闵亚琪,马鑫,翟振刚,莫家庆,吕小毅

• 1:新疆大学信息科学与工程学院
• 2:特变电工股份有限公司新疆变压器厂
• 3:乌鲁木齐高新区(新市区)经济和发展改革委员会
• 4:西安交通大学电子与信息工程学院

摘要(Abstract)：

为了提高电力变压器故障诊断的准确率,提出一种基于改进粒子群算法(PSO)优化SVM的变压器故障诊断方法。在对变压器故障进行诊断时采用支持向量机(SVM)与油中溶解气体分析(DGA)相结合的方法,利用PSO对SVM故障诊断模型进行参数寻优,并通过模拟退火算法(SA)改进PSO以提高PSO算法的全局搜索能力。对电力变压器故障诊断的实例分析结果表明,该方法不仅能够有效地进行变压器故障诊断,而且准确率高于传统的变压器故障诊断方法,更适合在变压器故障诊断中应用。

关键词(KeyWords)： 变压器;故障诊断;DGA;模拟退火算法;粒子群优化算法;SVM

Abstract:

Keywords:

基金项目(Foundation): 自治区科技人才培养项目:“万人计划”后备人选培养项目(QN2016YX0324);; 国家高层次人才特殊支持计划:青年拔尖新疆后备人才工程资助项目(新疆[2104]22)~~

作者(Author): 闵亚琪,马鑫,翟振刚,莫家庆,吕小毅

DOI: 10.16652/j.issn.1004-373x.2018.15.028

参考文献(References)：

• [1]DUVAL M,DE PABLO A.Interpretation of gas in oil analysis using new IEC publication 60599 and IEC TC 10 databases[J].IEEE electrical insulation magazine,2001,17(2):31-41.
• [2]TRIPATHY M,MAHESHWARI R P,VERMA H K.Power transformer differential protection base on optimal probabilistic neural network[J].IEEE transactions on power delivery,2010,25(1):102-112.
• [3]ZHANG Y,DING X,LIU Y,et al.An artificial neural network approach to transformer fault diagnosis[J].IEEE transactions on power delivery,1996,11(4):1836-1841.
• [4]陈伟根,潘翀,云玉新,等.基于小波网络及油中溶解气体分析的电力变压器故障诊断方法[J].中国电机工程学报,2008(7):121-126.CHEN Weigen,PAN Chong,YUN Yuxin,et al.Power transformer fault diagnosis method based on wavelet network and dissolved gas analysis in oil[J].Proceedings of the CSEE,2008(7):121-126.
• [5]MENG K,DONG Z Y,WANG D H,et al.A self-adaptive RBF neural network classifier for transformer fault analysis[J].IEEE transactions on power systems,2010,25(3):1350-1360.
• [6]公茂法,柳岩妮,王来河,等.基于混沌优化粒子群BP神经网络的电力变压器故障诊断[J].电测与仪表,2016,53(15):13-16.GONG Maofa,LIU Yanni,WANG Laihe,et al.Power transformer fault diagnosis based on chaotic optimized particle swarm BP neural network[J].Electrical measurement&instrumentation,2016,53(15):13-16.
• [7]李赢,舒乃秋.基于模糊聚类和完全二叉树支持向量机的变压器故障诊断[J].电工技术学报,2016,31(4):64-70.LI Ying,SHU Naiqiu.Transformer fault diagnosis based on fuzzy clustering and complete binary tree SVM[J].Transactions of China electrotechnical society,2016,31(4):64-70.
• [8]VAPNIK V N.The nature of statistical learning theory[M].New York:Springer Verlag,1995.
• [9]刘义艳,陈晨,亢旭红,等.基于支持向量机的变压器故障诊断[J].现代电子技术,2011,34(24):118-120.LIU Yiyan,CHEN Chen,KANG Xuhong,et al.Transformer fault diagnosis based on SVM[J].Modern electronics technique,2011,34(24):118-120.
• [10]张明慧.基于DGA的变压器故障诊断算法研究[D].淮南:安徽理工大学,2013.ZHANG Minghui.Research on transformer fault diagnosis algorithm based on DGA[D].Huainan:Anhui University of Science&Technology,2013.
• [11]仲元昌,万能飞,夏艳,等.基于油气参数分析的电力变压器故障分步式诊断算法[J].高电压技术,2014,40(8):2279-2284.ZHONG Yuanchang,WAN Nengfei,XIA Yan,et al.Stepwise diagnosis algorithm of power transformer fault based on analysis of oil and gas parameters[J].High voltage engineering,2014,40(8):2279-2284.
• [12]STEINBRUNN M,MOERKOTTE G,KEMPER A.Heuristic and randomized optimization for the join ordering problem[J].The VLDB journal,1997,6(3):8-17.
• [13]吕丹,童创明,钟卫军.基于粒子群和模拟退火算法的混合算法研究[J].计算机工程与设计,2011,32(2):663-666.LüDan,TONG Chuangming,ZHONG Weijun.Hybrid algorithm research based on particle swarm optimization and simulated annealing algorithm[J].Computer engineering and design,2011,32(2):663-666.
• [14]冯一博.基于粒子群思想改进支持向量机优化算法的研究[D].哈尔滨:哈尔滨理工大学,2013.FENG Yibo.Research on improvement of SVM optimization algorithm based on particle swarm optimization[D].Harbin:Harbin University of Science and Technology,2013.
• [15]KENNEDY J,EBERHART R.Particle swarm optimization[C]//Proceedings of 1995 IEEE International Conference on Neural Networks.[S.l.]:IEEE,1995:1942-1948.
• [16]杨光友.混合粒子群优化及其在嵌入式智能控制中的应用[D].武汉:武汉理工大学,2006:22-62.YANG Guangyou.Hybrid particle swarm optimization and its application in embedded intelligent control system[D].Wuhan:Wuhan University of Technology,2006:22-26.
• [17]郑含博,王伟,李晓纲,等.基于多分类最小二乘支持向量机和改进粒子群优化算法的电力变压器故障诊断方法[J].高电压技术,2014,40(11):3424-3429.ZHENG Hanbo,WANG Wei,LI Xiaogang,et al.Power transformer fault diagnosis method based on multi class least squares SVM and improved particle swarm optimization algorithm[J].High voltage engineering,2014,40(11):3424-3429.