Structural Damage Identification Research Articles

Identification of Structural Damage by Rate of Change of Non-Dimensional Displacement of Beams Subject to Moving Loads

Identification of Structural Damage by Rate of Change of Non-Dimensional Displacement of Beams Subject to Moving Loads

Comparison of the Applicability of Bayesian Filters for System Identification of Sudden Structural Damage

Comparison of the Applicability of Bayesian Filters for System Identification of Sudden Structural Damage

Development of a wireless multichannel miniature impedance measurement system and its application for bolt loosening detection

The piezoelectric impedance-based technique is always regarded as one of the most promising structural health monitoring and nondestructive evaluation methods. In recent years, impedance measurement chip AD5933 with the characteristics of high integration and cost-effectiveness makes it possible to address the huge and high-cost problems of the commercialized impedance measurement instrument during the process of structural health monitoring and defect identification. However, it still faces lots of challenges for the chips to be utilized in practical applications due to several limitations, such as short distance for data transmission, single measurement channel and artificial attendant requirement. In this paper, a wireless multichannel miniature impedance measurement system composed by the front-end measurement device and the remote measurement and control platform on the server, is firstly developed and presented with the functions of wireless data transmission, multi-channel acquisition and remote data post-processing. Subsequently, the design concept and composition of the system were introduced in detail. Then, a series of piezoelectric transducers related tests were conducted to validate its impedance measurement performance, especially when comparing with the ones measured by commercialized instruments. In addition, to verify its effectiveness and feasibility of the developed system for the structural damage detection, a bolt loosening detection experiment on the flange connection of a pipeline specimen was investigated for its damage localization and severity quantification. Finally, all the results demonstrated that the developed system provides a great possibility to be used as a convenient and portable impedance measurement tool for the civil structural health monitoring and damage identification in practical applications.

Structural damage identification based on Bayesian updating

Due to factors such as model accuracy, sensor arrangement, noise influence, eigenvalue selection and the influence of local damage on the overall response, the structural damage identification process inevitably has uncertainties, so it is necessary to introduce probabilistic statistical methods to improve its accuracy and robustness. In this paper, structural damage identification is carried out based on Bayesian updating. Bayesian updating is combined with real-time monitoring data (e.g. displacement, acceleration), and the real-time data reflect the current state of the structure and contain damage information. The experimental results show that the update results of the Bayesian method correlate well with the actual data, which verifies the feasibility of Bayesian updating in structural damage identification. The structural prior probability can be effectively updated by this method, which shows high accuracy and robustness in structural damage identification and is able to maintain stable performance under different working conditions and environments. Based on Bayesian updating, this structural damage identification method provides a new technical means for structural health monitoring and damage assessment, with broad application prospect and development space.

Piezoelectric Impedance-based Structural Damage Identification Empowered with Tunable Circuitry Integration and Multi-objective Optimization based Inverse Analysis

Abstract The piezoelectric impedance-based technique is increasingly recognized for its promise in structural health monitoring and damage identification. Built upon their self-sensing actuation capability, piezoelectric transducers can be integrated to host structures to acquire the system-level impedance information in high frequency range with small wavelength. Furthermore, the frequency-sweeping harmonic excitations in impedance measurements lead to the potential for model-based inverse identification of damage location and severity. A major challenge in damage identification, however, is that the inverse analysis is generally underdetermined, as the measurement information may not be adequate to yield a unique solution. In this research, a new methodology of tunable sensing in conjunction with multi-objective optimization inverse analysis is established. Taking advantage of the two-way electromechanical coupling of piezoelectric transducers, tunable inductance is integrated into the measurement circuit. For the same damage scenario, by tuning the inductance to a series of values, a family of impedance measurements can be acquired. Meanwhile, the inverse analysis is cast into a multi-objective optimization problem, aiming at minimizing the difference between measurement and model prediction and achieving sparsity in damage index vector. A Q-learning based multi-objective particle swarm optimization is synthesized to reach a small yet diverse solution set. We report the circuitry integration details as well as the algorithm enhancement with systematic case investigations. It is validated that the new methodology with enriched measurement can produce smaller solution set encompassing the true damage scenario, thereby providing vital information for diagnoses and prognosis.

