Lei Wang, Xiaoling Wang, Jun Zhang, Jiajun Wang, Hongling Yu
{"title":"基于自监督学习的大坝变形监测异常数据成像时间序列检测与分类方法","authors":"Lei Wang, Xiaoling Wang, Jun Zhang, Jiajun Wang, Hongling Yu","doi":"10.1016/j.istruc.2024.107148","DOIUrl":null,"url":null,"abstract":"Dam safety monitoring systems collect a significant amount of data, including numerous instances of abnormal data attributed to factors such as aging equipment and recording errors. The accurate detection and classification of abnormal data can effectively enhance the reliability of rockfill dam safety assessments based on monitoring data. Note that the scarcity of the abnormal data in actual monitoring datasets poses a significant challenge to existing data-driven anomaly detection studies. To address these issues, we develop a novel self-supervised learning-based framework for abnormal data detection and classification of rockfill dam deformation data. This framework includes an abnormal data detection method based on transformers and synthetic abnormal data. By analyzing and further modeling the real-world abnormal data, a criterion for synthesizing abnormal data is proposed to augment the scale of abnormal data. Additionally, we introduce an abnormal data classification method using imaging time series, which captures the multi-scale features of sequence data in a higher dimension by encoding it into image representations and employing a residual network (ResNet) for feature extraction. The effectiveness of the proposed approach is demonstrated through an engineering case study. The F1 scores for abnormal data detection and classification are 0.9722 and 0.9596, respectively, which surpass those of other conventional methods. The results demonstrate that the proposed approach achieves high-precision detection and classification of abnormal data, even under adverse conditions where abnormal data are sparse, thus ensuring reliable safety assessment of rockfill dams.","PeriodicalId":48642,"journal":{"name":"Structures","volume":null,"pages":null},"PeriodicalIF":3.9000,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A self-supervised learning-based approach for detection and classification of dam deformation monitoring abnormal data with imaging time series\",\"authors\":\"Lei Wang, Xiaoling Wang, Jun Zhang, Jiajun Wang, Hongling Yu\",\"doi\":\"10.1016/j.istruc.2024.107148\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Dam safety monitoring systems collect a significant amount of data, including numerous instances of abnormal data attributed to factors such as aging equipment and recording errors. The accurate detection and classification of abnormal data can effectively enhance the reliability of rockfill dam safety assessments based on monitoring data. Note that the scarcity of the abnormal data in actual monitoring datasets poses a significant challenge to existing data-driven anomaly detection studies. To address these issues, we develop a novel self-supervised learning-based framework for abnormal data detection and classification of rockfill dam deformation data. This framework includes an abnormal data detection method based on transformers and synthetic abnormal data. By analyzing and further modeling the real-world abnormal data, a criterion for synthesizing abnormal data is proposed to augment the scale of abnormal data. Additionally, we introduce an abnormal data classification method using imaging time series, which captures the multi-scale features of sequence data in a higher dimension by encoding it into image representations and employing a residual network (ResNet) for feature extraction. The effectiveness of the proposed approach is demonstrated through an engineering case study. The F1 scores for abnormal data detection and classification are 0.9722 and 0.9596, respectively, which surpass those of other conventional methods. The results demonstrate that the proposed approach achieves high-precision detection and classification of abnormal data, even under adverse conditions where abnormal data are sparse, thus ensuring reliable safety assessment of rockfill dams.\",\"PeriodicalId\":48642,\"journal\":{\"name\":\"Structures\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.9000,\"publicationDate\":\"2024-09-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Structures\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1016/j.istruc.2024.107148\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, CIVIL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Structures","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1016/j.istruc.2024.107148","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
引用次数: 0
摘要
大坝安全监测系统收集了大量数据,其中不乏因设备老化和记录错误等因素造成的异常数据。对异常数据进行准确检测和分类,可有效提高基于监测数据的堆石坝安全评估的可靠性。需要注意的是,实际监测数据集中异常数据的稀缺性给现有的数据驱动异常检测研究带来了巨大挑战。为解决这些问题,我们开发了一种基于自监督学习的新型框架,用于对堆石坝变形数据进行异常数据检测和分类。该框架包括基于变压器和合成异常数据的异常数据检测方法。通过对真实世界异常数据的分析和进一步建模,我们提出了一种合成异常数据的标准,以扩大异常数据的规模。此外,我们还介绍了一种使用成像时间序列的异常数据分类方法,该方法通过将序列数据编码为图像表示并使用残差网络(ResNet)进行特征提取,在更高的维度上捕捉序列数据的多尺度特征。通过工程案例研究证明了所提方法的有效性。异常数据检测和分类的 F1 分数分别为 0.9722 和 0.9596,超过了其他传统方法。结果表明,即使在异常数据稀少的不利条件下,所提出的方法也能实现对异常数据的高精度检测和分类,从而确保对堆石坝进行可靠的安全评估。
A self-supervised learning-based approach for detection and classification of dam deformation monitoring abnormal data with imaging time series
Dam safety monitoring systems collect a significant amount of data, including numerous instances of abnormal data attributed to factors such as aging equipment and recording errors. The accurate detection and classification of abnormal data can effectively enhance the reliability of rockfill dam safety assessments based on monitoring data. Note that the scarcity of the abnormal data in actual monitoring datasets poses a significant challenge to existing data-driven anomaly detection studies. To address these issues, we develop a novel self-supervised learning-based framework for abnormal data detection and classification of rockfill dam deformation data. This framework includes an abnormal data detection method based on transformers and synthetic abnormal data. By analyzing and further modeling the real-world abnormal data, a criterion for synthesizing abnormal data is proposed to augment the scale of abnormal data. Additionally, we introduce an abnormal data classification method using imaging time series, which captures the multi-scale features of sequence data in a higher dimension by encoding it into image representations and employing a residual network (ResNet) for feature extraction. The effectiveness of the proposed approach is demonstrated through an engineering case study. The F1 scores for abnormal data detection and classification are 0.9722 and 0.9596, respectively, which surpass those of other conventional methods. The results demonstrate that the proposed approach achieves high-precision detection and classification of abnormal data, even under adverse conditions where abnormal data are sparse, thus ensuring reliable safety assessment of rockfill dams.
期刊介绍:
Structures aims to publish internationally-leading research across the full breadth of structural engineering. Papers for Structures are particularly welcome in which high-quality research will benefit from wide readership of academics and practitioners such that not only high citation rates but also tangible industrial-related pathways to impact are achieved.