Process Monitoring for Multimodal Processes With Mode-Reachability Constraints

被引:32
|
作者
Afzal, Muhammad Shahzad [1 ]
Tan, Wen [2 ,3 ]
Chen, Tongwen [1 ]
机构
[1] Univ Alberta, Dept Elect & Comp Engn, Edmonton, AB T6G 1H9, Canada
[2] Univ Alberta, Edmonton, AB T6G 1H9, Canada
[3] North China Elect Power Univ, Sch Control & Comp Engn, Beijing 102206, Peoples R China
基金
加拿大自然科学与工程研究理事会;
关键词
Hidden Markov models (HMMs); multi-modal processes; Viterbi algorithm; PRINCIPAL COMPONENT ANALYSIS; HIDDEN MARKOV-MODELS; FAULT-DETECTION; DIAGNOSIS; INFERENCE;
D O I
10.1109/TIE.2017.2677351
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
For increased efficiency and profitability, many processes have multiple modes of operation. Switching between different operating modes is performed according to the standard operating procedures. These procedures are set by considering safety and operating limitations of various subsystems and equipment, and thus put restrictions on the switching of the process modes. In this paper, a hidden Markov model based monitoring method is proposed that can not only handle the multimodality of process data but can also capture the mode switching restrictions. A two-step Viterbi algorithm is proposed for effective mode detection in the event of faults, and a reconstruction-based fault isolation algorithm is developed to build the contribution plots. Application examples demonstrate the effectiveness of the proposed monitoring method.
引用
收藏
页码:4325 / 4335
页数:11
相关论文
共 50 条
  • [1] Modeling and Performance Monitoring of Multivariate Multimodal Processes
    Feital, Thiago
    Kruger, Uwe
    Dutra, Julio
    Pinto, Jose Carlos
    Lima, Enrique Luis
    AICHE JOURNAL, 2013, 59 (05) : 1557 - 1569
  • [2] Hidden Markov models combining local and global information for nonlinear and multimodal process monitoring
    Yu, Jianbo
    JOURNAL OF PROCESS CONTROL, 2010, 20 (03) : 344 - 359
  • [3] Process pattern construction and multi-mode monitoring
    Zhu, Zhibo
    Song, Zhihuan
    Palazoglu, Ahmet
    JOURNAL OF PROCESS CONTROL, 2012, 22 (01) : 247 - 262
  • [4] Nonstationary Discrete Convolution Kernel for Multimodal Process Monitoring
    Tan, Ruomu
    Ottewill, James R.
    Thornhill, Nina F.
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (09) : 3670 - 3681
  • [5] Process monitoring based on mode identification for multi-mode process with transitions
    Wang, Fuli
    Tan, Shuai
    Peng, Jun
    Chang, Yuqing
    CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2012, 110 (01) : 144 - 155
  • [6] Analysis of multiscale process monitoring in industrial processes from a bibliometric perspective
    Nawaz, Muhammad
    Maulud, Abdulhalim Shah
    Zabiri, Haslinda
    COMPUTERS & CHEMICAL ENGINEERING, 2022, 168
  • [7] Progress of Process Monitoring for the Multi-Mode Process: A Review
    Ma, Jie
    Zhang, Jinkai
    APPLIED SCIENCES-BASEL, 2022, 12 (14):
  • [8] Modeling and monitoring of nonlinear multi-mode processes
    Zhang, Yingwei
    Li, Shuai
    CONTROL ENGINEERING PRACTICE, 2014, 22 : 194 - 204
  • [9] Multirate Mixture Probability Principal Component Analysis for Process Monitoring in Multimode Processes
    Lyu, Yuting
    Zhou, Le
    Cong, Ya
    Zheng, Hongbo
    Song, Zhihuan
    IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2024, 21 (02) : 2027 - 2038
  • [10] A mixture of probabilistic predictable feature analysis for multi-mode dynamic process monitoring
    Fan, Wei
    Ren, Shaojun
    Yu, Cong
    Yu, Haiquan
    Wang, Peng
    Si, Fengqi
    JOURNAL OF THE TAIWAN INSTITUTE OF CHEMICAL ENGINEERS, 2023, 143