Long-term Structural Health Monitoring Research Articles

Thermal compensation of monolithic distributed fibre optic sensors: From the lab to the field

Distributed fibre optic sensing (DFOS) is gaining popularity as a diagnostic solution for short-term non-destructive testing (NDT) and long-term structural health monitoring (SHM). However, there are still challenges to be overcome, particularly with regard to long-term measurements under real field conditions, taking into account, among other things, temperature changes. These changes affect strain measurements through both thermal expansion and optical effects, and appropriate correction depends on the internal design of the sensor and the installation methods. Therefore, despite the fact that thermal compensation is one of the key prerequisites for correct data interpretation, there are no universal and clear procedures for DFOS. The lack of sufficient guidelines and proven applications is the main motivation for undertaking studies. The scope and novelty of the presented research lies in 1) the theoretical explanation of the thermal performance of monolithic DFOS sensors compared to the layered sensing cables; 2) the analysis and correction of strain data measured with monolithic sensors placed in a thermal chamber; 3) the verification of the laboratory results and the proposed approach in real field conditions: in a concrete footbridge deck and in a steel underground gas pipeline. All presented measurements were performed with high spatial resolution (mm order) Rayleigh-based interrogators under the control of conventional reference spot thermistors. The research demonstrated the linear thermal response of the monolithic sensors and confirmed their usefulness for distinguishing between length- and stress-dependent strains. Finally, the thermal compensation approach was proposed and verified in real operating conditions.

Machine learning-augmented multi-arrayed fiber bragg grating sensors for enhanced structural health monitoring by discriminating strain and temperature variations

AbstractFiber optic sensors (FOS) in long-term structural health monitoring (SHM) have drawn significant attention due to their pivotal role in detecting defects and measuring structural performance in diverse infrastructures. While using FOS, temperature variation due to environmental factors is still considered one of the major challenges to isolating sensing parameters. To address this issue, we reported a machine learning (ML)-augmented multi-parameter sensing system that enables simultaneous detection of strain and temperature effects based on one single fiber Bragg gratings (FBGs) sensor for SHM. The initial phase entailed designing, fabricating, and characterizing a novel FBG sensor in the laboratory, incorporating a set of four FBGs, each distinguished by distinct Bragg wavelengths. In the next phase, ML algorithms are employed to separate temperature effects from strain variations. As a proof of concept, mechanical loading tests are conducted on the sensor, exposing the FBG portion to various temperature conditions. In the final phase, data collected from a post-tensioned concrete bridge embedded with both strain and temperature FBG sensors are utilized, and the developed ML models are applied to observe real-environment outcomes. Despite the limited feature points of collected FBG spectrums, the developed ML models effectively address cross-sensitivity issues induced by temperature perturbations. The long-term benefit of using FOS is that it will enable a better understanding and utilization of aging infrastructure. This will potentially reduce embodied carbon of infrastructure in the future and assist in the global efforts to achieve Net-Zero.

Acoustic emission monitoring for industrial pressure vessels and infrastructure

Acoustic emission (AE) is a phenomenon that occurs in materials that are exposed to stress. Defects in the material, such as cracks can grow and release energy in the form of a mechanical wave that propagates through the material. With the help of piezoelectric sensors, the mechanical wave is converted into an electrical signal. The signals are recorded by the measuring system and are available for further processing. Acoustic emission as a method that records and processes the incoming signals in real time is therefore very suitable for 24/7 long-term structural health monitoring. With new approaches in data processing, acoustic emission can be moved from the classic periodic test approach to an online monitoring process. The in-service monitoring brings measuring challenges with it, like application on hot surfaces and inside explosion hazard areas. New developments in hardware and software provide tailor-made solutions for a variety of monitoring tasks. The use of artificial intelligence algorithms helps to improve the analysis of measurement data and guarantees safe operation of pressure equipment and infrastructure around-the-clock. Some examples of continuous monitoring are shown on pressure vessels from the industry sector and on infrastructure buildings e.g., steel bridges. Also, a new lean system approach in structural health monitoring with acoustic emission is presented.

