Structural Damage Detection Method Research Articles

Structural Damage Detection through Dual-Channel Pseudo-Supervised Learning

Structural damage detection is crucial for maintaining the health and safety of buildings. However, achieving high accuracy in damage detection remains challenging, especially in noisy environments. To improve the accuracy and noise robustness of damage detection, this study proposes a novel method that combines the Conformer model and the dual-channel pseudo-supervised (DCPS) learning strategy for structural damage detection. The DCPS learning strategy improves the stability and accuracy of the model in noisy environments. It enables the model to input acceleration signals with different noise levels into each branch of the dual-channel network, thereby learning noise-robust features. The Conformer model, as the backbone network, integrates the advantages of convolutional neural networks (CNNs) and Transformers to effectively extract both local and global features from acceleration signals. The proposed method is validated using a four-story single-span steel-frame building model and the IASC-ASCE simulated benchmark structure. The results show that the proposed method achieves a higher classification accuracy than existing structural damage detection methods. Compared to the single Conformer-based method, this method improves the accuracy by 1.57% and 4.93% for the two validation structures, respectively. Moreover, the proposed method benefits from the DCPS learning strategy’s ability to achieve superior noise robustness compared to other methods. The proposed method holds potential value for improving the accuracy of damage detection and noise robustness in scenarios such as maintenance and extreme events.

Damage detection of truss structures using meta-heuristic algorithms and optimized group method of data handling surrogate model

Optimization-based methods are increasingly being implemented for structural damage detection (SDD) problems through the minimization of the objective functions based on vibration data. Meanwhile, the challenge of high computational cost hinders the applied use of SDD methods, especially upon addressing large-scale structures. In this study, a two-stage damage detection approach is proposed for damage localization as well as extent quantification which reduces the computational time of SDD problems. In the first stage of the proposed framework, suspected locations of damage are identified by employing a residual force vector. Then in the second stage, damage extent of already identified elements will be assessed by model updating method through three different optimization algorithms, namely particle swarm optimization (PSO), differential evolution (DE), and enhanced colliding bodies optimization (ECBO). To spare time-consuming modal analysis in each iteration of optimization algorithms, a PSO-based group method of data handling (GMDH) polynomial neural network (PNN) surrogate model is proposed. Performance of GMDH PNN strongly depends on the input variables, the number of input variables, and the order of the polynomial. The PSO-based GMDH PNN, developed in this study, employs PSO for the optimum selection of these parameters. Furthermore, the efficiency of Elemental Energy Quotient Indicator (EEQI) as a new damage index proposed in this paper is compared with the approach based on the natural frequency-based index. This paper also deals with the incomplete modal data measured from limited number of sensors. This problem is addressed by employing the model reduction technique and solving the SDD problem with modal information obtained from the reduced model. Numerical examples show that the suggested PSO-based GMDH surrogate model is an accurate tool for various types of SDD problems, and it can provide promising results with a significant reduction in computational time.

Unsupervised quantitative structural damage identification method based on BiLSTM networks and probability distribution model

Current unsupervised structural damage identification methods mainly focus on unsupervised damage detection, i.e., detecting whether damage occurs, but rarely involve damage localization and quantification in practical civil engineering structures. Thus, based on bidirectional long short-term memory (BiLSTM) networks and a probability distribution model, i.e., generalized extreme value distribution (GEVD), this paper proposes an unsupervised structural damage detection, localization, and quantification method. The response correlations model among sensors under healthy conditions was built by employing the BiLSTM networks for reconstructing response data. Then, reconstruction error between reconstructed and true data is used as damage-sensitive features and thus is applied to detect and localized damage. In addition, a stable damage quantification result can be obtained based on the probability distribution model of damage-sensitive features. The proposed method is validated by using the data obtained from a numerical steel beam model and a practical long-span cable-stayed bridge. The research results demonstrate that the proposed method can effectively detect, localize, and quantify damage in an unsupervised manner, even with a limited number of sensors and low-order modal information in acceleration data. The proposed method possesses the capability to autonomously furnish alerts regarding structural damage location and severity under Environmental and Operational Conditions.

