Search

This study presents a convolutional neural network (CNN) deep learning approach for identifying damage in submerged structure-foundation systems using vibration data. Firstly, foundation damage in a lab-scale caisson-foundation system is simulated to measure time-history responses. Singular value decomposition (SVD) responses are derived from the time-history responses. Secondly, the 1-D CNN deep learning model is trained using both the time-history responses and SVD responses. Finally, the trained CNN models are implemented to evaluate the foundation damage under conditions of noise contamination and partially untrained data. The experimental results demonstrate the effectiveness of CNN models for damage identification and highlight the comparative strengths of time-history and SVD data. The CNN model trained using SVD data outperforms the other model when under noise contamination conditions, while the CNN model trained using time-history data maintains better accuracy in partially untrained data conditions. Integrating both types of data enhances the accuracy of damage classification.

This work explores the potential of self-powered MEMS devices for application in the preventive conservation of cultural heritage. The main objective is to evaluate the effectiveness of piezoelectric aluminum nitride MEMS (AlN-MEMS) for monitoring vibrations and to investigate its potential for harvesting energy from vibrations, including those induced by visitors. A preliminary laboratory comparison was conducted between AlN-MEMS and the commercial device Tromino®. The study was then extended to the Picture Gallery of Ursino Castle, where joint measurements with the two devices were carried out. The analysis focused on identifying natural frequencies and vibrational energy levels by key metrics, including spectral peaks and the Power Spectral Density (PSD). The results indicated that the response of the AlN-MEMS aligned well with the data collected by the commercial device, especially observing high vibrational energy around 100 Hz. Such results validate the potential of AlN-MEMS for effective vibration measurement and for converting kinetic energy into electrical power, thereby eliminating the need for external power sources. Additionally, the vibrational analysis highlighted specific locations, such as the measurement point Cu4, as exhibiting the highest vibrational energy levels. These points could be used for placing MEMS sensors to ensure efficient vibration monitoring and energy harvesting.

Monitoring induced vibrations caused by blasting works is becoming an increasingly common form of preventive activity conducted in open-pit mines. Measurement stations also record other events unrelated to blasting works. This article presents a comparison of the intensity of vibrations induced by blasting works in an open-pit mine and mining tremors in an underground mine. The recorded data and conducted analyses of vibration intensity and frequency structure also allowed for a comparison of the impact of vibrations on a building structure. Calculations and analyses, conducted in accordance with the procedures provided in the standard PN-B-02170:2016-12 and the rules for applying the Mining Seismic Intensity Scale MSIS-2017, demonstrated a stronger impact on the building from induced vibrations in an underground mine located 10 km away compared to vibrations induced by blasting operations conducted in an open-pit mine, which is approximately 600 m away from the building. The presented material constitutes a unique set of data that can be used to introduce any necessary corrections in the methodology of analyzing vibrations regarding their harmfulness to building structures. The velocity value of vibrations correlated with frequency alone, without taking into account the vibration duration, can lead to incorrect interpretation.

Vibration monitoring is essential for maintaining the optimal performance and reliability of industrial machinery, which experiences dynamic forces and vibrations during operation. This study delved into a comprehensive analysis of vibration monitoring in hydraulic presses, utilizing advanced measurement systems equipped with accelerometers. The proposed system included a three-axis accelerometer, data acquisition unit, and dedicated measurement software, facilitating the precise monitoring and analysis of vibrations. The influence of the sensor placement and sampling frequency on the measurement results was examined. A time and frequency analysis of the recorded measurements was performed. The results demonstrated the correlation between vibration levels and various production parameters, such as the number of parts simultaneously produced and press pressure. These findings underscore the potential for vibration measurement as a pivotal component in controlling production parameter settings.

With the rapid development of metro construction, shield machines inevitably have to traverse a variety of complex geological conditions, leading to the frequent occurrence of geological disasters, equipment failures, building vibration and other problems. Vibration, as an important feature of the shield tunneling process, has received more and more attention in recent years. This paper summarizes the relevant research progress of vibration monitoring during shield construction from 2015 to 2023. It analyzes the shield vibration generation mechanism, monitoring methods and application areas. Firstly, the shield vibration type is divided into mechanical vibration triggered by internal excitation and forced vibration triggered by external excitation, and the principles of vibration generated by shield main bearing, gearbox and disc cutter are discussed. Then, the commonly used vibration monitoring methods are outlined according to the installation location of the sensors (inside and outside of the shield). Finally, the applications of vibration signals in the diagnosis of shield faults, the identification of geologic conditions, and the evaluation of the current status of the interference with the buildings are summarized. This paper discusses the development trend of vibration monitoring during shield tunneling based on the current research situation and the current technology level, which provides valuable insights to enhance the safety and intelligence of shield construction.