Sensitivity analysis of model parameters in a nonlinear model-updating approach for prestressed concrete bridges

Automated monitoring systems in structural health monitoring (SHM) using finite element models can measure system responses of the structure and provide information about behavior and damage scenarios. To describe the reactions and damages of the physical structure, the parameters of the FE-model have to be adjusted accordingly. A common approach therefore is model-updating, an iterative modification of unknown parameters of a finite element model by adapting the response of the model to the measurement results of the physical bridge. The adapted model can be used for assessments and predictions of the structure and provides accurate structural properties to a digital twin. The proposed monitoring concept includes damage detection, based on nonlinear model-updating using Artificial Intelligence (AI) methods and is applied to a prestressed, reinforced concrete bridge based on the observation of static response. For a practical application in long-term SHM, system properties and load values are identified simultaneously by using optimization methods based on Evolutionary Algorithms (EA). Due to the high dimensionality and complexity of the optimization results, Principal Component Analysis (PCA) including autoencoder networks for dimensionality reduction are required to evaluate and visualize the identified structural properties for their reliability. Based on physical 3D nonlinear finite element sensitivity analysis, the influence of damage scenarios and load situations on the bearing behavior of the bridge will be analyzed. The generated data and the results are presented and serve as the basis for the reliability analysis and evaluating the proposed concept. Furthermore, by comparing the measurements of the parameterized investigated models, conclusions about the behavior of the structure and the sensor placement can be obtained.

Application of regression and remote sensing technology for determining sufficiency of contact-based sensors in long-term SHM of civil structures

Long-span bridges are huge, complex, and vital civil engineering structures for every society. Due to the critical importance of such structures, structural health monitoring (SHM) systems utilizing both contact and non-contact sensor platforms are often considered to measure influential parameters, such as environmental/operational factors and various structural responses. In some circumstances, such as bridge locations, services, weather conditions, harsh environments, and budget constraints, it may not be practical or necessary to utilize all possible sensor systems and measure all parameters, especially environmental/operational (E/O) factors. To devise and implement an affordable SHM program for large-scale civil structures, it is necessary to develop more efficient sensing systems compared to state-of-the-art ones. Against this backdrop, this paper proposes a new methodology for verifying the sufficiency of contact-based E/O sensors installed in long-span bridges using spaceborne remote sensing and regression modeling. The main premise of the proposed methodology is that structural responses obtained from certain remote sensing products enable us to assess the sufficiency of contact sensors and the impacts of both measured and unmeasured E/O conditions. Utilizing structural displacement responses from remote sensing and measured E/O data from contact-based sensors, a supervised regression model using a feedforward artificial neural network is developed to reconstruct or predict displacement responses and to determine the regression accuracy using the R-squared measure. When the accuracy rate is high, one can infer that the contact-based E/O sensors are sufficient; otherwise, it may be essential to install additional E/O sensors and apply the proposed methodology with new information. Real-world long-span bridges are examined to validate the proposed methodology, using displacement responses and recorded temperature data from contact-based thermocouples. The results demonstrate that the methodology offers an effective but affordable system for long-term SHM programs.

Enhancing data sparsity in spectral signals using wavelet decomposition for improved compression and storage efficiency

Wavelet decomposition (WD) is integrated into the Compressive Sensing (CS) model to enhance data sparsity. This approach aims to ensure efficiency and quality in the received data after compression and reconstruction processes. The proposed WD-CS model is developed for reflected spectra signals from Fiber Bragg Gratings-based extensometers, which were subjected to induced deflections simulating the underground soil movement. WD decomposes the input signal before compressive measurement, followed by transferring and storing the compressed data in the cloud. The spectral data were reconstructed using Orthogonal Matching Pursuit (OMP) followed by wavelet reconstruction. The impact of wavelet decomposition on the quality of compression and reconstruction is assessed and compared against that of the standard CS model. The findings indicate that the WD-CS model can improve data sparsity by a factor of three and compressibility by a factor of ten without degenerating the reconstructed data quality. The error in the Bragg wavelength shift of the reconstructed spectra is minimal extracted using Pseudo-high Resolution Interrogation (PHRI) method. The proposed WD-CS model is useful in improving data compression for FBG spectra as well as storage efficiency, which make it potentially applicable in FBG-based sensor networks for long-term structural health monitoring applications.

