Search

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]

In recent years, researchers have extensively explored the application of drive-by inspection technology for bridge damage assessment. This approach involves using the response of a sensing vehicle to identify damage. However, many existing methods rely on data collected from both healthy and damaged bridge conditions, which may not always be available. Therefore, this study introduces a fully unsupervised computer vision-based methodology for bridge structural health monitoring (BSHM) using drive-by inspection. It analyzes the time–frequency domain of a two-axle vehicle's response by deriving a novel formulation for the contact point response from vehicle axles. The axles signals are then processed through subtraction, filtering, and decomposition using empirical Fourier decomposition with an improved segmentation approach based on the Savitzky–Golay filter (SGEFD). Relevant Intrinsic Mode Functions (IMF) are extracted as features representing damage, and the Wavelet Synchro-squeezed transform (WSST) is obtained from these features and used as input for the damage assessment algorithm. The performance of two state-of-the-art unsupervised generative machine learning methods, namely convolutional variational autoencoders (CVAE) and convolutional adversarial autoencoders (CAAE), is compared for the damage assessment task. These methods are trained solely with the residual WSST obtained from the vehicle responses when traversing a bridge in its reference state. A damage index (DI) is defined based on the measured error between the original and reconstructed images, and a damage threshold is calculated from the DI distribution of samples from the benchmark bridge state. During testing, the error between the original and reconstructed WSST is compared to the damage threshold, enabling the classification of new samples as healthy or damaged. The methodology is evaluated using both numerical and experimental vehicle–bridge interaction (VBI) models, considering various damage locations, severities, and the influence of road roughness. [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]

Developing robust bridge health monitoring (BHM) frameworks based on the vehicle-mounted sensing, or so-called indirect structural health monitoring (SHM) or Drive-by Bridge Inspection is currently a rapidly growing research area. The goal is to monitor any change in the structural integrity of a bridge using the vibration responses measured from sensors installed on a vehicle passing over the bridge. To this aim, we present a novel data-driven approach by integrating a nonlinear dimensionality-reduction technique using Uniform Manifold Approximation and Projection (UMAP) together with a non-parametric clustering technique using Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). Ultimately, through the combined use of UMAP and HDBSCAN, it is demonstrated that such methods align perfectly well with the problems and restrictions present when analyzing drive-by bridge inspection data. That is, in the drive-by bridge inspection context data sets may have low cardinality, and the individual clusters may have different sizes and densities and do not need to have a spherical shape. Furthermore, new clusters may emerge over time as new damage cases evolve. The pairing of UMAP and HDBSCAN will be shown to assist in these issues in a principled manner. For the validation, we first make use of the theoretical formulation of the vehicle-bridge interaction system and conduct a finite element simulation of this system to obtain the moving vehicle response once traveling over five different bridge states. Further, a simply supported bridge model in the laboratory is considered for the experimental validation. The structure of the bridge model is gradually changed by adding multiple stiffener plates, and by gradually increasing a concentrated mass at mid-span. The proposed method is then applied to identify changes that occur in the laboratory bridge model. The experimental results for damage characterization demonstrate that various bridge states can successfully be separated from one another. The contributions of the work are three-fold; (1) First, a novel feature extraction and classification framework based on the combined use of UMAP and HDBSCAN is developed and validated. (2) Second, this paper demonstrates one of the early successful attempts of drive-by bridge inspection for monitoring the progressive change in the structure of a bridge based on the extensive numerical and experimental investigations. (3) Finally, the research presented in this work can open up new opportunities for condition monitoring of bridge network. • A novel feature extraction and classification framework is developed and validated. • Superior performance of the method by combined use of UMAP and HDBSCAN is presented. • One of the early successful attempts of drive-by bridge inspection is demonstrated. [ABSTRACT FROM AUTHOR]

In this paper a new scheme of damage detection and localisation is presented by implementing frequency response functions (FRFs) of damaged structure only. First damage sensitive shape signals are generated by taking the second order derivatives of the operational mode shapes at each frequency coordinate and then the anti-symmetric extension of each shape signal at the beginning and at the end of the signal is created to avoid boundary distortion phenomenon. In order to highlight the damage influence on shape signals, the shape signals are normalised with respect to the maximum value to adjust the amplitude difference between shape signals at different frequencies. It is illustrated that normalisation of shape signals significantly improves the damage localisation results. After normalising the shape signals, a two-dimensional (2-D) map of all shape signals is created and then is analysed by employing 2-D discrete wavelet transform (DWT). By performing 2-D DWT, three sets of horizontal, vertical and diagonal detailed wavelet coefficients will be obtained. It is demonstrated that amongst these three sets, horizontal detail coefficients are the most sensitive ones to any perturbation in the shape signals due to damage occurrence and, thus, are utilised to localise damage in this study. [ABSTRACT FROM AUTHOR]

The development of a fully automated system identifier without the need for human intervention, is a key step for real-time vibration-based Structural Health Monitoring (SHM). In this paper a novel approach based on the Dirichlet Process Gaussian Mixture Model (DP-GMM) is developed in order to analyze the stabilization diagram. The aim is to separate the true physical modes from the mathematically spurious modes in a fully automated manner, whilst eliminating the need for any manually specified parameters or thresholds. The parametric Covariance Driven Stochastic Subspace Identification (SSI-Cov) is adopted to estimate the modal parameters, and consequently establish the initial stabilization diagram. From there, the use of a two-stage algorithm involving a DP-GMM is proposed to non-parametrically perform an automated cleaning of the stabilization diagram. The contributions of the paper are five-fold: (1) A probabilistic approach based on a DP-GMM is proposed to analyze the stabilization diagram. To the best knowledge of the authors, this study presents one of the first attempts of DP-GMM for full automation of Operational Modal Analysis (OMA). The method is validated using the field test data from a large-scale operating cable-stayed bridge, which has two closely-spaced modes around 3 Hz. Not only are these two complicated scenarios consistently identified, but the performance of the method with respect to the problem of missing modes is compared against a reference method based on the conventional multi-stage clustering technique used in OMA, wherein superior performance of the proposed method is demonstrated. (2) The method does not require specification of any threshold or parameter at any stage of the algorithm for cleaning the stabilization diagram, making the approach a potential for robust and fully automated modal identification. (3) Compared to many conventional multi-stage clustering techniques, the proposed approach is computationally efficient as intelligent updates are made to the model using multiple linear algebra properties. (4) New feature vectors are developed which are justified using a combination of mathematical rigor, visual understanding, and engineering intuition. (5) Due to the probabilistic nature of the method, the identification results are accompanied with uncertainty bounds. Several mathematical proofs are presented to explain the observed behavior of the uncertainty bounds. [ABSTRACT FROM AUTHOR]