摘要
本论文主要研究了神经网络、灰关联度理论、遗传算法以及模糊优选理论在变压器故障诊断中的应用。文中所采用的智能算法都明显提高了变压器的故障识别率。
神经网络在故障诊断中的应用通常是采用标准BP网络。为了提高BP网络的学习效率，本文将Levenberg-Marquart(L-M)算法引入到BP网络中进行网络权值的学习。其收敛速度和稳定性都优于标准BP算法。本文将该算法用于变压器的在线实时故障诊断中，取得了较满意的效果。
利用灰色关联度可以对系统动态发展过程量化分析以考察系统诸因素之间的相关程度，其基本思想是根据曲线间相似程度来判断因素间的关联程度。在变压器的故障诊断中普遍采用油中溶解气体分析(DGA)导则推荐的三比值法。但因其比值范围不全，常导致在实际诊断过程中出现不能判断的情况。本文提出的方法可在一定程度上弥补这一缺点。
遗传算法是一种模仿生物进化过程的全局优化算法。它提供了一种求解复杂系统优化问题的通用框架，对问题的种类有很强的鲁棒性。本文在概率因果推理模型的基础上，引入模糊理论，重新建立了模糊概率因果变压器故障诊断模型，并从非线性组合优化的角度提出了该模型的遗传算法求解策略。仿真结果表明，本文提出的新方法同时提高了并发性故障和单故障的识别率。
本文提出的模糊优选法进行变压器故障诊断，是根据标准故障模式对待检模式相似的相对隶属度的大小来判断故障，比模糊平均加权模型对故障的判别更为清晰。仿真结果亦表明该方法不仅能诊断出使用三比值方法中所无法判断的故障，而且对故障的判别更为清晰。所建模型还能部分地对故障进行定位分析，这对维修策略的制定具有一定的指导意义。
This paper researches the applications of neural network, grey relation degree theory, genetic algorithm and fuzzy optimum selecting theory in transformer fault diagnosis. These intelligent algorithms used in this paper have improved the transformer fault identifying rate greatly.
Normal BP algorithm is usually used in fault diagnosis based neural network. In order to improve the learning rate of backpropagation neural network, Levenberg-Marquart algorithm was proposed to learning network optimized weight parameters. Its training speed and stability are higher than the normal BP algorithm. Levenberg-Marquart algorithm is used in transformer online fault diagnosis, acquiring satisfied result.
In order to review relation grade of system factors, the grey relation degree is used to quantifying analyse system dynamic development process. It estimates relation degree between factors according to curves analogue degree.3 ration method is usually used for transformer fault diagnosis, it sometimes can not judge fault because of its lack of enough ration codes. Grey relation degree may make up the disadvantage in some extent.
Genetic algorithm is a global optimization algorithm imitating biology evolution process. It provides a currency frame of resolving complicated system optimization problem. A fuzzy probability reasoning model for transformer faults diagnosis is rebuilded based on probability reasoning and fuzzy theory. A GA resolvent for the model is put forward from the point of nonlinear combinatorial optimization view. The result of simulation shows the new method has improved the identifying rate of single and multi faults.
According to the relative membership degree of normal fault mode to
needing checking mode, fuzzy optimum selecting theory is application
to transformer fault diagnosis. It may judge fault more explicit than fuzzy even weight model. The result of simulation shows the method may diagnose not only these faults that cann t be diagnosed by using 3 ratio method but also judge fault more explicit. The model may analyze oriently to faults partly, that is a guidance to servicing.
引文
1. Eberhart R C, Dobbins R W. Neural network PC tools. New York:Academic Press, 1990
2．张立明．人工神经网络的模型及其应用[M]．上海：复旦大学出版社，1993
3．罗发龙，李衍达．神经网络信号处理[M]．北京：电子工业出版社，1993
4．焦李成．神经网络系统理论[M]．西安：西安电子科技大学出版社，1996
5．虞和济，陈长征，张省，周建男．基于神经网络的智能诊断[M]．北京：冶金工业出版社．
6．师汉明，陈吉红．人工神经网络及其在机械工程领域中的应用[J]．中国机械工程，1997，8(2)：5～10．
7．杨天奇，邵惠鹤．基于神经专家系统的故障诊断方法[J]．系统共同理论方法应用．1995，4(1)：18～23
8. Sorsa T, Heikki N.Koivo.Neural Network in Process Fault Diagnosis[J]. IEEE Transactions on System,Man, and Cybernetics. 1991,21(4): 815～8
9．周东华，叶银忠．现代故障诊断与容错控制[M]．北京，清华大学出版社．2000．
10. Hagan M T, Men haj M B. Training feed forward netword networks with the Marquardt algorithm.[J]IEEE trans Neural net, 1994,5(6): 989-993.
