Approach For Structural Damage Detection Research Articles

A data fusion-based approach for structural damage detection with distributed long-gauge strain measurements

Distributed long gauge strain sensing technology has solved the problem of difficult identification of local damage in traditional ‘point’ monitoring, and has received extensive attention in the field of structural damage identification. Owing to the inevitable presence of measurement noise and environmental factors in the macro strain response measurement, a single damage index has also underlined some drawbacks generally arising when multiple damages occur, or errors affect the identified dynamic properties of the systems. To address these challenges, this paper proposes a data fusion method based on the Dempster–Shafer evidence theory, relying on distributed strain sensing technology. The identification results of the modal macro strain-based index and quasi-static macro strain energy-based damage index are fused to make a comprehensive decision on structural damage location. Damage identification studies are conducted on different types of structures under impact loads and random wind loads to verify the effectiveness and accuracy of the proposed data fusion method in the case of single and multiple damage conditions. The results show that the proposed data fusion method can accurately identify the damage location and effectively reduce misjudgment on undamaged locations; it has potential application value in practical structural health monitoring.

Image-based machine learning approach for structural damage detection through wavelet transforms

Structural integrity is essential for safety in infrastructure, as it can help prevent catastrophic failures and financial losses. The significance of vibration-based damage detection has grown substantially in fields such as civil and mechanical engineering. Concurrently, the advancements in computational capacities have facilitated the integration of machine learning into damage detection processes through post-processing algorithms. Nevertheless, these require extensive data from structure-affixed sensors, raising computational requirements. In an effort to address this challenge, we propose a novel approach utilizing a pre-trained convolutional neural network (CNN) based on images to identify and assess structural damage. This method involves employing wavelet transform and scalograms to convert numerical acceleration data into image data, preserving spatial and temporal information more effectively compared to conventional Fourier transform frequency analysis. Six acceleration data channels are collected from carefully chosen nodes on a mini bridge model and a corresponding finite element bridge model, to train the CNN. The efficiency of training is further enhanced by applying transfer machine learning through two pre-trained CNNs, namely Alexnet and Resnet. We evaluate our method using different damage scenarios, and both Alexnet and Resnet show prediction accuracies over 90%.

Cross-correlation difference matrix based structural damage detection approach for building structures

Cross-correlation difference matrix based structural damage detection approach for building structures

Output-only structural damage identification based on Q-learning hybrid evolutionary algorithm and response reconstruction technique

Various structural damage identification methods have been developed and employed, while the absence of input excitation measurements may pose a huge challenge in their application since the input forces such as seismic load, traffic load, wind load, are not directly measurable. To address this issue, in the present paper, a novel output-only structural damage detection approach based on Q-learning hybrid evolutionary algorithm (QHEA) and response reconstruction technique is presented. On the one hand, the external excitation and structural acceleration responses are reconstructed with the aid of response reconstruction and Tikhonov regularization techniques in time domain. Structural damage identification can be formulated as an optimization-based inverse problem. On the other hand, a new optimization framework QHEA integrating Jaya algorithm, differential evolution, Q-learning algorithm is developed as search tool. The unknown structural parameters and unmeasured input force are iteratively updated by using two different measurement sets until the reconstructed acceleration responses agree well with the measured responses. Numerical examples involving a cantilever beam structure under single excitation and a simply-supported 51-bar truss structure under multiple excitations, as well as an experimental five-floor steel frame structure in the laboratory are carried out to validate the effectiveness of the proposed method. The final results demonstrate that the proposed method can accurately detect damage locations and quantify damage extents without the information of input excitation. In addition, the superiority of QHEA over other heuristic algorithms, the uncertainties of measurement noise and modeling errors on damage identification results are further examined.

