油浸式电力变压器故障诊断方法研究
|
摘要
变压器是输配电系统中的关键设备,及时而准确地检测出变压器早期潜伏性故障,对于保障电力系统的可靠运行具有重大意义。本文在分析电力变压器故障机理和现有故障诊断方法的基础上,研究了自组织抗体网络、极限学习机和证据理论等人工智能方法,并用于解决电力变压器故障诊断问题。论文的主要内容如下。
自组织抗体网络的学习算法中没有网络压缩机制,训练后的网络中存在大量的冗余抗体。针对该问题,本文提出了改进的自组织抗体网络。该方法将网络压缩机制引入自组织抗体网络,利用亲和度阈值调节免疫网络的记忆抗体分布。仿真实验表明,网络压缩机制可以加快网络的收敛速度,优化网络结构,同时维持免疫网络的稳定性。
将自组织抗体网络应用于变压器故障诊断时,由于其初始抗体是随机选取的,网络性能并不稳定。文中将免疫算子引入自组织抗体网络,提出了基于混合免疫算法的变压器故障诊断方法。该方法利用K-means最佳聚类算法获取初始抗体,并通过粒子群优化算法优化亲和度阈值。仿真实验表明,混合免疫算法的性能比自组织抗体网络更加稳定,其诊断正确率高于单一诊断方法。
基于混合免疫算法的变压器故障诊断方法中提取疫苗需要进行大量的计算,并且存在训练速度慢和参数确定困难的问题。为此,文中将极限学习机和核极限学习机用于解决变压器故障诊断问题,并利用粒子群优化算法优化核极限学习机的学习参数。仿真实验表明,极限学习机比混合免疫算法的诊断正确率稍高,训练时间远远少于后者,但其性能不太稳定；和其他智能诊断方法相比,核极限学习机需要的训练时间和测试时间最少,训练正确率和测试正确率最高,并且性能更加稳定。
由于变压器气体征兆与故障原因之间存在复杂性和模糊性,各种故障诊断方法的判断结果容易出现分歧。文中提出了一种基于证据理论的变压器故障诊断方法,利用冲突证据合成规则将混合免疫算法、核极限学习机和模糊理论的诊断结果进行融合,实现了多特征信息、多诊断方法的有效融合。实例分析表明,该融合方法可以提高故障诊断的可靠性。
Power transformers are among the key equipment in electrical power transmission/distribution systems, and to detect early incipient faults in transformers timely and accurately is of great significance for enabling reliable operations of power systems. On the basis of the analysis of the fault mechanism and the existing fault diagnosis methods, self-organization antibody net (soAbNet), extreme learning machine (ELM) and evidence theory has been studied and applied to fault diagnosis of power transformer in this dissertation. The main content of the thesis are as follows.
There is no network compression mechanism in the learning algorithm of soAbNet. As a result, there are many redundant antibodies in the trained immune network. To solve this problem, an improved soAbNet was proposed. In this method, a network compression mechanism was introduced into soAbNet, and the distribution of memory antibodies in immune network was adjusted with an affinity threshold. Experiment results show that the network compression mechanism could accelerate the convergence speed of soAbNet, optimize the network structure and maintain the stability of the immune network simultaneously.
Because of the initial antibodies are randomly selected in soAbNet, its network performance is instability when soAbNet is applied to transformer fault diagnosis. A hybrid immune network was proposed for transformer fault diagnosis, which is a combination of soAbNet and immune operator. Immune operator obtains initial antibodies using K-means optimal clustering algorithm, and the affinity threshold is optimized by using particle swarm optimization (PSO) algorithm. Experiment results show that the performance of hybrid immune network is more stable than that of soAbNet, and the diagnostic accuracy is higher than that derived from individual diagnosis approaches.
However when the proposed hybrid immune network is applied to transformer fault diagnosis, it requires a large number of calculations to obtain initial antibodies, its learning speed is slow, and it is difficult to determine its learning parameters. Therefore, ELM and kernel-based ELM (KELM) were applied to transformer fault diagnosis, and the learning parameters of KELM were optimized by using PSO. Experiment results show that the diagnostic accuracy of ELM is a bit higher than that derived from hybrid immune network, and its learning time is far less than the latter, unfortunately its performance is instability; compared with other intelligent diagnosis approaches, KELM requires the least training time and testing time, its correct diagnosis rates on training dataset and testing dataset are the highest, and its performance is very stable.
Since the relations between characteristic gases and transformer fault are complicated and fuzzy, the results of different diagnosis techniques might be inconsistent. A fault diagnosis for power transformer based on evidence theory was proposed to combine the diagnosis results of hybrid immune network, KELM and fuzzy theory by using combination rule for conflicting evidence, and it could effectively integrate multiple diagnosis techniques with multiple feature information. Experiment results show that the proposed fusion method could improve the reliability of transformer fault diagnosis.
自组织抗体网络的学习算法中没有网络压缩机制,训练后的网络中存在大量的冗余抗体。针对该问题,本文提出了改进的自组织抗体网络。该方法将网络压缩机制引入自组织抗体网络,利用亲和度阈值调节免疫网络的记忆抗体分布。仿真实验表明,网络压缩机制可以加快网络的收敛速度,优化网络结构,同时维持免疫网络的稳定性。
将自组织抗体网络应用于变压器故障诊断时,由于其初始抗体是随机选取的,网络性能并不稳定。文中将免疫算子引入自组织抗体网络,提出了基于混合免疫算法的变压器故障诊断方法。该方法利用K-means最佳聚类算法获取初始抗体,并通过粒子群优化算法优化亲和度阈值。仿真实验表明,混合免疫算法的性能比自组织抗体网络更加稳定,其诊断正确率高于单一诊断方法。
基于混合免疫算法的变压器故障诊断方法中提取疫苗需要进行大量的计算,并且存在训练速度慢和参数确定困难的问题。为此,文中将极限学习机和核极限学习机用于解决变压器故障诊断问题,并利用粒子群优化算法优化核极限学习机的学习参数。仿真实验表明,极限学习机比混合免疫算法的诊断正确率稍高,训练时间远远少于后者,但其性能不太稳定；和其他智能诊断方法相比,核极限学习机需要的训练时间和测试时间最少,训练正确率和测试正确率最高,并且性能更加稳定。
由于变压器气体征兆与故障原因之间存在复杂性和模糊性,各种故障诊断方法的判断结果容易出现分歧。文中提出了一种基于证据理论的变压器故障诊断方法,利用冲突证据合成规则将混合免疫算法、核极限学习机和模糊理论的诊断结果进行融合,实现了多特征信息、多诊断方法的有效融合。实例分析表明,该融合方法可以提高故障诊断的可靠性。
Power transformers are among the key equipment in electrical power transmission/distribution systems, and to detect early incipient faults in transformers timely and accurately is of great significance for enabling reliable operations of power systems. On the basis of the analysis of the fault mechanism and the existing fault diagnosis methods, self-organization antibody net (soAbNet), extreme learning machine (ELM) and evidence theory has been studied and applied to fault diagnosis of power transformer in this dissertation. The main content of the thesis are as follows.
