摘要
异步电机广泛应用于工业生产等部门,一些大型电机一旦发生故障,就可能引起生产线上其它部件甚至整个系统的停产或者损坏,有时甚至会造成严重的事故,这就给异步电机的故障诊断技术提出了非常高的要求。基于知识的智能化故障诊断方法是提高故障监测与诊断系统综合性能的有效途径。
人工免疫网络和算法在故障检测与诊断方面有其独特的优点,本文尝试将其应用于异步电机故障监测与诊断问题。从电机正常和三种常见故障状态下的振动幅值信号和定子电流信号中采集特征参数,将其用于系统检测器训练。
针对现有基于人工免疫的反面选择算法存在的以下不足:该算法产生的检测器是随机的,不可避免产生大量无效检测器,且检测器不能够很好的覆盖非己空间。本文引入适合异步电机故障检测与诊断的改进型反面选择算法,使产生的检测器不能检测自己空间,只捕获非己空间的特征;设定匹配阈值,依据部分匹配原则取消能检测共有特征空间且与两个以上故障模式相匹配的检测器,但保留与各故障模式独有空间相匹配且只能检测一种故障的检测器。按已设定的匹配阈值,将训练好的检测器集与自己集相比较来确定设备发生了何种故障;若没有检测器与自己串匹配,则尝试改变初始设定的匹配阈值重复上一步骤直到有检测器与自己串匹配。将改进型反面选择算法应用于异步电机故障检测与诊断问题,仿真结果表明其对自己串和非己串数据的异常检测准确率较高。
借鉴免疫系统的克隆选择原理及已有的克隆选择算法,结合故障诊断的实际应用,研究了既具有故障诊断能力又具有对故障样本的连续学习功能的自适应故障诊断方法。尝试性引入了基于克隆选择原理的故障诊断模型,该模型可以实现对训练样本的学习、记忆、标识,同时还可以实现对未出现过的抗原样本进行在线诊断和动态再学习,通过笼型异步电动机故障诊断实例仿真研究验证了所引入方法和模型的有效性。
Induction motor is widely used to industrial production departments. But once some large-scale motors go wrong, there may be cause to other parts in production-line even the overall system be stopped production or ruined, at times it will go to the length of making severe accidents. This makes the fault diagnosis technology of induction motor to put extraordinary high request. The method of intellectualized fault diagnasis based on knowledge is efficient path for advancing overall performance of fault monitoring and diagnostic system.
Both artificial immunity networks and algorithms in aspect of fault detection and diagnosis have their unique advantage,and this paper attempts to apply them to the problem of induction motor fault monitoring and diagnosis. Collect characteristic parameters from motor vibration amplitude value signal and stator current signal in the state of normal and three kind of constant faults, and put them use to system detectors training.
Aim at the available negative selection algorithm based on artificial immunity in being following short: The brought detectors of the algorithm is random, so inevitability produce a great deal invalidation detectors, even the detectors are out of condition covering non-self space well enough; The paper introduces the generation negative selection algorithm which suits fault detection and diagnosis of the induction motor: Make the produced detectors can not detect self space, only capture non-self spacial characteristics; Set match threshold, upon partial matching principle cancel the detectors which can detect the community feature space and match with being more than two faultpatterns. But reserve the detectors which match with each faultpattern possess singly space and only detect a sort of fault. Upon the set match threshold, compare the detectors multitude trained well with self multitude to determine the device has occur which fault; If there is no detecter matched with self train, then attempt to vary initial setting match threshold and repeat the back step till there will be detectors matched with self train. Apply generation negative selection algorithm to the problem of induction motor fault detection and diagnosis, the simulation result proves that the accuracy rate of anomaly detection towards self train and non-self train data is rather high.
Borrowing ideas from clonal selective principle of immune system and the available clonal selective algorithms, combining the practical application of fault diagnosis, adapting fault diagnosis means is studied which possess fault diagnosis ability as well as serial learning function for fault samples. It has introduced tentatively fault diagnosis model based on clonal selective principle, which might realize study、memory、identification for train samples, at the same time can also realize online diagnosis and dynamic restudy to new antigen samples, and through the cage type induction motor experiments it has demonstrated the validity of methods and models this paper introduced.