Structural damage detection based on structural macro-strain mode shapes extracted from non-stationary output responses

Abstract Long-gauge fiber Bragg grating strain sensors have been widely employed because of their broader measuring range and higher sensitivity. However, current structural damage detection methods using macro-strain modal parameters are based on structural frequency response function or stationary power spectrum density, which are not applicable to non-stationary responses. To overcome this limitation, an improved method is proposed in this paper for structural damage detection based on structural macro-strain responses under unknown multi-point non-stationary excitations. First, a new concept of macro-strain energy spectrum transmissibility (MEST) is proposed using structural non-stationary macro-strain responses, and it is derived that MEST at a certain system pole equals the ratio of macro-strain mode shape. Then, the singular value decomposition technique is adopted for the MEST matrix to identify structural natural frequencies and macro-strain mode shapes. Finally, two damage detection indicators are constructed based on the identified normalized macro-strain mode shape (NMMS). The first indicator is the difference in structural NMMS before and after structural damage. The second one is based on the curvatures of structural NMMS, which can be used for structures without intact baseline. Numerical verifications are conducted to identify beam-type structural damage under multi-point non-stationary excitations or vehicle loads. Five damage scenarios with different measurement noise levels are investigated, and damage detection results validate the effectiveness of the proposed method.

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.

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.

Unsupervised Vision‐Based Structural Anomaly Detection and Localization with Reverse Knowledge Distillation

Most of vision‐based methods for structural damage detection rely on supervised learning, requiring a substantial number of labeled images for model training, which is labor‐intensive and time‐consuming. To address these challenges, this study introduces a vision‐based structural anomaly detection and localization approach using unsupervised learning and reverse knowledge distillation. The proposed model incorporates a teacher model, a student model, and a trainable one‐class bottleneck embedding module. The asymmetrical architecture of the teacher and student models forms an encoder‐decoder structure for parameter transfer and feature extraction. The student network receives a specific embedding from the teacher network as input and target, facilitating the recovery of multiscale information from the teacher. Training images only contain the undamaged structures, and the teacher model, a pretrained model, instructs the student model to remember their undamaged features to detect and localize damages in unseen testing images. Through experiments, including a comparison among five candidate backbones for pretrained teacher models based on the residual network and testing across various structural damage types, the optimal model is identified, demonstrating good performance in both anomaly detection and localization. Furthermore, the model’s generalization performance is thoroughly validated, confirming its efficacy across diverse scenarios.

Study on the structural damage detection method using the flexibility matrix

Study on the structural damage detection method using the flexibility matrix

Development of a procedure for model selection in machine learning-based methods for structural damage detection

Output-only methods based on machine/deep-learning algorithms are highly practical approaches for timely detecting potential damages in civil structures as they directly employ measured vibration signals but do notrequire exact knowledge of input loading nor the service interruption for manual inspection. However, there isno one-size-fits-all model that is optimal for all problems in different perspectives; hence, it is necessary todiscover the advantages as well as drawbacks of different models, then leverage these understandings to selectthe most appropriate model for specific structures in reality. Therefore, this study develops a framework thatfacilitate the model selection by extensively comparing various machine learning-based methods ranging fromrelatively simple ones such as Na¨ıve Bayes to complex ones such as the extreme boosting tree-based ensemblemodel. The framework can provide comparison results include various aspects such as model complexity, training time, detection accuracy, and inference time.

Structural adaptive damage detection under uncertainty based on probability dissimilarity and moving average control chart

For engineering applications of guided-wave-based online structural damage detection, dealing with uncertainty caused by time-varying conditions (TVCs) is an issue of fundamental importance. In this study, a structural adaptive damage detection method based on probability dissimilarity and moving average control chart (MACC) is proposed. To suppress the uncertain effects of TVCs on signals, the probability dissimilarity-based damage index (PDDI) is extracted based on the proposed adaptive probability modeling of signal feature and probability distribution dissimilarity measure. Then, the automatic damage alarm mechanism based on MACC is proposed to determine alarm threshold adaptively and restrain the uncertain influence further by the moving average of PDDI. The proposed method is verified by the damage detection experiments on typical aircraft lug specimens under varying load and temperature, and then the method is applied to the full-scale aircraft fatigue test. The results demonstrate that the proposed method realizes reliable and adaptive structural damage detection under uncertain conditions.

