电力变压器状态评估及故障诊断方法研究
|
摘要
电力变压器是电网中能量转换、传输的核心，是电网安全第一道防御系统中的关键枢纽设备。目前，我国已有较多变压器运行年限超过20年，这些运行中的变压器面临着日益严重的如设备故障和绝缘老化问题，发生事故的概率不断增加。变压器一旦发生事故可能会造成设备资产和大停电等巨大损失，甚至会产生严重的社会影响。因此，对电力变压器进行有效的状态评估和深入的故障诊断研究，指导变压器的运行维护和状态检修，预防和降低故障的发生几率，具有重要的理论和实际意义。
论文在搜集整理大量技术标准、规程导则、专家经验以及变压器实际运行状态数据的基础上，深入研究了电力变压器状态评估的指标体系、评估方法和决策准则以及基于支持向量机和智能优化算法的变压器故障诊断技术，对变压器状态评估的集对分析方法和模糊与证据推理融合的绝缘状态评估模型进行了研究，在以油中溶解气体为特征量的变压器故障诊断方法研究上取得了一定进展，论文取得的创新性成果主要有：
在对变压器状态等级划分和指标参数提取的基础上，针对状态信息具有模糊和信息不完全所致的不确定性问题，提出了基于集对分析理论的电力变压器状态评估策略，构建了集对分析算法及实现步骤，用联系度及其数学表达式统一描述系统状态的不确定性问题，并结合信度准则实现了对变压器状态的评估，为电力变压器状态评估提供了一种新的思路。
针对变压器绝缘状态评估中存在影响评估结果因素多、评估因素不相容且影响程度又不尽相同的难题，提出了基于模糊和证据推理融合的变压器绝缘状态合决策模型，构建了模糊隶属度函数来描述评估模型的因素层指标，根据模糊评估结果确定证据推理决策模型的原始基本概率分配，利用证据融合得到了辨识框架中基本概率分配函数，最后基于最大基本概率分配函数决策规则进行评估目标判定。
将多分类最小二乘支持向量机（LS-SVM）应用于电力变压器故障诊断中，通过组合编码构造多个二分类LS-SVM分类器实现多类分类。利用粒子群优化（PSO）算法获得LS-SVM分类模型的最优参数，应用交叉验证（CV）的思想来提高分类算法的整体泛化性能，并采用加州大学欧文分校机器学习数据库的基准数据集进行验证。变压器故障诊断实例分析表明，提出的基于PSO和LS-SVM分类方法对电力变压器进行故障诊断是准确和有效的；与传统的IEC三比值法、反向传播神经网络（BPNN）、径向基神经网络（RBFNN）及标准支持向量机（SVM）的变压器故障诊断方法相比，提出的方法在训练和测试阶段都获得了较高的准确率。
针对经典PSO算法在实际应用中容易陷入局部最优的缺点，提出了带时变加速系数的PSO算法（PSO-TVAC）优化SVM模型。引入动态惯性权重和加速系数，控制了PSO算法的开发（exploitation）和探索（exploration）能力，平衡了PSO的全局搜索和局部搜索性能，实验证明，基于改进PSO算法的故障诊断收敛速度快，计算精度高，诊断效果更好。
研究了基于支持向量机回归（SVR）理论的预测方法，建立了基于PSO-TVAC优化最小二乘支持向量机回归（LS-SVR）和小波最小二乘支持向量机回归（W-LSSVR）的变压器油中溶解气体预测模型，避免了传统SVR方法中回归问题未知变量数目的膨胀，同时简化了支持向量机回归的参数优化。实例研究表明，提出的油中溶解气体预测模型较BPNN、RBFNN、广义回归神经网络（GRNN）及ε-SVR预测方法相比，无论在预测精度和稳定性方面均具有很大的优势。
在研究变压器油中溶解气体预测实质的基础上，为了能够进一步掌握油中溶解气体的发展变化趋势，首次提出了基于模糊信息粒化支持向量机回归的油中气体区间预测方法。建立了模糊信息粒化的时序模型，不丧失时间序列所蕴含的主要信息的基础上简化了时序的表现形式，利用PSO-TVAC优化的支持向量机回归模型来训练粒化集样本，根据获得的信息粒预测区间，得到了油中溶解气体变化趋势的最大值、最小值和平均值水平，与实际信息相吻合。
A power transformer is the core of the energy conversion and transmission grid. Itis key hub power equipment in the first line of defense of the grid security. At present, ithas been more transformers in China whose operation periods are over20years. Thoserunning transformers are facing increasingly serious problems of such as equipmentfailure and insulation aging, and at the same time have increasing probabilities of anaccident. Transformer failure may cause huge losses of equipment assets and blackout,and even serious social impact. Therefore, the effective condition assessment and faultdiagnosis analysis for power transformers, to guide the operation and maintenance ofpower transformers and prevent and reduce the failure probability, have an importanttheoretical and practical significance.
This dissertation collects a large number of technical standards, regulations,expertise, and actual state information considering power transformers. Stating with that,the dissertation studies the condition assessment index system, assessing methods,decision-making criteria and fault diagnosis approaches based on support vectormachine theory with intelligent optimization algorithms for power transformers. Thetransformer assessing decision-making models, based on set pair analysis theory and afuzzy with evidential reasoning integrated approach respectively, are studied in thisdissertation. And the research on transformer fault diagnosis based on DGA has beenmade some breakthroughs. The main innovative achievements are obtained asfollowing.
Considering the uncertain problem that the transformer state information is fuzzyand incomplete, a condition assessment strategy based on set pair analysis theory isproposed on the basis of condition grade division and index parameter extraction. Andthe set pair algorithm and implementation steps are also constructed. The connectiondegrees and mathematical expressions are used for describing the uncertainty of states,and then combination of confidence criteria, the results of transformer conditionassessments are achieved. This method also offers a new way of condition assessmentfor power transformers.
Aiming at the problem that there are so many assessing factors and indices, whichmay reflect the different aspects of transformers and have different assessing weights,the decision-making assessment model based on fuzzy and evidence reasoning for transformer insulation condition is proposed in this dissertation. A fuzzy membershipfunction is constructed to describe the factor layer of evaluation model. According tothe fuzzy evaluation results, the original basic probability assignment, which is used fordecision-making model of evidential reasoning, is determined. Thus the basicprobability assignment is obtained by evidence reasoning, and finally the assessmentresults are determined based on the decision rules of the maximum basic probabilityassignment function.
The multi-classification least squares support vector machine (LS-SVM) is appliedto transformer fault diagnosis in this dissertation. And the multi-class classificationscheme is achieved by constructing more binary LS-SVM classifiers using combinationencoding. The optimal parameters of the LS-SVM classification model are obtained byusing particle swarm optimization (PSO) algorithm, and the overall generalizationperformance of the classification algorithm is improved by application of the idea ofcross validation (CV). The benchmark data sets in UCI machine learning database areemployed for validation. The cases of transformer fault diagnosis show that theproposed approach based on PSO and LS-SVM is accurate and effective. And theproposed approach has higher accuracies both in training and testing phases, comparedwith the transformer diagnosis methods of IEC three-ratio method, the back propagationneural network (BPNN), radial basis function neural network (RBFNN) and thestandard support vector machine (SVM).
For the shortcomings that the classical PSO algorithm is easy to fall into localoptimum in practical applications, the PSO with time-varying acceleration coefficients(PSO-TVAC) is proposed to optimize the SVM model. Through introducing of dynamicinertia weights and acceleration coefficients, the ability of exploitation and explorationcan be controlled, and the PSO performance of global search and local search can bebalanced. The cases show that the improved approach has a faster convergence speed,higher accuracy and better diagnosis result.
This dissertation studies the forecasting approaches based on support vectormachine regression (SVR) theory. The forecasting models of dissolved gases intransformer oil based on PSO-TVAC considering least squares support vector machineregression (LS-SVR) and wavelet least squares support vector machine regression(W-LSSVR) are established, which avoid the expansion of the number of unknownvariables in the traditional SVR method while simplify the parameter optimization forsupport vector machine regression. The case studies show that the proposed forecasting models both have a greater advantage in terms of prediction accuracy and stability thanthat of BPNN, RBFNN, generalized regression neural network (GRNN) and ε-SVRapproaches.
In order to achieve accurate trend forecasting of gas contents in oil-immersedtransformers, a fuzzy information granulated particle swarm optimization-supportvector machine regression model is firstly proposed in this dissertation on the basis ofresearching on forecasting the dissolved gases in transformer oil. The time seriesprediction model of fuzzy information granulation is established, which simplify themanifestation for the time series model, without loss of the main information in timeseries. The granulated sample sets are trained by SVR model with PSO-TVAC. And onthe basis of the obtained prediction intervals of the information granules, the maximum,minimum and average levels of the dissolved gas contents are given by the forecastingmodel, which consistent with the actual information.
