evaluated between those bridges. The similarity metrics were found to be reflective of the similarities identified between the respective bridges' mode shapes for bridges of the same and different types. The significance of this finding is that it is an important step towards validating the PBSHM comparison approach for identify similar structures where transfer learning might be attempted. [ABSTRACT FROM AUTHOR]

In this paper, an alternative to solving Bayesian inverse problems for structural health monitoring based on a variational formulation with so-called transport maps is examined. The Bayesian inverse formulation is a widely used tool in structural health monitoring applications. While Markov Chain Monte Carlo (MCMC) methods are often implemented in these settings, they come with the problem of using many model evaluations, which in turn can become quite costly. We focus here on recent developments in the field of transport theory, where the problem is formulated as finding a deterministic, invertible mapping between some easy to evaluate reference density and the posterior. The resulting variational formulation can be solved with integration and optimization methods. We develop a general formulation for the application of transport maps to vibration-based structural health monitoring. Further, we study influences of different integration approaches on the efficiency and accuracy of the transport map approach and compare it to the Transitional MCMC algorithm, a widely used method for structural identification. Both methods are applied to a lower-dimensional dynamic model with uni- and multi-modal properties, as well as to a higher-dimensional neural network surrogate system of an airplane structure. We find that transport maps have a significant increase in accuracy and efficiency, when used in the right circumstances. [ABSTRACT FROM AUTHOR]

Vision-based methods have shown great potential in vibration-based structural health monitoring (SHM). However, these methods are not standard practices yet, since their accuracy and robustness may be influenced by extreme environmental conditions. To this end, this paper proposed a method, named dynamic regularized total variation correlation filter (DTVCF). In DTVCF, an effective optimization problem, which contains the space and structural shape information, is defined for dynamically updating the regularization weight map. Then the regularization weight map is smoothed by a total variation (TV) optimization. These are to better track the dramatically changing or almost invisible structural shape, caused by extreme environmental conditions. Moreover, efficient subpixel image registration (ESR) is used in each tracked region of interest (ROI), over time, to achieve subpixel accuracy. The superiority of DTVCF was validated in extreme environmental conditions. DTVCF could achieve subpixel level structural displacement estimation with high accuracy. Furthermore, DTVCF could process approximately 9.00 frame/s, and 3.50 frame/s in two shaking table tests, indicating its high efficiency for SHM applications. [ABSTRACT FROM AUTHOR]

Detecting anomalies in the vibrational features of age-old buildings is crucial within the Structural Health Monitoring (SHM) framework. The SHM techniques can leverage information from onsite measurements and environmental sources to identify the dynamic properties (such as the frequencies) of the monitored structure, searching for possible deviations or unusual behavior over time. The Temporal Fusion Transformer (TFT) network is a deep learning algorithm designed for multi-horizon time series forecasting and initially tested on electricity, traffic, retail, and volatility problems. In this paper, it is applied to SHM. More precisely, the TFT approach is adopted to investigate the behavior of the Guinigi Tower located in Lucca (Italy) and subjected to a long-term dynamic monitoring campaign. The TFT network is trained on the tower's experimental frequencies enriched with other environmental parameters. The transformer is then employed to predict the vibrational features (natural frequencies, root mean squares values of the velocity time series) and detect possible anomalies or unexpected events by inspecting how much the actual frequencies deviate from the predicted ones. The TFT technique is used to detect the effects of the Viareggio earthquake that occurred on 6 February 2022, and the structural damage induced by three simulated damage scenarios. [ABSTRACT FROM AUTHOR]

Continuous monitoring of acoustic events in concrete such as cracking and impacting, and providing their location information is a significant topic in structural health monitoring (SHM). This paper develops a combined technique of concrete implantable cube (CIC) and probabilistic localization method to monitor acoustic sources on concrete slabs. The CIC that integrates an octahedron-shaped piezoelectric sensor array can be implanted in concrete structures in long term and supply an omni-dimensional sensing capacity. Aiming at the designed sensor array and the impacts of randomness and heterogeneity of concrete material on the localization accuracy, a probabilistic localization method was proposed. To demonstrate the feasibility of the proposed technique, an experiment including 48 impact tests was conducted on a concrete slab specimen. The acoustic signals received by the implanted CIC were used to reconstruct localization maps to predict the impact areas. The results were quantified using three matrixes including accuracy, precision, and recall; consequently, the accuracy obtained the highest average score close to 0.98 and performed most steadily. In addition, to optimize the proposed technique furtherly, the sensitivity of two key parameters associated with this method were discussed. Overall, the experimental study showed a great potential of this developed technique for long-term monitoring acoustic events on concrete structures. [ABSTRACT FROM AUTHOR]

Damage localization based on ambient vibration data in combination with finite element models can be challenging, in particular due to the large number of parameters in the model and noisy measurement data. Changes in different structural parameters can cause similar changes in data-driven features, and vice versa, it can be challenging to identify which parameter caused the deviation in the data. The problem is ill-conditioned and slight variations in the features, due to inherent statistical uncertainty, can lead to significant errors in the result interpretation. A possible solution is sensitivity-based statistical tests in combination with a parameter clustering approach that considers the uncertainties of data-driven features. In this context, this paper introduces the concept of damage localizability , and provides a framework to evaluate it based on the minimum detectable parameter changes, possible false alarms in unchanged parameters, as well as the achievable damage localization resolution. Since clustering approaches depend on user-defined hyperparameters, such as the number of clusters, the second objective of this paper is to optimize the performance of the damage localization, by adjusting the hyperparameters for clustering. A particular strength of the approach is that the analysis can be conducted based on data and a numerical model from the undamaged structure alone, making it a suitable approach to assess and to optimize the diagnosis performance before damage occurs. For proof of concept, a laboratory case study on a simply-supported steel beam is presented, where the localizability of mass changes is analyzed and optimized. • An approach is developed to assess and optimize the performance of damage localization tests. • Clustering of sensitivity vectors avoids ill-conditioning. • Localizability is defined by the three criteria: resolution, detectability, and false alarms. • All criteria can be quantified based on data from undamaged structures, and a numerical model. • Experimental data confirm the predictive capabilities of the performance assessment. [ABSTRACT FROM AUTHOR]

Interfacial debonding identification within reinforced concrete (RC) structures is an ongoing and critical issue in structural health monitoring. In this paper, a novel nonlinear harmonics-based method for identifying, localizing, and quantifying interfacial debonding in RC beams is presented. The mode conversion phenomenon and contact acoustic nonlinearity of guided waves at interfacial debonding region are thoroughly examined using a combined theoretical, numerical, and experimental investigation, which sheds light on the propagation behavior of the first and second harmonics in RC beams with single interfacial debonding. Inspired by the phase-reversal approach, the temporal separation of the second harmonic is achieved by integrating the excitation results from both the original and phase-reversed signals. The theoretical investigation is conducted to correlate the arrival time of harmonics with structural damage, and its accuracy is validated by the numerical group velocity inversion and wavenumber-frequency analysis. The experimental evaluation, involving six RC beam specimens with varying debonding length, further demonstrates the validity of the method for precise interfacial debonding identification. The experimental and numerical evidence confirms the effectiveness of the proposed method, highlighting its potential for practical application. [ABSTRACT FROM AUTHOR]

Structural Health Monitoring has the potential to enhance the safety and serviceability of our aging infrastructures by detecting anomalies at an early stage. Bayesian Dynamic Linear Models (BDLM) have been shown to be effective at detecting anomalies by extracting structural patterns and latent variables from complex and noisy time series. However, the autoregressive component modelling the stationary prediction errors in most BDLM has a tendency to wrongfully capture patterns that should be attributed to anomalies, and thus hinders their detectability. This paper proposes a new bounded autoregressive (B A R) component, which imposes constraints on the autoregressive latent process with a new mixture Rectified Linear activation Unit. The B A R component is probabilistically verified on synthetic data using a new F1t metric, and is validated using real observations collected on a bridge and on a dam located in Canada. The experimental results demonstrate that the B A R model surpasses the performance of the existing autoregressive component with (1) an improved accuracy at estimating hidden states, (2) an early detection of anomalies, (3) a capacity to detect smaller anomaly magnitudes, and (4) the ability to control the tradeoff between the anomaly detectability and the false alarm rate. [ABSTRACT FROM AUTHOR]

