变压器故障综合诊断专家系统的研究与实现
|
摘要
电力变压器是电力系统的重要电气设备,其运行状态直接影响着电力系统的安全性。因此,及早发现变压器潜伏性故障,是电力部门关注的一个重要问题。借助专家系统和模糊理论等技术可以有效地实现变压器故障诊断的智能化,促进变压器故障诊断技术研究成果的快速、有效转化。
以油中溶解气体分析结果为特征量,利用三比值法对变压器进行故障诊断是一种十分广泛且有效的方法。本文在三比值法的基础上,利用人工智能相关技术构建了一个变压器故障综合诊断专家系统。该专家系统综合了基于产生式规则的诊断、模糊诊断和可视化诊断。当气体含量比值不在三比值法编码边界处时,采用基于产生式规则的方法进行快速诊断；当气体含量比值在编码边界处时,采用模糊诊断法以提高诊断准确率。进一步,为了使用户能更清晰、直观地观测到变压器当前运行故障在故障空间中的位置,该综合诊断专家系统同时给出了可视化立体图示法和杜威(Duval)三角形法。这两种方法降低了模糊诊断方法所需要的计算负载,且杜威(Duval)三角形法总能给出一种辅助诊断结果。
实例证明,本文提出的变压器故障综合诊断专家系统,能够有效避免采用单一变压器故障诊断方法带来的诊断出错和得不出诊断结果等问题。并且,对于部分判断结果可以用该专家系统中的三种方法进行相互验证,从而提高诊断的准确性。
Power transformer is important electrical equipment in the electrical system, and the running status of the transformer affects directly the safety of the electrical system. Therefore, it is vital for electrical department to find out the potential faults of the transformer as soon as possible. With aids of the expert system and the fuzzy theory, the intelligent transformer fault diagnosis is achievable. And the intelligent realization accelerates the engineering application of the research results of the transformer fault diagnosis.
In general, the IEC-three ratio method is an effect method to be used in the transformer fault diagnosis based on the dissolved gases analysis (DGA) results. In this thesis, a novel transformer fault diagnosis method is presented by combining the IEC three-ratio method and the artificial intelligence techniques. The proposed method constructs a transformer fault integrated diagnosis expert system consisting of the IEC three-ratio method based on production rule, fuzzy diagnosis, and visual technique. In this expert system, the IEC three-ratio method based on production rule is used when the gas ratio is far from the three-ratio bounds, while the fuzzy diagnosis is utilized to increase the probability of correct diagnosis when the gas ratio lies in the three-ratio bounds. Furthermore, in this expert system, we present the visualized cubic schema method and visualized Duval triangular schema method to make the subscriber have a clean and intuitionistic view of the position of the transformer faults. In fact, the two visualized method can decrease the computational load of the fuzzy diagnosis, and the visualized Duval triangular schema method can always give an assistant diagnosis result.
Simulation results are also given to validate the proposed integrated diagnosis expert system. In particular, the proposed integrated diagnosis expert system can decrease effectively the probability of wrong diagnosis and avoid the problem of having no diagnosis results. Further, we can use the three methods in the expert system to check some diagnosis results simultaneously, which will result in an increased probability of correct diagnosis.
以油中溶解气体分析结果为特征量,利用三比值法对变压器进行故障诊断是一种十分广泛且有效的方法。本文在三比值法的基础上,利用人工智能相关技术构建了一个变压器故障综合诊断专家系统。该专家系统综合了基于产生式规则的诊断、模糊诊断和可视化诊断。当气体含量比值不在三比值法编码边界处时,采用基于产生式规则的方法进行快速诊断；当气体含量比值在编码边界处时,采用模糊诊断法以提高诊断准确率。进一步,为了使用户能更清晰、直观地观测到变压器当前运行故障在故障空间中的位置,该综合诊断专家系统同时给出了可视化立体图示法和杜威(Duval)三角形法。这两种方法降低了模糊诊断方法所需要的计算负载,且杜威(Duval)三角形法总能给出一种辅助诊断结果。
实例证明,本文提出的变压器故障综合诊断专家系统,能够有效避免采用单一变压器故障诊断方法带来的诊断出错和得不出诊断结果等问题。并且,对于部分判断结果可以用该专家系统中的三种方法进行相互验证,从而提高诊断的准确性。
Power transformer is important electrical equipment in the electrical system, and the running status of the transformer affects directly the safety of the electrical system. Therefore, it is vital for electrical department to find out the potential faults of the transformer as soon as possible. With aids of the expert system and the fuzzy theory, the intelligent transformer fault diagnosis is achievable. And the intelligent realization accelerates the engineering application of the research results of the transformer fault diagnosis.
