基于模糊Petri网的故障诊断系统的研究
|
摘要
随着科技的飞速发展，现代生产和生活中用到的设备越来越先进。设备能否有效的运行，关系着经济效益甚至人们的生命安全。因此，有必要对故障诊断技术进行研究。由于故障诊断知识本身具有不确定性、不精确性，如何表示故障知识以及对其进行推理，是故障诊断系统需要解决的关键问题。
Petri网作为一种图形化建模工具，可以很直观地表示系统并发、动态行为,将Petri网引入故障诊断领域，具有重要的理论价值和现实意义。模糊Petri网作为Petri网应用的一个重要拓展，不但具有Petri网的图形描述能力，而且继承了模糊系统强大的模糊推理能力。非常适合用模糊Petri网来表示故障诊断中的不确定的模糊信息，进行推理。
本文将模糊Petri网与故障诊断技术相结合，对以下内容作了重点研究：
1.简要地介绍了故障诊断技术，讨论了主要的故障诊断方法。介绍了Petri网与模糊Petri网的基本原理。
2.分析了基于传统Petri网的故障诊断技术的不足，提出一种适合故障诊断特点的基于模糊Petri网的诊断方法。提出的初始库所模糊token值的确定方法，能够量化不精确的，非定量的信息，有效地解决推理过程中关于传播路径的选择问题。根据诊断知识表示和推理的特点，建立的变迁点火机制与故障诊断反向推理算法，能够实现有效地推理，找出故障传播路径。
3.以电梯故障诊断为实例，来验证所提出的故障诊断算法的有效性与可行性。
With the rapid development of science and technology,the equipment used inindustry or life is more and more advanced. It is important that the key equipmentcan operate in good state so as to improve the industrial economic benefits,even thesafe of people’s life. Therefore,it is necessary to research fault diagnosis methods.The diagnosis knowledge has some features such as uncertainty and inaccurate.Howto express and reasoning the diagnosis knowledge is a key problem which needed tobe solved in the fault diagnosis system.
Petri net, as a graphical modeling tool, which can represent concurrence,asynchrony in intuitive way.It has very important theoretical value and paracticalsignificance to use Petri net into fault diagnosis.Fuzzy Petri nets, as a very importantdevelopment of Petri net,not only have the describe ability,but also inherite the greatfuzzy reasoning ability.It is very suitable to use fuzzy Petri nets for expressing andreasoning fuzzy information.
Based on the character of fault diagnosis,the Petri net is applied to the field offault diagnosis. Research work in the thesis focus on:
1.Introduce the fault diagnosis system,the knowledge of Petri net and fuzzyPetri net.
2.A method based on the fuzzy Petri net is put forward by analyzing theapplication limits of traditional Petri net in the fault diagnosis fields.An effectiveway is devised for computing fuzzy tokens ,which has the ability to express fuzzyinformation. We can use this method to solve the problem of fault propagationchosen.At last,a transition fired algorithm and a backward-reasoning algorithm is putforward ,which can applied for knowledge reasoning and find out fault propagationroutes.
3.Use the example of elevator fault diagnosis to confirm the feasibility andvalidity of this method.
Petri网作为一种图形化建模工具，可以很直观地表示系统并发、动态行为,将Petri网引入故障诊断领域，具有重要的理论价值和现实意义。模糊Petri网作为Petri网应用的一个重要拓展，不但具有Petri网的图形描述能力，而且继承了模糊系统强大的模糊推理能力。非常适合用模糊Petri网来表示故障诊断中的不确定的模糊信息，进行推理。
本文将模糊Petri网与故障诊断技术相结合，对以下内容作了重点研究：
1.简要地介绍了故障诊断技术，讨论了主要的故障诊断方法。介绍了Petri网与模糊Petri网的基本原理。
2.分析了基于传统Petri网的故障诊断技术的不足，提出一种适合故障诊断特点的基于模糊Petri网的诊断方法。提出的初始库所模糊token值的确定方法，能够量化不精确的，非定量的信息，有效地解决推理过程中关于传播路径的选择问题。根据诊断知识表示和推理的特点，建立的变迁点火机制与故障诊断反向推理算法，能够实现有效地推理，找出故障传播路径。
3.以电梯故障诊断为实例，来验证所提出的故障诊断算法的有效性与可行性。
With the rapid development of science and technology,the equipment used inindustry or life is more and more advanced. It is important that the key equipmentcan operate in good state so as to improve the industrial economic benefits,even thesafe of people’s life. Therefore,it is necessary to research fault diagnosis methods.The diagnosis knowledge has some features such as uncertainty and inaccurate.Howto express and reasoning the diagnosis knowledge is a key problem which needed tobe solved in the fault diagnosis system.
