摘要
人工免疫网络和算法在自己-非己识别、数据模式学习、记忆和分类方面有其独特的优点。将免疫算法应用于机械设备的异常检测和故障诊断中是一个独特而又极有研究价值和实际应用意义的课题。
为了对故障样本不足的设备进行异常状态检测,从免疫系统自己、非己的概念出发,对设备异常状态检测问题进行了描述,引进了状态空间、自己空间、非己空间等概念。为了更有效地检测设备的异常状态,在对免疫系统反向选择机理及现有反向选择算法进行分析的基础上,提出了一种改进型反向选择算法。给出了检测器数量的评估公式,同时对检测器在非己空间的分布程度给出了一个间接的评价。C618型车床齿轮箱异常检测的实验结果表明这种改进型反向选择算法能产生“高质量”的检测器并有对非己空间有很好地覆盖能力。
为了将故障检测与故障模式诊断有机结合,借鉴免疫系统的克隆选择机理及已有的人工免疫系统成果,研究了具有故障诊断能力,同时又具有对故障样本的连续学习功能和对数据样本标识的故障诊断方法。针对现有故障诊断方法缺乏连续、自适应学习能力等问题,提出了一种基于克隆选择机理的故障诊断模型;为解决设备状态数据模式的识别、分类问题,在抗原、抗体的定义中加入了一个标识类别的信息参数,并将克隆选择进化学习算法用于对数据样本的学习中;针对现有的克隆选择算法中对抗体克隆操作的不足,提出了一种在二维空间中的基于亲和力思想的克隆操作算子。通过C618型车床齿轮箱故障诊断实例验证了所提出方法及算法的有效性。
为解决非线性耦合、空间重叠及多故障情况的故障诊断问题,将免疫进化学习算法与径向基神经网络相结合,构造了一种免疫神经网络模型。利用免疫进化学习算法确定径向基神经网络的隐层结构及隐层中心参数,利用训练样本对免疫神经网络进行学习训练,最后将训练好的网络应用于故障诊断中。通过对7216型圆锥轴承和Iris数据的实验仿真,验证了该免疫神经网络的模式识别能力。
The artificial immune network and algorithm have its unique excellencies in the self and non-self reorganization、data pattern learning、memory and classify, etc. Applies the immune algorithm in the anomaly detection and fault diagnosis of mechanical equipment is an unique topic, which have a great deal of research value and the practical application significance.
In order to detect the abnormal state of the equipment,which is lack of fault samples. The abnormal state detection problem to equipment is described and some new terms (for example, state space, self space, non-self space, and so no) are introduced on the basis of the self and non-self concepts of immune system. In order to detect the abnormal state of equipment more efficiently, this paper proposes a modified negative selection algorithm based on analyzing the negative selection mechanism of immune system and the existing negative selection algorithm. A formula has given to evaluate the quantity of detectors, simultaneously; an indirect appraisement has given for the distributed degree of detector in the non-self space. The experimental results of the anomaly detection of C618 lathes gear box indicates this modified negative selection algorithm can generate "more quality" detectors and have good ability to cover the non-self space.
In order to combine anomaly detection with fault patter diagnosis, utilize the clonal selection mechanism of immune system and research achievements of artificial immune system, a new fault diagnosis approach with continuously learning and data samples identifiable abilities is investigated. Aim at solve the problem that the existing fault diagnosis approaches lack continuously、self-adaptive learning capabilities, a model of fault diagnosis based on clonal selection mechanism. In order to solve the problem of equipment state data pattern recognition and classified, an information parameter of identifier for sorts is joined in the definition of antigen and antibody. A clonal selection evolutional learning algorithm is used in the training phase of fault diagnosis. Aim at the problem that the clonal operation of antibody is insufficient; this paper proposes a clonal operation operator in the two-dimensional space based on affinity. Thought the experiment towards fault diagnosis of C618 lathe gear box demonstrated the validity of this method and algorithm.