Damage Identification of Plate Structures Based on a Non-Convex Approximate Robust Principal Component Analysis

Damage Identification of Plate Structures Based on a Non-Convex Approximate Robust Principal Component Analysis

Multi-stage damage identification method for PC structures based on machine learning driven by piezoelectric singular feature

Efficient and accurate damage identification methods are great significant for ensuring the structural safety. This study proposes a multi-stage damage identification method for prestressed concrete (PC) structures based on machine learning driven by piezoelectric singular feature to improve the identification accuracy. This method extracts the singular value vector in the piezoelectric signal as the damage feature by multi-layer wavelet packet transform and singular value decomposition. The singular value vectors are put into the improved back propagation neural network (BPNN) model to achieve complete damage identification. This method is verified by analyzing the piezoelectric signals collected by PZT patches based on the static load failure test. The results show that the amplitude and energy of the signal gradually decreases and the frequency subject gradually develops from high frequency to low frequency with the development of damage. The extracted singular values effectively retain the main information of the piezoelectric signal as damage feature. The peak singular value decreases from fast to slow with the development of damage, which finally tends to be stable. The improved BPNN model has strong flexibility and adaptability, which enhances its ability of damage identification. The proposed method can achieve high-precision damage identification using piezoelectric signals, which has great application potential in the field of damage identification for PC structures.

Novel approach for precise identification of vibration frequencies and damping ratios from free vibration decay time histories data of nonlinear single degree of freedom models

The significance of Single Degree of Freedom (SDOF) systems lies in their ability to serve as foundational elements for modeling more complex dynamic problems. By capturing essential dynamic behavior with simplicity, SDOF models enable efficient analysis and comprehension of complex systems, justifying the investigation of these simplified models. In nonlinear scenarios, SDOF models result in time series data wherein vibration frequencies vary over time. Classically, time–frequency or Hilbert transforms applied to temporal responses are frequently used to identify the evolution of frequencies and damping ratio over time. These techniques provide results that reflect the spectrum composition achieved for the analyzed time window and present difficulties in precisely determining the magnitude and the exact instant of an effective frequency or damping ratio variation. In this sense, this work introduces a new methodology capable of accurately identifying the vibration frequency as a function of time, i.e., the instantaneous frequency, along with the instantaneous damping ratio. At this initial stage, the focus is on validating the methodology by comparing its performance with the classical approach based on time–frequency transforms. The initial results obtained from synthetic free vibration decay responses of SDOF nonlinear models highlight the accuracy of our findings compared to those obtained from time–frequency transforms. The presented methodology holds promise for further advancement, with potential impacts including structural damage identification, modal identification and nonlinear dynamic analysis.

Structural damage identification by using physics-guided residual neural networks

In recent years, vibration-based structural damage identification has made significant progress by exploiting data-driven deep learning techniques, which can efficiently extract damage-sensitive features from a large amount of data. However, in some practical engineering applications, large volumes of measurement data are not readily available. This paper proposes a novel physics-guided residual neural network (PhyResNet) framework to improve the robustness and accuracy of structural damage identification under data-scarce conditions. In contrast to the state-of-the-art purely data-driven ResNet, the proposed method embedded available physics knowledge (e.g., governing equations of dynamics) of structures into the feature learning process via a novel physics-based loss function. The input-output relationship of the network is constrained to retain its physical meaning implicitly while the demand for large amounts of labeled training data is reduced. Notably, even with only 5 % of the dataset used for training, PhyResNet achieves a 13.1 % improvement in R-Value. The performance of the proposed approach is evaluated through both numerical and experimental verifications. Results demonstrate that damage localization and quantification are achieved with high accuracies and good robustness.

An output-only damage identification method based on reinforcement-aided evolutionary algorithm and heterogeneous response reconstruction

The absence of excitation measurements may pose a huge challenge in the application of many damage identification methods since it is difficult to acquire the external excitations, such as wind load, traffic load. To deal with this issue, a novel output-only structural damage identification approach based on reinforcement-aided evolutionary algorithm and heterogeneous response reconstruction with Bayesian inference regularization is developed. On the one hand, heterogeneous measurements (e.g., displacements, strains, accelerations) are rescaled and reconstructed with the aid of Bayesian inference regularization technique. Structural damages are identified by minimizing the discrepancies between the measured and reconstructed responses. On the other hand, to solve the optimization-based inverse problem, a reinforcement-aided evolutionary algorithm, named Q-learning hybrid evolutionary algorithm (QHEA), integrating Jaya algorithm, differential algorithm, and Q-learning algorithm is proposed as search tool. To validate the feasibility and applicability of the proposed method, numerical studies on a three-span beam structure and laboratory tests on a five-story steel frame structure are carried out. The effects of data rescaling and data fusion on response reconstruction and damage identification are also investigated. The results clearly demonstrate the superiority of QHEA over other heuristic algorithms and heterogeneous data fusion over a single type of measurement. It is shown that both the locations and extents of the damaged elements can be accurately identified by the proposed method without the information of input force.