Petri net, as a graphical modeling tool, which can represent concurrence,asynchrony in intuitive way.It has very important theoretical value and paracticalsignificance to use Petri net into fault diagnosis.Fuzzy Petri nets, as a very importantdevelopment of Petri net,not only have the describe ability,but also inherite the greatfuzzy reasoning ability.It is very suitable to use fuzzy Petri nets for expressing andreasoning fuzzy information.
Based on the character of fault diagnosis,the Petri net is applied to the field offault diagnosis. Research work in the thesis focus on:
1.Introduce the fault diagnosis system,the knowledge of Petri net and fuzzyPetri net.
2.A method based on the fuzzy Petri net is put forward by analyzing theapplication limits of traditional Petri net in the fault diagnosis fields.An effectiveway is devised for computing fuzzy tokens ,which has the ability to express fuzzyinformation. We can use this method to solve the problem of fault propagationchosen.At last,a transition fired algorithm and a backward-reasoning algorithm is putforward ,which can applied for knowledge reasoning and find out fault propagationroutes.
3.Use the example of elevator fault diagnosis to confirm the feasibility andvalidity of this method.
引文
[1]侯俊剑.基于声像模式识别的故障诊断机理研究：[上海交通大学博士学位论文].上海:上海交通大学,2011
[2]高立新,张建宇,崔玲丽.基于小波分析的低速重载设备故障诊断.机械工程学报,2005,41(12):222-227
[3] Lada,E.K,J.e.Lu and J.R.Wilson.A wavelet-based proeedure for proeess faultdeteetion.IEEE Transaetions on Semieonduetor Manufaeturing, 2002,15(l):79-90
[4] Lin,J.. Feature extraetion of maehine sound using wavelet and its applieation infault diagnosis.Ndt&E International,2001,34(l):25-30
[5]李军,俞建定,徐铁峰.基于小波变换的故障诊断信号非平稳性分析.系统工程与电子技术,2006,28(7):1109-1111
[6] DavisR..Dia,gnostic reasoning based on structure and behavior troubleshootingdigita electronic cireuits. Artifieial Intelligenee, 1984, 24(3):347-410
[7] Reiter,RA theory of diagnosis from first Prineiples.Artifieial Intelligenee, 1987,32(l):57-95
[8]张育林,李东旭.动态系统故障诊断理论与应用.长沙:国防科技大学出版社.1997
[9]曹志强,刘俊兴,李争乐等.构建测站专家故障诊断系统.飞行器测控学报,2004，23(2): 19-23
[10]杨叔子，丁洪，史铁林，郑小军.基于知识的诊断推理.北京:清华大学出版社，1993
[11]薛伟.汽车综合性能检测线实时故障诊断专家系统：[山东大学硕士学位论文].山东:山东大学,2007:1-35
[12]王荣杰,胡清.基于知识的故障诊断方法的发展现状与展望.微计算机信息,2006,22(3):220
[13]吴军强,梁军.基于图论的故障诊断技术及其发展.机电工程. 2003, 20(5)：188-190
[14]丁彩红，黄文虎，姜兴谓．Petri网用于故障诊断．计算机工程设计，2000,21(1)：22-24
[15]陆宝春，夏敬华，张世琪．基于Petri网的设备故障诊断研究．南京理工大学学报，1999，23(6)：522-526
[16]伍燕芳，尉忠信．用于故障诊断的模糊Petri网．航空学报，1995，6(5)：564-568
[17]庆胜，邬学礼．模糊Petri网在FMS故障诊断中的应用研究．计算机研究与发展，1994，35(4)：358-361
