Damage Diagnosis Method Research Articles

Damage localization for composite structure using guided wave signals with Gramian angular field image coding and convolutional neural networks

Accurate detection of damage in composite structures is of great significance to ensure safe service and avoid catastrophic accidents. In this paper, a novel damage diagnosis method, integrating guided wave (GW)-based structural health monitoring (SHM) with Gramian angular field (GAF) image coding and convolutional neural networks (CNNs), is proposed to improve the accuracy of damage localization in composite structures. Firstly, an improved piecewise aggregate approximation (PAA) algorithm is proposed to achieve guided wave data compression and obtain a series of damage indexes (DIs) characterizing the damage for effectively improving the localization accuracy. Then, the multi-path fused DI sequences are converted into two-dimensional (2-D) images using GAF to take full advantage of the significant benefits of CNN in machine vision. Secondly, a CNN model is constructed to learn high-level feature representations and conduct damage location regression. Finally, the proposed method is tested and assessed on measured GW signal datasets with the addition of zero-mean Gaussian noise. The experimental results show that the mean relative error of the proposed method for damage localization on the invisible datasets is 3.59%. The proposed method demonstrates better generalization and localization performance than other selected state-of-the-art damage localization techniques.

An unsupervised learning damage diagnosis method based on virtual impulse response function and time series models

As it contains the inherent properties of the structure and is insensitive to variation of the input, the transmissibility function (TF) is widely used for structural damage detection under ambient excitation. However, in TF-based methods, the selection of the optimal damage sensitivity band often requires access to vibration data under different operating conditions, which is not conducive to unsupervised learning. In order to accommodate unsupervised learning and extract more damage information, this paper proposes a data-driven unsupervised damage detection method based on the virtual impulse response function (VIRF) and time series model (TSM). In this method, the VIRF is used as a damage-sensitive feature (DSF), the TSM is used for low-dimensional feature extraction of the VIRF, and the distance metric of the model coefficients is used to detect the occurrence of anomalies. The study analyses the type of TSM applied to VIRF and uses the parameter adjusted cosine similarity (PACS) as a more accurate statistical distance tool for the model coefficients. The application of two well-known benchmark structure experiments verifies the accuracy and practicality of the proposed method in damage detection under minor operational variations and ambient excitations. The comparative analysis and detection results indicate that the proposed method is advantageous in qualitatively quantifying the extent of the damage. Structural anomalies can be detected in both linear and nonlinear damage scenarios.

Damage identification during an impact event using the Hilbert-Huang transform of decomposed propagation modes

This work proposes a novel baseline-free method for real-time structural damage diagnosis during low-and high-velocity impact, based on the decomposition of the propagating modes caused by impact events. The high-frequency components (extensional) and the medium–low frequency components (flexural) of the measured waves are separated via Hilbert-Huang transform (HHT) through the intrinsic mode function (IMF), to obtain the amplitude and phase of the two extensional and flexural propagation modes. The Energy Ratio Ξ defined as the ratio between the maximum instant energy of the extensional mode and the maximum instant energy of the flexural mode is proposed. Results show that values of Ξ between 0 and 1 are a sign of low probability of damage during impact. When the Ξ parameter is reaching values higher than 1, penetration and perforation of the structure is likely to occur, since the extensional component in this scenario is more dominant than the flexural one. Tests were conducted on aluminium and CFRP samples with simple and complex geometries, subjected to low- and high-velocity impacts (with and without perforation) to validate the flexibility of the proposed method. Experimental results have demonstrated the effectiveness of the technique to discern elastic and damaging impact on different sample geometries and at different impact velocities in real-time and without the requirement of baseline datasets.

Adversarial Auxiliary Weighted Subdomain Adaptation for Open-Set Deep Transfer Bridge Damage Diagnosis.

Deep learning models have been widely used in data-driven bridge structural damage diagnosis methods in recent years. However, these methods require training and test datasets to satisfy the same distribution, which is difficult to satisfy in practice. Domain adaptation transfer learning is an efficient method to solve this problem. Most of the current domain adaptation methods focus on close-set scenarios with the same classes in the source and target domains. However, in practical applications, new damage caused by long-term degradation often makes the target and source domains dissimilar in the class space. For such challenging open-set scenarios, existing domain adaptation methods will be powerless. To effectively solve the above problems, an adversarial auxiliary weighted subdomain adaptation algorithm is proposed for open-set scenarios. Adversarial learning is introduced to proposed an adversarial auxiliary weighting scheme to reflect the similarity of target samples with source classes. It effectively distinguishes unknown damage from known states. This paper further proposes a multi-channel multi-kernel weighted local maximum mean discrepancy metric (MCMK-WLMMD) to capture the fine-grained transferable information for conditional distribution alignment (sub-domain alignment). Extensive experiments on transfer tasks between three bridges verify the effectiveness of the algorithm in open-set scenarios.

