A semi-analytical multimodal Lamb wave imaging algorithm for damage identification in structural health monitoring.

Machine learning inverse surrogates for damage identification in plates based on Lamb waves.

Two-Step Algorithmic Adaptive Particle Filter for System Identification of Sudden Structural Damage

Segmentation-enhanced multi-scale deep hashing for chest X-ray image retrieval.

Rapid identification of surface damage in ablative materials via inversion of isotherm dynamics

Tensile damage identification of high-strength CrMoV steel based on acoustic emission and machine learning

Cross-domain structural damage identification using frequency guided cycle-consistent generative adversarial network

Energy difference of dynamic displacement curvature with frequency band selection for damage identification in bridges

Damage Identification Based on Bridge Displacement Response Considering Autocorrelation of the Dynamic Component

While supervised structural health monitoring (SHM) systems can potentially accurately detect and localize damage in bridge structures, they require labeled datasets containing healthy and damaged states to develop decision-making models. Obtaining supervised data from in situ bridges is often impractical. Unsupervised algorithms address this challenge by leveraging baseline (i.e., “healthy”) data, thereby eliminating the need for damaged datasets to detect anomalies. Conventional SHM techniques rely on sensor data to assess the structural condition; however, accurately detecting damage remains a challenge, especially when dealing with differing structure types and sizes and varying loading conditions. This study introduces an unsupervised damage detection methodology that aims to classify bridge health using structural response data under variable loading by leveraging deep learning. A variational autoencoder (VAE) network was employed to develop a data-driven methodology to identify structural anomalies based on response data collected during tests of an in situ bridge. Collected datasets included strain time histories representing three structural states (i.e., “healthy,” two levels of damage). The model was trained using strain data collected from healthy bridge loading tests and validated on separate healthy trials, while testing included both healthy and damaged scenarios to evaluate the method’s generalization and damage sensitivity. A VAE network was trained to learn underlying patterns of healthy behavior under moving live load. The training helped develop a compressed strain time-history representation using a network encoder and accurately reconstructed that input from a lower-dimension space. Normalized data reconstruction errors were used to define a damage index that permitted quantitative assessment of structural deterioration. In addition, clustering each test dataset corresponding as a function of structural state helped quantify response deviation from the healthy state. Results demonstrated that the proposed approach effectively detected increasing damage levels, thereby distinguishing different structural states from one another. Results highlighted the potential robustness and adaptability of the proposed approach to real-world SHM applications.

Purpose Aiming at the problems of high cost, high risk and traffic impact of in situ load testing of Bridges after fire, this paper proposes a fire bridge structural damage identification method based on a fire dynamics simulator (FDS)-Kriging model modification and a unit modal strain energy damage index, so as to effectively assess the damage of bridge structures after fire. Determine whether it can continue to be used and whether it affects driving safety. Design/methodology/approach Propose a fire bridge structural damage identification method to establish the FDS-Kriging model correction. Findings The finite element model of the fire bridge modified using FDS-Kriging approach can reflect the actual situation of the bridge structure more accurately, and the damage location and degree identified by the modal strain energy method are consistent with the actual bridge. Therefore, the effectiveness of the proposed method has been verified, and a new strategy for fire bridge damage identification has been provided. Research demonstrates that the finite element model of the fire-damaged bridge, modified using the FDS-Kriging method, can more accurately reflect the actual structural state. Moreover, the damage location and severity identified via the modal strain energy method align well with the actual bridge conditions. Thus, the effectiveness and engineering applicability of the proposed method are validated, offering a comprehensive new strategy and technical support for the integrated performance evaluation, damage identification and reliability analysis of fire-damaged bridges. Originality/value By determining the finite element correction interval and combining it with the Kriging model, the method realizes the fine correction of the finite element model of the fire bridge. Structural damage identification is carried out by using the unit modal strain energy damage index. This verifies the effectiveness and engineering applicability of the proposed method, which offers a novel approach and technical support for the comprehensive performance evaluation, damage identification and reliability analysis of fire-damaged bridges.

ABSTRACT Load-bearing structures are critical components in buildings, however, during service, they are susceptible to damage due to various factors. If such damage cannot be detected and addressed in a timely manner, it may lead to serious consequences. Therefore, this paper proposes a damage imaging and identification method in cylindrical structures based on a fused damage index formulated in the cylindrical coordinate system, taking cylindrical concrete structures as the research object. In this method, the direct waves of guided wave response signals before and after structural damage are utilised to construct a fused damage index. Furthermore, a GE-RAPID (Geometrically Extended RAPID) algorithm is proposed, which extends the planar elliptical path principle of the traditional RAPID algorithm to the cylindrical coordinate system, thereby enabling three-dimensional damage identification and imaging of cylindrical structures. Numerical simulations and experimental validations demonstrate that the proposed method can effectively achieve the identification and imaging of single, multiple, and different types of damage in cylindrical structures. The results indicate that the proposed approach exhibits satisfactory damage identification performance, providing an important reference for research on damage detection in cylindrical structures.