Structural damage detection based on modal strain energy assurance criterion using adaptive region shrinkage assisted IGOA

The efficiency in high-dimension optimization, premature convergence and noise robustness are common challenges that restrict the application of swarm-based algorithms in structural damage detection (SDD). In order to overcome these limitations, an improved grasshopper optimization algorithm (IGOA) based SDD approach assisted with adaptive region shrinkage strategies is proposed using modal strain energy assurance criterion. Firstly, the effectiveness of GOA in handling SDD is investigated, and an improved version is subsequently introduced with two adaptive region shrinkage strategies: adaptive Lévy flight mechanism and elite opposition-based learning, aiming to achieve more accurate and stable SDD results. Additionally, a novel objective function is defined, combining the frequency change ratio (FCR) and modal strain energy assurance criterion (MSEAC). To assess the performance of the proposed algorithm, a comparative analysis is conducted with four other selected swarm intelligent algorithms and GOAs with individual modification using four CEC benchmark functions. The results demonstrate that the proposed algorithm achieves improved convergence rate and accuracy. Furthermore, the effectiveness and efficiency of the proposed algorithm in SDD are validated through two numerical simulations and an experimental test. The SDD results obtained from both numerical simulations and experimental tests confirm the accuracy and robustness of the proposed method.

A Novel Approach for Structural Damage Detection Using Multi-Headed Stacked Deep Ensemble Learning

A Novel Approach for Structural Damage Detection Using Multi-Headed Stacked Deep Ensemble Learning

Modified reconstruction algorithm for probabilistic inspection of damage based on damaged virtual sensing paths

Ultrasonic guided wave is an effective approach for structural damage detection, among which the reconstruction algorithm for probabilistic inspection of damage (RAPID) is widely used. For the problem that the localization accuracy of traditional RAPID is seriously affected by the damage shape factor β, this paper proposes a modified RAPID based on damaged virtual sensing paths (DVSPs). The DVSP is determined by the time of flight (TOF) or damage index (DI) and is defined as a line of passing damage from a real actuator to a virtual sensor. Using DVSPs instead of real paths for damage localization can effectively avoid the β selection dilemma. Experiments were conducted on an aluminum plate and composite laminates. With the change of β, the average localization error does not exceed 9 mm, and the variation is less than 2 mm, while the error variance of the traditional RAPID is more than 35 mm.

Semi-supervised vibration-based structural health monitoring via deep graph learning and contrastive learning

Civil structures are vital and expensive assets that are regularly inspected and monitored, resulting in a large volume of measured data. Thus, labeling structural health monitoring-related data is a tedious, time-consuming, and tricky process. In order to alleviate the dependence on labeled data, this study investigates a semi-supervised structural damage detection approach, named semi-SDD, for evaluating structures’ health status based on vibration data from multiple sensors mounted across the structure. First, a deep graph neural network is designed to combine spatial information of sensor locations with time-varying vibration data into latent representations. Next, the latent representation is empowered via contrastive learning before going through a multiple-layer perceptron layer to identify the structure’s state. The applicability and performance of the proposed framework are consistently validated through three examples, including both numerically generated data and experimentally measured data (from the literature). Furthermore, additional comparison, parametric and robustness studies are carried out to gain helpful insight into the proposed method’s performance.

Towards a deep learning-based unified approach for structural damage detection, localisation and quantification

Ultrasonic guided waves have been extensively employed for characterising structural damage thanks to their sensitivity to defects. Although they are easy to excite and acquire, heavy processing is often required to extract single-valued indicators of damage presence, or damage indices, from the acquired signals. Traditionally, damage indices have been elaborated through tomographic algorithms to generate damage probability maps, even though limitations affect the performance of such approach. Recently, the potentialities of machine learning have been leveraged to improve the accuracy of frameworks processing guided waves for damage diagnosis. However, most methods still require extracting damage indices from the acquired signals, which may bring to loss of diagnostic information and reduced accuracy. Furthermore, damage position and extent are usually roughly estimated through classification, while regression should be employed instead. In this context, this work aims (i) to test the capabilities of different supervised machine learning algorithms to localise and quantify damage through regression and (ii) to carry out a critical discussion about possible limitations of using damage indices instead of unprocessed signals. Results are compared to identify which algorithm performs better and if machine learning can improve the accuracy of damage diagnosis compared to traditional imaging methods. An experimentally validated numerical case study was used to test the capabilities of the proposed machine learning-based framework and to bring evidence of the accuracy of the algorithms involved to characterise damage with properties not seen during training.