Physical data-driven modeling of deformation mechanism constraints on earth-rock dams based on deep feature knowledge distillation and finite element method

Constructing an interpretable model for the long-term deformation Structural Health Monitoring (SHM) of earth-rock dams is of great significance for improving the safety state evaluation and monitoring effect. In this paper, a physics-data-driven model for the deformation SHM of earth-rock dams is proposed based on deep mechanism knowledge distillation. Firstly, the deterministic model is established based on the Finite Element Model (FEM) and outputs the hydraulic load component curve and aging component curve. Then a regression prediction model (HTSGAN) between influencing factors and deformation measurements at multiple measurement points is established based on the Graph Convolutional Network (GCN) and attention mechanism. Finally, the Teacher-Hydraulic-Time-Seepage Graph Attention Networks (T-HTSGAN) model is established based on the feature-based multi-teacher knowledge distillation using the knowledge of hydraulic loading physics and soil-rock creep physics of the FEM for mechanism constraints. The model effectively solves the problems of poor model interpretability and lack of physics knowledge constraints in previous earth-rock dam SHM models. The research results are applied to a project of a 185.5-meter-high concrete-faced rockfill dam, and the predictive performance of the model is more effective and stable through the comparison of six baseline models. The comparative analysis of the component curves proves the effectiveness of the proposed knowledge distillation method for mechanism constraints and improves the interpretability of the neural network model. Therefore, the model is more suitable for engineering applications.

Simulation and prediction of vortex-induced vibration of a long suspension bridge using SHM-based digital twin technology

Although wind tunnel tests have already become a design basis for improving the stability of long-span bridges under the action of wind loads, vortex-induced vibration (VIV) events of in-service long-span bridges have still been frequently reported in recent years. The reasons behind this could be attributed to the limitations and uncertainties involved in wind tunnel tests as well as the changes and degradations of in-service bridges. In consideration that most long-span bridges have now been equipped with long-term structural health monitoring (SHM) systems and that digital twins could provide a new solution for simulating and predicting the reality, this study aims at developing a digital twin for VIV of a long suspension bridge to simulate and predict its VIV. The design document-based finite element (FE) model of the bridge is first updated using the measured dynamic characteristics. The numerical model for VIV of the bridge is then established using the vortex-induced force (VIF) model established based on wind tunnel test results. The numerical model together with the VIF model are finally updated against the measured vortex-induced responses (VIR) to produce a digital twin for VIV of the bridge. The relationships between the parameters in the VIF model and wind characteristics are further investigated to enable the digital twin to predict future VIV events. The accuracy of the digital twin for predicting the future VIV and the influence of the VIF parameters obtained from wind tunnel tests on the prediction accuracy both are confirmed through comparisons between the predicted and measured results.

Temperature Effect Separation of Structure Responses from Monitoring Data Using an Adaptive Bandwidth Filter Algorithm.

Temperature is one of the most important factors significantly affecting damage detection performance in civil engineering. A new method called the Adaptive Bandwidth Filter Algorithm (ABFA) is proposed in this paper to separate the temperature effect from quasi-static long-term structural health monitoring data. The Adaptive Bandwidth Filter Algorithm (ABFA) is referred to as an algorithm of automatically adjusting the frequency bandwidth filter via the particle swarm optimization (PSO) algorithm. Considering the obvious multi-scale feature of the collected data of civil structure, the acquired time series are divided into different time scales (for example, day, month, year, etc.), and these scales in the frequency domain correspond to the center frequencies of the adaptive bandwidth filter. The temperature effect on structure responses across different time scales is thereafter explored by adaptively adjusting the frequency bandwidth of the filter based on the known center frequencies of different scales. The relationship between the temperature and the structure responses is established through statistical regression facilitated by sufficient in situ monitoring data. Simulation and experiment results show the very promising performance of the proposed algorithm and decouple the temperature effect accurately from the contaminated data; thus an enhanced capability of damage detection is achieved.