Damage identification of steel bridge based on data augmentation and adaptive optimization neural network

With the advancement of deep learning, data-driven structural damage identification (SDI) has shown considerable development. However, collecting vibration signals related to structural damage poses certain challenges, which can undermine the accuracy of the identification results produced by data-driven SDI methods in scenarios where data is scarce. This paper introduces an innovative approach to bridge SDI in a few-shot context by integrating an adaptive simulated annealing particle swarm optimization-convolutional neural network (ASAPSO-CNN) as the foundational framework, augmented by data enhancement techniques. Firstly, three specific types of noise are introduced to augment the source signals used for training. Subsequently, the source signals and augmented signals are recombined to construct a four-dimensional matrix as the input to the CNN, while defining the damage feature vector as the output. Secondly, a CNN is constructed to establish the mapping relationship between the input and output. Then, an adaptive fitness function is proposed that simultaneously considers the accuracy of SDI, model complexity, and training efficiency. The ASAPSO is employed to adaptively optimize the hyperparameters of the CNN. The proposed method is validated on an experimental model of a three-span continuous beam. It is compared with four other data-driven methods, demonstrating good effectiveness and robustness of SDI under cases of scarce data. Finally, the effectiveness of this SDI method is validated in a real-world case of a steel truss bridge.

A temperature compensation approach using dynamic time warping for electro-mechanical admittance-based concrete structural damage identification

A temperature compensation approach using dynamic time warping for electro-mechanical admittance-based concrete structural damage identification

Structural damage identification based on dual sensitivity analysis from optimal sensor placement

Structural damage identification (SDI) methods using incomplete modal information can avoid the extension for unmeasured degrees of freedom, but the absence of essential damage information often leads to the failure of SDI. To address this problem, a novel SDI method based on dual sensitivity analysis and optimal sensors placement technique is proposed in this study. Firstly, in the optimal sensor placement technique, an improved eigenvector sensitivity method combined with weighted modal kinetic energy is proposed, which enables the acquisition of eigenvector information related to damage sensitivity, and incorporates it into the modal strain energy sensitivity matrix to obtain the dual sensitivity analysis matrix. Then, the sparsity of structural damage is considered, and the L1 sparse regularization is selected and introduced into the dual sensitivity analysis damage equation for better SDI results. Finally, to assess the effectiveness of the proposed method, a series of numerical simulations and experimental verifications were carried out under different structural damage scenarios. The results indicate that the proposed method can efficiently localize and quantify the structural damage with minimal modal information in one single step.

Rail crack identification of in-service turnout through Bayesian inference

In-service railway turnout, suffering from multi-factor coupling of operational and environmental loadings and special wheel–rail interaction, is prone to structural damage. The paper aims to develop a Bayesian damage identification method for crack-alike damage of the turnout rail under uncertainties. It consists of three core parts, including a damage index (DI) constructed by the transformation of time–frequency components of responses for generating damage-sensitive relationships, Bayesian models describing the crack-sensitive relationships hidden in the members of the damage index, and a mechanism synthesizing individual assessment results associated with the different reference models for providing one quantitative solution. The abnormal change in the stable relationships derived from the index can reflect damage occurrence and severity. The Bayesian approach is adopted to model the relationships under uncertainties of in-service railway turnout. The models trained by using monitoring data of the turnout rail before being damaged serve as a reference for healthy state, and deviations of actual observations from model predictions may indicate the existence of damage. The synthesizing process helps to offer a more rational assessment result through the weighted summation of individual quantitative assessment results. Rail monitoring data of a railway turnout are acquired to examine the damage detection performance of the proposed method. By exempting loadings measurement and physical model derivation, this data-driven methodology is potentially capable of supporting the damage identification and quantitative assessment of other structures in railway engineering.