Research on the Damage Diagnosis Model Algorithm of Cable-Stayed Bridges Based on Data Mining

To obtain an effective data mining method for cable-stayed bridge damage diagnosis, the algorithm of the cable-stayed bridge damage diagnosis model based on data mining was studied, and a data mining method is proposed. This method is oriented to the damage diagnosis of cable-stayed bridges. After algorithm comparison, the support vector machine (SVM) and limit gradient-boosting (XGBoost) algorithms, with advantages in damage location and quantification, are combined and optimized to obtain the damage diagnosis model for cable-stayed bridges. First, a refined benchmark finite element model is established by Abaqus, and postprocessing data such as vibration frequency and modal curvature are used as a data mining dataset. Second, feature se-lection is conducted, and the damage-sensitive modal curvature change rate index is selected as the feature of data mining. Next, the SVM and XGBoost algorithms are optimized by grid and random search, and the optimized SVM and XGBoost algorithms are used to locate and quantify the damage. Finally, the damage diagnosis model for cable-stayed bridges is obtained. Taking a cable-stayed bridge as an example, the proposed method is applied and analyzed, and the results show the effectiveness of the proposed method.

Bridge damage identification under the moving vehicle loads based on the method of physics-guided deep neural networks

Modeling uncertainty or modeling error has been widely recognized as one major challenge for damage identification of bridge structures by moving vehicles. This study proposed a physics-guided deep neural network approach to improve the accuracy of damage identification in vehicle-induced bridge vibration response, which aims to minimize the influence of the modeling uncertainty on damage identification. Firstly, the physical relationship between the damage to the bridge with the acceleration signal of the bridge, the physics-guided deep neural network, and its damage diagnosis method is introduced. The feasibility of the damage identification method based on physics-guided deep neural networks is theoretically explained. Secondly, a numerical case of damage identification of the simply supported bridge under moving vehicle loads is conducted to compare the accuracy of damage identification between the proposed method and the traditional method. Finally, a bridge field test is implemented to verify the applicability and effectiveness of the proposed method. The results illustrate that the method can be utilized to accurately identify the damage locations of simply supported bridges under a moving vehicle.

Automatic Damage Detection and Diagnosis for Hydraulic Structures Using Drones and Artificial Intelligence Techniques

Large-volume hydraulic concrete structures, such as concrete dams, often suffer from damage due to the influence of alternating loads and material aging during the service process. The occurrence and further expansion of cracks will affect the integrity, impermeability, and durability of the dam concrete. Therefore, monitoring the changing status of cracks in hydraulic concrete structures is very important for the health service of hydraulic engineering. This study combines computer vision and artificial intelligence methods to propose an automatic damage detection and diagnosis method for hydraulic structures. Specifically, to improve the crack feature extraction effect, the Xception backbone network, which has fewer parameters than the ResNet backbone network, is adopted. With the aim of addressing the problem of premature loss of image detail information and small target information of tiny cracks in hydraulic concrete structures, an adaptive attention mechanism image semantic segmentation algorithm based on Deeplab V3+ network architecture is proposed. Crack images collected from concrete structures of different types of hydraulic structures were used to develop crack datasets. The experimental results show that the proposed method can realize high-precision crack identification, and the identification results have been obtained in the test set, achieving 90.537% Intersection over Union (IOU), 91.227% Precision, 91.301% Recall, and 91.264% F1_score. In addition, the proposed method has been verified on different types of cracks in actual hydraulic concrete structures, further illustrating the effectiveness of the method.

A new deep transfer learning method for intelligent bridge damage diagnosis based on muti-channel sub-domain adaptation

Deep learning has been successfully and widely used in the field of intelligent diagnosis to accurately identify damage. These successes are based on the assumption that the training and test data are independent and identically distributed. They ignore that there is a distribution discrepancy between training (source domain) and test data (target domain) obtained under different working environments, loads, or bridges. This distribution discrepancy leads to severe performance degradation of the diagnostic model. To address these problems, a novel intelligent diagnosis method is proposed for bridges, namely, the multi-channel subdomain adaptation based deep transfer learning network. In this network, a multi-scale-based parallel multi-channel feature extractor and a multi-kernel local maximum mean discrepancy-based multi-channel subdomain adaptation module are proposed to learn domain-invariant features. Data sets from three different bridges are used for transfer diagnosis experiments to verify the generality and superiority of the method. This study will further facilitate the intelligentisation of structural health monitoring systems in the field of bridges.

