一种可用于机车部件故障诊断的神经网络专系统研究
|
摘要
本文针对内燃机车的并发故障和交叉故障多的特点，提出了诊断机车故障的一种神经网络专家系统模型，首先依据机车的结构和各个部分的组成设计分布式协同专家系统，将专家系统的各种知识和规则分布于各个协作的子专家系统中。在子专家系统中采用了传统的基于规则的故障诊断方式和神经网络故障诊断方式。各个协同工作的专家系统利用规则推理来解释神经网络的识别结果，神经网络用来避免烦琐的推理而直接识别故障类型。因此本系统通过在传统的专家系统中引入神经网络提高了专家系统的适应性和灵活性，并具有了一定的联想功能，可以识别带有噪声和残缺的数据。在本系统中选用ART神经网络，ART网络具有自动聚类的功能，特别适合于发现偶发性故障。
在推理过程中为了比较灵活的处理各种情况，系统使用了不精确推理、非单调推理等高级推理技术，利用可信度因子，严重程度因子来解决推理过程中可能出现冲突问题。
本论文分析了机车的结构和组成，给出了专家系统模型诊断的机理和实现，对系统的诊断过程做出说明。并指出了本系统的优缺点、适用范围以及将来的发展方向。
The paper proposes a model to support fault diagnostic expert system for large and complex diesel locomotive. The model based on the structure and the parts of diesel locomotive is a distributed and cooperated expert system. The rules and knowledge is distributed many subordinate expert system. In the subordinate expert system, there are two ratiocinating modes. The one is the mode based on rules by usual expert system another is mode using neural network to recognize the type of the faults . That is giving the system the ability to recognize the fragmentary data or the data with noise. The system used the ART neural network because study of the ART is without teachers and can learn real time, So it is suited to recognize the faults that happen by accident.
the system uses the advanced ratiocination such as uncertain ratiocinations and the default ratiocinations. By used the degree of reliability and the degree of importance to solve the confliction.
The paper analysis the structure and makeup of diesel locomotive firstly, gives the the principle and realization of the expert system and gives the concrete design and implement of subordinate expert system, it evaluates the advantages and disadvantages of the system and give the area suited for this system and look forward the development of fault diagnosis system.
在推理过程中为了比较灵活的处理各种情况，系统使用了不精确推理、非单调推理等高级推理技术，利用可信度因子，严重程度因子来解决推理过程中可能出现冲突问题。
本论文分析了机车的结构和组成，给出了专家系统模型诊断的机理和实现，对系统的诊断过程做出说明。并指出了本系统的优缺点、适用范围以及将来的发展方向。
The paper proposes a model to support fault diagnostic expert system for large and complex diesel locomotive. The model based on the structure and the parts of diesel locomotive is a distributed and cooperated expert system. The rules and knowledge is distributed many subordinate expert system. In the subordinate expert system, there are two ratiocinating modes. The one is the mode based on rules by usual expert system another is mode using neural network to recognize the type of the faults . That is giving the system the ability to recognize the fragmentary data or the data with noise. The system used the ART neural network because study of the ART is without teachers and can learn real time, So it is suited to recognize the faults that happen by accident.
the system uses the advanced ratiocination such as uncertain ratiocinations and the default ratiocinations. By used the degree of reliability and the degree of importance to solve the confliction.
The paper analysis the structure and makeup of diesel locomotive firstly, gives the the principle and realization of the expert system and gives the concrete design and implement of subordinate expert system, it evaluates the advantages and disadvantages of the system and give the area suited for this system and look forward the development of fault diagnosis system.
