用户名: 密码: 验证码:
基于神经网络专家系统的电机故障诊断研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
针对交流电机的故障特点,列举并分析了交流电机在实际工况下的典型振动故障和定子电流故障,对各种故障的原因和所表现出的振动、电流、频率特性进行了详尽的研究,并根据电机的特点列出了交流电机故障诊断知识库,为故障诊断打下了基础。
     在基于知识的传统专家系统的基础上,提出了一种新的电机故障诊断专家系统模式——基于神经网络(NNES)的专家系统,克服了传统专家系统不能进行自学习、自适应的缺陷。
     针对交流电机的故障特点,将反映故障的振动、电流、频率信号进行处理,以能更好的反映故障的随机性和不确定性。在本系统中,选用的是BP反向传播和Kohonen自适应算法,利用神经网络学习算法获取知识,通过神经网络的连接模型表示知识,以充分利用神经网络学习能力的优势。在传统专家系统方法中,知识是通过符号以某种数据结构来表示的。本方法将电机故障知识库信息分布到神经网络的网络结构、权值和阈值中,从而可以较好地表示专家知识。
     在研究的过程中,首先根据故障的知识库建立合适的神经网络,并进行学习和训练,达到所需的精度后,对所输入的信号进行故障诊断,从而得出正确的诊断结果。经过实际的电机故障诊断,证明了本方法的正确性和容错性,并显示出了优于传统专家系统的特点。
In this paper, the classical vibration and stator current faults of the AC electromotor under the practical circumstance are lifted and analyzed, the characters of vibration and stator current faults are studied in detail, the corresponding repository of the AC electromotor is also listed, it is the base of studying the fault diagnose on AC electromotor.
    On the base of the studying traditional Expert system, a new Expert system
    mode on the fault diagnose of AC electromotor ------ the Neural network Expert
    system is put forward, it will conquer the limitation of the traditional Expert system, such as can not self-study, self-adaption.
    The signals of vibration, current and frequency are deal with to reflect the randomicity and uncertainty of the fault freely. In this
    system, the BP and Kohonen neural network are selected to capture the information. The modes of the neural network are used to express the knowledge, so the superiority of self-study of Neural network can be used sufficiently. The knowledge in traditional Expert system is expressed by a kind data structure. On contrast to the traditional Expert system, the new method can distribute the information of repository to the value of weight and threshold of the Neural network, the knowledge of expert can be expressed preferably.
    During the studying Expert system, the very Neural network must be created firstly, then it should be trained, when the reach precision that we need, we can input the signal to diagnose fault. The practical diagnose proved that our method is correct and precede the traditional Expert system.
引文
[1]吴金培.模糊诊断理论及其应用.北京:科学出版社,1995
    [2]Beck Ms,Williams R A.Process Tomography. A European Innovation and Its Applications.Measurement Science & Technology, 1996,7(3):215~224.
    [3]Yvind Isaksen A Review of Reconstruction Techniques for Capacitance Tomography:Measurement Science & Technology, 1996, 7(3): 325~337.
    [4]李宏,刘江涛.主观Bayes方法与神经网络相结合的多传感器数据融合空间点目标识别方法.红外与毫米波学报,1997,16(6)
    [5]滕召胜.基于多传感器数据融合的热处理炉温度测量方法.计量学报,2000,21(2):148~152.
    [6]罗志增,蒋静萍.应用模糊信息融合实现目标物体的分类.仪器仪表学报,1999,20(4):401~404.
    [7]王婷杰,施惠昌.一种基于模糊理论的一致性数据融合方法.传感器技术,1999,18(6):50~53.
    [8]吴成东,刘宗富.多传感器数据最优融合.传感器技术,1994(3):21~24.
    [9]张智星,孙春在.神经-模糊和软计算.西安:西安交通大学出版社,2000:238~259
    [10]LIF, Uncertainty in Artificial Intelligence, Beijing: Meteorology Press(李凡.人工智能中的不确定性,北京:气象出版社)
    [11]赵振宇,徐用懋.模糊理论和神经网络的基础与应用.北京:清华大学出版社,1996
    [12]滕召胜,郁文贤.数据融合技术在储粮水分自动测试系统中的应用.应用科学学报,199,17(4)
    [13]杨淳.模糊优化在测量领域中的应用研究.仪表技术与传感器,2000(12)
    [14]徐爱钧.基于模糊推理决策的智能化多点温度巡回检测系统.工业仪表与自动化装置,2000(4)
    [15]宋国民.基于模糊推理的多维传感器解耦算法研究.工业仪表与自动化装置,2001(1)
    [16]施惠昌.一种利用函数链神经网络的传感器建模新方法.传感器技术,2000,19(3)
    [17]马常霞.基于传感器阵列与前馈神经网络的气体辨识系统.测控技术,2001,20(3)
    [18]张立明.人工神经网络的模型及其应用.上海:复旦大学出版社,1994
    [19]吴祖堂.基于神经网络预测器的传感器数据证实实现技术研究,电子技术应用,2001(1)
    