Due to the capability of multiplexing thousands of sensors on a single optical cable, ultra-weak fiber Bragg grating (UWFBG) vibration sensing technology has been utilized in monitoring the vibration response of large-scale infrastructures, particularly urban railway tracks, and the volume of the collected monitoring data can be huge with the great number of sensors. Even though the train-induced vibration responses of urban railway tracks constitute the most informative and crucial component, they comprised less than 7% of the total operational period. This is mainly attributed to the temporal sparsity of commuting trains. Consequently, the majority of the stored data consisted of low-informative environmental noise and interference excitation data, leading to an inefficient structural health monitoring (SHM) system. To address this issue, this paper introduced an adaptive monitoring strategy for railway track structures, which is capable of identifying train-load patterns by leveraging deep learning techniques. Inspired by image semantic segmentation, a U-net model with one-dimensional convolution layers (U-net-1D) was developed for the pointwise classification of vibration monitoring data. The proposed model was trained and validated using a dataset obtained from an actual urban railway track in China. Results indicated that the proposed method outperforms the traditional dual-threshold method, achieving an Intersection over Union (IoU) of 94.27% on the segmentation task of the test dataset.

Experimental monitoring of blade vibration in turbomachinery is typically based on blade-mounted strain gauges. Their signals are used to derive vibration amplitudes which are compared to modal scope limits, including a safety factor. According to industrial guidelines, this factor is chosen conservatively to ensure safe operation of the machine. Within the experimental campaign with the open-test-case composite fan ECL5/CATANA, which is representative for modern lightweight Ultra High Bypass Ratio (UHBR) architectures, measurements close to the stability limit have been conducted. Investigation of phenomena like non-synchronous vibrations (NSV) and rotating stall require a close approach to the stability limit and hence demand for accurate (real-time) quantification of vibration amplitudes to ensure secure operation without exhaustive safety margins. Historically, short-time Fourier transforms of vibration sensors are used, but the complex nature of the mentioned coupled phenomena has an influence on amplitude accuracy, depending on evaluation parameters, as presented in a previous study using fast-response wall-pressure transducers. The present study investigates the sensitivity of blade vibration data to evaluation parameters for different spectral analysis methods and provides guidelines for fast and robust surveillance of critical vibration modes.

The development of an effective hydraulic unit (HU) diagnostic system, which recognizes critical fault at an early stage of their development, is a relevant and practically important objective for many hydroelectric power plants (HPP). The main trends in recent years in this area are the expansion of the hardware base and the introduction of digital technologies to handle the increasing flow of data monitoring. At the same time, much less attention is paid to the improvement of algorithms for potential defect recognition and the creation of new diagnostic rules; much of the monitoring data are used only for the trend construction, and do not participate in the diagnosis. The method of vector diagrams is proposed for estimating actual forces applied towards the support joints of an HU: each mode of operation is represented on a phase plane in the form of a vector proportional to the vibration displacement. The vector difference determines the actual forces of mechanical, electromagnetic and hydraulic origin in each operating mode, taking into account the individual characteristics of the HU. The example of vector diagram analysis shows how to obtain more useful information about the technical status of the unit from the same amount of basic vibration monitoring data, to predict possible deterioration in the operation of the equipment well before the generation of a warning or an alarm signal by the diagnostic system.

Mechanical action can damage physical objects, such as building structures. The transfer of energy to the ground through the falling mass, forming a crater, can cause kinematic forces in the soil medium. An effect of these forces, connected with the technology of geotechnical machines, is vibrations of the ground and building structures. When finding the energy impact on the object is difficult or even impossible, vibration monitoring and indirect estimation of the negative energy impact effects is possible. Commercial off-the-shelf solutions exist for vibration monitoring and recording, but they are dedicated to one application type and are relatively expensive. This paper presents a proprietary system for monitoring and recording vibrations of building objects transmitted through the ground. This allows for local registration and remote administration and presentation of data via a computer network. Vibrations can be analysed according to the requirements of developers and clients. The developed system shows that creating an effective approach for collecting data on building vibrations using components from different suppliers is possible. The waveforms collected using the system confirm the effectiveness and flexibility of the presented solution, providing a possibility of using the results to decide whether the vibrations are within the standard limits.

Active and passive vibration control systems are of paramount importance in many engineering applications. If an external load excites a structure’s resonance and the damping is too low, detrimental events, such as crack initiation, growth and, in the worst case, fatigue failure, can be entailed. Damping systems can be commonly found in applications such as industrial machines, vehicles, buildings, turbomachinery blades, and so forth. Active control systems usually achieve higher damping effectiveness than passive ones, but they need a sensor to detect the working conditions that require damping system activation. Recently, the development of such systems in rotating structures has received considerable interest among designers. As a result, the development of vibration monitoring equipment in rotating structures is also a topic of particular interest. In this respect, a reliable, inexpensive and wireless monitoring system is of utmost importance. Typically, optical systems are used to measure vibrations, but they are expensive and require rather complex processing algorithms. In this paper, a wireless system based on a commercial MEMS accelerometer is developed for rotating blade vibration monitoring. The proposed system measurement accuracy was assessed by means of comparison with a reference wired measurement setup based on a mini integrated circuit piezoelectric (ICP) accelerometer adapted for data acquisition in a rotating frame. Both the accelerometers were mounted on the tip of the blade and, in order to test the structure under different conditions, the first four blade resonances were excited by means of piezoelectric actuators, embedded in a novel experimental setup. The frequency and amplitude of acceleration, simultaneously measured by the reference and MEMS sensors, were compared with each other in order to investigate the viability and accuracy of the proposed wireless monitoring system. The rotor angular speed was varied from 0 to 300 rpm, and the data acquisitions were repeated six times for each considered condition. The outcomes reveal that the wireless measurement system may be successfully used for vibration monitoring in rotating blades.

