摘要
设备故障诊断技术，其实质是了解和掌握设备在运行过程中的状态；预测设备的可靠性；确定其整体或局部是正常或异常；早期发现故障，并对其原因、部位、危险程度等进行识别和评价；预报故障的发展趋势，并针对具体情况做出实施维护决策的技术。
免疫系统是一种复杂的分布式信息处理学习系统，这种系统具有免疫防护、免疫耐受、免疫记忆、免疫监视功能，尤其具有较强的自适应性、多样性、学习、识别和记忆等特点。这些功能和特点的结合促成了各种基于免疫机理的人工免疫智能方法，解决了大量的非线性科学问题。免疫系统信息处理机制在故障诊断方面的应用具有重要的理论意义和实用价值。
本文所做的主要工作如下
(1)借助遗传算法中变异的机制，对能检测出异常变化的阴性选择算法作了新改进。试验结果表明了新改进的算法在基本能覆盖自己空间范围的前提下，计算复杂度明显下降的同时对异常检测的有效性大大提高。
(2)将人工免疫系统的克隆选择原理结合思维进化思想，设计了一种人工免疫进化计算模型。该模型中利用克隆选择原理对故障进行模式学习和识别，利用思维进化思想定义了免疫趋同算子和免疫异化算子来对抗体进行扩增和抑制。将其应用在模拟机组的状态识别，试验结果表明，所提出的模型对状态检测有较高的有效性。
(3)基于克隆选择原理和K-Nearest Neighbor分类法按照免疫疫苗、免疫学习和免疫应答三个过程设计了能生成有效检测器的故障检测算法。试验结果表明了该算法产生的检测器能以较高的准确率来检测故障。
The essence of the fault diagnosis technology is to know the state of the equipment in the process of running, to forecast its reliability, to determine its normality or exceptionality, to discovery fault earlier and estimate and identify its reason, position and criticality. It is also to predict the development trend of fault and make decision through its concrete status.
Immune system is the complex distributional information processing learning system. Its have kinds of function such as immune protection, immunological tolerance, immune memory, immune surveillance, especially have kinds of characteristic such as stronger adaptability, multiplicity, study, recognition and memory. The combination between functions and characteristics gained various artificial intelligence methods based on immune mechanism, which solve the massive non-linear scientific problem. The information processing mechanism of immune system is of important theoretical significance and practical value in fault diagnosis.
The primary subject of this paper is to
(1) The negative-selection algorithm that can be detected abnormity is improved by the mutation mechanism of genetic algorithm. The result of simulation show that the computing complexity of the improved algorithm which can basically cover the self-space declines in evidence. Meanwhile its efficiency greatly improves to fault detection.
(2) In the mixture of the idea of Mind Evolutionary Computation (MEC) and the clonal selection principle of artificial immune system, a model of artificial immune evolutionary computing is designed. The models learn and recognize to fault mode in clone selection theory, and the immune similartaxis operator to expend antibody and the immune dissimilation operator to restrain antibody are defined using the thought of mine evolutionary computing. The algorithm are used in state recognize of simulation machine unit. The experiment result shows that the algorithm has a better validation to state recognize.
(3 ) Based on conal selection principle and K-Nearest Neighbor method, a fault detection algorithm that can produce the valid detector to diagnose fault is designed by the three parts of immune vaccine, immune learning and immune response. The simulation examples show that the detector produced by the algorithm has a better accuracy to fault detection.
引文
[1] 裴峻峰，杨其俊，机械故障诊断技术，东营：石油大学出版社，1997：3-5
[2] 虞和济，韩庆大，李沈等，设备故障诊断工程，北京：冶金工业出版社，2001：2-6
[3] 柯拉科多 RA，机械故障的诊断与情况监测，北京：机械工业出版社，1983
[4] 李秀琴，李书臣，一类非线性系统的故障检测与容错控制算法，测控技术，2005，24(8)：31-33
[5] 夏良华，贾希胜，徐英，机械系统故障诊断与状态监测的发展趋势，火炮发射与控制学报，2005，(2)：69-72
[6] 唐贵基，田丽洁，田学航等，基于神经网络的混合智能故障诊断技术研究，煤矿机械，2005，(3)：133-135
[7] 魏霞，徐敏强，鹿卫国，故障诊断技术及应用综述，热力透平，2004，4(300)：238-242，246
[8] 彭涛，谢勇，故障检测诊断技术与先进控制理论，株洲工学院学报，2002，16(4)：19-22
[9] 王耀才，智能故障诊断技术的现状与展望，徐州建筑职业技术学院学报，2003，3(1)：36-38
[10] 周东华，叶银忠，现代故障诊断与容错控制，北京：清华大学出版社，2000
[11] 沈剑贤，沈烔，李益国等，人工免疫系统原理及其应用，汽轮机技术，2005，47(4)：248-257
[12] Jerne N K. The immune system. Scientific Ametican, 1973, 229(1):51-60
[13] Perelson A. Immune network theory. Immunological Review, 1989, 110:5-36