引文
[1] Tavner P J,Penman J.[英]著.姜建国,史家燕译.电机的状态监测.北京:水利电力出版社.1992
[2]沈标正.电机故障诊断技术.北京:机械工业出版社.1996
[3] Birnett R,Watson J F,Elder S.The application of modern signal processing techniques to motor fault detection and location within three-phase induction motors.IEEE Trans on Power Delivery.1995,10(3):426～431
[4]邱阿瑞,孙健.电机故障模式识别与诊断.清华大学学报(自然科学版).1999.3,39(3):72～74
[5]冷军发,荆双喜.基于小波分析的电机故障诊断研究.大电机技术. 2003.(5):28～30
[6]何雨傧,阎桂荣,张道立.基于不平衡电流的电机定子故障模糊诊断方法.中国电机工程学报. 1996.3,16(2):135～138
[7] Cardoso A J Marques.In-turn stator winding fault diagnosis in three phase induction motors by Park’s vector approach.IEEE Trans on Instrumentation and Measurement. 1997,38(2):18～21
[8] Arkan M,Unswort P J.Stator fault diagnosis in induction motors using power decomposition.IEEE industry Applications.1999,41(3):781～791
[9] Wolbank Thomas M,Wohrnschimmel Reinbard.Online stator winding faults detection in inverter fed induction motors by stator current reconstruction.IEEE Transon Power Delivery.1999,40(9):630～642
[10]董爱华,付子义,康润生,等.频谱分析及其在异步电动机转子断条诊断方面的应用.焦作工学院学报.1998.1,17(1):71～74
[11]许伯强,叶东,孙丽玲.笼型异步电动机转子断条在线检测新方法.华北电力大学学报.1998,25(3):34～39
[12]殷桂梁,肖丽萍,吴长奇.免疫原理用于异步电动机故障诊断的研究.中国电机工程学报.2003,vol.23(6):132～136
[13] Schoen R R,HabetLer T G,Kamran F. Motor bearing damage detection using stator current monitoring. IEEE Trans on Power Delivery.1994,39(10):322～332
[14] Moo C S.A digital measurement scheme for time-varying transient harmonics.IEEE Trans on Power Delivery.1995,10(2):588～594
[15]任震,胡国胜,黄雯莹,等.基于线调频小波变换的电机故障信号消噪方法.电工技术学报. 2002.6,17(3):59～64
[16]丁康,朱小勇,陈亚华.齿轮箱典型故障特征与诊断策略.振动与冲击.2001(3):7～12
[17]刘树林.基于免疫机理的设备故障诊断方法及应用研究:[博士学位论文].哈尔滨:哈尔滨工业大学.2003
[18]王江萍.机械设备故障诊断技术与应用.西安:西北工业大学出版社.2001:93～107
[19]时文刚,刘树林,张嘉钟,等.基于支持向量机的往复泵泵阀故障诊断方法.机械强度.2002,24(3):362～364
[20] Jerne NK.The immune system.Scientific American,1973,229(1):51～60
[21] Farmer J D,Packard N H,Perelson A S.The immune system,adaptation,and machine learning.Physica D,1986,22:187～204
[22] Dasgupta D,Attoh-Okine N.Immunity based systems:A survey.In:Proc IEEE International Conference on Systems,Man,and Cybernetics,Orlando,Florida,1997:369～374
[23] Timmis J,Knight T.Artificial immunes system:Using the immune system as inspiration for data mining. In:Abbass Proceedings of the Second International Conference on,1:257～267
[24]王学利.基于人工免疫原理的网络入侵检测的研究.网络与通信,2004,17:30～32
[25] Hunt J E,Cooke D E.Learning using an artificial immune system.Journal of Network and ComputerApplication,1996,19(2):189～212
[26] Farmer J D,Packard N H,Perelson A S.The immune system,adaptation,and machine learning.Physics D,1986,22:187～204
[27] H A,Sarker R A,Newton C S eds.Data Mining:A Heuristic Approach. Hershey:Idea Publishing Group,2001.209～230
[28] Forrest S,Hofmeyr S A,Immunology as information processing.In:Design Principles for the Immune System and Other Distributed Autonomous Systems.USA:Oxford University Press,2000
[29] Forrest S,Hofmeyr S A,Somayaji A.Computer immunology.Communications of the ACM,1997,40(10):88～96