Experimental study on strain of SFRC tunnel lining segments using a comprehensive embedded optical fiber sensing system

In comparison to current techniques, optical fiber sensors (OFS) for structural health monitoring (SHM) of steel fibre reinforced concrete (SFRC) tunnel lining segments is an emerging technology that could enhance tunnel safety and reliability. However, the utilizing many measurement techniques in a single OFS technology has pros and cons, making it difficult to meet the demands for a comprehensive and reliable assessment for long-term monitoring inside tunnels. We present comprehensive OFS system for strain monitoring inside concrete tunnel lining segments. The system involves distributed optical fiber sensing (DOFS) cable, fiber Bragg grating (FBG) sensors, and chirped fiber Bragg grating (CFBG) sensors. The proposed system is particularly useful for high-risk or difficult-to-access locations, such as inside tunnel structures. We provide the deployment design after introducing the sensing principle of the system. To validate its effectiveness and reliability, we conduct a scaled-down laboratory experiment to evaluate the strain behavior. The proposed comprehensive OFS system accurately captures the strain evolution over time in various stages of tunnel lining segments, including casting, curing, loading, and even after failure. This system demonstrates high-resolution, and reliable monitoring of internal strain in tunnel lining segments, making it suitable for practical application in full-scale and long-term SHM during the construction and operation stages of shield tunnels with connection expansion for segments.

A real-time quantitative acceleration monitoring method based on triboelectric nanogenerator for bridge cable vibration

Real-time monitoring of vibration acceleration of civil infrastructure is imperative for effective management and safe operation of structures. Although the triboelectric nanogenerator (TENG) shows potential for self-powered sensing, it faces challenges in correlating limited experimental electrical amplitudes to structural responses, thereby hindering comprehensive performance analysis of civil infrastructure. Herein, a self-driven acceleration TENG sensor (A-TENG) is designed and manufactured, comprising an outer shell and an inner mass-spring-damper system. By establishing a sensing model based on vibration theory and the TENG mechanism, the electrical signals generated by the sensors can be correlated with structural acceleration, enabling self-driven real-time quantitative characterization. Indoor and on-site experiments demonstrate that the A-TENG sensor is capable of continuously monitoring the acceleration profile with excellent consistency compared to commercial sensors. The non-contact free-standing sliding mode design and ultra-lightweight construction of the A-TENG sensor (∼8 g) enhance its start-up sensitivity (∼0.1 m/s2), long-term stability (∼30,000 loading cycles) while minimizing mass interference. The proposed sensing theory renders a novel approach to offering complete time-domain information, which is vital for the precise analysis of structural behavior. This work facilitates understanding of self-driven sensors utilizing TENG technology and provides a useful tool for long-term real-time quantitative structural health monitoring.

A Review of Approaches for Mitigating Effects from Variable Operational Environments on Piezoelectric Transducers for Long-Term Structural Health Monitoring.

Extending the service life of ageing infrastructure, transportation structures, and processing and manufacturing plants in an era of limited resources has spurred extensive research and development in structural health monitoring systems and their integration. Even though piezoelectric transducers are not the only sensor technology for SHM, they are widely used for data acquisition from, e.g., wave-based or vibrational non-destructive test methods such as ultrasonic guided waves, acoustic emission, electromechanical impedance, vibration monitoring or modal analysis, but also provide electric power via local energy harvesting for equipment operation. Operational environments include mechanical loads, e.g., stress induced deformations and vibrations, but also stochastic events, such as impact of foreign objects, temperature and humidity changes (e.g., daily and seasonal or process-dependent), and electromagnetic interference. All operator actions, correct or erroneous, as well as unintentional interference by unauthorized people, vandalism, or even cyber-attacks, may affect the performance of the transducers. In nuclear power plants, as well as in aerospace, structures and health monitoring systems are exposed to high-energy electromagnetic or particle radiation or (micro-)meteorite impact. Even if environmental effects are not detrimental for the transducers, they may induce large amounts of non-relevant signals, i.e., coming from sources not related to changes in structural integrity. Selected issues discussed comprise the durability of piezoelectric transducers, and of their coupling and mounting, but also detection and elimination of non-relevant signals and signal de-noising. For long-term service, developing concepts for maintenance and repair, or designing robust or redundant SHM systems, are of importance for the reliable long-term operation of transducers for structural health monitoring.