Initial structural damage detection approach via FE-based data augmentation and class activation map

Damage is generally initiated locally and spread to the entire structure. To avoid the destruction of the entire structure, it is crucial to detect and act on damage at an early stage through the real-time monitoring of the entire structure. However, the attachment of the many sensors to obtain sufficient detection resolution could change the structural dynamic characteristics of the structure. To compensate for these shortcomings, research has been conducted on digital image correlation (DIC) as a non-contact method of displacement/strain measurement. In addition, the real-time monitoring of a structure using DIC equipment is relatively straightforward. The final goal of this study is to predict the location of damage using the displacement of the structure surface which can be via DIC. This paper introduces a method for monitoring damage locations using a class activation map (CAM) network. The feasibility of the proposed process using the finite element method for an example considering the experimental situation was confirmed. To generate training data, the finite element method was used to obtain the displacement and strain of a target structure. Herein, sub-structuring approach with data augmentation using Gaussian integration point interpolation were employed to obtain the benign performance of the proposed approach. Thus, the proposed CAM network could classify the presence or absence of damage by considering strain fields. Moreover, the relevant result of the CAM network is a CAM image, which indicates the location of the damage. Finally, this CAM network was applied to a tensile specimen example and show good performance in the classification and detection of damage locations.

A Novel Structural Damage Detection Method via Multisensor Spatial–Temporal Graph-Based Features and Deep Graph Convolutional Network

Structural damage detection plays an important part in structural health monitoring for engineering structures. However, monitored signals are easily polluted by noise and the damaged data are difficult to obtain. In this work, a novel structural damage detection approach using multisensor spatial–temporal graph-based features and deep graph convolutional networks (DGCNs) is presented. The spatial–temporal graph is constructed by the graph theory based on continuous wavelet transform (CWT) of vibration signals. Then, the multisensor spatial–temporal graph-based feature is extracted based on the Laplacian matrix derived from the spatial–temporal graph of the multisensor data. To overcome the limitation of small data size which obstructed the use of the artificial neural network and convolutional neural network, a DGCN is utilized to classify the damage type of the monitored structure. The extracted multisensor spatial–temporal graph-based feature vector is used to represent the node of the global graph as the input of the DGCN. The node with the same condition of the structure can be classified by using the well-trained DGCN. Experiments of the International Association for Structural Control (IASC)-American Society of Civil Engineers (ASCE) SHM benchmark structure and Qatar steel frame structure in the laboratory are performed to verify the effectiveness of the proposed approach. The experimental results show that the DGCN method can be used to detect structural damage by learning from the constructed global graphs. Comparative experiments demonstrate that the proposed approach performs better than the conventional approach, especially for the limited dataset and noise-polluted case.

Vibration-based structural damage detection using 1-D convolutional neural network and transfer learning

This paper presents a novel vibration-based structural damage detection approach by using a one-dimensional convolutional neural network (1-D CNN) and transfer learning (TL). The CNN can effectively extract structural damage information from the vibration signals. However, the CNN training needs enough samples, while some damage samples (scenarios) obtained from real structures are limited, which will compromise the CNN ability to detect structural damage. As a solution, the numerical models have potential to provide sufficient CNN training samples; meanwhile, the state-of-the-art TL technique can significantly shorten the network training time and improve the accuracy. Therefore, this paper proposes a new method to detect the damage of a bridge model. The 1-D CNN is firstly trained with the samples of the single damage scenarios of the numerical bridge model. And then it is transferred to the complex scenarios of multi-damage (double or triple simultaneously), random size structures, and experimental model. The results demonstrate that: with the TL, the accuracy of damage detection is increased by about 47% at most, and the convergence speed is increased by at least 50%; in particular, the TL can inhibit over-fitting, and for the real bridge case, the accuracy also increased by 44.4%. It is demonstrated that: the TL can effectively improve the damage detection accuracy and convergence effect, and the application of this method to the random size structures also proves its generalization.

A Two-Stage Approach for Damage Diagnosis of Structures Based on a Fully Distributed Strain Mode under Multigain Feedback Control

The application of distributed fiber sensing technology in civil engineering has been developed to obtain more accurate and reliable information for structural health monitoring (SHM). With this sensing technique, high-density strain data are provided to benefit the stability and robustness in a closed-loop damage detection method which has not yet been investigated. To address this concern, a two-stage approach for structural damage detection combining a modal strain energy-based index (MSEBI) method with a hybrid artificial neural network (ANN) and particle swarm optimization (PSO) algorithm is proposed. In this study, the fully distributed strain measurement is taken advantage of, and a strain-based, closed-loop system with multiple gains aggregated for damage sensitivity enhancement is established, by which high-precision damage location and quantification can be realized through the proposed two-stage method. For the first step, the closed-loop strain mode shapes are used to construct the MSEBI for damage localization. For the second step, we adopt the PSO algorithm to train the parameters (weights and biases) of the neural network in order to reduce the difference between the real and expected outputs and then use the trained network for quantifying the damage extent. Furthermore, validation is completed by contemplating a two-span, bridge-like structure.