The stability of the Great Wall is mainly affected by traffic vibrations and natural hazards, such as strong winds, heavy rainfall, and thunderstorms, which are extremely harmful to the safety of the Great Wall. To determine the impact of the above factors on the Great Wall, a comparative analysis based on MEMS (micro-electro-mechanical system) accelerometer data was conducted between the non-impacts and the impacts of the above factors. An analysis of the relationship between vibration acceleration and each potential hazard based on a visual time series chart was presented using the data of accelerometers, traffic video, meteorology, rainfall, and wind. According to the results, traffic vibration is one of the primary dangerous factors affecting the stability of the Great Wall, Moreover, the intensity of the vibrations increases with the traffic flow. Thunderstorms also influence the stability of the Great Wall, with enhanced thunderstorm excitation resulting in increased vibration displacement. Furthermore, wind load is an influencing factor, with average wind speeds greater than 9 m/s significantly affecting the stability of the Great Wall. Rainfall has no impact on the stability of the Great Wall in the short term. This research can provide important guidance for risk assessment and protection of the Great Wall.

Wind energy is one of the most relevant clean energies today, so wind turbines must have good health and be reliable in operation. Current wind turbines have slender and elastic structures that can be easily damaged through vibrations and compromise their health; therefore, vibration monitoring is essential to ensure safe operation. Here, we present a method for simple wind turbine vibration monitoring in the laboratory by means of an accelerometer placed on a weathervane under different scenarios, with recording of different amplitudes of vibrations caused at a constant speed of 10 km/h. The variables, trends, and data captured during vibration monitoring were then used to implement a prediction system of synthetic failure using machine learning methods such as: Medium Trees, Cubic SVN, Logistic Regression Kernel, Optimized Neural Network, and Bagged Trees, with the last demonstrating an accuracy of up to 0.87%.

In order to study the applicability of high-pressure gas expansion rock-cracking technology in hard rock tunnel near historic sites, theoretical analysis, field tests as well as vibration monitoring are conducted to obtain suitable rock mass cracking parameters for tunnel excavation. The results show that the ideal effect of rock mass cracking can be achieved with the cutting mode of “central vertical empty hole + double wedge cutting hole” and the auxiliary hole network parameter of “0.8 m × 0.7 m”. The measured vibration velocity is less than 0.1 cm/s at the monitoring point 60 m away from the tunnel face in the field test, which meets the vibration control requirements of the historic sites in the process of tunnel excavation. The research results show that as long as there is a high quality of hole plugging and no punching, the high-pressure gas expansion rock-cracking technology has the advantages of little vibration, low noise and less flying rocks, which provides a technical reference for the excavation of hard rock tunnels near ancient buildings and historic sites.

In this paper, an IoT sensor node, based on smart Bluetooth low energy (BLE), for the health monitoring of artworks and large wooden structures is presented. The measurements from sensors on board the node are collected in real-time and sent to a remote gateway. The sensor node allows for the monitoring of environmental parameters, in particular, temperature and humidity, with accurate and robust integrated sensors. The developed node also embeds an accelerometer, which also allows other mechanical quantities (such as tilt) to be derived. This feature can be exploited to perform structural monitoring, exploiting the processing of data history to detect permanent displacements or deformations. The node is triggered by acceleration transients; therefore, it can also generate alarms related to shocks. This feature is crucial, for instance, in the case of transportation. The developed device is low-cost and has very good performance in terms of power consumption and compactness. A reliability assessment showed excellent durability, and experimental tests proved very satisfactory robustness against working condition variations. The presented results confirm that the developed device allows for the realization of pervasive monitoring systems, in the context of the IoT paradigm, with sensor nodes devoted to the monitoring of each artwork present in a museum or in a church.

In recent years, the ENEA has introduced a novel methodology based on motion magnification (MM) into the Italian cultural heritage protection and monitoring field. It consists of a digital video signal processing technique able to amplify enormously the tiny movements recorded in conventional videos, while preserving the general topology of the acquired frames. Though the idea of such a methodology is not new, it has recently been provided with an efficient algorithm that makes possible a viable and low-cost magnification. Applications are extremely varied in almost every field of science and technology; however, we are interested in its application to the safeguarding of architectural heritage, a sector of the utmost importance for Italy. As ancient buildings can be extremely sensitive to even minimally invasive instrumentation, most common monitoring sensors can be replaced by contactless tools and methods, such as video-based techniques like MM. It offers many advantages: easy to use, contactless devices, virtual sensors, reusability of the videos, practicality, intuitive graphical results, quantitative analyses capability and low costs. These characteristics are well suited to the monitoring of large ancient monuments; on the other hand, historical sites have peculiarities of their own, requiring careful approaches, proper tools and trained personnel. Moreover, outdoor applications of MM present quite notable difficulties from a practical point of view, e.g., the dimensions of the studied objects, uncontrolled environmental conditions, spurious vibrations, lighting change/instability, etc. Here we give a general idea of the potential of MM and related issues, using some relevant in-the-field case studies in Italian heritage protection.