• A high-SNR ultrasonic method is developed for the full matrix capture dataset. • The method shows strong advantage for weakly heterogenous medium in image quality. • The method is suitable for the multilayer medium and is competitive in efficiency. • The method can adapt to the probes with various shapes. • Simulation and experiments are conducted for the method validation. Ultrasonic full matrix capture (FMC) dataset has been widely used in various fields including biomedical imaging, non-destructive detection and structural health monitoring. However, the measurement medium is usually weakly heterogeneous, which leads to the speckle artifacts in the imaging result of the conventional methods and reduces the signal-to-noise ratio (SNR). To overcome this deficiency, this paper proposes a novel high-SNR method to recover the targets in the weakly heterogeneous medium clearly from the FMC dataset. Singular value decomposition (SVD) is utilized to extract the signal subspace, and it transforms the passive reflector detection problem into an active source location problem. Then, the beamforming is conducted with the cross-spectral matrix calculated by the signal subspace. Furthermore, the deconvolution process is implemented with the non-stationary point spread function (PSF) for the further suppression of speckle artifacts. In addition, the phase shift factor is introduced to make the proposed method adapt to the multilayer medium. Three existing imaging methods for FMC datasets are introduced to make comparisons with the proposed method. The simulation and experiment results demonstrate that the proposed method can recover the image with much higher SNR (>20 dB) wherein the speckle artifacts in the background are well suppressed. Additionally, the proposed method is more efficient than total focusing method, and it only takes about 2 s to obtain the high-quality imaging result. [ABSTRACT FROM AUTHOR]

Fatigue damage prognosis studies typically involve updating a degradation model based on the collected measurements. The updated model can accurately depict the past degradation process, while it is always assumed to be capable of describing the future damage progression, and thus can be used for remaining useful life (RUL) prediction. However, this assumption cannot always hold true, due to the uncertainties arising from the degradation process. In this context, this paper proposes a scheme of prognostic-aided model updating in a particle filter (PF)-based prognostic framework, which empowers the updated model to capture both the historical and future degradation process, and consequently, enhances the prognostic performance. First, two degradation models are formulated using the physics-based damage state and the data-driven health indicator (HI), respectively. The former is then re-formulated in state space by incorporating a measurement model. Next, the state space model is updated by the latest measurement through PF, providing the RUL and lifetime percentage (LP) distributions. Finally, the particles of damage state and parameters are modified by comparing the LP distributions from the updated model and the latter degradation model. The feasibility and robustness of the proposed method are validated by an experimental study, where an aluminum lug joint subject to fatigue crack growth is monitored by a guided wave measurement system. [ABSTRACT FROM AUTHOR]

Health monitoring technologies, empowered by sensor-driven information and model updating, play an important role in assessing the status of civil structures and detecting anomalies. However, significant domain discrepancies exist in the distribution of physical parameters between numerical structural models and their real-world counterparts. As a result, many health monitoring theories struggle to be effective in practice, even if they perform perfectly in the simulated data. To bridge the domain discrepancies, this paper proposes an unsupervised domain adaptation approach based on an adapted cycle-consistent generative adversarial network (CycleGAN) that incorporates physical constraints and a self-attention mechanism. The approach focuses on the mutual transformation of the multi-channel time series obtained from numerical models and actual structures. Specifically, the physical constraints are derived from the governing equation of linear dynamic systems, while the self-attention mechanism is achieved by adding transformer structures to both the generator and discriminator. Through free-vibration experiments on a steel beam and a large-scale steel bridge model, the physical constraints and transformer structures have proven beneficial for improving the learning capability and training stability of the GAN model. Furthermore, the proposed approach is not only verified as effective in transforming acceleration responses between the test structures and their corresponding finite element models in both time and frequency domains but has also been shown to reproduce mode shapes accurately. [ABSTRACT FROM AUTHOR]

• An AEKF-UM approach is proposed for identifying time-variant parameters with unknown mass distribution. • A real-time updating procedure is presented for improving the process and measurement noise covariance matrices. • An index is defined basing on dramatic increase of measurement noise covariance for damage instant detection. • The covariance resetting technique is used to enhance the tracking capability for effectively capturing the time-varying parameters. Although the extended Kalman filter (EKF) provides a promising way for structural state estimation, it cannot effectively track time-varying parameters online. Besides, the structural mass distribution is usually assumed to be known in advance for many EKF-based methods, limiting their applications. In this paper, by using limited observations, an adaptive EKF with unknown mass coefficients (AEKF-UM) approach is proposed for the identification of time-variant parameters and mass distribution at the same time. A real-time updating procedure is presented for improving the process and measurement noise covariance matrices at each time step to assure the stability and accuracy of convergence results. Based on the dramatic increase of measurement noise covariance, an index is defined for determining the damage instant. A covariance resetting technique is then used to enhance the tracking capability for the purpose of effectively capturing the time-varying parameters. The unknown mass coefficients can be estimated at the same time by adding them into the extended state vector. To validate the effectiveness of the proposed approach, two numerical cases are considered, i.e. (i) the Phase I ASCE structural health monitoring benchmark building structure, and (ii) a four-story nonlinear structure equipped with a magneto-rheological (MR) damper. Experimental tests on a four-story building model subject to base excitation are also conducted to investigate the performance of the proposed approach. Results show that the proposed approach is capable of satisfactorily tracking abrupt changes of stiffness parameters with unknown mass distributions. [ABSTRACT FROM AUTHOR]

• A novel deep neural network model is proposed, which uses two branches to reconstruct the real and imaginary parts of the signal, solving the key problem that deep neural network models are difficult to extract effective features from compressed signals in the time domain. • A large-scale frequency transformation matrix is decomposed into the multiplication of two small-scale matrices, greatly reducing the number of trainable parameters. • A Fourier Unit is introduced and its feature extraction ability is improved, further enhancing the feature extraction ability of the whole model without significantly increasing the model parameters. • The proposed method is capable of reconstructing vibration responses without relying on sparsity assumptions. Compressive sensing (CS) has become a promising technique for addressing the transmission and storage challenges associated with big data in structural health monitoring. However, classic CS methods require signals to have good sparsity, limiting their performance in low-sparse situations. In order to address this challenge, this paper proposes a deep learning-based CS algorithm for high accuracy reconstruction of structural vibration responses without the assumption of sparsity. The key innovations of the proposed method can be mainly divided into three points. Firstly, a novel deep neural network model is proposed, which uses two branches to reconstruct the real and imaginary parts of the signal in the frequency domain, solving the key problem that deep neural network models are difficult to extract effective features from compressed signals in the time domain. Secondly, a large-scale frequency transformation matrix is decomposed into the multiplication of two small-scale matrices, greatly reducing the number of trainable parameters, and solving the problem that the original frequency transformation block cannot be directly used to extract global frequency-domain features of structural vibration responses due to the large number of parameters. Thirdly, a Fourier Unit is introduced and its feature extraction ability is improved, further enhancing the feature extraction ability of the whole model without significantly increasing the model parameters. The model does not use the adversarial training strategy, and the training process is simple and stable. It also does not require a large amount of adjustment of hyper-parameters. The number of trainable parameters of the model is only about 4 million, and the model training can be carried out with low-cost hardware. The effectiveness of the proposed method is verified by the low sparsity vibration response of a laboratory grandstand simulator. The maximum sparsity level of the vibration response of the simulator with 30 nodes is 0.381, which is larger than the sparsity level of the vibration response of common large-scale civil structures, that is, the sparsity is smaller and the reconstruction difficulty is greater. Experimental results show that the reconstruction error of the two classic CS algorithms is more than 3 times higher than that of the proposed method across all compression ratios. The identification results of the modal parameters of the original response and the reconstructed response show excellent consistency in their frequencies and vibration modes. The maximum relative error of the first 12 frequencies is only 0.038%, and the modal assurance criterion of the first 12 mode shapes is at least 0.9962. Overall, in large-scale low-sparse situations, the proposed method has high accuracy and high computational efficiency in reconstructing structural vibration responses, which can greatly alleviate the transmission and storage problems of monitoring big data with very low hardware requirements. [ABSTRACT FROM AUTHOR]