[14] Farmer J D, Packard N H, Perelson A S. The immune system, adaptation, and machine learning. Physical D, 1986, 22:187-204
[15] Ishida Y, Fully Distributed Diagnosis by PDP Learning Algorithm: Towards Immune Network PDP Model. Proceedings of ICNN90, San Diego, 1990
[16] Kayawa M, Sugita Y, Morooka, Sensor Diagnosis System Combing Immune Network and Learning Vector Quantization. Electrical Engineering in Japan, 1997:44-55
[17] Dasgupta D, Forrest S. Artificial Immune Systems in Industrial Applications. Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials, 1999:257-267
[18] Ishiguro A, Watanabe Y, Uchikawa Y. Fault diagnosis of plant systems using immune networks. In: Proc IEEE International Conference On multi-sensor Fusion and Integration for Intelligent Systems, Las Vegas, NV, 1994,34-42
[19] Tang Z, Yamaguchi T, Tashima K et al. Multiple-valued immune network model and its simulation. In: Proc the 27 International Symposium on Multiple-Valued Logic, Antigonish, Nova Scotia, Canada, 1997, 519-524
[20] 刘树林，黄文虎，王日新等基于免疫系统的往复泵在线故障诊断方法，中国机械工程学报，2002，13(8)：686-689
[21] 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(2)：24-29
[22] 栾家辉，姜兴渭，免疫状态观测器的设计及应用，中国空间科学技术，2005，5：34-39
[23] 庞茂，周晓军，孟庆华，基于免疫学的在线故障检测算法的研究及应用，中国电机工程学报，2005，25(24)：149-153
[24] 李伟，黄席樾，基于免疫原理的故障诊断推理模型研究，计算机仿真，2005，22(7)：111-113
[25] 陈强，郑德玲，基于免疫原理的齿轮箱故障检测和诊断方法研究，矿山机械，2005，33(5)：75-77
[26] 韩捷，张瑞林等，旋转机械故障机理及诊断技术，北京：机械工业出版社，1997：2-4，35-37
[27] 莫宏伟，人工免疫系统原理与应用，哈尔滨：哈尔滨工业大学出版社，2003：20-40
[28] 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
[29] 李伟，基于免疫原理的可重构诊断系统研究，博士学位论文，重庆：重庆大学，2005
[30] D'haeseleer P, Forrest S, Helman P. An Immunological Approach to Change Algorithms: Analysis and Implications. In: Proc IEEE Symposium On Security and Privacy, Las Alamitos, CA, USA, 1996, 110-119
[31] Forrest S, Hofmeyr S A, Immunology as Information Processing[M]. In: Segel and Cohen eds. Design Principles for the Immune System and Other Distributed Autonomous Systems, USA: Oxford University Press, 2000
[32] 屈梁生，何正嘉，机械故障诊断学，上海：上海科学技术出版社，1986
[33] 张清华，基于人工免疫系统的机组故障诊断技术研究，博士学位论文，广州：华南理工大学，2004
[34] 徐宗本，张讲社，郑亚林．计算智能中的仿生学：理论与算法，北京：科学出版社，2003
[35] De Castro L N, Von Zuben F J. Clonal selection algorithm with engineering applications. In: Proc GECCO OO, Las Vegas, Nevada, USA, 2000, 36-37
[36] 孙承意，谢克明，思维进化—高效率的进化计算方法．，第三届全球智能控制与自动化大会论文集：中国，合肥，2000．6．28-2000．7．2，118-121
[37] Keming Xie, Changhua Mou, Gang Xie. The Multi-parameter Combination Mind-evolutionary-based Machine Learning and its Application. Proceedings of 2000 IEEE International Conference on Systems, Man, and Cybernetics(SMC2000), 2000.10, Music City Sheraton, Nashville, Tennessee, USA, 183-187
[38] 宋丹，傅明，基于多种群的自适应免疫进化计算，控制与决策，2005，20(11)：1251-1255
[39] 赵翔，黄磊，刘健，周绍骑，现代故障诊断技术研究现状与趋势，后勤工程学院学报，2006，2：94-98
[40] 徐波，于劲松，李行善，复杂系统的智能故障诊断，信息与控制，2004，33(1)：56-60
[41] 桂卫华，刘晓颖，基于人工智能方法的复杂过程故障诊断技术，控制工程，2002，9(4)：1-6
[42] Tang T H, Lin X, Li J R, etal. A new fuzzy neural network approach for intelligent monitoring system[A] .Proceedings of IFAC Transportation Systems Conference. 1997.691～696.
[43] 罗文坚，曹先彬，王煦法，检测器自适应生成算法研究，自动化学报，2005，31(6)：907-916
[44] 熊浩，孙才新，李小虎，基于克隆选择分类算法的电力变压器故障诊断，电网技术，2006，30(4)：65-68
[45] De Castro, L. N. ,Von Zuben, E J. Learning and Optimization Using the Clonal Selection Principle[A], IEEE Transactions on Evolutionary Computation, Special Issue on Artificial Immune Systems, 2002,6(3), pp. 239-251.
[46] 陈进法，裴战朝，设备故障诊断技术及应用，北京：北京伊麦特科技有限公司资料， 145-150。
[47] 陈向东，赵登峰，王国强等，基于神经网络的滚动轴承故障监测，轴承，2003(2)：23-26
[48] De Castro L N, Von Zuben F J. An evolutionary immune network for data clutering. In: Proc 6 the Brazilian Symposium or Neural Networks, Rio de Janeiro, Brazil, 2000, 84-89.
[49] 王正林，刘明，精通MATLAB7，北京：电子工业出版社，2006