Structural Health Monitoring System Research Articles

An ultrafast and robust structural damage identification framework enabled by an optimized extreme learning machine

Artificial intelligence (AI) has recently been implemented in structural health monitoring (SHM) systems for damage detection and identification. However, existing AI methods often involve a high number of parameters, resulting in the laborious workload during model training and implementation. In this study, we develop a lightweight damage identification framework embedded with an optimized extreme learning machine (ELM) using a significantly reduced number of parameters from frequency features of the structural vibrational signals. Coupled with the ensemble empirical mode decomposition (EEMD), the frequency features were abstracted from the structural vibrational signals in the data pre-processing step. Then, a metaheuristic algorithm (chaos game optimization, CGO) was chosen to optimize the model weight of the ELM to guarantee damage identification accuracy. Once the model is trained, the structural damages can be precisely identified despite the noise-contaminated data. We validated the efficiency and accuracy of the proposed framework with a public database and compare its performance with several common metaheuristic algorithms. With the proven capability, the proposed framework shows a promising future as a handy and reliable AI-assisted digital tool for robust development in next-generation structural monitoring systems.

Evaluation of the single-frequency variometric approach based on low-cost GNSS observations and different satellite combinations for detecting short-term dynamic behaviors

Abstract This study presents the capability of the single-frequency (SF) variometric approach (VA) technique with low-cost GNSS observations to detect short-term dynamic behaviors. Harmonic oscillations with amplitudes between 5 and 20 mm and frequencies between 0.3 and 5.0 Hz were generated employing a single-axis shake table to investigate the performance of the SF-VA technique in the Structural Health Monitoring (SHM) system. Besides, a Mw 6.9 Kobe, 1995 earthquake simulation was generated using the shake table to analyze the SF-VA performance for the Earthquake Early Warning (EEW) system. A low-cost u-blox ZED-F9P GNSS receiver and ANN-MB-00 patch antenna were used to collect GNSS observations at a 20 Hz sampling rate during the experiments. The observations were processed using the MATLAB-based open-source PPPH-VA software in real-time mode, considering eight different satellite combinations. The capability of the SF-VA technique to detect horizontal dynamic behaviors in real-time mode was investigated in the frequency and time domains, accepting the displacements from the Linear Variable Differential Transformer (LVDT) sensor as a reference. The results in the frequency domain demonstrate that the SF-VA technique with low-cost GNSS observations can successfully detect the peak frequency value of short-term harmonic oscillations up to 5 Hz. Moreover, time domain findings emphasize that the short-time dynamic oscillations can be determined with the SF-VA technique with an accuracy ranging from 0.8 to 6.4 mm. Earthquake simulation experiment results demonstrate that the strong ground motions caused by mega earthquakes can be determined at mm-level by the SF-VA method. The results of both experiments show that multi-GNSS observations contribute to the SF-VA technique considerably. Overall, the findings reveal that the SHM and EEW systems can be operated with low-cost GNSS receivers, and the natural frequency of the man-made structures and accurate displacement values of seismic waveforms can be determined in real-time with the SF-VA technique.

Train-induced vibration response reconstruction for bridge damage detection with a deep learning methodology

Sensor malfunctions in bridge structural health monitoring system (BSHMS) could cause the missing of measured data, reducing the accuracy of damage detection. It is of great significance to reconstruct the data of faulty sensors with measured data of well-functioning sensors for bridge structural state assessment. In this paper, a train-induced vibration response reconstruction approach for bridge damage detection is proposed. An enhanced deep densely connected neural network (ED-DCNN) introducing a multi-head self-attention mechanism and a skip connection is designed to reconstruct the missing bridge responses, aiming to improve the vibration correlation between the faulty sensors and good sensors and benefit the learning of temporal and spatial features of responses. Then to further validate the accuracy and reliability of the ED-DCNN, an alternate down-sampling residual network (AD-ResNet) is built to identify bridge damage with the complete responses, including the reconstructed ones and the measured, which extracts the structural damage features at different scales utilizing different types of residual blocks in an alternating manner. The efficiency and robustness of the two networks are comprehensively studied using the collected acceleration data from a heavy-haul railway bridge, considering different noise levels. The results demonstrate that under various conditions, the reconstructed responses match the real responses well in time domain, with a low RMSE below 0.4% and a high correlation coefficient of 0.9744, which indicates that the incorporation of a multi-head self-attention module effectively improves the construction of correlations between responses. Additionally, the natural frequencies of bridge are accurately identified from the reconstructed responses. In terms of bridge damage detection, taking both the measured and reconstructed responses as inputs, the identification accuracy obviously improves by 33.57% compared to cases without the reconstructed responses, further emphasizing an excellent reconstruction capability of the ED-DCNN.