Double-shield TBM is more efficient than shield tunnel construction in hard rock strata. It is widely used in subway tunnel construction, such as in Qingdao and Chongqing in China. However, construction vibration problems caused by double-shield TBM critically affect human comfort in surface buildings. In order to study the vibration influence law of double-shield TBM, the on-site monitoring plan of double-shield TBM is developed, relying on a tunnel section of Qingdao Metro Line 4. Then, the vibration monitoring results are analyzed, and the time domain and frequency domain characteristics of vibration acceleration are obtained. Subsequently, taking vibration peak acceleration as the research object, the transverse and longitudinal vibration laws of double-shield TBM construction are studied. Finally, according to the standard of human comfort in buildings, the vibration influence ranges of double-shield TBM construction are obtained. The research results can provide a reference for the vibration effect of double-shield TBM passing through houses, highways and bridges. Moreover, it can also provide a basis for the disputes that double-shield TBM tunnel construction affects the lives of inhabitants.

Used in many industrial applications, centrifugal pumps have optimal operating criteria specified at design. These criteria may not be precisely adhered to during operation which will ultimately reduce the life of the asset. Operators would therefore benefit from anticipating how often the design point is deviated from and hence how much asset degradation results. For centrifugal pumps, a novel set of covariates were proposed in this paper which formally partition observed operating zones with an Empirical Bivariate Quantile Partitioned distribution. This captured the dependency relation between operating parameters across plant configurations to predict the component wear that results from particular settings. The effectiveness of this was demonstrated through an operational case study in civil nuclear generation feedwater pumps where corroboration with bearing movements provides an indicator of plant wear. Such a technique is envisaged to inform operators of optimal plant configuration from multiple possibilities in advance of undertaking them.

Vibration monitoring provides a good-quality source of information about the health condition of machines, and it is often based on the use of accelerometers. This article focuses on the use of accelerometer sensors in fabricating a low-cost system for monitoring vibrations in agricultural machines, such as rotary tedders. The aim of the study is to provide useful data on equipment health for improving the durability of such machinery. The electronic prototype, based on the low-cost AVR microcontroller ATmega128 with 10-bit ADC performing a 12-bit measurement, is able to acquire data from an accelerometer weighing up to 10 g. Three sensors were exposed to low accelerations with the use of an exciter, and their static characteristics were presented. Standard experimental tests were used to evaluate the constructed machine monitoring system. The self-contained prototype system was calibrated in a laboratory test rig, and sinusoidal and multisinusoidal excitations were used. Measurements in time and frequency domains were carried out. The amplitude characteristic of the preformed system differed by no more than 15% within a frequency range of 10 Hz–10 kHz, compared to the AVM4000 commercial product. Finally, the system was experimentally tested to measure acceleration at three characteristic points in a rotational tedder, i.e., the solid grease gearbox, the drive shaft bearing and the main frame. The RMS amplitude values of the shaft vibrations on the bearing in relation to the change in the drive shaft speed of two tedders of the same type were evaluated and compared. Additionally, the parameters of kurtosis and crest factor were compared to ascertain the bearing condition.

Gearboxes are frequently used in the mining industry, especially for power transmission between the electric drive and the ball mill; besides the extreme complexity of a ball mill gear transmission system, the fault diagnosis by vibration analysis can be easily distorted by the presence of impulsive noises due to the ball pulses on the mill shell. Although several works in the literature are related to the influence of an impulsive noise on the accuracy of the diagnosis, no dynamic model exists yet in the literature that can explain the influence of these forces on the dynamic behavior of gearboxes. This paper presents a new approach to determine the influence of the grinding forces in crack defects diagnosis. This approach is based on a hybrid numerical model of a 24-degree-of-freedom gearbox, simulating one gear train and two drive shafts. The impact forces of the mill drum are modelled by a discrete element method (DEM). The ball-filling rate (Fr), the mill speed (Nr), and the ball size (Db) are considered to study this phenomenon. The simulations results show by a time series representation, fast Fourier transform, and short-time Fourier transform (STFT), that the acceleration is significantly affected by the presence of the grinding forces, developing an impulsive noise due to the impact of the balls governed by the studied parameters.

Building structures are subject to various deformations caused by external and internal factors. Deformations are determined by various methods in the form of monitoring. It is very important to monitor the dynamic vibration response on bridge structures since these measurements allow us to identify any possible damage over time and take appropriate action. Our experiment, described in this article, is based on the use of non-contact methods, among which we used a geodetic instrument RTS (Robotic Total Station) and a seismograph to measure vibrations. The purpose and novelty of our work are reflected in the use of geodetic instruments to determine the dynamic response and synchronization of the obtained results. When using RTS technology, we increased data acquisition from 9 to 26 measurements per second. Comparative analysis of the measured signals was performed using FFT (Fast Fourier Transformation) and LSP (Lomb–Scargle Periodogram), based on LSSA (Least-Squares Spectral Analysis). The results showed us that when using the RTS geodetic instrument, it is possible to achieve frequency spectra comparable to those measured with a seismograph instrument. By increasing the number of measurements, the RTS method can be used to obtain more continuous data, which are essential for dynamic analyses.