Fully distributed strain-based output feedback for enhanced sensitivity in damage diagnosis of structures

The closed-loop damage diagnosis method has shown significant improvement in recent years, while closed-loop eigenvectors are seldomly used in previous damage diagnosis research due to the lack of adequate measurement points, by which a better damage diagnosis effect can be achieved. With the maturity of fully distributed optical fiber sensing technology, strain data acquisition with many (high-density) measurement points can be realized; in this manner, fully distributed strain-based output feedback for sensitivity enhancement is first investigated in this study, while the main contribution is to first develop a calculation algorithm of closed-loop strain modal shape sensitivity with high-density strain measurements. First, the desired eigenstructure assignment scheme is constructed, and a reasonable range of closed-loop pole selection is determined. On this basis, a sensitivity-based damage diagnosis method using closed-loop strain modal shapes is proposed, with sensitivity and robustness selected as the optimization goals. The optimal gain is obtained, which can benefit the closed-loop damage identification accuracy and stability. The effectiveness of the proposed method is validated and compared with the closed-loop eigenvalue-based method by numerical simulation, and the results indicate that the proposed method can effectively enhance the performance of damage diagnosis and improve system robustness.

Multi-objective variational autoencoder: an application for smart infrastructure maintenance

Multi-way data analysis has become an essential tool for capturing underlying structures in higher-order data sets where standard two-way analysis techniques often fail to discover the hidden correlations between variables in multi-way data. We propose a multi-objective variational autoencoder (MO-VAE) method for smart infrastructure damage detection and diagnosis in multi-way sensing data based on the reconstruction probability of autoencoder deep neural network (ADNN). Our method fuses data from multiple sensors in one ADNN at which informative features are being extracted and utilized for damage identification. It generates probabilistic anomaly scores to detect damage, asses its severity and further localize it via a new localization layer introduced in the ADNN. We evaluated our method on multi-way laboratory-based and real-life structural datasets in the area of structural health monitoring for damage diagnosis purposes. The data was collected from our deployed data acquisition system on a cable-stayed bridge in Western Sydney, a reinforced concrete cantilever beam which replicates one of the major structural components on the Sydney Harbour Bridge and a laboratory based building structure obtained from Los Alamos National Laboratory (LANL). Experimental results show that the proposed method can accurately detect structural damage. It was also able to estimate the different levels of damage severity, and capture damage locations in an unsupervised aspect. Compared to the state-of-the-art approaches, our proposed method shows better performance in terms of damage detection and localization.

Multisensory collaborative damage diagnosis of a 10 MW floating offshore wind turbine tendons using multi-scale convolutional neural network with attention mechanism

An effective damage diagnosis and prognostic management method can considerably reduce operation and maintenance costs of floating wind turbines. In this research, an intelligent damage diagnosis framework, named “MS-ACNN”, has been developed using a multi-scale deep convolution neural network model fused with an attention mechanism. The framework is used to detect, localize, and quantify existing and potential damages on multibody floating wind turbine tendons. The MS-ACNN framework is fitted with two multi-scale extractors, designed to capture multi-scale information from raw wind turbine response signals measured using multi-sensor. The attention mechanism uses weight ratios of extracted damage feature to enhance the MS-ACNN's capability in offering a better generalization in damage diagnosis. The framework's performance is examined under normal and noisy environments and with a diagnosis accuracy of 80%, which is higher than those obtained using most generic industrial grade diagnostic tools (MS–CNN–I, MSCNN-II, CNN, CNN-LSTM and CNN-BiLSTM) by at least 10%. The framework is also fitted with a Majority Weighted Voting rule to reduce false alarms and ensure optimum performance of the multi-sensor during collaborative diagnosis. Further examination shows that the inclusion of a voting rule increases the diagnostic performance's F1 index from 90% for single sensor and 84% for multi-sensor results to 94%.

