Spatiotemporal Transform Network-Based Anomaly Detection and Localization of Distributed Parameter Systems
- 6 January 2025
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (4) , 2770-2778
Abstract
Due to complex spatiotemporal couplings, it is difficult to detect and locate spatiotemporal abnormal sources for distributed parameter systems (DPSs) with unknown governing equations. In this research, a spatiotemporal transform network-based anomaly detection and localization framework is proposed for unknown DPSs. Considering the orthogonality, the spatial basis functions (SBFs) are optimized by the nonlinear space–time separation network to achieve the minimal reconstruction error. The Gaussian process regression is used to identify the temporal dynamics, based on which the temporal statistic is constructed. A comprehensive statistic is designed by considering the temporal dynamics and spatial dissimilarity for reliable detection. With the spatial construction, the weighted absolute error of SBFs is constructed for anomaly localization. The anomaly detectability is proven by theoretical analysis. Experiments on a lithium-ion battery demonstrate the effectiveness and superiority of the proposed method in detecting and localizing battery internal short circuits.Keywords
Funding Information
- National Natural Science Foundation of China (52407250, U24B20103)
- Fundamental Research Funds for the Central Universities (WUT: 2024IVA044)
This publication has 31 references indexed in Scilit:
- Multiscale dynamic construction for abnormality detection and localization of Li-ion batteriesApplied Energy, 2022
- Actuator and Sensor Fault Detection and Failure Prediction for Systems with Multi-dimensional Nonlinear Partial Differential EquationsInternational Journal of Control, Automation, and Systems, 2022
- Thermal runaway propagation behavior within 18,650 lithium-ion battery packs: A modeling studyJournal of Energy Storage, 2020
- A tutorial on Gaussian process regression: Modelling, exploring, and exploiting functionsJournal of Mathematical Psychology, 2018
- Electrochemical thermal modeling and experimental measurements of 18650 cylindrical lithium-ion battery during discharge cycle for an EVApplied Thermal Engineering, 2018
- Model-based fault detection, estimation, and prediction for a class of linear distributed parameter systemsAutomatica, 2016
- Internal short circuit detection for battery pack using equivalent parameter and consistency methodJournal of Power Sources, 2015
- Learning similarity with cosine similarity ensembleInformation Sciences, 2015
- Data-driven Design of Fault Diagnosis and Fault-tolerant Control Systems2014
- Fault detection and identification of nonlinear processes based on kernel PCAChemometrics and Intelligent Laboratory Systems, 2005