Structural Condition Assessment and Temperature Effect Analysis of Cable–Pylon Anchorage Zone Using Long-Term SHM Data

To study the temperature effect in the anchorage zone of a long-span cable-stayed bridge, a wavelet multiresolution analysis and layered stripping method were used in this paper. Based on long-term structural health monitoring data, the signals were decomposed and reconstructed at multiple time scales, confirming temperature to be the main factor causing the stress change in the anchorage zone. The results of structural condition during operation showed that the general compressive stress level of the anchorage zone was low. However, the tensile stress level of the sidewall was high, which led to a severe concrete cracking. Excluding the influence of the seasonal temperature, the compressive stress increased slightly, the horizontal tensile stress in the upstream inner pylon wall increased, and the crack width increased gradually. By analysing the daily temperature effect on the upstream and downstream pylon walls, the regression model proposed in this study can be used to predict the daily temperature effect at any time in the diurnal cycle. The accuracy of the model is reliable within 6 days, but for the location of severe cracks, the monitoring data should be updated in real time to ensure the precision.

Elimination of Thermal Effects from Limited Structural Displacements Based on Remote Sensing by Machine Learning Techniques

Confounding variability caused by environmental and/or operational conditions is a big challenge in the structural health monitoring (SHM) of large-scale civil structures. The elimination of such variability is of paramount importance in avoiding economic and human losses. Machine learning-aided data normalization provides a good solution to this challenge. Despite proper studies on data normalization using structural responses/features acquired from contact-based sensors, this issue has not been explored properly via new features, such as displacement responses from remote sensing products, including synthetic aperture radar (SAR) images. Hence, the main aim of this work was to eliminate environmental variability, particularly thermal effects, from different and limited structural displacements retrieved from a few SAR images related to long-term health monitoring programs of long-span bridges. For this purpose, we conducted a comprehensive comparative study to investigate two supervised and two unsupervised data normalization algorithms. The supervised algorithms were based on Gaussian process regression (GPR) and support vector regression (SVR), for which temperature records acquired from contact temperature sensors and structural displacements retrieved from spaceborne remote sensors produce univariate predictor (input) and response (output) data for the regression problem. For the unsupervised algorithms, this paper employed principal component analysis (PCA) and proposed a deep autoencoder (DAE), both of which conform with unsupervised reconstruction-based data normalization. In contrast to the GPR- and SVR-based data normalization algorithms, both the PCA and DAE methods only consider the SAR-based displacement (output) data without any requirement of the environmental and/or operational (input) data. Limited displacement sets of long-span bridges from a few SAR images of Sentinel-1A, related to long-term SHM programs, were considered to assess the aforementioned techniques. Results demonstrate that the proposed DAE-aided data normalization is the best approach to remove thermal effects and other unmeasured environmental and/or operational variability.

Statistical Analyses of the Non-Uniform Longitudinal Temperature Distribution in Steel Box Girder Bridge

The frequently conventional assumption that bridge temperature is uniformly distributed on long-span bridges could lead to uncertainty when analyzing temperature effects. This study investigated the surface temperature of steel box girders on a long-span suspension bridge, emphasizing the distribution characteristics in the longitudinal (spanwise) direction. The girder surface temperature distribution was monitored using the long-term structural health monitoring system (SHMS). First, the probability density functions (PDF) of the girder surface temperature were analyzed. The results showed that the PDFs had bimodal characteristics and could be well-fitted using the weighted superposition of two normal distributions. Meanwhile, there was an obvious difference between the PDFs of the measuring points at different longitudinal sections of the bridge, which is inconsistent with the assumption that the temperature was uniformly distributed in the longitudinal direction. Subsequently, the longitudinal distributions of the girder surface temperature were statistically analyzed, and polynomial functions were introduced to fit the distribution curves along the left and right sides of the mid-span. A correlation analysis was then performed, highlighting the variability in temperature in the longitudinal direction. Additionally, the longitudinal temperature distribution pattern could be summarized as (i) the highest in the mid-span, the lowest in the tower, and increasing along the side span; (ii) there were also significant differences between the left and right sides of the mid-span. Finally, the time- and space- distributions of the temperature were studied, and a contour map was displayed. The results showed that the girder surface temperature had significant three-dimensional spatial characteristics and was not only non-uniformly distributed in space but also in time. This work is useful for a more accurate analysis of temperature effects on long-span bridges.