There is no network compression mechanism in the learning algorithm of soAbNet. As a result, there are many redundant antibodies in the trained immune network. To solve this problem, an improved soAbNet was proposed. In this method, a network compression mechanism was introduced into soAbNet, and the distribution of memory antibodies in immune network was adjusted with an affinity threshold. Experiment results show that the network compression mechanism could accelerate the convergence speed of soAbNet, optimize the network structure and maintain the stability of the immune network simultaneously.
Because of the initial antibodies are randomly selected in soAbNet, its network performance is instability when soAbNet is applied to transformer fault diagnosis. A hybrid immune network was proposed for transformer fault diagnosis, which is a combination of soAbNet and immune operator. Immune operator obtains initial antibodies using K-means optimal clustering algorithm, and the affinity threshold is optimized by using particle swarm optimization (PSO) algorithm. Experiment results show that the performance of hybrid immune network is more stable than that of soAbNet, and the diagnostic accuracy is higher than that derived from individual diagnosis approaches.
However when the proposed hybrid immune network is applied to transformer fault diagnosis, it requires a large number of calculations to obtain initial antibodies, its learning speed is slow, and it is difficult to determine its learning parameters. Therefore, ELM and kernel-based ELM (KELM) were applied to transformer fault diagnosis, and the learning parameters of KELM were optimized by using PSO. Experiment results show that the diagnostic accuracy of ELM is a bit higher than that derived from hybrid immune network, and its learning time is far less than the latter, unfortunately its performance is instability; compared with other intelligent diagnosis approaches, KELM requires the least training time and testing time, its correct diagnosis rates on training dataset and testing dataset are the highest, and its performance is very stable.
Since the relations between characteristic gases and transformer fault are complicated and fuzzy, the results of different diagnosis techniques might be inconsistent. A fault diagnosis for power transformer based on evidence theory was proposed to combine the diagnosis results of hybrid immune network, KELM and fuzzy theory by using combination rule for conflicting evidence, and it could effectively integrate multiple diagnosis techniques with multiple feature information. Experiment results show that the proposed fusion method could improve the reliability of transformer fault diagnosis.
引文
[1]Kulkarni S V, Khaparde S A. Transformer Engineering:Design, Technology, and Diagnostics[M]. Boca Raton:CRC Press,2012
[2]河南省电力公司.变压器检修[M].北京：中国电力出版社,2012
[3]国家电网公司运维检修部.变压器类设备典型故障案例汇编：2006-2010年[M].北京：中国电力出版社,2012
[4]操郭奎,许维宗,阮国方.变压器运行维护与故障分析处理[M].北京：中国电力出版社,2008
[5]胡启凡.变压器试验技术[M].北京：中国电力出版社,2010
[6]滕国军,牛林.变压器试验与分析[M].北京：中国电力出版社,2013
[7]王致杰,徐余法,刘三明,等.电力设备状态监测与故障诊断[M].上海：上海交通大学出版社,2012
[8]陈安伟,董国轮,胡文堂.输变电设备状态检修[M].北京：中国电力出版社,2012
[9]牛林.变压器状态监测诊断技术[M].北京：中国电力出版社,2013
[10]朱德恒,严璋,谈克雄,等.电气设备状态监测与故障诊断技术[M].北京：中国电力出版社,2009
[11]孙才新,陈伟根,李俭,等.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
[12]Tang W H, Wu Q H. Condition Monitoring and Assessment of Power Transformers Using Computational Intelligence[M]. New York:Springer Verlag Press,2011:95-104
[13]徐康健,孟玉婵.变压器油中溶解气体的色谱分析实用技术[M].北京：中国质检出版社,2011
[14]DL/T722-2000,变压器油中溶解气体分析和判断导则[S].北京：中华人民共和国国家经济贸易委员会,2000
[15]IEC Publication 60599 (2007-05), Mineral oil-impregnated electrical equipment in service - Guide to the interpretation of dissolved and free gases analysis[S]. Geneva:IEC Central Office,2007
[16]IEEE Std C57.104-2008. IEEE guide for the Interpretation of gases generated in oil-Immersed transformers[S]. New York:the Institute of Electrical and Electronics Engineers,2008
[17]GB/T17623-1998,绝缘油中溶解气体组分含量的气相色谱测定法[S].北京： 中华人民共和国国家质量监督检验检疫总局,1998
[18]操敦奎.变压器油色谱分析与故障诊断[M].北京：中国电力出版社,2010
[19]牛林.变压器状态监测诊断技术[M].北京：中国电力出版社,2013