[18] Viswanadham N,Johnson T .L.Fault detection and diagnosis of automatedmanufacturing systems．Decision and Control，Proceedings of the 27thIEEEConference，1988(3)：2301-2306
[19] A.Szucs,M.Gerzson,K.M.Hangos.An intelligent diagnostic System based onPetri nets.Computer chem.Engng,1998,22(9):1335-1344
[20] Ouali M.-S，Ait-Kadi D，Rezg N．Fault Diagnosis Model Based on Petri NetWithFuzzy Colors，Computers & Industrial Engineering，1999(37)：173-176
[21]张才炎.基于Petri网的机车故障诊断方法研究：[中南硕士学位论文].湖南：中南大学，2010：1-59
[22]张白一,崔尚森.基于模糊Petri网的汽车故障诊断方法.长安大学学报,2008(2):93-96
[23]向永生,刘武，乐晓波，秦娜.基于模糊Petri网的汽车故障诊断仿真研究.计算机工程与科学,2009,31(3):86-88
[24]孙静,秦世引,宋永华.模糊Petri网在电力系统故障诊断中的应用.中国电机工程学报,2004,24(9):74-79
[25]曾庆锋.基于自适应模糊Petri网和有色Petri网的电网故障诊断方法研究：[西南交通大学硕士学位论文].成都：西南交通大学,2010,1-33
[26]梁远华,苑秉成.基于TS算法的FPN鱼雷电子系统故障诊断方法.仪器仪表学报,2009,30(11):2316-2320
[27]戎梅,赵廷弟，郭江杰.模糊Petri网在航天发射系统故障诊断中的应用研究.航天控制,2009,27(4):82-87
[28]宗群,王波，牙淑红.模糊Petri网在电梯故障诊断中的应用.起重运输机械,2004,(4):44-48.
[29]刘铮.基于Petri网的电梯控制系统故障诊断研究：[浙江工业大学硕士论文].杭州：浙江工业大学，2004：1-78
[30]刘敬，刘文静.基于FPN—RSVM的电梯故障诊断方法.微处理机.2008,(3):142-145
[31]黄文虎，夏松波，刘瑞岩等.设备故障诊断原理技术及应用.北京：科学出版社，1996：1-30
[32]袁崇义.Petri网原理.北京:电子工业出版社，2005
[33] Chen Shyiming,Ke Jyhsheng,Chang Jinfu.Knowledge Representation UsingFuzzy Petri Nets.IEEE Transactions on Knowldege and Data Engineering,1990,2(3):311-319
[34] Looney C G. Fuzzy Petri nets forrule based decision making. IEEE Trans. Syst. ,Man, Cybern. , 1988, 18(1)：178-183
[35] Scarpelli H , Gomide F , Yager R. A Reasoning Algorithm for High Level FuzzyPetri Nets. IEEE Transactions on Fuzzy Systems , August 1996 ,4(3) :282-294
[36]贾立新.采用模糊Petri网的形式化推理算法及其应用.西安交大学报.2003.37(12):1263-1266
[37]高梅梅.吴智铭.模糊推理Petri网及其在故障诊断中的应用.自动化学报.2002.26(5):677-680
[38]鲍培明.模糊Petri网模型的反向推理算法.南京师范大学学报,2003,3(3)：21-24
[39] Takeshi Furuhashi,Hidehiro Yamamoto.Fuzzy Control Stability Analysis Using aGeneralized Fuzzy Petri Net Model.Journal of Advanced ComputationalIntelligence and Intelligent Informatics, 1999, 3(2):99-105
[40]胡志刚,马好,廖麟.基于模糊神经Petri网的故障诊断模型.小型微型计算机系统,2005,26(11):1978-1982
[41]陈亚华，吴时霖.基于模糊有色Petri网的不确定性学习和推理方法.系统仿真学报,2003,8(15):56-58
[42]张鹏程,李人厚等.模糊着色Petri网及其在工作流建模中的应用.计算机辅助设计与图形学学报,2002,14(8):713-716
[43] Li Xiaoou, Yu Wen, Lara-Rosano F. Dynamic Knowledge Inference and Learningunder Adaptive Fuzzy Petri Net Framework. IEEE Transaction on Systems,Man, and Cybernetic Part C: Applications and Reviews,2000,30(4):442-450
[44] Li Xiaoou, Lara-Rosano F. Adaptive Fuzzy Petri Net for Dynamic KnowledgeRepresentation and Inference. E-xpert System with Applications,2000,19(3):235-241
[45] Chen Shyiming. Weighted Fuzzy Reasoning using Weight-ed Fuzzy Petri Nets.IEEE Transactions on Knowledge and Data Engineering. 2002, 14(2): 386-397
