Structural Damage Identification Research Articles

Comparative Analysis of Measurement Points for Structural Damage Identification in Free-Free Aluminium Beam using Response Surface Methodology and FRF Curvature

This research paper presents a comprehensive comparative analysis of measurement points for structural damage identification in free-free aluminium beams using Response Surface Methodology (RSM) and Frequency Response Function (FRF) curvature. The primary objective is to determine the optimal measurement points for establishing a relationship between the input parameters and response features, thus forming a surrogate model. The investigation focuses on analyzing the influence of the number of measurement points on RSM's capability to identify structural damage. Three distinct Design of Experiment (DOE) techniques are explored: central composite design (CCD), Box-Behnken design (BBD), and D-optimal design, each incorporating different numbers of measurement points (10 elements, 15 elements, and 20 elements). The study's results highlight BBD's strong capability in detecting damage with fewer measurement points, while CCD design accurately identifies damage in finer measurement points. The findings reveal a clear trend: as the number of measurement points increases, the model becomes more refined, yielding higher stiffness reduction factor (SRF) values. The results underscore the significance of selecting an appropriate number of measurement points to enhance RSM's efficiency in identifying structural damage, thereby optimizing damage identification processes. This study contributes valuable insights into the selection of measurement points for effective structural damage identification, offering practical implications for engineering applications.

Transfer Learning-Based Structural Damage Identification for Building Structures with Limited Measurement Data

Structural damage detection is crucial for ensuring the safety of civil building structures in operational environments. Recently, deep learning-based methods have gained increasing attention from engineers and researchers. The performance of conventional deep learning methods for structural damage detection relies on a large number of labeled training datasets. However, it is difficult or/and impossible to obtain sufficient datasets to cover various damage scenarios for in-service structures. A little research has been conducted to identify both the damage severity and location with limited labeled measurement data. A novel transfer learning-based method for structural damage identification with limited measurements has been proposed utilizing frequency response functions (FRFs) as the input. The real structure is regarded as the target domain and its numerical model is as the source domain. The samples for various damage scenarios are generated using the numerical model, and a designed deep convolutional neural network (CNN) is pre-trained. The knowledge of the pre-trained network is transferred to identify the damage location and severity of the real structure using limited measurement data. Numerical and experimental studies have been conducted on a three-story building structure to verify the performance of the proposed method. To understand transfer learning and model interpretability, the t-SNE feature visualization is adopted to show the feature distribution changes during transfer learning. Numerical and experimental results show that the proposed approach outperforms conventional CNN models, and it is effective and accurate in identifying structural damage location and severity in real structures with limited measurement data.

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.

A deep neural network based surrogate model for damage identification in full-scale structures with incomplete noisy measurements

A deep neural network based surrogate model for damage identification in full-scale structures with incomplete noisy measurements

Damage Identification of Offshore Platform Structure Based on EARCH Model and Optimized KPCA under Environmental Interference

Damage Identification of Offshore Platform Structure Based on EARCH Model and Optimized KPCA under Environmental Interference

A Novel Bayesian Empowered Piecewise Multi-Objective Sparse Evolution for Structural Condition Assessment

In this study, a novel Bayesian empowered piecewise multi-objective function is developed, in which a traditional objective function is applied to realize the rough optimization in the first stage to determine the approximate results. Then, a sparse Bayesian learning-based objective function is applied to realize refined optimization with the obtained approximate results in the second stage. On the other hand, considering the sparsity of the structural damage identification, two simple but effective calculation frameworks, the colony initial sparsification and elite clustering framework, are integrated into the evolution, making the algorithm adaptable to handle the defined sparse optimization problem. Therefore, the proposed calculation framework is more efficient and robust while no initial conditions are needed. We will carry out a numerical example on a truss and an experimental validation on a fixed-end beam with a single-sensor measurement system to verify the method.

ARX-Naïve Bayes based structural damage identification

ABSTRACT The nature of damage identification is close to a pattern recognition process that classifies different damage patterns. The naïve Bayes classifier (NBC) can effectively handle multiple-classification problems by choosing patterns with high probabilities. Therefore, by absorbing the autoregressive model with exogenous inputs (the ARX model), an ARX-Naïve Bayes damage identification strategy has been proposed in which the autoregressive coefficients of the ARX model are taken as the sensitive damage feature. The classification training and test sample datasets are then built on these coefficients corresponding to various damage scenarios. The model order of an AR model is first determined for the subsequent order selection of the ARX model, whose autoregressive coefficients are further used to construct the NBC. This procedure can enhance the pattern recognition robustness to uncertainties such as measurement noises. Different damage patterns are determined by calculating the sum of logarithmic likelihoods of testing samples. The effectiveness of the proposed method has been verified against a bridge benchmark model having different damage scenarios under the noise pollution. In addition, an experimental five-story shear frame structure was adopted for validation, showing that compared with the SVM algorithm suitable for handling binary classification problems, the proposed method excels in multi-classification of damage patterns.

