Damage Detection Method Research Articles

Combination of in-/and ex-situ damage detection methods to investigate the forming behavior of fiber-metal-laminates

In this study, the forming behavior of fiber-metal laminates (FML) is investigated by a combination of different (in- and ex-situ) measurement techniques. Using FML-samples consisting of aluminum and carbon fiber reinforced polyamide-6, deep-drawing tests were employed at high temperatures. It can be concluded a conventional approach based on the forming limit curve (FLC) is not suitable to predict the failure initiated in the multi-material setup as principal strains cannot differentiate the strain in aluminum and CFRP and lack sensitivity to detect other relevant failure modes, such as debonding as well as debonding in between layers. To better understand the failure behavior due to forming of FML, an experimental setup, that based on the Nakajima-test, was developed, using in-situ acoustic emission testing, 3D digital image correlation as well as ex-situ X-ray computed tomography. The combined results from all methods helped to gain a deeper insight into how thermoplastic FML behave during deep drawing at elevated temperatures especially focusing on evolving damage inside the hybrid material

Nonlinear vibration characteristics and damage detection method of blade with breathing fatigue crack

In aero-engine, blades operate under harsh conditions for extended periods, which makes them highly susceptible to fatigue cracks. The localized and nonlinear structural changes caused by blade crack lead to complex vibration characteristics that are not well understood, posing challenges to the identification of these cracks. This paper proposes an approach for identifying breathing fatigue crack in compressor blade, leveraging the nonlinear features induced by the cracks. Crucial sensitive characteristics are extracted and a crack indicator for accurate crack detection is defined. Initially addressing the typical morphology of fatigue breathing cracks, a dynamic model of blade with cracks is developed to analyze their impact on the natural frequencies. Nonlinear contact forces are introduced to characterize the "breathing" effect of the fatigue crack, allowing for the determination of the harmonic distribution patterns in the blade's vibration response under various excitation conditions. A finite element model is then established considering the crack morphology, by adopting the contact element. Based on that, the nonlinear response characteristics associated with the blade's primary, sub-harmonic, and super-harmonic resonances are explored. A crack-sensitive parameter is defined and extracted from the nonlinear responses, under different crack propagation stages. At last, effectiveness and reliability of the defined parameter for identifying cracks is validated through a vibration fatigue test.

A Stacked Neural Network Model for Damage Localization.

Traditional vibration-based damage detection methods often involve human intervention in decision-making, therefore being time-consuming and error-prone. In this study, we propose using Artificial Neural Networks (ANNs) to detect patterns in the structural response and create accurate predictions. The features extracted from the response signal are the Relative Frequency Shifts (RFSs) of the first eight weak-axis bending vibration modes, and the predictions refer to the damage location. To increase the accuracy of the predictions, we propose a novel stacked neural network approach, capable of detecting damage locations with high accuracy. The dataset used for training involves, as input data, the RFSs calculated with an original method for numerous damage locations and severities. The following models were used as building blocks for our stacked approach: Multilayer Perceptron, Recurrent Neural Network, Long Short-term Memory, and Gated Recurrent Units. The entire beam was thus split into segments and each network was trained in this stacked model on one beam segment. All results obtained with the models are also compared to a standard neural network trained on the entire beam. The results obtained show that the model that performs the best contains 14 stacked two-layer feedforward networks.

Pavement crack detection based on depth-supervision FRRN model

Timely detection of early pavement distress is crucial for effective pavement maintenance. A promising approach involves the segmenting the road surface cracks area from its images. However, the previously employed full-resolution residual network (FRRN), when employing a large number of full-resolution residual units (FRRUs), is susceptible to challenges such as exploding and vanishing gradients. Addressing these issues, this paper has introduced a depth supervision mechanism into FRRN, leading to the development of the Depth Supervision FRRN (DSFRRN) model, designed specifically for accurate segmentation of cracks in road images. This model enhances nonlinear expressiveness while retaining essential features, achieving high precision in pavement crack segmentation. Through experimental validation using a dataset comprising 1565 images of damaged pavements, the result demonstrate that DSFRRN outperforms the original FRRN in terms of both F1 score and Jaccard index, accurately delineating cracks. Consequently, the automated pavement damage detection method presented herein facilitates cost-effective and efficient pavement inspection, contributing to the safeguarding of roadway surfaces and transportation infrastructure.

