Fault detection and isolation of an on-line analyzer for an ethylene cracking process

被引：30
作者：
Kampjarvi, Petteri
Sourander, Mauri
Komulainen, Tiina
Vatanski, Nikolai
Nikus, Mats
Jamsa-Jounela, Sirkka-Liisa
机构：
[1] Aalto Univ, Lab Proc Control & Automat, FIN-02150 Espoo, Finland
[2] Porvoo Refinery, Neste Oil Oy, FIN-06101 Porvoo, Finland
[3] Proc & Automat Technol, Neste Jacobs Oy, FIN-06101 Porvoo, Finland
来源：
CONTROL ENGINEERING PRACTICE | 2008年 / 16卷 / 01期
关键词：
ethylene cracking; process monitoring; fault detection; fault isolation; principal component analysis; self-organizing map;
D O I：
10.1016/j.conengprac.2007.03.007
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Fault diagnosis methods based on process history data have been studied widely in recent years, and several successful industrial applications have been reported. Improved data validation has resulted in more stable processes and better quality of the products. In this paper, an on-line fault detection and isolation system consisting of a combination of principal component analysis (PCA) Lind two neural networks (NNs), radial basis function network (RBFN) and self-organizing map (SOM), is presented. The system detects Lind isolates faulty operation of the analyzers in an ethylene cracking furnace. The test results with real-time process data are presented and discussed. (c) 2007 Elsevier Ltd. All rights reserved.
引用
收藏
页码：1 / 13
页数：13
相关论文
共 28 条
[21]   Sensor validation and process fault diagnosis for FCC units under MPC feedback [J].
Pranatyasto, TN ;
Qin, SJ .
CONTROL ENGINEERING PRACTICE, 2001, 9 (08) :877-888
[22]  
Qin SJ, 1998, COMPUT CHEM ENG, V22, P503, DOI 10.1016/S0098-1354(97)00262-7
[23]   Neural virtual sensor for the inferential prediction of product quality from process variables [J].
Rallo, R ;
Ferre-Giné, J ;
Arenas, A ;
Giralt, F .
COMPUTERS & CHEMICAL ENGINEERING, 2002, 26 (12) :1735-1754
[24]   A review of process fault detection and diagnosis Part III: Process history based methods [J].
Venkatasubramanian, V ;
Rengaswamy, R ;
Kavuri, SN ;
Yin, K .
COMPUTERS & CHEMICAL ENGINEERING, 2003, 27 (03) :327-346
[25]   A review of process fault detection and diagnosis Part I: Quantitative model-based methods [J].
Venkatsubramanian, V ;
Rengaswamy, R ;
Yin, K ;
Kavuri, SN .
COMPUTERS & CHEMICAL ENGINEERING, 2003, 27 (03) :293-311
[26]   Adaptive resonance theory based neural network for supervised chemical pattern recognition (FuzzyARTMAP) .2. Classification of post-consumer plastics by remote NIR spectroscopy using an InGaAs diode array [J].
Wienke, D ;
vandenBroek, W ;
Buydens, L ;
HuthFehre, T ;
Feldhoff, R ;
Kantimm, T ;
Cammann, K .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 1996, 32 (02) :165-176
[27]  
YOON S, 2001, P 4 IFAC WORKSH ONL, P384
[28]   Multidimensional non-orthogonal wavelet-sigmoid basis function neural network for dynamic process fault diagnosis [J].
Zhao, JS ;
Chen, BZ ;
Shen, JZ .
COMPUTERS & CHEMICAL ENGINEERING, 1998, 23 (01) :83-92
123