论文在搜集整理大量技术标准、规程导则、专家经验以及变压器实际运行状态数据的基础上，深入研究了电力变压器状态评估的指标体系、评估方法和决策准则以及基于支持向量机和智能优化算法的变压器故障诊断技术，对变压器状态评估的集对分析方法和模糊与证据推理融合的绝缘状态评估模型进行了研究，在以油中溶解气体为特征量的变压器故障诊断方法研究上取得了一定进展，论文取得的创新性成果主要有：
在对变压器状态等级划分和指标参数提取的基础上，针对状态信息具有模糊和信息不完全所致的不确定性问题，提出了基于集对分析理论的电力变压器状态评估策略，构建了集对分析算法及实现步骤，用联系度及其数学表达式统一描述系统状态的不确定性问题，并结合信度准则实现了对变压器状态的评估，为电力变压器状态评估提供了一种新的思路。
针对变压器绝缘状态评估中存在影响评估结果因素多、评估因素不相容且影响程度又不尽相同的难题，提出了基于模糊和证据推理融合的变压器绝缘状态合决策模型，构建了模糊隶属度函数来描述评估模型的因素层指标，根据模糊评估结果确定证据推理决策模型的原始基本概率分配，利用证据融合得到了辨识框架中基本概率分配函数，最后基于最大基本概率分配函数决策规则进行评估目标判定。
将多分类最小二乘支持向量机（LS-SVM）应用于电力变压器故障诊断中，通过组合编码构造多个二分类LS-SVM分类器实现多类分类。利用粒子群优化（PSO）算法获得LS-SVM分类模型的最优参数，应用交叉验证（CV）的思想来提高分类算法的整体泛化性能，并采用加州大学欧文分校机器学习数据库的基准数据集进行验证。变压器故障诊断实例分析表明，提出的基于PSO和LS-SVM分类方法对电力变压器进行故障诊断是准确和有效的；与传统的IEC三比值法、反向传播神经网络（BPNN）、径向基神经网络（RBFNN）及标准支持向量机（SVM）的变压器故障诊断方法相比，提出的方法在训练和测试阶段都获得了较高的准确率。
针对经典PSO算法在实际应用中容易陷入局部最优的缺点，提出了带时变加速系数的PSO算法（PSO-TVAC）优化SVM模型。引入动态惯性权重和加速系数，控制了PSO算法的开发（exploitation）和探索（exploration）能力，平衡了PSO的全局搜索和局部搜索性能，实验证明，基于改进PSO算法的故障诊断收敛速度快，计算精度高，诊断效果更好。
研究了基于支持向量机回归（SVR）理论的预测方法，建立了基于PSO-TVAC优化最小二乘支持向量机回归（LS-SVR）和小波最小二乘支持向量机回归（W-LSSVR）的变压器油中溶解气体预测模型，避免了传统SVR方法中回归问题未知变量数目的膨胀，同时简化了支持向量机回归的参数优化。实例研究表明，提出的油中溶解气体预测模型较BPNN、RBFNN、广义回归神经网络（GRNN）及ε-SVR预测方法相比，无论在预测精度和稳定性方面均具有很大的优势。
在研究变压器油中溶解气体预测实质的基础上，为了能够进一步掌握油中溶解气体的发展变化趋势，首次提出了基于模糊信息粒化支持向量机回归的油中气体区间预测方法。建立了模糊信息粒化的时序模型，不丧失时间序列所蕴含的主要信息的基础上简化了时序的表现形式，利用PSO-TVAC优化的支持向量机回归模型来训练粒化集样本，根据获得的信息粒预测区间，得到了油中溶解气体变化趋势的最大值、最小值和平均值水平，与实际信息相吻合。
A power transformer is the core of the energy conversion and transmission grid. Itis key hub power equipment in the first line of defense of the grid security. At present, ithas been more transformers in China whose operation periods are over20years. Thoserunning transformers are facing increasingly serious problems of such as equipmentfailure and insulation aging, and at the same time have increasing probabilities of anaccident. Transformer failure may cause huge losses of equipment assets and blackout,and even serious social impact. Therefore, the effective condition assessment and faultdiagnosis analysis for power transformers, to guide the operation and maintenance ofpower transformers and prevent and reduce the failure probability, have an importanttheoretical and practical significance.
This dissertation collects a large number of technical standards, regulations,expertise, and actual state information considering power transformers. Stating with that,the dissertation studies the condition assessment index system, assessing methods,decision-making criteria and fault diagnosis approaches based on support vectormachine theory with intelligent optimization algorithms for power transformers. Thetransformer assessing decision-making models, based on set pair analysis theory and afuzzy with evidential reasoning integrated approach respectively, are studied in thisdissertation. And the research on transformer fault diagnosis based on DGA has beenmade some breakthroughs. The main innovative achievements are obtained asfollowing.
Considering the uncertain problem that the transformer state information is fuzzyand incomplete, a condition assessment strategy based on set pair analysis theory isproposed on the basis of condition grade division and index parameter extraction. Andthe set pair algorithm and implementation steps are also constructed. The connectiondegrees and mathematical expressions are used for describing the uncertainty of states,and then combination of confidence criteria, the results of transformer conditionassessments are achieved. This method also offers a new way of condition assessmentfor power transformers.
Aiming at the problem that there are so many assessing factors and indices, whichmay reflect the different aspects of transformers and have different assessing weights,the decision-making assessment model based on fuzzy and evidence reasoning for transformer insulation condition is proposed in this dissertation. A fuzzy membershipfunction is constructed to describe the factor layer of evaluation model. According tothe fuzzy evaluation results, the original basic probability assignment, which is used fordecision-making model of evidential reasoning, is determined. Thus the basicprobability assignment is obtained by evidence reasoning, and finally the assessmentresults are determined based on the decision rules of the maximum basic probabilityassignment function.
The multi-classification least squares support vector machine (LS-SVM) is appliedto transformer fault diagnosis in this dissertation. And the multi-class classificationscheme is achieved by constructing more binary LS-SVM classifiers using combinationencoding. The optimal parameters of the LS-SVM classification model are obtained byusing particle swarm optimization (PSO) algorithm, and the overall generalizationperformance of the classification algorithm is improved by application of the idea ofcross validation (CV). The benchmark data sets in UCI machine learning database areemployed for validation. The cases of transformer fault diagnosis show that theproposed approach based on PSO and LS-SVM is accurate and effective. And theproposed approach has higher accuracies both in training and testing phases, comparedwith the transformer diagnosis methods of IEC three-ratio method, the back propagationneural network (BPNN), radial basis function neural network (RBFNN) and thestandard support vector machine (SVM).
For the shortcomings that the classical PSO algorithm is easy to fall into localoptimum in practical applications, the PSO with time-varying acceleration coefficients(PSO-TVAC) is proposed to optimize the SVM model. Through introducing of dynamicinertia weights and acceleration coefficients, the ability of exploitation and explorationcan be controlled, and the PSO performance of global search and local search can bebalanced. The cases show that the improved approach has a faster convergence speed,higher accuracy and better diagnosis result.
This dissertation studies the forecasting approaches based on support vectormachine regression (SVR) theory. The forecasting models of dissolved gases intransformer oil based on PSO-TVAC considering least squares support vector machineregression (LS-SVR) and wavelet least squares support vector machine regression(W-LSSVR) are established, which avoid the expansion of the number of unknownvariables in the traditional SVR method while simplify the parameter optimization forsupport vector machine regression. The case studies show that the proposed forecasting models both have a greater advantage in terms of prediction accuracy and stability thanthat of BPNN, RBFNN, generalized regression neural network (GRNN) and ε-SVRapproaches.
In order to achieve accurate trend forecasting of gas contents in oil-immersedtransformers, a fuzzy information granulated particle swarm optimization-supportvector machine regression model is firstly proposed in this dissertation on the basis ofresearching on forecasting the dissolved gases in transformer oil. The time seriesprediction model of fuzzy information granulation is established, which simplify themanifestation for the time series model, without loss of the main information in timeseries. The granulated sample sets are trained by SVR model with PSO-TVAC. And onthe basis of the obtained prediction intervals of the information granules, the maximum,minimum and average levels of the dissolved gas contents are given by the forecastingmodel, which consistent with the actual information.
引文
[1] U.S.-Canada Power system outage task force. Final report [EB/OL]. http://reports.energy.gov/,March31,2003.
[2] G. Beck, D. Povh, D. Retzmann, E. Teltsch.全球大停电的经验教训[J].中国电力,2007,40(10):75-81.
[3]李春艳,孙元章,陈向宜,邓桂平.西欧“11.4”大停电事故的初步分析及防止我国大面积停电事故的措施[J].电网技术,2006,30(24):16-21.
[4]赵兴勇,张秀彬,何斌.电网大停电自组织临界性的概率统计分析法[J].电网技术,2008,32(20):60-63.
[5]孙才新.输变电设备状态在线监测与诊断技术现状和前景[J].中国电力,2005,38(2):1-7.
[6]胡超凡,陈刚,朱伟江,赵玉柱.2005年国家电网安全运行情况分析[J].中国电力,2006,39(5):1-4.
[7]胡超凡,董昱,王轶禹,赵玉柱.2006年国家电网安全运行情况分析[J].中国电力,2007,40(5):23-27.
[8]赵晔,罗治强,赵玉柱.2007年国家电网安全运行情况分析[J].中国电力,2008,41(5):65-69.
[9]罗治强,董昱,胡超凡.2008年国家电网安全运行情况分析[J].中国电力,2009,42(5):8-12.
[10]马珂,王轶禹,董昱.2009年国家电网安全运行情况分析[J].中国电力,2010,43(11):1-4.