[20]Duval M. Dissolved gas analysis and the Duval triangle[C]. TechCon Asia Pacific 2006, Sydney, Australia,2006
[21]Duval M, Dukarm J. Improving the reliability of transformer gas-in-oil diagnosis[J]. Electrical Insulation Magazine, IEEE,2005,21(4):21-27
[22]Duval M. A review of faults detectable by gas-in-oil analysis in transformers[J]. Electrical Insulation Magazine, IEEE,2002,18(3):8-17
[23]刘白林.人工智能与专家系统[M].西安：西安交通大学出版社,2012
[24]王大忠,徐文,周泽存,等.模糊理论、专家系统及人工神经网络在电力变压器故障诊断中应用-基于油中溶解气体进行分析诊断[J].中国电机工程学报.1996,16(5)：349-353
[25]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[J].高电压技术.1998,24(4)：6-8,12
[26]廖瑞金,姚陈果,孙才新,等.多专家合作诊断变压器绝缘故障的黑板型专家系统[J].电工技术学报.2002,17(1)：85-90
[27]项新建.基于粗糙集理论的变压器故障诊断专家系统研究[J].仪器仪表学报.2005,26(1)：93-96
[28]厉劫翀,周宁,吕彬.基于神经网络、模糊理论的变压器油中溶解气体诊断专家系统[J].电网技术.2006,30(增刊)：125-128
[29]王美铃.基于多知识库电力变压器故障诊断专家系统[D].长沙：中南大学,2011
[30]Haykin Simon. Neural networks and learning machines[M]. Upper Saddle River:Prentice Hall,2009
[31]丁晓群,林钟云.神经网络应用于电力变压器故障诊断[J].电力系统自动化.1996,20(2)：32-35
[32]杨启平,薛五德,蓝之达.基于人工神经网络的变压器故障诊断[J].变压器.2000,37(3)：33-36
[33]刘娜,高文胜,谈克雄.基于组合神经网络模型的电力变压器故障诊断方法[J].电工技术学报.2003,18(2)：83-86
[34]梁永春,李彦明.改进型组合RBF神经网络的变压器故障诊断[J].高电压技术.2005,31(9)：31-33
[35]曹永刚,周玲,丁晓群,等.基于概率神经网络的电力变压器故障诊断[J].继电器.2006,34(3)：9-11
[36]张东波,徐瑜,王耀南.主动差异学习神经网络集成方法在变压器DGA故障诊断中的应用[J].中国电机工程学报.2010,30(22)：64-70
[37]高骏,何俊佳.量子遗传神经网络在变压器油中溶解气体分析中的应用[J].中国电机工程学报.2010,30(30)：121-127
[38]杨晓伟,郝志峰.支持向量机的算法设计与分析[M].北京：科学出版社,2013
[39]吕干云,程浩忠,董立新,翟海保.基于多级支持向量机分类器的电力变压器故障识别[J].电力系统及其自动化学报,2005,17(1)：19-22,52
[40]董明,孟源源,徐长响,等.基于支持向量机及油中溶解气体分析的大型电力变压器故障诊断模型研究[J].中国电机工程学报,2003,23(7)：88-92
[41]Sheng-wei Fei, Xiao-bin Zhang. Fault diagnosis of power transformer based on support vector machine with genetic algorithm[J]. Expert Systems with Applications,2009,36(8):11352-11357
[42]殷建平,祝恩,刘越,等.人工智能：一种现代的方法[M].北京：清华大学出版社,2013
[43]王平.基于模糊综合评判的变压器故障模糊诊断法[J].电力系统自动化,1996,20(12)：30-33
[44]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
[45]杨莉,尚勇.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,2000,20(7)：19-23
[46]邹杰慧.电力变压器故障诊断模糊专家系统研究开发[D].长沙：湖南大学,2004
[47]骆思佳,廖瑞金,王有元,等.带变权的电力变压器状态模糊综合评判[J].高电压技术,2007,33(8)：106-110
[48]Timmis J, Neal M, Hunt J. An artificial immune system for data analysis[J]. BioSystems,2000,55(1-3):143-150
[49]de Castro L N, Von Zuben F J. Immune and neural network models:theoretical and empirical comparisons[J]. International Journal of Computational Intelligence and Applications,2001,1(3):239-257
[50]焦李成,杜海峰,刘芳,等.免疫优化：计算、学习与识别[M].北京：科学出版社,2006
[51]徐雪松.免疫智能信息处理系统及其应用[M].长沙：湖南大学出版社,2011
[52]龚涛,蔡自兴.基于正常模型的人工免疫系统及其应用[M].北京：清华大 学出版社,2011
[53]田玉玲,段富.免疫优化算法、模型及应用[M].北京：国防工业出版社,2013
[54]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
[55]熊浩,孙才新,陈伟根.电力变压器故障诊断的人工免疫网络分类算法[J].电力系统自动化,2006,30(6)：57-60
[56]周爱华,张彼德,张厚宣.基于人工免疫分类算法的电力变压器故障诊断[J].高电压技术,2007,33(8)：77-80
[57]宋绍民,王耀南,孙炜,等.基于免疫聚类算法的变压器DGA数据故障诊断方法[J].变压器,2008,45(8)：70-72
[58]周爱华,张彼德,方春恩,等.基于模糊免疫识别方法的电力变压器故障诊断[J].电网技术,2009,33(3)：99-102
[59]李中,苑津莎,张利伟.基于自组织抗体网络的电力变压器故障诊断[J].电工技术学报,2010,25(10)：200-206
[60]郑蕊蕊,赵继印,赵婷婷,等.基于遗传支持向量机和灰色人工免疫算法的电力变压器故障诊断[J].中国电机工程学报,2011,31(7)：56-63
[61]王永强,律方成,李和明.基于粗糙集理论和贝叶斯网络的电力变压器故障诊断方法[J].中国电机工程学报,2006,26(8)：137-141
[62]尚勇,闫春江,严璋,等.基于信息融合的大型油浸电力变压器故障诊断[J].中国电机工程学报,2002,22(7)：115-118
[63]廖瑞金,廖玉祥,杨丽君,等.多神经网络与证据理论融合的变压器故障综合诊断方法研究[J].中国电机工程学报,2006,26(3)：119-124
[64]熊浩,杨俊,李卫国,等.多种类证据体的变压器故障综合诊断方法[J].中国电机工程学报,2008,28(28)：24-30
[65]魏星,舒乃秋,崔鹏程,等.基于改进PSO-BP神经网络和D-S证据理论的大型变压器故障综合诊断[J].电力系统自动化,2006,30(7)：46-50
[66]Dasgupta D. Advances in artificial immune systems[J]. Computational Intelligence Magazine, IEEE,2006,1(4):40-49
[67]Hunt J E, Cooke D E. Learning using an artificial immune system[J]. Journal of network and computer applications,1996,19(2):189-212
[68]Hunt J E, Fellows A. Introducing an immune response into a CBR system for data mining[C]. BCS ESG'96 Conference:Research and Development in Expert System VIII,1996:35-42
[69]Hunt J, Timmis J, Cooke E, et al. Jisys:The envelopment of an artificial immune system for real world applications[M]. Artificial Immune Systems and their Applications. Springer Berlin Heidelberg,1999:157-186