A novel CNN architecture for robust structural damage identification via strain measurements and its validation via full-scale experiments

In this study, an innovative two-dimensional Convolutional Neural Network (2D CNN) architecture is proposed and investigated for the classification of bridge damage. Employing unique strain time-history data transformed into grayscale images, the approach seamlessly combines feature extraction and classification, allowing for the precise identification and categorization of structural damage. The method’s effectiveness was validated through field experiments on a full-scale bridge mock-up sample subjected to several controlled damage states under nonstationary, commercial vehicle loads. A wide range of realistic damage conditions, from minor to severe structural damage states, was included in the experimental scenarios together with inherent operational uncertainties. The robustness of the 2D CNN model was rigorously tested against fluctuating loads and introduced noise. Demonstrating remarkable accuracy, the 2D CNN successfully classified different damage states with over 95% accuracy, effectively identifying a damage state that was visually undetectable. Furthermore, the architecture proved to be highly versatile, effectively handling variations in the number of sensors. uncertainties included in the experimental data, and elevated levels of measurement noise.

Structural damage identification based on Wasserstein Generative Adversarial Network with gradient penalty and dynamic adversarial adaptation network

Transfer learning-based damage identification is widely explored as it can utilize prior damage knowledge from finite element model (FEM) to identify damage without real structure damage labels. However, lacking a substantial amount of real structure data and overlooking the variances in conditional (local) distributions between source domain (data generated by FEM) and target domain (real structure data) severely restrict its practical application. This paper proposes a transfer learning-based damage identification method by combining Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) and Dynamic Adversarial Adaptation Network (DAAN). Firstly, WGAN-GP generative model is employed to augment real structure samples to address the issue of insufficient data. Then, an optimization transfer model with the capability of balancing the importance of marginal and conditional distributions between FEM data and real structure data is proposed based on DAAN transfer model. It dynamically learns damage-invariant features for damage identification. Thirdly, damage identification procedures are provided by combining the generative model WGAN-GP and the transfer model DAAN with moving load induced responses as inputs. Numerical and experimental examples indicate that the proposed method achieves superior transfer effect with limited real structure data and maintains high damage identification accuracy compared to the traditional transfer learning-based methods.

Research on Damage Identification of Civil Engineering Structures based on CiteSpace

Research on Damage Identification of Civil Engineering Structures based on CiteSpace

Automatic damage detection and data completion for operational bridge safety using convolutional echo state networks

Structural response data might be partially missing during acquisition and transmission by a structural health monitoring (SHM) system, affecting subsequent structural damage identification. Conventional deep learning methods require a substantial amount of data and have low training efficiency. With this in mind, this paper proposes a hybrid approach for data reconstruction and damage identification using an echo state network embedded with convolutional layers. The network has a training-free reservoir layer and focuses on historical information and multi-channel spatial features. As data redundancy occurs in most measured structural vibration responses, the extended Frobenius norm-principal component analysis method is applied to select valuable samples for updating the network, which greatly enhances the training efficiency. Experimental and numerical data from a physical bridge model is used to verify the data reconstruction capability and damage identification accuracy of the proposed method, and its performance is further compared with several existing deep learning methods.

Research on Structural Damage Identification of Shear Buildings Based on Modal Curvature Change

In the past few decades, various techniques for structural damage identification based on dynamic properties have been widely studied, among which modal curvature is the research hotspot, due to its high sensitivity to local damage. To realize story-level structural damage identification of shear buildings, this paper first derives the patterns of variation in modal curvature of the damaged structure. Then, a new damage index sensitive to local damage called the Modal Curvature Change modified with Softmax (MCCSM for short), is proposed to improve the accuracy of structural damage identification. Afterward, the validity of the damage index is verified by a shaking table test of a scaled RC frame structure model and its corresponding numerical model. The research results show that the damage location indicated by MCCSM corresponds well with the damage phenomenon in the shaking table test and numerical simulation; compared with using the theoretical mode shape, the MCCSM index can give comparable damage identification results using the mode shape obtained through operational modal analysis from vibration time-history data, which proves the feasibility in engineering practices; through numerical simulation, it is proved that the MCCSM index is applicable in a wide range of damage cases with different story position, number of damaged story, and damage extent.

Bayesian model selection for structural damage identification: comparative analysis of marginal likelihood estimators

Bayesian model selection for structural damage identification: comparative analysis of marginal likelihood estimators