[30]莫宏伟,吕淑萍,管凤旭,等.基于人工免疫系统的数据挖掘技术原理与应用.计算机工程与应用,2004,14:28～33
[31]宫新保,周希朗.一种新型的网络安全技术一人工免疫系统.电气电子教学学报,2003,25(3):47～50
[32] Dasqupta D,Forrest S.Aritifial immune systems in industrial applications. Intelligent Processingand Manufacturing of Materials,1999.IPMM'99.Proceedings of the Second International Conference on,1999,1:257～267
[33]梁新荣,刘智勇,毛宗源.人工免疫系统研究及其工程应用.计算机应用与软件,2005,22(8):19～22
[34] Dasgupta D,Forrest S.1999.Artificial Immune Systems in Industrial Applications.Intelligent Processing and Manufacturing of Materials,1999.IPMM'99
[35] Araujo M,Aguilar J.Fault detection system in gas lift well based on artificial immune system.Neural Networks,2003.Proceedings of the international Joint Conference on,3:1673～1677
[36] NEAL M,HUNT J,TIMMIS J.Augmenting an artificial immune network.IEEE international conference on systems,man,and cybernetics.Sandiego,CA,USA,1998,(4):3821～3826
[37] DASGUPTA D,FORREST S.Novelty detection in time series data using ideas from immuneology.5th International conference on intelligent systems.Reno,Nevada,1996:19～21
[38]刘树林,张嘉钟,王日新,等.基于免疫系统的旋转机械在线故障诊断.大庆石油学院学报.2001, 25(4):69～72
[39]杜海峰,王孙安.基于ART-人工免疫网络的多级压缩机故障诊断.机械工程学报.2002,38(4):88～90
[40]杨江云,李蓓智,杨建国,等.人工免疫机理在故障诊断中的应用.东华大学学报.2004.2,vol.30(1):41～44
[41]殷桂梁,肖丽萍,吴长奇.免疫原理用于异步电动机故障诊断的研究.中国电机工程学报.2003,23(6):132～136
[42]汤红诚,李著信,武华峰,等.基于人工免疫的异步电机故障诊断系统.中国电机工程学报.2005,25(23):158～162
[43]刘海龙.基于框架理论的电机故障诊断专家系统的研究:[硕士学位论文].大连:大连理工大学,2002:17～18
[44]时献江.交流感应电动机故障诊断方法研究.哈尔滨电工学院学报.1994(3):80～85
[45]邱阿瑞.提取感应电动机转子故障特征的新方法.清华大学学报.1997,37(1):35～37
[46]姜建国,汪庆生,杨秉寿,等.用自适应方法提取鼠笼式异步电机转子断条的特征分量.电工技术学报.1990,(4):1～6
[47]曹志彤,何国光,陈宏平,等.电机故障特征值的倍频小波分析.中国电机工程学报.2003,23(7):112～116
[48]冷军发,荆双喜,李臻.基于小波分析的电机故障诊断研究.大电机技术.2003,(5):28～30
[49]漆安慎,杜婵英.免疫的非线性模型.上海:上海科技教育出版社,1998:2～5
[50] Jerne N K. Towards a network theory of the immune system. Annual Immunology,1974,125C:373～389
[51] Varela F.,Coutinho A.,Dupire B. and Vaz N..Cogntive networks:Immune,neural and otherwise.In perelson A.(Ed.),Thoretical Immunology.Vol.2 SFI Series on the Science of Complexity,Addisson Wesley,New Jersey,1998
[52] Varela F,Sanchez V and Coutinho A.Adaptive strategies gleaned from immune networks.In Goodwin B.and Saunders P.(Eds.),Evolutionary and epigenetic order from comples systems:A Waddington Memorial Volune.AEdinburgh U.Press,1989
[53] Tang Z.,Yamaguchi T,Tashima K,Ishizuka O,Multiple T K.Multiple-valued immune network model and its simulations.In:Proc 27th International Symposium on Multiple-Valued Logic.Antigonish,Nova Scotia,Canada.1997:519～524
[54] Nunes de Casto L,Von Zuben F J.An Evolutionary Immune Network for Data Clustering.In Proc.of Sixth Brazilian Symposium on Neural Network,Rio de Janeiro,22-25 November,2000:84～89
[55] Tarakanov S,Dasgupta D.A formal model of an artificial immune system.Biosystems,2000,55
[56]莫宏伟.人工免疫系统原理及应用.哈尔滨:哈尔滨工业大学出版社.2002
[57] Farmer. J D,Packard. N H. &Perelson. A.S. The Immune System,Adaptation,and Machine Learning. Physica 22D, 1986:187-204.