[70]Timmis J, Neal M. A resource limited artificial immune system for data analysis[J]. Knowledge-Based Systems,2001,14(3):121-130
[71]Watkins A B, Boggess L C. A resource limited artificial immune classifier[C]. Proceedings of Congress on Evolutionary Computation, Part of the 2002 IEEE World Congress on Computational Intelligence, Honolulu, HI, USA,2002: 926-931
[72]Nasraoui O, Gonzalez F, Cardona C, et al. A scalable artificial immune system model for dynamic unsupervised learning[C]. Genetic and Evolutionary Computation—GECCO 2003, Chicago, IL, USA,2003:219-230
[73]Nasraoui O, Dasgupta D, Gonzalez F A. An novel artificial immune system approach to robust data mining[C]. Proceedings of the Intemational Conference Genetic and Evolutionary Computation (GECCO), New York, USA,2002: 356-363
[74]Nasaroui O, Gonzalez F, Dasgupta D. The fuzzy artificial immune system: Motivations, basic concepts, and application to clustering and web profiling[C]. Proceedings of the 2002 IEEE International Conference on Fuzzy Systems, 2002,1:711-716
[75]Nasraoui O, Dasgupta D, Gonzalez F. The promise and challenges of artificial immune system based web usage mining:Preliminary results[C]. Second SIAM International Conference on Data Mining (SDM), Arlington, USA,2002
[76]de Castro L N, Von Zuben F J. aiNet:an artificial immune network for data analysis[J]. Data mining:a heuristic approach,2001,1:231-259
[77]de Castro L N, Timmis J I. Artificial immune systems as a novel soft computing paradigm[J]. Soft computing,2003,7(8):526-544
[78]Bezerra G B, de Castro L N. Bioinformatics data analysis using an artificial immune network[J]. Artificial Immune Systems,2003:22-33
[79]de Castro L N, Von Zuben F J. The clonal selection algorithm with engineering applications[C]. Proceedings of the Genetic and Evolutionary Computation Conference, Las Vagas, Nevada, USA,2000:36-39
[80]Forrest S, Perelson A S, Allen L, et al. Self-nonself discrimination in a computer[C]. Proceedings of 1994 IEEE Computer Society Symposium on Research in Security and Privacy, Oakland, USA,1994:202-212
[81]李中.基于人工免疫系统的电力变压器故障诊断技术研究[D].保定：华北电力大学,2010
[82]Chih-Chung Chang and Chih-Jen Lin, LIBSVM:a library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2:27:1-27:27,2011
[83]Tin Kam Ho, Eugene M. Kleinberg. Building projectable classifiers of arbitrary complexity[C]. Proceedings of the 13th International Conference on Pattern Recognition, Vienna, Austria,1996
[84]Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA:University of California, School of Information and Computer Science
[85]Al-Enezi J R, Abbod M F, Alsharhan S. Artificial immune systems-models, algorithms and applications[J]. International Journal of Research & Reviews in Applied Sciences,2010,3(2):118-131
[86]焦李成,杜海峰.人工免疫系统进展与展望[J].电子学报,2003,31(10)：1540-1548
[87]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,2002,38(4)：88-90
[88]戴汝为,王玉.智能系统中的互补策略[J].模式识别与人工智能,1993,6(1)：1-11
[89]焦李成,王磊.免疫进化算法[C].1999年中国神经网络与信号处理学术会议,汕头,中国,1999
[90]王磊,潘进.免疫算法[J].电子学报,2000,28(7)：74-78
[91]孙吉贵,刘杰,赵连宇.聚类算法研究[J].软件学报,2008,19(1)：48-61
[92]周世兵.聚类分析中的最佳聚类数确定方法研究及应用[D].无锡：江南大学,2011
[93]Calinski T, Harabasz J. A dendrite method for cluster analysis[J]. Communications in Statistics-theory and Methods,1974,3(1):1-27
[94]杨维,李歧强.粒子群优化算法综述[J].中国工程科学,2004,6(5)：87-94
[95]Huang G B, Wang D H, Lan Y. Extreme learning machines:a survey[J]. International Journal of Machine Learning and Cybernetics,2011,2(2): 107-122
[96]Huang G B, Zhu Q Y, Siew C K. Extreme learning machine:a new learning scheme of feedforward neural networks[C].2004 IEEE International Joint Conference on Neural Networks, Budapest, Hungary,2004,2:985-990
[97]Cambria E, Huang G B. Extreme Learning Machines[J]. Trans. Neural Networks,2006,17(4):879-892
[98]Huang G B, Siew C K. Extreme learning machine:RBF network case[C].8th International Conference on Control, Automation, Robotics and Vision, Kunming, China,2004,2:1029-1036
[99]Zhu Q Y, Qin A K, Suganthan P N, et al. Evolutionary extreme learning machine[J]. Pattern recognition,2005,38(10):1759-1763
[100]Huang G B, Zhu Q Y, Siew C K. Extreme learning machine:theory and applications[J]. Neurocomputing,2006,70(1):489-501