[46] Gao Meimei, Wu Zhiming, Zhou Mengc-hu. A Petri Net-based Formal ReasoningAlgorithm for Fuzzy Production Rule-based System. IEEE InternationalConference on System, Man, and Cybernetics, 2000, 4(5):314-324
[47] Yao Y.A Petri net model for temporal representations and reasoning. IEEETrans.on Systems.Man and Cybernetics.1994,24(9):1374-1382
[48] Cardoso J.etal.Petri net based reasoning for the diagnosis of dynamic discreteevent systems.In:6:th Intl.Fuzzy Systems Association World Congress.IFSA’95,Sao Paulo,Brazil,July,1995,4(1):333-336
[49] Koriem S M. A Fuzzy Petri NetTool forModeling and Verification ofKnowledge-Based Systems. The Computer Journal,2000,43(3): 206-223
[50] Fay A. A Fuzzy Knowledge-Based System for Railway Traffic Control.Engineering Applications of Artificial Intelligence,2000, 13(5):719-729
[51] Shyue-Liang Wang, Yi-huey Wu. Reasoning in Fuzzy Production Systems WhenInput Information is Incomplete. In:1999 IEEE International Fuzzy SystemsConference Proceedings. Seoul, Korea: 1999,8(22):1557-1561
[52]丁富玲，李承家.模糊Petri网的发展.杭州电子科技大学学报，2008,28(6):147-150
[53] GAO M,ZHOU M C,HUANG X,et al.Fuzzy reasoning Petri nets[J].IEEETransactions on Systems,Man and Cybernetics,Part A, 2003, 33(3): 314 - 324
[54] TANG Y,ZHOU M,GAO M.Fuzzy-Petri-net-based disassembly planningconsidering human factors.IEEE Transactions on System,Man and Cybernetics,Part A,2006,36(4):718-726
[55]陈玉宝，夏继强，邬学礼．Petri网模型在故障诊断领域的应用研究．中国机械工程，2004,11(12):1386-1388
[56]姜浩，罗军舟，方宁生．模糊Petri网在带权不精确知识表示和推理中的应用研究．计算机研究与发展，2000,37(8):918-923
[57] D S Yeung,ECC Tsang,A Multilevel Weighted Fuzzy Reasoning Algotithm forExpert Systems.IEEE Transactions on System,Man and Cybernetics, 1998, 28(2):149-158
[58]付阶辉.基于Petri网的故障诊断方法研究：[东南大学硕士学位论文].南京:东南大学，2004:1-57
[59]姜超.基于粗糙集的电梯故障诊断系统研究：[西安工业大学硕士学位论文].西安:西安工业大学，2011:5-36
[60]熊瑞庭.基于模糊神经网络的电梯故障诊断系统的研究：[武汉理工大学硕士学位论文].武汉:武汉理工大学，2009:1-55
[2]高立新,张建宇,崔玲丽.基于小波分析的低速重载设备故障诊断.机械工程学报,2005,41(12):222-227
[3] Lada,E.K,J.e.Lu and J.R.Wilson.A wavelet-based proeedure for proeess faultdeteetion.IEEE Transaetions on Semieonduetor Manufaeturing, 2002,15(l):79-90
[4] Lin,J.. Feature extraetion of maehine sound using wavelet and its applieation infault diagnosis.Ndt&E International,2001,34(l):25-30
[5]李军,俞建定,徐铁峰.基于小波变换的故障诊断信号非平稳性分析.系统工程与电子技术,2006,28(7):1109-1111
[6] DavisR..Dia,gnostic reasoning based on structure and behavior troubleshootingdigita electronic cireuits. Artifieial Intelligenee, 1984, 24(3):347-410
[7] Reiter,RA theory of diagnosis from first Prineiples.Artifieial Intelligenee, 1987,32(l):57-95