An Influence of Actuator Gluing on Elastic Wave Excited in the Structure.

In this article, the practical issues connected with guided wave measurement are studied: (1) the influence of gluing of PZT plate actuators (NAC2013) on generated elastic wave propagation, (2) the repeatability of PZT transducers attachment, and (3) the assessment of the possibility of comparing the results of Laser Doppler Vibrometry (LDV) measurement performed on different 2D samples. The consideration of these questions is crucial in the context of the assessment of the possibility of the application of the guided wave phenomenon to structural health-monitoring systems, e.g., in civil engineering. In the examination, laboratory tests on the web of steel I-section specimens were conducted. The size and shape of the specimens were developed in such a way that they were similar to the elements typically used in civil engineering structures. It was proved that the highest amplitude of the generated wave was obtained when the exciters were glued using wax. The repeatability and durability of this connection type were the weakest. Due to this reason, it was not suitable for practical use outside the laboratory. The permanent glue application gave a stable connection between the exciter and the specimen, but the generated signal had the lowest amplitude. In the paper, the new procedure dedicated to objective analysis and comparison of the elastic waves propagating on the surface of different specimens was proposed. In this procedure, the genetic algorithms help with the determination of a new coordinate system, in which the assessment of the quality of wave propagation in different directions is possible.

Design and simulation of fiber Bragg grating based structural health monitoring system for metal structure

Design and simulation of fiber Bragg grating based structural health monitoring system for metal structure

Data reconstruction for tunnel structural health monitoring: An updated KNN model with gray relational analysis

Structural health monitoring (SHM) system is an important way to evaluate the tunnel structural performance. In practice, the missing data is inevitably induced in the SHM dataset, which may cause deviation or even misleading results of the data analysis, and hence, need to be accurately reconstructed. This study proposes a new KNN data reconstruction method based on a gray correlation measure (GRA-KNN). Compared to the traditional KNN, the GRA-KNN can measure the structural similarity of data better, and the pre-filling can make full use of the information of known data to estimate missing data. By comparing with the other five machine learning methods (i.e., Ridge Regression, Support Vector Regression, Multilayer Perceptron, RandomForest, and XGBoost), the imputation performance of this method is examined using two real-time SHM datasets from Nanjing Yangtze River tunnel and Hong Kong-Zhuhai-Macao Bridge Undersea Tunnel. Results show that the GRA-KNN method possesses a better performance and stronger robustness under a wide range of missing ratios from 10% to 90%, showing great potential in SHM data reconstruction. In particular, when the missing ratio is larger than 60%, the imputation error of the proposed method is the smallest compared to that of the other machine learning methods.

Adaptive Vibration Monitoring of Railway Track Structures Using the UWFBG by the Identification of Train-Load Patterns

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.

Response of a novel all-solid-state sodium-based-electrolyte battery to quasi-static and dynamic stimuli

In response to growing environmental and economic concerns, developing new technologies prioritising safety, sustainability, and reliability has become imperative. In the energy sector, batteries play an increasingly significant role in applications such as powering electronic devices and vehicles. In this context, lithium-ion batteries have raised environmental concerns, driving the exploration of alternative technologies. Sodium-based batteries have emerged as an attractive option due to their environmental and economic advantages, as well as their potential for multi-functional applications. This study investigates a novel battery developed by a research team at the University of Porto, with a specific focus on its strain-sensing capabilities for potential applications in damage detection of structures. The battery under investigation is a novel all-solid-state design, comprised of a sodium-ion ferroelectric electrolyte and zinc and copper as the negative and positive electrodes, respectively. A series of quasi-static and dynamic tests are conducted to qualitatively assess the piezoelectric behaviour of the battery. The consistent findings show that the battery generates a difference in the electric potential in response to mechanical stimuli, thus confirming its piezoelectric nature. Furthermore, the results demonstrate the battery can accurately detect the operating frequencies of a shaker, despite encountering inherent electromagnetic interference noise from the electrical grid during testing. These promising outcomes highlight the substantial potential of this emerging technology for a wide range of applications, including but not limited to structural health monitoring systems. Given its novelty, this technology presents multi-functional capabilities for diverse practical future applications, such as energy harvesting that leads to self-powered structural health monitoring systems.

