Structural Damage Diagnosis Research Articles

An improved generalized flexibility matrix-based damage identification technique for derrick steel structures

An improved generalized flexibility matrix-based method using matrix partitioning technique for structure damage identification is proposed. As an effective damage identification method, the generalized flexibility matrix requires fewer vibration frequencies and corresponding modal shapes compared with the traditional flexibility matrix method. By introducing a new partitioning technique of the matrices involved in the constructive process of the governing equation, the improved method simplifies the process of calculation with a dramatic reduction in computational cost while maintaining accuracy of identification results. In the case of incomplete measured modal data, an improved matrix partitioning technique based on the model expansion method is applied and the damaged indicators can be identified using partial measured modal data. A K-type derrick steel structure in service is considered as a numerical example for inspection the validity and feasibility of the proposed method. Numerical results show better accuracy and efficiency of this method for various damage scenarios, and can be used for damage diagnosis or health monitoring of other large structures.

Integrated MUSIC array for high-precision damage diagnosis in complex composite structures

Guided Wave (GW)-based Multiple Signal Classification (MUSIC) damage imaging presents several advantages, such as high resolution, which makes it a promising technique for localizing damage in composite structures. However, the application of this technology in aircraft is confronted with various challenges. The variability in performance of MUSIC array sensors is attributed to material and manufacturing process dispersion. Additionally, the conventional wiring of MUSIC array sensors adds considerable weight and is not compatible with complex structural configurations. Furthermore, within intricate configurations, the attenuation of scattering signals induced by structural damage impacts the accuracy of imaging. Moreover, the manual and individual placement of sensors on structures, along with structural anisotropy, may introduce phase errors in the signals detected by MUSIC array sensors. This can lead to a reduction in the accuracy of MUSIC imaging and result in compromised long-term sensor reliability. This paper proposes a high-precision integrated MUSIC array for the diagnosis of complex composite damage. This approach aims to address the challenges related to damage imaging in materials with complex structures. Impedance curve screening and surface-mount co-curing technology are utilized to manage the performance variation of MUSIC array sensors, enhance layout uniformity, and improve long-term stability. Subsequently, a focus compensation algorithm is proposed within the integrated MUSIC design to enhance precision, reduce weight, and adapt to complex structures. The effectiveness of the proposed method is confirmed through experimental validation on an actual complex composite wing box segment, demonstrating a maximum error of 2 cm in locating impact damage.

Diagnosis and assessment of cyclic freeze–thaw damage in tunnel lining concrete using piezoelectric-based electromechanical impedance technique

Cold regional tunnel linings extensively suffer from severe cyclic freeze–thaw damage, which adversely influences their stability, durability and in-service safety. Consequently, the diagnosis and assessment of cyclic freeze–thaw damage in concrete linings have garnered worldwide attention. This study presents a pioneering effort in using the PZT-based electromechanical impedance (EMI) technique to monitor the evolving damage within lining concrete concurrently exposed to bending loads and freeze–thaw cycles. First of all, ultrasonic measurements and four-point bending tests were performed on cyclically freeze-thawed concrete specimens under two different bending loads. Both the degrading flexural strength and the diminishing ultrasonic wave velocity were measured. Particularly, the damage evolution was characterized by the flexural strength degradation ratio, which exponentially increased by 44.81% and 64.28% under two bending scenarios, respectively. Moreover, conductance signatures driven by two vibration modes (d31 and d33 modes) of embedded piezoelectric transducers were recorded, and both localized and overall variations in the signals were analyzed. It is concluded that both the resonant frequency shift and the statistic metric RMSD within the d31-dominated frequency range could accurately indicate the cyclic freeze–thaw damage of lining concrete. Their linear correlation coefficients with the damage variable reached 0.957 and 0.935, respectively. This research establishes a quantitative framework for monitoring the progressive damage of tunnel lining subjected to freeze–thaw cycling using the EMI technique and lays the groundwork for a broader range of future applications in structure damage diagnosis and assessment.