A turbomachine is a fundamental engineering apparatus meant to transfer energy between a rotor and a fluid. Turbomachines are the core of power generation in many engineering applications such as electric power generation plants, aerospace, marine power, automotive etc. Their relevance makes them both mission critical and safety critical in many fields. To foster reliability and safety, then, continuous monitoring of the rotor is more than desirable. One promising monitoring technique is, with no doubt, the Blade Tip-Timing, which, being simple and non-invasive, can be easily implemented on many different rotors. Blade Tip-Timing is based on the recording of the time of arrival of the blades passing in front of a probe located at a fixed angular position. The non-contact nature of the measurement prevents influences on the measured vibration, that can be recovered for all the blades simultaneously, possibly even online. In this regard, a novel algorithm is presented in this paper for obtaining a good estimate of the vibration of the blades with minimum system complexity (i.e., only one Blade Tip-Timing probe) and minimum computational effort, so to create a simple vibration monitoring system, potentially implementable online. The methodology was tested on a dataset from a SAFRAN turbomachine made available during the Surveillance 9 international conference for a diagnostic contest.

Mediumfrequency fiber Bragg grating (FBG) acceleration sensors are used in important applications in mechanical, aerospace and weapon equipment, and have strict requirements in terms of resonance frequency and sensitivity. A novel medium-frequency accelerometer, based on fiber Bragg grating and flexible hinges, is proposed in this paper. The differential structure doubles the sensitivity of the sensor while avoiding temperature effects. The structure model and principle for the sensor are introduced, the sensor’s sensing characteristics are theoretically analyzed, and the structure parameters for the sensor are determined through numerical analysis. The sensing experiments show that the resonance frequency of the sensor is approximately 2800 Hz, the sensitivity is 21.8 pm/g in the flat frequency range of 50–1000 Hz, and the proposed sensor has a good temperature self-compensation function and lateral anti-interference capability.

This paper develops a novel hybrid feature learner and classifier for vibration-based fault detection and isolation (FDI) of industrial apartments. The trained model extracts high-level discriminative features from vibration signals and predicts equipment state. Against the limitations of traditional machine learning (ML)-based classifiers, the convolutional neural network (CNN) and deep neural network (DNN) are not only superior for real-time applications, but they also come with other benefits including ease-of-use, automated feature learning, and higher predictive accuracies. This study proposes a hybrid DNN and one-dimensional CNN diagnostics model (D-dCNN) which automatically extracts high-level discriminative features from vibration signals for FDI. Via Softmax averaging at the output layer, the model mitigates the limitations of the standalone classifiers. A diagnostic case study demonstrates the efficiency of the model with a significant accuracy of 92% (F1 score) and extensive comparative empirical validations.

Machinery with several rotating and stationary components tends to produce non-stationary and random vibration signatures due to the fluctuations in the input loads and process defects due to long hours of operation. Traditional heuristics methods are suitable for the detection of fault signatures, however, they become more complicated when the level of uncertainty or randomness exceeds beyond control. A novel methodology to identify these fault signatures using optimal filtering of vibration data is proposed to eliminate any false alarms and is expected to provide a higher probability of correct diagnosis. In this paper, a detailed pipeline of the algorithms are presented along with the results of the investigation that was carried out. These investigations are performed using open-source vibration data published by the NASA prognostics centre. The performance of these algorithms are evaluated based on the ground truth results published by NASA researchers. Based on the performance of these algorithms several parameters are fine-tuned to ensure generalisation and reliable performance.

Monitoring the structural health of wind turbine blades is essential to increase energy capture and operational safety of turbines, and therewith enhance competitiveness of wind energy. With the current trends of designing blades ever longer, detailed knowledge of the vibrational characteristics at any point along the blade is desirable. In our approach, we monitor vibrations during operation of the turbine by wirelessly measuring accelerations on the outside of the blades. We propose an algorithm to extract so-called vibration-based fingerprints from those measurements, i.e., dominant vibrations such as eigenfrequencies and narrow-band noise. These fingerprints can then be used for subsequent analysis and visualisation, e.g., for comparing fingerprints across several sensor positions and for identifying vibrations as global or local properties. In this study, data were collected by sensors on two test turbines and fingerprints were successfully extracted for vibrations with both low and high operational variability. An analysis of sensors on the same blade indicates that fingerprints deviate for positions at large radial distance or at different blade sides and, hence, an evaluation with larger datasets of sensors at different positions is promising. In addition, the results show that distributed measurements on the blades are needed to gain a detailed understanding of blade vibrations and thereby reduce loads, increase energy harvesting and improve future blade design. In doing so, our method provides a tool for analysing vibrations with relation to environmental and operational variability in a comprehensive manner.