[11]孙建锋,葛睿,郑力,胡超凡.2010年国家电网安全运行情况分析[J].中国电力,2011,44(5):1-4.
[12]孙才新,陈伟根,李俭,等.电气设备油中气体在线监测及故障诊断技术[M].北京:科学出版社,2003.
[13]程志华,章剑光.状态检修技术及其辅助分析系统的应用[J].电网技术,2003,27(7):16-18.
[14] N. Dominelli, A. Rao, P. Kundur. Life extension and condition assessment: techniques for anaging utility infrastructure[J]. IEEE Power and Energy Magazine,2006,4(3):25-35.
[15]熊浩,孙才新,杜鹏,等.基于物元理论的电力变压器状态综合评估[J].重庆大学学报（自然科学版）,2006,29(10):24-28.
[16]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.
[17]廖瑞金,王谦,骆思佳,等.基于模糊综合评判的电力变压器运行状态评估模型[J].电力系统自动化,2008,32(3):70-75.
[18] Y. Zhang, X. Ding, Y. Liu, P. J. Griffin. An artificial neural network approach to transformerfault diagnosis[J]. IEEE Trans. Power Del.,1996,11(4):1836-1841.
[19] J. L. Guardado, J. L. Naredo, P. Moreno, C. R. Fuerte. A comparative study of neural networkefficiency in power transformers diagnosis using dissolved gas analysis[J]. IEEE Trans. PowerDel.,2001,16(4):643-647.
[20] W. H. Tang, J. Y. Goulermas, Q. H. Wu, Z. J. Richardson, J. Fitch. A probabilistic classifier fortransformer dissolved gas analysis with a particle swarm optimizer[J]. IEEE Trans. Power Del.,2008,23(2):751-759.
[21] Z. Yang, W. H. Tang, A. Shintemirov, Q. H. Wu. Association rule mining-based dissolved gasanalysis for fault diagnosis of power transformers[J]. IEEE Trans. Syst., Man, Cybern., Part C:Appl. Rev.,2009,39(6):597-610.
[22] A. Chatterjee, N. K. Roy. Health monitoring of power transformers by dissolved gas analysisusing regression method and study the effect of filtration on oil[J]. World Academy of Science,Engineering and Technology,2009,5(59):37-42.
[23] B. H. Ward. A survey of New Techniques in Insulation Monitoring of Power Transformers[J].IEEE Electrical Insulation Magazine,2001,17(3):16-23.
[24]崔雪梅.以复小波提取局部放电信号特征的原理及方法研究[D].重庆大学博士学位论文,2004.
[25] Ekard Grossmann, Kurt Feser. Sensitive online PD-measurements of onsite oil/paper-insulateddevices by means of optimized acoustic emission techniques (AET)[J]. IEEE Trans. on PowerDelivery,2005,20(1):158-162.
[26] M. S. Sachdev, T. S. Sidhu, M. C. Wood. A digital relaying algorithm for deteting transformerwinding faults[J]. IEEE Transactions on Power Delivery,1989,4(3):1638-148.
[27]熊浩.电力变压器绝缘状态综合评估方法研究[D]．重庆大学博士学位论文,2003.
[28] R. Blue, D. Uttamchandani, O. Farish. Determination of FFA concentration in transformer oilby fluorescence measurements[J]. IEEE Transactions on Dielectrics and Electrical Insulation,1998,5(6):892-895.
[29] Lijun Yang, Ruijin Liao, Caixin Sun, et al. Influence of natural ester on thermal agingcharacteristics of oil–paper in power transformers[J]. European Transactions on ElectricalPower,2009,20(8):1223-1236.
[30] T. K. Saha. Review of modern diagnostic techniques for assessing insulation condition in agedtransformers[J]. IEEE Trans. Dielectr. Electr. Insul.,2003,10(5):903-917.
[31] M. H. Wang, C. P. Hung. Novel grey model for the prediction of trend of dissolved gases inoil-filled power apparatus[J]. Electr. Power Syst. Res.,2003,67(1):53-58.
[32] M. H. Wang. Grey-extension method for incipient fault forecasting of oil-immersed powertransformer[J]. Electr. Power Compon. Syst.,2004,32(10):959-975.
[33] J. Singh, Y. R. Sood, R. K. Jarial, P. Verma. Condition monitoring of powertransformers-bibliography survey[J]. IEEE Elect. Insul. Mag.,2008,24(3):11-25.
[34] S. W. Fei, Y. Sun. Forecasting dissolved gases content in power transformer oil based onsupport vector machine with genetic algorithm[J]. Electr. Power Syst. Res.,2008,78(3):507-514.
[35]肖燕彩.支持向量机在变压器状态评估中的应用研究[D].北京交通大学博士学位论文,2008.
[36] H. T. Yang，C. C. Liao, J. H. Chou．Fuzzy learning vector quantization networks for powertransformer condition assessment[J]．IEEE Transactions on Dielectrics and Electrical Insulation,2001,8(1):143-149.
[37] W. H. Tang, K. Spurgeon, Q. H. Wu, Z. J. Richardson. An evidential reasoning approach totransformer condition assessments[J]. IEEE Trans. Power Del.,2004,19(4):1696-1703.
[38] V. Sokolov, Z. Berler, V. Rashkes. Effective methods of assessment of insulation systemconditions in power transformers: a view based on practical experience[C]. ElectricalInsulation Conference and Electrical Manufacturing&Coil Winding Conference, Cincinnati,Oct.1999:659-667.
[39]黄华,傅晨钊.大型电力变压器状态分析综述[J].华东电力,2004,32(3):24-26.
[40] E. Rivas, J. C. Burgos, J. C. García-Prada. Condition assessment of power OLTC by vibrationanalysis using wavelet transform[J]. IEEE Transactions on Power Delivery,2009,24(2):687-694.
[41]吴立增.变压器状态评估方法的研究[D].华北电力大学博士学位论文,2005.
[42]袁志坚,孙才新,袁张渝,等.变压器健康状态评估的灰色聚类决策方法[J].重庆大学学报,2005,28(3):22-25.
[43] M. Arshad, S. M. Islam. Significance of cellulose power transformer condition assessment[J].IEEE Transactions on Dielectrics and Electrical Insulation,2011,18(5):1591-1598.
[44]郭创新,高振兴,张健,等.油浸式电力变压器状态评估模型及方法[J].控制工程,2011,18(6):881-885.
[45]谢红玲,律方成.基于信息融合的变压器状态评估方法研究[J].华北电力大学学报,2006,33(2):8-11.
[46]程崯,王宇,余轩,毛志强.电力变压器运行状态综合评判指标的权重确定[J].中国电力,2011,44(4):26-30.
[47]廖瑞金,黄飞龙,杨丽君,等.多信息量融合的电力变压器状态评估模型[J].高电压技术,2010,36(6):1455-1460.
[48]赵文清,朱永利,姜波,等.基于贝叶斯网络的电力变压器状态评估[J].高电压技术,2008,34(5):1032-1039.
[49]郑蕊蕊,赵继印,吴宝春,等.基于加权灰靶理论的电力变压器绝缘状态分级评估方法[J].电工技术学报,2008,23(8):60-66.
[50]王昌长,李福祺,高胜友,等.电气设备的在线监测与故障诊断技术[M].北京:清华大学出版社,2006.
[51] GB/T7252-2001.变压器油中溶解气体分析和判断导则.2001.
[52]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,(1):22-26.
[53] B. Fallou, F. Viale, Davies, et al. Application of physical-chemical methods of analysis to thestudy of deterioration in the insulation of electrical apparatus[C]. CIGER, Paris, France,1970:Rep.15-07.
[54] IEC Publication599. Interpretation for the analysis of gases in transformers and oil-filledelectrical equipment in service.1978.
[55] R. R. Rogers. IEEE and IEC codes to interpret incipient faults in transformers using gas in oilanalysis[J]. IEEE Trans. Electr. Insul.,1978,EI-13(5):349-353.
[56]潘翀.电力变压器绝缘故障诊断技术及热状态参量预测模型研究[D].重庆大学博士学位论文,2009.
[57]操敦奎.变压器油中气体分析诊断与故障检查[M].北京:中国电力出版社,2005.
[58] M. Duval. Dissolved gases analysis: it can save your transformer[J]. IEEE Elect. Insul. Mag.,1989,5(6):22-27.
[59] M. Duval and A. dePablo. Interpretation of gas-in-oil analysis using new IEC publication60599and IEC TC10databases[J]. IEEE Elect. Insul. Mag.,2001,17(2):31-41.
[60] IEEE Std. C57.104-2008. IEEE Guide for the Interpretation of Gases Generated inOil-Immersed Transformers.2008.
[61] I. A. Zadeh. Fuzzy sets[J]. Inform. Control,1965,8(3):338-353.
[62] K. Tomsovic, M. Tapper, T. Ingvarsson. A fuzzy information approach to integrating differenttransformer diagnostic methods[J]. IEEE Trans. Power Del.,1993,8(3):1638-1646.
[63] Y. C. Huang, H. T. Yang, C. L. Huang. Developing a new transformer fault diagnosis systemthrough evolutionary fuzzy logic[J]. IEEE Trans. Power Del.,1997,12(2):761-767.