A novel procedure for cable damage identification of cable-stayed bridge using particle swarm optimization and machine learning

The cables are crucial components in the ensuring safety of the stayed-cable bridges. The early identification and quantification of cable damage based on the inherent structural health monitoring (SHM) system is a priority to prevent disasters. In this study, a procedure is proposed to identify the cable damage in the cable-stayed bridges using the particle swarm optimization (PSO) and the categorical gradient boosting (CatBoost) algorithm. The PSO-based finite element model updating method is implemented to establish the baseline model while a practical advanced analysis program is used to generate simulation data. As an efficient and up-to-date machine learning (ML) algorithm, CatBoost is utilized to capture the complex nonlinear correlations between the vibration characteristics and the cable damages. A case study of a benchmark bridge where cable damage has been identified is considered to evaluate the efficiency of the proposed procedure. The fivefold cross-validation and grid search methods are used to find the optimal model. The accuracy of the proposed cable damage identification model using CatBoost is also verified through the comparison with three existing ML methods: random forest, decision tree, and extreme gradient boosting. The identification results of both simulation and real cases of cable damage demonstrate that the proposed procedure is a novel and powerful approach for cable damage identification of the cable-stayed bridge using measurement data of the existing SHM system.

Full-field displacement measurement of long-span bridges using one camera and robust self-adaptive complex pyramid

Full-field motion with a high spatial resolution can reflect the health state of long-span bridges. Traditional structural health monitoring (SHM) systems measure the structural displacement at sparse points only. Despite the development of various methods for obtaining high-resolution responses, they fail to estimate the multi-scale motions of real long-span bridges. A novel full-field motion estimation method is proposed to directly measure the entire structural responses using one digital camera. In this approach, multi-scale motions of different components under unknown excitations are encoded in a complex pyramid. The parameters of the complex pyramid are determined by the localization index to record robust local phases at each measurement point. Two indices, namely, the spatial Laplacian of the phase and the amplitude value degradation index, are designed to adaptively estimate multi-scale displacements contained in the complex pyramid. The proposed method estimates the full-field displacements of a steel frame accurately in an experimental test. Moreover, the full-field displacement of the 1377-m long main span Tsing Ma Bridge is estimated using only one shot. Results suggest that the displacement estimated by the proposed method matches well with the GPS data and further visualizes the bridge mode shapes with a high resolution.

Methodology for geometry assessment of self-drilling micropiles using distributed fibre optic sensors

Self-drilling micropiles (SDMs) are gaining popularity as bearing foundation elements, as this construction technique allows for considerable time and cost savings. However, the irregular geometry and variability in the bearing capacity present uncertainty and a significant risk that has limited SDM deployment. To date, no reliable technology has been used to measure the SDM geometry. This paper proposes a methodology that uses distributed fibre optics (DFO), heat conduction modelling and inverse analysis to measure the pile geometry, and could also be extended to assess its bearing capacity. The temperature distribution during cement hydration was measured using two DFO investigative technologies and was compared to traditional temperature measurements using point sensors. An inverse analysis of SDM geometry was subsequently carried out based on the DFO measurement of temperature, a finite-element heat conduction model and a calibration pile. Finally, the calculated pile geometry was compared to the geometry of an excavated pile in the uppermost part. The methodology presented here is not only intended as a tool for designing SDMs but can also be deployed as a structural health monitoring system to detect and monitor crack formation.

Contact-point response reconstruction for indirect bridge monitoring via Bayesian expectation-maximization based augmented Kalman filter

The drive-by bridge dynamic measurement using an instrumented vehicle during its passage over the bridge can be an indirect bridge structural health monitoring system. The identification of the contact-point (CP) responses between vehicle wheels and bridge structure from vehicle responses offers an efficient and economical way for the modal identification and condition assessment of short- to mid-span road bridges. This paper proposes a novel method for the contact-point displacement response reconstruction of the vehicle-bridge interaction (VBI) system in a joint input-state estimation manner based on Bayesian Expectation-Maximization (BEM). An analytical model of VBI including the road approach in front of a simply-supported bridge is presented firstly. Then the augmented state-space model of the vehicle with the contact-point responses included as variables along with vehicle states is established. A new method by integrating the augmented Kalman filter (AKF) with a BEM strategy is proposed to solve the state estimation problem without knowing the vehicle axle responses. The vehicle states and CP displacement responses are identified simultaneously. The effects of the measurement noise, road surface roughness and vehicle speed on the identified results are investigated using numerical simulations. The experimental tests are used to further verify the feasibility and accuracy of the proposed method. The results show that the proposed method has potential for drive-by bridge condition assessment using on-board vehicle response measurements for a large population of short- to mid-span bridges.