Abstract Modal sensitivity-based model updating has proven to be an effective approach for damage identification. However, the numerical ill-conditioned problem due to the large condition number of the sensitivity matrix and the uncertainties caused by inadequacies in models and noise in measurements greatly affect the performance of existing modal sensitivity-based model updating. In our early work, we have proposed a robust sparse Bayesian learning (RSBL) method, in which the mixture of Gaussians (MoGs) is employed to accurately model the real uncertainties of damage identification. RSBL effectively mitigates the impact of uncertainties on damage identification, but its performance is still limited by the ill-conditioned problem. In this paper, we find theoretically that the sensitivity matrix’s condition number governs the accuracy of damage identification, and propose to reduce the sensitivity matrix’s condition number by incorporating a matrix balancing in RSBL. As a result, an improved RSBL method based on modal sensitivity using matrix balancing and MoGs is proposed, and it is solved through an iterative expectation-maximization algorithm combined with the Laplace approximation. Extensive numerical and experimental studies show that the proposed method significantly reduces the sensitivity matrix’s condition number, which in turn remarkably improves the accuracy of damage identification compared to RSBL.

Sparse Bayesian learning achieves great success in damage identification by employing a sparsity-inducing prior distribution on the sparse coefficients. However, if the input force is unknown, a sparse prior cannot be applied to both the damage and force parameters. In order to construct a sparse Bayesian learning model for damage and unknown load input identification, a sensitivity-based sparse Bayesian method for the damage detection with unknown input is proposed. An optimization equation is constructed on the basis of the dynamic response sensitivity to convert the complex non-linear relationships into linear equations. The prior information for the force and damage parameters is established using uniform and Gaussian priors, respectively, depending on the specific characteristics of each parameter. The Bayesian learning framework based on the sensitivity-based model is derived to compensate the linear truncation errors and measurement noise. The validation of the proposed approach is conducted using both a numerical frame structure and an experimental structure. Results indicate that this method can simultaneously identify both damage and forces, even when faced with significant measurement noise and limited sensor data.

Railroad bridges are a crucial component of the U.S. freight rail system, which moves over 40% of the nation’s freight. However, ageing bridge infrastructure pose significant safety hazards and risk service disruptions. The U.S. rail network includes over 100,000 railroad bridges, averaging one every 1.4 miles of track, with steel bridges comprising over 50% of the network’s total bridge length. Early identification of damage in these bridges remain challenging tasks. This study proposes a physics-informed neural network (PINN) based approach for damage identification in steel truss railroad bridges. The proposed approach employs an unsupervised learning scheme that utilises train wheel load data and bridge response during train crossing events as inputs for damage identification. The PINN model explicitly incorporates the governing differential equations of the linear time-varying bridge-train system. Herein, this model employs a recurrent neural network based architecture incorporating a custom Runge-Kutta integrator cell, designed for gradient-based learning. A case study on the Calumet Bridge in Chicago, Illinois, with simulated damage scenarios, is used to demonstrate the model’s effectiveness in identifying damage while maintaining low false-positive rates. Furthermore, the damage identification pipeline is designed to integrate prior knowledge for enabling context-aware assessment of bridge’s condition.

ABSTRACT This paper proposes a damage detection method enhanced by a multi-scale product feature, which combines mode shape curvature and stationary wavelet transform (SWT) to address the difficulty in locating damage in composite laminated beams using traditional mode shape identification. The effectiveness of this method has been validated through numerical modelling and experimental validation. The primary innovation lies in the construction of an integrated damage identification framework that fuses ‘Mode Shape Curvature-SWT-Multi-Scale Product’. This framework effectively amplifies the local singularity induced by damage by using mode shape curvature as the initial input. Furthermore, it employs a multi-scale product strategy to achieve synergistic enhancement of damage features and nonlinear suppression of background noise. By using mode shape curvature as the SWT input, low-frequency damage features are more effectively elicited, causing the D3 frequency band to exhibit distinct damage peaks. Implementing the multiplication strategy further improves damage localization accuracy by 33%. In addition, a scanning laser vibrometer (PSV-400) was employed to measure the mode shapes of a carbon fibre laminated beam containing a pre-set crack, and damage detection on mode shape curvature. The results demonstrate that the proposed method can accurately identify damage locations, effectively validating its efficacy and practicality for detecting damage in composite laminated beams.