Mapping the Knowledge Structure of Image Recognition in Cultural Heritage: A Scientometric Analysis Using CiteSpace, VOSviewer, and Bibliometrix

The application of image recognition techniques in the realm of cultural heritage represents a significant advancement in preservation and analysis. However, existing scholarship on this topic has largely concentrated on specific methodologies and narrow categories, leaving a notable gap in broader understanding. This study aims to address this deficiency through a thorough bibliometric analysis of the Web of Science (WoS) literature from 1995 to 2024, integrating both qualitative and quantitative approaches to elucidate the macro-level evolution of the field. Our analysis reveals that the integration of artificial intelligence, particularly deep learning, has significantly enhanced digital documentation, artifact identification, and overall cultural heritage management. Looking forward, it is imperative that research endeavors expand the application of these techniques into multidisciplinary domains, including ecological monitoring and social policy. Additionally, this paper examines non-invasive identification methods for material classification and damage detection, highlighting the role of advanced modeling in optimizing the management of heritage sites. The emergence of keywords such as ‘ecosystem services’, ‘models’, and ‘energy’ in the recent literature underscores a shift toward sustainable practices in cultural heritage conservation. This trend reflects a growing recognition of the interconnectedness between heritage preservation and environmental sciences. The heightened awareness of environmental crises has, in turn, spurred the development of image recognition technologies tailored for cultural heritage applications. Prospective research in this field is anticipated to witness rapid advancements, particularly in real-time monitoring and community engagement, leading to the creation of more holistic tools for heritage conservation.

Damage identification method for jacket platform based on dual-channel model

To address the challenges posed by noisy vibration signals and underutilized time-series data in jacket platforms, this paper proposes a dual-channel damage detection method that integrates Temporal Convolutional Networks (TCN) and Gated Recurrent Units (GRU) in parallel. A multi-head attention mechanism (MA) is employed to reassign feature weights, improving detection accuracy. The optimized features are fused using the Concatenate function for the final output. Two experimental scenarios—isolated noise and ocean noise—were designed to evaluate the method. The results demonstrate that the combination of TCN, GRU and MA effectively detects damage in offshore platforms, surpassing other deep learning models. Although the method shows strong potential for real-world applications, further testing in more complex ocean environments is required to address potential limitations in handling highly variable noise patterns.

Detection and Prediction of Probe Mark Damage in Wafer Testing

In wafer testing, the test probe needs to contact the surface of the semiconductor wafer to measure electrical parameters such as resistance, capacitance, and current. The probe mark damage frequently occurs on the machine during wafer testing. This phenomenon causes inaccuracies in electrical parameter testing, significantly reducing the yield in IC packaging processes and resulting in substantial manufacturing cost losses. Therefore, this study proposed an effective probe mark damage detection and prediction method to prevent significant yield reduction due to inaccurate testing. This study uses importance analysis from random forests and correlation analysis to identify the critical parameters influencing probe mark damage. Introducing these parameters into a Sparse Transformer with hybrid normalization can successfully train an intelligent model for predicting the occurrence of probe mark damage. The model accurately predicts the probability of probe mark damage and promptly adjusts machine parameters to avoid inaccuracies in electrical parameter settings. The proposed approach can outperform other methods, achieving two very high accuracies of 95.1% (at room temperature) and 93.5% (at high temperature) and significantly reducing the occurrence of large-area probe mark damage.

Whale Optimization Algorithm for structural damage detection, localization, and quantification

This paper introduces an approach for vibration-based damage detection based on matrix updating aided by the Whale Optimization Algorithm (WOA). The methodology uses the Data-driven Stochastic Subspace Identification (SSI-DATA) technique to determine the modal parameters, which are compared with those obtained from both healthy and damaged conditions of the structure. The methodology’s efficacy is assessed through three distinct steps: numerical simulations, experimental data, and real-world data from a bridge. Initially, numerical analyses are conducted on a cantilever beam, a 10-bar truss, and a Warren truss subjected to environmental vibrations with varying damage cases and noise levels. Subsequently, experimental validations are performed on a test system and in the Z24 Bridge. Results from the computational simulations demonstrate the method’s promise to identify, locate, and quantify single and multiple damage cases, even amidst signal noise, variations in the first vibration mode as minimal as 0.015%, and complex structures with 54 elements. Moreover, the matrix updating method utilizing WOA showcased superior accuracy compared to existing techniques in the literature. In addition, the Z24 Bridge example validated the capability of the presented damage detection method to localize structural damage solely based on natural frequencies.

