Knowledge-Assisted Multi-Graph Dependency Learning for Multivariate Time Series Anomaly Detection in Multi-Stage Industrial Processes
Machine LearningArtificial Intelligence
Summary
The authors address the challenge of detecting anomalies in complex industrial systems that use many sensors over multiple stages. They point out that previous methods using graph neural networks (GNNs) often ignore important knowledge about how the industrial processes actually work. To fix this, they create a new approach that builds three types of graphs: one from data alone and two others that include process knowledge. Their method uses a multi-graph attention network to better understand sensor relationships and detect issues more accurately, as shown in tests on real industrial data.
Authors
Jaeyeong Lee, Taeseong Yoon, Wonmo Koo, Heeyoung Kim
Abstract
Industrial processes often generate complex, interdependent time-series data from multiple sensors across multiple stages, forming complex dependencies among variables and process stages. Effective monitoring and timely anomaly detection of these time series through multivariate time series anomaly detection (MTAD) is crucial for preventing failures and ensuring the reliability of automated systems. Graph neural networks (GNNs) have advanced MTAD by leveraging data-driven graphs to model complex dependencies among variables, effectively capturing relational structures within multivariate time series to enhance anomaly detection performance. However, existing GNN-based approaches often overlook critical process knowledge, and even when this knowledge is considered, seamlessly incorporating it into existing models remains inherently challenging, leading to suboptimal performance. To address this limitation, we propose a knowledge-assisted multi-graph framework for modeling sensor dependencies in multi-stage industrial processes for MTAD, which explicitly incorporates process knowledge into graph learning to enhance dependency modeling and improve anomaly detection performance. Our method constructs three complementary graphs: one purely data-driven and two refined by integrating structural constraints derived from process knowledge. To effectively leverage these graphs for anomaly detection, we employ a multi-graph attention network, enabling a more accurate and robust representation of complex dependencies. Comprehensive experiments on two real-world, multi-stage industrial datasets demonstrate that incorporating process knowledge substantially enhances anomaly detection performance.