Vibration-condition monitoring aims to detect bearing damages of rotating machinery’s incipient failures mainly through time–frequency methods because of their efficient analysis of nonstationary signals. However, by having failures with impulse behavior, short-term events have a tendency to be diluted under variable-speed conditions, while information on frequency changes tends to be lost. Here, we introduce an approach to highlighting bearing impulsive failures by measuring short-term spectral components to deal with variable-speed vibrations. The short-term estimator employs two sliding windows: a small one that measures the instantaneous amplitude level and tracks impulsive components and a large interval that evaluates the average background amplitude. Aiming to characterize cyclo-non-stationary processes with impulsive behavior, the emphasizing high-order-based estimator based on the principle of spectral entropy is introduced. For evaluation, both visual inspection and classifier performance are assessed, contrasting the spectral-entropy estimator with the widely used spectral-kurtosis approach for dealing with impulsive signals. The validation of short-time/-angle spectral analysis performed on three datasets at variable speed showed that the proposed spectral-entropy estimator is a promising indicator for emphasizing bearing failures with impulse behavior.

Hypergravity accelerators are a type of large machinery used for gravity training or medical research. A failure of such large equipment can be a serious problem in terms of safety or costs. This paper proposes a prediction model that can proactively prevent failures that may occur in a hypergravity accelerator. An experiment was conducted to evaluate the performance of the method proposed in this paper. A 4-channel accelerometer was attached to the bearing housing, which is a rotor, and time-amplitude data were obtained from the measured values by sampling. The method proposed in this paper was trained with transfer learning, a deep learning model that replaced the VGG19 model with a Fully Connected Layer (FCL) and Global Average Pooling (GAP) by converting the vibration signal into a short-time Fourier transform (STFT) or Mel-Frequency Cepstral Coefficients (MFCC) spectrogram and converting the input into a 2D image. As a result, the model proposed in this paper has seven times decreased trainable parameters of VGG19, and it is possible to quantify the severity while looking at the defect areas that cannot be seen with 1D.

Estimating the remaining useful life (RUL) of components is a crucial task to enhance reliability, safety, productivity, and to reduce maintenance cost. In general, predicting the RUL of a component includes constructing a health indicator (HI) to infer the current condition of the component, and modelling the degradation process in order to estimate the future behavior. Although many signal processing and data-driven methods have been proposed to construct the HI, most of the existing methods are based on manual feature extraction techniques and require the prior knowledge of experts, or rely on a large amount of failure data. Therefore, in this study, a new data-driven method based on the convolutional autoencoder (CAE) is presented to construct the HI. For this purpose, the continuous wavelet transform (CWT) technique was used to convert the raw acquired vibrational signals into a two-dimensional image; then, the CAE model was trained by the healthy operation dataset. Finally, the Mahalanobis distance (MD) between the healthy and failure stages was measured as the HI. The proposed method was tested on a benchmark bearing dataset and compared with several other traditional HI construction models. Experimental results indicate that the constructed HI exhibited a monotonically increasing degradation trend and had good performance in terms of detecting incipient faults.

Low frequency vibration monitoring has significant implications on environmental safety and engineering practices. Vibration expressed by visual information should contain sufficient spatial information. RGB-D camera could record diverse spatial information of vibration in frame images. Deep learning can adaptively transform frame images into deep abstract features through nonlinear mapping, which is an effective method to improve the intelligence of vibration monitoring. In this paper, a multi-modal low frequency visual vibration monitoring system based on Kinect v2 and 3DCNN-ConvLSTM is proposed. Microsoft Kinect v2 collects RGB and depth video information of vibrating objects in unstable ambient light. The 3DCNN-ConvLSTM architecture can effectively learn the spatial-temporal characteristics of muti-frequency vibration. The short-term spatiotemporal feature of the collected vibration information is learned through 3D convolution networks and the long-term spatiotemporal feature is learned through convolutional LSTM. Multi-modal fusion of RGB and depth mode is used to further improve the monitoring accuracy to 93% in the low frequency vibration range of 0–10 Hz. The results show that the system can monitor low frequency vibration and meet the basic measurement requirements.

Electromagnetic dampers are emerging as alternatives to conventional dampers applied to stay cables of bridges because they can reduce maintenance costs and allow vibration monitoring owing to their permanent driving characteristics and self-generation function. In this study, the main equations (including those for the induced electromotive force of the active coils and the total damping force of the damper) were derived through magnetic circuit analysis using the main parameters of the electromagnetic damper model. Characteristic tests were performed on electromagnetic damper prototypes to analyze the hysteretic dynamics and derive characteristics according to their structure and excitation conditions. On the basis of the results, we proposed a regenerative hybrid electrodynamic damper with an oxygen-free copper tube and teeth structure. Its physical and electromagnetic behaviors were examined through an electromagnetic analysis of the finite element model of the proposed damper. The results confirmed that attenuation occurred via strengthened magnetic flows, and the estimated power production is suitable for energy harvesting applications. Therefore, we confirmed the feasibility of constructing a system that can simultaneously perform cable attenuation and vibration monitoring using the proposed damper.

In this paper, the problem of optimal sensor arrangement during vibration monitoring is analysed. The wave propagation caused by horizontal excitation is investigated to predict the areas of the largest ground and structure response. The equations of motion for a transversally isotropic elastic medium with appropriate absorbing boundary conditions are solved using the finite element method (FlexPDE software). The possibility of an amplified soil medium response is examined for points located on the ground surface and at various depths. The results are presented in the form of a dimensionless vibration reduction factor, defined as the ratio of the peak particle velocity observed at the selected depth to the corresponding value observed at the ground surface. Significant amplifications (≈50%) can be observed below the ground surface, especially in the case of a weak layer below a stiff layer. The effect of vibration amplification is most significant near the boundary surface of two layers. For the points located on the ground surface, the greatest peak particle velocities are observed in the direction perpendicular to the load direction. However, the greatest vertical velocity component at the ground surface is observed in front of the applied force.