[8]张育林,李东旭.动态系统故障诊断理论与应用.长沙:国防科技大学出版社.1997
[9]曹志强,刘俊兴,李争乐等.构建测站专家故障诊断系统.飞行器测控学报,2004，23(2): 19-23
[10]杨叔子，丁洪，史铁林，郑小军.基于知识的诊断推理.北京:清华大学出版社，1993
[11]薛伟.汽车综合性能检测线实时故障诊断专家系统：[山东大学硕士学位论文].山东:山东大学,2007:1-35
[12]王荣杰,胡清.基于知识的故障诊断方法的发展现状与展望.微计算机信息,2006,22(3):220
[13]吴军强,梁军.基于图论的故障诊断技术及其发展.机电工程. 2003, 20(5)：188-190
[14]丁彩红，黄文虎，姜兴谓．Petri网用于故障诊断．计算机工程设计，2000,21(1)：22-24
[15]陆宝春，夏敬华，张世琪．基于Petri网的设备故障诊断研究．南京理工大学学报，1999，23(6)：522-526
[16]伍燕芳，尉忠信．用于故障诊断的模糊Petri网．航空学报，1995，6(5)：564-568
[17]庆胜，邬学礼．模糊Petri网在FMS故障诊断中的应用研究．计算机研究与发展，1994，35(4)：358-361
[18] Viswanadham N,Johnson T .L.Fault detection and diagnosis of automatedmanufacturing systems．Decision and Control，Proceedings of the 27thIEEEConference，1988(3)：2301-2306
[19] A.Szucs,M.Gerzson,K.M.Hangos.An intelligent diagnostic System based onPetri nets.Computer chem.Engng,1998,22(9):1335-1344
[20] Ouali M.-S，Ait-Kadi D，Rezg N．Fault Diagnosis Model Based on Petri NetWithFuzzy Colors，Computers & Industrial Engineering，1999(37)：173-176
[21]张才炎.基于Petri网的机车故障诊断方法研究：[中南硕士学位论文].湖南：中南大学，2010：1-59
[22]张白一,崔尚森.基于模糊Petri网的汽车故障诊断方法.长安大学学报,2008(2):93-96
[23]向永生,刘武，乐晓波，秦娜.基于模糊Petri网的汽车故障诊断仿真研究.计算机工程与科学,2009,31(3):86-88
[24]孙静,秦世引,宋永华.模糊Petri网在电力系统故障诊断中的应用.中国电机工程学报,2004,24(9):74-79
[25]曾庆锋.基于自适应模糊Petri网和有色Petri网的电网故障诊断方法研究：[西南交通大学硕士学位论文].成都：西南交通大学,2010,1-33
[26]梁远华,苑秉成.基于TS算法的FPN鱼雷电子系统故障诊断方法.仪器仪表学报,2009,30(11):2316-2320
[27]戎梅,赵廷弟，郭江杰.模糊Petri网在航天发射系统故障诊断中的应用研究.航天控制,2009,27(4):82-87
[28]宗群,王波，牙淑红.模糊Petri网在电梯故障诊断中的应用.起重运输机械,2004,(4):44-48.
[29]刘铮.基于Petri网的电梯控制系统故障诊断研究：[浙江工业大学硕士论文].杭州：浙江工业大学，2004：1-78
[30]刘敬，刘文静.基于FPN—RSVM的电梯故障诊断方法.微处理机.2008,(3):142-145
[31]黄文虎，夏松波，刘瑞岩等.设备故障诊断原理技术及应用.北京：科学出版社，1996：1-30
[32]袁崇义.Petri网原理.北京:电子工业出版社，2005
[33] Chen Shyiming,Ke Jyhsheng,Chang Jinfu.Knowledge Representation UsingFuzzy Petri Nets.IEEE Transactions on Knowldege and Data Engineering,1990,2(3):311-319
[34] Looney C G. Fuzzy Petri nets forrule based decision making. IEEE Trans. Syst. ,Man, Cybern. , 1988, 18(1)：178-183
[35] Scarpelli H , Gomide F , Yager R. A Reasoning Algorithm for High Level FuzzyPetri Nets. IEEE Transactions on Fuzzy Systems , August 1996 ,4(3) :282-294
[36]贾立新.采用模糊Petri网的形式化推理算法及其应用.西安交大学报.2003.37(12):1263-1266
[37]高梅梅.吴智铭.模糊推理Petri网及其在故障诊断中的应用.自动化学报.2002.26(5):677-680
[38]鲍培明.模糊Petri网模型的反向推理算法.南京师范大学学报,2003,3(3)：21-24
[39] Takeshi Furuhashi,Hidehiro Yamamoto.Fuzzy Control Stability Analysis Using aGeneralized Fuzzy Petri Net Model.Journal of Advanced ComputationalIntelligence and Intelligent Informatics, 1999, 3(2):99-105