[64] A. P. Chen, C. C. Lin. Fuzzy approaches for fault diagnosis of transformers[J]. Fuzzy Sets andSystems,2001,118(1):139-151.
[65] D. R. Morais, J. R. da Silva, J. G. Rolim. A fuzzy system for detection of incipient faults intransformers based on the dissolved gas analysis of insulation oil[C]. Proc.5th IEEE Int. Symp.Diagnostics Electr. Machines, Power Electronics and Drives, Vienna, Sept.2005:1-6.
[66] M. S. Kalavathi, B. R. Reddy, B. P. Singh. Transformer fault diagnosis using fuzzy logic andneural network[C]. Annual Report Conf. Electrical Insulation and Dielectric Phenomena, Oct.2005:486-489.
[67] L. Xie, L. Zhou, X. J. Tong, M. Y. Chen. Fault diagnosis of power transformer insulation basedon fuzzy normal partition and logic reasoning[C]. Proc. Int. Conf. Machine Learning andCybernetics, Hong Kong, Aug.2007:1081-1085.
[68]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.
[69] Q. Su, C. Mi, L. L. Lai, P. Austin. A fuzzy dissolved gas analysis method for the diagnosis ofmultiple incipient faults in a transformer[J]. IEEE Trans. on Power Systems,2000,15(2):593-598.
[70]张鸣柳,孙才新.变压器油中溶解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.
[71]孙才新,郭俊峰,廖瑞金,等.变压器油中溶解气体分析中的模糊模式多层聚类故障诊断方法的研究[J].中国电机工程学报,2001,21(2):37-41.
[72]王建元,纪延超.模糊Petri网络知识表示方法及其在变压器故障诊断中的应用[J].中国电机工程学报,2003,23(1):121-125.
[73]李俭,孙才新,陈伟根,等.灰色聚类与模糊聚类集成诊断变压器内部故障的方法研究[J].中国电机工程学报,2003,23(2):112-115.
[74]符杨,江玉蓉,崔椿洪,等.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.
[75]熊浩,李卫国,畅广辉,等.模糊粗糙集理论在变压器故障诊断中的应用[J].中国电机工程学报,2008,28(7):141-147.
[76]符杨,田振宁,江玉蓉,等.加权模糊核聚类法在电力变压器故障诊断中的应用[J].高电压技术,2010,36(2):371-374.
[77] C. E. Lin, J. M. Ling, C. L. Huang. An expert system for transformer fault diagnosis usingdissolved gas analysis[J]. IEEE Trans. Power Del.,1993,8(1):231-238.
[78]廖瑞金.变压器绝缘故障诊断黑板型专家系统和基于遗传算法的故障预测研究[D].重庆大学博士学位论文,2003.
[79] P. Purkait, S. Chakravorti. Time and frequency domain analyses based expert system forimpulse fault diagnosis in transformers[J]. IEEE Trans. Dielect. Elect. Insulation,2002,9(3):433-445.
[80]何定,唐国庆,陈珩.电力变压器故障诊断专家系统TFDES[J].电力系统自动化,1993,17(7):32-35.
[81]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.
[82]束洪春,孙向飞,司大军.电力变压器故障诊断专家系统知识库建立和维护的粗糙集方法[J].中国电机工程学报,2002,22(2):31-35.
[83]廖瑞金,姚陈果,孙才新,等.基于人工智能的电力变压器绝缘故障诊断面向对象知识库[J].电工技术学报,2001,16(6):59-64.
[84]孙才新,郭俊峰,曹毅,等.基于行为的变压器油色谱分析模型诊断专家系统研究[J].电工技术学报,2001,16(3):49-52.
[85]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.
[86]王财胜,孙才新,廖瑞金.变压器色谱监测中的BPNN故障诊断法[J].电网技术,1997,17(5):323-325.
[87]徐文,王大忠,周泽存,等.结合遗传算法的人工神经网络在电力变压器故障诊断中的应用[J].中国电机工程学报,1997,17(2):109-112.
[88]高文胜,钱政,严璋.基于决策树神经网络模型的电力变压器故障诊断方法[J].西安交通大学学报,1999,33(6):11-16.
[89]刘那,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.
[90]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.
[91]彭宁云,文习山,舒翔.模糊神经网络在变压器故障诊断中的应用[J].高电压技术,2004,30(5):14-17.
[92]章剑光,周浩,项灿芳.基于Super SAB神经网络算法的主变压器故障诊断模型[J].电工技术学报,2004,19(7):49-52.
[93]章剑光,周浩,盛晔.基于RPROP神经网络算法的主变DGA故障诊断模型[J].电力系统自动化,2004,28(14):63-66.
[94]周建华,胡敏强.自构形神经网络在变压器故障诊断中的应用[J].电工技术学报,2004,19(9):77-81.
[95]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].电工技术学报,2010,30(22):64-70.
[96] W. G. Chen, C. Pan, Y. X. Yun, Y. L. Liu. Wavelet networks in power transformers diagnosisusing dissolved gas analysis[J], IEEE Trans. on Power Delivery,2009,24(1):187-194.
[97]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的研究[J].中国电机工程学报,2006,26(3):119-124.
[98]邓宏贵,罗安,曹建,等.基因多点交叉遗传算法在变压器故障诊断中的应用[J].电网技术,2004,28(24):1-4.
[99]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.
[100]孙才新,李俭,郑海平,等.基于面积关联度分析的电力变压器绝缘故障诊断方法[J].电网技术,2002,26(7):24-29.
[101]杨廷方,李景禄,曾祥君,等.基于多种方法组合诊断模型的大型变压器故障诊断[J].电力系统自动化,2009,33(20):92-95.
[102]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.
[103]莫娟,王雪,董明,等.基于粗糙集理论的电力变压器故障诊断方法[J].中国电机工程学报,2004,24(7):162-167.
[104]董明,屈彦明,周孟戈,等.基于组合决策树的油浸式电力变压器故障诊断[J].中国电机工程学报,2005,25(16):35-41.
[105]王永强,律方成,李和明.基于贝叶斯网络和油中溶解气体分析的变压器故障诊断算法[J].电工技术学报,2004,19(12):74-77.
[106]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.
[107]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.
[108]陈江波,文习山,蓝磊,等.基于新径向基函数网络的变压器故障诊断法[J].高电压技术,2007,33(3):140-143.
[109]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.
[110]V. N. Vapnik. The Nature of Statistical Learning Theory[M]. New York, Springer-Verlag,1998.
[111]吕干云,程浩忠,董立新,等.基于多级支持向量机分类器的电力变压器故障识别[J].电力系统自动化学报,2005,17(1):19-22.
[112]S. W. Fei, M. J. Wang, Y. B. Miao, et al. Particle swarm optimization-based support vectormachine for forecasting dissolved gases content in power transformer oil[J]. EnergyConversion and Management,2009,50(6):1604-1609.
[113]F. E. H. Tay, L. J. Cao. Application of support vector machines in financial time seriesforecasting[J]. Omega-International Journal of Management Science,2001,29(4):309-317.
[114]Q. Wu. The forecasting model based on wavelet v-support vector machine[J]. Expert Syst.Appl.,2009,36(4):7604-7610.
[115]R. E. James, Q. Su. Condition Assessment of High Voltage Insulation in Power SystemEquipment[M]. London, The Institution of Engineering and Technology,2008.
[116]罗运柏,于萍,宁斌,等.用灰色模型预测变压器油中溶解气体的含量[J].中国电机工程学报,2001,21(3):65-69.
[117]赵文清.基于数据挖掘的变压器故障诊断和预测研究[D].华北电力大学博士学位论文,2009.
[118]费胜巍,孙宇.融合粗糙集与灰色理论的电力变压器故障预测[J].中国电机工程学报,2008,28(16):154-160.
[119]杨廷方,刘沛,李浙,等.应用新型多方法组合预测模型估计变压器油中溶解气体深度[J].中国电机工程学报,2008,28(31):108-113.
[120]C. C. Chang, C. J. Lin. LIBSVM–A library for support vector machines.[Online]. Available:http://www.csie.ntu.edu.tw/~cjlin/libsvm.2001.
[121]T. Van Gestel, J. A. K. Suykens, D. E. Baestaens. Financial time series prediction using leastsquares support vector machines within the evidence framework[J]. IEEE Trans. NeuralNetworks,2001,12(4):809-821.
[122]Y. Zhang, Y. C. Liu. Traffic forecasting using least squares support vector machines[J].Transportmetrica,2009,5(3):193-213.
[123]P. F. Pai, W. C. Hong. Forecasting regional electricity load based on recurrent support vectormachines with genetic algorithms[J]. Electric Power Systems Research,2005,74(3):417-425.
[124]赵文清,朱永利,张小奇.应用支持向量机的变压器故障组合预测[J].中国电机工程学报,2008,28(25):14-19.
[125]Z. Yang, X. S. Gu, X. Y. Liang, L. C. Ling. Genetic algorithm-least squares support vectorregression based predicting and optimizing model on carbon fiber composite integratedconductivity[J]. Materials&Design,2010,31(3):1042-1049.
[126]DL/5961996.电力设备预防性试验规程.1996.
[127]廖玉祥.一种电力变压器运行状态综合评估模型的研究[D]．重庆大学硕士学位论文,2006.
