Deep Multimanifold Transformation-Based Multivariate Time Series Fault Detection
- 1 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (10) , 18397-18407
Abstract
Unsupervised fault detection in multivariate time series (MTS) plays a vital role in ensuring the stable operation of complex systems. Traditional methods often assume that normal data follow a single Gaussian distribution and identify anomalies as deviations from this distribution. However, this simplified assumption fails to capture the diversity and structural complexity of real-world time series, which can lead to misjudgments and reduced detection performance in practical applications. To address this issue, we propose a new method that combines a neighborhood-driven data augmentation strategy with a multimanifold representation learning framework. By incorporating information from local neighborhoods, the augmentation module can simulate contextual variations of normal data, enhancing the model's adaptability to distributional changes. In addition, we design a structure-aware feature learning approach that encourages natural clustering of similar patterns in the feature space while maintaining sufficient distinction between different operational states. Extensive experiments on several public benchmark datasets demonstrate that our method achieves superior performance in terms of both accuracy and robustness, showing strong potential for generalization and real-world deployment.Keywords
Funding Information
- “Pioneer” and “Leading Goose” Research and Development Program of Zhejiang (2024C01140)
- Key Research and Development Program of Hangzhou (2023SZD0073)
- Beijing Natural Science Foundation (L221013)
- InnoHK Program
This publication has 30 references indexed in Scilit:
- Advancing generalizations of multi-scale GAN via adversarial perturbation augmentationsKnowledge-Based Systems, 2023
- Statistical identification guided open-set domain adaptation in fault diagnosisReliability Engineering & System Safety, 2022
- DLME: Deep Local-Flatness Manifold Embedding2022
- A novel unsupervised directed hierarchical graph network with clustering representation for intelligent fault diagnosis of machinesMechanical Systems and Signal Processing, 2022
- A deep manifold-regularized learning model for improving phenotype prediction from multi-modal dataNature Computational Science, 2022
- End-to-end unsupervised fault detection using a flow-based modelReliability Engineering & System Safety, 2021
- Predictive maintenance in the Industry 4.0: A systematic literature reviewComputers & Industrial Engineering, 2020
- Momentum Contrast for Unsupervised Visual Representation Learning2020
- A systematic methodology for Prognostic and Health Management system architecture definitionReliability Engineering & System Safety, 2020
- A Dataset to Support Research in the Design of Secure Water Treatment Systems2017