Long Horizon Anomaly Prediction in Multivariate Time Series with Causal Autoencoders

Abstract

Predictive maintenance is essential for complex industrial systems to foresee anomalies before major system faults or ultimate breakdown. However, the existing efforts on Industry 4.0 predictive monitoring are directed at semi-supervised anomaly detection with limited robustness for large systems, which are often accompanied by uncleaned and unlabeled data. We address the challenge of predicting anomalies through data-driven end-to-end deep learning models using early warning symptoms on multivariate time series sensor data. We introduce AnoP, a long multi-timestep anomaly prediction system based on unsupervised attention-based causal residual networks, to raise alerts for anomaly prevention. The experimental evaluation on large data sets from detector health monitoring of the Hadron Calorimeter of the CMS Experiment at LHC CERN demonstrates the promising efficacy of the proposed approach. AnoP predicted around 60% of the anomalies up to seven days ahead, and the majority of the missed anomalies are abnormalities with unpredictable noisy-like behavior. Moreover, it has discovered previously unknown anomalies in the calorimeter’s sensors.