    
    [20]张士峰,蔡洪.Bayes分析中的多源信息融合问题.系统仿真学报,2000,12(1)
    [21]蒙以正.MATLAB5.X应用与技巧.北京:科学出版社:1999:144~167
    [22]徐昕,李涛,伯晓晨.Matlab工具箱应用指南.北京:电子工业出版社,2000:276~238
    [23]侯北平,卢佩.基于MATLAB的BP神经网络建模及系统仿真.自动化与仪表,2001(1)
    [24]朱文,侯北平.基于MATLAB的自适应神经-模糊控制器的设计与计算机仿真.2001全国计算机仿真学术会议论文集
    [25]沈清,胡德文.神经网络应用技术.长沙:国防科技大学出版社,1993
    [26]胡守仁.神经网络导论.长沙:国防科技大学出版社,1993
    [27]王永庆.人工智能原理.西安交通大学出版社,1994
    [28]杨叔子.基于知识的诊断推理.北京:清华大学出版社,1997
    [29]刘有才,刘增良.模糊专家系统原理与设计.北京:北京航空航天大学出版社
    [30]万建伟.一种新的采用神经网络的图象分类方法研究.系统工程与电子技术,1995(2)
    [31]吴金培.故障诊断专家系统的一种新的设计方案.振动、测试与诊断,1996(4)
    [32]吴金培.模糊时间序列模型的辨识.模糊系统与数学,1995(4)
    [33]杨建刚.改进BP网络在旋转机械诊断中的应用.振动工程学报,1999(4)
    [34]张良杰.模糊神经网络技术的新近进展.信息与控制,1995(1)
    [35]谭民.神经元网络在故障诊断中的双向联想记忆法,自动化学报,1991(1)
    [36]张杰.专家系统的发展及其在化工生产中的应用.化工自动化及仪表,1996(3)
    [37]王飚舵.基于专家系统和神经网络的机车电路故障诊断系统研究.北方交通大学学报:1996(4)
    [38]沈建强,李平.神经模糊技术的现状与发展.控制与决策,1995(5)
    [39]张雪江.气轮发电机组故障诊断专家系统知识处理技术的研究.振动工程学报,1996(3)
    [40]阎平凡.人工神经网络的容量、学习与计算复杂性.电子学报,1995(5)
    [41]王继成.一个基于规则的神经网络系统.电子学报,1995(2)
    [42]张铃.神经网络中的BP算法分析.模式识别与人工智能,1994(3)
    [43]关惠玲.故障诊断的模糊神经网络模型.振动工程学报,1997(4)
    [44]关惠玲.捕获设备故障信号的神经网络模型.振动、测试与诊断,1998
    [45]关惠玲.模糊神经网络故障诊断专家系统.郑州工学院学报,1997(1)
    
    
    [46] Wu J.P.(吴今培),A Fuzzy Diagnosis Method for the Diesel Engine,Proceedings of the International Conference on structural Dynamics,Vibration,Noise and Control,Hong Kong Polytechnic University, pp. 1316-1321,Dec. 1995.
    [47] Fu L.M., Rule Generation from Neural Networks,IEEE Trans.on SMC,Vol.24, No.8, pp.1114-1124,1994.
    [48] Frederick W.R. and Michael L.D.,Human Congnition and the Expert System Interface:Mental Models and Inference Explanations, IEEE Trans.on SMC,Vol.23,No.6, pp.1649-1661,1993.
    [49] Si-Zhao Q., Hong-Te S.and Thomas J.M.,Comparison of Four Neural Net Learning Methods for Dynamics System Identifacation, IEEE Trans. on Nns, Vol.3, No.1, pp.122-130, 1992.
    [50] Buckley J.J. and Hayashi Y. Fuzzy Neural Networks: A Survey, Fuzzy Sets and Systems Vol.66, No.1, pp.1-13, 1994.
    [51] Huang J.X.et al.,Fuzzy Art Properties,Neural Networks,Vol.8,No.2,pp. 203-213,1995.
    [52] Sushmita. M.and Sankar K.P.,Fuzzy Multi-Layer Perception,Inferencing and Rule Generation,IEEE Trans.on Nns,Vol. 6,No.1 pp.51-63,1995
    [53] Tang Z.Y. and Gary J.K., Deterministic Global Optimal FNN Training Algorithms, Neural Networks,Vol.7,No.2,pp.301-311,1994.
    [54] Sushmita M. and Sankar K.p.,Logical Operation Based Fuzzy MLP for Classification and Rule Generation,Neural Network,Vol.7,No.2,pp.353-373,1994
    [55] Vincent W.P. et al, Alternative Neural Network Training Methods, IEEE Expert, pp.16-22, 1995.
    [56] Chung F.L. and Lee T., Fuzzy Competitive Learning, Neural Networks,Vol.7, No.3, pp.539-551,1994.
    [57] Benedikt K.H.,Improving Back Propagation with a New Error Function,Neural Networks,Vol.7,No.8, pp.1191-1192,1994.
    [58] Ronald R.Y.,Modeling and Formulating Fuzzy Knowledge Bases Using Neural Networks,Neural Networks, Vol.7, No.8, pp.1273-1283, 1994.
    [59] Kosko B., Fuzzy Associative Memories,In A.Kandel(ed).fuzzy Expert System Reading,MA:Addison Wesley, 1987.
    [60] Kosko B., Neural Networks and Fuzzy Systems,Prentice Hall,Inc. 1992.
    [61] Gallant S.I.,Connectionist Expert Systems,Communications of the AcM,Vol.31, No.2, pp.152-169, 1988.
    [62] Funahashi K., On the Approximate Realization of Continuous Mappings by
    
