摘要
故障诊断是通过从故障征兆空间到故障空间的映射,实现对故障的识别和诊断。然而,复杂系统经常处在动态变化的过程中,其行为特点不好把握,各种故障的发生具有很强的不确定性,所有这些都为有效地获取、表示和利用诊断知识进行智能化推理带来了很大的困难。独特型网络理论指出:免疫网络模型中的各个细胞、分子不是处在一种孤立的状态,而是通过自我识别、相互刺激和相互制约构成了一个动态平衡的网络结构,这和大型机电设备结点之间的相互影响是完全相似的,因此通过这种动态免疫网络的研究,可望产生更有效的设备故障诊断方法。
随着目前大型设备的日益复杂,传感器结点之间的数据是动态互相影响的,如果仅靠从知识库中去寻找最佳匹配来诊断故障,很容易发生漏诊或误诊。目前人工免疫算法中的相似和浓度的定义存在一些问题,例如:利用信息熵的方法计算亲和力和浓度有一些缺陷,同时在抗体评价方面,如果仅以抗体亲合度作为评价标准,不能体现抗原对抗体的影响程度,采用通常的抗体浓度定义,又不能得到抗体亲合度的信息。为此本文根据Jerne的独特型网络理论提出了一个简单、通用性好,又能通过模型的动力学行为综合反映网络细胞(抗体和抗原)的浓度、相似度信息,以提高免疫算法的全局搜索能力的模型,并利用案例检索的优势,考虑了机电设备传感器结点之间相互影响的特性。实验证明,该模型在加快免疫算法在后期的收敛速度和提高故障检测率方面均高于其他算法。
本文研究工作的核心是基于独特型免疫网络的故障诊断系统的设计及其在故障诊断中的应用。首先简单介绍了生物免疫系统的一些基本概念、工作原理、生物免疫系统的一些重要机制和生物免疫网络,对故障诊断技术及电机设备故障诊断原理进行了总结。接着介绍了人工免疫网络当前的研究及应用状况,并对一些经典的免疫网络模型的基本结构和算法流程进行了研究和分析。最后基于这些工作提出了一个基于独特型免疫网络原理的故障诊断模型,并利用改进的抗原、记忆抗体在形态空间的表现形式和简化的抗体刺激度及抗体浓度计算公式以及改进的亲和力计算公式进行训练。通过仿真实验,研究了该免疫模型的性能及其在电机故障诊断中的有效性。
Fault diagnosis is to identify and diagnose fault through the mapping from the defective symptoms space to the defective space. However, many complex systems often change dynamically, and their characteristics are not grasped, so some faults have very strong uncertainties. All of these brought us great difficulties for intelligent diagnostic reasoning via obtaining, expressing and using diagnosis knowledge effectively. Idiotypic-Network theory points out that the various cells and molecules are not in a state of isolation in immune-network model. They constitute a dynamic network structure through self-identification, mutual stimulation and their mutual constraints. This phenomenon is quite similar to the interaction between the nodes of large-scale mechanical and electrical equipments. So we expect to design more efficient fault diagnosis methods by studying this dynamic immune network.
With the large equipments becoming more and more complicated, data collected from transducer nodes are influence each other, therefore, which lead to diagnostic errors or misdiagnosis when we only depend on matching the analogical data from fault diagnose knowledge-base. However, the definition of analogy and concentration in the artificial immune algorithms has some problems, for example, the methods for calculating affinity and concentration by using entropy of information have some defects. At the same time, when we evaluate antibodies only by antibody's affinity-degree, we can not accurately acquired the influence between antigen and antibody. If we evaluate it by accustomed definition, we can not acquire the information of antibody's affinity-degree.This thesis proposes a simple model which can synthetically reflect the density of network cells (antibody and antigen) and the information of alike-degree between them according to Jerne's Idiotypic-Network theory,this model also consider the characteristic of influence between transducer nodes and utilization advantage of CBR. Experiments show that the model is faster than other immune algorithms in speeding the later rate of convergence of immune algorithms and improveing the rate of fault diagnosis.
The core content of this thesis is the design of fault diagnosis system based on idiotypic immune network and its application to fault diagnosis. Firstly, some basic concepts, framework and principles of the biological immune systems are briefly introduced. We then introduce the research content, research status and basic theory of the artificial immunological network. The framework and flow of some classical algorithms of immunological network model and its structure are studied and analyzed. This thesis also summarizes the fault diagnosis technologies and the principle of electrical equipment fault diagnosis. At last, this thesis gives us a simple fault diagnosis model based on Idiotypic Immune Network, and train it by improved formula including affinity calculation, antibody concentration, antibody stimulation and the form of performance of improved antigen and memory antibody in modal space. The simulation experiment about asynchronous electromotor shows the feasibility of the artificial immune-network system proposed above.