A 2D-CNN-Based Two-Stage Structural Damage Localization and Quantification Technique Using Time Domain Vibration Data

The conventional approaches for detecting structural degradation are time-consuming, labor-intensive, and costly. The physical monitoring of the structure also poses risks to the health and safety of supervisors. Therefore, damage estimation of any structure using artificial intelligence (AI), more specifically deep learning (DL), is becoming more significant in civil infrastructure. In the presented research article, an efficient two-stage damage detection method is proposed for structural damage detection (SDD) from time domain vibration signals. The proposed method utilizes two-dimensional convolutional neural network (2D-CNN) architecture as a DL algorithm for damage detection. Here, a computer-aided damage detection method for steel beam and frame-type structures is developed using 2D-CNN algorithm in the Google Colab platform. The effectiveness of the proposed method is first verified, and it provides more than 90% accuracy for identifying the damage location and severity of a cantilever beam for single- and multi-damage scenarios from numerically simulated noisy displacement data. The algorithm is also experimentally validated through the raw acceleration data of damaged steel frame joints collected from the Qatar University Grandstand simulator (QUGS). The proposed 2D-CNN algorithm performs better than other DL algorithms by achieving 100% accuracy within 10 epochs for damage detection of steel frames using QUGS data. It demonstrates significant potential for detecting damage location and quantifying damages for single- and multi-damage scenarios using noise-free and noisy datasets. The primary contribution of this study resides in the implementation of two-stage damage detection algorithm utilizing 2D-CNN with time domain vibration response for multiclass damage identification and quantification.

An Output-Only, Energy-Based, Damage Detection Method Using the Trend Lines of the Structural Acceleration Response

Using the trendlines of an acceleration response as a tool to decompose a structural response is a new topic that was proposed by authors in 2020. This paper provides a numerical/experimental investigation of using a Savitzky–Golay filter (SGF) in a method to calculate the trendline and decompose building acceleration responses when subjected to a seismic load. Hence, this paper proposes an output-only, energy-based, damage detection method in which the trend lines of a building’s structural acceleration responses are used to locate the damage. For this purpose, an adjusted SGF is utilized to calculate an especial trend line for each floor’s acceleration response of the building structural model. The energy of these trend lines is then calculated and normalized. Two damage indices are used, of which, the second one is being proposed for the first time in this paper. The accuracy of the proposed method is numerically and experimentally investigated using a five-floor building structural model subjected to white noise excitation through a shake table. The results prove that the proposed method is capable of accurately locating and quantifying structural damages with a severity of more than 10% in a noisy environment. In view that the proposed method locates the damage with no need of determining the structural modal properties or parameters, it can be categorized as an online and quick structural damage detection method.

Bridge anomaly detection based on reconstruction error and structural similarity of unsupervised convolutional auto-encoder

This study presents a novel bridge anomaly detection approach that employs the reconstruction error and structural similarity of an unsupervised convolutional auto-encoder. The presence of structural damage in a bridge typically results in changes in its vibration signals, and thus, the use of these signals for structural damage detection (SDD) has been widely investigated, with many methods relying on supervised learning. However, such existing SDD methods based on the supervised learning require prior knowledge of the damage states and cannot process monitoring data in real-time, thereby limiting their application to in-service bridges. To address this challenge, the authors propose the use of a convolutional auto-encoder as the reconstruction algorithm for real-time vibration signals. The auto-encoder is trained using normal signals and then used to reconstruct new inputs (either normal or abnormal). Two damage indicators (reconstruction error and structural similarity) are then calculated based on the reconstruction results and clustered to detect abnormal signals. The proposed approach was applied to the detection of various abnormalities in the old ADA Bridge, the results were 100% accurate, and about a 10% increase in accuracy was observed when compared to other control experiments. These results demonstrate the effectiveness of the proposed approach, with the auto-encoder achieving excellent reconstruction results for normal signals and clear discrepancies for abnormal signals. The proposed method was also validated on a cable-stayed bridge and an arch bridge, demonstrating its wide applicability in bridge anomaly detection.