The prediction of electrical machines’ Remaining Useful Life (RUL) can facilitate making electrical machine maintenance policies, which is important for improving their security and extending their life span. This paper proposes an RUL prediction model with similarity fusion of multi-parameter and multi-sample. Firstly, based on the time domain and frequency domain extraction of vibration signals, the performance damage indicator system of a gearbox is established to select the optimal damage indicators for RUL prediction. Low-pass filtering based on approximate entropy variance (Aev) is introduced in this process because of its stability. Secondly, this paper constructs Dynamic Time Warping Distance (DTWD) as a similarity measurement function, which belongs to the nonlinear dynamic programming algorithm. It performed better than the traditional Euclidean distance. Thirdly, based on DTWD, similarity fusion of multi-parameter and multi-sample methods is proposed here to achieve RUL prediction. Next, the performance evaluation indicator Q is adopted to evaluate the RUL prediction accuracy of different methods. Finally, the proposed method is verified by experiments, and the Multivariable Support Vector Machine (MSVM) and Principal Component Analysis (PCA) are introduced for comparative studies. The results show that the Mean Absolute Percentage Error (MAPE) of the similarity fusion of multi-parameter and multi-sample methods proposed here is below 14%, which is lower than MSVM’s and PCA’s. Additionally, the RUL prediction based on the DTWD function in multi-sample similarity fusion exhibits the best accuracy.

Nowadays, the subject of machine diagnostics is gathering growing interest in the research field as switching from a programmed to a preventive maintenance regime based on the real health conditions (i.e., condition-based maintenance) can lead to great advantages both in terms of safety and costs. Nondestructive tests monitoring the state of health are fundamental for this purpose. An effective form of condition monitoring is that based on vibration (vibration monitoring), which exploits inexpensive accelerometers to perform machine diagnostics. In this work, statistics and hypothesis testing will be used to build a solid foundation for damage detection by recognition of patterns in a multivariate dataset which collects simple time features extracted from accelerometric measurements. In this regard, data from high-speed aeronautical bearings were analyzed. These were acquired on a test rig built by the Dynamic and Identification Research Group (DIRG) of the Department of Mechanical and Aerospace Engineering at Politecnico di Torino. The proposed strategy was to reduce the multivariate dataset to a single index which the health conditions can be determined. This dimensionality reduction was initially performed using Principal Component Analysis, which proved to be a lossy compression. Improvement was obtained via Fisher’s Linear Discriminant Analysis, which finds the direction with maximum distance between the damaged and healthy indices. This method is still ineffective in highlighting phenomena that develop in directions orthogonal to the discriminant. Finally, a lossless compression was achieved using the Mahalanobis distance-based Novelty Indices, which was also able to compensate for possible latent confounding factors. Further, considerations about the confidence, the sensitivity, the curse of dimensionality, and the minimum number of samples were also tackled for ensuring statistical significance. The results obtained here were very good not only in terms of reduced amounts of missed and false alarms, but also considering the speed of the algorithms, their simplicity, and the full independence from human interaction, which make them suitable for real time implementation and integration in condition-based maintenance (CBM) regimes.

On-line vibration monitoring is significant for high-speed rotating blades, and blade tip-timing (BTT) is generally regarded as a promising solution. BTT methods must assume that rotating speeds are constant. This assumption is impractical, and blade damages are always formed and accumulated during variable operational conditions. Thus, how to carry out BTT vibration monitoring under variable rotation speed (VRS) is a big challenge. Angular sampling-based order analyses have been widely used for vibration signals in rotating machinery with variable speeds. However, BTT vibration signals are well under-sampled, and Shannon’s sampling theorem is not satisfied so that existing order analysis methods will not work well. To overcome this problem, a reconstructed order analysis-based BTT vibration monitoring method is proposed in this paper. First, the effects of VRS on BTT vibration monitoring are analyzed, and the basic structure of angular sampling-based BTT vibration monitoring under VRS is presented. Then a band-pass sampling-based engine order (EO) reconstruction algorithm is proposed for uniform BTT sensor configuration so that few BTT sensors can be used to extract high EOs. In addition, a periodically non-uniform sampling-based EO reconstruction algorithm is proposed for non-uniform BTT sensor configuration. Next, numerical simulations are done to validate the two reconstruction algorithms. In the end, an experimental set-up is built. Both uniform and non-uniform BTT vibration signals are collected, and reconstructed order analysis are carried out. Simulation and experimental results testify that the proposed algorithms can accurately capture characteristic high EOs of synchronous and asynchronous vibrations under VRS by using few BTT sensors. The significance of this paper is to overcome the limitation of conventional BTT methods of dealing with variable blade rotating speeds.