• A Hierarchical Bayesian formulation is proposed for updating structural models. • An Expectation-Maximization strategy is offered to mitigate computational costs. • Difficulties of treating close modes are resolved using a geometric approach. • Applications to an offshore platform are provided to verify the proposed method. Updating Finite Element (FE) models based on modal data has become a standard tool for condition monitoring and damage detection in structures. The basis of this approach is to minimize the discrepancy between the experimental and analytical modal frequencies and shapes through a particular loss function derived through deterministic or probabilistic methods. However, the weighting of modal features can affect the identified structural model parameters, which requires proper treatment. This paper revisits this problem by proposing a novel hierarchical Bayesian formulation, wherein the covariance matrix of modal residuals is identified from the data, leading to automated weighting of the modal residuals. As the calculation of the posterior distribution encounters computational overheads, an efficient Expectation-Maximization algorithm is proposed to approximate the optimal values of the parameters. Bayesian information criterion is employed to select the most plausible layout for the prediction errors covariance matrix. A new strategy is also established for handling dynamical modes with close modal frequencies. Finally, the proposed approaches are examined using simulated and real data from FINO3 offshore platform. As a result, reasonable estimations with desirable uncertainty bounds are acquired. Although the weighting of modal features varies on a case-to-case basis, it is observed that the proposed method might lead to non-trivial and interesting weighting factors according to the data-driven uncertainty of modal residuals. [ABSTRACT FROM AUTHOR]

• A hybrid approach based on modulation transfer and vibroacoustic modulation is used for damage detection and localisation. • The damage indicators are calculated from frequency components obtained by the proposed algorithm. • The experiment is conducted on both the damaged and undamaged beams. • The complementarity of methods based on modulation transfer and vibroacoustic modulation phenomena. • Manifestation of various non-linear mechanisms responsible for modulation transfer and vibroacoustic modulation. This paper describes a hybrid approach to fault detection by using modulation transfer and vibroacoustic modulation. The work aims to locate faults and study the components of the response signals. This research is relevant for two reasons. The first is the small amount of research concerning hybrid modulation methods in fault localisation. The second is related to the insufficient knowledge of the response signals composition, which is crucial for fault detection procedures. Thus, the tests were carried out on two beams made of aluminium, one damaged and the other undamaged. The tested structures were excited by two sources. The first was a piezo stack actuator that introduced an amplitude-modulated wave with a modal frequency carrier. The second source was a piezoelectric exciter that introduced a harmonic ultrasonic wave. The tests were performed for several amplitude levels applied to the piezo stack actuator. The recorded responses were processed to calculate frequency spectra and prepare damage index trend charts. The spectrum analysis revealed the presence of components related to the modulation transfer and vibroacoustic modulation phenomenon. The trend analysis indicated that modulation transfer can be applied for damage localisation and complement vibroacoustic modulation techniques. [ABSTRACT FROM AUTHOR]

Structural identification is an essential process in structural health monitoring, condition assessment and structural safety evaluation. This inverse problem becomes more challenging when information on the dynamic loads is missing or not fully known. Hence, it is important to establish methods to identify structural parameters and dynamic loads simultaneously from the measured structural responses which are easy to obtain compared to dynamic loads. This paper proposes a novel method to identify simultaneously structural parameters and dynamic loads from structural responses measured on a limited set of degrees-of-freedom. Firstly, an objective function is defined as the difference between the measured structural responses and the theoretically computed responses, and then the derivative of the residual function with respect to structural parameters is calculated numerically using the forward-difference method. The derivative of the residual function with respect to the external dynamic loads is computed using the state-space formulation and the system matrix composed of Markov parameters to facilitate the derivative-based identification. Secondly, the nonlinear optimization problem is solved using the Levenberg–Marquardt algorithm. Several numerical examples are analysed to demonstrate the effectiveness and robustness of the method. Finally, the effect of initial estimates of the parameters and dynamic loads and the effect of measurement noise, as well as the effects of number of measurements are investigated. The proposed method is also shown to achieve a satisfactory solution even when the initial estimates of parameters and dynamic loads are far from their true values. • The structural parameters and the dynamic loads are identified simultaneously. • A state-space formulation is used to facilitate the identification. • The Levenberg–Marquardt algorithm is used to solve the optimization problem. • The effects of noise, number of measurements and excitations are analysed. [ABSTRACT FROM AUTHOR]

In this paper, the problem of bridge health monitoring is formulated as an unsupervised semantic segmentation where the aim is to identify the onset of structural damage by detecting unexpected irregularities in the time series data. In particular, the main objective of this study is to approach this problem through an indirect sensing framework based on the concept of vehicle-mounted scanning. Thus, the sole source of information is the acceleration responses of the moving vehicle passing over the bridge. This is achieved through automatic feature learning by adopting the concept of matrix profile to conduct an all-pair-similarity search for a given time series, where the location of the contextual change is determined by the corresponding Corrected Arc Crossings (CAC) profile. The performance of the method is first evaluated through numerical investigations for different damage cases where the effect of operational uncertainties such as road roughness, and variability in vehicle properties are considered. Further, the method is experimentally evaluated using a lab-scale bridge model with different damage cases. Through these investigations, it is consistently observed that the location of the change point always coincides with the minimum point of the CAC profile. The proposed framework has three major advantages making it more appealing compared to the competing techniques. First, it has been fully formulated in the context of unsupervised learning where no access to labeled data is required. Second, it is capable of working with a limited amount of data yet providing promising results. Finally, it can be easily applied to online settings where data is streaming in real-time. These successful results demonstrate the potential of the proposed method as a cost-effective and rigorous bridge inspection tool and open up opportunities in the field of indirect bridge health monitoring. [ABSTRACT FROM AUTHOR]

Data-driven machine-learning algorithms generally suffer from a lack of labelled health-state data, mainly those referring to damage conditions. To address such an issue, population-based structural health monitoring seeks to enrich the original dataset by transferring knowledge from a population of monitored structures. Within this context, this paper presents a transfer learning approach, based on domain adaptation, to leverage information from completely-labelled bridge structure data to accurately predict new instances of an unknown target domain. Since intrinsic structural differences may cause distribution shifts, domain adaptation attempts to minimise the distance between the domains and to learn a mapping within a shared feature space. Specifically, the methodology involves the long-term acquisition of natural frequencies from several structural scenarios. Such damage-sensitive features are then aligned via domain adaptation so that a machine-learning algorithm can effectively utilise the labelled source domain data and generalise well to the unlabelled target-domain data. The described procedure is applied to two case studies, including the Z24 and the S101 benchmark bridges and their finite element models, respectively. The results demonstrate the successful exchange of health-state labels to identify the damage class within a population of bridges equipped with SHM systems, showing potential to reduce computational efforts and to deal with scarce or poor data sets in application to bridge network monitoring. • A data-based domain adaptation framework is applied to bridge monitoring. • Domain Adaptation aligns and transform damage-sensitive features into a shared feature space. • Joint Domain Adaptation and Normal Condition Alignment are compared and discussed. • The KNN algorithm uses the transformed features to perform damage detection and classification. • The method is applied to transfer health-state labels across real bridges and finite element models. [ABSTRACT FROM AUTHOR]

Accurate damage quantification for an individual aircraft by using structural health monitoring (SHM) technology poses a persistent challenge in practical engineering. Existing damage quantification models typically rely on prior data acquired from ground design and tests. However, an individual aircraft is subject to diverse uncertainties throughout its whole service time, such as time-varying environmental and operational conditions, different flight missions, and different damage morphologies. Consequently, employing a prior trained model for damage quantification inevitably introduces errors, thereby limiting the engineering applicability of SHM. To improve the damage quantification accuracy for individual aircraft under the influence of uncertainty, a new whole lifetime data-based damage quantification model hierarchical evolution mechanism is proposed in this paper. Multi-source data from the design, service, and maintenance stages of individual aircraft are adopted to continuously evolve the probabilistic damage diagnosis model, enabling it to characterize the specific data distribution and track the damage propagation. The proposed method is validated through fatigue tests of a landing gear beam structure, which is an important aircraft load-carrying component, with guided wave monitoring based hidden Markov model quantifying its crack propagation. The validation result demonstrates the effectiveness of the proposed method in ensuring the long-term reliability of the model and achieving more accurate damage quantification for an individual aircraft. [ABSTRACT FROM AUTHOR]

