Normalizing flows for novelty detection in industrial time series data

TL;DR

This paper explores the use of flow-based deep generative models, specifically normalizing flows, for novelty detection in industrial time series data, demonstrating their effectiveness over traditional methods.

Contribution

It introduces the application of normalizing flows, including Masked Autoregressive Flows and Free-form Jacobian models, for anomaly detection in time series data.

Findings

Flow-based models outperform Local Outlier Factor in experiments.

Models successfully detect anomalies in synthetic and industrial data.

Normalizing flows provide exact likelihood scores for novelty detection.

Abstract

Flow-based deep generative models learn data distributions by transforming a simple base distribution into a complex distribution via a set of invertible transformations. Due to the invertibility, such models can score unseen data samples by computing their exact likelihood under the learned distribution. This makes flow-based models a perfect tool for novelty detection, an anomaly detection technique where unseen data samples are classified as normal or abnormal by scoring them against a learned model of normal data. We show that normalizing flows can be used as novelty detectors in time series. Two flow-based models, Masked Autoregressive Flows and Free-form Jacobian of Reversible Dynamics restricted by autoregressive MADE networks, are tested on synthetic data and motor current data from an industrial machine and achieve good results, outperforming a conventional novelty detection method, the Local Outlier Factor.