In order to solve those problems of nonlinear coupling and multi-faults in fault diagnosis. Combined the immune evolutional learning algorithm and Radial Basis Function Neural Network (RBFN), an Immune Neural Network model is designed. Use the immune evolutional learning algorithm to ascertain the crytic-layers structure and crytic-layers central parameters of RBFN. Utilize the training samples to train the Immune Neural Network. Finally, apply the trained network to fault diagnosis. Thought the experiments of 7216 tapered bearings and Iris datum demonstrated the pattern recognition capability of this Immune Neural Network.
引文
[1] 吴今培,肖健华. 智能故障诊断与专家系统[M]. 科学出版社. 1997.
[2] 吴今培. 智能故障诊断技术的发展和展望[J]. 振动、测试与诊断. 1999,19(2):79-86.
[3] 陈永云,刘爱伦.俞金寿. 故障诊断的近期发展[J]. 世界仪表与自动化.2003,vol.7(3):1-3.
[4] 丁永生,任立红. 人工免疫系统:理论与应用[J]. 模式识别与人工智能. 2000,13(1):52-59.
[5] D.Dasgupta, N.Attoh-Okine. Immunity-based Systems:A Survey[C]. Proceedings of the International Conference on Systems, Man and Cybernetics. Orlando, FL, USA, 1997, 1:869-874.
[6] 韩建,张乐,蔡瑞英. 基于人工免疫算法的入侵检测系统[J]. 南京工业大学学报. 2004,1.vol.26(1):48-50.
[7] 杨晓宇,周佩玲,傅忠谦. 人工免疫与网络安全[J]. 计算机仿真. 2001, vol.18(6):83-85.
[8] John E.Hunt and Denise E Cooke. Learning using an artificial immune system [J]. Journal of Network and Computer Applications. vol 19:189-212.1996.
[9] Jon Timmis, Mark Neal, and John Hunt. An artificial Immune System for data analysis[J]. Biosystems. vol.55,no.1/3,pp.143-150,2000.
[10] Roberto T, Alves, MyRiam R, et al. An Artificial Immune System for Fuzzy-Rule Induction in Data Mining[C]. Computer Science.Berlin: Springer-Verlag. v.3242:1011-1020, 2004.
[11] 莫宏伟. 基于人工免疫网络的联想记忆器[J]. 自动化技术与应用. 2002, vol.1:18-20.
[12] 李海潮,陈强. 基于人工免疫的监督学习模型及其应用[J]. 计算技术与自动化. 2006.vol 25(2):120-123.
[13] 付冬梅,郑德玲等. 人工免疫控制器的设计及其控制效果的仿真[J]. 北京科技大学学报. 2004, vol.26(4):442-445.
[14] 丁永生,任立红. 一种新颖的模糊自调整免疫反馈控制系统[J]. 控制与决策. 2000, 15(4):443-446.
[15] 谈英姿,沈烔等. 免疫 PID 控制器在气温控制子系统中的应用研究[J]. 中国电机工程学报. 2002, 22(10):148-153.
[16] 杨建国,李蓓智,项前. 基于免疫遗传计算的零件多目标优化[J]. 工程图学学报. 2003,vol.2:13-19.
[17] 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[J]. 机械工程学报. 2002, vol. 38(4):88-90.
[18] 刘树林,王日新等. 基于反面选择算法的压缩机振动在线监测方法研究[J]. 压缩机技术. 2001, vol.5:9-11.
[19] 杨江云,李蓓智等. 人工免疫机理在故障诊断中的应用[J]. 东华大学学报. 2004, vol. 30(1):41-44.
[20] 丁康,朱小勇,陈亚华. 齿轮箱典型故障特征与诊断策略[J]. 振动与冲击. 2001(3):7-12.
[21] 周颖,郑德玲等. 一种基于生物免疫原理的识别算法[J]. 北京科技大学学报. 2004, 26(4):438-441.
[22] 焦李成,杜海峰,刘芳,公茂果著. 免疫优化计算学习与识别[M]. 科学出版社. 2006.