In general, the IEC-three ratio method is an effect method to be used in the transformer fault diagnosis based on the dissolved gases analysis (DGA) results. In this thesis, a novel transformer fault diagnosis method is presented by combining the IEC three-ratio method and the artificial intelligence techniques. The proposed method constructs a transformer fault integrated diagnosis expert system consisting of the IEC three-ratio method based on production rule, fuzzy diagnosis, and visual technique. In this expert system, the IEC three-ratio method based on production rule is used when the gas ratio is far from the three-ratio bounds, while the fuzzy diagnosis is utilized to increase the probability of correct diagnosis when the gas ratio lies in the three-ratio bounds. Furthermore, in this expert system, we present the visualized cubic schema method and visualized Duval triangular schema method to make the subscriber have a clean and intuitionistic view of the position of the transformer faults. In fact, the two visualized method can decrease the computational load of the fuzzy diagnosis, and the visualized Duval triangular schema method can always give an assistant diagnosis result.
Simulation results are also given to validate the proposed integrated diagnosis expert system. In particular, the proposed integrated diagnosis expert system can decrease effectively the probability of wrong diagnosis and avoid the problem of having no diagnosis results. Further, we can use the three methods in the expert system to check some diagnosis results simultaneously, which will result in an increased probability of correct diagnosis.
引文
[1]孙才新,陈伟根,李俭.电气设备油中气体在线监测与故障诊断技术[M].北京：科学出版社,2003.1-11.
[2]Mizutani Yoshinobu, Takahashi Tsuguhiro, Ito Testuo. Lifetime evaluation method for pole transformer based on transient temperature analysis[J]. IEEE Transactions on Power and Energy.2007,127(5).653-658.
[3]Ward, A.Sayed. Evaluating transformer condition using DGA oil analysis[C]. Conference on Electrical Insulation and Dielectric Phenomena(CEIDP), Annual Report.2003,10.463-468.
[4]石荣德,赵廷弟.故障诊断专家系统[J].北京航空航天大学学报.1995,21(4).7-12.
[5]高文胜,严璋,谈克雄.基于油中溶解气体分析的电力变压器绝缘故障诊断方法[J].电工电能新技术.2000,19(1).22-26.
[6]Morais R.M, Mannheimer W.A, Carballeira M. Furfural analysis for assessing degradation of thermally upgraded papers in transformer insulation[J]. IEEE Transactions on Dielectrics and Electrical Insulation.1999,6(2).159-163.
[7]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[J].变压器.1999,36(1).30-34.
[8]Ning Gao, Zhang Yan. New approach on comprehensive diagnosis of insulation faults in power transformer[C]. Conference Record of the 2002 IEEE International Symposium on Electrical Insulation.2002,4.203-206.
[9]宋斌,于萍,罗运柏.变压器油状态监测的专家系统及应用研究[J].变压器.1998,35(12).27-30.
[10]Tomsovic K, Tapper M, Ingvarsson T. A fuzzy information approach to integrating different transformer diagnostic methods [J], IEEE Transactions On Power Delivery.1993,8(3).1638-1646.
[11]Eulalia Szmidt, Janusz Kacprayk. Intuitionism fuzzy sets for the softening of group decision making models[C]. The International Conference on System Science.2001,2.237-240.
[12]Shyi-Ming Chen. Fuzzy group decision making for evaluating the rate of aggregative risk in software development[J]. Fuzzy Sets and System.2001, 118(1).75-83.
[13]L.H Chen, H.W Lu. An approximate for ranking fuzzy numbers based on left and right dominance[J]. Computer and Mathematics with Application.2001, 41(12).1589-1602.
