摘要
电力变压器故障诊断对电力系统的安全运行有着十分重要的意义。本文在广泛收集变压器故障诊断专家知识和经验的基础上，讨论变压器故障原因、种类以及检测与判断流程，总结现有的诊断方法，提出了基于信息融合的多层分布式推理机制的变压器故障诊断专家系统的思路与实现方法。该系统以国内外公认的油中溶解气体分析作为诊断内部潜伏性故障的主线，结合各种相应的试验项目（预防性试验、油务试验等）进行综合诊断，确定故障的大体部位。专家系统知识库包括：由针对各类试验项目组成的基本规则与复合规则；隐含分布于组合混沌神经网络中的诊断规则；各类变压器故障实例组成的源范例。采取正向推理与混沌神经网络模型相结合并与范例推理相互验证的推理机制弥补了单一方式的不足。本文深入研究了人工神经网络在变压器故障诊断中的应用，对目前最常采用的BP算法做出了较大改进，在原有算法中引入混沌动力学原理构造了混沌神经网络BP算法，并提出了训练样本集的预处理方法，在仿真训练中取得了满意的效果。结合菏泽电业局具体软件工程项目，开发了基于B/S架构的软件应用系统，达到了变压器远程诊断与状态检修的目的。
Power transformer fault diagnosis is vital to power system safe operating. After discussing transformer fault cause, fault type and diagnostic procedure, this paper summarizes existing diagnosis method and puts forward idea of transformer fault diagnosis expert system based on multilayer distributed reasoning mechanism on the basis of collecting extensively expert knowledge and experience. The dissolve gas analysis method which adopted widely at home and abroad is used as dominant idea to diagnose internal incipient fault. Synthetical diagnosis on the basis of combining all kinds of relevant tests make a decision for the fault position. Tests include routine test for oil and preventive test for transformer. The knowledge base includes diversified rules, such as basic and complex rule composed of vary tests item, diagnosis rule that distributed impliedly over combined chaos neural network and the transformer fault case. It supply a gap of single way to adopt the reasoning mechanism cooperated with case-based reasoning and the combination of positive reasoning and chaos neural network model. After researching the application of artificial neural network to fault diagnosis of transformer, the back propagation algorithm is improved observably. Inducting chaos dynamics principium to create chaos neural network back propagation algorithm and using the pretreatment of training sample, the emulation program show that this method is effective. Combining the software engineering project of Heze power supply bureau, the system software is developed which based on browser/server structure. A condition based maintenance transformer fault diagnosis expert system software on internet is presented.
引文
[1]. 杨以涵,唐国庆,高曙. 专家系统及其在电力系统中的应用. 中国电力出版社, 1995
[2]. 陈丽安,张培铭,雷德森. 人工智能在电气设备中的应用现状与前景展望. 电网技术, 2000,24(7):21-24
[3]. 韩祯祥,文福拴,张琦. 人工智能在电力系统中的应用. 电力系统自动化,2000, 25(1):2-10
[4]. 谢峰,刘民. 电力变压器故障诊断专家系统研究现状及开发前景. 山东电力技术, 1998,5:25-28
[5]. Lin C E, Ling J M, Huang C L. An expert system for transformer fault diagnosis using dissolved gas analysis [J]. IEEE Trans on Power Delivery, 1993,8(1)
[6]. 张建文,赵大光,董连文. 基于模糊数学的变压器故障诊断专家系统. 高电压技术, 1998 ,24(4):6-9
[7]. 孟大伟,温祥龙. 电力变压器的故障诊断专家系统. 黑龙江电力技术, 1999.21(2):33-37
[8]. 李天云,应鸿,陈化钢. 人工神经网络在变压器故障诊断中的应用. 高电压技术, 1996, 22(4):58-60
[9]. Zhang Y. An artificial new network approach to transformer fault diagnosis [J]. IEEE Transactions on Power Delivery, 1996,11(4):1836-1841.