Machine learning methods for multi-rotor UAV structural damage detection based on MEMS sensor

Multi-rotor Unmanned Aerial Vehicles (UAVs) have become increasingly important in industries and early detection of structural damage is crucial to prevent unexpected breakdowns, ensure production efficiency, and maintain operational safety. This paper proposes machine learning techniques for detecting damage caused by loosened screws which is not easy founded based on vibration signals. An independent data acquisition device with a Micro Electro Mechanical Systems (MEMS) sensor is designed and fixed onto the multi-rotor UAVs to acquire the vibration data. Four machine learning algorithms, namely Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Decision Tree, and Random Forest, are employed for damage detection. The results demonstrate successful utilization of the vibration data from the MEMS sensor for damage detection, with the random forest model outperforming other models with an accuracy of 90.07.

A modified mode shape data-based method for beams structural damage detection

Damage detection methods based on changing modal parameters have received considerable attention in engineering applications due to the satisfactory results and the low associated cost compared with other techniques. The Mode Shape Data Based Indicator (MSDBI) is a damage indicator available in the literature, being used to identify damage in beam structures from the mode shape, mode shape slope and mode shape curvature, in the undamaged and damaged configurations of the element under study. However, in some situations, the configuration of the displacement mode shape of the ith mode, of the undamaged structure compared to the damaged one, presents mirroring. The damage identification algorithm could be a better indicator when these situations occur. Them, this paper presents a proposal to modify this method, called MSDBIM. The proposed modified method (MSDBIM) and the traditional method (MSDBI) were applied in two numerical examples that were elaborated in commercial software of finite elements, namely a simply supported concrete beam and a fixed-end steel beam in different single and multiple damage scenarios with sensitivity studies. A new discretization for the fixed-end beam was performed to assess whether there is a direct influence on the damage identification method. The results show that the proposed method (MSDBIM) performs better than the traditional method (MSDBI).

Structural Damage Detection Based on Improved Sensitivity Function of Modal Flexibility and Iterative Reweighted lp Regularization

The [Formula: see text] regularization is usually used to deal with the problems of under-determinacy and measurement noise for the conventional sensitivity-based model updating damage detection methods. However, the [Formula: see text] regularization technique often provides overly smooth solutions and thus cannot exhibit the sparsity of the structural damage due to the promotion of the 2-norm term on smoothness. In the study, a structural damage detection method is proposed based on an improved modal flexibility sensitivity function and an iterative reweighted [Formula: see text] (IR[Formula: see text] regularization. Specifically, the sensitivity function is established by introducing changes in the mode shapes into the derivative of eigenvalue and can be applied to identify the localized damage more accurately. Additionally, IR[Formula: see text] regularization is proposed to deal with the ill-posed problem of damage detection in a noisy environment. The proposed IR[Formula: see text] regularization is compared with the [Formula: see text] and [Formula: see text] regularizations through a numerical and an experimental examples. The numerical and experimental results indicate that the IR[Formula: see text] regularization can more accurately locate and quantify the single and multiple damages under the noise situation. The maximum identification errors are only 5.16% and 5.67%, respectively. Moreover, compared to the basic modal flexibility sensitivity function, the improved function is more sensitive to the damage. The maximum identification error of the improved function is less than 6%, while the relative errors are significantly larger in the basic function.

Baseline-free structural damage detection using PCA- Hilbert transform with limited sensors

Conventional vibration-based damage identification methods need a large number of sensors on the bridge to identify the structural modal information and rely on the response data of bridges under a non-damage state for comparison, which restricts their implementations in the health monitoring of bridge structures in service. This paper proposes a baseline-free structural damage detection method based on limited sensor information. The proposed method uses the Hilbert transform combined with principal component analysis (PCA) to locate the damage. Firstly, PCA is performed on the displacement response data matrix of the bridge under a moving load to obtain the principal component matrix. According to the physical interpretation of PCA of the responses of a beam-like bridge under a moving load, each column of the principal component matrix, namely the principal component, composes of a mode shape and the dynamic information at this modal frequency of the bridge. The dynamic information of the modal frequency is indirectly obtained by filtering out the mode shape by low pass filter. Then the Hilbert transform is used to process the dynamic component information to receive the instantaneous frequency which is regarded as the damage index. When the structure is damaged, the first instantaneous frequency at the damaged location changes abruptly. To demonstrate the effectiveness and performance of the proposed method, numerical simulations and experimental validations on beam bridge models are conducted. The results show that the method is free from the requirement of the information of bridges under the undamaged state, and only limited sensors are needed to locate the damage.