[14]Shu-Hsien Liao. Expert system methodologies and applications-a decade review from 1995 to 2004[J]. Expert Systems with Application.2005,28(1).93-103.
[15]徐文,王大忠,周泽群.基于模糊理论的变压器故障诊断专家系统[J].电力系统自动化.1995,19(6).32-35.
[16]符杨,江玉蓉,崔椿洪.基于模糊数学和概率论的变压器故障诊断[J].高电压技术.2008,34(5).1040-1044.
[17]Zhiyong Wang, Chuangxin Guo, Quanyuan Jiang. A fault diagnosis method for transformer integrating rough set with fuzzy rules [J]. Transactions of the Institute of Measurement and Control.2006,28(3).243-251.
[18]王道勇.变压器故障检测方法的改进[J].电力系统自动化.1998,22(11).44-48.
[19]Takeki Nogami, Yoshihide Yokoi, Hideo Ichiba. Gas discrimination method for detecting transformer faults by neural network[C]. IEEE World Congress on Computational Intelligence.1994,6.3800-3805.
[20]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[J].湖南大学学报.2000,27(4).72-75.
[21]王楠,律方成,刘云鹏.粗糙集理论在电力变压器故障诊断中的应用[J].华北电力大学学报.2003,30(4).21-25.
[22]Yann-Chang Huang, Chao-Ming Huang. Evolving wavelet networks for power transformer condition monitoring[J]. IEEE Transaction on Power Delivery.2002, 14(2).412-416.
[23]Sheng-Wei Fei, Yu Sun. Forecasing dissolved gases content in power transformer oil based on support vector machine with genetic algorithm[J]. Electric Power Systems Research.2008,78(3).507-514.
[24]杨兴,朱大奇,桑庆兵.专家系统研究现状与展望[J].计算机应用研究.2007,24(5).4-9.
[25]徐彤,雷英杰.一种基于知识规则推理C++实现方法[J].空军工程大学学报(自然科学版).2002,3(6).75-78.
[26]E.Oliveira, R.Camacho. A Shell for cooperating expert systems[J]. Expert System. 1991,8(2).75-84.
[27]Sunil Vadera, Said Nechab. The MD Shell and its use to develop Dust-Expert[J]. Expert System.1995,12(3).231-237.
[28]王永庆.人工智能原理与方法[M].第1版.西安：西安交通大学出版社,2002.
[29]M.Tanaka, N.Aoyama, A.Sugiura. Integration of multiple knowledge representation for classification problems[J]. Artificial Intelligence in Engineering.1995,9(4).243-247.
[30]中华人民共和国电力行业标准.变压器油中溶解气体分析和判断导则DL/T722-2000.
[31]操敦奎.变压器油中气体分析诊断与故障检查[M].第2版.北京：中国电力出版社,2006.
[32]何新贵.知识处理与专家系统[M].北京：国防工业出版社,1990.
[33]王赛.基于规则的专家系统开发工具中基本技术的研究[D].哈尔滨：哈尔滨工业大学硕士论文,2000.
[34]吴伟名,舒勤.基于关系数据库表示产生式规则[J].四川联合大学学报(工程科学版).1998,2(6).88-95.
[35]王能斌.数据库系统[M].第1版.北京：电子工业出版社,1995.
[36]董德成,郝博.基于SQL Server数据库和C++实现专家系统外壳[J].微型电脑应用.2008,24(2).34-36.
[37]卢学军,王一欧,陈仲仪.故障诊断专家系统知识处理及知识库管理方法研究[J].计算机工程与应用.2001,37(24).167-169.
[38]Wick, Michael R. Expert system explanation in retrospect:a case study in the evolution of expert system explanation[J]. Journal of systems and software. 1992,19(2).159-169.
[39]楚丽平,杨麦顺,刘晓东等.小麦节水专家系统的推理机制[J].计算机工程与应用.2004,40(12).216-219.
[40]高春鸣,陈新跃.正向推理机系统研究[J].计算机工程与应用.2002,38(19).78-80.
[41]孙臣良,孙福玉,梁宏友.基于规则的非精确反向推理专家系统[J].辽宁工程技术大学学报(自然科学版).2004,22(2).145-147.