Structural damage detection for spatial frame structures with semi-rigid joints using multiple set wireless measurements

Damage detection of a complex spatial frame structure with semi-rigid joints is a challenging task. Most existing damage detection methods consider the joint as rigid and the nonuniform cross section of the member is not considered. This assumption results to a large error in the structural damage identification. A novel generic element is proposed for the nonuniform cross-section member with semi-rigid joints at both ends in this study. The finite element model of spatial structures with semi-rigid joints is established using the proposed element. The modal strain energy-based damage index is defined and its sensitivity to the member and joint damage has been investigated using numerical and experimental study. An 8-m long bridge model with the bolted connection at joints is built in the laboratory. Dynamic responses of the bridge under random excitations are monitored using 13 wireless tri-axis accelerometers. The spatial mode shapes of the bridge are extracted using the reference-based stochastic subspace identification from multiple set wireless measurements. The numerical model is validated using experimental results. Dynamic responses of the bridge with different damage scenarios have been simulated using the validated model and the corresponding damage indices are obtained. The results show that the proposed method is reliable and accurate to analyze dynamic behavior of the spatial structure with semi-rigid joints, and structural damage can be identified accurately using the modal strain energy-based damage index.

Structural digital Twin for damage detection of CFRP composites using meta transfer Learning-based approach

Using deep learning approaches to identify and locate defects in composite structures made of Carbon Fiber Reinforced Plastics (CFRP) is becoming increasingly popular. However, when the training data is limited, the existing deep learning methods do not work well. Moreover, the lack of data for damaged conditions of CFRP structures causes a severe data imbalance, which makes this problem even harder. In this paper, we present a novel damage detection method called DFMTR which stands for Digital Twin based Few-shot Meta Transfer Learning. It creates numerical model as the digital twin to generate a large amount of virtual data under different damage conditions for model training. Then, it applies relational network and domain adaptive techniques to achieve effective few-shot transfer. That means, it can detect damage accurately with only a very small amount of real data. This is very useful and practical for damage detection of high-end CFRP equipment. In experiments, our approach outperforms existing methods in all commonly used metrics. The classification accuracy can be improved to more than 82% from 55% by using only 4 real samples, and the accurate localization of damaged area is also successfully achieved.

Noise-robust automated sudden damage detection using blind source separation enhanced by variational mode decomposition and support vector machine based on shapelet transform

Compared to parametric counterparts, non-parametric (aka, model-free) damage detection methods have no requirements of accurate models, with the potential of autonomous monitoring of various complex structures. However, noises, or low signal-to-noise ratio (SNR), are one of the main challenges. This study is aimed at improving blind source separation (BSS)-based damage detection method, one of the most advanced non-parametric methods, in both aspects of noise robustness and autonomous operation. In particular, the measured acceleration responses are processed by variational mode decomposition (VMD) and wavelet transform (WT) in sequential, acting as the input for a BSS model. The BSS is then solved by independent component analysis (ICA), which approves to be more noise-robust compared to the state-of-the-art counterparts. Furthermore, shapelet transform is applied to extract the universal shape-based spike-like feature from the BSS model for training a support vector machine (SVM) model, applicable to different structures; it finally automates the sudden damage detection process and enables online monitoring. The effectiveness of the proposed method is illustrated by a numerical example and an experimental test, and demonstrated by a real-world seismic-excited structure. The results show that both single and multiple sudden damages can be automatically detected with high accuracy. Compared with the existing BSS methods, the proposed BSS method is more capable to detect small damages at relatively low SNR. In addition, the classification accuracy of SVM is also improved when shapelet-based feature is used for training, which reduces the malfunction of automated damage detection as shown by the numerical example. Therefore, the proposed strategy has the potential for rapid condition assessment of structures during rare/extreme events, before engineers are sent for further post-event inspection.