Mathematical Modelling for Failure Analysis of Composite Drive Shaft Using Modal Flexibility and Curvature Method

Early damage identification in composite structures has attracted a lot of attention in post-failure examinations in recent years. In the research, torsional fatigue test of composite drive shafts has been done and numerical methodologies have been employed for the validation for premature failure using modal flexibility and modal curvature methods. Initially, the eigenvalue and eigenvectors of healthy and fractured drive shafts are evaluated using a numerical model and verified by fatigue experimental approach. Flexibility variance and the absolute curvature difference between the drive shafts that are fractured and those that are healthy are evaluated after mass normalization. Variations in absolute modal curvatures and variations in local flexibilities that are utilized to identify the existence, location, and severity of a drive shaft fracture. The position and severity of the fracture are predicted more precisely by the modal curvature approach than by the modal flexibility approach.

Cross-domain structural damage identification using transfer learning strategy

In damage identification of civil structures, training deep neural networks (DNNs) often requires a large volume of annotated training data. However, artificial damage to real-world structures is always forbidden, resulting in insufficient data for training. Transfer learning provides a solution that allows structural damage information in a data-rich domain to be transferred and shared as the prior knowledge to a data-scarce domain, thereby indirectly augmenting available training data in the latter domain. To this end, a multi-task transfer learning strategy has been adopted for the purpose of achieving cross-domain damage identification between a plane frame in the source domain and a three-dimensional frame in the target domain. The strategy can share the learning knowledge from the domain with sufficient training data to the target domain with insufficient data. Thereby, the DNN (named DNN#2) in the target domain can be trained on a small amount of training data. Owing to their ability in data feature extraction, stacked auto-encoders (SAEs) are used to construct the desirable DNN#1 and DNN#2 corresponding to different damage identification tasks, named Task#1 and Task#2, in the two domains. The two DNNs share the hidden layers in order to share damage feature information between the source and target domains. The training datasets of the two domains are first used to jointly pre-train the auto-encoders’ parameters in an unsupervised learning way. Afterwards, a supervised fine-tuning step is carried out to retraining the entire SAEs for better performance. By these means, Task#2 receives some prior knowledge from Task#1, and thus, it is accomplished on limited training data when Task#1 is synchronously achieved. The analysis results demonstrate that the proposed multi-task learning strategy requires only a single training session to simultaneously realize the cross-domain damage identification of two different steel frames.

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.

Research on detection of switch rail defects based on pulse reflection method of the dominant mode

Guided wave structural health monitoring offers a promising way for continuous surveillance and identification of structural damage. However, due to the variable cross-section properties of the switch rail in the longitudinal direction, there are different modes present on different cross-sections, so the guided wave signals excited are very complex. The traditional baseline subtraction method can be used to extract defect echo features, but it is prone to false positives due to the influence of external factors such as field temperature change and environmental noise. This paper proposes a switch rail defect detection method based on the pulse reflection method of the dominant mode. Initially, eight typical cross-sections are chosen based on the cross-sectional dimensions of the switch rail. Semi-analytical finite element(SAFE) method is utilized to solve the dispersion curves and wave structure matrix of guided waves in the switch rail. According to the 3σ rule, the dominant mode whose node amplitude is much higher than other modes is selected, and the excitation signal is applied at the maximum value of the mode, which successfully excites the dominant mode. Through simulation and experimental validation, the reflected waves of the dominant mode at the defect are observable and visible, and the pulse reflection method can be used to detect the defects at the switch rail foot with a positioning error of less than 10 cm. The pulse reflection method of the dominant mode proposed in this paper, which has high detection efficiency and is not affected by the ambient temperature, provides a new idea and way to detect defects of the switch rail based on the ultrasonic guided wave method.

A new neural-network-based method for structural damage identification in single-layer reticulated shells

A new neural-network-based method for structural damage identification in single-layer reticulated shells

Research on structural damage identification of shear buildings based on modal curvature change

Research on structural damage identification of shear buildings based on modal curvature change

Intelligent crack identification method for high‐rise buildings aided by synthetic environments

SummaryCracks can develop in high‐rise buildings because of long‐term environmental changes and extreme loading events such as strong winds or earthquakes. Although deep learning‐based identification methods can efficiently identify cracks, the accuracy of crack identification in high‐rise buildings needs to be improved due to the lack of crack datasets specifically related to high‐rise structures. Moreover, the number of available images of cracks in high‐rise is limited. To this end, this paper establishes an intelligent crack identification method based on a photorealistic synthetic modeling technique. First, a computer graphics (CG) model of a high‐rise building with assumed damage is constructed. Subsequently, the CG model is utilized to generate a dataset that includes photorealistic images of the high‐rise building as well as corresponding labels for various components and types of damage. The generated dataset is then used to train a DeepLabv3 + neural network for structural component and damage identification, followed by validation by employing images of both synthetic and full‐scale high‐rise buildings. The trained network can accurately identify different components in images of the full‐scale, high‐rise building and identify cracks that are intentionally synthesized in those images. The results show that the synthetic dataset generated by the CG model not only allows for fast and efficient labeling for the purpose of neural network training but also outperforms methods that do not consider any application‐specific context in crack identification.

