Process Monitoring for Multimodal Processes With Mode-Reachability Constraints

被引:35
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 36 条
[1]   Process Monitoring Using Hidden Markov Models [J].
Alshraideh, Hussam ;
Runger, George .
QUALITY AND RELIABILITY ENGINEERING INTERNATIONAL, 2014, 30 (08) :1379-1387
[2]  
Atlas L, 2000, INT CONF ACOUST SPEE, P3887, DOI 10.1109/ICASSP.2000.860252
[3]   STATISTICAL INFERENCE FOR PROBABILISTIC FUNCTIONS OF FINITE STATE MARKOV CHAINS [J].
BAUM, LE ;
PETRIE, T .
ANNALS OF MATHEMATICAL STATISTICS, 1966, 37 (06) :1554-&
[4]  
Chao Ning, 2015, IFAC - Papers Online, V48, P619, DOI 10.1016/j.ifacol.2015.09.595
[5]   Model-based fault-detection and diagnosis - status and applications [J].
Isermann, R .
ANNUAL REVIEWS IN CONTROL, 2005, 29 (01) :71-85
[6]  
Jackson J. E, 2005, USERS GUIDE PRINCIPA, V587
[7]   Fault diagnosis using contribution plots without smearing effect on non-faulty variables [J].
Liu, Jialin .
JOURNAL OF PROCESS CONTROL, 2012, 22 (09) :1609-1623
[8]  
Livingston J., 2015, NUCL ELECT ENG ED RE
[9]   STATISTICAL PROCESS-CONTROL OF MULTIVARIATE PROCESSES [J].
MACGREGOR, JF ;
KOURTI, T .
CONTROL ENGINEERING PRACTICE, 1995, 3 (03) :403-414
[10]   Non-parametric confidence bounds for process performance monitoring charts [J].
Martin, EB ;
Morris, AJ .
JOURNAL OF PROCESS CONTROL, 1996, 6 (06) :349-358