Machine learning-based improvement of crack localization in concrete structures

Acoustic emission (AE) method is useful for damage detection in structures. However, processing the massive amount of AE data with traditional analysis methods is time-consuming. Therefore, machine learning (ML) integration provides a more rational and efficient solution by accelerating the data analysis and improving the damage detection accuracy. This study aims to improve source localization, which provides to identify cracking patterns by signal-based analysis, by training the ML model with the AE dataset for accurate damage diagnosis of concrete structures. Analyzes were conducted on the ML model using AE data collected on a concrete member under laboratory conditions. In this way, the ML model that learned signals with multi-variable wave characteristics and parameters was integrated into the source localization algorithm and thus, AE source location results were enhanced. Furthermore, due to its ability to identify damaged areas, this approach is essential for structural safety by providing early damage detection and accurate localization of cracks. This integration of the machine learning model with AE data will be considered as an advanced tool for the effective monitoring of damages in structures.

Damage localization in composite structures based on Lamb wave and modular artificial neural network

Lamb wave-based technology for damage diagnosis in composite structures has emerged as a promising tool for structural health monitoring (SHM). However, traditional SHM faces challenges in multi-sensor localization, including complex data processing, high costs, and cumbersome maintenance management. The current trend is to employ data-driven approaches, but achieving precise damage localization across the entire structure with fewer sensors still presents difficulties. To address this issue, a damage localization method based on Lamb wave envelope characteristics and modular artificial neural network (M-ANN) is developed. In this approach, the envelope characteristics are employed to characterize the damage information and reduce the data dimension. Subsequently, the M-ANN model is innovatively designed with dropout layers in each hidden layer, significantly enhancing performance on random datasets. In the composite laminate experiment using only four sensors, the proposed method achieves an average relative error of 2.96 % for random damage samples, with 95 % falling within 6.17 %, outperforming other advanced damage localization approaches. Additionally, the method is utilized to investigate the requirements for the relative density of data acquisition under different damage localization needs in composite structures.

Physics-Informed Machine Learning for Structural Damage Diagnosis in Aluminium Plates

Damage diagnosis plays a crucial role in Structural Health Monitoring (SHM) by facilitating the identification, localization, and estimation of the extent of defects in structures. Lamb waves, known for their sensitivity to defects, are widely employed in SHM methods for thin-walled structures. Most of those traditional methods require extracting damage indices from Lamb wave signals. This operation involves substantial post-processing and implies that part of the diagnostic information is lost. To solve those limitations and improve the damage diagnosis accuracy, machine learning methods have recently been proposed in the literature. However, the reluctance of the industrial sector to adopt conventional black-box models due to their lack of explainability poses a challenge. This study proposes a physics-informed machine-learning approach to address the limitations of standard black-box methods. Particularly, a Physics-Informed Neural Network (PINN) is implemented to predict the density of an aluminium plate based on measurements of plate displacements caused by Lamb wave excitation. This is made possible by the implementation of a specific loss function, which leverages physical knowledge in the form of the partial differential equation governing Lamb waves. Predicting the plate density based on measured displacements eliminates the need for artificial damage indices, utilizing the density variation itself to detect and localize damage. Additionally, the outputs of the PINN, rooted in physics equations, offer enhanced explainability compared to standard black-box models. The versatility of this framework extends to predicting material properties distributions for components, and efforts will be directed towards adapting the method for composite materials, where the approach may pose additional challenges.

High-Precision Monitoring Method for Bridge Deformation Measurement and Error Analysis Based on Terrestrial Laser Scanning