Joint parameter-input estimation for digital twinning of the Block Island wind turbine using output-only measurements

This paper presents a recursive Bayesian inference framework for digital twinning of an offshore wind turbine (OWT) in the Block Island Wind Farm (BIWF), the first commercial offshore wind farm in the U.S. with jacket substructure. The framework employs a window-based extended Kalman filter (EKF) to jointly estimate the dynamic input loads and unknown model parameters of the finite element (FE) model of the turbine using sparse output-only measurements. The estimation of input loads on the OWT is critical for fatigue life estimation, foundation monitoring and control strategy. In the proposed joint estimation algorithm, unknown input time histories are divided into overlapping windows and the current window of inputs is concatenated with uncertain model parameters to form an augmented state vector. To account for the uncertainty about wind direction and misalignment between wind direction and the turbine yaw angle, two independent horizontal wind load time histories in X and Y directions are estimated at the nacelle level. A numerical validation study is first performed in which wind loads of the OWT are simulated using the multi-physics platform FAST, and structural vibration responses are generated using the FE model in OpenSees. The window-based EKF is implemented using the simulated measurements, and the estimations of structural stiffness as the updating model parameter and input loads are observed to have high accuracy. The proposed algorithm is then validated using in-situ measurements on one of the OWT in BIWF. To investigate the effectiveness and robustness of the method under different environmental and operational conditions, four cases are considered in which the turbine is operating at the rated rotor speed (region 3 of power generation), below the rated rotor speed (region 2), idling rotor state (region 1 or no power), and region 4 beyond cut-out wind speed. Accurate predictions of acceleration and strain data are obtained using the proposed algorithm, and the estimations of model parameter are consistent and close to their nominal value under different conditions. These results from numerical and experimental studies validate the proposed window-based EKF for joint parameter-input estimation and digital twinning for long-term structural health monitoring of the OWT.

A methodology for long-term offshore structural health monitoring using stand-alone GNSS: case study in the Gulf of Mexico

This article presents a robust methodology for long-term offshore structural health monitoring (SHM) using the Global Navigation Satellite Systems (GNSS). The methodology relies on recently developed regional reference frames and single-receiver phase-ambiguity-fixed Precise Point Positioning techniques. The stable Gulf of Mexico Reference Frame 2020 (GOM20) provides a robust and consistent reference system for long-term offshore SHM in the Gulf of Mexico (GOM). Continuous GNSS observations (DEV1, 2010–2020) on a fixed platform in the Eugene Island 330 oil field are used to illustrate the methodology. The platform was installed in 1982 in 82-m water about 130 km away from the Mississippi Delta coastline. The major monitoring items include horizontal movements, seafloor subsidence, structure submergence, and seasonal oscillations. The stand-alone GNSS monitoring achieves 3- to 4-mm root-mean-square accuracy in the horizontal direction and 7 mm in the vertical direction for daily positions in the GOM region. According to this study, the GNSS antenna (DEV1) has moved 6 cm toward the northeast with respect to GOM20 since 2010; the ongoing structure submergence rate in the Eugene Island 330 oil field area is approximately 15 mm/year, a combination of seafloor subsidence (12 mm/year) and sea-level rise (2.6 mm/year) with respect to GOM20. The submergence in the future 40 years (2021–2060) would be greater than 0.6 m, likely between 0.8 and 1.0 m, but is unlikely to exceed 1.3 m. The peak-to-trough amplitudes of the seasonal movements at the top of the platform are below 5 mm in all three directions, comparable with the seasonal movements recorded by onshore GNSS in the Louisiana coastal region. The methodology introduced in this article can be applied to SHM in other offshore regions where stable regional reference frames are available.