[128]骆思佳.电力变压器运行状态分级评估模型的研究[D]．重庆大学硕士学位论文,2008.
[129]国家电网公司生产技术部.设备状态检修规章制度和技术标准汇编[S].北京:中国电力出版社,2008.
[130]李诚.预防性试验对电力变压器的有效性分析[J].华中电力,2002,15(6):29-32.
[131]陈人翔,工寅仲,海世杰.绝缘电阻试验判断变压器绝缘的判据探讨[J].高电压技术,2004,30(10):21-22.
[132]李军.变压器铁芯多点接地故障的检测及处理方法[J].青海电力,2001,(2):50-51.
[133]陈化钢.电力设备预防性试验方法及诊断技术[M].北京:中国水利水电出版社,2009.
[134]王谦.基于模糊理论的电力变压器运行状态综合评估方法研究[D]．重庆大学硕士学位论文,2005.
[135]祝景中.浅谈变压器油中的水分[J].中国电力,1999,29(3):61-62.
[136]姚化亭,刘国跃.变压器油介损异常原因及处理[J].农村电气化,2006,(4):56-57.
[137]J. M. K. MacAlpine,张潮海.糠醛浓度判断变压器绝缘纸寿命的综述[J].高电压技术,2001,27(4):63-67.
[138]向彬,廖瑞金,杨丽君,等.变压器矿物油中糠醛的稳定性研究[J].高电压技术,2007,33(8):85-87.
[139]徐志强,刘阳,赵敏乔,等.油中糠醛浓度判定变压器固体绝缘劣化程度的研究[J].电力建设,2010,31(2):36-38.
[140]国家电网公司.110(66)kV~500kV油浸式变压器（电抗器）检修规范[S].2005.
[141]胡惠然,魏光华.湖北电网110kV及以上有载分接开关统计分析[J].湖北电力,2001,25(1):38-43.
[142]韩洪刚,王海宽.电力变压器分接开关故障及其检测技术[J].变压器,2004,41(12):35-38.
[143]孙国彬.大型电力变压器的非电量保护[J].电气时代,2004,(2):72-73.
[144]王志方.气体继电器与变压器运行时的安全[J].变压器,2005,42(9):40-41.
[145]杨保初,刘晓波,戴玉松.高电压技术[M].重庆:重庆大学出版社,2009.
[146]严璋,朱德恒.高电压绝缘技术[M].北京:中国电力出版社,2007.
[147]T. L. Saaty. The Analytic Hierarchy Process[M]. McGraw-Hill, New York,1980.
[148]梁梁,盛昭翰,徐南荣.一种改进的层次分析法[J].系统工程,1989,7(3):5-7.
[149]梁梁,余磊.对《一种改进的AHP法》的补注[J].系统工程,1991,9(3):64-65.
[150]IEEE Std. C57.140. IEEE Guide for the Evaluation and Reconditioning of Liquid ImmersedPower Transformers.2006.
[151]顾煜炯,董玉亮,杨昆.基于模糊评判和RCM分析的发电设备状态综合评价[J].中国电机工程学报,2004,24(6):189-194.
[152]赵克勤.集对分析及其初步应用[M].杭州:浙江科学技术出版社,2000.
[153]王栋,朱元甡,赵克勤.基于集对分析和模糊集合论的水体营养化评价[J].水文,2004,24(3):9-13.
[154]W. S. Wang, J. L. Jin, J. Ding, et al. A new approach to water resources system assessment—setpair analysis method[J]. Science in China Series E: Technological Sciences,2009,52(10):3017-3023.
[155]金华征,程浩忠,杨晓梅,等.模糊集对分析法应用于计及ATC的多目标电网规划[J].电力系统自动化,2005,29(21):45-49.
[156]程乾生.属性识别理论模型及其应用[J].北京大学学报（自然科学版）,1997,33(1):12-20.
[157]J. B. Yang, M. G. Singh. An evidential reasoning approach for multiple-attribute decisionmaking with uncertainty[J]. IEEE Trans. Syst., Man, Cybern.,1994,24(1):1-18.
[158]IEEE Std.637-1985. IEEE Guide for the Reclamation of Insulating Oil and Criteria for Its Use.1985.
[159]IEEE Std. C57.125-1991. IEEE Guide for Failure Investigation, Documentation, and Analysisfor Power Transformers and Shunt Reactors.1991.
[160]IEEE Std. C57.106-2006. IEEE Guide for Acceptance and Maintenance of Insulating Oil inEquipment.2006.
[161]J. Yen, L. Wang. Fuzzy logic–a modern perspective[J]. IEEE Trans. Knowledge Data Eng.,1999,11(1):153-165.
[162]G. Deschrijver, E. E. Kerre. On the relationship between some extensions of fuzzy set theory[J].Fuzzy Sets and Systems,2003,133(2):227-235.
[163]F. Herrera, E. Herrera-Viedma, L. Martinez. A fusion approach for managing multi-granularitylinguistic term sets in decision making[J]. Fuzzy Sets and Systems,2000,114(1):43-58.
[164]龚本刚.基于证据理论的不完全信息多属性决策方法研究[D].中国科学技术大学博士学位论文,2007.
[165]肖明珠.基于证据理论的不确定性处理研究及其在测试中的应用[D].电子科技大学博士学位论文,2008.
[166]彭宁云.基于DGA技术的变压器故障智能诊断系统研究[D].武汉大学博士学位论文,2004.
[167]孙永奎.基于支持向量机的模拟电路故障诊断方法研究[D].电子科学大学博士学位论文,2009.
[168]W. S. Sarle. Neural Network FAQ.[Online]. Available:ftp://ftp.sas.com/pub/neural/FAQ2.html.
[169]李烨.基于支持向量机的集成学习研究[D].上海交通大学博士学位论文,2007.
[170]V. N. Vapnki, A. Chervonenkis. On the uniform convergence of relative frequencies of eventsto their probabilities[J]. Theory Probab. Apl.,1971,16:264-280.
[171]段华.支持向量机的增量学习算法研究[D].上海交通大学博士学位论文,2008.
[172]J. Weston, C. Watkins. Multi-class support vector machines[C]. Proc. ESANN99, M. Verleysen,Ed., Brussels, Belgium,1999.
[173]T. VAN. Gestel, J. A. K. Suykens, B. Baesens, et al. Benchmarking least squares support vectormachine classifiers[J]. Machine Learning,2004,54,(1):5-32.
[174]A. Mathur, G. M. Foody. Multiclass and binary SVM classification: Implications for trainingand classification users[J]. IEEE Geos. Remote Sens. Letters,2008,5,(2):241-245.
[175]A. Passerini, M. Pontil, P. Frasconi. New results on error correcting output codes of kernelmachines[J]. IEEE Trans. Neural Networks,2004,15,(1):45-54.
[176]C. W. Hsu, C. J. LIN. A comparison of methods for multiclass support vector machines[J].IEEE Trans. Neural Networks,2002,13,(2):415-425.
[177]T. G. Dietterich, G. Bakiri. Solving multiclass learning problems via error-correcting outputcodes[J]. Journal of Artificial Intelligence Research,1995,2:263-286.
[178]T. Van Gestel, J. A. K. Suykens, G. Lanckriet. Multiclass LS-SVMs: moderated outputs andcoding-decoding schemes[J]. Neural Processing Letters,2002,15(1):45-48.
[179]甘良志.核学习算法与集成方法研究[D].浙江大学博士学位论文,2010.
[180]J. C. Platt. Fast training of support vector machines using sequential minimal optimization[M].Advances in Kernel Methods-Support Vector Learning, Cambridge, MA:MIT Press,1998.
[181]J. A. K. Suykens, T. Van Gestel, J. De Brabanter, et al. Least Squares Support VectorMachines[M]. World Scientific, Singapore,2002.
[182]S. S. Keerthi, C. J. Lin. Asymptotic behaviors of support vector machines with Gaussiankernel[J]. Neural Computation,2003,15(7):1667-1689.
[183]甘良志.核学习算法与集成方法研究[D].浙江大学博士学位论文,2005.
[184]张丽平.粒子群优化算法的理论及实践[D].浙江大学博士学位论文,2005.
[185]J. Kennedy, R. C. Eberhart. Particle swarm optimization[C]. Proc. IEEE Int. Conf. NeuralNetworks,1995,4:1942-1948.
[186]A. Frank, A. Asuncion. UCI machine learning repository.[Online]. Available:http://archive.ics.uci.edu/ml.2010.
[187]K. Meng, Z. Y. Dong, D. H. Wang, et al. A self-adaptive RBF neural network classifier fortransformer fault analysis[J]. IEEE Trans. Power Syst.,2010,25,(3):1350-1360.
[188]Y. Shi, R. C. Eberhart. Empirical study of particle swarm optimization[J]. Proc. IEEE Int.Congr. Evolut. Comput.,1999,3,(1):101-106.
[189]A. Ratnaweera, S. K. Halgamuge, H. C. Watson. Self-organizing hierarchical particle swarmoptimizer with time-varying acceleration coefficients[J]. IEEE Trans. Evolut. Comput.,2004,8,(3):240-255.
[190]A. J. Smola, B. Scholkopf. A tutorial on support vector regression[J]. Statistics and Computing,2004,14,(3):199-222.
[191]C. de Boor. A practical guide to splines[M]. New York, Springer-Verlag,1978.