[23] 刘树林. 基于免疫机理的设备故障诊断方法及应用研究[D]. 哈尔滨工业大学博士学位论文. 2003.
[24] 王江萍. 机械设备故障诊断技术与应用[M]. 西北工业大学出版社, 2001:93-107.
[25] 时文刚,刘树林,张嘉钟,黄文虎. 基于支持向量机的往复泵泵阀故障诊断方法[J]. 机械强度. 2002,24(3):362-364.
[26] Ishida Y. Fully distributed diagnosis by PDP learning algorithm towards immune network PDP model[C]. In Proc International Joint Conference on Neural Networks. San Diego, CA, USA. 1990:777-782.
[27] Ishida Y. An Immune Network Model and Its Application to Process Diagnosis [J]. Systems and Computers (In Japan). 1993, 24(6):38-45.
[28] Ishiguro A, Watanabe Y, Uehikawa Y. Fault Diagnosis of Plant Systems Using Immune Networks[C]. Proc 1994 IEEE Int Conf Multisensor Fusion and Integration for Intelligent Systems. Las Vegas, 1994, 34-42.
[29] Tang Z., Yamaguchi T, Tashima K et al. Multiple-valued immune network model and its simulations[C]. In: Proc 27th International Symposium on Multiple-Valued Logic. Antigonish, Nova Scotia, Canada. 1997. 519-524.
[30] Dasgupta D, Forrest S. Artificial Immune Systems in Industrial Application[C]. Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials. Honolulu, HI, USA. 1999, 257-267.
[31] P.J.Costa Branco, J.A.Dente, and R.Vilela Mends. Using Immunology Principles for Fault Detection[J]. IEEE Transactions on Industrial Electronics. vol 50, No.2 April 2003:362-372.
[32] 刘树林,王日新等. 基于反面选择算法的压缩机振动在线监测方法研究[J]. 压缩机技术. 2001, vol.5:9-11.
[33] 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[J]. 机械工程学报. 2002,vol.38(4):88-90.
[34] 杨江云,李蓓智等. 人工免疫机理在故障诊断中的应用[J]. 东华大学学报. 2004,2 vol.30(1):41-44.
[35] 漆安慎,杜婵英. 免疫的非线性模型[M]. 上海科技教育出版社. 1998:2-5.
[36] 陈慰峰. 医学免疫学(第三版)[M]. 人民卫生出版社. 2000, 10.
[37] Jerne. N J. Towards a network theory of the immune system [J]. Annual Immunology, 1974. 125C.
[38] Varela F., Coutinho A,. Dupire B. and Vaz N. Cogntive networks: Immune, neural and otherwise [J]. In perelson A.(Ed.), Thoretical Immunology. Vol.2 SFI Series on the Science of Complexity, Addisson Wesley, New Jersey, 1998.
[39] Varela F, Sanchez V. and Coutinho A. Adaptive strategies gleaned from immune networks [J]. In Goodwin B. and Saunders P. (Eds.), Evolutionary and epigenetic order from comples systems: A Waddington Memorial Volune. AEdinburgh U.Press, 1989.
[40] 李涛. 计算机免疫学[M]. 电子工业出版社. 2004:7-37, 62-63.
[41] Smith D J, Forrest S, Perelson A S. Immunological memory iaa associative. In: Workshop Notes, Workshop 4: Immunity Based Systems[C]. Intnl. Conf, on Multiagent Systems. Tokyo, Japan, 1996, 1.
[42] Abbattista F, Gioia G D, Santo G D, Fanelli A M. An associative memory based on the immune networks[C]. IEEE International Conference on Neural Networks. Washington. DC. USA. 1996, 1.
[43] Ishiguro A.Kuboshiki S, Ichikawa S, etc. Gait control of Hexapod Walking Robots Using Mutual-Coupled Immune Networks[J]. Advanced Robots, 1996(10):179-195.
[44] Zak M. Physical model of immjune inspired computing [J]. Information Science, 2000,129.
[45] De Castro L N, Von Zuben F J. The Clonal Selection Algorithm with Engineering Application[C]. Genetic and evolutionary computation conference. Las vegas, USA, 2000.
