Cognitive fault diagnosis in Tennessee Eastman Process using learning in the model space

被引:57
作者
Chen, Huanhuan [1 ]
Tino, Peter [2 ]
Yao, Xin [2 ]
机构
[1] Univ Sci & Technol China, Sch Comp Sci & Technol, UBRI, Hefei 230027, Peoples R China
[2] Univ Birmingham, Sch Comp Sci, CERCIA, Birmingham B15 2TT, W Midlands, England
基金
英国工程与自然科学研究理事会; 中国国家自然科学基金; 英国生物技术与生命科学研究理事会;
关键词
Learning in the model space; Tennessee Eastman Process; Fault detection; Cognitive fault diagnosis; Reservoir computing; One class learning; PRINCIPAL COMPONENT ANALYSIS; SUPPORT VECTOR MACHINES; SYSTEMS; DISTURBANCES; RECOGNITION; SENSOR;
D O I
10.1016/j.compchemeng.2014.03.015
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
This paper focuses on the Tennessee Eastman (TE) process and for the first time investigates it in a cognitive way. The cognitive fault diagnosis does not assume prior knowledge of the fault numbers and signatures. This approach firstly employs deterministic reservoir models to fit the multiple-input and multiple-output signals in the TE process, which map the signal space to the (reservoir) model space. Then we investigate incremental learning algorithms in this reservoir model space based on the "function distance" between these models. The main contribution of this paper is to provide a cognitive solution to this popular benchmark problem. Our approach is not only applicable to fault detection, but also to fault isolation without knowing the prior information about the fault signature. Experimental comparisons with other state-of-the-art approaches confirmed the benefits of our approach. Our algorithm is efficient and can run in real-time for practical applications. (C) 2014 Elsevier Ltd. All rights reserved.
引用
收藏
页码:33 / 42
页数:10
相关论文
共 40 条
[1]  
[Anonymous], 2001, ECHO STATE APPROACH
[2]   Self adaptive growing neural network classifier for faults detection and diagnosis [J].
Barakat, M. ;
Druaux, F. ;
Lefebvre, D. ;
Khalil, M. ;
Mustapha, O. .
NEUROCOMPUTING, 2011, 74 (18) :3865-3876
[3]  
Bishnoi P., 2001, COMPUT CHEM ENG, V25, P1313
[4]   Predictive on-line monitoring of continuous processes [J].
Chen, G ;
McAvoy, TJ .
JOURNAL OF PROCESS CONTROL, 1998, 8 (5-6) :409-420
[5]   Learning in the Model Space for Cognitive Fault Diagnosis [J].
Chen, Huanhuan ;
Tino, Peter ;
Rodan, Ali ;
Yao, Xin .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2014, 25 (01) :124-136
[6]   Towards distributed diagnosis of the Tennessee Eastman process benchmark [J].
Chen, J ;
Howell, J .
CONTROL ENGINEERING PRACTICE, 2002, 10 (09) :971-987
[7]  
Chen J, 2012, ROBUST MODEL BASED F
[8]  
Chen X., 2011, P 25 AAAI C ART INT, P313, DOI DOI 10.1109/CVPR.2016.425
[9]   Fault diagnosis based on Fisher discriminant analysis and support vector machines [J].
Chiang, LH ;
Kotanchek, ME ;
Kordon, AK .
COMPUTERS & CHEMICAL ENGINEERING, 2004, 28 (08) :1389-1401
[10]   Fault identification for process monitoring using kernel principal component analysis [J].
Cho, JH ;
Lee, JM ;
Choi, SW ;
Lee, D ;
Lee, IB .
CHEMICAL ENGINEERING SCIENCE, 2005, 60 (01) :279-288