[101]Deng W, Zheng Q, Chen L. Regularized extreme learning machine[C].2009 IEEE Symposium on Computational Intelligence and Data Mining Proceedings, Nashville, USA,2009:389-395
[102]Liu N, Wang H. Ensemble based extreme learning machine[J]. Signal Processing Letters, IEEE,2010,17(8):754-757
[103]Huang G B, Ding X, Zhou H. Optimization method based extreme learning machine for classification[J]. Neurocomputing,2010,74(1):155-163
[104]Wang Y, Cao F, Yuan Y. A study on effectiveness of extreme learning machine[J]. Neurocomputing,2011,74(16):2483-2490
[105]Rajesh R, Prakash J S. Extreme learning machines-a review and state-of-the-art[J]. International Journal of Wisdom Based Computing,2011, 1(1):35-48
[106]Zong W, Huang G B. Face recognition based on extreme learning machine[J]. Neurocomputing,2011,74(16):2541-2551
[107]吴正苗.基于信息融合和极限学习机的模拟电路故障诊断[D].长沙：湖南大学,2011
[108]Han F, Yao H F, Ling Q H. An improved evolutionary extreme learning machine based on particle swarm optimization[J]. Neurocomputing,2013,116: 87-93
[109]Liu X, Gao C, Li P. A comparative analysis of support vector machines and extreme learning machines[J]. Neural Networks,2012,33:58-66
[110]Cao J, Lin Z, Huang G B, et al. Voting based extreme learning machine[J]. Information Sciences,2012,185(1):66-77
[111]毛力,王运涛,刘兴阳,等.基于改进极限学习机的短期电力负荷预测方法[J].电力系统保护与控制,2012,40(20)：140-144
[112]张英堂,马超,尹刚,等.基于多极限学习机在线集成的柴油机故障诊断方法研究[J].车用发动机,2012(6)：88-92
[113]马超,张英堂,李志宁,等.基于ELM和证据理论的发动机故障诊断[J].车用发动机,2013(3)：88-92
[114]张文博,姬红兵.融合极限学习机[J].电子与信息学报,2013,35(11)：2728-2732
[115]王杰,郭晨龙.小波核极限学习机分类器[J].微电子学与计算机,2013,30(10)：73-76
[116]王杰,毕浩洋.一种基于粒子群优化的极限学习机[J].郑州大学学报：理 学版,2013,45(1)：100-104
[117]杨易旻.基于极限学习的系统辨识方法及应用研究[D].长沙：湖南大学,2013
[118]宋超.基于极限学习机的AUV决策控制系统的研究[D].青岛：中国海洋大学,2013
[119]史峰,王辉,郁磊,等.MATLAB智能算法30个案例分析[M].北京：北京航空航天大学出版社,2011
[120]Huang G B, Siew C K. Extreme learning machine with randomly assigned RBF kernels[J]. International Journal of Information Technology,2005,11(1):16-24
[121]Huang G B, Zhou H, Ding X, et al. Extreme learning machine for regression and multiclass classification[J]. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on,2012,42(2):513-529
[122]Dempster A P. Upper and lower probabilities induced by a multivalued mapping[J]. The annals of mathematical statistics,1967:325-339
[123]Shafer G. A mathematical theory of evidence[M]. Princeton:Princeton university press,1976
[124]段新生.证据理论与决策、人工智能[M].北京：中国人民大学出版社,1993
[125]杨风暴,王肖霞.D-S证据理论的冲突证据合成方法[M].北京：国防工业出版社,2010
[126]Lefevre E, Colot O, Vannoorenberghe P. Belief function combination and conflict management[J]. Information fusion,2002,3(2):149-162
[127]Florea M C, Jousselme A L, Bosse e, et al. Robust combination rules for evidence theory[J]. Information Fusion,2009,10(2):183-197
[128]Denosux T. Conjunctive and disjunctive combination of belief functions induced by nondistinct bodies of evidence[J]. Artificial Intelligence,2008, 172(2):234-264
[129]Fu C, Yang S, Luo H. Analyzing the degree of consistency among evidence from different sources[J]. Systems Engineering-Theory & Practice,2009,29(5): 166-174
[130]邓勇,施文康,朱振福.一种有效处理冲突证据的组合方法[J].红外与毫米波学报,2004,23(1)：27-32
[131]Murphy C K. Combining belief functions when evidence conflicts[J]. Decision support systems,2000,29(1):1-9
[132]杨静,田亮,赵爱军,等.基于典型样本的证据理论信度函数分配构造方法[J].华北电力大学学报,2008,35(5)：70-72
[133]赵亮宇,田亮,王琪,等.基于改进信度函数分配方法的煤种判别技术[J]. 华北电力大学学报,2011,38(4)：71-75
[134]朱永利,尹金良.组合核相关向量机在电力变压器故障诊断中的应用研究[J].中国电机工程学报,2013,33(22)：68-74
[2]河南省电力公司.变压器检修[M].北京：中国电力出版社,2012
[3]国家电网公司运维检修部.变压器类设备典型故障案例汇编：2006-2010年[M].北京：中国电力出版社,2012
[4]操郭奎,许维宗,阮国方.变压器运行维护与故障分析处理[M].北京：中国电力出版社,2008
[5]胡启凡.变压器试验技术[M].北京：中国电力出版社,2010
[6]滕国军,牛林.变压器试验与分析[M].北京：中国电力出版社,2013
[7]王致杰,徐余法,刘三明,等.电力设备状态监测与故障诊断[M].上海：上海交通大学出版社,2012
[8]陈安伟,董国轮,胡文堂.输变电设备状态检修[M].北京：中国电力出版社,2012
[9]牛林.变压器状态监测诊断技术[M].北京：中国电力出版社,2013
[10]朱德恒,严璋,谈克雄,等.电气设备状态监测与故障诊断技术[M].北京：中国电力出版社,2009
[11]孙才新,陈伟根,李俭,等.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
[12]Tang W H, Wu Q H. Condition Monitoring and Assessment of Power Transformers Using Computational Intelligence[M]. New York:Springer Verlag Press,2011:95-104