In bridge structure monitoring and evaluation, deformation data serve as a crucial basis for assessing structural conditions. Different from discrete monitoring points, spatially continuous deformation modes provide a comprehensive understanding of deformation and potential information. Terrestrial laser scanning (TLS) is a three-dimensional deformation monitoring technique that has gained wide attention in recent years, demonstrating its potential in capturing structural deformation models. In this study, a TLS-based bridge deformation mode monitoring method is proposed, and a deformation mode calculation method combining sliding windows and surface fitting is developed, which is called the SWSF method for short. On the basis of the general characteristics of bridge structures, a deformation error model is established for the SWSF method, with a detailed quantitative analysis of each error component. The analysis results show that the deformation monitoring error of the SWSF method consists of four parts, which are related to the selection of the fitting function, the density of point clouds, the noise of point clouds, and the registration accuracy of point clouds. The error caused by point cloud noise is the main error component. Under the condition that the noise level of point clouds is determined, the calculation error of the SWSF method can be significantly reduced by increasing the number of points of point clouds in the sliding window. Then, deformation testing experiments were conducted under different measurement distances, proving that the proposed SWSF method can achieve a deformation monitoring accuracy of up to 0.1 mm. Finally, the proposed deformation mode monitoring method based on TLS and SWSF was tested on a railway bridge with a span of 65 m. The test results showed that in comparison with the commonly used total station method, the proposed method does not require any preset reflective markers, thereby improving the deformation monitoring accuracy from millimeter level to submillimeter level and transforming the discrete measurement point data form into spatially continuous deformation modes. Overall, this study introduces a new method for accurate deformation monitoring of bridges, demonstrating the significant potential for its application in health monitoring and damage diagnosis of bridge structures.

Zero-shot knowledge transfer for seismic damage diagnosis through multi-channel 1D CNN integrated with autoencoder-based domain adaptation

Accurate and timely structural damage diagnosis is crucial to efficient disaster response and city renovation in post-earthquake events. The scarcity of labeled data hinders the powerful deep learning techniques from in-domain damage detection on target structures. Cross-domain transfer learning has emerged as a captivating strategy through digging knowledge from the abundant source domain to detect the damage in the target domain. However, the heterogeneity among multi-domain structures poses the challenge in seismic damage diagnosis. This study proposes a novel zero-shot knowledge transfer approach for seismic damage diagnosis through multi-channel one-dimensional convolutional neural networks (1D CNN) integrated with deep autoencoder (DAE)-based domain adaptation (DA). The framework consists of three modules, namely, data preprocessor adaptive to seismic vibration signals, DAE-based DA module, and damage diagnosis via multi-channel 1D CNN. The DA module is customized to seamlessly translate the unseen target-domain data to mimic latent representation via a DAE pretrained on the source data, thus realizing rigorous zero-shot learning. Imbalanced data distribution is also considered during the network training and testing. Two representative phases of knowledge transfer are performed to substantiate the knowledge transferability of the proposed method. The first phase involves multi-class damage quantification on two ASCE benchmark models from the simplified model to the refined one, and the second phase conducts binary damage detection on a three-story reinforced frame structure from the finite element numerical model to the laboratory-tested physical model. Both examples show that the proposed method exhibits high prediction accuracy and a lower false negative rate in achieving zero-shot knowledge transfer for cross-domain structural damage diagnosis. With a delicate network design for diverse data, the proposed knowledge transfer framework can be further extended from the present zero-shot approach to the few-shot learning paradigm, thus suggesting a feasible algorithm adaptability and promising engineering applicability.

A novel damage identification method based on acceleration response sensitivity and finite element model updating: Numerical and experimental

The utilization of time-domain data for structural damage diagnosis and finite element model updating has several benefits, such as direct implementation of the measured data with no requirement for domain changing and susceptibility to structural damages. This study introduces a straightforward sensitivity relation for the measured acceleration response, avoiding the requirement for computational techniques like direct differentiation methods. The proposed equation establishes a linear relationship between variations of the structural parameters and structural responses. The proposed sensitivity equation operates at the level of improved equations and exhibits greater accuracy compared to the current approaches. The numerical evaluation of the proposed sensitivity equation on two offshore jacket platforms reveals the accuracy of the proposed method. Additionally, an experimental case study to examine the efficacy and validation of the introduced sensitivity relation in real-world settings demonstrates the procedure’s viability. The numerical and experimental results reveal the accuracy of the proposed sensitivity equation.

