Enhanced neural network modelling for process fault diagnosis

被引：0
|
作者：
Chang, TK [1 ]
Yu, DL [1 ]
Williams, D [1 ]
机构：
[1] Liverpool John Moores Univ, Control Syst Res Grp, Liverpool L3 5UX, Merseyside, England
来源：
CONTROL APPLICATIONS IN MARINE SYSTEMS 2001 (CAMS 2001) | 2002年
关键词：
fault detection; fault isolation; neural networks; non-linear systems; process identification;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
A neural network (NN) based fault detection and isolation (FDI) approach for unknown non-linear system is proposed. This FDI scheme is able to detect both actuator and sensor faults. An enhanced parallel (independent) NN model is trained to represent the process, and used to generate residual. A mean-weight strategy is introduced to overcome the unmodelled noise and disturbance problem. An information pre-processor is implemented to convert the quantitative residual to qualitative form and applied to a NN fault classifier to isolate different faults. The developed techniques are demonstrated with a multi-variable non-linear tank process. Copyright (C) 2001 IFAC.
引用
收藏
页码：215 / 220
页数：6
相关论文
共 50 条
  • [31] Neural network modelling of a depollution process
    Steyer, JP
    Pelayo-Ortiz, C
    González-Alvarez, V
    Bonnet, B
    Bories, A
    [J]. BIOPROCESS ENGINEERING, 2000, 23 (06) : 727 - 730
  • [32] Neural network modelling of an electrochemical process
    Seker, S
    Becerik, I
    [J]. ANNALI DI CHIMICA, 2003, 93 (5-6) : 551 - 560
  • [33] An enhanced convolutional neural network with enlarged receptive fields for fault diagnosis of planetary gearboxes
    Han, Yan
    Tang, Baoping
    Deng, Lei
    [J]. COMPUTERS IN INDUSTRY, 2019, 107 : 50 - 58
  • [34] Rolling bearing fault diagnosis using enhanced convolutional neural network with compressed sensing
    Liang, Tianchen
    Wang, Jiayao
    Wang, Haoyu
    Wu, Shuaipeng
    [J]. 2018 INTERNATIONAL CONFERENCE ON SENSING, DIAGNOSTICS, PROGNOSTICS, AND CONTROL (SDPC), 2018, : 148 - 152
  • [35] In Situ Motor Fault Diagnosis Using Enhanced Convolutional Neural Network in an Embedded System
    Lu, Siliang
    Qian, Gang
    He, Qingbo
    Liu, Fang
    Liu, Yongbin
    Wang, Qunjing
    [J]. IEEE SENSORS JOURNAL, 2020, 20 (15) : 8287 - 8296
  • [36] Enhanced Recurrent Neural Network for Fault Diagnosis of Uncertain Wind Energy Conversion Systems*
    Dhibi, Khaled
    Mansouri, Majdi
    Bouzrara, Kais
    Nounou, Hazem
    Nounou, Mohamed
    [J]. 2022 8TH INTERNATIONAL CONFERENCE ON CONTROL, DECISION AND INFORMATION TECHNOLOGIES (CODIT'22), 2022, : 1330 - 1335
  • [37] An Enhanced Fault Diagnosis Method with Uncertainty Quantification Using Bayesian Convolutional Neural Network
    Fang, Qihang
    Xiong, Gang
    Shang, Xiuqin
    Liu, Sheng
    Hu, Bin
    Shen, Zhen
    [J]. 2020 IEEE 16TH INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING (CASE), 2020, : 588 - 593
  • [38] Transformer fault diagnosis technology based on AdaBoost enhanced transferred convolutional neural network
    Tao, Weige
    Sun, Zhigang
    Yang, Zhao
    Liang, Bao
    Wang, Guotao
    Xiao, Shuyan
    [J]. Expert Systems with Applications, 2025, 264
  • [39] Gated recurrent unit-enhanced deep convolutional neural network for real-time industrial process fault diagnosis
    Zhang, Jiaxin
    Miao, Zhang
    Feng, Zemin
    Lv, Ruifang
    Lu, Chenyang
    Dai, Yiyang
    Dong, Lichun
    [J]. PROCESS SAFETY AND ENVIRONMENTAL PROTECTION, 2023, 175 : 129 - 149
  • [40] Fault diagnosis with fault gradation using neural network group
    Ma, Cheng-Cai
    Gu, Xiao-Dong
    [J]. Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics, 2009, 31 (01): : 225 - 228
12345