    Neural Networks, Neural Networks,Vol.2,No.1,pp.183-192,1989.
    [63] 电机工程手册编辑委员会.电机工程手册第4卷.北京:清华大学出版社,1996
    [64] 李颂论.电气测量技术.西安:西北工业大学出版社,1992
    [65] 徐伯雄.电机量测.北京:清华大学出版社,1996
    [66] 刘彦清.电机结构.北京:机械工业出版社,1992
    [67] 沈标正.大型电机安装与维修.北京:机械工业出版社,1986
    [68] 应善成.船用电机负载噪声声强法测定,杭州:浙江大学,1990
    [69] 陈永校.采用声强法对660KW异步电机进行现场声功率测定.杭州:浙江大学,1995
    [70] 俞鑫昌.低噪音电机.北京:北京电机工程委员会,1990
    [71] Girosi F., Regularization Theory and Neural Networks Architectures, Neural Computation, Vol.7, pp.219-269, 1995.
    [72] Connor J. t. et al, Recurrent Neural Networks and Robust Time Series Prediction, IEEE Trans. on Nns, Vol.5, No.2, pp.240-254, 1994.
    [73] Brooks R.A., Intelligence without Representation, Artificial Intelligence, Vol.47, pp.139-159, 1991.
    [74] Peng Y. and Reggia J.A., Diagnostic Problem Solving with Causal Chaining, Int. J. Intelligence System, Vol.2, pp.265-302, 1987.
    [75] Reggia J.A.et al., A Formal Model of Diagnosis Inference-Part Ⅰ: Problem Formulation and Decomposition, Information Sci., Vol.37, pp.227-256,1985.
    [76] Shafer G., A Mathematical Theory of Evidence, Princeton Univ. Press., 1976.
    [77] Botanna F. and Bahamonde A., Shape: A Machine Learning System form Examples, Int. J. Human Computer Studies,Vol.42, pp.137-155, 1995.
    [78] Lansdale M., New Method for Discovering Rules from Examples, Man-Machine Studies, Vol.36, pp.127-143, 1992
    [79] Davis R. and Lenat D., Knowledge-based System in Artificial Intelligence, Mc-Graw-hill, New York, 1980.
    [80] Winston P.H., Artificial Intelligence, Second Edition, Addison-Wesley, 1984.
    [81] Fink P.K. and Lusth J.c., Expert System and Diagnostic Expertise in the Mechanical and Electrical Domains, IEEE Trans. on SMC, Vol.17, No.3, pp.340-349, 1987.
    [82] 王士同.神经模糊系统及其应用.北京:北京航天航空出版社,1997
    [83] 赵振宇.模糊理论和神经网络的基础与应用.北京:清华大学出版社,1996
    [84] 张良杰.智能控制的模糊神经技术的研究与展望.电子学报,1995(8)
    
    
    [85] 刘增良,刘有才.模糊逻辑与神经网络.北京:北京航空航天大学出版社,1996
    [86] 刘叙华.模糊逻辑与模糊推理.长春:吉林大学出版社,1996
    [87] 应行仁.采用BP神经网络记忆模糊规则的控制.自动化学报,1991(2)
    [88] 王士同.问题求解的人工智能与神经网络方法.北京:气象出版社,1995。

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700