Nonlinearity and high dimensionality emerge as two primary challenges in the realm of system identification within the context of structural health monitoring (SHM) applications. Particle filter (PF) has been demonstrated efficient for nonlinear identification, but it suffers from the curse of dimensionality and behaves poorly in high-dimensional problems. The idea of state and measurement partitioning has been used in many PF algorithms to simplify high-dimensional identification problems into the identification of several lower-dimensional subgroups, but with very few applications to SHM problems. In this context, by combining multiple particle filters (MPF) with the decay of correlations property, this paper develops a novel multiple local particle filter (MLPF) for high-dimensional identification problems. A whole state vector is partitioned into several state subgroups, each consisting of fewer state components and then estimated by one PF through a novel likelihood including the local state and measurement vectors. The feasibility and efficiency of the proposed method are tested through a benchmark toy example, a case study of a twenty-story Bouc-Wen frame structure under ground motion, and an experimental study of fatigue delamination growth in composites. [ABSTRACT FROM AUTHOR]

Structural health monitoring (SHM) strategies seek to evaluate, predict, and maintain structural integrity, to improve the safety and design service life of structures in operation. Many of these strategies involve monitoring changes in structural dynamics, as damage can affect modal properties and present as changes in the characteristics of the resonance peaks of the frequency response function (FRF). While recent advances have improved the safety and reliability of structures, a number of challenges remain, impeding the practical implementation and generalisation of these systems. Like damage, benign variations, such as those caused by changes in temperature or other environmental fluctuations, can affect dynamic properties, making it difficult to distinguish between damage and normal operating conditions. In addition, newly-deployed structures can have insufficient data to describe the normal operating conditions (i.e., data scarcity), which can impair the development of data-based prediction models. Another common challenge is data loss (i.e., data sparsity), which may result from transmission issues, sensor failure, a sample-rate mismatch between sensors, and other causes. Missing data in the time domain will result in decreased resolution in the frequency domain, which can impair dynamic characterisation. For situations that may benefit from information sharing among datasets, e.g., population-based SHM of similar structures, the hierarchical Bayesian approach provides a useful modelling structure. Hierarchical Bayesian models learn statistical distributions at the population (or parent) and the domain levels simultaneously, to bolster statistical strength among the parameters. As a result, variance is reduced among the parameter estimates, particularly when data are limited. In this paper, a combined probabilistic FRF model is developed for a small population of nominally-identical helicopter blades, using a hierarchical Bayesian structure, to support information transfer in the context of sparse data. The modelling approach is also demonstrated in a traditional SHM context, for a single helicopter blade exposed to varying temperatures, to show how the inclusion of physics-based knowledge can improve generalisation beyond the training data, in the context of scarce data. These models address critical challenges in SHM, by accommodating benign variations that present as differences in the underlying dynamics, while also considering (and utilising), the similarities among the domains. [ABSTRACT FROM AUTHOR]

High-speed trains inevitably experience the impact of complex temperature loads during operation, which can easily result in cracks. Structural health monitoring methods based on Lamb waves are affected by the impact of temperature on their propagation mechanism, leading to difficulties in constructing accurate damage diagnostic models. This paper proposes a crack damage identification method based on adaptive multi-scale sample entropy under variable temperature environment. A sliding window method is proposed to obtain multiple wave packets in a Lamb wave, which avoids the disadvantage of insufficient information of a single wave packet and improves the robustness and reliability of diagnosis. A variance-based multiscale transform method is proposed to process Lamb wave signals, which reduces the sensitivity of Lamb wave signals to temperature compared to the traditional mean-based multiscale transform method. Lamb waves in different sliding windows are transformed at multiple scales to extract damage Multi-scale sample entropy (MSE) at different scales. The Quantum genetic algorithm (QGA) is introduced to optimize sliding windows and MSE, achieving adaptive MSE extraction under variable temperature environments. Based on the advantage of adaptive multiscale entropy, a quantitative crack diagnosis model is established. To verify the effectiveness of the proposed method, crack detection experiments under variable temperatures were conducted. The results show that the proposed adaptive MSE has good resistance to temperature changes and can accurately identify crack length. [ABSTRACT FROM AUTHOR]

The current image processing techniques heavily rely on classic windows for suppressing spectral leakage. However, the limited capability of these classic windows to suppress spectral leakage restricts their application in the field of high-precision measurement. This paper proposes a novel family of windows capable of suppressing spectral leakage associated with the Moiré fringes pattern, thereby enhancing the accuracy of lithography alignment. Specifically, a novel two-dimensional Hanning self-convolution window is introduced, which is derived from the Hanning window to inherit its advantage of ultra-rapid sidelobe decay. The behaviors of the main lobe and desirable sidelobes of the 1st- to 4th-order are examined. Additionally, a novel fringe phase extraction algorithm is established based on the proposed window, which demonstrates high accuracy and efficiency. Simulation and experimental results validate the feasibility and practicality of the proposed window. In particular, the proposed window outperforms classic windows in suppressing spectral leakage, thereby successfully enhancing the phase extraction accuracy to achieve high-precision misalignment measurement at the sub-2-nm level (1.47 nm @ 3σ criterion). The proposed method can be easily extended to other real engineering applications utilizing fringe to achieve high-precision measurements, such as fringe projection profilometry, damage detection, and visual mechanical vibration monitoring. [ABSTRACT FROM AUTHOR]

Structural health monitoring (SHM) systems have been increasingly employed to continually assess the current state of bridges. However, the vast amounts of sensor data generated by SHM systems, along with constantly changing environmental and operational conditions, make structural damage assessment a computationally demanding and challenging task. Traditional data-driven approaches primarily utilise machine learning methods for pattern recognition and feature extraction to address this issue. This paper introduces a methodology for assessing bridge conditions using a probabilistic temporal autoencoder (PTAE). The proposed approach effectively extracts features and captures temporal relationships in multi-sensor data collected only during train crossings. By calculating the reconstruction loss and KL divergence-based of damage features, the methodology enables the identification of potential damage of a monitored bridge. An Exponentially Weighted Moving Average (EWMA) filter and a control chart-based threshold mechanism are applied to further refine the damage assessment process, facilitating the distinction between healthy and progressively deteriorating damage cases. The proposed method is adaptable to various monitoring scenarios and sensor configurations, and robust to varying operational and environmental conditions. The effectiveness of the methodology is assessed using numerically generated data and validated with real-world data from the KW51 bridge. The results demonstrate that the proposed method can detect damage with a limited number of sensors, making it a valuable approach to enhance bridge safety. • PTAE-based method processes multi-sensor SHM data for accurate damage assessment under varying conditions. • Reconstruction loss and KL divergence-based features enable potential bridge damage detection during train crossings. • EWMA filter and control chart threshold refines assessment, differentiating healthy and deteriorating cases. • Adaptable, robust methodology suits various monitoring scenarios and sensor configurations, enhancing bridge safety. • The method's effectiveness is validated through numerical and real-world KW51 bridge data, highlighting its practical applicability. [ABSTRACT FROM AUTHOR]