Influence of microstructure and geometric dimension on metal magnetic memory testing

Metal magnetic memory testing (MMMT) is a prominent NDT method for early damage diagnosis of ferromagnetic structures due to its significant advantages in stress concentration state evaluation. While it is still challengeable to apply the existing criteria from the laboratory to practical application, and some of the main reasons are the microstructure transformation and geometric dimensions for the ferromagnetic material itself. To explore the influence of microstructure and geometric dimension on MMMT, static tensile tests of specimens made of Optim 900QC steel with different microstructures and geometric dimensions have been carried out, and the MMMT signals of the specimens during the tests were collected and analyzed. It is found that the microstructure not only change the strength of the steel, but also affect the MMMT signal of the steel, and the bigger the grain is, the stronger the magnetic field is. Geometric dimension would also affect the MMMT signal, and thickness affects the MMMT signal the most, width less, and length the least. The results of the present work indicate that the microstructure and the geometric dimensions should be the same to fix the gap of damage determination criteria between the laboratory and the engineering application. When it is impossible to fabricate specimens with the same dimension with the engineering structure, set the same thickness would improve the accuracy of the criteria.

Enhancing Seismic Damage Detection and Assessment in Highway Bridge Systems: A Pattern Recognition Approach with Bayesian Optimization.

Highway bridges stand as paramount elements within transportation infrastructure systems. The ability to ensure swift recovery after extreme events, such as earthquakes, is a fundamental trait of resilient communities. Consequently, expediting the recovery process necessitates near real-time diagnosis of structural damage to provide dependable information. In this study, a data-driven approach for damage detection and assessment is investigated, focusing on bridge columns-the pivotal supporting elements of bridge systems-based on simulations derived from nonlinear time history analysis. This research introduces a set of cumulative intensity-based damage features, whose efficacy is demonstrated through unsupervised learning techniques. Leveraging the support vector machine, a prominent pattern recognition algorithm in supervised learning, alongside Bayesian optimization with a Gaussian process, seismic damage detection and assessment are explored. Encouragingly, the methodology yields high estimation accuracies for both binary outcomes (indicating the presence of damage or the occurrence of collapse) and multi-class classifications (indicating the severity of damage). This breakthrough opens avenues for the practical implementation of on-board sensor computing, enabling near real-time damage detection and assessment in bridge structures.

Data-Driven Structural Health Monitoring: Leveraging Amplitude-Aware Permutation Entropy of Time Series Model Residuals for Nonlinear Damage Diagnosis.

In structural health monitoring (SHM), most current methods and techniques are based on the assumption of linear models and linear damage. However, the damage in real engineering structures is more characterized by nonlinear behavior, including the appearance of cracks and the loosening of bolts. To solve the structural nonlinear damage diagnosis problem more effectively, this study combines the autoregressive (AR) model and amplitude-aware permutation entropy (AAPE) to propose a data-driven damage detection method. First, an AR model is built for the acceleration data from each structure sensor in the baseline state, including determining the model order using a modified iterative method based on the Bayesian information criterion (BIC) and calculating the model coefficients. Subsequently, in the testing phase, the residuals of the AR model are extracted as damage-sensitive features (DSFs), and the AAPE is calculated as a damage classifier to diagnose the nonlinear damage. Numerical simulation of a six-story building model and experimental data from a three-story frame structure at the Los Alamos Laboratory are utilized to illustrate the effectiveness of the proposed methodology. In addition, to demonstrate the advantages of the present method, we analyzed AAPE in comparison with other advanced univariate damage classifiers. The numerical and experimental results demonstrate the proposed method's advantages in detecting and localizing minor damage. Moreover, this method is applicable to distributed sensor monitoring systems.

On the effectiveness of sparse regularization for structural damage diagnosis using dynamic strain measurements

Strain measurement is considered inherently suitable for structural health monitoring due to the ease of extracting damage-sensitive features. However, the need for pre- and post-damage feature extraction, especially in the absence of baseline data for aging infrastructures in service, has engendered skepticism concerning the practical efficacy of strain-based damage diagnosis. To address this, this study incorporates limited prior information on structures and sparse regularization to ascertain the locations and severities of structural damages based on dynamic strain response data. A model-assisted approach is presented, including the typical three-step process of damage feature extraction, finite element modeling, and analytical sensitivity-based model updating. In particular, sparse regularization technique aids in robustly identifying structural damage by tackling the hindrance encountered during model updating, involving ill-posedness and the impact of measurement and modeling uncertainties. The approach’s effectiveness is substantiated through a numerical investigation of a Bailey truss bridge model exposed to operating loads and an experiment with a steel beam equipped with an array of fiber Bragg grating sensors. The results demonstrate that using the proposed damage diagnosis approach enables accurately locating and quantifying element-level damages, even when significant modeling errors or a lack of baseline features exist.