An approach to seismic damage detection and evaluation in RC bridge piers through vibration data

A timely post-earthquake damage evaluation in existing bridges is fundamental for an efficient emergency management. Structural Health Monitoring (SHM) systems can allow a fast damage assessment; however, a lack of methods for the SHM data interpretation is recognised. The present paper proposes an approach for the probabilistic seismic damage detection and quantification in ductile bridge piers from vibration-based SHM data by comparing time variations of modal properties. To this aim, the selected modal properties are natural frequencies and mode-shapes, expressed in terms of CoMAC and ECoMAC indices. Experimental results of quasi-static cyclic tests and output-only modal identification tests are adopted to calibrate a reliable finite element model able to predict the variations in fundamental modal properties of ductile RC piers due to seismic damage. The calibrated model is used to perform probabilistic analyses to derive probability distributions for the variation of the considered modal-based features of piers at different seismic damage levels. The approach provides fragility models to support a timely assessment of serviceability levels in monitored assets in the immediate aftermath of an earthquake by monitoring the variation of natural frequencies. Conversely, CoMAC and ECoMAC resulted slightly sensitive to seismic damage for the investigated piers portfolio.

Technological Basis for Data Interoperability of Highway Structural Health Monitoring Systems and Intelligent Transport Systems

Technological Basis for Data Interoperability of Highway Structural Health Monitoring Systems and Intelligent Transport Systems

Structural condition assessment with structural health monitoring systems and nonlinear simplified models

Structural condition assessment with structural health monitoring systems and nonlinear simplified models

Online Real-Time Monitoring System of A Structural Steel Railway Bridge Using Wireless Smart Sensors

In the transportation network, railway bridges are crucial for the transfer of both passengers and commodities. Railway bridges require continuous monitoring to observe their performance. A structural health monitoring system is one method for assessing the viability of a railway bridge structure. The functioning of railroad bridge structures has been extensively observed using wireless technology. This research aims to implement smart wireless sensors for monitoring the structural health of the railway bridge online in real-time during operation. Many sensor kinds were installed on the railway bridge, including strain gauges, accelerometers, linear variable displacement transducers, and proximity sensors. Geometric modeling and numerical simulation were performed to find critical frame locations on the railway bridge where the instrumentation sensors would be placed. In this study, MONITA® is employed for data acquisition modules. The MONITA® system consists of a combination of hardware and software that functions to retrieve, send, store, and process data. This paper describes the result of the establishment of this method to comprehend the performance of the steel railway bridge structure in real-time via the human-machine interface display dashboard. As a result, the monitoring system can appropriately be used to assess a structural railway bridge in real-time. This study may be helpful to practicing engineers and researchers in future studies of steel railway bridge evaluation. This could be a useful reference for future studies in implementing such systems as the railway bridge early warning system technique in detecting bridge damage.

Theoretical investigation on scattering of ultrasonic Lamb waves at damaged area in quasi-isotropic CFRP laminates based on Mindlin plate theory

ABSTRACT With the wide application of carbon fibre reinforced plastic (CFRP) structure, a structural health monitoring (SHM) system that can easily detect damages in CFRP structures is urgently needed. Since it is possible to detect damages effectively in a large area in CFRP by using the scattering of Lamb waves, in this research, we investigated the scattering of Lamb waves at an impact damaged area in quasi-isotropic (QI) CFRP laminate. By modelling the impact damage as a cylinder area with a uniform stiffness degradation, the scattering waves are calculated based on Mindlin plate theory, which is more precise than Kirchhoff plate theory. It is shown that in the low-frequency region, the calculation results based on Kirchhoff and Mindlin plate theory was similar, but in a higher frequency range, the results differed. The calculation results were compared with the simulation results, suggesting the validity of Mindlin plate theory within a practical frequency range. Moreover, we validated the analytical and simulation results experimentally using a QI CFRP laminate with a hole. We also conducted some parameter study based on the analytical calculation to clarify influential stiffness components. Since scattering behaviour of Lamb waves can be calculated in a fast and easy way using this method, this work is useful for the successful development of a scattering-based SHM system.