The occurrence of manufacturing defects in wind turbine blade (WTB) production can result in significant increases in operation and maintenance costs of WTBs, reduce capacity factors of wind farms, and occasionally lead to severe and disastrous consequences. Therefore, inspection during the manufacturing process is crucial to ensure consistent fabrication of composite materials. Non-contact sensing techniques, such as Frequency Modulated Continuous Wave (FMCW) radar, are becoming increasingly popular as they offer a full view – cross sectional analysis – of these complex structures during assembly and curing. In this paper, we enhance the quality assurance of WTB manufacturing utilising FMCW radar as a non-destructive sensing modality. Additionally, a novel anomaly detection pipeline is developed that offers the following advantages: (1) We use the analytic representation of the Intermediate Frequency signal of the FMCW radar as a feature to disentangle material-specific and round-trip delay information from the received wave. (2) We propose a novel anomaly detection methodology called focus Support Vector Data Description (focus-SVDD). This methodology involves defining the limit boundaries of the dataset after removing healthy data features, thereby focusing on the attributes of anomalies. (3) The proposed method employs a complex-valued autoencoder to remove healthy features and we introduces a new activation function called Exponential Amplitude Decay (EAD). EAD takes advantage of the Rayleigh distribution, which characterises an instantaneous amplitude signal. The effectiveness of the proposed method is demonstrated through its application to collected data, where it shows superior performance compared to other state-of-the-art unsupervised anomaly detection methods. This method is expected to make a significant contribution not only to structural health monitoring but also to the field of deep complex-valued data processing and SVDD application. The code and dataset will be made publicly available. The code and dataset are available here 1 1 https://github.com/FrusqueGaetan/Focus_SVDD_EAD. [ABSTRACT FROM AUTHOR]

Structural Damage Identification (SDI) is a crucial branch in the field of structural health monitoring, providing an essential support for the safe operation of structures. In this paper, a novel structural damage identification method based on a surrogate-assisted evolutionary optimization algorithm is proposed. This method incorporates cost-effective surrogate modelling techniques and swarm intelligence optimization algorithms with powerful global optimization capabilities. Three popular surrogate models are fused based on a weighted average strategy to construct an integrated surrogate model with stronger generalization ability and higher accuracy. In addition, the self-designed movement strategy is more suitable for the characteristics of Termite Life Cycle Optimizer (TLCO), allowing the improved TLCO to have stronger robustness and the capability to escape from local optimum. The effectiveness of the proposed method for solving the SDI problem is confirmed in a damaged dam model with different complexities. Some important findings are as follows: (i) Compared with the conventional SDI methods, which directly combines optimization algorithms and finite element models, the proposed method maintains reliable accuracy, while improving computational efficiency by a factor of more than 100. (ii) There is no direct relationship between the accuracy of the surrogate models and the effectiveness of the SDI method based on their combination with ITLCO. The proposed method can serve as a promising tool for damage identification in large-scale structures. [ABSTRACT FROM AUTHOR]

Accurate condition monitoring has been a major challenge among railroad management authorities as they work to minimize collisions that lead to fatalities or damage to railroads infrastructure. Hence, research and technological developments in railroad maintenance and inspection are vital. Several research studies, on the inspection and defect detection techniques for railroads have been conducted by scholars. Despite the significant advancements made in this area, extensive studies are still required to enhance the accuracy of prognostic methods for railroad structural health monitoring (SHM) and condition monitoring (CM). Distributed acoustic sensing (DAS) has been recognized as a promising measurement method because of its quick sensing capabilities over long distances and for massive structures. DAS systems are classified according to the optical sensing quality and sensing range. As DAS produces large noisy datasets, in the case of railroad applications, algorithms for precise real-time and reliable analysis are essential. Meanwhile, data-driven and machine learning (ML) methods for defect detection have emerged as valuable approaches for SHM. Engineers and stakeholders can use ML algorithms to examine the large volumes of data produced by SHM systems to identify patterns and behaviors that might not appear in manual inspections. To support more precise and accurate maintenance and inspection for railroad systems, methodologies used to detect, identify, and characterize abnormal conditions in railroads using DAS and signal processing approaches for DAS large size and noisy signals, must be reviewed. Accordingly, in this literature survey, the applications of DAS methods for railroad CM are investigated. Among the variety of DAS methods, optical time domain reflectometry (OTDR) is reviewed in more details, since it is the most common approach in distributed fiber optic sensing. In addition, different OTDR-based DAS research for train tracking and railroad SHM are reviewed, and a comprehensive summary of different railroad defects is provided for further investigation. In all, this review paper provides a comprehensive background on distributed fiber optic sensing, the importance and challenges in railroad continuous CM, and the state-of-the-art application and future roadmap for the application of DAS in the railroad industry. [ABSTRACT FROM AUTHOR]

It has been demonstrated that acoustic-emission (AE), inspection of structures can offer advantages over other types of monitoring techniques in the detection of damage; namely, an increased sensitivity to damage, as well as an ability to localise its source. There are, however, numerous challenges associated with the analysis of AE data. One issue is the high sampling frequencies required to capture AE activity. In just a few seconds, a recording can generate very high volumes of data, of which a significant portion may be of little interest for analysis. Identifying the individual AE events in a recorded time-series is therefore a necessary procedure for reducing the size of the dataset and projecting out the influence of background noise from the signal. In this paper, a state-of-the-art technique is presented that can automatically identify cluster the AE events from a probabilistic perspective. A nonparametric Bayesian approach, based on the Dirichlet process (DP), is employed to overcome some of the challenges associated with this task. Additionally, the developed model is applied for damage detection using AE data collected from an experimental setup. Two main sets of AE data are considered in this work: (1) from a journal bearing in operation, and (2) from an Airbus A320 main landing gear subjected to fatigue testing. [ABSTRACT FROM AUTHOR]

Effective bridge structural health monitoring systems offer a route to assist in the safe and economic operation of bridges, but have seen limited adoption onto the short and medium-span bridges which represent the majority of our bridge stock. This lack of adoption is in part due to the practical challenges of deploying bridge SHM systems in resource-constrained environments, especially where long-term monitoring at transport network-scales is considered. This paper tackles the problem of implementing an effective sampling method to facilitate long-term, bridge rotation-based damage detection, particularly within the confines of a resource-constrained setting. We demonstrate that leveraging readily available expected traffic-volume information enables the creation of more effective bridge SHM sampling methods by capturing more vehicle crossings in the same time. Furthermore, we introduce an empirically tuned, temperature-capable bridge finite-element model for long-term simulations, incorporating a stochastic vehicle arrival model and a feature error model to allow for the presence of any residual noise/dynamics due to imperfect filtering or inaccuracies in the feature extraction stages. This allowed us to simulate 60 years worth of bridge rotation monitoring data with varying damage severities to evaluate the impact of environmental and operational variations on our proposed expected traffic volume based sampling methods. Our results show that sampling only the peak traffic hours was the most effective for the same reduced 'on' time, i.e. for an 8x reduction in 'on' time only a 1.5x increase in the minimum detectable damage was observed versus a 2x increase for naive random sampling. [ABSTRACT FROM AUTHOR]

In recent years, there has been a growing interest in the development of ground-based Synthetic Aperture Radars (GBSAR) for the purpose of monitoring structural displacements. GBSAR offers high-resolution monitoring over a wide area and can capture data every few minutes. However, compact high-frequency multiple input multiple output (MIMO) radars have emerged as an alternative for monitoring sub-second displacements, such as structural vibrations. MIMO radar has sub-second acquisition interval. However, it has limited cross-range resolution compared to GBSAR, and interference between antennas and presence of multiple scatterers in the scene can cause strong sidelobes in the processed data. On the other hand, GBSAR utilizes a long synthetic aperture to achieve high cross-range resolution. However, due to its longer data acquisition time compared to MIMO radar, conventional methods are insufficient for detecting scatterers' sub-second displacements that occur during the data acquisition process. This study proposes a method to effectively monitor sub-second or sub-minute displacements using GBSAR signals. The proposed method enhances the conventional radar interferometric processes by employing spectral estimation, allowing for multi-dimensional detection of targets' azimuth angle, linear displacement, and vibrational characteristics. Consequently, this method improves both the processing of MIMO radar data and enables high-resolution fast displacement monitoring from GBSAR signals. The paper presents the theoretical details and mathematical formulations of the proposed method for both MIMO radar and GBSAR imaging modes. To evaluate the effectiveness of the proposed method, numerical simulations and real experiments are conducted. The experimental results validate the capability of the proposed method in both GBSAR and MIMO configuration modes for high-resolution monitoring of fast linear displacements and vibrations. The results exhibit promising signal-to-noise ratio (SNR) and peak-to-sidelobe ratio (PSLR) values. [ABSTRACT FROM AUTHOR]