A two-stage approach for structural damage detection using a damage localization indicator vector and cluster particle swarm optimization

A two-stage approach based on the finite element model is proposed for structural damage detection. In the first stage, the damage identification problem is transformed into an -minimization issue related to the natural-frequencies-based sensitivity matrix, which can be quickly solved using the alternating directional multiplication method. Based on this, a damage localization indicator vector (DLIV) is proposed for dimensionality reduction. In the second stage, a particle swarm optimization (PSO) algorithm with four-cluster topology, namely Cluster PSO, is employed to identify the location and severity of the actual damage after dimensionality reduction. Therefore, the proposed two-stage approach can be denoted as the DLIV-based Cluster PSO. In the numerical simulations, the performance of the proposed DLIV-based Cluster PSO is evaluated for single and multiple damage detection of a cantilever beam. The simulation results demonstrate that the proposed DLIV-based Cluster PSO approach provides faster convergence, less computational time and better noise tolerance.

Structural damage detection via phase space based manifold learning under changing environmental and operational conditions

The feasibility and performance of existing vibration-based damage detection methods to real world civil engineering structures are inevitably affected by the varying environmental and operational conditions. Reliable damage detection methods with damage features that are sensitive to structural condition change but robust to environmental and loading effects are desirable for practical applications. This paper proposes a novel structural damage detection approach based on manifold learning for the effective condition assessment of real-world structures under environmental and operational conditions. The phase space representation of the vibration characteristics is reconstructed using the identified natural frequencies of structures. Then, the intrinsic nonlinear manifold between the environmental variables and natural frequencies in the high dimensional phase space is projected to a low-dimensional representation via manifold learning. The Gaussian process regression technique is introduced to extract reliable damage index from the learned manifold structure. The effectiveness and superiority of the proposed approach are demonstrated by two real-world engineering structures, that is, the Dowling Hall Footbridge and Z24 bridge. Damage detection results obtained from the proposed approach are compared with those from the current state-of-the-art Kernel PCA method, which is a representative nonlinear dimensionality reduction method to alleviate the environmental effects. The results demonstrate that the proposed approach is sensitive to structural damage but insensitive to changes in environmental and operational conditions. More importantly, the nonlinear environmental effects can be efficiently characterized by the proposed approach, using only partial datasets with environmental variations in the training datasets.

Structural damage detection by integrating robust PCA and classical PCA for handling environmental variations and imperfect measurement data

This paper proposes a vibration-based structural damage detection approach considering the effects of uncertainties, including environmental variations and random errors that possibly stem from measurement and automatic modal identification. The existing methods that only employ the classical Principle Component Analysis (PCA) have been demonstrated effective to remove the effects of environmental variations while extremely sensitive to random errors. Therefore, the robust PCA is firstly introduced to remove the random errors, especially outliers, that significantly corrupt the low-rank property of the stacked damage sensitive feature (DSF) matrix. Then, the classical PCA is used to extract the environmental variation-free residues, which are inherently damage-dependent and can be used to detect the existence of damage. The problem of missing data is also considered in this study. It is tackled by adding virtual random errors to the locations of missing entities and thus can be addressed by the introduced robust PCA. The advantages of the proposed approach include: (1) Handling the random error-contaminated DSF data regardless of the error’s amplitude, which is an intractable problem for the existing classical PCA-based methods to consider the environmental effects; (2) Damage detection process can be automatic since the missing data can be automatically predicted and the random errors are not required to be manually distinguished. The effectiveness and performance of the proposed method are demonstrated on a numerical beam structure and an experimentally tested wooden bridge model.