引文
[1]周东华,叶银忠,现代故障诊断与容错控制[M],第1版,北京:清华大学出版社,2000.12:4-5
[2]于宗艳,基于人工免疫算法的故障诊断问题研究[D],硕士学位论文,大庆:大庆石油学院,2006.3:5-6
[3]徐章遂,房立清,王希武等,故障信息诊断原理及应用[M],北京:国防工业出版社,2000.7:3-6
[4]郑日荣,毛宗源,一种改进的人工免疫算法[J],北京:计算机工程与应用,2003,34:35-37
[5]Farmer J.D.,Packard N.H.,Perelson A.S.,The Immune System,Adaptation,and Machine Learning[J],Physica D,1986,22:187-204
[6]De Castro,Fernando J.,An Evolutionary Immune Network for Data Clustering[A],Proc 6~(th)Brazilian Symposium on Neural Networks[C],Rio de Janeiro,Brazil:[s.n.],2000,84-89
[7]Forrest S.,Perelson A.S,Allen L.Et al.,Self-nonself discrimination in a computer[A],Proc IEEE Symposium on Research in Security and Privacy[C],Okaland:CA,1994:202-212
[8]N Mitsumoto,T Fukuda et al.,Control of the distributed autonomous robotic system based on the biologically inspired immunological architecture[C],In:Proceedings-IEEE International Conference on Robotics and Aotomation,1997:3551-3556
[9]Timmis J.,Neal M.,Hunt J.,An artificial immune system for data analysis[J],Biosystem,2000,55(1-3):143-150
[10]A Ishiguro,S Kuboshiki et al.,Gait control of hexapod walking robots using mutual-coupled immune networks[J],Advanced Robotics,1996:10(2):179-195
[11]N.K.Jerne.,Towards a Network Theory of the Immune System[J],Annual Immunology,1974:125:373-389
[12]Alan S.Perrlson,Immune network theory,Immunological Review[J],1989,No.110:5-36
[13]Varela F.J.& Coutinho A.,Second genernation immune network[J],Imm.Today, 1991.12(5):159-166
[14]R.Davis,Diagnostic Reasoning Based on Structure and Behavior[J],Artificial Intelligence,1984,24(3):347-410
[15]R.Reiter,A Theory of Diagnosis from First Principle,Artificial Intelligence[J],1987,32(1):57-96
[16]J.S.米切尔,机械故障的分析与监测[M],北京:机械工业出版社,1990:5-16
[17]史忠植,高级人工智能[M],北京:科学出版社,1998:1-14
[18]朱大奇,于盛林,陈小平,基于故障树分析及虚拟仪器的电子部件故障诊断研究[J],北京:仪器仪表学报,2002,23(1):16-19
[19]师汉民,陈吉红,阎兴等,人工神经网络及其在机械工程中的应用,北京:中国电力[J],1996,29(4):5-10
[20]D.J.Sebald,J.A.Bucklew,Support Vector Machine Techniques for Nonlinear Equalization[C],IEEE Transactions on Signal Processing,2000,48(11):3217-3226
[21]李永刚,模糊理论在汽轮发电机故障诊断中的应用[J],保定:华北电力大学学报,1998,(1):26-31
[22]Z.Pawlak,Rough Sets,International Journal of Information and Computer Science[C],1982,(11):341-356
[23]安云庆,免疫学基础[M],北京:北京科学技术出版社,1998:1-2
[24]周光炎,免疫学原理[M],上海:上海科学技术文献出版社,2000:1-2
[25]骆珍,基于免疫原理的网络入侵检测系统研究[D],硕士学位论文,西安:西安电子科技大学,2007.1:17
[26]葛红,毛宗源,一种新的数据分析方法:人工免疫网络[J],北京:计算机工程与应用,2002,13:6
[27]邵继业,基于免疫机理的故障诊断方法研究[D],硕士学位论文,哈尔滨:哈尔滨工业大学,2004.6:12-13
[28]王小平,曹立明,遗传算法-理论、应用与软件实现[M],西安:西安交通大学出版社,2002.1:222-224
[29]张清华,基于人工免疫系统的机组故障诊断技术研究[D],博士学位论文,广州:华南理工大学,2004.5:17-21,26-29
[30]杨斌,基于Multiagent独特性人工免疫网络[D],硕士学位论文,西安:西安电子科技大学,2005.1:17-18
[31]杨叔子等,机械设备诊断学的探讨[J],武汉:华中工学院学报,1987(2):4
