Pattern-Based Time-Series Risk Scoring for Anomaly Detection and Alert Filtering -- A Predictive Maintenance Case Study
Elad Liebman
TL;DR
The paper tackles time-series anomaly detection in industrial systems by introducing a fast, pattern-based risk-scoring approach that leverages multivariate sequential patterns rather than static summaries. It emphasizes pattern similarity for anomaly detection and alert filtering, avoiding the computational burden of RNNs or attention mechanisms while remaining scalable to large industrial datasets. Empirical results demonstrate applicability to real-world systems and robustness on a public dataset, with an optimization objective focused on alert recall to improve practical monitoring performance. The work offers a scalable predictive maintenance solution with broad applicability to industrial time-series data and demonstrates competitive performance against state-of-the-art baselines.
Abstract
Fault detection is a key challenge in the management of complex systems. In the context of SparkCognition's efforts towards predictive maintenance in large scale industrial systems, this problem is often framed in terms of anomaly detection - identifying patterns of behavior in the data which deviate from normal. Patterns of normal behavior aren't captured simply in the coarse statistics of measured signals. Rather, the multivariate sequential pattern itself can be indicative of normal vs. abnormal behavior. For this reason, normal behavior modeling that relies on snapshots of the data without taking into account temporal relationships as they evolve would be lacking. However, common strategies for dealing with temporal dependence, such as Recurrent Neural Networks or attention mechanisms are oftentimes computationally expensive and difficult to train. In this paper, we propose a fast and efficient approach to anomaly detection and alert filtering based on sequential pattern similarities. In our empirical analysis section, we show how this approach can be leveraged for a variety of purposes involving anomaly detection on a large scale real-world industrial system. Subsequently, we test our approach on a publicly-available dataset in order to establish its general applicability and robustness compared to a state-of-the-art baseline. We also demonstrate an efficient way of optimizing the framework based on an alert recall objective function.