• Proposing a novel double-hybrid learning method for damage assessment under different environmental variation patterns. • Leveraging a self-adaptive neighbor searching algorithm for automatically determining the number of nearest neighbors. • Improving a hybrid clustering algorithm with a simple but effective approach to selecting the number of clusters. • Proposing a non-parametric hybrid anomaly detector based on local outlier factor. Monitoring of modal frequencies under an unsupervised learning framework is a practical strategy for damage assessment of civil structures, especially bridges. However, the key challenge is related to high sensitivity of modal frequencies to environmental and/or operational changes that may lead to economic and safety losses. The other challenge pertains to different environmental and/or operational variation patterns in modal frequencies due to differences in structural types, materials, and applications, measurement periods in terms of short and/or long monitoring programs, geographical locations of structures, weather conditions, and influences of single or multiple environmental and/or operational factors, which may cause barriers to employing state-of-the-art unsupervised learning approaches. To cope with these issues, this paper proposes a novel double-hybrid learning technique in an unsupervised manner. It contains two stages of data partitioning and anomaly detection, both of which comprise two hybrid algorithms. For the first stage, an improved hybrid clustering method based on a coupling of shared nearest neighbor searching and density peaks clustering is proposed to prepare local information for anomaly detection with the focus on mitigating environmental and/or operational effects. For the second stage, this paper proposes an innovative non-parametric hybrid anomaly detector based on local outlier factor. In both stages, the number of nearest neighbors is the key hyperparameter that is automatically determined by leveraging a self-adaptive neighbor searching algorithm. Modal frequencies of two full-scale bridges are utilized to validate the proposed technique with several comparisons. Results indicate that this technique is able to successfully eliminate different environmental and/or operational variations and correctly detect damage. [ABSTRACT FROM AUTHOR]

Visual displacement measurement methods for flexible structural bodies like large-span bridges has gained wide popularity in recent years, but practical applications still have some limitations. For instance, when acquiring images of large-span flexible bridges at a distance, the slight angular tilt of the detection target due to irregular vibrations can cause extremely serious misfit errors in the displacement curves returned by the vision measurement algorithm. To improve the reliability of vibration displacement measurement of flexible structural bodies, this paper takes the bridge subjected to external excitation in the acquired image sequence as the object of vibration displacement measurement and uses a designed high-precision displacement measurement algorithm for a single-stage rotating target tracking anchor-free box to track the vibration displacement of the target in the flexible structural body. We first extract multi-scale feature information of bridge model image sequences using the improved YOLOv5-s backbone network and combine the Transformer self-attention mechanism with PANet to perform a top-down and bottom-up bi-directional fusion of target feature maps at three different scales to achieve semantic feature fusion of shallow and deep information. Second, the improved Efficient Decoupled Head performs the detection of rotating target centroid offset and bounding box size. Finally, the detected results are passed into the multi-objective tracking algorithm ByteTrack, which strengthens the spatio-temporal correlation between frames and obtains a better-fitting vibration displacement curve. The validation and comparison of traditional visual measurement methods and deep learning measurement methods on cable-stayed bridge models, small arch bridges, and large span bridges show that the vibration displacement trajectories regressed by the algorithm in this paper have the best fit with the actual vibration displacement trajectories, which also verifies that the algorithm in this paper has good potential for engineering applications and implementation space in the field of condition monitoring of flexible structural bodies. [Display omitted] • Introducing anchor-free box and efficient decoupling head to achieve high accuracy detection. • The proposed RIoU loss function is used for the accurate positioning of rotating boxes. • Introducing Transformer module to improve the characterization ability of the network. • Combine the target tracking algorithm to enhance the inter-frame correlation. • Experiments verify the accuracy and robustness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The use of Machine Learning (ML) has rapidly spread across several fields of applied sciences, having encountered many applications in Structural Dynamics and Vibroacoustic (SD&V). An advantage of ML algorithms compared to traditional techniques is that physical phenomena can be modeled using only sampled data from either measurements or simulations. This is particularly important in SD&V when the model of the studied phenomenon is either unknown or computationally expensive to simulate. This paper presents a survey on the application of ML algorithms in three classical problems of SD&V: structural health monitoring, active control of noise and vibration, and vibroacoustic product design. In structural health monitoring, ML is employed to extract damage-sensitive features from sampled data and to detect, localize, assess, and forecast failures in the structure. In active control of noise and vibration, ML techniques are used in the identification of state-space models of the controlled system, dimensionality reduction of existing models, and design of controllers. In vibroacoustic product design, ML algorithms can create surrogates that are faster to evaluate than physics-based models. The methodologies considered in this work are analyzed in terms of their strength and limitations for each of the three considered SD&V problems. Moreover, the paper considers the role of digital twins and physics-guided ML to overcome current challenges and lay the foundations for future research in the field. • Review of machine learning applied in vibroacoustic and structural dynamics. • Basic principles of the machine learning methods commonly used are presented. • Control, structural health monitoring and design are the most relevant applications. • The current implementation scenario and challenges are reviewed for each application. • This article sheds light on trends and research opportunities merging both fields. [ABSTRACT FROM AUTHOR]

This paper concerns the use of ultrasonic guided waves (UGW) in predictive maintenance (PM). Generally, PM is based on machine or process parameters such as current, voltage, temperature and pressure. However, research studies on the use of structural health monitoring (SHM) techniques in PM are seldom (to the best knowledge of the authors). Hence, the main purpose of the present study is to investigate the feasibility of using UGW, in order to reinforce the PM of a given installation. An approach that combines diagnostic and prognostic models is developed. The predictive model is hybrid and based on Empirical Mode Decomposition (EMD) and Autoregressive Integrated Moving Average (ARIMA). The built model is applied on data collected from two kinds of structures, namely flexible and rigid risers. Residual useful life (RUL) of each structure is estimated and compared with its simulated actual value. The paper provides a fruitful discussion about the applicability of UGW for prognostic as this is an important step in SHM and there is still a lack of research related to this topic. [ABSTRACT FROM AUTHOR]

This paper proposes an approach for anomaly/damage detection via structural health monitoring (SHM) systems based on a Binomial Distribution Classifier (BDC). The approach consists of two monitoring levels, labeled as alert and alarm states, respectively, where a damage index (DI) is computed and tracked over time. The alert state is reached when the DI exceeds a given threshold. At this stage, the BDC algorithm starts counting the number of DI values above the threshold within an observation window and computing the related probability of occurrence by using the binomial probability distribution. If the probability falls below a desired limit, the alarm state is triggered. Conversely, the SHM system returns in the non-alert condition. The proposed approach is discussed and evaluated through case studies involving both simulated and experimental data. In the examples, the DI is computed using the Mahalanobis distance of the monitored modal frequencies. The results demonstrate the capability of the BDC to reduce false alarms while preserving the probability of detection. [ABSTRACT FROM AUTHOR]

Concerning the cost- and resource-saving maintenance of assembly products, it is vital to detect any potential malfunctions, defects or structural damage at the earliest-possible stage. For this reason, considerable efforts are being put into the development of Structural Health Monitoring, a field encompassing different approaches to damage identification and capable of preventing defects and even failure. Structural Health Monitoring is often supported by machine learning, a tool for rapid and effective damage identification that can recognize patterns or changes in the data received from the structure. Despite the advances machine learning has made in recent years, obtaining a suitable data set for the efficient training of machine learning algorithms within Structural Health Monitoring remains a challenge. Currently, the data are usually obtained experimentally, with numerical or analytical models. However, the experimental approach can often be time consuming, while the reliability of numerically obtained data relies heavily on the accuracy of the numerical models in capturing the true behavior of the structure. Analytical models may be constrained by the complexity of the observed object. In this paper an alternative approach based on an experimental–numerical (i.e., hybrid) modeling approach is proposed to build a training set for Structural Health Monitoring. Frequency Based Substructuring is utilized to determine the response model of the assembled system based on the properties of its components as well as to mix experimental and numerical models, while leveraging the advantages of each. This makes it possible to generate the samples of the training set in the form of hybrid models of the structure of interest, exhibiting the realistic properties of a physical structure, with a reasonable measurement effort. Here, the approach is demonstrated for the process of joint-damage identification. [Display omitted] • An approach to machine learning training set generation is proposed. • The proposed approach focuses on joint-damage identification. • Analytical, numerical and experimental data are used to obtain training data. • Dynamic substructuring is utilized to obtain training samples. • The proposed approach is tested in a case-study on a laboratory structure. [ABSTRACT FROM AUTHOR]