Bridge Structural Damage Identification Based on Parallel Multi-head Self-attention Mechanism and Bidirectional Long and Short-term Memory Network

Bridge Structural Damage Identification Based on Parallel Multi-head Self-attention Mechanism and Bidirectional Long and Short-term Memory Network

Research on structural damage identification method of aircraft aluminium alloy skin based on power spectral entropy

Skin is an important structural component which covers the surface of aircraft widely, the structural health of skin has a great impact on the overall safety of aircraft. Due to the harsh operating environment, complex and changing working conditions, and high-intensity service process of aircraft, it is easy to cause damage to the skin. Thus, the in-situ health monitoring for aircraft skin is an effective approach to ensure its safety and reliability. Thanks to the ability of Lamb waves to propagate over long distances and recognize small-scale defects, they have shown great potential in the health monitoring of thin-walled structures and have received widespread attention. However, the traditional Lamb wave-based damage identification methods generally suffer from the problems of large number of sensors and low efficiency. Therefore, a skin damage identification method based on power spectral entropy is proposed in this paper, which can estimate the damage extent by extracting the nonlinear component increase caused by damage, and the experiments validate that the proposed method has higher sensitivity and computational efficiency than the existing other entropy-based methods.

Harnessing collaborative learning automata to guide multi-objective optimization based inverse analysis for structural damage identification

Structural damage identification based on physical models is often transformed into an optimization problem that minimizes the difference between measurement information of structure being monitored and the model prediction in the parametric space. However, the objective function in this context often exhibits multimodality, involving high-dimensional variables due to the reliance on finite element models for damage identification. These features pose challenges to optimization algorithms, where entrapment in local solutions can lead to false positives and false negatives in damage identification. In this research, we propose a reinforcement learning based multi-swarm optimizer to tackle such challenges in pursuit of a small yet diverse solution set that can capture the true damage scenario as one of the solutions. The proposed method leverages the flexibility of the particle swarm optimizer and incorporates novel strategies of metaheuristics to realize targeted improvement. To enable the particle swarm to adaptively select the appropriate search strategy based on the current environment, we adopt the learning automata technique, which sidesteps the need for reward strategy selection that is usually ad hoc at each step of the search. The integration harnesses the automatic learning and self-adaptation capabilities of learning automata, enabling the particles to navigate based on environmental signals. This leads to accumulated probabilities tied to advantageous movements, fostering an adaptive exploration of particles in the search space. The proposed approach is first validated through implementing into benchmark test cases with comparisons. It is then applied to structural damage identification with piezoelectric admittance experimental signals. `The results highlight the capability of the algorithm to identify a small solution set with high accuracy to match the actual damage scenario.

Optimization of structural damage identification method based on finite element method and Bayesian updating

The application of Bayesian updates to the finite element method for structural damage detection represents an avant-garde approach in the industry. Its merit lies in astutely transforming the influence of uncertainty into a forward problem. Nonetheless, the selection of simulation experiments and loading measurement schemes still relies to a certain extent on exhaustive methods. In this paper, based on the finite element method and Bayesian method, the OpenSees software platform is used to compare the actual experimental values with a large number of simulation experiments. The sensitivity of loading and measuring schemes is clarified, and the significance of simulation experiments in finding efficient schemes and reducing detection costs is verified. Concurrently, taking a truss structure as a case study, the combination of structural optimization and simulation experiment is deeply studied. The conclusion of this paper can provide a way to improve the level of simulation experiments and save computing resources.

Application of deep convolutional generative adversarial network to identification of bridge structural damage

Application of deep convolutional generative adversarial network to identification of bridge structural damage

Structural Damage Identification Based on Preprocessing Samples Mixed Training of Multi-Channel and Multi-Source Dynamic Response Data

Previous studies have shown that sampling processing and identification methods for neural networks damage identification in multi-channel and multi-source structural dynamic response data exhibit diversity, and the robustness and generalization issues of the model have not been effectively solved. This paper proposes a sample preprocessing technique and mixed training method suitable for multi-channel and multi-source dynamic response data to optimize the current structural damage identification methods based on neural networks. Through multi-dimensional discrete autocorrelation processing and Fourier transform, the preprocessed datasets from multiple sensors with multi-channel can access multi-channel CNN. Furthermore, the measured datasets from the actual structures are mixed with numerical simulation datasets before being used for neural network model training to address the model calibration and the imbalanced sample size under each classification label. The results of extensive model experiments and finite element verification of specimens show that the method performs outstandingly in detecting and identifying damage to simply supported beam structures using multi-channel CNN. The neural network model trained with preprocessed samples exhibits excellent robustness. The model using the mixed training method still performs well in identifying the accuracy of damage location and degree in simply supported beam structures after changing beam section and initial excitation. The method has certain generalization ability in detecting unknown damage in simply supported beam structures.