[58] Chun J S,Kim M K,Jung H K.Shape optimization of electromagnetic devices using immune algorithm,IEEE Trans on Magnetics,1997,33(2):1876～1879
[59]周明,孙树栋.遗传算法原理与应用.北京:国防工业出版社,2000
[60]潘正军,康立山,陈毓屏.演化计算.北京:清华大学出版社,2000
[61] Hajela P &Yoo J S.Immune Network Modelling in Design Optimization.In New Ideas in Optimization,(Eds.) D.Come,M. Dorigo &F. Glover,McGraw Hill,London,1999:203～215
[62]莫宏伟,王科俊,金鸿章.计算智能的融合应用研究.自动化技术及应用.2002,(1):12～36
[63] B. K Choi.Multiobjective Optimum Design of Rotor-Bearing Systems With Dynamic Constraints Using Immune-Genetic Algorithm.Proceeding of IEEE Interntional Conference on Systems and Man and Cybernetics (SMC).Japan,1996:108～113
[64]刘树林,黄文虎,夏松波,等.活塞压缩机气阀故障检测的免疫神经网络方法研究.中国机械工程. 2005,vol.16(15):1384～1387
[65]唐斌,胡光锐.基于免疫神经网络的雷达天线扫描方式的识别.应用科学学.2003,Vo1.21(1): 37～38
[66]唐斌,胡光锐.免疫神经网络用于侦察测向的技术.上海交通大学学报.2002,Vol.36 (12):1851～1853
[67]郑建国,刘芳,焦李成.用免疫神经网络做数据挖掘.计算机学报.2002,vol.29(10):51～55
[68]侯家利,朱梅阶,彭宏.模块化免疫神经网络的模型研究.电子学报.2005,Vol.33(8):1502～1505
[69] D.Dasgupta,N.Attoh-Okine.Immunity-based Systems:A Survey.Proceedings of the International Conference on Systems,Man and Cybernetics.Orlando,FL,USA,1997,1:869～874
[70]漆安慎,杜婵英.免疫的非线性模型.上海:上海科技教育出版社.1998:2～5
[71]姜梅.基于生物免疫系统的计算机入侵检测技术研究:[博士学位论文].南京:南京航空航天大学.2001:21～23
[72]高俊峰,刘树林,王日新.反面选择算法在转动设备故障预测中的应用.石油机械.2002,30(6):33～36
[73] Jerne N K.Toward a network theory of the immune system.Annual Immunology.1974,125:373～389
[74] Forrest S,Perelson A S,Allen L,et al.Self-nonself Discrimination in a Computer.In:Proc IEEE Symposium on Research in Security and Privacy,Okaland,CA,1994:202～212
[75] D.Dasgupta,N.Majumdar.Anomaly Detection in Multidimensional Data Using Negative Selection Algorithm.Procedings of the IEEE International Conference on Evolutionary Computation. Honolulu,Hawaii.2002:1039～1044
[76] Dasgupta D,Forrest S.Artificial Immune Systems in Industrial Application.Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials.Honolulu,HI,USA.1999,257～267
[77] D.Dasgupta,K.KrishnaKumar,D.Wong and M.Berry.Negative Selection Algorithm for Aircraft Fault Detection.Proceedings of the Third International Conference on Artificial Immune Systems (ICARIS- 2004),Catania,Italy.September 13-16,2004
[78] D.W.Bradley,A.M.Tyrrell.Hardware Fault Tolerance:An Immunological Solution.In the proceedings of IEEE International Conference on Systems,Man and Cybernetics (SMC),Nashville. October 8-11,2000
[79] Sathyanath S,Sahin F.An AIS approach to a color image classification problem in a real time industrial application.In Proceedings of the 2001 IEEE systems,man and cybernetics conference,2001:2285～2290
[80]谷吉海,姜兴渭,刘树林,等.免疫系统的反面选择算法在故障诊断中的应用.中国空间科学技术.2002.4,(2):24～29
