Multisensor Anomaly Detection and Interpretable Analysis for Linear Induction Motors

doi:10.1109/TITS.2023.3267462

Multisensor Anomaly Detection and Interpretable Analysis for Linear Induction Motors

2023-09-01

3

PRE

AI

DOI：10.1109/TITS.2023.3267462

Original

Original request for help

Save

Abstract

En 中文

In this paper, a graph neural network anomaly detection framework is proposed to improve the safety of linear induction motors, a key component of high-speed maglev trains. In our framework, each sensor sequence is treated as a separate feature. The similarity and correlation between multi-dimensional features are learned as prior knowledge for graph structure learning. The spatial-temporal graph attention network incorporates prior knowledge to learn complex correlations between nodes. Furthermore, the framework optimises a joint model for anomaly detection, avoiding the trap of falling into either local or global optimisation and thus achieving the most stable detection. Experimental results of our method on four real-world datasets show that it is more accurate than other state-of-the-art methods in detecting anomalies and capturing inter-sensor correlations. Further analysis of graph attention weights and visualization subgraphs show that our framework is well interpretable and allowing users to locate the root cause of anomalies.

Keywords:

Time series analysis

Correlation

Anomaly detection

Predictive models

Knowledge engineering

Induction motors

Feature extraction

Intelligent transportation systems

anomaly detection

interpretable analysis

graph attention networks

linear induction motors

Multisensor Anomaly Detection and Interpretable Analysis for Linear Induction Motors

Abstract

Journal

Organization