[13]徐康健,孟玉婵.变压器油中溶解气体的色谱分析实用技术[M].北京：中国质检出版社,2011
[14]DL/T722-2000,变压器油中溶解气体分析和判断导则[S].北京：中华人民共和国国家经济贸易委员会,2000
[15]IEC Publication 60599 (2007-05), Mineral oil-impregnated electrical equipment in service - Guide to the interpretation of dissolved and free gases analysis[S]. Geneva:IEC Central Office,2007
[16]IEEE Std C57.104-2008. IEEE guide for the Interpretation of gases generated in oil-Immersed transformers[S]. New York:the Institute of Electrical and Electronics Engineers,2008
[17]GB/T17623-1998,绝缘油中溶解气体组分含量的气相色谱测定法[S].北京： 中华人民共和国国家质量监督检验检疫总局,1998
[18]操敦奎.变压器油色谱分析与故障诊断[M].北京：中国电力出版社,2010
[19]牛林.变压器状态监测诊断技术[M].北京：中国电力出版社,2013
[20]Duval M. Dissolved gas analysis and the Duval triangle[C]. TechCon Asia Pacific 2006, Sydney, Australia,2006
[21]Duval M, Dukarm J. Improving the reliability of transformer gas-in-oil diagnosis[J]. Electrical Insulation Magazine, IEEE,2005,21(4):21-27
[22]Duval M. A review of faults detectable by gas-in-oil analysis in transformers[J]. Electrical Insulation Magazine, IEEE,2002,18(3):8-17
[23]刘白林.人工智能与专家系统[M].西安：西安交通大学出版社,2012
[24]王大忠,徐文,周泽存,等.模糊理论、专家系统及人工神经网络在电力变压器故障诊断中应用-基于油中溶解气体进行分析诊断[J].中国电机工程学报.1996,16(5)：349-353
[25]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[J].高电压技术.1998,24(4)：6-8,12
[26]廖瑞金,姚陈果,孙才新,等.多专家合作诊断变压器绝缘故障的黑板型专家系统[J].电工技术学报.2002,17(1)：85-90
[27]项新建.基于粗糙集理论的变压器故障诊断专家系统研究[J].仪器仪表学报.2005,26(1)：93-96
[28]厉劫翀,周宁,吕彬.基于神经网络、模糊理论的变压器油中溶解气体诊断专家系统[J].电网技术.2006,30(增刊)：125-128
[29]王美铃.基于多知识库电力变压器故障诊断专家系统[D].长沙：中南大学,2011
[30]Haykin Simon. Neural networks and learning machines[M]. Upper Saddle River:Prentice Hall,2009
[31]丁晓群,林钟云.神经网络应用于电力变压器故障诊断[J].电力系统自动化.1996,20(2)：32-35
[32]杨启平,薛五德,蓝之达.基于人工神经网络的变压器故障诊断[J].变压器.2000,37(3)：33-36
[33]刘娜,高文胜,谈克雄.基于组合神经网络模型的电力变压器故障诊断方法[J].电工技术学报.2003,18(2)：83-86
[34]梁永春,李彦明.改进型组合RBF神经网络的变压器故障诊断[J].高电压技术.2005,31(9)：31-33
[35]曹永刚,周玲,丁晓群,等.基于概率神经网络的电力变压器故障诊断[J].继电器.2006,34(3)：9-11
[36]张东波,徐瑜,王耀南.主动差异学习神经网络集成方法在变压器DGA故障诊断中的应用[J].中国电机工程学报.2010,30(22)：64-70
[37]高骏,何俊佳.量子遗传神经网络在变压器油中溶解气体分析中的应用[J].中国电机工程学报.2010,30(30)：121-127
[38]杨晓伟,郝志峰.支持向量机的算法设计与分析[M].北京：科学出版社,2013
[39]吕干云,程浩忠,董立新,翟海保.基于多级支持向量机分类器的电力变压器故障识别[J].电力系统及其自动化学报,2005,17(1)：19-22,52
[40]董明,孟源源,徐长响,等.基于支持向量机及油中溶解气体分析的大型电力变压器故障诊断模型研究[J].中国电机工程学报,2003,23(7)：88-92
[41]Sheng-wei Fei, Xiao-bin Zhang. Fault diagnosis of power transformer based on support vector machine with genetic algorithm[J]. Expert Systems with Applications,2009,36(8):11352-11357
[42]殷建平,祝恩,刘越,等.人工智能：一种现代的方法[M].北京：清华大学出版社,2013
[43]王平.基于模糊综合评判的变压器故障模糊诊断法[J].电力系统自动化,1996,20(12)：30-33
[44]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
[45]杨莉,尚勇.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,2000,20(7)：19-23
[46]邹杰慧.电力变压器故障诊断模糊专家系统研究开发[D].长沙：湖南大学,2004
[47]骆思佳,廖瑞金,王有元,等.带变权的电力变压器状态模糊综合评判[J].高电压技术,2007,33(8)：106-110
[48]Timmis J, Neal M, Hunt J. An artificial immune system for data analysis[J]. BioSystems,2000,55(1-3):143-150
[49]de Castro L N, Von Zuben F J. Immune and neural network models:theoretical and empirical comparisons[J]. International Journal of Computational Intelligence and Applications,2001,1(3):239-257
[50]焦李成,杜海峰,刘芳,等.免疫优化：计算、学习与识别[M].北京：科学出版社,2006
[51]徐雪松.免疫智能信息处理系统及其应用[M].长沙：湖南大学出版社,2011
[52]龚涛,蔡自兴.基于正常模型的人工免疫系统及其应用[M].北京：清华大 学出版社,2011
[53]田玉玲,段富.免疫优化算法、模型及应用[M].北京：国防工业出版社,2013
[54]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
[55]熊浩,孙才新,陈伟根.电力变压器故障诊断的人工免疫网络分类算法[J].电力系统自动化,2006,30(6)：57-60
[56]周爱华,张彼德,张厚宣.基于人工免疫分类算法的电力变压器故障诊断[J].高电压技术,2007,33(8)：77-80
[57]宋绍民,王耀南,孙炜,等.基于免疫聚类算法的变压器DGA数据故障诊断方法[J].变压器,2008,45(8)：70-72
[58]周爱华,张彼德,方春恩,等.基于模糊免疫识别方法的电力变压器故障诊断[J].电网技术,2009,33(3)：99-102
[59]李中,苑津莎,张利伟.基于自组织抗体网络的电力变压器故障诊断[J].电工技术学报,2010,25(10)：200-206
[60]郑蕊蕊,赵继印,赵婷婷,等.基于遗传支持向量机和灰色人工免疫算法的电力变压器故障诊断[J].中国电机工程学报,2011,31(7)：56-63
[61]王永强,律方成,李和明.基于粗糙集理论和贝叶斯网络的电力变压器故障诊断方法[J].中国电机工程学报,2006,26(8)：137-141
[62]尚勇,闫春江,严璋,等.基于信息融合的大型油浸电力变压器故障诊断[J].中国电机工程学报,2002,22(7)：115-118
[63]廖瑞金,廖玉祥,杨丽君,等.多神经网络与证据理论融合的变压器故障综合诊断方法研究[J].中国电机工程学报,2006,26(3)：119-124
[64]熊浩,杨俊,李卫国,等.多种类证据体的变压器故障综合诊断方法[J].中国电机工程学报,2008,28(28)：24-30
[65]魏星,舒乃秋,崔鹏程,等.基于改进PSO-BP神经网络和D-S证据理论的大型变压器故障综合诊断[J].电力系统自动化,2006,30(7)：46-50
