Deep Anomaly Detection on Tennessee Eastman Process Data

03/10/2023

∙

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.

READ FULL TEXT

Deep Anomaly Detection on Tennessee Eastman Process Data

Anomaly Detection Based on Deep Learning Using Video for Prevention of Industrial Accidents

Deep Learning for Anomaly Detection: A Review

A Generalized Active Learning Approach for Unsupervised Anomaly Detection

Network Anomaly Detection: A Survey and Comparative Analysis of Stochastic and Deterministic Methods

Dependency-based Anomaly Detection: Framework, Methods and Benchmark

Adaptive Model Pooling for Online Deep Anomaly Detection from a Complex Evolving Data Stream

Lifelong Learning for Anomaly Detection: New Challenges, Perspectives, and Insights

Deep Anomaly Detection on Tennessee Eastman Process Data

Related Research

Anomaly Detection Based on Deep Learning Using Video for Prevention of Industrial Accidents

Deep Learning for Anomaly Detection: A Review

A Generalized Active Learning Approach for Unsupervised Anomaly Detection

Network Anomaly Detection: A Survey and Comparative Analysis of Stochastic and Deterministic Methods

Dependency-based Anomaly Detection: Framework, Methods and Benchmark

Adaptive Model Pooling for Online Deep Anomaly Detection from a Complex Evolving Data Stream

Lifelong Learning for Anomaly Detection: New Challenges, Perspectives, and Insights