引文
[1]、Chan C.W, Peng Yao, Chen Lin-Li .Knowledge acquisition and ontology modelling for construction of a control and monitoring expert system . International Journal of Systems Science v 33 n 6 May 15 2002, p 485-503
[2]、Lhotska, Lenka, vlcek, Tomas . Efficiency enhancement of rule-based expert systems. Proceedings of the IEEE Symposium on Computer-Based Medical Systems Jun 4-7 2002, p 53-58
[3]、Liu Yan, Schulz, Noel N . Knowledge-based system for distribution system outage locating using comprehensive information . IEEE Transactions on Power Systems v 17 n 2 May 2002 , p 451-456
[4]、Ranjan Anubhav, Glassey Jarka, Montague Gary, Mohan Pankaj . From process experts to a real-time knowledge-based system. Expert Systems v 19 n 2 May 2002 p 69-79
[5]、Mussi Silvano . Expert Systems v 19 n 2 May 2002 p 99-108
[6]、Kontogiannis Tom, Moustakis Vassilis. An experimental evaluation of comprehensibility aspects of knowledge structures derived through induction techniques: A case study of industrial fault diagnosis . Behaviour and Information Technology v 21 n 2 March/April 2002 p 117-135
[7]、Neagu Ciprian-Daniel, Avouris Nikolaos, Kalapanidas Elias, Palade Vasile. Neural and neuro-fuzzy integration in a knowledge-based system for air quality prediction. Applied Intelligence v 17 n 2 September/october 2002. p 141-169
[8]、Adamson M S, Roberge P R. Development of a deep knowledge diagnostic expert system using fault tree analysis information . Canadian Journal of Chemical Engineering v 69 n 1 Feb 1991 p 76-80
[9]、Xu Changsheng, Liu Sixing, Zhou Zhaoying, Zhang Yao. Object-oriented synergetic expert system for fault diagnosis. Conference Record - IEEE Instrumentation and Measurement Technology Conference 1 May 10-12 1994 p 398-401
[10]、Yuan Qing, Li Weiping . Fault diagnosis expert system by CLIPS . Proceedings of the International Symposium on Test and Measurement Jun 2-Jun 4 1999 p 376-380
[11]、Naruo Nobuyuki, Lehto Mark ,Salvendy Gavriel . Development of a
knowledge-based decision support system for diagnosing malfunctions of advanced production equipment. International Journal of Production Research v 28 n 12 Dec 1990 p 2259-2276
[12]、Elliott W Jr, Schneider M. The learning aspects of the FAULT FINDER expert system . : Proceedings of The International Symposium on Multiple-Valued Logic May 23-25 1990 p 378-385
[13]、Khaparde S A, Jadid S . Expert system for fault diagnosis and restoration of Iran's 400 KV network. International Journal of Engineering Intelligent Systems for Electrical Engineering and Communications v 5 n 2 Jun 1997 p 107-114
[14]、Chen Jiann-Liang, Chen Chern-Lin. Connectionist expert system for fault diagnosis :Electric Power Systems Research v 24 n 2 Aug 1992 p 99-103
[15]、西南交大内燃机车教研组 内燃机车基本知识。人民铁道出版社 1980 8-12