[32]李军旗等,诊断专家系统的不确定性问题研究[J],武汉:华中理工大学学报,1994,22(7):19-22
[33]徐章遂,马爱文,故障信息相近的故障识别[J],咸阳:火炮发射与控制,1994.2:31-36
[34]Dembo Amir.,Inequalities in Information Theory[C],IEEE Transaction on information Theory,1991.11:1501-1518
[35]E.D.Kamin,A Simple Procedure for Puning Back Propagation Trained Neural Networks[C],IEEE.Trans.Neural Network,1990.1
[36]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[J],大庆:大庆石油学院学报,Vol.25,No.4,2001.12:71
[37]熊春柳,人工免疫在故障诊断中的应用[D],硕士学位论文,杭州:浙江大学,2006.5:7
[38]谢明,模糊人工免疫网络研究及应用[D],硕士学位论文,西安:西安电子科技大学,2005.1:13-14
[39]莫宏伟,人工免疫系统原理与应用[M],哈尔滨:哈尔滨工业大学出版社,2002.11:80-81,132-135
[40]谷吉海,姜兴渭,刘树林,免疫系统的反面选择算法在故障诊断中的应用[J],北京:中国空间科学技术,2002.4(2):25-26
[41]张乐,人工免疫系统研究与应用[D],硕士学位论文,南京:南京工业大学,2004.3:20-21
[42]Varela F.J.& Coutinho A.,Dupire E.,Vaz N.N.Immune,neural nd otherwise[C],In:A.S.,editor,Theoretical Immunology,1988:359-375
[43]Hoffmann,W Geoffrey,Immune system:A neglected challenge for network theorists[C],In:Proceedings-IEEE International Symposium on Circuits and Systems,1989:1620-1623
[44]J T Ootsuki et al.,Immune system response network approach for finding firing sequences of a sub-class of Petri nets[C],In:Proceedings-IEEE International Conference on Systems,Man and Cybernetrics,1998:148-153
[45]刘克胜,张军,曹先彬等,一种基于免疫原理的自律机器人行为控制算法[J],北京:计算机工程与应用,2000:36(5):30-32
[46]Z.Tang et al.,Multiple-valued immune network model and its simulations[C],In:Proceedings of The International Symposium on Multiple-valued Logic,Autigonish,Canada,1997:233-238
[47]章洁,基于免疫机制和生态机制的组合优化问题研究[D],硕士学位论文,合肥:中国科学技术大学,1998
[48]肖人斌,王磊,人工免疫系统:原理、模型、分析及展望[J],北京:计算机学报,2002(12):1282-1284
[49]Germain R N.MHC-Associated Antigen Processing,Presentation,and Recognition,Adolescence,Maturity and Beyond[J],The Immunologist,1995.6(3-5):185-190
[50]王珺,刘希玉,王鑫,人工免疫系统及其模型分析[J],西安:计算机技术与发展,2006,Vol 16,No.7,106-107
[51]陈真勇,何永勇,褚福磊等,多Agent故障诊断原型系统研究[J],武汉:中国机械工程,2002,Vol 13,No.13,1085-1087
[52]Seiden PE.& Celade.F.,A Computer Model of Cellular Interactions in the Immune System[J],Imm.Today,1992,13(2):56-62
[53]Ishida Y.,Distributed and Autonomous Sensing based on Immune Network[C],Proc.of AROB 96,1996:214-217
[54]Ishide Y.,The Immune System as a Prototype of Autonomous Decentralized Systems:An Overview[C].In Proc.of ternational Symposium on Autonomous Decentralized System(ISAD97),Berlin,April9-11,1997:85-92
[55]侯胜利,李应红,李名魁等,基于人工免疫网络模型的航空发动机传感器故障诊断[J],北京:推进技术,Vol.28,No.1,2007:87-88
[56]谭光兴,李中华,毛宗源,基于独特型网络动力学模型的人工免疫算法[J],广州:华南理工大学学报(自然科学版),Vol.34,No.1,2006.1:62-63
[57]刘光,CBR技术在多主体系统中的应用[D],硕士学位论文,北京:北京化工大学,2004.11:30-31
[58]葛红,毛宗源,免疫算法几个参数的研究[J],广州:华南理工大学学报(自然科学版),2002,30(12):15-18
[59]葛红,免疫算法及核聚类人工免疫网络应用研究[D],博士学位论文,广州:华南理工大学,2003.5:5