Multi‐Channel Domain Adaptation Deep Transfer Learning for Bridge Structure Damage Diagnosis

The successful application of deep learning in bridge damage diagnosis relies on the assumption that the training and test data sets obey the same distribution. However, it is difficult to obtain labeled data of damage status for a bridge in using. Otherwise, it is difficult to apply a model trained with bridge A (source domain) to diagnose bridge B (target domain) because of the distribution discrepancy of data from different working environments or bridges. In response to these problems, motivated by transfer learning, a new bridge damage diagnosis method, namely, the multichannel domain adaptation deep transfer learning based method (MDADTL), is proposed in this paper. First, a CNN based multichannel multi‐scale feature extractor is introduced to extract features. Second, a multichannel domain adaptation module based on maximum mean discrepancy (MMD) is proposed for transfer learning, so that the learned features are domain‐invariant. Through the above process, MDADTL trained with labeled data obtained in the laboratory or the testing bridge is expected to diagnose other bridges with unlabeled data. Experiments prove the effectiveness and advancement of the proposed method. This exploration will promote the practical application of deep learning in bridge damage diagnosis. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

Distribution Sub-Domain Adaptation Deep Transfer Learning Method for Bridge Structure Damage Diagnosis Using Unlabeled Data

Deep learning based bridge damage diagnosis methods can successfully use labeled data to detect bridge damage. These successful applications usually need that the training samples (source domain) and test samples (target domain) obey the same probability distribution. However, it is difficult to acquire a large amount of labeled data with damage information from actual bridges. It is also difficult to apply a model trained with bridge A to diagnose bridge B because of the distribution discrepancy of data from different bridges or environments. Therefore, transferring a well-trained damage diagnosis model to another bridge with unlabeled data remains a major challenge. Motivated by transfer learning, this paper proposes a new intelligent damage diagnosis method for bridges, namely, sub-domain adaptive deep transfer learning network (SADTLN), to solve the feature generalization problem in different bridges. In our method, a multi-kernel local maximum mean discrepancy (MK-LMMD) based sub-domain adaptation module, including a domain classifier for aligning the global distribution and a sub-domain multi-layer adaptation for aligning local distribution, is proposed for transfer learning, so that the learned features are domain-invariant. Experiments prove the effectiveness and advancement of the proposed method. This exploration will promote the practical application of intelligent bridge structural damage diagnosis.

Damage Diagnosis of Single-Layer Latticed Shell Based on Temperature-Induced Strain under Bayesian Framework.

Under the framework of Bayesian theory, a probabilistic method for damage diagnosis of latticed shell structures based on temperature-induced strain is proposed. First, a new damage diagnosis index is proposed based on the correlation between temperature-induced strain and structural parameters. Then, Markov Chain Monte Carlo is adopted to analyze the newly proposed diagnosis index, based on which the frequency distribution histogram for the posterior probability of the diagnosis index is obtained. Finally, the confidence interval of the damage diagnosis is determined by the posterior distribution of the initial state (baseline condition). The damage probability of the unknown state is also calculated. The proposed method was validated by applying it to a latticed shell structure with finite element developed, where the rod damage and bearing failure were diagnosed based on importance analysis and temperature sensitivity analysis of the rod. The analysis results show that the proposed method can successfully consider uncertainties in the strain response monitoring process and effectively diagnose the failure of important rods in radial and annular directions, as well as horizontal (x- and y-direction) bearings of the latticed shell structure.

Detecting Damage in Reinforced Concrete Beams Using Vibrational Characteristics

This paper evaluates two methods of diagnosing damage, Natural frequency and Stiffness-Frequency change-Based damage detection method in reinforced concrete beams under load using vibration characteristics such as natural frequency and mode shape. The research uses finite element method with crack damage instead of deleting or reducing the bearing capacity of the element like in previous studies. First, a theory of the damage diagnosis method based on the change of natural frequency and mode shape is presented. Next, the simulation results of reinforced concrete beams using ANSYS will be compared with the experiment. Particularly, the investigated damage cases are cracks in reinforced concrete beams under loads. Finally, we will evaluate the accuracy of the damage diagnosis methods and suggest the location of the vibration data and specify the failure threshold of the methods.

Study on Bridge Structure Damage and Health Diagnosis Method Based on Health Monitoring

Study on Bridge Structure Damage and Health Diagnosis Method Based on Health Monitoring

A Novel Bridge Damage Diagnosis Algorithm Based on Deep Learning with Gray Relational Analysis for Intelligent Bridge Monitoring System

In recent years, intelligent structural damage diagnosis algorithms using machine learning have achieved much success. However, because of the fact that in real bridge applications, the working environment (load, temperature, and noise) is changing all the time, degradation of the performance of intelligent structural damage diagnosis methods is very serious. To address these problems, a novel bridge diagnosis algorithm based on deep learning is proposed. Our contributions include: First, we proposed an improved denoising auto‐encoder‐based deep neural networks, which is optimized by the gray relational analysis. It is able to automatically extract high‐level features from raw signals via a multi‐layer extraction to satisfy any damage diagnosis objective and thus does not need any time consuming denoising prepossessing. The model can achieve high accuracy under noisy environment. Second, the algorithm does not rely on any domain adaptation algorithm or require information of the target domain. It can achieve high accuracy when working environment is changed. Numerical simulations and experimental investigations on real bridges conducted to present the accuracy and efficiency of the proposed algorithm, comparing with other commonly machine learning‐based algorithms. The result shows it is deemed as an ideal and effective method for damage diagnosis of bridge structures. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

