Structural Health Monitoring最新文献

{"title":"Fault diagnosis using variational autoencoder GAN and focal loss CNN under unbalanced data","authors":"Weihan Li, Dunke Liu, Yang Li, Ming Hou, Jie Liu, Zhen Zhao, Aibin Guo, Huimin Zhao, Wu Deng","doi":"10.1177/14759217241254121","DOIUrl":"https://doi.org/10.1177/14759217241254121","url":null,"abstract":"For the poor model generalization and low diagnostic efficiency of fault diagnosis under imbalanced distributions, a novel fault diagnosis method using variational autoencoder generation adversarial network and improved convolutional neural network, named VGAIC-FDM, is proposed in this paper. First, to capture local features of vibration signals, continuous wavelet transform is employed to convert the original one-dimensional fault signals into wavelet time–frequency images. Second, for the data dimensionality reduction and model simplification, the time–frequency wavelet images are processed in grayscale to generate single-channel grayscale time–frequency images. Then, sample augmentation is performed on grayscale time–frequency images to balance the dataset by using a variational autoencoder generation adversarial network. Finally, the generated images and the original images are fused and trained by using a focus-loss-optimized CNN classifier to achieve fault diagnosis under unbalanced conditions. The experimental results show that the VGAIC-FDM effectively captures the potential spatial distribution of real samples and alleviates the impact caused by the inconsistent difficulty of sample classification. As a result, it enhances the fault diagnosis performance of the model when dealing with unbalanced datasets, leading to higher accuracy and F1-score values.","PeriodicalId":515545,"journal":{"name":"Structural Health Monitoring","volume":"97 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141807935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Long-tailed multi-domain generalization for fault diagnosis of rotating machinery under variable operating conditions","authors":"Chu Jian, Guopeng Mo, Yonghe Peng, Yinhui Ao","doi":"10.1177/14759217241256690","DOIUrl":"https://doi.org/10.1177/14759217241256690","url":null,"abstract":"As the operating conditions (also known as domains) of rotating machinery become increasingly diverse, fault diagnosis has garnered growing attention. However, fault diagnosis frequently encounters challenges such as long-tailed data distributions, domain shifts in monitoring data, and the unavailability of target-domain data. Existing approaches can only address some of these challenges, limiting their applications. To address these challenges concurrently, we introduce a novel learning paradigm called long-tailed multi-domain generalized fault diagnosis (LMGFD) and propose a two-stage learning framework for LMGFD, comprising domain-invariant feature learning and balanced classifier learning. In the first stage, we leverage a balanced multi-order moment matching (BMMM) module to align subdomains with long-tailed distributions. Additionally, a balanced prototypical supervised contrastive (BPSC) module is developed to effectively alleviate the contrastive imbalance. The combination of BMMM and BPSC enables the effective learning of long-tailed domain-invariant features. In the second stage, we extend the focal loss to a multi-class version and re-weight it using effective sample numbers to strengthen tailed-class loss, thereby mitigating the overfitting problem. Experimental results on both a public dataset and a private dataset support the competitiveness and effectiveness of the proposed method. The findings suggest that we present a promising solution for fault diagnosis of rotating machinery under variable operating conditions.","PeriodicalId":515545,"journal":{"name":"Structural Health Monitoring","volume":"55 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141808844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fault diagnosis of high-speed motorized spindles based on lumped parameter model and enhanced transfer learning","authors":"Xiangming Zhang, Zhimin Ma, Yongying Jiang","doi":"10.1177/14759217241255285","DOIUrl":"https://doi.org/10.1177/14759217241255285","url":null,"abstract":"Condition monitoring of rotating components is crucial for ensuring the reliability and safety of mechanical systems, and artificial intelligence (AI) plays a significant role in achieving the goal. However, the high costs and complexity associated with components like high-speed motorized spindles present significant challenges in collecting complete fault samples. Therefore, we propose a new approach to tackle the challenges. The process commences with establishing a lumped parameter dynamic model for the high-speed motorized spindle. Then, the parameters such as stiffness, eccentricity, and damping in the lumped parameter model were optimized using genetic algorithm. Subsequently, simulated fault samples are acquired by introducing excitation to normal simulated signals. Finally, transfer learning techniques are utilized for intelligent fault diagnosis. The training set consists of