[10]. 蔡超豪. 利用人工神经网络对电力变压器故障进行早期诊断. 中国电力,1997,30(1): 66-67
[11]. 赵浩波. 人工神经网络在电力变压器色谱分析应用中的探讨. 山西电力技术,1998(2):53-56
[12]. 徐勇,林峰. 基于小波神经网络的变压器PD故障诊断模型的研究. 湖南大学学报,2000,27(4):72-75
[13]. 徐洪波,王科俊,金鸿章,李国斌. 一种基于模糊神经网络的专家系统推理的方法. 黑龙江自动化技术与应用, 1999,18(5):11-13
[14]. 杨莉,尚勇,周跃峰,严璋. 基于概率推理和模糊数学的变压器综合故障诊断模型. 中国电机工程学报, 2000,20(7):19-23
[15]. 张冠军,钱政,严璋. 变压器绝缘诊断中的ISODATA法. 高电压技术, 1999,25(1):1-3
[16]. 杨沁,施文康. 变压器故障的模糊检测. 变压器, 1998, 35(2):32-35
[17]. 于海斌,薛劲松,王浩波. 混合专家系统的研究与进展. 系统工程理论与实践,1997(8):43-50
[18]. A neural expert system concept applied to diagnostics Drabarek, J.; Wirski, R. Electronics, Circuits and Systems, 2001. ICECS 2001. The 8th IEEE International Conference, 2001 Page(s): 1301-1304 vol.3
[19]. A neural model for multi-expert architectures Toussaint, M. Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on, 2002 Page(s): 2755-2760 vol.3
[20]. 张建文. 电力变压器故障诊断方法分析. 煤矿机电, 1999,3:6-9
[21]. 操敦奎. 变压器油中气体分析与诊断. 湖北省电力试验研究所, 1987
[22]. 电力工业部. 电力设备预防性试验规程(DL/T596-1996). 1996
[23]. 严璋. 电气绝缘在线检测技术. 北京: 水利电力出版社, 1995
[24]. 阳少军,肖登明. 变压器色谱在线监测的新型传感器. 高电压技术, 2002,28(1):30-31
[25]. 肖长春. 色谱、绝缘在线监测系统在变压器中的应用. 高电压技术, 2001,27(5):73-74
[26]. 张利刚. 变压器油中溶解气体的成分和含量与充油电力设备绝缘故障诊断的关系, 变压器, 2000,37(3):39-42
[27]. 倪健. 变压器内部潜伏性故障的诊断方法, 高压电器, 2001,37(3):54-55
[28]. 董明,赵文彬,严璋. 油气分析诊断变压器故障方法的改进. 高电压技术, 2002,28(4):6-8
[29]. IEC60599. Mineral oil-impregnated electrical equipment in service- guide to the interpretation of dissolved and free gases! analysis, second edition. 1999
[30]. Michel Duval, A lfonso de Pablo. Interpretation of gas- in-oil analysis using new IEC publication 60599 and IEC TC10 database. IEEE Electrical Insulation Insulation Magazine, 2001, (17):2-31
[31]. 李义仓. 变压器油中和与绝缘材料劣化的关系与故障诊断. 华东电力, 1993，21(2):16-19
[32]. 张冠军,钱政,严璋. DGA技术在电力变压器绝缘故障诊断中的应用与进展. 变压器,1999,36(1):30-34
[33]. 施鸿宝,王秋荷. 专家系统. 西安交通大学出版社, 1990
Dissolved gas analysis: It can save your transformer Duval, M. IEEE Electrical Insulation
[34]. Magazine, Volume: 5 Issue: 6 , Nov.-Dec. 1989 Page(s): 22-27
[35]. Electrical insulation diagnostic method and maintenance criteria for oil-immersed power transformers Okubo, H.; Kobayashi, S.; Aoshima, Y.; Takagi, H.; Mori, E.; Ikeda, M.; Kishi, A. Dielectric Liquids, 1999. (ICDL '99) Proceedings of the 1999 IEEE 13th International Conference on , 1999 Page(s): 372-377
[36]. Study of machine fault diagnosis system using neural networks Hayashi, S.; Asakura, T.; Sheng Zhang Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on , 2002 Page(s): 956-961 vol.1
[37]. 王大忠,徐文,周泽存,陈珩. 模糊理论、专家系统及人工神经网络在变压器故障诊断中的应用–基于油中溶解气体进行分析诊断. 中国电机工程学报, 1996,16(5):349-353
[38]. Lin CE, Ling J M, Huang C L. An expert system for transformer fault diagnosis using dissolved gas analysis [J]. IEEE Transactions on Power Delivery, 1993,8(1):231-238.
[39]. Wang Z Y. A combined ANN and expert system tool for transformer fault diagnosis [J]. IEEE Transactions on Power Delivery, 1998,13(4):1224-1229.
[40]. Chow M et al. On the application and design of artificial neural networks for motor fault detection, IEEE Trans. Ind. Electron, 1991, 38(6): 448-453
[41]. 黄德双. 神经网络模式识别系统理论. 电子工业出版社, 1996
[42]. 李众立,王成瑞. 神经网络自适应学习步长研究. 电子科技大学学报,1996,25(6):644-648
[43]. 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
[44]. 关惠玲,韩捷. 设备故障诊断专家系统原理及实践. 机械工业出版社, 2000
[45]. 阎平凡,张长水. 人工神经网络与模拟进化计算. 北京:清华大学出版社, 2000
[46]. 刘镇清. 一种改进的人工神经网络学习算法及其在超声检测中的应用. 声学技术, 2000,19(4):179-181
[47]. 叶春,忻建华. 基于BP网络的热力系统参数仿真. 上海交通大学学报, 1999,33(3):301-304
[48]. 唐巍,李殿璞. 电力系统经济负荷分配的混沌优化算法. 中国电机工程学报, 2000, 20(10):36-39
[49]. 顾玉巧. 人工神经网络中的非线性动力学及其应用. 天津:南开大学, 1999
[50]. 李维. Delphi 5.x分布式多层应用系统篇. 机械工业出版社,2000