[1]曲彦光,张勤,朱群雄.动态不确定因果图在化工系统动态故障诊断中的应用[J].智能系统学报,2015,10(03):354-361.[doi:10.3969/j.issn.1673-4785.201503012]
 QU Yanguang,ZHANG Qin,ZHU Qunxiong.Application of dynamic uncertain causality graph to dynamic fault diagnosis in chemical processes[J].CAAI Transactions on Intelligent Systems,2015,10(03):354-361.[doi:10.3969/j.issn.1673-4785.201503012]
点击复制

动态不确定因果图在化工系统动态故障诊断中的应用(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第10卷
期数:
2015年03期
页码:
354-361
栏目:
出版日期:
2015-06-25

文章信息/Info

Title:
Application of dynamic uncertain causality graph to dynamic fault diagnosis in chemical processes
作者:
曲彦光1 张勤2 朱群雄1
1. 北京化工大学 信息科学与技术学院, 北京 100029;
2. 北京航空航天大学 计算机学院, 北京 100083
Author(s):
QU Yanguang1 ZHANG Qin2 ZHU Qunxiong1
1. College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China;
2. School of Computer Science and Engineering, Beihang University, Beijing 100083, China
关键词:
化工过程动态不确定因果图故障诊断TE过程概率推理
Keywords:
chemical processdynamic uncertain causality graphfault diagnosisTennessee Eastman (TE) processprobabilistic reasoning
分类号:
TP391.41
DOI:
10.3969/j.issn.1673-4785.201503012
文献标志码:
A
摘要:
为了避免化工工程中经济及生命的损失,有效及时检测出故障是十分必要的.动态不确定因果图(DUCG)是一种根据有向图实现动态不确定因果关系表达与推理的方法.其处理信息的特性,对于目前规模庞大的化工过程故障诊断有着自身的优势.因此运用DUCG,通过构建对象系统知识库、对故障数据进行概率推理,实现化工过程的故障诊断,并针对化工过程的震荡信号,对原DUCG系统的数据发送模块做出改进,使之适用范围更全面.为了验证DUCG理论的有效性,采用TE过程作为实验对象,建立包含54个变量、114条因果关系的DUCG模型.该模型对TE过程中的故障得到较高诊断排序概率,诊断正确概率达到了100%,与贝叶斯网络的平均诊断正确概率79.71%相比,说明了DUCG是一种行之有效的方法.
Abstract:
In chemical processes, it is necessary to effectively diagnose the fault on time in order to avoid losses of economy and lives. Dynamic uncertain causality graph is a method, which represents and infers the dynamic, uncertain causalities of the process system according to directed graph. Based on the characteristics of processing information, DUCG has its own advantages for fault diagnosis in chemical processes on a large scale. Therefore, this article applies DUCG to realize fault diagnosis of chemical processes by constructing the object system knowledge base and probabilistic reasoning on fault data. The data transmission module of the former DUCG system is improved to deal with the vibrational signals in the chemical process, and to widen the scope of application. The Tennessee Eastman (TE) simulator is taken as the experimental subject to test the effectiveness of DUCG methodology and software. 54 variables and 114 causalities are included in the constructed DUCG knowledge model. According to this model, all the failures simulated by TE are diagnosed in a high probability of ranking. The correct diagnosis rate is 100%. In comparison of Bayesian Network (BN), the mean correct diagnosis rate is 79.71% reportedly, showing that DUCG is an effective method.

参考文献/References:

[1] ABDULGHAFOUR M, EL-GANAL M A. A fuzzy logic system for analog fault diagnosis[C]//1996 IEEE International Symposium on Circuits and Systems. Atlanta, USA, 1996: 97-100.
[2] ICHALAL D, MARX B, RAGOT J, et al. An approach for the state estimation of Takagi-Sugeno models and application to sensor fault diagnosis[C]//Proceedings of the 48th IEEE Conference on Decision and Control, Jointly with the 28th Chinese Control Conference. Shanghai, China, 2009: 7789-7794.
[3] BACHIR S, TNANI S, TRIGEASSOU J C, et al. Diagnosis by parameter estimation of stator and rotor faults occurring in induction machines[J]. IEEE Transactions on Industrial Electronics, 2006, 53(3): 963-973.
[4] REPPA V, TZES A. Fault detection and diagnosis based on parameter set estimation[J]. IET Control Theory and Applications, 2011, 5(1): 69-83.
[5] DARWISH H A, TAALAB A M I, KAWADY T A. Development and implementation of an ANN-based fault diagnosis scheme for generator winding protection[J]. IEEE Transactions on Power Delivery, 2001, 16(2): 208-214.
[6] MOREIRA M P, SANTOS L T B, VELLASCO M M B R. Power transformers diagnosis using neural networks[C]//International Joint Conference on Neural Networks. Orlando, USA, 2007: 1929-1934.
[7] FERRACUTI F, GIANTOMASSI A, LONGHI S, et al. Multi-scale PCA based fault diagnosis on a paper mill plant[C]//2011 IEEE Conference on Emerging Technologies & Factory Automation. Toulouse, France, 2011: 1-8.
[8] ZHAO X X, YUN Y X. A fault diagnosis method combined fuzzy logic with CMAC neural network for power transformers[C]//Chinese Conference on Pattern Recognition. Nanjing, China, 2009: 1-5.
[9] LAU C K, GHOSH K, HUSSAIN M A, et al. Fault diagnosis of Tennessee Eastman process with multi-scale PCA and ANFIS[J]. Chemometrics and Intelligent Laboratory Systems, 2013, 120: 1-14.
[10] KARIMI I, SALAHSHOOR K. A new fault detection and diagnosis approach for a distillation column based on a combined PCA and ANFIS scheme[C]//2012 24th Chinese Control and Decision Conference. Taiyuan, China, 2012: 3408-3413.
[11] CHEN X Y, YAN X F. Using improved self-organizing map for fault diagnosis in chemical industry process[J]. Chemical Engineering Research and Design, 2012, 90(12): 2262-2277.
[12] DONG C L, WANG Y J, ZHANG Q, et al. The methodology of dynamic uncertain causality graph for intelligent diagnosis of vertigo[J]. Computer Methods and Programs in Biomedicine, 2014, 113(1): 162-174.
[13] ZHANG Qin, DONG Chunling, CUI Yan, et al. Dynamic uncertain causality graph for knowledge representation and probabilistic reasoning: statistics base, matrix, and application[J]. IEEE Transactions on Neural Networks and Learning Systems, 2014, 25(4): 645-663.
[14] 杨佳婧, 张勤, 朱群雄. 动态不确定因果图在化工过程故障诊断中的应用[J]. 智能系统学报, 2014, 9(2): 154-160.YANG Jiajing, ZHANG Qin, ZHU Qunxiong. Application of dynamic uncertain causality graph to fault diagnosis in chemical processes[J]. CAAI Transactions on Intelligent Systems, 2014, 9(2): 154-160.
[15] ZHANG Qin. Dynamic uncertain causality graph for knowledge representation and reasoning: discrete DAG cases[J]. Journal of Computer Science and Technology, 2012, 27(1): 1-23.
[16] VERRON S, TIPLICA T, KOBI A. Monitoring of complex processes with Bayesian networks[M]//REBAI A. Bayesian Network. Rijeka, Croatia: Sciyo, 2010: 213-228.

相似文献/References:

[1]杨佳婧,张勤,朱群雄.动态不确定因果图在化工过程故障诊断中的应用[J].智能系统学报,2014,9(02):154.[doi:10.3969/j.issn.1673-4785.201402012]
 YANG Jiajing,ZHANG Qin,ZHU Qunxiong.Application of Dynamic Uncertain Causality Graphto fault diagnosis in chemical processes[J].CAAI Transactions on Intelligent Systems,2014,9(03):154.[doi:10.3969/j.issn.1673-4785.201402012]

备注/Memo

备注/Memo:
收稿日期:2015-3-9;改回日期:。
基金项目:国家自然科学基金资助项目(61273330;61473026).
作者简介:曲彦光,男,1990年生,硕士研究生,主要研究方向为动态不确定因果图及故障诊断. 张勤,男,1956年生,教授,博士生导师,博士,主要研究方向为动态不确定因果图理论及应用、系统可靠性评价与管理、知识产权理论及应用等.任国际原子能机构《与安全有关的专家系统》中方课题负责人,国家“九五”重大软课题负责人、国家自然科学基金、国家中长期科技发展规划纲要等多项课题负责人,中国人工智能学会不确定性人工智能专业委员会主任.朱群雄,男,1960年生,教授,博士生导师,博士,主要研究方向为智能建模与优化、数据挖掘与故障诊断.主持完成国家自然科学基金、国家“863”计划、省部级科研和企业工程项目20余项,获省部级科技进步一等奖2项、二等奖1项,发明专利和国家软件著作权10余项,发表学术论文200余篇.
通讯作者:张勤. E-mail: zhangqin@buaa.edu.cn. 朱群雄. E-mail: zhuqx@mail.buct.edu.cn.
更新日期/Last Update: 2015-07-15