Time series data recovery in SHM of large-scale bridges: Leveraging GAN and Bi-LSTM networks

This paper proposes the utilization of a Bidirectional Long Short-Term Memory (Bi-LSTM) network and a Generative Adversarial Network (GAN) model, to recover measured time-series data from Structural Health Monitoring (SHM) systems. In civil engineering, time-series data plays a crucial role in SHM systems. However, unforeseen incidents, such as equipment malfunctions, flawed data collection procedures, or human errors may result in missing data or adversely affect the accuracy of the data collected. To address this challenge, researchers have recently introduced various methods for time series data imputation. Nevertheless, it is evident that many existing approaches are hindered by inherent limitations: (1) neglecting bidirectional temporal correlations; (2) failing to model correlations among variables; (3) generating data that inadequately reflects the distribution of the original dataset, leading to inaccuracies in the recovered data. To overcome these limitations, this study proposes the utilization of Bi-LSTM-GAN for recovering time-series data in the context of SHM. Bi-LSTM demonstrates remarkable proficiency in capturing bidirectional temporal and cross-variable correlations, while GAN is utilized to precisely acquire the distribution of the original data. Additionally, Bi-LSTM significantly bolsters the capacity for long-term data recovery in contrast to a conventional Recurrent Neural Network (RNN). To evaluate the efficacy of this approach, we employ two real-world models: a laboratory-based cable-stayed bridge and an actual three-span continuous bridge. The obtained results compellingly demonstrate that Bi-LSTM-GAN not only achieves data restoration effectively but also yields superior accuracy when compared to conventional GAN model.

Typhoon- and temperature-induced responses of a cable-stayed bridge

Long-span bridges are subjected to wind and temperature actions. Wind action is generally the governing load of long-span bridges in design, while temperature action is also significant. Accurate separation of typhoon- and temperature-induced responses is thus necessary for in-depth investigation of their effects and comprehensive evaluation of structural performance. This paper separates the temperature- and typhoon-induced responses of the Qingzhou Bridge by using a unified global analysis approach. The field-monitored meteorological data and structural responses collected from the structural health monitoring system installed on the bridge are analyzed in detail, with emphasis on the comparison of those during typhoon Higos (Signal No. 9) and a typical sunny day after the typhoon. Results show that the quasi-static variation of displacement and stress responses are higher on a typical sunny day than those during the typhoon period, which is out of intuition. Through the unified analysis, the temperature-induced responses are calculated, and the typhoon-induced responses can be separated. The temperature- and typhoon-induced longitudinal displacement, mid-span deflection, and stress of the girder are compared. The temperature-induced response accounts for a large part of the total quasi-static recording either on a typical sunny day or during the typhoon period, whereas typhoon caused significant dynamic responses. The typhoon-induced quasi-static and dynamic responses are also in good agreement with the wind tunnel test results. This case study demonstrates the effectiveness of the unified global analysis in separating the temperature effect.

Development of data anomaly classification for structural health monitoring based on iterative trimmed loss minimization and human-in-the-loop learning

Huge amounts of data can be generated during long-term monitoring performed by structural health monitoring (SHM) and structural integrity management applications. Monitoring data can be corrupted, and the presence of abnormal data can distort information during signal processing, extract incorrect characteristics during system identification, produce false conclusions during damage detection, and ultimately lead to misjudgment of structural conditions during diagnosis and prognosis. Therefore, developing effective techniques to autonomously detect and classify anomalies becomes necessary and significant. Generally, conventional physics-based strategies can be straightforward, but their performance highly depends on prior knowledge of measurement. Recently, data-driven methods leveraging machine learning (ML) have been used to directly handle the task. This study proposes an ML-based classifier and improves it by incorporating the human-in-the-loop (HITL) learning. The classifier is built on a shallow neural network with high performance to address potential online or real-time applications for long-term monitoring. First, a field monitoring dataset is introduced, and various anomalies are defined to investigate the effectiveness. To further enhance the performance of the proposed classifier, the mislabels in the monitoring dataset are examined, and a correction technique is performed. Additionally, HITL ML is developed to overcome the disadvantages of the conventional correction technique. As a result, the proposed procedure can improve both the classifier and the field dataset, and the proposed classifier can now function as a fundamental component in achieving a continuous and autonomous SHM system.