[42]张鸣柳,孙才新.变压器油中气体色谱分析中以模糊综合评判进行故障诊断的研究[J].电工技术学报.1998,13(1).51-54.
[43]严璋.电气绝缘在线检测技术[M].北京：中国电力出版社,1995.
[44]Su Q. A fuzzy logic tool for transformer fault diagnosis[C]. International Conference on Power System Technology.2000,12.265-268.
[45]张乃尧,阎平凡.神经网络与模糊控制[M].北京：清华大学出版社,2004.
[46]胡宝清.模糊理论基础[M].武汉：武汉大学出版社,2005.
[47]徐宗本,张进社,郑亚林.计算智能中的仿生学理论与算法[M].北京：科学出版社,2003.
[48]刘晓慧.基于模糊理论的电机故障诊断专家系统的研究与实现[D].沈阳：东北大学硕士论文,2007.
[49]李雷.基于产生式规则的变压器故障诊断专家系统[D].西安：西安电子科技大学硕士论文,2008.
[50]彭宁云.基于DGA技术的变压器故障智能诊断系统研究[D].武汉：武汉大学博士论文,2004.
[51]钱政,严璋,罗承林.电力变压器绝缘故障综合诊断方法的研究[J].电网技术.2002,26(2).32-36.
[52]何新贵.模糊知识处理的理论与技术[M].第2版.北京：国防工业出版社,1998.
[53]张金玉,张优云,谢友柏.复杂设备的模糊综合诊断理论及其算法[J].中国机械工程.2000,11(7).783-786.
[54]Zhenyuan Wang. Artificial intelligence applications in the diagnosis of power transformer incipient faults[D]. Faulty of the Virginia Polytechnic Institute and State University Ph.D dissertation,2000.
[55]电力部电力科学研究院.SD187-86变压器油中溶解气体分析和判断导则编制说明.北京：水利电力出版社,1998.
[56]陈伟根,孙才新,廖瑞金.变压器局部放电与油中气体浓度的关系[J].重庆大学学报(自然科学版).2000,23(4).86-89.
[57]冯圣洪,周心权.一种综合评价指标属性值归一量化技术新途径[J].系统工程学报.2002,15(2).187-191.
[58]B.H McCormick. Visualization in scientific computing[J]. Computer Graphics. 1988,10(1).15-21.
[59]姜远,周志华,陈世福.可视化技术在电力变压器状态检测专家系统中的应用[J].计算机应用研究.2002,17(3).69-75.
[60]李军,周月琴.可视化技术在遥感图像处理系统中的应用[J].测绘通报.1998,(8).13-16.
[61]陈江波,文习山,彭宁云.基于数据库的变压器可视化故障诊断系统[J].高电压技术.2003,29(9).1-3.
[62]M Duval. A review of fault detectable by gas in oil analysis in trans[J]. IEEE Electrical Insulation Magazine.2002,18(3).8-17.
[63]李俭.大型电力变压器以油中溶解气体为特征量的内部故障诊断模型研究[D].重庆：重庆大学博士论文,2001.
[2]Mizutani Yoshinobu, Takahashi Tsuguhiro, Ito Testuo. Lifetime evaluation method for pole transformer based on transient temperature analysis[J]. IEEE Transactions on Power and Energy.2007,127(5).653-658.
[3]Ward, A.Sayed. Evaluating transformer condition using DGA oil analysis[C]. Conference on Electrical Insulation and Dielectric Phenomena(CEIDP), Annual Report.2003,10.463-468.
[4]石荣德,赵廷弟.故障诊断专家系统[J].北京航空航天大学学报.1995,21(4).7-12.
[5]高文胜,严璋,谈克雄.基于油中溶解气体分析的电力变压器绝缘故障诊断方法[J].电工电能新技术.2000,19(1).22-26.
[6]Morais R.M, Mannheimer W.A, Carballeira M. Furfural analysis for assessing degradation of thermally upgraded papers in transformer insulation[J]. IEEE Transactions on Dielectrics and Electrical Insulation.1999,6(2).159-163.
[7]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[J].变压器.1999,36(1).30-34.