[81]李涛.计算机免疫学.北京:电子工业出版社.2004:7～37,62～63
[82] J. Timmis, M. Neal. A Resource Limited Artificial Immune Systems for Data Analysis.Knowledge Based Systems.2001, 14(3～4):121～130
[83] J.Timmis,M.Neal. Investigating the Evolution and Stability of a Resource Limited Artificial Immune System.Proceeding of GECCO.Las Vegas,Nevada,USA, AAAI Press.2000:40～41
[84] A.B.Watkins,L.C.Boggess.A Resource Limited Artificial Immune Classifier.Proceedings of the International Conference on Evolutionary Computation.Honolulu,HI,USA.2002:12～17
[85] T.Knight, J.Timmis. A Multi-Layered Immune Inspired Approach to Data Mining. Proceedings of the 4th International Conference on Resent Advances on Soft Computiong. Nottingham, UK. 2002:266～271
[86] J.Timmis.Aivis-Artificial Immune Network Visualization.Proceedings of the International Conference on Eurographics.London.2001:61～69
[87] L.N.Castro,F.Zuben.The Clonal Selection Algotithm with Engineering Applications.Proceedings of GECCO.2000:36～37
[88] L.N.Castro,J.Timmis.Hierarchy and Convergence of Immune Networks:Basic Ideas and Preliminary Results.Proceedings of the 1st International Conference on Artificial Immune Systems.Canterbury,UK. 2002:231～240
[89] L.N.Castro,F.Zuben.Learning and Optimization Using the Clonal Selection Principal.IEEE Transaction on Evolutionary Computation.2002,6(3):239～251
[90] L.N.Castro,J.Timmis.An Artificial Immune Network for Multimodal Function Optimization. Proceedings of IEEE Internatioal Conference on Evolutionary Computation.Honolulu,Hawaii. 2002:699～674
[91] L.N.Castro,F.Zuben.A Pruning Self-Organizing Algorithm to Select Centers of Radial Basis Function Neural Networks.Proceedings of the International Conference on Artificial Neural Networks and Genetic Algorithm.2001:54～59
[92] L.N.Castro,J.Timmis.Artificial Immune Systems:A Novel Approach to Pattern Recognition. Proceedings of the International Conference on Neural Networks.2002:67～84
[93] L.N.Castro,J.Timmis.Artificial Immune Systems:A New Computing Intelligent Approach.Springer- Verlag.London,2002:1～20
[94] L.N.Castro,F.Zuben.An Evolutionary Immune Network for Data Clustering.Proceedings of the IEEE SBRN on Artificial Neural Networks.2000:84～89
[95]陈慰峰.医学免疫学(第三版).北京:人民卫生出版社. 2000,10
[96] L.N.Castro,F.J.Von Zuben.The Clonal Selection Algotithm with Engineering Applications.Genetic and evolutionary computation conference.Las vegas,USA,2000:36～37
[97] L.N.Castro,F.J.Von Zuben.Learning and Optimization Using the Clonal Selection Principal.IEEE Transaction on Evolutionary Computation.2002,6(3):239～251
[98]周颖,郑德玲,位耀光,等.一种基于生物免疫原理的识别算法.北京科技大学学报.2004,26(4): 438～441