Manufacturing processes are of great relevance nowadays, when there is a constant claim for better productivity with high quality at low cost. The contribution of this work is the development of a fused smart-sensor, based on FPGA to improve the online quantitative estimation of flank-wear area in CNC machine inserts from the information provided by two primary sensors: the monitoring current output of a servoamplifier, and a 3-axis accelerometer. Results from experimentation show that the fusion of both parameters makes it possible to obtain three times better accuracy when compared with the accuracy obtained from current and vibration signals, individually used.

This paper deals with the performance analysis of a vibration-isolation system for Michelangelo Buonarroti’s famous Ronadanini Pietà statue based on the monitoring and analysis of vibration signals. A tuned mass-damper–inerter is introduced in order to increase the effectiveness of the isolator in the horizontal direction. Specifically, a multi-degree-of-freedom (MDOF) model for the system, including non-linear terms, is proposed. The monitoring data of the structure inside the museum were utilized to update the MDOF model of this structure. Then, the effect of different parameters was analysed, and some modifications proposed to enhance the efficiency of the isolation system in its working condition. A combination of tuned mass-dampers (TMD) with an inerter is proposed to attain a considerable increase in the performance of the isolation system based on the main feature of the tuned mass-damper–inerter (TMDI), which can apply high apparent mass to a system without adding considerable real mass to the original system. Various performance functions are used to illustrate the efficiency of the proposed TMDI. It is shown that a significant effect of this passive method is to reduce the level of vibration in the updated model of this sensitive and valuable object.

Due to the increasing share of new renewable energies like wind and solar in the generation of electricity the need for power regulation and energy storage is becoming of paramount importance. One of the systems to store huge amounts of energy is pumped storage using reversible hydropower units. The machines used in these power plants are pump-turbines, which can operate as a pump and as a turbine. The surplus of electrical energy during low consumption hours can be converted into potential hydraulic energy by pumping water to a higher level. The stored energy can be converted into electricity again by operating the runner as a turbine. Due to new regulation requirements machines have to extend the operating range in order to match energy generation with consumption for the grid stability. In this paper the consequences of extending the operating range in existing pump-turbines have been studied. For that purpose, the data obtained after two years of condition monitoring were analyzed. Vibrations and pressure fluctuations of two pump-turbines of 85 MW each have been studied during pump and turbine operation. For turbine operation the effects of extending the operating range from the standard range of 45–85 MW to and increased range of 20–85 MW were analyzed. The change in vibration levels and signatures at very low load are presented with the identification of the phenomena that occur under these conditions. The influence of head in the vibration behavior is also presented. The appearance of fluid instabilities generated at part load that may produce power swing is also presented. Finally, the effect of head on the vibration levels for pump operation is shown and analyzed.

In bridge health monitoring, tiltmeters have been used for measuring rotation and curvature; however, their application in dynamic parameter identification has been lacking. This study installed fiber Bragg grating (FBG) tiltmeters on the bearings of a bridge and monitored the dynamic rotational angle. The dynamic features, including natural frequencies and mode shapes, have been identified successfully. The innovation presented in this paper is the first-time use of FBG tiltmeter readings to identify the natural frequencies of a long-span steel girder bridge. The identified results have been verified using a bridge finite element model. This paper introduces a new method for the dynamic monitoring of a bridge using FBG tiltmeters. Limitations and future research directions are also discussed in the conclusion.

A vibration sensor based on the use of a Software-Defined Radio (SDR) platform is adopted in this work to provide a contactless and multipurpose solution for low-cost real-time vibrations monitoring. In order to test the vibration detection ability of the proposed non-contact method, a 1 GHz Doppler radar sensor is simulated and successfully assessed on targets at various distances, with various oscillation frequencies and amplitudes. Furthermore, an SDR Doppler platform is practically realized, and preliminary experimental validations on a device able to produce a harmonic motion are illustrated to prove the effectiveness of the proposed approach.

To meet the requirements for low-frequency vibration monitoring, a new type of FBG (fiber Bragg grating) accelerometer with a bended spring plate is proposed. Two symmetrical bended spring plates are used as elastic elements, which drive the FBG to produce axial strains equal in magnitude but opposite in direction when exciting vibrations exist, leading to doubling the wavelength shift of the FBG. The mechanics model and a numerical method are presented in this paper, with which the influence of the structural parameters on the sensitivity and the eigenfrequency are discussed. The test results show that the sensitivity of the accelerometer is more than 1000 pm/g when the frequency is within the 0.7–20 Hz range.

By fixing two FBGs on the surface of a rotating shaft along the direction of ±45° and using dynamic wavelength demodulation technology, we propose an optical fiber sensing system to monitor the driving torque and torsion angle of the rotating shaft. In theory, the dependence relation of the dynamic difference of central wavelengths on the torque and torsion angle of the rotating shaft has been deduced. To verify an optical fiber sensing system, a series of sensing experiments have been completed and the measured data are approximately consistent with the theoretical analysis. The difference of two central wavelengths can be expressed as the sum of two parts: a “DC” part and a harmonic “AC” part. The driving torque or torsion angle is linear with the “DC” part of the difference of two central wavelengths, the harmonic “AC” part, meaning the torsion angle vibration, illustrates that periodic vibration torque may be caused by inhomogeneous centrifugal forces or inhomogeneous additional torques produced by the driving system and the load.