[16]、吴今培．模糊诊断理论及其应用．北京：科学出版社，1995 163-176
[17]、王克宏等．知识工程与知识处理系统．北京：清华大学出版社，1994 2 211-251
[18]、吴泉源．人工智能与专家系统．北京：清华大学出版社，1995 3 45-56
[19]、吴今培，肖健华．智能故障诊断与专家系统．北京：科学出版社，1997 231-241
[20]、王道平，张义忠，故障智能诊断系统的理论与方法．冶金工业出版社，2001 143-162
[21]、周祖德，陈幼平，现代机械制造系统的监控与故障诊断．华中理工大学出版社 1999 24-35
[22]、覃组旭．智能、信息及其在导航系统中应用．北京：北京航空航天大学，1995 47-56
[23]、关惠玲，韩捷．设备故障诊断专家系统原理及实践．机械工业出版社，2000 87-90
[24]、周东华，叶银忠．现代故障诊断与容错控制．清华大学出版社，2000 34-46
[25]、施鸿宝，王秋荷．专家系统．西安交通大学出版社，1991 208-231
[26]、虞和济，陈长征等．基于神经网络的智能诊断．冶金工业出版社，2000 243-255
[27]、刘润华，蒋新华．用于内燃机车运行工况的状态监测系统．长沙铁道学院学报 2001年9月第19卷第3期 43-54
[28]、钱大群，孙振飞．神经网络的知识获取与行为解释．自动化学报，1994(3)
73-79
[29]、陆汝钤，石纯一，张松懋．面向Agent的常识知识库．中国科学(E辑)第30卷 第5期 85-89
[30]、钟佩思，徐文胜，范文慧．层次化领域知识库的有效性检查研究．机械设计 2000．2 56-62
[31]、王钰，戴汝为．建造带有人工神经元网络知识系统的一种方法．计算机学报，1990(5)2 34-42
[32]、张瑾，李人厚．实时控制神经网络专家结构及推理算法．模式识别及人工智能，1995(2)3 63-72
[33]、曾树青，晏建军，何永保．利用神经网络从例子中提取规则．模式识别及人工智能，1995(1)4 87-94
[34]、张定会，邵惠鹤．实时故障诊断系统知识库的建造．计算机工程与应用，1996，(6)72-86
[35]、潘惠勇，张建培，葛芦生．基于现场总线分布式轧制力信号采集及故障监测系统．华东冶金学院学报，2000，4 59-65
[36]、霍志红，基于神经网络的故障诊断研究．工业控制计算机，2001，10 67-80
[37]、曹存根．知识云及其在知识获取中的意义．软件学报，1995，6(3) 61-70
[38]、吴伟蔚，杨叔子，吴今培．故障Agent的研究．振动工程学报，第13卷第3期 72-80
[39]、吴今培，吴伟蔚，一种分布式专家系统开发策略．长沙铁道学院学报，第20卷第1期 20-31
[40]、李斌，雷渊超，吴今培．一个模糊神经网络诊断专家系统及其实现．北京轻工业学院学报，第15卷第1期 89-103
[41]、马绍汉，陶雪红．一类树型知识库的更新算法．软件学报，第10卷第11期 134-142
[42]、和利，王厚军．基于知识的故障诊断系统的设计．计算机测量与控制，2002，10(5) 89-95
[43]、吴长华，章少华．基于主动式知识库的专家系统建模和推理研究，杭州电子工业学院学报 第21卷第1期 68-72
[44]、陈兆乾，李红兵，陈世福．一个面向对象的推理机OOIE的设计与实现．计算机研究与发展，1997，34(3) 23-31
[45]、吴今培．基于可能性理论的设备故障诊断．模糊系统与数学，第十三卷第二期 45-51
[2]、Lhotska, Lenka, vlcek, Tomas . Efficiency enhancement of rule-based expert systems. Proceedings of the IEEE Symposium on Computer-Based Medical Systems Jun 4-7 2002, p 53-58
[3]、Liu Yan, Schulz, Noel N . Knowledge-based system for distribution system outage locating using comprehensive information . IEEE Transactions on Power Systems v 17 n 2 May 2002 , p 451-456
[4]、Ranjan Anubhav, Glassey Jarka, Montague Gary, Mohan Pankaj . From process experts to a real-time knowledge-based system. Expert Systems v 19 n 2 May 2002 p 69-79
[5]、Mussi Silvano . Expert Systems v 19 n 2 May 2002 p 99-108
[6]、Kontogiannis Tom, Moustakis Vassilis. An experimental evaluation of comprehensibility aspects of knowledge structures derived through induction techniques: A case study of industrial fault diagnosis . Behaviour and Information Technology v 21 n 2 March/April 2002 p 117-135
[7]、Neagu Ciprian-Daniel, Avouris Nikolaos, Kalapanidas Elias, Palade Vasile. Neural and neuro-fuzzy integration in a knowledge-based system for air quality prediction. Applied Intelligence v 17 n 2 September/october 2002. p 141-169
[8]、Adamson M S, Roberge P R. Development of a deep knowledge diagnostic expert system using fault tree analysis information . Canadian Journal of Chemical Engineering v 69 n 1 Feb 1991 p 76-80