Development of a Semi-Autonomous Pulse and Receive Concrete Inspection System

Concrete structures are being subjected to increasing loads and used beyond their intended lifespan. When combined with operators shrinking maintenance budgets it is imperative structures are monitored for damage. Acoustic Emission (AE) and AE Tomography offer a method for damage detection and characterisation. However, they are encumbered by their equipment and setup requirements, and best used on areas where damage is already known to have occurred. An autonomous pulse catch system could be used to identify these areas. To explore the potential of such a system, seven concrete beams differentiated by their aggregate size were tested using an automated pulse and receive system. The effect of aggregate size, and pulse frequency on attenuation and wavespeed are investigated. The pulse regime consisted of narrowband pulses ranging from 30 kHz to 500 kHz. The results show that high frequency pulses experienced greater attenuation than low frequency pulses. Whilst a link appears between the size of the aggregate and the rate of attenuation of high frequency signals. A strong negative correlation between amplitude loss and pulse frequency was observed. For the specimen containing coarse aggregate, pulse velocity was constant between 100 kHz and 500 kHz, whereas specimens containing coarse aggregate experienced frequency dependant attenuation. This testing shows the significant potential for an automated pulse and receive system, which could lead to the development of an autonomous health monitoring system. In addition, the approach can be instrumental in developing large data sets, that can be used in Machine Learning processes, to develop a deeper understanding of AE signal propagation in concrete materials.

A vine-copulas based multi-sensor fusion structural damage monitoring method and its application in dam engineering

As a civil engineer that is susceptible to the mechanism of slow and continuous deterioration, the dam must detect damage according to the static data of the arranged sensors, which is an important issue in structural health monitoring. Due to the characteristics of huge solid structures, damage with a slight degree and small range usually does not cause significant changes in the monitoring data of a single sensor. Therefore, it is difficult to effectively detect local damage by traditional monitoring methods that establish operating warning values for a single sensor. Currently, there have been some approaches to fuse sensor information that consider correlations between multiple sensors as well as the overall operational behavior of the dam. However, their objectives are focused on improving the accuracy of response variable prediction models without addressing the local damage identification aspect. In this study, we apply the Vine-Copula model for the first time in a multi-sensor information fusion dam damage detection method based on static monitoring data. In this way, it improves the sensitivity of local damage identification for huge solid structures. A prediction model is fitted with the measuring data of each sensor to obtain the residual series. Then the joint probability distribution of the multidimensional residuals is acquired by constructing the Vine-Copula model. Finally, the joint cumulative distribution function value is used as an alarm limit to determine whether the structure has an abnormal damage condition. The effectiveness and accuracy of the proposed method were demonstrated in both a numerical arch dam simulating local damage and an actual rockfill dam engineering with cracks at the crest.

Advancing structural health monitoring: Deep learning-enhanced quantitative analysis of damage in composite laminates using surface strain field

Composite materials have been widely used as critical components in aerospace applications due to their excellent performance characteristics. The real-time accurate identification and quantification of various types of damage within composite material structures pose a significant challenge. This study introduces an innovative damage detection method based on strain fields, which centrally employs deep learning techniques. Utilizing the Res-Mask R–CNN, this study accurately detects and categorizes various forms of damage within composite laminates, including open holes, subsurface holes, and delamination. Moreover, this method also enables precise localization and quantification of damaged areas. A series of experiments and simulations have validated the accuracy and robustness of the network model. Damage inversion experiments demonstrate that the area error of the damaged regions has been reduced to 7.4 %, and the positional error does not exceed 3.31 mm. In simulated scenarios, the shape context distance for complex damage contours does not exceed 0.21, indicating that the critical geometric features of the damage have been successfully preserved. This study provides an effective new approach for damage detection and real-time structural health monitoring of composite laminates.

Novel Deep Learning-Based Method for Seismic-Induced Damage Detection

Novel Deep Learning-Based Method for Seismic-Induced Damage Detection

A first step towards the detection of damage processes in endodontic Ni-Ti alloy files, using acoustic emission

Despite major instrumental developments over the last decade, endodontic files are still not infallible. It is well known that NiTi rotary files can break without any visible sign of deformation. Instrument breakage under combined flexion-torsion loading is still common in clinical practice. Unfortunately, breakage of this type of instrument mainly occurs in narrow canals, through pinching in the apical region. When such an incident occurs, the endodontist must adopt a debris retrieval strategy that is both stressful and not guaranteed success. This study proposes a new method for experimental damage detection leading to the fracture of Ni-Ti shape memory alloy endodontic files. It is based on the acoustic emission (AE) technique and mechanical parameters measured in real-time and image analysis. It has been shown that the AE results correlate with the damage observations and torque and force measurements recorded during the tests.Having carried out numerous root canal treatment on resin blocks, it appears that this new detection and analysis technique can be used to analyze and anticipate the first signs of damage leading to endodontic file failure. The technological development of such a method, at the level of the engine itself, associated with the act in service procedure, would constitute a revolution in the field of endodontics.

