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

被引:15
|
作者
Zhu, Jinlin [1 ,2 ]
Jiang, Muyun [3 ]
Liu, Zhong [4 ]
机构
[1] Jiangnan Univ, State Key Lab Food Sci & Technol, Wuxi 214122, Jiangsu, Peoples R China
[2] Jiangnan Univ, Sch Food Sci & Technol, Wuxi 214122, Jiangsu, Peoples R China
[3] Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore 639798, Singapore
[4] Jiangnan Univ, Key Lab Adv Proc Control Light Ind, Minist Educ, Wuxi 214122, Jiangsu, Peoples R China
基金
中国国家自然科学基金;
关键词
process monitoring; deep model; variational autoencoder; deep reconstruction; dynamic process;
D O I
10.3390/s22010227
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
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.
引用
收藏
页数:26
相关论文
共 50 条
  • [1] A review on autoencoder based representation learning for fault detection and diagnosis in industrial processes
    Qian, Jinchuan
    Song, Zhihuan
    Yao, Yuan
    Zhu, Zheren
    Zhang, Xinmin
    CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2022, 231
  • [2] Comparison of autoencoder architectures for fault detection in industrial processes
    Spina, Deris Eduardo
    Campos, Luiz Felipe de O.
    de Arruda, Wallthynay F.
    Melo, Afranio
    Alves, Marcelo F. de S.
    Rabello, Gildeir Lima
    Anzai, Thiago K.
    Pinto, Jose Carlos
    DIGITAL CHEMICAL ENGINEERING, 2024, 12
  • [3] Industrial Process Modeling and Fault Detection with Recurrent Kalman Variational Autoencoder
    Zhang, Zheng
    Zhu, Jinlin
    Liu, Yang
    Ge, Zhiqiang
    PROCEEDINGS OF 2020 IEEE 9TH DATA DRIVEN CONTROL AND LEARNING SYSTEMS CONFERENCE (DDCLS'20), 2020, : 1370 - 1376
  • [4] Adversarial Autoencoder Based Feature Learning for Fault Detection in Industrial Processes
    Jang, Kyojin
    Hong, Seokyoung
    Kim, Minsu
    Na, Jonggeol
    Moon, Il
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2022, 18 (02) : 827 - 834
  • [5] A Spatial-Temporal Variational Graph Attention Autoencoder Using Interactive Information for Fault Detection in Complex Industrial Processes
    Lv, Mingjie
    Li, Yonggang
    Liang, Huiping
    Sun, Bei
    Yang, Chunhua
    Gui, Weihua
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (03) : 3062 - 3076
  • [6] A comprehensive fault detection and diagnosis method for chemical processes
    Rao, Silin
    Wang, Jingtao
    CHEMICAL ENGINEERING SCIENCE, 2024, 300
  • [7] Residual attention convolutional autoencoder for feature learning and fault detection in nonlinear industrial processes
    Xing Liu
    Jianbo Yu
    Lyujiangnan Ye
    Neural Computing and Applications, 2021, 33 : 12737 - 12753
  • [8] Residual attention convolutional autoencoder for feature learning and fault detection in nonlinear industrial processes
    Liu, Xing
    Yu, Jianbo
    Ye, Lyujiangnan
    NEURAL COMPUTING & APPLICATIONS, 2021, 33 (19): : 12737 - 12753
  • [9] Dual-attention LSTM autoencoder for fault detection in industrial complex dynamic processes
    Zeng, Lei
    Jin, Qiwen
    Lin, Zhiming
    Zheng, Chenghang
    Wu, Yingchun
    Wu, Xuecheng
    Gao, Xiang
    PROCESS SAFETY AND ENVIRONMENTAL PROTECTION, 2024, 185 : 1145 - 1159
  • [10] Hierarchical monitoring of industrial processes for fault detection, fault grade evaluation, and fault diagnosis
    Luo, Lijia
    Lovelett, Robert J.
    Ogunnaike, Babatunde A.
    AICHE JOURNAL, 2017, 63 (07) : 2781 - 2795