[9]、Xu Changsheng, Liu Sixing, Zhou Zhaoying, Zhang Yao. Object-oriented synergetic expert system for fault diagnosis. Conference Record - IEEE Instrumentation and Measurement Technology Conference 1 May 10-12 1994 p 398-401
[10]、Yuan Qing, Li Weiping . Fault diagnosis expert system by CLIPS . Proceedings of the International Symposium on Test and Measurement Jun 2-Jun 4 1999 p 376-380
[11]、Naruo Nobuyuki, Lehto Mark ,Salvendy Gavriel . Development of a
knowledge-based decision support system for diagnosing malfunctions of advanced production equipment. International Journal of Production Research v 28 n 12 Dec 1990 p 2259-2276
[12]、Elliott W Jr, Schneider M. The learning aspects of the FAULT FINDER expert system . : Proceedings of The International Symposium on Multiple-Valued Logic May 23-25 1990 p 378-385
[13]、Khaparde S A, Jadid S . Expert system for fault diagnosis and restoration of Iran's 400 KV network. International Journal of Engineering Intelligent Systems for Electrical Engineering and Communications v 5 n 2 Jun 1997 p 107-114
[14]、Chen Jiann-Liang, Chen Chern-Lin. Connectionist expert system for fault diagnosis :Electric Power Systems Research v 24 n 2 Aug 1992 p 99-103
[15]、西南交大内燃机车教研组 内燃机车基本知识。人民铁道出版社 1980 8-12
[16]、吴今培．模糊诊断理论及其应用．北京：科学出版社，1995 163-176
[17]、王克宏等．知识工程与知识处理系统．北京：清华大学出版社，1994 2 211-251
[18]、吴泉源．人工智能与专家系统．北京：清华大学出版社，1995 3 45-56
[19]、吴今培，肖健华．智能故障诊断与专家系统．北京：科学出版社，1997 231-241
[20]、王道平，张义忠，故障智能诊断系统的理论与方法．冶金工业出版社，2001 143-162
[21]、周祖德，陈幼平，现代机械制造系统的监控与故障诊断．华中理工大学出版社 1999 24-35
[22]、覃组旭．智能、信息及其在导航系统中应用．北京：北京航空航天大学，1995 47-56
[23]、关惠玲，韩捷．设备故障诊断专家系统原理及实践．机械工业出版社，2000 87-90
[24]、周东华，叶银忠．现代故障诊断与容错控制．清华大学出版社，2000 34-46
[25]、施鸿宝，王秋荷．专家系统．西安交通大学出版社，1991 208-231
[26]、虞和济，陈长征等．基于神经网络的智能诊断．冶金工业出版社，2000 243-255
[27]、刘润华，蒋新华．用于内燃机车运行工况的状态监测系统．长沙铁道学院学报 2001年9月第19卷第3期 43-54
[28]、钱大群，孙振飞．神经网络的知识获取与行为解释．自动化学报，1994(3)
73-79
[29]、陆汝钤，石纯一，张松懋．面向Agent的常识知识库．中国科学(E辑)第30卷 第5期 85-89
[30]、钟佩思，徐文胜，范文慧．层次化领域知识库的有效性检查研究．机械设计 2000．2 56-62
[31]、王钰，戴汝为．建造带有人工神经元网络知识系统的一种方法．计算机学报，1990(5)2 34-42
[32]、张瑾，李人厚．实时控制神经网络专家结构及推理算法．模式识别及人工智能，1995(2)3 63-72
[33]、曾树青，晏建军，何永保．利用神经网络从例子中提取规则．模式识别及人工智能，1995(1)4 87-94
[34]、张定会，邵惠鹤．实时故障诊断系统知识库的建造．计算机工程与应用，1996，(6)72-86
[35]、潘惠勇，张建培，葛芦生．基于现场总线分布式轧制力信号采集及故障监测系统．华东冶金学院学报，2000，4 59-65
[36]、霍志红，基于神经网络的故障诊断研究．工业控制计算机，2001，10 67-80
[37]、曹存根．知识云及其在知识获取中的意义．软件学报，1995，6(3) 61-70
[38]、吴伟蔚，杨叔子，吴今培．故障Agent的研究．振动工程学报，第13卷第3期 72-80
[39]、吴今培，吴伟蔚，一种分布式专家系统开发策略．长沙铁道学院学报，第20卷第1期 20-31
[40]、李斌，雷渊超，吴今培．一个模糊神经网络诊断专家系统及其实现．北京轻工业学院学报，第15卷第1期 89-103
[41]、马绍汉，陶雪红．一类树型知识库的更新算法．软件学报，第10卷第11期 134-142
[42]、和利，王厚军．基于知识的故障诊断系统的设计．计算机测量与控制，2002，10(5) 89-95
[43]、吴长华，章少华．基于主动式知识库的专家系统建模和推理研究，杭州电子工业学院学报 第21卷第1期 68-72
[44]、陈兆乾，李红兵，陈世福．一个面向对象的推理机OOIE的设计与实现．计算机研究与发展，1997，34(3) 23-31
[45]、吴今培．基于可能性理论的设备故障诊断．模糊系统与数学，第十三卷第二期 45-51