Comparative Analysis of ARIMA and LSTM Model-Based Anomaly Detection for Unannotated Structural Health Monitoring Data in an Immersed Tunnel
作者机构:School of Naval ArchitectureOcean and Civil EngineeringShanghai Jiao Tong UniversityShanghai200240China Key Laboratory of Road and Bridge Detection and Maintenance Technology of Zhejiang ProvinceHangzhou311305China Zhejiang Scientific Research Institute of TransportHangzhou310023China State Key Laboratory of Coal Mine Dynamics and ControlChongqing UniversityChongqing400044China Hong Kong-Zhuhai-Macao Bridge AuthorityZhuhai519060China
出 版 物:《Computer Modeling in Engineering & Sciences》 (工程与科学中的计算机建模(英文))
年 卷 期:2024年第139卷第5期
页 面:1797-1827页
核心收录:
学科分类:08[工学] 0701[理学-数学] 0812[工学-计算机科学与技术(可授工学、理学学位)]
基 金:supported by the Research and Development Center of Transport Industry of New Generation of Artificial Intelligence Technology(Grant No.202202H) the National Key R&D Program of China(Grant No.2019YFB1600702) the National Natural Science Foundation of China(Grant Nos.51978600&51808336)
主 题:Anomaly detection dynamic predictive model structural health monitoring immersed tunnel LSTM ARIMA
摘 要:Structural Health Monitoring(SHM)systems have become a crucial tool for the operational management of long *** immersed tunnels exposed to both traffic loads and the effects of the marine environment,efficiently identifying abnormal conditions from the extensive unannotated SHM data presents a significant *** study proposed amodel-based approach for anomaly detection and conducted validation and comparative analysis of two distinct temporal predictive models using SHM data from a real immersed ***,a dynamic predictive model-based anomaly detectionmethod is proposed,which utilizes a rolling time window for modeling to achieve dynamic *** the assumption of temporal data similarity,an interval prediction value deviation was employed to determine the abnormality of the ***,dynamic predictive models were constructed based on the Autoregressive Integrated Moving Average(ARIMA)and Long Short-Term Memory(LSTM)*** hyperparameters of these models were optimized and selected using monitoring data from the immersed tunnel,yielding viable static and dynamic predictive ***,the models were applied within the same segment of SHM data,to validate the effectiveness of the anomaly detection approach based on dynamic predictive modeling.A detailed comparative analysis discusses the discrepancies in temporal anomaly detection between the ARIMA-and LSTM-based *** results demonstrated that the dynamic predictive modelbased anomaly detection approach was effective for dealing with unannotated SHM *** a comparison between ARIMA and LSTM,it was found that ARIMA demonstrated higher modeling efficiency,rendering it suitable for short-term *** contrast,the LSTM model exhibited greater capacity to capture long-term performance trends and enhanced early warning capabilities,thereby resulting in superior overall performance.