Damage detection of bridges subjected to moving load based on domain-adversarial neural network considering measurement and model error

Bridge damage detection methods based on moving load induced response and deep learning are popular, and they are effective when the training data generated by a finite element model (FEM) and the testing data measured from the actual bridge have the same distribution. However, their distributions are normally different due to the measurement and model error. This paper proposes a Domain-adversarial Neural Network (DANN) based damage detection method for bridge structures. The moving load induced displacement responses of the FEM and the actual bridge are taken as network inputs, and the feature space with the minimum differentiation between the edge distributions of the FEM (source domain) and the actual bridge (target domain) is extracted by adversarial training between the domain discriminator and the feature extractor. This feature space is a domain invariant feature of the source domain and the target domain and contains damage information only. Thus the damage label information is transferred from the source domain to the target domain for damage detection. Numerical and experimental examples manifest that the proposed method can reduce the distribution gap between the source domain and the target domain, and achieve higher damage detection accuracy than that of the traditional deep learning method by using a small number of sensors without a large amount of damage label data.

Damage Imaging Identification of Honeycomb Sandwich Structures Based on Lamb Waves.

In the field of structural health monitoring, Lamb Wave has become one of the most widely used inspection tools due to its advantages of wide detection range and high sensitivity. In this paper, a new damage detection method for honeycomb sandwich structures based on frequency spectrum and Lamb Wave Tomography is proposed. By means of simulation and experiment, a certain number of sensors were placed on the honeycomb sandwich plate to stimulate and receive the signals in both undamaged and damaged cases. By Lamb Wave Tomography, the differences of signals before and after damage were compared, and the damage indexes were calculated. Furthermore, the probability of each sensor path containing damage was analyzed, and the damage image was finally realized. The technology does not require analysis of the complex multimode propagation properties of Lamb Wave, nor does it require understanding and modeling of the properties of materials or structures. In both simulation and experiment, the localization errors of the damage conform to the detection requirements, thus verifying that the method has certain feasibility in damage detection.

Numerical Investigation of the Time-of-Flight and Wave Energy Dependent Hybrid Method for Structural Damage Detection

BackgroundStructural damage can be caused by various factors such as aging, environmental conditions, and unexpected events like earthquakes. Early detection of damage is crucial to prevent further deterioration, avoid catastrophic failure, and reduce maintenance costs. Damage detection methods that use piezoelectric sensors have gained popularity due to their non-destructive and non-invasive nature. Despite the progress made in the field of damage detection using piezoelectric sensors, there is still a need to improve the accuracy and reliability of those methods.ObjectiveThis study aims to contribute to this by investigating the damage detection hybrid method, which uses the time-of-flight (ToF) criteria of acquired signals besides the energy loss damage index (DI) between damaged and intact states of a specimen, and exploring its possible improvements. The improvement potential in the investigated method regarding the signal processing details and the specification of the ToF used within the method, where the lack of information has been identified. Thus, the present study concentrates on those factors to get more benefit of the suggested method and extend its applicability.ResultsThe investigated factors play significant role in the accuracy and reliability of the method. By analyzing these criteria, this study contributes to the development of more advanced and reliable damage detection methods that can be applied to a wide range of structures, improving the ability to assess their structural health and safety. This study provides a better understanding of the hybrid method and contributes to the development of more accurate and reliable damage detection methods. The results of this study indicate that the proposed hybrid method effectively detects damage in the structural components under investigation with high accuracy and reliability.MethodsA 2D concrete plate is utilized to apply the proposed methodology. Hereby, various ToF criteria, truncation strategies of the signals, and the number of piezoelectric transducers used in the numerical experiment are examined to investigate their impact on the damage detection accuracy. ConclusionPerformance of the method was found to be significantly affected by selection of the investigated parameters, as well as of the number and placement of sensors. The findings suggest that a thorough analysis of these criteria can lead to further improvements in the accuracy and reliability of damage detection methods.