Structural damage identification method based on vibration statistical indicators and support vector machine

This study presents a support vector machine (SVM) based structural damage detection approach for a steel frame model. Totally 10 structural scenarios including one undamaged and nine damaged cases (D1–D9) are defined by replacing different column elements to reduce the lateral stiffness between layers. Sensors are laid out at each layer of the frame structure to pick up acceleration response stirred up by the simulated white noise excitations. Statistical analysis is carried out and three damage indictor features are extracted from 800 samples of record duration. Subsequently, the SVM classifiers are developed to conduct a series of indictor fusion schemes to identify multiple damage states. The results indicate that the approach has good identification performance with damage features from three indicators, especially for a high dimensional input eigenvector. Meanwhile, acceptable detection accuracy can be obtained in situations with incomplete measurement; the robustness in terms of the resistance against noise is also discussed.

A New Structural Health Monitoring Approach Based on Smartphone Measurements of Magnetic Field Intensity

In this paper, a new structural damage detection approach is proposed, based on monitoring of the magnetic field intensity variations using smartphones. Experimental and numerical studies are conducted on steel plates to verify the efficiency of the proposed approach. Various damage scenarios are introduced to the steel plates. Then, a smartphone magnetometer sensor is deployed to measure the changes of the magnetic flux due to damage progression. The experimental and numerical results agree well with each other. Based on the results, the magnetic field intensity increases as the damage progresses. Furthermore, the damage detection accuracy declines as the distance of the smartphone increases from the steel plate surface. The proposed method can be considered as a promising, cost-effective and crowdsourcing sensing platform empowered by citizens for structural health monitoring of civil infrastructure systems.

A hybrid computational intelligence approach for structural damage detection using marine predator algorithm and feedforward neural networks

Finite element (FE) based structural health monitoring (SHM) algorithms seek to update structural damage indices through solving an optimisation problem in which the difference between the response of the real structure and a corresponding FE model to some excitation force is minimised. These techniques, therefore, exploit advanced optimisation algorithms to alleviate errors stemming from the lack of information or the use of highly noisy measured responses. This study proposes an effective approach for damage detection by using a recently developed novel swarm intelligence algorithm, i.e. the marine predator algorithm (MPA). In the proposed approach, optimal foraging strategy and marine memory are employed to improve the learning ability of feedforward neural networks. After training, the hybrid feedforward neural networks and marine predator algorithm, MPAFNN, produces the best combination of connection weights and biases. These weights and biases then are re-input to the networks for prediction. Firstly, the classification capability of the proposed algorithm is investigated in comparison with some well-known optimization algorithms such as particle swarm optimization (PSO), gravitational search algorithm (GSA), hybrid particle swarm optimization-gravitational search algorithm (PSOGSA), and grey wolf optimizer (GWO) via four classification benchmark problems. The superior and stable performance of MPAFNN proves its effectiveness. Then, the proposed method is applied for damage identification of three numerical models, i.e. a simply supported beam, a two-span continuous beam, and a laboratory free-free beam by using modal flexibility indices. The obtained results reveal the feasibility of the proposed approach in damage identification not only for different structures with single damage and multiple damage, but also considering noise effect.

Bayesian‐optimized unsupervised learning approach for structural damage detection

AbstractStructural health monitoring (SHM) is developing rapidly to fulfill the world's need for resilient and sustainable communities. Due to the current advancements in machine learning and data science, data‐driven SHM is an attractive solution for real‐time damage detection compared to the traditional nondestructive evaluation techniques. However, most widely available data‐driven SHM methods rely on fully or partially simulated data to train the statistical model, and thus require a number of predefined assumptions and parameters, or are not adapted for post‐extreme events damage diagnosis. In this study, we propose a density‐based unsupervised learning approach for structural damage detection and localization. This approach leverages cumulative intensity measures for damage‐sensitive feature extraction for the first time in an unsupervised learning approach. Furthermore, a statistical model construction process is proposed based on kernel density maximum entropy (KDME) and Bayesian optimization. The framework is evaluated in three case studies. The first two involve a numerical three‐story building and a numerical nine‐story asymmetrical building that are both subjected to 100 ground motion excitations while considering environmental variations. The proposed framework is able to detect and localize damage in those case studies with an average accuracy of 92%. The third case study, which contains 44 shake‐table tests of a three‐story frame structure with masonry infill, is used to experimentally validate the proposed framework in damage detection. The three case studies demonstrate the potential and robustness of the proposed Bayesian‐optimized, multivariate KDME novelty detection framework for detecting and localizing structural damage, especially after extreme events.