Reconstruction of long-term strain data for structural health monitoring with a hybrid deep-learning and autoregressive model considering thermal effects

Complete data are essential for implementing reliable structural health monitoring (SHM); however, data loss due to equipment malfunction or other potential factors is unavoidable. Therefore, it is necessary to develop reliable structural-response-reconstruction methods. However, previous strain reconstruction methods have three shortcomings that lead to relatively low accuracy: 1) they typically do not use modules with better ability to capture the long- and short-term variation patterns of time series, such as the bidirectional gated recurrent unit (BiGRU) and convolutional neural network (CNN); 2) they do not simultaneously consider the spatiotemporal correlation among sensors and the strong correlation between temperature and strain, each of which has been demonstrated to contribute to improving the reconstruction accuracy separately; and 3) they do not carefully consider the linear and nonlinear correlations among SHM data. To address these problems, we proposed a strain reconstruction method that combines a nonlinear deep-learning (DL) component with a linear autoregressive (AR) component. The method also utilizes BiGRU and CNN in the DL component to capture the long- and short-term patterns of the SHM data better, as well as the two above-mentioned data correlations. To fully validate the performance of the proposed method, the long-term SHM data of a long-span steel box girder suspension bridge were utilized for validation. The results show that the hybrid DL and AR model can reconstruct the long- and short-term missing data with higher accuracy under different scenarios than previous models, such as the CNN.

Restoration of electromechanical admittance signature via solving constrained optimization problems for concrete structural damage identification

Effective restoration of lossy data is prerequisite to guarantee the reliability of early warning information for damage diagnosis, considering large amounts of sensor data to be collected, transmitted and stored in long-term structural health monitoring (SHM) process. In this study, a compressive sampling matching pursuit (CoSaMP) algorithm was developed for solving the restoration problem of electromechanical admittance (EMA, inverse of impedance) signatures-based damage identification. Observed vectors through a random matrix projection were collected as a substitute of the EMA signatures used in conventional method, and EMA signature restorations from incomplete observed vectors were transformed into solving constrained optimization problems. Then the CoSaMP algorithm was utilized to recover EMA signatures with loss in observed vectors. Validation of the approach was conducted by a series of tests on artificial crack identification for a standardized concrete cube under laboratory conditions, which was compared with that using iterative shrinkage-thresholding algorithm (ISTA)-based algorithm. Additionally, impacts of different loss ratios on restoration accuracy were discussed. The proposed approach showed promising availability for damage identification using EMA technique encountered with lossy data.

A data-driven sensor placement strategy for reconstruction of mode shapes by using recurrent Gaussian process regression

Current Optimal Sensor Placement (OSP) strategies for bridges mostly rely on data from a finite element model rather than from the real structure due to high cost in placing massive sensors for data collection. For large-scale bridges, however, it is difficult to formulate a precise model and thus the OSP strategies building upon a finite element model inevitably suffer from modelling errors. Besides, the finite element model cannot account for real measurement noise. Premised on the fact that it is not expensive to make in-situ trial measurements with a few sensors on a target bridge before deploying a structural health monitoring (SHM) system on it, a data-driven OSP strategy is proposed in this study which aims at accurately reconstructing mode shapes (to facilitate vibration-based structural damage detection) by using only a few vibration sensors to be included in the SHM system. The proposed OSP strategy is also applicable for the upgrade of a long-term SHM system currently deployed on a bridge, by using historical data collected from the current SHM system. To precisely reconstruct mode shapes, a two-stage OSP strategy in terms of Recurrent Gaussian Process Regression (RGPR) is developed, and its performance is validated on a simulation model and a real bridge. In the first stage, the greedy algorithm is leveraged to temporarily deploy sensors on the structure and train accurate RGPR models using the collected data, which are used to afford spatially complete mode shape data for optimization later. Starting from a few sensors temporarily deployed on the bridge, a one-by-one sensor adding procedure is performed to configure increasing sensors until the target is achieved. In the second stage, Cuckoo Search (CS) algorithm is pursued to obtain the globally optimal sensor placement solution, from which the temporarily deployed sensors can be re-configured to the optimum positions. Both the best sensor quantity and positions are obtained by the proposed OSP strategy.