[192]A. J. Smola, B. Sch lkopf, K. Müller. The connection between regularization operators andsupport vector kernels[J]. Neural Networks,1998,11(4):637-649.
[193]Q. H. Zhang, A. Benveniste. Wavelet networks[J]. IEEE Trans. Neural Networks,1992,3(6):889-898.
[194]L. Zhang, W. D. Zhou, L. C. Jiao. Wavelet support vector machine[J]. IEEE Trans. Syst., Man,Cybern., Part B: Cybernetics,2004,34(1):34-39.
[195]董克强.时间序列的信息粒化及基于粒化的聚类分析[D].北京师范大学硕士学位论文,2005.
[196]C. Kao, C. L. Chyu. A fuzzy linear regression model with better explanatory power[J]. FuzzySets Syst.,2002,126,(3):401-409.
[197]Y. S. Ding, X. P. Song, Y. M. Zen. Forecasting financial condition of Chinese listed companiesbased on support vector machine[J]. Expert Syst. Appl.,2008,34,(4):3081-3089.
[198]W. Q. Lin, J. H. Jiang, Y. P. Zhou, et al. Support vector machine based training of multilayerfeedforward nueral networks as optimized by particle swarm algorithm: application in QSARstudies of bioactivity of organic compounds[J]. J. Comput. Chem.,2007,28,(2):519-527.
[199]L. A. Zadeh. Toward a theory of fuzzy information granulation and its centrality in humanreasoning and fuzzy logic[J]. Fuzzy Sets Syst.,1997,90,(1):111-127.
[200]W. Z. Wu, M. Zhang, H. Z. Li. Knowledge reduction in random information systems viaDempster-Shafer theory of evidence[J]. Inform. Sciences,2005,174,(3-4):143-164.
[201]Z. Pawlak, A. Skowron. Rudiments of rough sets[J]. Inform. Sciences,2007,177,(1):3-27.
[202]R. Xu, D. Wunsch. Survey of clustering algorithms[J]. IEEE Trans. Neural Networks,2005,16,(3):645-678.
[203]W. Pedrycz, A. Gacek. Temporal granulation and its application to signal analysis[J]. Inform.Sciences,2002,143,(1-4):47-71.
[204]F. S. Yu, W. Pedrycz. The design of fuzzy information granules: tradeoffs between specificityand experimental evidence[J]. Appl. Soft Comput.,2009,9,(1):264-273.
[2] G. Beck, D. Povh, D. Retzmann, E. Teltsch.全球大停电的经验教训[J].中国电力,2007,40(10):75-81.
[3]李春艳,孙元章,陈向宜,邓桂平.西欧“11.4”大停电事故的初步分析及防止我国大面积停电事故的措施[J].电网技术,2006,30(24):16-21.
[4]赵兴勇,张秀彬,何斌.电网大停电自组织临界性的概率统计分析法[J].电网技术,2008,32(20):60-63.
[5]孙才新.输变电设备状态在线监测与诊断技术现状和前景[J].中国电力,2005,38(2):1-7.
[6]胡超凡,陈刚,朱伟江,赵玉柱.2005年国家电网安全运行情况分析[J].中国电力,2006,39(5):1-4.
[7]胡超凡,董昱,王轶禹,赵玉柱.2006年国家电网安全运行情况分析[J].中国电力,2007,40(5):23-27.
[8]赵晔,罗治强,赵玉柱.2007年国家电网安全运行情况分析[J].中国电力,2008,41(5):65-69.
[9]罗治强,董昱,胡超凡.2008年国家电网安全运行情况分析[J].中国电力,2009,42(5):8-12.
[10]马珂,王轶禹,董昱.2009年国家电网安全运行情况分析[J].中国电力,2010,43(11):1-4.
[11]孙建锋,葛睿,郑力,胡超凡.2010年国家电网安全运行情况分析[J].中国电力,2011,44(5):1-4.
[12]孙才新,陈伟根,李俭,等.电气设备油中气体在线监测及故障诊断技术[M].北京:科学出版社,2003.
[13]程志华,章剑光.状态检修技术及其辅助分析系统的应用[J].电网技术,2003,27(7):16-18.
[14] N. Dominelli, A. Rao, P. Kundur. Life extension and condition assessment: techniques for anaging utility infrastructure[J]. IEEE Power and Energy Magazine,2006,4(3):25-35.
[15]熊浩,孙才新,杜鹏,等.基于物元理论的电力变压器状态综合评估[J].重庆大学学报（自然科学版）,2006,29(10):24-28.
[16]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.
[17]廖瑞金,王谦,骆思佳,等.基于模糊综合评判的电力变压器运行状态评估模型[J].电力系统自动化,2008,32(3):70-75.
[18] Y. Zhang, X. Ding, Y. Liu, P. J. Griffin. An artificial neural network approach to transformerfault diagnosis[J]. IEEE Trans. Power Del.,1996,11(4):1836-1841.
[19] J. L. Guardado, J. L. Naredo, P. Moreno, C. R. Fuerte. A comparative study of neural networkefficiency in power transformers diagnosis using dissolved gas analysis[J]. IEEE Trans. PowerDel.,2001,16(4):643-647.
[20] W. H. Tang, J. Y. Goulermas, Q. H. Wu, Z. J. Richardson, J. Fitch. A probabilistic classifier fortransformer dissolved gas analysis with a particle swarm optimizer[J]. IEEE Trans. Power Del.,2008,23(2):751-759.
[21] Z. Yang, W. H. Tang, A. Shintemirov, Q. H. Wu. Association rule mining-based dissolved gasanalysis for fault diagnosis of power transformers[J]. IEEE Trans. Syst., Man, Cybern., Part C:Appl. Rev.,2009,39(6):597-610.
[22] A. Chatterjee, N. K. Roy. Health monitoring of power transformers by dissolved gas analysisusing regression method and study the effect of filtration on oil[J]. World Academy of Science,Engineering and Technology,2009,5(59):37-42.
[23] B. H. Ward. A survey of New Techniques in Insulation Monitoring of Power Transformers[J].IEEE Electrical Insulation Magazine,2001,17(3):16-23.
[24]崔雪梅.以复小波提取局部放电信号特征的原理及方法研究[D].重庆大学博士学位论文,2004.
[25] Ekard Grossmann, Kurt Feser. Sensitive online PD-measurements of onsite oil/paper-insulateddevices by means of optimized acoustic emission techniques (AET)[J]. IEEE Trans. on PowerDelivery,2005,20(1):158-162.
[26] M. S. Sachdev, T. S. Sidhu, M. C. Wood. A digital relaying algorithm for deteting transformerwinding faults[J]. IEEE Transactions on Power Delivery,1989,4(3):1638-148.
[27]熊浩.电力变压器绝缘状态综合评估方法研究[D]．重庆大学博士学位论文,2003.
[28] R. Blue, D. Uttamchandani, O. Farish. Determination of FFA concentration in transformer oilby fluorescence measurements[J]. IEEE Transactions on Dielectrics and Electrical Insulation,1998,5(6):892-895.
[29] Lijun Yang, Ruijin Liao, Caixin Sun, et al. Influence of natural ester on thermal agingcharacteristics of oil–paper in power transformers[J]. European Transactions on ElectricalPower,2009,20(8):1223-1236.
[30] T. K. Saha. Review of modern diagnostic techniques for assessing insulation condition in agedtransformers[J]. IEEE Trans. Dielectr. Electr. Insul.,2003,10(5):903-917.
[31] M. H. Wang, C. P. Hung. Novel grey model for the prediction of trend of dissolved gases inoil-filled power apparatus[J]. Electr. Power Syst. Res.,2003,67(1):53-58.
[32] M. H. Wang. Grey-extension method for incipient fault forecasting of oil-immersed powertransformer[J]. Electr. Power Compon. Syst.,2004,32(10):959-975.
[33] J. Singh, Y. R. Sood, R. K. Jarial, P. Verma. Condition monitoring of powertransformers-bibliography survey[J]. IEEE Elect. Insul. Mag.,2008,24(3):11-25.
[34] S. W. Fei, Y. Sun. Forecasting dissolved gases content in power transformer oil based onsupport vector machine with genetic algorithm[J]. Electr. Power Syst. Res.,2008,78(3):507-514.
[35]肖燕彩.支持向量机在变压器状态评估中的应用研究[D].北京交通大学博士学位论文,2008.
[36] H. T. Yang，C. C. Liao, J. H. Chou．Fuzzy learning vector quantization networks for powertransformer condition assessment[J]．IEEE Transactions on Dielectrics and Electrical Insulation,2001,8(1):143-149.
[37] W. H. Tang, K. Spurgeon, Q. H. Wu, Z. J. Richardson. An evidential reasoning approach totransformer condition assessments[J]. IEEE Trans. Power Del.,2004,19(4):1696-1703.
[38] V. Sokolov, Z. Berler, V. Rashkes. Effective methods of assessment of insulation systemconditions in power transformers: a view based on practical experience[C]. ElectricalInsulation Conference and Electrical Manufacturing&Coil Winding Conference, Cincinnati,Oct.1999:659-667.
[39]黄华,傅晨钊.大型电力变压器状态分析综述[J].华东电力,2004,32(3):24-26.