RETRACTED: Elastic wave methods for non-destructive damage diagnosis in the axisymmetric viscoelastic cylindrical waveguide

The popular technique for damage detection in a cylindrical waveguide is the ultrasonic guided wave propagation based acoustic emission (AE) monitoring method. It comes under the dynamic non-destructive evaluation (NDE) category, primarily established on the fluctuations in AE signal features to detect the structural damage in real-time. In this paper, the numerical modeling of wave scattering by a structural discontinuity in axisymmetric high strength steel wire - viscoelastic waveguide medium for analyzing the wave interaction by inhomogeneity is presented. The hybrid standard three-dimensional finite element (3D FE) method and semi-analytical finite element (SAFE) method for numerical analysis of guided ultrasonic wave propagation are employed. For the simulation of waveguide media with arbitrary defect shapes, the hybrid 3D FE-SAFE method can be used. The basic idea is to express the frequency response of the cross-section at the two ends of the 3D FE part as a modal superposition calculated by the semi-analytical method. A case study on a steel wire is conducted to calculate the displacement response under a narrow-band external force excitation. The AE signal characteristics are used to understand the wave interaction of the pitting corrosion and tapered section in steel wire. The investigation of the amplitude of elastic waves passing through the discontinuity for the both undamped and damped cylindrical waveguide is proposed to understand the distribution of energy at points of reflections or refraction and the ratio between the amplitudes arriving at that point. Another contribution of the research work includes the robust algorithm for wave reflection and scattering based on the hybrid element method, which can effectively improve the calculation competence using an internal degree of freedom condensation and modal acceleration. It is suitable for models with multiple damages in the 3D FE area, and the accuracy of the results on wave-damage interactions can be achieved. The recommended method can be used to distinguish damages present in a viscoelastic cylindrical waveguide.

Research on the Beam Damage Diagnosis Method for a High-Speed Transplanter Based on the Strain Mode

Abstract. The vibration of agricultural machinery significantly influences driving comfort and operation reliability. In recent years, research on the vibrational characteristics of agricultural machinery has gradually expanded. To solve the problem of the obvious vibration of a high-speed transplanter under operating conditions, this article examines the method of beam damage diagnosis for high-speed transplanters based on the strain mode. Based on the modal theory, the displacement and strain modal analysis of the beam of the high-speed transplanter is performed. The analysis shows that the relative deviation of the modal frequencies of the same order before and after the beam is damaged is small. There is no obvious abrupt change in the displacement mode shape, while the strain mode shape has a sudden change peak after the beam is damaged. Thus, the strain mode change rate is constructed as a diagnostic index for beam damage. The analysis results show that the strain mode change rate increases with the increase in beam damage degree. Finally, the least squares method is used to fit the corresponding relationship between the two quantities. The results show that the strain mode change rate is sensitive and reliable as an index of damage diagnosis, which can better determine the location and degree of damage to the beam. Keywords: Beam, Damage, Diagnosis, Rice transplanter, Strain mode.

Structural Damage Diagnosis Based on the Temporal Moment of Partially Measured Structural Responses

Structural damage diagnosis is still a challenging task because most current methods are either insensitive to local structural damage or sensitive to measurement noise. A statistical moment–based structural damage detection (SMBDD) algorithm has been proposed to locate and detect damages, revealing superiority in noise immunity. However, it requests that the number of measured responses should be no fewer than that of unknown structural parameters. In this paper, to reduce the number of measurements required in the SMBDD algorithm, an improved method for damage diagnosis is proposed based on the temporal moment of partially measured structural responses. Firstly, structural partial acceleration responses are measured and split into several time segments. Then, the temporal moment in each segment of the measured acceleration response time history is estimated. Finally, an objective error function is established by the temporal moments of measured accelerations and calculated accelerations, and structural stiffness can be identified by minimizing the objective error function. The proposed method is simple and feasible with a robust antinoise property and can identify structural damage when the number of measured responses is lower than that of the structural stiffness. Numerical simulations and an experimental study are conducted, respectively, to verify the feasibility and effectiveness of the proposed method.