• A unified method for solving Bayesian model updating and model class selection. • New formulations for Bayesian model class selection with data fit and information gain. • Theoretical basis for developing the adaptive sampling scheme. • The method is shown to be potential for practical inverse problems by a full-scale structure. For complex engineering structures, it is important to systematically select a model class among various choices and search the complicated parameter space, while also quantifying uncertainties. This paper develops an enhanced adaptive sequential Monte Carlo (ASMC) method to solve Bayesian model updating and model class selection in a unified manner. Main contributions are: (1) Analysis of the sequential sampling process reveals difficulties of sampling from complex probability density functions (PDFs), which naturally leads to the PDF approximation using incremental weights of samples, and then the adaptive sampling scheme with this approximation. (2) Following ASMC framework, new formulations are derived to calculate model class evidence; these formulations enable the separate quantification of data fit and information gain of a model class. A simulated and a full-scale structure were used to demonstrate the proposed method. This work lays good foundation for downstream research such as automation in construction and structural health monitoring. [ABSTRACT FROM AUTHOR]

The sections of pipe bends are susceptible to wall thinning by flow-accelerated corrosion due to the sudden change in the fluid flow direction and velocity. Compared to existing screening approaches, Guided Wave Tomography (GWT) has been demonstrated to provide more accurate information about the defect. In GWT an inversion problem is solved, in which a forward model is used to predict a synthetic dataset for a given physical model. Two-dimensional (2D) forward models are preferred for the inversion scheme due to the feasibility of combining these with tomographic algorithms. Since 2D models resemble the GW propagation of a plate, they do not consider the cyclic nature of the pipe. To overcome this limitation, a robust helical path separation was introduced in Huthwaite and Seher (2015) for a straight pipe. However, it relies on time-reversing the measured wave field ϕ (t) as a function of the propagation distance x s , r from the source to the receiver. Although ray-tracing and grid-based methods are capable of computing the distance x s , r for complex geometries such as the pipe bend, they are complex and time-consuming. Hence, in this paper a straight forward approach is proposed to compute x s , r based on the pipe geometry and the geodesic equations of a torus. Then the computed distance x s , r is used for removing the helical path trajectories. Compared to the distance obtained by using the Hilbert envelope, the results show that the geodesic distances preserve the information of the wavefront of interest, including the focusing effect and the scattered wave field from a Hann-shaped defect. The technique is applied to experimental data and demonstrated to separate the wavefront of interest. [ABSTRACT FROM AUTHOR]

In order for a practical application of structural health monitoring to be considered successful, not only is the detection of anomalies important but so is the tracking of various other behaviors, which may be induced by changing operational conditions or environmental variations. Rather than being problems of anomaly detection, these are known as problems of changing contexts or changing semantics. In this paper, we propose a novel, and efficient method which is able to perform both tasks: anomaly detection, and semantic analysis, simultaneously, and which is also able to scale to a multi-sensor network array. The proposed methodology works to combine a recent development from the field of time series data mining known as matrix profiling, as well as ideas from a popular area of mathematics known as optimal transport theory. In particular, matrix profiles will be used to generate curves of semantic segmentation, over multivariate time series data. From here, it will be demonstrated that by finding the unbalanced optimal transport barycenter one can successfully pool together information from a sensor array network in such a way that the presence of false positive transition points is reduced significantly when compared to the baseline mean. Moreover, this will be demonstrated to occur in a hierarchical fashion by employing a variational mode decomposition across each sensor in the network array. Overall, the proposed methodology: (i) Can work in the small data context without requiring a large amount of data for model training and validation, (ii) Applies readily to unsupervised and semi-supervised learning settings, (iii) Can extend to the online learning setting, (iv) Is adaptable and robust for sensor array network problems, (v) Does not require specifying any threshold, and (vi) Is highly interpretable. Finally, the proposed methodology will be validated on three different levels of investigation: (i) A numerical dataset of an aerospace model based on a two-dimensional plate model, (ii) An experimental dataset of a building from Los Alamos National Laboratories, and finally, (iii) A field investigation on a cable-stayed bridge located in Sydney, Australia. [ABSTRACT FROM AUTHOR]

The number of bridges worldwide is extensive, making it financially and technically challenging for the authorities to install a structural health monitoring (SHM) system and collect large quantities of data for every bridge. Transfer learning has gained relevance in the last few years to extend the SHM concept for most bridges, while minimizing costs with monitoring systems and time with data measurement. It can be especially suitable for bridges structurally similar and replicated extensively, like overpasses integrated into highways. Therefore, this paper intends to lay down the foundations of transfer learning for SHM of bridges and to highlight the importance of the quality of knowledge transferred across different bridges for damage detection. Transfer Component Analysis, Joint Distribution Adaptation, and Maximum Independence Domain Adaptation methods are applied to data sets from different bridges, where classifiers have access to labeled training data from one bridge (source domain) and unlabeled monitoring test data from another bridge (target domain) that present similarities. The effectiveness of those methods is compared through the classification performance using real-world monitoring data sets collected from the Z-24 Bridge in Switzerland, and the PI-57 and PK 075+317 Bridges in France. [ABSTRACT FROM AUTHOR]

Due to the inherent uncertainty and complexity of civil infrastructure, it is challenging to simulate their structural dynamic responses accurately and efficiently. Existing model updating methods normally need distributed sensors and use modal parameters to construct objective functions, which can achieve frequency domain agreement between the numerical model and the real structure. Nevertheless, time domain alignment is still difficult to achieve, especially when the sensor number is limited. To enhance the simulation accuracy, this paper proposes a two-step model updating approach through updating in frequency and time domains sequentially. A virtual force is introduced in the second step to represent structural complexity and input error, and is derived by using three representative algorithms. The approach was verified on a scaled wind turbine model in the laboratory. Parametric studies were performed on different arrangements of sensors and virtual force. The results show that the virtual force should be placed at a sensor point and close to the acting point of external loads. The approach can achieve time domain alignment between numerical model and real structure with a normalized mean square error averaging 3.25% in the optimal setting. Based on the results, the proposed framework may find vast application in the establishment of numerical models towards structural dynamic twins. [ABSTRACT FROM AUTHOR]

Person identification is important in providing personalized services in smart buildings. Many existing studies focus on closed-world person identification, which only identifies a fixed group of people who have training data; however, they assume everyone has pre-collected data, which is not practical in real-world scenarios when newcomers are present. To overcome this drawback, open-world person identification recognizes both newcomers and registered people, which opens up new opportunities for smart building applications that involve newcomers, such as smart visitor management, customized retail, personalized health monitoring, and public emergency assistance. To achieve this, structural vibration sensing has various advantages when compared with the existing sensing modalities (e.g., cameras, wearables, and pressure sensors) because it only needs sparsely deployed sensors mounted on the floor, does not require people to carry devices, and is perceived as more privacy-friendly. However, one fundamental challenge in analyzing footstep-induced structural vibration data is its high variability due to the structural heterogeneity and the footstep variations. Therefore, it is difficult to distinguish different people given this high variability within each person, and it is more challenging to recognize a new person as that data is unobserved before. In this paper, we characterize the variability in footstep-induced structural vibration to develop an open-world person identification framework. Specifically, we address three variability challenges in developing our method. First, the high variability within each person comes from multiple sources that are entangled in the vibration signals, and thus is difficult to be decomposed and reduced. Secondly, the distribution of features extracted from the vibration signals is irregularly shaped, and therefore is difficult to model. Moreover, the identity of the next person is correlated with the previous observations, which makes the identification process more complicated. To overcome these challenges, we first characterize multiple variability sources and design a transformation function that results in signal features that are less variable within one person and more separable between different people. We then develop a modified Chinese Restaurant Process (mCRP) for nonparametric Bayesian modeling to capture the irregularly shaped feature patterns both from local and global perspectives. Finally, we design an adaptive hyperparameter α that represents the prior probability of newcomers at each observation, which keeps updating depending on the time, location, and previous predictions. We evaluate our approach through walking experiments with 20 people across 2 different structures. With only 1 pre-recorded person at each structure, our method achieves up to 92.3% average accuracy with randomly appearing newcomers. [ABSTRACT FROM AUTHOR]