simulated fault samples, while the testing set comprises experimental fault samples. Our approach aims to enhance the efficiency and accuracy of fault diagnosis for high-speed motorized spindles while also addressing the challenge of high cost.","PeriodicalId":515545,"journal":{"name":"Structural Health Monitoring","volume":"65 31","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141806634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Depth estimation of pipe wall thinning using multifrequency reflection coefficients of T(0,1) mode-guided waves with supervised multilayer perceptron","authors":"Ryujin Katsuma, Koki Tada, Tomoya Iriguchi, Kotaro Seno, Shinsuke Kondo, Masashi Ishikawa, Motoki Goka, Hideo Nishino","doi":"10.1177/14759217241249240","DOIUrl":"https://doi.org/10.1177/14759217241249240","url":null,"abstract":"This study entailed the development of a novel method for estimating the depth of wall thinning of pipes using multifrequency (30–65 kHz) reflection coefficients (MRCs) of the T(0,1) mode-guided waves and a multilayer perceptron (MLP). First, this study established why MRCs are a critical feature of the input layer of the MLP for the defect depth estimation of wall thinning. Further, a mathematical model that can quickly collect large amounts of training data was used to calculate the reflection waveforms. The depths of artificial and actual wall thinning were estimated using the MLP based on the MRCs and the mathematical model. Experiments were conducted using the T(0,1) mode-guided waves to obtain the MRCs for 21 artificial and 6 actual wall thinnings to estimate the defect depths. A maximum of 8347 training data points were prepared using the mathematical model. Because the optimization of the MLP strongly depended on the initial weights and biases, 100 random initial values were prepared to evaluate the average estimations and their standard deviations. The classification scheme of the MLP was used, with classification step widths of 0.5 and 0.25 mm. The correct answer rates for the 21 artificial defects were 93%, with a tolerance of ±0.5 mm for the 0.5 mm classification scheme; those for the 0.25 mm classification scheme were 89%. For the six actual defects, the correct answer rates were 100% with a tolerance of ±0.5 mm for both the 0.5 and 0.25 mm classification schemes. Sufficiently high correct answer rates were obtained in all the cases.","PeriodicalId":515545,"journal":{"name":"Structural Health Monitoring","volume":"37 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141807271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive cyclic content ratiogram: a new signal decomposition method for bearing concurrent fault diagnosis","authors":"Cai Yi, Ye Tao, Jiayin Tang, Xiaoyu Xian, Fengkun Yang, Qiuyang Zhou, Yunzhi Lin, Hao Wang, Jianhui Lin, Weihua Zhang","doi":"10.1177/14759217241255126","DOIUrl":"https://doi.org/10.1177/14759217241255126","url":null,"abstract":"Fast kurtogram (FK) has been proven to be an effective tool for resonance frequency band detection, which is widely used in bearing fault diagnosis. However, FK is not robust to impulsive noise, and its frequency band segmentation rule is fixed, which leads to over-decomposition or under-decomposition of the fault resonance frequency band in its signal decomposition results. Therefore, an adaptive cyclic content ratiogram is proposed in this paper. Firstly, based on the energy distribution of vibration signals on different frequency components, the frequency spectral segmentation is performed adaptively, and multiple sub-signals containing different frequency components are obtained. Secondly, the ratio of cyclic content (RCC), which cannot only more accurately characterize the cyclostationarity of bearing fault impacts but also be insensitive to impulsive noise, is applied to evaluate the fault feature information contained in each sub-signal separately. In the meanwhile, considering that fault characteristic frequency information is required in the process of RCC evaluation, the proposed method performs adaptive fault characteristic frequency detection for each sub-signal based on the envelope spectrum. The RCC maximization is used to locate the fault resonance frequency band. Also, combined with the estimated fault characteristic frequencies, the proposed method can achieve the extraction of concurrent fault features. Simulation and experimental data verify the effectiveness of the proposed method.","PeriodicalId":515545,"journal":{"name":"Structural Health Monitoring","volume":"66 48","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141806480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Monitoring and assessing concrete member states using implantable sensing technology and enhanced long short-term memory networks","authors":"Qingzhao Kong, Yewei Ding, Bin Ma, Xiaoming Qin, Ziqian Yang","doi":"10.1177/14759217241259081","DOIUrl":"https://doi.org/10.1177/14759217241259081","url":null,"abstract":"Monitoring the state of concrete structures and assessing their performance are significant tasks for civil engineering. This study proposes a