Enhancing Multivariate Time Series Anomaly Detection With an Inference Stacked Recurrent-Autoencoder in Strong Mechanistic Contexts

Tianming Xie, Zhiwei Gao*, Qifa Xu, Cuixia Jiang, Aihua Zhang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Downloads (Pure)

Abstract

Existing self-supervised multivariate time series anomaly detection methods struggle with interference among variables during reconstruction. They also tend to miss capturing critical anomaly information, resulting in unsatisfactory performance, especially in scenarios with strong mechanistic contexts. To this end, we propose a targeted anomaly detection algorithm called inference stacked recurrent autoencoder (ISRAE). Its key contribution lies in the design of a specific inference kernel, derived from specialist knowledge, which captures the strong mechanistic relationships among variables. This kernel is then fused with the multidimensional anomalies predicted by the SRAE, which mitigates interference among variables through the stacking technique. Furthermore, a novel differential constraint is introduced into the loss function, which not only highlights anomaly reconstruction errors, but also smooths the reconstructions, enhancing overall detection performance. Comprehensive comparison experiments and ablation studies show that ISRAE achieves superior anomaly detection performance under strong mechanistic contexts and highlight the importance of each key module in ISRAE.
Original languageEnglish
Pages (from-to)1-10
Number of pages10
JournalIEEE Transactions on Industrial Informatics
Early online date13 Nov 2024
DOIs
Publication statusE-pub ahead of print - 13 Nov 2024

Keywords

  • Anomaly detection
  • inference kernel
  • inference stacked recurrent-autoencoder (ISRAE)
  • multivariate time series
  • self-supervised method
  • strong mechanistic context
  • inference stacked recurrent-Autoencoder (ISRAE)

Cite this