[40] E. Rivas, J. C. Burgos, J. C. García-Prada. Condition assessment of power OLTC by vibrationanalysis using wavelet transform[J]. IEEE Transactions on Power Delivery,2009,24(2):687-694.
[41]吴立增.变压器状态评估方法的研究[D].华北电力大学博士学位论文,2005.
[42]袁志坚,孙才新,袁张渝,等.变压器健康状态评估的灰色聚类决策方法[J].重庆大学学报,2005,28(3):22-25.
[43] M. Arshad, S. M. Islam. Significance of cellulose power transformer condition assessment[J].IEEE Transactions on Dielectrics and Electrical Insulation,2011,18(5):1591-1598.
[44]郭创新,高振兴,张健,等.油浸式电力变压器状态评估模型及方法[J].控制工程,2011,18(6):881-885.
[45]谢红玲,律方成.基于信息融合的变压器状态评估方法研究[J].华北电力大学学报,2006,33(2):8-11.
[46]程崯,王宇,余轩,毛志强.电力变压器运行状态综合评判指标的权重确定[J].中国电力,2011,44(4):26-30.
[47]廖瑞金,黄飞龙,杨丽君,等.多信息量融合的电力变压器状态评估模型[J].高电压技术,2010,36(6):1455-1460.
[48]赵文清,朱永利,姜波,等.基于贝叶斯网络的电力变压器状态评估[J].高电压技术,2008,34(5):1032-1039.
[49]郑蕊蕊,赵继印,吴宝春,等.基于加权灰靶理论的电力变压器绝缘状态分级评估方法[J].电工技术学报,2008,23(8):60-66.
[50]王昌长,李福祺,高胜友,等.电气设备的在线监测与故障诊断技术[M].北京:清华大学出版社,2006.
[51] GB/T7252-2001.变压器油中溶解气体分析和判断导则.2001.
[52]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,(1):22-26.
[53] B. Fallou, F. Viale, Davies, et al. Application of physical-chemical methods of analysis to thestudy of deterioration in the insulation of electrical apparatus[C]. CIGER, Paris, France,1970:Rep.15-07.
[54] IEC Publication599. Interpretation for the analysis of gases in transformers and oil-filledelectrical equipment in service.1978.
[55] R. R. Rogers. IEEE and IEC codes to interpret incipient faults in transformers using gas in oilanalysis[J]. IEEE Trans. Electr. Insul.,1978,EI-13(5):349-353.
[56]潘翀.电力变压器绝缘故障诊断技术及热状态参量预测模型研究[D].重庆大学博士学位论文,2009.
[57]操敦奎.变压器油中气体分析诊断与故障检查[M].北京:中国电力出版社,2005.
[58] M. Duval. Dissolved gases analysis: it can save your transformer[J]. IEEE Elect. Insul. Mag.,1989,5(6):22-27.
[59] M. Duval and A. dePablo. Interpretation of gas-in-oil analysis using new IEC publication60599and IEC TC10databases[J]. IEEE Elect. Insul. Mag.,2001,17(2):31-41.
[60] IEEE Std. C57.104-2008. IEEE Guide for the Interpretation of Gases Generated inOil-Immersed Transformers.2008.
[61] I. A. Zadeh. Fuzzy sets[J]. Inform. Control,1965,8(3):338-353.
[62] K. Tomsovic, M. Tapper, T. Ingvarsson. A fuzzy information approach to integrating differenttransformer diagnostic methods[J]. IEEE Trans. Power Del.,1993,8(3):1638-1646.
[63] Y. C. Huang, H. T. Yang, C. L. Huang. Developing a new transformer fault diagnosis systemthrough evolutionary fuzzy logic[J]. IEEE Trans. Power Del.,1997,12(2):761-767.
[64] A. P. Chen, C. C. Lin. Fuzzy approaches for fault diagnosis of transformers[J]. Fuzzy Sets andSystems,2001,118(1):139-151.
[65] D. R. Morais, J. R. da Silva, J. G. Rolim. A fuzzy system for detection of incipient faults intransformers based on the dissolved gas analysis of insulation oil[C]. Proc.5th IEEE Int. Symp.Diagnostics Electr. Machines, Power Electronics and Drives, Vienna, Sept.2005:1-6.
[66] M. S. Kalavathi, B. R. Reddy, B. P. Singh. Transformer fault diagnosis using fuzzy logic andneural network[C]. Annual Report Conf. Electrical Insulation and Dielectric Phenomena, Oct.2005:486-489.
[67] L. Xie, L. Zhou, X. J. Tong, M. Y. Chen. Fault diagnosis of power transformer insulation basedon fuzzy normal partition and logic reasoning[C]. Proc. Int. Conf. Machine Learning andCybernetics, Hong Kong, Aug.2007:1081-1085.
[68]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.
[69] Q. Su, C. Mi, L. L. Lai, P. Austin. A fuzzy dissolved gas analysis method for the diagnosis ofmultiple incipient faults in a transformer[J]. IEEE Trans. on Power Systems,2000,15(2):593-598.
[70]张鸣柳,孙才新.变压器油中溶解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.
[71]孙才新,郭俊峰,廖瑞金,等.变压器油中溶解气体分析中的模糊模式多层聚类故障诊断方法的研究[J].中国电机工程学报,2001,21(2):37-41.
[72]王建元,纪延超.模糊Petri网络知识表示方法及其在变压器故障诊断中的应用[J].中国电机工程学报,2003,23(1):121-125.
[73]李俭,孙才新,陈伟根,等.灰色聚类与模糊聚类集成诊断变压器内部故障的方法研究[J].中国电机工程学报,2003,23(2):112-115.
[74]符杨,江玉蓉,崔椿洪,等.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.
[75]熊浩,李卫国,畅广辉,等.模糊粗糙集理论在变压器故障诊断中的应用[J].中国电机工程学报,2008,28(7):141-147.
[76]符杨,田振宁,江玉蓉,等.加权模糊核聚类法在电力变压器故障诊断中的应用[J].高电压技术,2010,36(2):371-374.
[77] C. E. Lin, J. M. Ling, C. L. Huang. An expert system for transformer fault diagnosis usingdissolved gas analysis[J]. IEEE Trans. Power Del.,1993,8(1):231-238.
[78]廖瑞金.变压器绝缘故障诊断黑板型专家系统和基于遗传算法的故障预测研究[D].重庆大学博士学位论文,2003.
[79] P. Purkait, S. Chakravorti. Time and frequency domain analyses based expert system forimpulse fault diagnosis in transformers[J]. IEEE Trans. Dielect. Elect. Insulation,2002,9(3):433-445.
[80]何定,唐国庆,陈珩.电力变压器故障诊断专家系统TFDES[J].电力系统自动化,1993,17(7):32-35.
[81]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.
[82]束洪春,孙向飞,司大军.电力变压器故障诊断专家系统知识库建立和维护的粗糙集方法[J].中国电机工程学报,2002,22(2):31-35.
[83]廖瑞金,姚陈果,孙才新,等.基于人工智能的电力变压器绝缘故障诊断面向对象知识库[J].电工技术学报,2001,16(6):59-64.
[84]孙才新,郭俊峰,曹毅,等.基于行为的变压器油色谱分析模型诊断专家系统研究[J].电工技术学报,2001,16(3):49-52.
[85]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.
[86]王财胜,孙才新,廖瑞金.变压器色谱监测中的BPNN故障诊断法[J].电网技术,1997,17(5):323-325.
[87]徐文,王大忠,周泽存,等.结合遗传算法的人工神经网络在电力变压器故障诊断中的应用[J].中国电机工程学报,1997,17(2):109-112.
[88]高文胜,钱政,严璋.基于决策树神经网络模型的电力变压器故障诊断方法[J].西安交通大学学报,1999,33(6):11-16.
[89]刘那,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.
[90]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.
[91]彭宁云,文习山,舒翔.模糊神经网络在变压器故障诊断中的应用[J].高电压技术,2004,30(5):14-17.
[92]章剑光,周浩,项灿芳.基于Super SAB神经网络算法的主变压器故障诊断模型[J].电工技术学报,2004,19(7):49-52.
[93]章剑光,周浩,盛晔.基于RPROP神经网络算法的主变DGA故障诊断模型[J].电力系统自动化,2004,28(14):63-66.
[94]周建华,胡敏强.自构形神经网络在变压器故障诊断中的应用[J].电工技术学报,2004,19(9):77-81.
[95]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].电工技术学报,2010,30(22):64-70.
[96] W. G. Chen, C. Pan, Y. X. Yun, Y. L. Liu. Wavelet networks in power transformers diagnosisusing dissolved gas analysis[J], IEEE Trans. on Power Delivery,2009,24(1):187-194.
[97]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的研究[J].中国电机工程学报,2006,26(3):119-124.
[98]邓宏贵,罗安,曹建,等.基因多点交叉遗传算法在变压器故障诊断中的应用[J].电网技术,2004,28(24):1-4.
[99]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.
[100]孙才新,李俭,郑海平,等.基于面积关联度分析的电力变压器绝缘故障诊断方法[J].电网技术,2002,26(7):24-29.
[101]杨廷方,李景禄,曾祥君,等.基于多种方法组合诊断模型的大型变压器故障诊断[J].电力系统自动化,2009,33(20):92-95.