Structural Damage Detection under Ambient Excitation Using Symbolic Three-Order Square Matrix Formed by Specific-Interval-Sampled Time-Domain Signals.

In the structural health monitoring of vibration systems, varying excitation always affects the accuracy of damage identification. The proposed symbolic three-order square matrix damage detection method with the matrix norm as a damage indicator can solve the difficult problem of damage identification under ambient excitation. The new sampling pattern extracts data from signals in the time domain at specific intervals based on the structural properties with the help of the autocorrelation coefficient. Then, the data extracted are converted into symbols and arranged into a three-order square matrix, and the Frobenius norm of the matrix is used for structural damage identification as a reliable damage indicator. In this process, the transmissibility function is employed to eliminate the effects of varying excitation. First, the method was verified by a cracked simply supported beam-a simulated Abaqus model. Then, a wooden truss bridge in the laboratory and an actual engineering scenario under ambient excitation together demonstrated the effectiveness and accuracy of the damage identification method and proved the proposed method to be robust to different types of damage under ambient excitation. Compared with other related methods, this method is more intuitive and efficient.

Vibration based dual-criteria damage detection method using deep neural networks in highway bridges with steel girders

This article introduces a new method for assessing the damage in steel girders of highway bridges using deep neural networks. The method uses modified forms of modal strain energy damage index and modal flexibility damage index to train the neural network and prevent unsafe decisions. The neural network is trained using damage indexes achieved from numerical simulations of the bridge with different damage scenarios. Three types of neural networks, including convolutional neural network (CNN), Long short-term memory (LSTM) neural network, and conventional artificial neural network (ANN) are compared to achieve the best performance. The proposed method overcomes previous detection problems such as false-positive indications, limited damage locations, and scenarios, and insufficient accuracy in cases with multiple damage scenarios. The results show that the proposed method and CNN can accurately identify unspecified damage locations and severity in multi-span highway bridges. The new training method of the CNN deep neural network systems overcomes some shortcomings in ANN, such as being time-consuming, having a low convergence rate, and experiencing data overfitting. Additionally, the CNN training scheme can limit the need for massive amounts of input data and increase the speed and accuracy of network training, especially in multiple damage scenarios.

Omni-directional wavenumber dictionary modified imaging method for orthotropic composites damage detection using ultrasonic guided waves

The sparse reconstruction imaging method is promising for detecting damage in isotropic and quasi-isotropic materials. However, its effectiveness relies on an accurate dictionary. When applied to orthotropic materials without accounting for wavenumber directionality, the accuracy of the dictionary degrades, leading to inaccurate damage localization. To address this limitation, this paper presents an omnidirectional wavenumber dictionary modified imaging method for orthotropic composites damage detection. The omni-directional wavenumber dispersion curve of ultrasonic guided waves is calculated numerically by converting of elastic stiffness coefficient of orthotropic composites at various propagation angles. A modified propagation model, informed by the omni-directional wavenumber dispersion curve, enhances the precision of the acoustic field dictionary. Utilizing a coherent matched field processor, the method compares the scattered signal's envelope with the acoustic field dictionary's envelope to generate an ambiguity function, which in turn forms a damage image. Simulation and experimental results confirm the method's superiority in resolving damage localization inaccuracies and artifacts typically associated with orthotropic composites. The proposed method exhibits enhanced signal-to-noise ratio and lower positioning error, facilitating precise multi-damage detection in orthotropic composites compared to existing methods.

Recognition and quantification of apparent damage to concrete structure based on computer vision

To solve the problems of poor recognition of apparent concrete damage and the difficulty of efficient quantitative characterization of the damage parameters, this study proposes a damage detection method that integrates the target localization algorithm and the quantitative characterization algorithm of the damage based on computer vision. This paper proposes a YOLO v5-RS network combining Res2Net and SimAM to solve the problem of indistinctive apparent damage feature. The damage is segmented by image processing, and the crack and crush damage quantification method are proposed. The results show that compared with YOLO v5, the mAP and F1 of YOLO V5-RS are improved by 8.4% and 0.07, respectively, which indicates that the recognition of apparent structural damage has high robustness. To verify the recognition method’s generalization ability and the characterization method’s accuracy, four cases of different scale are introduced in this paper.