[40]胡志刚,马好,廖麟.基于模糊神经Petri网的故障诊断模型.小型微型计算机系统,2005,26(11):1978-1982
[41]陈亚华，吴时霖.基于模糊有色Petri网的不确定性学习和推理方法.系统仿真学报,2003,8(15):56-58
[42]张鹏程,李人厚等.模糊着色Petri网及其在工作流建模中的应用.计算机辅助设计与图形学学报,2002,14(8):713-716
[43] Li Xiaoou, Yu Wen, Lara-Rosano F. Dynamic Knowledge Inference and Learningunder Adaptive Fuzzy Petri Net Framework. IEEE Transaction on Systems,Man, and Cybernetic Part C: Applications and Reviews,2000,30(4):442-450
[44] Li Xiaoou, Lara-Rosano F. Adaptive Fuzzy Petri Net for Dynamic KnowledgeRepresentation and Inference. E-xpert System with Applications,2000,19(3):235-241
[45] Chen Shyiming. Weighted Fuzzy Reasoning using Weight-ed Fuzzy Petri Nets.IEEE Transactions on Knowledge and Data Engineering. 2002, 14(2): 386-397
[46] Gao Meimei, Wu Zhiming, Zhou Mengc-hu. A Petri Net-based Formal ReasoningAlgorithm for Fuzzy Production Rule-based System. IEEE InternationalConference on System, Man, and Cybernetics, 2000, 4(5):314-324
[47] Yao Y.A Petri net model for temporal representations and reasoning. IEEETrans.on Systems.Man and Cybernetics.1994,24(9):1374-1382
[48] Cardoso J.etal.Petri net based reasoning for the diagnosis of dynamic discreteevent systems.In:6:th Intl.Fuzzy Systems Association World Congress.IFSA’95,Sao Paulo,Brazil,July,1995,4(1):333-336
[49] Koriem S M. A Fuzzy Petri NetTool forModeling and Verification ofKnowledge-Based Systems. The Computer Journal,2000,43(3): 206-223
[50] Fay A. A Fuzzy Knowledge-Based System for Railway Traffic Control.Engineering Applications of Artificial Intelligence,2000, 13(5):719-729
[51] Shyue-Liang Wang, Yi-huey Wu. Reasoning in Fuzzy Production Systems WhenInput Information is Incomplete. In:1999 IEEE International Fuzzy SystemsConference Proceedings. Seoul, Korea: 1999,8(22):1557-1561
[52]丁富玲，李承家.模糊Petri网的发展.杭州电子科技大学学报，2008,28(6):147-150
[53] GAO M,ZHOU M C,HUANG X,et al.Fuzzy reasoning Petri nets[J].IEEETransactions on Systems,Man and Cybernetics,Part A, 2003, 33(3): 314 - 324
[54] TANG Y,ZHOU M,GAO M.Fuzzy-Petri-net-based disassembly planningconsidering human factors.IEEE Transactions on System,Man and Cybernetics,Part A,2006,36(4):718-726
[55]陈玉宝，夏继强，邬学礼．Petri网模型在故障诊断领域的应用研究．中国机械工程，2004,11(12):1386-1388
[56]姜浩，罗军舟，方宁生．模糊Petri网在带权不精确知识表示和推理中的应用研究．计算机研究与发展，2000,37(8):918-923
[57] D S Yeung,ECC Tsang,A Multilevel Weighted Fuzzy Reasoning Algotithm forExpert Systems.IEEE Transactions on System,Man and Cybernetics, 1998, 28(2):149-158
[58]付阶辉.基于Petri网的故障诊断方法研究：[东南大学硕士学位论文].南京:东南大学，2004:1-57
[59]姜超.基于粗糙集的电梯故障诊断系统研究：[西安工业大学硕士学位论文].西安:西安工业大学，2011:5-36
[60]熊瑞庭.基于模糊神经网络的电梯故障诊断系统的研究：[武汉理工大学硕士学位论文].武汉:武汉理工大学，2009:1-55