[46] De Castro L N, Von Zuben F J. Artificial Immune Systems: Part I-Basic Theory and Applications[R]. Technical Report, TR-DCA 01/99, 1999.
[47] Tarakanov S, Dasgupta D. A formal model of an artificial immune system [J]. Biosystems, 2000, 55.
[48] 莫宏伟. 人工免疫系统原理及应用[M]. 哈尔滨工业大学出版社. 2002.
[49] Farmer. J D, Packard. N H. &Perelson. A.S. The Immune System, Adaptation, and Machine Learning [J]. Physica 22D, 1986:187-204.
[50] 周明,孙树栋. 遗传算法原理与应用[M]. 北京:国防工业出版社,2000.
[51] 潘正军,康立山,陈毓屏. 演化计算[M]. 北京:清华大学出版社,2000.
[52] Hajela P. &Yoo J S. Immune Network Modelling in Design Optimization[C]. In New Ideas in Optimization ,(Eds.) D. Come, M. Dorigo &F. Glover ,McGraw Hill, London, 1999.203-215.
[53] 莫宏伟,王科俊,金鸿章. 计算智能的融合应用研究[J].自动化技术及应用.2002(1):12-36.
[54] B. K Choi. Multiobjective Optimum Design of Rotor-Bearing Systems With Dynamic Constraints Using Immune-Genetic Algorithm[C]. Proceeding of IEEE Interntional Conference on Systems and Man and Cybernetics (SMC). Japan, 1996:108-113.
[55] 刘树林,黄文虎,夏松波,丛蕊. 活塞压缩机气阀故障检测的免疫神经网络方法研究[J]. 中国机械工程. 2005,vol. 16(15):1384-1387.
[56] 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[J]. 应用科学学. 2003,Vo1.21(1):37-38.
[57] 唐斌,胡光锐. 免疫神经网络用于侦察测向的技术[J]. 上海交通大学学报. 2002,Vo1. 36(12):1851-1853.
[58] 郑建国,刘芳,焦李成. 用免疫神经网络做数据挖掘[J]. 计算机学报. 2002 vol. 29(10):51-55.
[59] 侯家利,朱梅阶,彭宏. 模块化免疫神经网络的模型研究[J]. 电子学报. 2005,Vol 33(8):1502-1505.
[60] 黄文虎,夏松波,刘瑞岩等. 设备故障诊断原理、技术及应用[M]. 科学出版社. 1996:4-7.
[61] 姜梅. 基于生物免疫系统的计算机入侵检测技术研究[D]. 南京航空航天大学博士论文. 2001:21-23.
[62] S Forest, A S Perelson and L. Allen. Self-Nonself Discrimination in a Computer[C]. Proceedings of the IEEE Symposium on Research in Security and Provacy. Okaland, CA. 1994:202-211.
[63] D.Dasgupta, N.Majumdar. Anomaly Detection in Multidimensional Data Using Negative Selection Algorithm[C]. Procedings of the IEEE International Conference on Evolutionary Computation. Honolulu, Hawaii. 2002:1039-1044.
[64] D.Dasgupta, K.KrishnaKumar, D.Wong and M.Berry. Negative Selection Algorithm for Aircraft Fault Detection[C]. Proceedings of the Third International Conference on Artificial Immune Systems (ICARIS-2004), Catania, Italy. September 13-16, 2004.
[65] D.W.Bradley, A.M.Tyrrell. Hardware Fault Tolerance: An Immunological Solution [C]. In the proceedings of IEEE International Conference on Systems, Man and Cybernetics (SMC), Nashville. October 8-11, 2000.
[66] Zhou Ji, D. Dasgupta. Estimating the Detector Coverage in a Negative Selection Algorithm[C]. Proceedings of GECCO, Washington.D.C. 2005:1-8.