[8]Ning Gao, Zhang Yan. New approach on comprehensive diagnosis of insulation faults in power transformer[C]. Conference Record of the 2002 IEEE International Symposium on Electrical Insulation.2002,4.203-206.
[9]宋斌,于萍,罗运柏.变压器油状态监测的专家系统及应用研究[J].变压器.1998,35(12).27-30.
[10]Tomsovic K, Tapper M, Ingvarsson T. A fuzzy information approach to integrating different transformer diagnostic methods [J], IEEE Transactions On Power Delivery.1993,8(3).1638-1646.
[11]Eulalia Szmidt, Janusz Kacprayk. Intuitionism fuzzy sets for the softening of group decision making models[C]. The International Conference on System Science.2001,2.237-240.
[12]Shyi-Ming Chen. Fuzzy group decision making for evaluating the rate of aggregative risk in software development[J]. Fuzzy Sets and System.2001, 118(1).75-83.
[13]L.H Chen, H.W Lu. An approximate for ranking fuzzy numbers based on left and right dominance[J]. Computer and Mathematics with Application.2001, 41(12).1589-1602.
[14]Shu-Hsien Liao. Expert system methodologies and applications-a decade review from 1995 to 2004[J]. Expert Systems with Application.2005,28(1).93-103.
[15]徐文,王大忠,周泽群.基于模糊理论的变压器故障诊断专家系统[J].电力系统自动化.1995,19(6).32-35.
[16]符杨,江玉蓉,崔椿洪.基于模糊数学和概率论的变压器故障诊断[J].高电压技术.2008,34(5).1040-1044.
[17]Zhiyong Wang, Chuangxin Guo, Quanyuan Jiang. A fault diagnosis method for transformer integrating rough set with fuzzy rules [J]. Transactions of the Institute of Measurement and Control.2006,28(3).243-251.
[18]王道勇.变压器故障检测方法的改进[J].电力系统自动化.1998,22(11).44-48.
[19]Takeki Nogami, Yoshihide Yokoi, Hideo Ichiba. Gas discrimination method for detecting transformer faults by neural network[C]. IEEE World Congress on Computational Intelligence.1994,6.3800-3805.
[20]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[J].湖南大学学报.2000,27(4).72-75.
[21]王楠,律方成,刘云鹏.粗糙集理论在电力变压器故障诊断中的应用[J].华北电力大学学报.2003,30(4).21-25.
[22]Yann-Chang Huang, Chao-Ming Huang. Evolving wavelet networks for power transformer condition monitoring[J]. IEEE Transaction on Power Delivery.2002, 14(2).412-416.
[23]Sheng-Wei Fei, Yu Sun. Forecasing dissolved gases content in power transformer oil based on support vector machine with genetic algorithm[J]. Electric Power Systems Research.2008,78(3).507-514.
[24]杨兴,朱大奇,桑庆兵.专家系统研究现状与展望[J].计算机应用研究.2007,24(5).4-9.
[25]徐彤,雷英杰.一种基于知识规则推理C++实现方法[J].空军工程大学学报(自然科学版).2002,3(6).75-78.
[26]E.Oliveira, R.Camacho. A Shell for cooperating expert systems[J]. Expert System. 1991,8(2).75-84.
[27]Sunil Vadera, Said Nechab. The MD Shell and its use to develop Dust-Expert[J]. Expert System.1995,12(3).231-237.
[28]王永庆.人工智能原理与方法[M].第1版.西安：西安交通大学出版社,2002.
[29]M.Tanaka, N.Aoyama, A.Sugiura. Integration of multiple knowledge representation for classification problems[J]. Artificial Intelligence in Engineering.1995,9(4).243-247.
[30]中华人民共和国电力行业标准.变压器油中溶解气体分析和判断导则DL/T722-2000.
[31]操敦奎.变压器油中气体分析诊断与故障检查[M].第2版.北京：中国电力出版社,2006.
[32]何新贵.知识处理与专家系统[M].北京：国防工业出版社,1990.
[33]王赛.基于规则的专家系统开发工具中基本技术的研究[D].哈尔滨：哈尔滨工业大学硕士论文,2000.
