{"title":"基于冲击回波信号实验-仿真混合数据集迁移学习的无监督域自适应混凝土内部缺陷可视化","authors":"Gao Shang, Jun Chen","doi":"10.1177/14759217231192058","DOIUrl":null,"url":null,"abstract":"Detecting concrete internal defects through deep learning analysis of impact echo signals faces two challenges: (1) the traditional signal processing method such as wavelet transform (WT) fails to reflect data-sensitive damage characteristics due to the uncertainty principle and (2) the limited labeled data acquired from real structures impedes network training. To address the first challenge, this paper proposes the WT-based synchrosqueezing transform (WT-SST) for the conversion of time-series data to the time-frequency spectrogram, which can provide effective features for the network in time and frequency domains simultaneously. To overcome the second challenge, numerical simulation data are supplemented for the augment of labeled data. To minimize the effect of data variance between experiments and simulations, this paper uses an unsupervised domain adaptation (DA) network for the transfer training of labeled simulation data (original domain) and unlabeled experimental data (target domain). The DA network extracts domain-invariant features by maximizing the domain recognition error and minimizing the probability distribution distance. The damage probability is calculated by the trained model to produce a 2D defect contour image of concrete specimens, and the three-dimensional visualization of internal defects by estimating the defect depth based on the defect area of contour image. Finally, the recognition precision, recall, F1-score, and accuracy of the model of unsupervised DA network trained by a hybrid dataset reaches 89.4%, 88.4%, 88.9%, and 94.7%, respectively.","PeriodicalId":51184,"journal":{"name":"Structural Health Monitoring-An International Journal","volume":null,"pages":null},"PeriodicalIF":5.7000,"publicationDate":"2023-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Visualization of concrete internal defects based on unsupervised domain adaptation algorithm for transfer learning of experiment-simulation hybrid dataset of impact echo signals\",\"authors\":\"Gao Shang, Jun Chen\",\"doi\":\"10.1177/14759217231192058\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Detecting concrete internal defects through deep learning analysis of impact echo signals faces two challenges: (1) the traditional signal processing method such as wavelet transform (WT) fails to reflect data-sensitive damage characteristics due to the uncertainty principle and (2) the limited labeled data acquired from real structures impedes network training. To address the first challenge, this paper proposes the WT-based synchrosqueezing transform (WT-SST) for the conversion of time-series data to the time-frequency spectrogram, which can provide effective features for the network in time and frequency domains simultaneously. To overcome the second challenge, numerical simulation data are supplemented for the augment of labeled data. To minimize the effect of data variance between experiments and simulations, this paper uses an unsupervised domain adaptation (DA) network for the transfer training of labeled simulation data (original domain) and unlabeled experimental data (target domain). The DA network extracts domain-invariant features by maximizing the domain recognition error and minimizing the probability distribution distance. The damage probability is calculated by the trained model to produce a 2D defect contour image of concrete specimens, and the three-dimensional visualization of internal defects by estimating the defect depth based on the defect area of contour image. Finally, the recognition precision, recall, F1-score, and accuracy of the model of unsupervised DA network trained by a hybrid dataset reaches 89.4%, 88.4%, 88.9%, and 94.7%, respectively.\",\"PeriodicalId\":51184,\"journal\":{\"name\":\"Structural Health Monitoring-An International Journal\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":5.7000,\"publicationDate\":\"2023-09-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Structural Health Monitoring-An International Journal\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1177/14759217231192058\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Structural Health Monitoring-An International Journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1177/14759217231192058","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}
Visualization of concrete internal defects based on unsupervised domain adaptation algorithm for transfer learning of experiment-simulation hybrid dataset of impact echo signals
Detecting concrete internal defects through deep learning analysis of impact echo signals faces two challenges: (1) the traditional signal processing method such as wavelet transform (WT) fails to reflect data-sensitive damage characteristics due to the uncertainty principle and (2) the limited labeled data acquired from real structures impedes network training. To address the first challenge, this paper proposes the WT-based synchrosqueezing transform (WT-SST) for the conversion of time-series data to the time-frequency spectrogram, which can provide effective features for the network in time and frequency domains simultaneously. To overcome the second challenge, numerical simulation data are supplemented for the augment of labeled data. To minimize the effect of data variance between experiments and simulations, this paper uses an unsupervised domain adaptation (DA) network for the transfer training of labeled simulation data (original domain) and unlabeled experimental data (target domain). The DA network extracts domain-invariant features by maximizing the domain recognition error and minimizing the probability distribution distance. The damage probability is calculated by the trained model to produce a 2D defect contour image of concrete specimens, and the three-dimensional visualization of internal defects by estimating the defect depth based on the defect area of contour image. Finally, the recognition precision, recall, F1-score, and accuracy of the model of unsupervised DA network trained by a hybrid dataset reaches 89.4%, 88.4%, 88.9%, and 94.7%, respectively.
期刊介绍:
Structural Health Monitoring is an international peer reviewed journal that publishes the highest quality original research that contain theoretical, analytical, and experimental investigations that advance the body of knowledge and its application in the discipline of structural health monitoring.