Deep Anomaly Detection on Tennessee Eastman Process Data
This work addresses the problem of choosing effective anomaly detection methods for chemical process data, which is incremental as it benchmarks existing methods on a known dataset.
The paper conducted the first comprehensive evaluation of modern deep-learning unsupervised anomaly detection methods on the Tennessee Eastman process dataset, a standard benchmark for nearly three decades, to aid in selecting appropriate methods for industrial applications.
This paper provides the first comprehensive evaluation and analysis of modern (deep-learning) unsupervised anomaly detection methods for chemical process data. We focus on the Tennessee Eastman process dataset, which has been a standard litmus test to benchmark anomaly detection methods for nearly three decades. Our extensive study will facilitate choosing appropriate anomaly detection methods in industrial applications.