Wind turbine bearings play an important role in power generation operations, and their damages will cause security risks. To identify the damages of wind turbine bearings effectively, a novel stochastic resonance assisted deconvolution method is proposed. In this method, two key parts of deconvolution are designed for extracting damage component. On the one hand, traditional second-order stochastic resonance (SSR) is improved based on parameter exploration and the defined indicator. Besides, an adjusted SSR technology is developed and fused with minimum Mahalanobis distance criterion to get the objective function, which is utilized for guiding the deconvolution orientation. On the other hand, a filter structure named iterative approximation structure is creatively constructed by the eigenvectors of covariance matrix for updating the filter coefficients of the deconvolution operation, which is utilized to recover damage component from the measured signal. The analysis results of the experimental signals and the engineering case demonstrate that this proposed method can effectively identify the damages, and the characteristic extraction ability, as well as the identification precision of this proposed method are better than those contrastive methods.

Structural damage identification is a critical technique for ensuring the safety and reliability of large-scale civil structures. However, existing purely data-driven approaches based on deep learning still suffer from limited physical interpretability and generalization capability. To address this limitation, a physics-informed graph neural network framework, namely the Temporal Power Flow Graph Network (TPF-GNet), is proposed. The principal innovation of TPF-GNet is the Temporal Power Flow Propagation (TPFP) module, which explicitly characterizes energy transmission in structural dynamics and embeds dynamic power flow into the message-passing process of graph neural networks. TPF-GNet utilizes multi-sensor acceleration responses around a target node as input, reconstructs the target sensor's acceleration time history by simulating the energy flow process, and enables unsupervised damage detection and localization through reconstruction errors. Numerical simulations and scaled benchmark frame tests demonstrate that TPF-GNet surpasses conventional GNN and LSTM baseline models in both accuracy and physical interpretability. The results demonstrate that incorporating dynamic power flow markedly improves the model's ability to capture structural state changes induced by stiffness degradation or local damage. This study establishes a physics-constrained paradigm for structural health monitoring, particularly well-suited to engineering applications without damage labels.

ABSTRACT Identification of damage and key structural elements is vital to the monitoring and management of civil engineering projects, education, and training. However, practical inspection training is often constrained by cost, safety risk, and limited access to real structures, which reduces opportunities for repeated practice and feedback‐rich learning. To address these constraints, recent research has explored virtual reality (VR) in civil engineering to deliver immersive training for infrastructural inspections and reduce reliance on in‐person field trips and site visits. Despite the many advantages of VR as a learning tool, its adoption in civil engineering education remains limited. As a result, many engineers‐in‐training receive limited opportunities to practice realistic inspection workflows that combine defect recognition with structural health monitoring (SHM) interpretation. This paper presents a novel VR‐based educational tool designed to teach visual damage identification and structural condition assessment through immersive, scaffolded simulations. In this research, users explore a photorealistic 3D bridge reconstructed through drone‐based photogrammetry, annotate multiple damage types, and interact with embedded virtual sensors displaying multi‐year structural data collected from real‐world instrumentation. Unlike traditional approaches, the system integrates gamified scoring, real‐time feedback, and both qualitative and quantitative analysis tasks into a single, performance‐tracked learning experience. A classroom study with graduate students evaluated the tool's impact on learner motivation and confidence using a structured motivation model and a validated engineering self‐efficacy scale, demonstrating measurable improvements in damage assessment skills. This study advances the educational use of VR in civil engineering by combining interactive infrastructure scans, authentic sensor data, and experiential learning to offer a compelling, cost‐effective alternative to traditional field‐based inspection training.

Guided wavefields in composite structures contain a wealth of information related to anomalies caused by interactions between waves and structural damage. Guided wave curvature has emerged as one of the most important damage indices due to its ability to extract spatial characteristics of the full wavefield. However, its practical application is limited by the classical modal curvature method, which requires central difference estimation. This approach is highly sensitive to measurement resolution and noise, resulting in poor stability and reduced reliability in damage identification. To address these limitations, a two-dimensional Fourier spectral method for guided wave curvature estimation is proposed. This study investigates the sensitivity of curvature derived from different guided wave modes, namely the symmetric and antisymmetric modes, in relation to damage detection. The two-dimensional Fourier transform is applied in the wavenumber domain to compute the modal curvature of the wavefields with improved numerical stability. The method is further assessed for its robustness to noise using experimental data obtained from composite structures. Compared with the classical central difference method, the proposed approach demonstrates significantly enhanced noise tolerance while preserving the accuracy of damage localization. The results validate that the twodimensional Fourier spectral curvature method provides a stable and reliable means for detecting invisible damage in composite materials.