combined technique of novel concrete implantable bar (CIB) transducers and enhanced long short-term memory (LSTM) networks for monitoring and assessing reinforced concrete (RC) beam state over the whole loading process. The CIB can be installed on the inspected structure in an implantable manner. It contains an array of piezoceramic sensing units that can generate and receive ultrasonic waves from a concrete medium. To enhance the LSTM network’s ability to learn very long-series data, a time-shift energy (TSE) strategy was developed. Compared with another existing convolutional neural network (CNN)–LSTM network, the proposed TSE–LSTM network is highlighted to fully consider the ultrasound propagation characteristics in concrete when extracting sample features, instead of using simple convolution operation. A numerical study was conducted to investigate the sensitivity of the TSE feature to different concrete damage levels through mesoscale finite element models. The results provided the best parameter settings of the TSE. Eventually, to validate the feasibility of the proposed technique, an RC beam four-point bending test was carried out, in which two CIBs were implanted into the specimen for emitting and collecting ultrasonic waves in different damage states to establish a dataset. Two schemes including a classification model for predicting RC beam stress stages and another regression model for predicting the carried forces were separately investigated. The experimental results showed that the TSE–LSTM networks can successfully predict the signature of three stages of RC beams and can, in general, predict their carried forces. The comparison to the results obtained by CNN–LSTM networks further highlighted the stability and accuracy of the proposed one in learning long ultrasound series. The combined technique of CIB transducers and TSE–LSTM networks shows a promising application for monitoring and assessing RC structures.","PeriodicalId":515545,"journal":{"name":"Structural Health Monitoring","volume":"11 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141807792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pattern recognition in electromechanical impedance spectroscopy damage detection of adhesive joints using multidimensional scaling","authors":"A. Francisco, G. Tenreiro, António M Lopes, Lucas FM da Silva","doi":"10.1177/14759217241258666","DOIUrl":"https://doi.org/10.1177/14759217241258666","url":null,"abstract":"Adhesive joints are prone to various types of damage sources, which may not be identifiable with current non-destructive tests (NDTs). Structural health monitoring techniques, such as those based on electromechanical impedance spectroscopy (EMIS), aim to outperform NDTs in damage detection, by continuously monitoring structures. Although the EMIS-based algorithmic performance of damage detection has been evaluated on metallic and composite components, integrity monitoring of adhesive joints is yet to be fully determined. Therefore, this article investigates the use of multidimensional scaling (MDS) to cluster and visualize experimental impedance measurements of bonded joints in a three dimensional space. With these results, an Euclidean distance damage metric is used to try and classify the type of damage. The results show that damage detection is easily performed with the MDS algorithm, but effectiveness is dependent on the spectral measurement conditions. Furthermore, reduced dimensional spaces can yield information regarding the size and location of the damage in the adhesive layer, yielding increased knowledge on the integrity of structural adhesive joints.","PeriodicalId":515545,"journal":{"name":"Structural Health Monitoring","volume":"12 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141807583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Priori knowledge-based multi-task wavelet network for guided wave interfacial debonding detection in RC structures","authors":"Zhiwei Liao, Pizhong Qiao","doi":"10.1177/14759217241252485","DOIUrl":"https://doi.org/10.1177/14759217241252485","url":null,"abstract":"Reinforced concrete (RC) has been widely used in infrastructure construction. Interfacial debonding between concrete and reinforcing bars, which is one of the most serious causes of structural failure, has always been a focus of research. In this paper, a novel deep learning-based guided wave analysis framework, termed the Priori Knowledge-based Multi-task Wavelet Network, is proposed for detecting interfacial debonding in RC structures. An end-to-end structure is utilized to surmount the challenges of manual feature uncertainty and dependence on expert knowledge inherent in traditional methods. Incorporating the multi-task learning principles, a deep learning network with branching structures is designed to simultaneously recognize, localize, and quantify the size of interfacial debonding. Damage-sensitive and task-invariant features of guided wave signals are extracted automatically based on supervised learning. To improve the noise resilience the proposed framework incorporates the environmental adaptive training based on