[66]Dasgupta D. Advances in artificial immune systems[J]. Computational Intelligence Magazine, IEEE,2006,1(4):40-49
[67]Hunt J E, Cooke D E. Learning using an artificial immune system[J]. Journal of network and computer applications,1996,19(2):189-212
[68]Hunt J E, Fellows A. Introducing an immune response into a CBR system for data mining[C]. BCS ESG'96 Conference:Research and Development in Expert System VIII,1996:35-42
[69]Hunt J, Timmis J, Cooke E, et al. Jisys:The envelopment of an artificial immune system for real world applications[M]. Artificial Immune Systems and their Applications. Springer Berlin Heidelberg,1999:157-186
[70]Timmis J, Neal M. A resource limited artificial immune system for data analysis[J]. Knowledge-Based Systems,2001,14(3):121-130
[71]Watkins A B, Boggess L C. A resource limited artificial immune classifier[C]. Proceedings of Congress on Evolutionary Computation, Part of the 2002 IEEE World Congress on Computational Intelligence, Honolulu, HI, USA,2002: 926-931
[72]Nasraoui O, Gonzalez F, Cardona C, et al. A scalable artificial immune system model for dynamic unsupervised learning[C]. Genetic and Evolutionary Computation—GECCO 2003, Chicago, IL, USA,2003:219-230
[73]Nasraoui O, Dasgupta D, Gonzalez F A. An novel artificial immune system approach to robust data mining[C]. Proceedings of the Intemational Conference Genetic and Evolutionary Computation (GECCO), New York, USA,2002: 356-363
[74]Nasaroui O, Gonzalez F, Dasgupta D. The fuzzy artificial immune system: Motivations, basic concepts, and application to clustering and web profiling[C]. Proceedings of the 2002 IEEE International Conference on Fuzzy Systems, 2002,1:711-716
[75]Nasraoui O, Dasgupta D, Gonzalez F. The promise and challenges of artificial immune system based web usage mining:Preliminary results[C]. Second SIAM International Conference on Data Mining (SDM), Arlington, USA,2002
[76]de Castro L N, Von Zuben F J. aiNet:an artificial immune network for data analysis[J]. Data mining:a heuristic approach,2001,1:231-259
[77]de Castro L N, Timmis J I. Artificial immune systems as a novel soft computing paradigm[J]. Soft computing,2003,7(8):526-544
[78]Bezerra G B, de Castro L N. Bioinformatics data analysis using an artificial immune network[J]. Artificial Immune Systems,2003:22-33
[79]de Castro L N, Von Zuben F J. The clonal selection algorithm with engineering applications[C]. Proceedings of the Genetic and Evolutionary Computation Conference, Las Vagas, Nevada, USA,2000:36-39
[80]Forrest S, Perelson A S, Allen L, et al. Self-nonself discrimination in a computer[C]. Proceedings of 1994 IEEE Computer Society Symposium on Research in Security and Privacy, Oakland, USA,1994:202-212
[81]李中.基于人工免疫系统的电力变压器故障诊断技术研究[D].保定：华北电力大学,2010
[82]Chih-Chung Chang and Chih-Jen Lin, LIBSVM:a library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2:27:1-27:27,2011
[83]Tin Kam Ho, Eugene M. Kleinberg. Building projectable classifiers of arbitrary complexity[C]. Proceedings of the 13th International Conference on Pattern Recognition, Vienna, Austria,1996
[84]Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA:University of California, School of Information and Computer Science
[85]Al-Enezi J R, Abbod M F, Alsharhan S. Artificial immune systems-models, algorithms and applications[J]. International Journal of Research & Reviews in Applied Sciences,2010,3(2):118-131
[86]焦李成,杜海峰.人工免疫系统进展与展望[J].电子学报,2003,31(10)：1540-1548
[87]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,2002,38(4)：88-90
[88]戴汝为,王玉.智能系统中的互补策略[J].模式识别与人工智能,1993,6(1)：1-11
[89]焦李成,王磊.免疫进化算法[C].1999年中国神经网络与信号处理学术会议,汕头,中国,1999
[90]王磊,潘进.免疫算法[J].电子学报,2000,28(7)：74-78
[91]孙吉贵,刘杰,赵连宇.聚类算法研究[J].软件学报,2008,19(1)：48-61
[92]周世兵.聚类分析中的最佳聚类数确定方法研究及应用[D].无锡：江南大学,2011
[93]Calinski T, Harabasz J. A dendrite method for cluster analysis[J]. Communications in Statistics-theory and Methods,1974,3(1):1-27
[94]杨维,李歧强.粒子群优化算法综述[J].中国工程科学,2004,6(5)：87-94
[95]Huang G B, Wang D H, Lan Y. Extreme learning machines:a survey[J]. International Journal of Machine Learning and Cybernetics,2011,2(2): 107-122