Structural Damage Diagnosis of Aerospace CFRP Components: Leveraging Transfer Learning in the Matching Networks Framework

This paper introduces a damage diagnosis method based on the reassignment method and matching networks (MNs) to study the structural health monitoring of aerospace composite material components. This aims to facilitate the mapping of signal features to complex failure modes. We introduce a signal processing technique based on the reassignment method, employing a sliding analysis window to re‐estimate local instantaneous frequency and group delay. By utilizing the short‐time phase spectrum of the signal, we correct the nominal time and frequency coordinates of the spectrum data, aligning them more accurately with the true support region of the analyzed signal. Subsequently, this paper developed a deep matching network (DMN) damage diagnosis model based on MNs. This model utilizes a convolutional neural network (CNN) to extract damage‐related features from the signal and introduces the full context embedding (FCE) method to enhance the compatibility of sample embeddings. In this process, the embeddings of each sample in the training set should be mutually independent, while the embeddings of test samples should be regulated by the distribution of training set sample data. Ultimately, the damage category of test samples is determined based on cosine similarity. We validate our model using damage sample data collected from experiments and simulations conducted under varying components and operating conditions. Comparative assessments with five mainstream methods reveal an average accuracy exceeding 96%. This underscores the exceptional recognition accuracy and generalization performance of our proposed method in cross‐operating condition fault diagnosis experiments concerning aircraft composite material components.

Autonomous Identification of Bridge Concrete Cracks Using Unmanned Aircraft Images and Improved Lightweight Deep Convolutional Networks

The identification of the development of structural defects is an important part of bridge structure damage diagnosis, and cracks are considered the most typical and highly dangerous structural disease. However, existing deep learning‐based methods are mostly aimed at the scene of concrete cracks, while they rarely focus on designing network architectures to improve the vision‐based model performance from the perspective of unmanned aircraft system (UAS) inspection, which leads to a lack of specificity. Because of this, this study proposes a novel lightweight deep convolutional neural network‐based crack pixel‐level segmentation network for UAS‐based inspection scenes. Firstly, the classical encoder‐decoder architecture UNET is utilized as the base model for bridge structural crack identification, and the hourglass‐shaped depthwise separable convolution is introduced to replace the traditional convolutional operation in the UNET model to reduce model parameters. Then, a kind of lightweight and efficient channel attention module is used to improve model feature fuzzy ability and segmentation accuracy. We conducted a series of experiments on bridge structural crack detection tasks by utilizing a long‐span bridge as the research item. The experimental results show that the constructed method achieves an effective balance between reasoning accuracy and efficiency with the value of 97.62% precision, 97.23% recall, 97.42% accuracy, and 93.25% IOU on the bridge concrete crack datasets, which are significantly higher than those of other state‐of‐the‐art baseline methods. It can be inferred that the application of hourglass‐shaped depth‐separable volumes can actively reduce basic model parameters. Moreover, the lightweight and efficient attention modules can achieve local cross‐channel interaction without dimensionality reduction and improve the network segmentation performance.

Structure damage diagnosis of bleacher based on DSKNet model

Structure damage diagnosis of bleacher based on DSKNet model

Musculoskeletal ultrasonography in rheumatic diseases.