[34]吴伟名,舒勤.基于关系数据库表示产生式规则[J].四川联合大学学报(工程科学版).1998,2(6).88-95.
[35]王能斌.数据库系统[M].第1版.北京：电子工业出版社,1995.
[36]董德成,郝博.基于SQL Server数据库和C++实现专家系统外壳[J].微型电脑应用.2008,24(2).34-36.
[37]卢学军,王一欧,陈仲仪.故障诊断专家系统知识处理及知识库管理方法研究[J].计算机工程与应用.2001,37(24).167-169.
[38]Wick, Michael R. Expert system explanation in retrospect:a case study in the evolution of expert system explanation[J]. Journal of systems and software. 1992,19(2).159-169.
[39]楚丽平,杨麦顺,刘晓东等.小麦节水专家系统的推理机制[J].计算机工程与应用.2004,40(12).216-219.
[40]高春鸣,陈新跃.正向推理机系统研究[J].计算机工程与应用.2002,38(19).78-80.
[41]孙臣良,孙福玉,梁宏友.基于规则的非精确反向推理专家系统[J].辽宁工程技术大学学报(自然科学版).2004,22(2).145-147.
[42]张鸣柳,孙才新.变压器油中气体色谱分析中以模糊综合评判进行故障诊断的研究[J].电工技术学报.1998,13(1).51-54.
[43]严璋.电气绝缘在线检测技术[M].北京：中国电力出版社,1995.
[44]Su Q. A fuzzy logic tool for transformer fault diagnosis[C]. International Conference on Power System Technology.2000,12.265-268.
[45]张乃尧,阎平凡.神经网络与模糊控制[M].北京：清华大学出版社,2004.
[46]胡宝清.模糊理论基础[M].武汉：武汉大学出版社,2005.
[47]徐宗本,张进社,郑亚林.计算智能中的仿生学理论与算法[M].北京：科学出版社,2003.
[48]刘晓慧.基于模糊理论的电机故障诊断专家系统的研究与实现[D].沈阳：东北大学硕士论文,2007.
[49]李雷.基于产生式规则的变压器故障诊断专家系统[D].西安：西安电子科技大学硕士论文,2008.
[50]彭宁云.基于DGA技术的变压器故障智能诊断系统研究[D].武汉：武汉大学博士论文,2004.
[51]钱政,严璋,罗承林.电力变压器绝缘故障综合诊断方法的研究[J].电网技术.2002,26(2).32-36.
[52]何新贵.模糊知识处理的理论与技术[M].第2版.北京：国防工业出版社,1998.
[53]张金玉,张优云,谢友柏.复杂设备的模糊综合诊断理论及其算法[J].中国机械工程.2000,11(7).783-786.
[54]Zhenyuan Wang. Artificial intelligence applications in the diagnosis of power transformer incipient faults[D]. Faulty of the Virginia Polytechnic Institute and State University Ph.D dissertation,2000.
[55]电力部电力科学研究院.SD187-86变压器油中溶解气体分析和判断导则编制说明.北京：水利电力出版社,1998.
[56]陈伟根,孙才新,廖瑞金.变压器局部放电与油中气体浓度的关系[J].重庆大学学报(自然科学版).2000,23(4).86-89.
[57]冯圣洪,周心权.一种综合评价指标属性值归一量化技术新途径[J].系统工程学报.2002,15(2).187-191.
[58]B.H McCormick. Visualization in scientific computing[J]. Computer Graphics. 1988,10(1).15-21.
[59]姜远,周志华,陈世福.可视化技术在电力变压器状态检测专家系统中的应用[J].计算机应用研究.2002,17(3).69-75.
[60]李军,周月琴.可视化技术在遥感图像处理系统中的应用[J].测绘通报.1998,(8).13-16.
[61]陈江波,文习山,彭宁云.基于数据库的变压器可视化故障诊断系统[J].高电压技术.2003,29(9).1-3.
[62]M Duval. A review of fault detectable by gas in oil analysis in trans[J]. IEEE Electrical Insulation Magazine.2002,18(3).8-17.
[63]李俭.大型电力变压器以油中溶解气体为特征量的内部故障诊断模型研究[D].重庆：重庆大学博士论文,2001.