[96]Huang G B, Zhu Q Y, Siew C K. Extreme learning machine:a new learning scheme of feedforward neural networks[C].2004 IEEE International Joint Conference on Neural Networks, Budapest, Hungary,2004,2:985-990
[97]Cambria E, Huang G B. Extreme Learning Machines[J]. Trans. Neural Networks,2006,17(4):879-892
[98]Huang G B, Siew C K. Extreme learning machine:RBF network case[C].8th International Conference on Control, Automation, Robotics and Vision, Kunming, China,2004,2:1029-1036
[99]Zhu Q Y, Qin A K, Suganthan P N, et al. Evolutionary extreme learning machine[J]. Pattern recognition,2005,38(10):1759-1763
[100]Huang G B, Zhu Q Y, Siew C K. Extreme learning machine:theory and applications[J]. Neurocomputing,2006,70(1):489-501
[101]Deng W, Zheng Q, Chen L. Regularized extreme learning machine[C].2009 IEEE Symposium on Computational Intelligence and Data Mining Proceedings, Nashville, USA,2009:389-395
[102]Liu N, Wang H. Ensemble based extreme learning machine[J]. Signal Processing Letters, IEEE,2010,17(8):754-757
[103]Huang G B, Ding X, Zhou H. Optimization method based extreme learning machine for classification[J]. Neurocomputing,2010,74(1):155-163
[104]Wang Y, Cao F, Yuan Y. A study on effectiveness of extreme learning machine[J]. Neurocomputing,2011,74(16):2483-2490
[105]Rajesh R, Prakash J S. Extreme learning machines-a review and state-of-the-art[J]. International Journal of Wisdom Based Computing,2011, 1(1):35-48
[106]Zong W, Huang G B. Face recognition based on extreme learning machine[J]. Neurocomputing,2011,74(16):2541-2551
[107]吴正苗.基于信息融合和极限学习机的模拟电路故障诊断[D].长沙：湖南大学,2011
[108]Han F, Yao H F, Ling Q H. An improved evolutionary extreme learning machine based on particle swarm optimization[J]. Neurocomputing,2013,116: 87-93
[109]Liu X, Gao C, Li P. A comparative analysis of support vector machines and extreme learning machines[J]. Neural Networks,2012,33:58-66
[110]Cao J, Lin Z, Huang G B, et al. Voting based extreme learning machine[J]. Information Sciences,2012,185(1):66-77
[111]毛力,王运涛,刘兴阳,等.基于改进极限学习机的短期电力负荷预测方法[J].电力系统保护与控制,2012,40(20)：140-144
[112]张英堂,马超,尹刚,等.基于多极限学习机在线集成的柴油机故障诊断方法研究[J].车用发动机,2012(6)：88-92
[113]马超,张英堂,李志宁,等.基于ELM和证据理论的发动机故障诊断[J].车用发动机,2013(3)：88-92
[114]张文博,姬红兵.融合极限学习机[J].电子与信息学报,2013,35(11)：2728-2732
[115]王杰,郭晨龙.小波核极限学习机分类器[J].微电子学与计算机,2013,30(10)：73-76
[116]王杰,毕浩洋.一种基于粒子群优化的极限学习机[J].郑州大学学报：理 学版,2013,45(1)：100-104
[117]杨易旻.基于极限学习的系统辨识方法及应用研究[D].长沙：湖南大学,2013
[118]宋超.基于极限学习机的AUV决策控制系统的研究[D].青岛：中国海洋大学,2013
[119]史峰,王辉,郁磊,等.MATLAB智能算法30个案例分析[M].北京：北京航空航天大学出版社,2011
[120]Huang G B, Siew C K. Extreme learning machine with randomly assigned RBF kernels[J]. International Journal of Information Technology,2005,11(1):16-24
[121]Huang G B, Zhou H, Ding X, et al. Extreme learning machine for regression and multiclass classification[J]. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on,2012,42(2):513-529
[122]Dempster A P. Upper and lower probabilities induced by a multivalued mapping[J]. The annals of mathematical statistics,1967:325-339
[123]Shafer G. A mathematical theory of evidence[M]. Princeton:Princeton university press,1976
[124]段新生.证据理论与决策、人工智能[M].北京：中国人民大学出版社,1993
[125]杨风暴,王肖霞.D-S证据理论的冲突证据合成方法[M].北京：国防工业出版社,2010
[126]Lefevre E, Colot O, Vannoorenberghe P. Belief function combination and conflict management[J]. Information fusion,2002,3(2):149-162
[127]Florea M C, Jousselme A L, Bosse e, et al. Robust combination rules for evidence theory[J]. Information Fusion,2009,10(2):183-197
[128]Denosux T. Conjunctive and disjunctive combination of belief functions induced by nondistinct bodies of evidence[J]. Artificial Intelligence,2008, 172(2):234-264
[129]Fu C, Yang S, Luo H. Analyzing the degree of consistency among evidence from different sources[J]. Systems Engineering-Theory & Practice,2009,29(5): 166-174
[130]邓勇,施文康,朱振福.一种有效处理冲突证据的组合方法[J].红外与毫米波学报,2004,23(1)：27-32
[131]Murphy C K. Combining belief functions when evidence conflicts[J]. Decision support systems,2000,29(1):1-9
[132]杨静,田亮,赵爱军,等.基于典型样本的证据理论信度函数分配构造方法[J].华北电力大学学报,2008,35(5)：70-72
[133]赵亮宇,田亮,王琪,等.基于改进信度函数分配方法的煤种判别技术[J]. 华北电力大学学报,2011,38(4)：71-75
[134]朱永利,尹金良.组合核相关向量机在电力变压器故障诊断中的应用研究[J].中国电机工程学报,2013,33(22)：68-74