Ultrasonography is an imaging technique based on sound waves used for the evaluation of soft tissues. Sound waves have been used for a long time in nonmedical fields, including military defense systems, radar systems, and detection of icebergs. Technological advances resulted in new techniques becoming available for medical imaging, including ultrasonography, magnetic resonance imaging, and computed tomography. Nowadays, the use of imaging has become a gold standard protocol in the diagnosis of many diseases, and recently developed diagnosis and therapy options provide more efficient treatment of rheumatic diseases. Thus, it has become possible to prevent structural damage and disability in patients with rheumatic disease. Musculoskeletal ultrasonography is becoming a preferred imaging technique for rheumatic diseases, as it has many advantages. Among its advantages are being inexpensive, being radiation-free, having a dynamic image capacity, helping to detect disease activity, and helping with early detection and diagnosis of structural damage. This review summarizes the use of ultrasonography in rheumatic diseases.

Application of Graph Convolutional Neural Networks Combined with Single-Model Decision-Making Fusion Neural Networks in Structural Damage Recognition

In cases with a large number of sensors and complex spatial distribution, correctly learning the spatial characteristics of the sensors is vital for structural damage identification. Graph convolutional neural networks (GCNs), unlike other methods, have the ability to learn the spatial characteristics of the sensors, which is targeted at the above problems in structural damage identification. However, under the influence of environmental interference, sensor instability, and other factors, part of the vibration signal can easily change its fundamental characteristics, and there is a possibility of misjudging structural damage. Therefore, on the basis of building a high-performance graphical convolutional deep learning model, this paper considers the integration of data fusion technology in the model decision-making layer and proposes a single-model decision-making fusion neural network (S_DFNN) model. Through experiments involving the frame model and the self-designed cable-stayed bridge model, it is concluded that this method has a better performance of damage recognition for different structures, and the accuracy is improved based on a single model and has good damage recognition performance. The method has better damage identification performance in different structures, and the accuracy rate is improved based on the single model, which has a very good damage identification effect. It proves that the structural damage diagnosis method proposed in this paper with data fusion technology combined with deep learning has a strong generalization ability and has great potential in structural damage diagnosis.

Guided Wave Characteristic Research and Probabilistic Crack Evaluation in Complex Multi-Layer Stringer Splice Joint Structure.

Multi-layer and multi-rivet connection structures are critical components in the structural integrity of a commercial aircraft, in which elements like skin, splice plate, strengthen patch, and stringer are fastened together layer by layer with multiple rows of rivets for assembling the fuselage and wings. Their non-detachability and inaccessibility pose significant challenges for assessing their health states. Guided wave-based structural health monitoring (SHM) has shown great potential for on-line damage monitoring in hidden structural elements. However, the multi-layer and multi-rivet features introduce complex boundary conditions for guided wave propagation and sensor layouts. Few studies have discussed the guided wave characteristic and damage diagnosis in multi-layer and multi-rivet connection structures. This paper comprehensively researches guided wave propagation characteristics in the multi-layer stringer splice joint (MLSSJ) structure through experiments and numerical simulations for the first time, consequently developing sensor layout rules for such complex structures. Moreover, a Gaussian process (GP)-based probabilistic mining diagnosis method with path-wave band features is proposed. Experiments on a batch of MLSSJ specimens are performed for validation, in which increasing crack lengths are set in each specimen. The results indicate the effectiveness of the proposed probabilistic evaluation method. The maximum root mean squared error of the GP quantitative diagnosis is 1.5 mm.

Intelligent damage diagnosis method for offshore platforms based on enhanced stabilization diagrams and convolutional neural network

Considering that it is difficult to evaluate the damage state of offshore platform structures under environmental excitation by stochastic subspace identification (SSI) stability diagrams alone, an intelligent damage diagnosis method based on enhanced stability diagrams and convolutional neural network (CNN) is proposed. The data-driven SSI algorithm and covariance-driven SSI algorithm are utilized to identify stability diagrams of monitoring data, and the stability diagrams of the two algorithms are superimposed together for image enhancement. Further, the enhanced stability diagrams are used as input samples for CNN training to distinguish the damage state of the structure. In the meanwhile, the whale optimization algorithm is employed to optimize the hyper parameters of CNN to ulteriorly improve the recognition performance. The final test accuracy of CNN is 97.20%, and is 13.09% higher than before hyper parameter optimization, which indicates that the damage diagnosis method based on enhanced stability diagrams and CNN is reasonable and effective, and is expected to be applied to real-time damage diagnosis of offshore platform structures.