Displacement is a crucial indicator reflecting the safety operational state of concrete arch dams. Consequently, the application of displacement monitoring models for arch dam structural health assessment has become widely prevalent. However, conventional singular displacement monitoring methods exhibit limited information extraction capabilities and lack precision, resulting in underexplored residual sequences from the monitoring model and unexcavated valuable information. To address this, this paper integrated cluster analysis with Long Short-Term Memory (LSTM), Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Least Squares Support Vector Machine (LSSVM), and Particle Swarm Optimization (PSO) methods to establish a combined prediction model of concrete arch dam displacement based on cluster analysis considering signal residual correction. Firstly, a model combining cluster analysis k-means++ with LSTM (k-LSTM), was proposed for displacement prediction of arch dams. Secondly, CEEMDAN was employed to adaptively decompose the residual sequences, where Pearson correlation coefficient (PCC) was introduced to filter and reconstruct intrinsic mode components. Subsequently, PSO-LSSVM was utilized to predict the reconstructed sequences and obtain residual correction values. Finally, based on the summation of residual correction values and k-LSTM model predictions, the arch dam displacement combination prediction model was constructed. Engineering case demonstrates the efficiency of this model in arch dam displacement prediction. By effectively mining and utilizing valuable information from residual sequences, this combined model exhibits superior generalization capabilities over traditional singular models, thereby providing technical support and novel research perspectives for concrete arch dam health monitoring and operational management. [ABSTRACT FROM AUTHOR]

The vibration signal analysis-based structural health monitoring (SHM) system has been widely used for bridge condition identification. With the development of artificial intelligence (AI), machine learning (ML) has made numerous breakthroughs in the detection of civil engineering structures. However, conventional data-driven ML methods heavily rely on prior knowledge for their performance. This paper proposes a deep learning (DL) model 1DCNN-BiLSTM for detecting small local structural changes of reinforced concrete (RC) beams, which applies the structure of the Inception module in GoogLeNet to one-dimensional convolution neural networks (1DCNNs) for feature extraction at different scales, and combines the advantages of bidirectional long short-term memory (BiLSTM) modules for processing long time-series data. Firstly, a three-dimensional numerical model of the RC beam was established using finite element software, and the accuracy of the numerical model was verified by comparing it with the test results. Based on the numerical model, tests on RC beams impacted by falling hammers were carried out, and the acceleration signals of the beam in different states were collected as a dataset. The proposed DL model can automatically extract the spatial and temporal domain features in the signals, accurately identify the location of small bridge local variations, the accuracy in the test set is 98.8% compared to 92.6% for a traditional ML model, and has better noise immunity performance and robustness to the missing data than the traditional ML model. Finally, the internal inference process of the model was explored and visualized, illustrating that the model has adaptive learning capabilities. [ABSTRACT FROM AUTHOR]

• A particle filter-based prognostic method combining multiple features is shown. • An online feature selection criterion is proposed based on bias estimation. • The method is tested by fatigue testing of an Aluminum lug joint with Lamb wave monitoring. • The robustness of the proposed method is tested on different specimens. Damage prognosis generally resorts to damage quantification functions and evolution models to quantify the current damage state and to predict the future states and the remaining useful life (RUL). The former typically consists of a function describing the relationship between the damage state and a statistical feature extracted from the measured signals, thus the prognostic performance will strongly depend on the selection of a proper feature. Given the best feature may vary for different specimens or even at each time instant for the same specimen during damage progression, such selection is a challenging task but has received little investigation so far. In this context, this paper proposes a particle filter-based damage prognosis framework, which involves an online feature fusion and selection scheme. A prognostic model is considered for each feature, with a multivariate process equation, formulated using both a damage degradation function and a bias parameter, and a measurement equation linking the damage state and that feature considering a data-driven model and the bias. One PF is used to estimate the damage state, its evolution parameters, and the bias for each model. Then, at each step, the feature with the smallest estimated bias is selected as the best feature providing the most likely state vectors and is used to select the most likely samples of the damage state and growth parameters for predicting the RUL and for calculating the prior at the next step. The proposed prognostic framework is demonstrated by an experimental study, where an aluminum lug structure subject to fatigue crack growth is monitored by a Lamb wave measurement system. [ABSTRACT FROM AUTHOR]

Nonlinear localization is an important component of structural nonlinear identification. Its accuracy is of great significance for damage localization, health monitoring, and performance prediction of structural systems. In this paper, a two-step localization method is proposed for the nonlinear localization of multi-degree-of-freedom (MDOF) systems with multiple local nonlinearities. The approach achieves accurate nonlinear localization in two steps. In the first step, subset nonlinearity detection is performed to initially narrow down the nonlinear localization range. This effectively reduces the dimensionality of the candidate nonlinear basis functions in the second step. In the second step, candidate nonlinear basis functions are used to further confirm the doubtful connections. The accuracy and effectiveness of the method are verified by two numerical examples of a one-dimensional chain-type structure and a two-dimensional structure. In addition, an experimental study is conducted on a floor structure with two local nonlinearities to verify the effectiveness of the proposed method. Results show that the proposed method has good accuracy in a noisy environment and it requires only the input and output data of the system under a wide-band excitation. [ABSTRACT FROM AUTHOR]

The present paper investigates damage detection in laminated composite beams under the action of a moving load. A novel approach is introduced to present damage indices by utilizing the dynamic response of the beam. The equations of motion for the beam have been derived by considering in-plane and out-of-plane deformations, rotary inertia, and shear effects. To obtain the solution, the finite element method, in conjunction with the Newmark algorithm, has been employed. Three damage indices, namely the Displacement Variation Index (DVI), Velocity Variation Index (VVI), and Acceleration Variation Index (AVI) have been introduced. These indices are utilized to detect the location of damage based on the beam's displacement, velocity, and acceleration, respectively. Furthermore, the proposed approach enables to detect single and multiple damages at different severities, locations, and boundary conditions. Likewise, it is applicable to various velocities of moving forces and can effectively operate in both normal and noisy conditions. The results of this investigation demonstrate that the proposed damage indices are able to accurately detect damage along the entire length of the beam without prior knowledge of its healthy state. It is noteworthy that the acceleration-based index, among the indices proposed in this study, exhibits the highest efficiency in determining the precise location of the damage under operational conditions. [ABSTRACT FROM AUTHOR]

One of the most prominent goals of a structural health monitoring (SHM) system is to infer the state of the structure to inform appropriate maintenance actions that affect performance and safety over the life cycle of the structure. SHM necessarily involves data acquisition at the beginning of the SHM workflow, but damage state inference may be fundamentally flawed if the sensing system itself initiates unreliable data. The operational and environmental conditions that these sensors face, in addition to normal manufacturing defects, may result in varying functionality in both space and time. Therefore, it becomes imperative to account for sensor reliability in the optimal sensor design process for the SHM system at the outset – that is, consider the possibility of sensors malfunctioning in the initial/pre-posterior design stage without the benefit of previous deployment information – such that the initial design is robust to sensor malfunction with regard to decision performance objectives. This paper details an optimal sensor design framework at the pre-posterior stage that incorporates the time-dependent reliability of the sensor network over the life cycle of the structure. The proposed framework can be used to obtain an intelligent initial design that can be updated with time, based on the principles and procedure presented here, but by considering the updated/current state of the structure. The generic framework is laid out and is finally demonstrated on a complex real-world miter-gate structure. [ABSTRACT FROM AUTHOR]