data augmentation and continuous wavelet transform. Both the numerical and real structures of RC beams containing with various interfacial debonding scenarios are established to evaluate the debonding detection performance of the framework. Evaluation results demonstrate that the framework exhibits superior interfacial debonding detection capability and enhanced generalizability to varying levels of external interference compared to baseline methods.","PeriodicalId":515545,"journal":{"name":"Structural Health Monitoring","volume":"3 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141336485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A hierarchical Bayesian model updating method for bridge structures by fusing multi-source information","authors":"Lanxin Luo, Mingming Song, Yixian Li, Limin Sun","doi":"10.1177/14759217241253361","DOIUrl":"https://doi.org/10.1177/14759217241253361","url":null,"abstract":"The expanding structural health monitoring (SHM) systems on bridge structures have provided an abundance of multi-source data for finite element model updating (FEMU). The SHM systems on bridges usually include surveillance cameras, vibration sensors (e.g., accelerometers, strain gauges, and displacement sensors), and sometimes a weight-in-motion (WIM) system. Currently, the majority of FEMU studies focus on identified modal parameters derived from vibration data, neglecting the incorporation of video and WIM data in the updating process, which impedes a thorough quantification of uncertainty associated with the structural parameters of interest. Therefore, this paper proposes a hierarchical Bayesian FEMU framework to comprehensively integrate a variety of information sources, including videos, WIM, and vibration data. The data features comprise the static deflections of the bridge under traffic load and modal parameters identified from acceleration measurements. The measured static deflections are extracted from raw displacement data using the locally weighted regression and smoothing scatterplots method. Computer vision-based technology is employed to pinpoint the location of vehicle load on the bridge, which is then integrated into a FEM to predict vehicle-load-induced static deflection. A two-stage Markov Chain Monte Carlo sampling approach is proposed to evaluate the high-dimensional posterior distribution efficiently. The effectiveness of the proposed method is demonstrated on a laboratory three-span bridge model. The results show that the hierarchical Bayesian FEMU can provide accurate estimation and uncertainty quantification on structural stiffness and mass parameters. The updated model accurately predicts both static deflection and modal parameters, exhibiting model-predicted variability in close alignment with the identified values for observed and unobserved responses. Remarkably, this holds true even for unseen loading conditions which are not included in the updating process. These observations validate the capability of the proposed method for multi-source data fusion and uncertainty quantification of real-world bridge structures under operational conditions.","PeriodicalId":515545,"journal":{"name":"Structural Health Monitoring","volume":"58 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141347611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved bidirectional echo state network-based time series reconstruction and prediction for structural response","authors":"Yan-Ke Tan, Yu-Ling Wang, Yiqing Ni, Qi-Lin Zhang, You-Wu Wang","doi":"10.1177/14759217241253082","DOIUrl":"https://doi.org/10.1177/14759217241253082","url":null,"abstract":"The integrity of the data collected by structural health monitoring systems has a significant impact on structural damage detection and state assessment. The missing or abnormal segments and unacquired future segments can be supplemented through signal reconstruction and prediction models. This paper proposes two novel models toward these two tasks based on bidirectional echo state network, which can exploit both historical and future signal segments to improve accuracies. Adaptive combination coefficient is introduced to control the rate of error accumulation. The effectiveness and robustness of the proposed models are verified by cases of synchronized missing, long-term missing, and boundary effect. A hyperparameter study related to both reservoir and memory is conducted to generate optimal models with maximum processing abilities. An ARIMAX and improved Kalman filter-based preprocessing method is adopted to keep all useful information and provide optimal estimation of the true signal values. The proposed models also show high performance in generating the high-frequency components. The superiority of the proposed models is validated through the datasets measured from Canton Tower, both stationary signals under free vibration and non-stationary signals under earthquake being considered.","PeriodicalId":515545,"journal":{"name":"Structural Health Monitoring","volume":"22 26","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141346623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}