Title: A variational autoencoders approach for process monitoring and fault diagnosis

Authors: Peng Tang; Kaixiang Peng; Jie Dong; Kai Zhang; Ruihua Jiao

Addresses: Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, 100083, China ' Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, 100083, China ' Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, 100083, China ' Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, 100083, China ' Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, 100083, China

Abstract: Probabilistic models, which can model the process noise and can handle the problem of missing data in the probabilistic framework, recently have been got much attention in process monitoring and fault diagnosis area. This paper presents a new probabilistic methodology for fault detection and diagnosis in nonlinear processes using a variational autoencoders (VAEs) models. Two statistic index, based on the probability density distribution of measure variables and latent structure variable, are built to monitoring fault. Then a probabilistic contribution analysis method, based on the concept of missing variable estimation, is proposed for fault diagnosis. The performance of fault detection and diagnosis is demonstrated through its application for the monitoring of Tennessee Eastman (TE) industrial process, and the effectiveness is verified.

Keywords: VAE; variational autoencoder; process monitoring and fault diagnosis; probabilistic contribution analysis; nonlinear processes; TE.

DOI: 10.1504/IJSCIP.2021.117696

International Journal of System Control and Information Processing, 2021 Vol.3 No.3, pp.229 - 245

Received: 03 Sep 2020
Accepted: 18 Feb 2021

Published online: 14 Sep 2021 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article