11．楼顺天，施阳．基于MATLAB的系统分析与设计-神经网络[M]．
12．邓聚龙．社会经济灰色系统的理论与方法．中国社会科学，1984(6)：47-60
13．李宝林等．棉蚜虫生物防治灰色模型．大自然探索，1984(3)：37-43
14. Zhou Chao Shun, Deng Julon.The Stability of Grey Linear Systems.Inter. J. Control, 1986(1): 313-320
15．祝海林，等．液压系统故障诊断的灰色理论方法探讨[J]．石油化工高等学校学报，1998，11(3)：55—59
16．邓聚龙．灰色控制系统(第二版)[M]．武汉，华中理工大学出版社．1997
17．水乃翔，董太亨，沙震．关于灰关联的一些理论问题．系统工程，10(6)：23-26
18．1SD187-86变压器油中溶解气体分析和判断导则．水电部标准[S]
19．张绍良，张国良．灰色关联度计算方法比较及其存在问题分析[J]．系统工程，1996．14(3)：45-48
20．谢科范．评灰色系统理论．系统工程，1991，9(4)：49-52
21．陈国良，王法，庄镇泉，王东生．遗传算法及应用[M]．北京：人民邮电出版社，1996
22. Holland J H. Adaption in Natural and Artificial System. MIT Press, 1975
23. Billings S A and Mao K Z. Structure detection for nonlinear rational models using genetic algorithms [J]. Int.J. of System Science, 1998,29(3):223-231
24. Farag W A, Quintana V H, Lambert-Torres G.A genetic-based neuro-fuzzy approach for modeling and control of dynamical systems[J]. IEEE Trans. On Networks, 1995 9(5): 756-767
25. Park D, Kandel A, langholz G. Genetic-based new fuzzy reasing models with application to fuzzy control[J]. IEEE Trans. On Syst. Man, Cybern, 1994, 24: 39-47
26. Homaifar A , McCormick E. Simultaneous design of membership functions and rule sets for fuzzy controllers using genetic algorithms[J]. IEEE Trans. Fuzzy Syst, 1995, 3(2): 129-139
27. Ishibuchi H , Nozaki K , yamamoto N, Tanaka H. Selecting fuzzy if-then rules for classification problems using genetic algorithms[J]. IEEE Trans. Fuzzy Syst, 1995,3:260-270
28．王道勇．变压器故障检测方法的改进——模糊识别阈值原则法[J]．电力系统自动化．1998，11(22)：44-46
29．杨莉，尚勇，等．基于概率推理和模糊数学的变压器综合故障诊断模型[J]．中国电机工程学报 2000，7(20)：19-23
30. Reggia J A, et al. A formal model of diagnosis inference[J].Information Science, 1985,37:227-285
31. Peng Y, Reggia J.A probabilistic causal model for diagnostic problem solving—part Ⅰ:integrating symbolic causal inference with numeric probabilistic inference[J]. IEEE Trans. SMC, 1987,17(3):146-162
32. Peng Y, Reggia J.A probabilistic causal model for diagnostic problem solving—part Ⅱ:diagnostic strategy[J].IEEE Trans. SMC, 1987, 17(3): 395-406
33．DL／T596-1996电力设备预防性试验规程．中华人民共和国电力行业标准[S]．
34．李杰．中小型电力变压器故障模式与可靠性运行[J]．变压器．1997，4(34)：10-12
35．张曾科．模糊数学在自动化技术中的应用[M]．北京：清华大学出版社，1997．
36．王平．基于模糊综合评判的变压器故障诊断法[J]．电力系统自动化．1996，20(12)：30-33．
37．周明，任建文，李庚银，徐开理．基于模糊推理的分布式电力系统故障诊断专家系统[J]．电力系统自动化．2001，25(24)：33-36．
38．徐文，王大忠，周泽存，李益民．模糊辨识在电力设备故障诊断中的应用[J]．电力系统自动化．1996，20(3)：45-49．
39．陈守煜．系统模糊决策理论与应用[M]．大连理工大学出版社．1994．
40．陈守煜，赵瑛琪．模糊优选理论与模型[J]．应用数学．1993，6(1)：1-5．
41．杨苹，吴捷，冯永新．200MW汽轮发电机组振动故障的模糊诊断系统[J]．电力系统自动化．2001，25(1)：45-49．
42．杨沁，施文康．(Yang Qin，Shi WenKang)．变压器故障的模糊检测[J]变压器．1998，35(2)：32-35．