Fault Detection and Diagnosis in Industrial Processes with Variational Autoencoder: A Comprehensive Study

This work considers industrial process monitoring using a variational autoencoder (VAE). As a powerful deep generative model, the variational autoencoder and its variants have become popular for process monitoring. However, its monitoring ability, especially its fault diagnosis ability, has not been...

Full description

Bibliographic Details
Main Authors: Jinlin Zhu, Muyun Jiang, Zhong Liu
Format: Article
Language:English
Published: MDPI AG 2021-12-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/22/1/227
_version_ 1797497609316728832
author Jinlin Zhu
Muyun Jiang
Zhong Liu
author_facet Jinlin Zhu
Muyun Jiang
Zhong Liu
author_sort Jinlin Zhu
collection DOAJ
description This work considers industrial process monitoring using a variational autoencoder (VAE). As a powerful deep generative model, the variational autoencoder and its variants have become popular for process monitoring. However, its monitoring ability, especially its fault diagnosis ability, has not been well investigated. In this paper, the process modeling and monitoring capabilities of several VAE variants are comprehensively studied. First, fault detection schemes are defined in three distinct ways, considering latent, residual, and the combined domains. Afterwards, to conduct the fault diagnosis, we first define the deep contribution plot, and then a deep reconstruction-based contribution diagram is proposed for deep domains under the fault propagation mechanism. In a case study, the performance of the process monitoring capability of four deep VAE models, namely, the static VAE model, the dynamic VAE model, and the recurrent VAE models (LSTM-VAE and GRU-VAE), has been comparatively evaluated on the industrial benchmark Tennessee Eastman process. Results show that recurrent VAEs with a deep reconstruction-based diagnosis mechanism are recommended for industrial process monitoring tasks.
first_indexed 2024-03-10T03:21:41Z
format Article
id doaj.art-ff1ad6c5007c456ab8d1822f6af636e2
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-03-10T03:21:41Z
publishDate 2021-12-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-ff1ad6c5007c456ab8d1822f6af636e22023-11-23T12:18:57ZengMDPI AGSensors1424-82202021-12-0122122710.3390/s22010227Fault Detection and Diagnosis in Industrial Processes with Variational Autoencoder: A Comprehensive StudyJinlin Zhu0Muyun Jiang1Zhong Liu2State Key Laboratory of Food Science and Technology, Jiangnan University, Wuxi 214122, ChinaSchool of Computer Science and Engineering, Nanyang Technological University, Singapore 639798, SingaporeKey Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi 214122, ChinaThis work considers industrial process monitoring using a variational autoencoder (VAE). As a powerful deep generative model, the variational autoencoder and its variants have become popular for process monitoring. However, its monitoring ability, especially its fault diagnosis ability, has not been well investigated. In this paper, the process modeling and monitoring capabilities of several VAE variants are comprehensively studied. First, fault detection schemes are defined in three distinct ways, considering latent, residual, and the combined domains. Afterwards, to conduct the fault diagnosis, we first define the deep contribution plot, and then a deep reconstruction-based contribution diagram is proposed for deep domains under the fault propagation mechanism. In a case study, the performance of the process monitoring capability of four deep VAE models, namely, the static VAE model, the dynamic VAE model, and the recurrent VAE models (LSTM-VAE and GRU-VAE), has been comparatively evaluated on the industrial benchmark Tennessee Eastman process. Results show that recurrent VAEs with a deep reconstruction-based diagnosis mechanism are recommended for industrial process monitoring tasks.https://www.mdpi.com/1424-8220/22/1/227process monitoringdeep modelvariational autoencoderdeep reconstructiondynamic process
spellingShingle Jinlin Zhu
Muyun Jiang
Zhong Liu
Fault Detection and Diagnosis in Industrial Processes with Variational Autoencoder: A Comprehensive Study
Sensors
process monitoring
deep model
variational autoencoder
deep reconstruction
dynamic process
title Fault Detection and Diagnosis in Industrial Processes with Variational Autoencoder: A Comprehensive Study
title_full Fault Detection and Diagnosis in Industrial Processes with Variational Autoencoder: A Comprehensive Study
title_fullStr Fault Detection and Diagnosis in Industrial Processes with Variational Autoencoder: A Comprehensive Study
title_full_unstemmed Fault Detection and Diagnosis in Industrial Processes with Variational Autoencoder: A Comprehensive Study
title_short Fault Detection and Diagnosis in Industrial Processes with Variational Autoencoder: A Comprehensive Study
title_sort fault detection and diagnosis in industrial processes with variational autoencoder a comprehensive study
topic process monitoring
deep model
variational autoencoder
deep reconstruction
dynamic process
url https://www.mdpi.com/1424-8220/22/1/227
work_keys_str_mv AT jinlinzhu faultdetectionanddiagnosisinindustrialprocesseswithvariationalautoencoderacomprehensivestudy
AT muyunjiang faultdetectionanddiagnosisinindustrialprocesseswithvariationalautoencoderacomprehensivestudy
AT zhongliu faultdetectionanddiagnosisinindustrialprocesseswithvariationalautoencoderacomprehensivestudy