[67] F. Gonzalez, D. Dasgupta and R. Kozma. Combining Negative Selection and Classification Techniques for Anomaly Detection[C]. Proceedings of the special sessions on artificial immune systems in Congress on Evolutionary Computation, IEEE World Congress on Computational Intelligence, Honolulu, Hawaii. May 2002.
[68] 陈强,李海潮. 基于实值反向选择算法的齿轮箱异常检测[J]. 煤矿机械. 2006, vol.27 (11):173-176.
[69] Fabio Gonzalez, Dipankar Dasgupta and Luis Fernado Nino. A Randomized Real-Valued Negative Selection Algorithm[C]. In the Proceedings of Second International Conference on Artificial Immune Systems (ICARIS2003). Napier University, Edinburgh, UK. September 1-3, 2003.
[70] J. Timmis, M. Neal. A Resource Limited Artificial Immune Systems for Data Analysis[J]. Knowledge Based Systems. 2001, 14(3-4):121-130.
[71] J.Timmis, M.Neal. Investigating the Evolution and Stability of a Resource Limited Artificial Immune System[C]. Proceeding of GECCO. Las Vegas, Nevada, USA, AAAI Press. 2000:40-41.
[72] A.B.Watkins, L.C.Boggess. A Resource Limited Artificial Immune Classifier[C]. Proceedings of the International Conference on Evolutionary Computation. Honolulu, HI, USA. 2002:12-17.
[73] T.Knight, J.Timmis. A Multi-Layered Immune Inspired Approach to Data Mining[C]. Proceedings of the 4th International Conference on Resent Advances on Soft Computiong. Nottingham, UK. 2002:266-271.
[74] J.Timmis. Aivis-Artificial Immune Network Visualization[C]. Proceedings of the International Conference on Eurographics. London. 2001:61-69.
[75] L.N.Castro, F.Zuben. The Clonal Selection Algotithm with Engineering Applications[C]. Proceedings of GECCO. 2000:36-37.
[76] L.N.Castro, J.Timmis. Hierarchy and Convergence of Immune Networks: Basic Ideas and Preliminary Results[C]. Proceedings of the 1st International Conference on Artificial Immune Systems. Canterbury, UK. 2002:231-240.
[77] L.N.Castro, F. Zuben. Learning and Optimization Using the Clonal Selection Principal[J]. IEEE Transaction on Evolutionary Computation. 2002, 6(3):239-251.
[78] L.N.Castro, J.Timmis. An Artificial Immune Network for Multimodal Function Optimization[C]. Proceedings of IEEE Internatioal Conference on Evolutionary Computation. Honolulu, Hawaii. 2002:699-674.
[79] L.N.Castro, F.Zuben. A Pruning Self-Organizing Algorithm to Select Centers of Radial Basis Function Neural Networks[C]. Proceedings of the International Conference on Artificial Neural Networks and Genetic Algorithm. 2001:54-59.
[80] L.N.Castro, J.Timmis. Artificial Immune Systems: A Novel Approach to Pattern Recognition[C]. Proceedings of the International Conference on Neural Networks. 2002:67-84.
[81] L.N.Castro, J.Timmis. Artificial Immune Systems: A New Computing Intelligent Approach[M]. Springer-Verlag. London, 2002:1-20.
[82] L.N.Castro, F.Zuben. An Evolutionary Immune Network for Data Clustering[C]. Proceedings of the IEEE SBRN on Artificial Neural Networks. 2000:84-89.
[83] 边肇祺,张学工. 模式识别——第二版[M]. 北京:清华大学出版社. 2000.
[84] 徐章遂,房立清,王希武,左宪章. 故障信息诊断原理及应用[M]. 国防工业出版社. 2000.7:11-32,104-184.
[85] 王磊. 免疫进化计算理论及应用[D]. 西安电子科技大学博士研究生学位论文. 2001.
[86] 陈强,郑德玲. 一种基于人工免疫的数据模式进化学习模型及其应用研究[J]. 计算机工程与应用. 2005, 20:40-43.
[87] R.A. Fisher, Michael Marshall. http://www.ics.uci.edu/~mlearn/databases/iris/.