[102]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.
[103]莫娟,王雪,董明,等.基于粗糙集理论的电力变压器故障诊断方法[J].中国电机工程学报,2004,24(7):162-167.
[104]董明,屈彦明,周孟戈,等.基于组合决策树的油浸式电力变压器故障诊断[J].中国电机工程学报,2005,25(16):35-41.
[105]王永强,律方成,李和明.基于贝叶斯网络和油中溶解气体分析的变压器故障诊断算法[J].电工技术学报,2004,19(12):74-77.
[106]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.
[107]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.
[108]陈江波,文习山,蓝磊,等.基于新径向基函数网络的变压器故障诊断法[J].高电压技术,2007,33(3):140-143.
[109]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.
[110]V. N. Vapnik. The Nature of Statistical Learning Theory[M]. New York, Springer-Verlag,1998.
[111]吕干云,程浩忠,董立新,等.基于多级支持向量机分类器的电力变压器故障识别[J].电力系统自动化学报,2005,17(1):19-22.
[112]S. W. Fei, M. J. Wang, Y. B. Miao, et al. Particle swarm optimization-based support vectormachine for forecasting dissolved gases content in power transformer oil[J]. EnergyConversion and Management,2009,50(6):1604-1609.
[113]F. E. H. Tay, L. J. Cao. Application of support vector machines in financial time seriesforecasting[J]. Omega-International Journal of Management Science,2001,29(4):309-317.
[114]Q. Wu. The forecasting model based on wavelet v-support vector machine[J]. Expert Syst.Appl.,2009,36(4):7604-7610.
[115]R. E. James, Q. Su. Condition Assessment of High Voltage Insulation in Power SystemEquipment[M]. London, The Institution of Engineering and Technology,2008.
[116]罗运柏,于萍,宁斌,等.用灰色模型预测变压器油中溶解气体的含量[J].中国电机工程学报,2001,21(3):65-69.
[117]赵文清.基于数据挖掘的变压器故障诊断和预测研究[D].华北电力大学博士学位论文,2009.
[118]费胜巍,孙宇.融合粗糙集与灰色理论的电力变压器故障预测[J].中国电机工程学报,2008,28(16):154-160.
[119]杨廷方,刘沛,李浙,等.应用新型多方法组合预测模型估计变压器油中溶解气体深度[J].中国电机工程学报,2008,28(31):108-113.
[120]C. C. Chang, C. J. Lin. LIBSVM–A library for support vector machines.[Online]. Available:http://www.csie.ntu.edu.tw/~cjlin/libsvm.2001.
[121]T. Van Gestel, J. A. K. Suykens, D. E. Baestaens. Financial time series prediction using leastsquares support vector machines within the evidence framework[J]. IEEE Trans. NeuralNetworks,2001,12(4):809-821.
[122]Y. Zhang, Y. C. Liu. Traffic forecasting using least squares support vector machines[J].Transportmetrica,2009,5(3):193-213.
[123]P. F. Pai, W. C. Hong. Forecasting regional electricity load based on recurrent support vectormachines with genetic algorithms[J]. Electric Power Systems Research,2005,74(3):417-425.
[124]赵文清,朱永利,张小奇.应用支持向量机的变压器故障组合预测[J].中国电机工程学报,2008,28(25):14-19.
[125]Z. Yang, X. S. Gu, X. Y. Liang, L. C. Ling. Genetic algorithm-least squares support vectorregression based predicting and optimizing model on carbon fiber composite integratedconductivity[J]. Materials&Design,2010,31(3):1042-1049.
[126]DL/5961996.电力设备预防性试验规程.1996.
[127]廖玉祥.一种电力变压器运行状态综合评估模型的研究[D]．重庆大学硕士学位论文,2006.
[128]骆思佳.电力变压器运行状态分级评估模型的研究[D]．重庆大学硕士学位论文,2008.
[129]国家电网公司生产技术部.设备状态检修规章制度和技术标准汇编[S].北京:中国电力出版社,2008.
[130]李诚.预防性试验对电力变压器的有效性分析[J].华中电力,2002,15(6):29-32.
[131]陈人翔,工寅仲,海世杰.绝缘电阻试验判断变压器绝缘的判据探讨[J].高电压技术,2004,30(10):21-22.
[132]李军.变压器铁芯多点接地故障的检测及处理方法[J].青海电力,2001,(2):50-51.
[133]陈化钢.电力设备预防性试验方法及诊断技术[M].北京:中国水利水电出版社,2009.
[134]王谦.基于模糊理论的电力变压器运行状态综合评估方法研究[D]．重庆大学硕士学位论文,2005.
[135]祝景中.浅谈变压器油中的水分[J].中国电力,1999,29(3):61-62.
[136]姚化亭,刘国跃.变压器油介损异常原因及处理[J].农村电气化,2006,(4):56-57.
[137]J. M. K. MacAlpine,张潮海.糠醛浓度判断变压器绝缘纸寿命的综述[J].高电压技术,2001,27(4):63-67.
[138]向彬,廖瑞金,杨丽君,等.变压器矿物油中糠醛的稳定性研究[J].高电压技术,2007,33(8):85-87.
[139]徐志强,刘阳,赵敏乔,等.油中糠醛浓度判定变压器固体绝缘劣化程度的研究[J].电力建设,2010,31(2):36-38.
[140]国家电网公司.110(66)kV~500kV油浸式变压器（电抗器）检修规范[S].2005.
[141]胡惠然,魏光华.湖北电网110kV及以上有载分接开关统计分析[J].湖北电力,2001,25(1):38-43.
[142]韩洪刚,王海宽.电力变压器分接开关故障及其检测技术[J].变压器,2004,41(12):35-38.
[143]孙国彬.大型电力变压器的非电量保护[J].电气时代,2004,(2):72-73.
[144]王志方.气体继电器与变压器运行时的安全[J].变压器,2005,42(9):40-41.
[145]杨保初,刘晓波,戴玉松.高电压技术[M].重庆:重庆大学出版社,2009.
[146]严璋,朱德恒.高电压绝缘技术[M].北京:中国电力出版社,2007.
[147]T. L. Saaty. The Analytic Hierarchy Process[M]. McGraw-Hill, New York,1980.
[148]梁梁,盛昭翰,徐南荣.一种改进的层次分析法[J].系统工程,1989,7(3):5-7.
[149]梁梁,余磊.对《一种改进的AHP法》的补注[J].系统工程,1991,9(3):64-65.
[150]IEEE Std. C57.140. IEEE Guide for the Evaluation and Reconditioning of Liquid ImmersedPower Transformers.2006.
[151]顾煜炯,董玉亮,杨昆.基于模糊评判和RCM分析的发电设备状态综合评价[J].中国电机工程学报,2004,24(6):189-194.
[152]赵克勤.集对分析及其初步应用[M].杭州:浙江科学技术出版社,2000.
[153]王栋,朱元甡,赵克勤.基于集对分析和模糊集合论的水体营养化评价[J].水文,2004,24(3):9-13.
[154]W. S. Wang, J. L. Jin, J. Ding, et al. A new approach to water resources system assessment—setpair analysis method[J]. Science in China Series E: Technological Sciences,2009,52(10):3017-3023.
[155]金华征,程浩忠,杨晓梅,等.模糊集对分析法应用于计及ATC的多目标电网规划[J].电力系统自动化,2005,29(21):45-49.
[156]程乾生.属性识别理论模型及其应用[J].北京大学学报（自然科学版）,1997,33(1):12-20.
[157]J. B. Yang, M. G. Singh. An evidential reasoning approach for multiple-attribute decisionmaking with uncertainty[J]. IEEE Trans. Syst., Man, Cybern.,1994,24(1):1-18.
[158]IEEE Std.637-1985. IEEE Guide for the Reclamation of Insulating Oil and Criteria for Its Use.1985.
[159]IEEE Std. C57.125-1991. IEEE Guide for Failure Investigation, Documentation, and Analysisfor Power Transformers and Shunt Reactors.1991.
[160]IEEE Std. C57.106-2006. IEEE Guide for Acceptance and Maintenance of Insulating Oil inEquipment.2006.
[161]J. Yen, L. Wang. Fuzzy logic–a modern perspective[J]. IEEE Trans. Knowledge Data Eng.,1999,11(1):153-165.
[162]G. Deschrijver, E. E. Kerre. On the relationship between some extensions of fuzzy set theory[J].Fuzzy Sets and Systems,2003,133(2):227-235.
[163]F. Herrera, E. Herrera-Viedma, L. Martinez. A fusion approach for managing multi-granularitylinguistic term sets in decision making[J]. Fuzzy Sets and Systems,2000,114(1):43-58.
[164]龚本刚.基于证据理论的不完全信息多属性决策方法研究[D].中国科学技术大学博士学位论文,2007.
[165]肖明珠.基于证据理论的不确定性处理研究及其在测试中的应用[D].电子科技大学博士学位论文,2008.
[166]彭宁云.基于DGA技术的变压器故障智能诊断系统研究[D].武汉大学博士学位论文,2004.
[167]孙永奎.基于支持向量机的模拟电路故障诊断方法研究[D].电子科学大学博士学位论文,2009.
[168]W. S. Sarle. Neural Network FAQ.[Online]. Available:ftp://ftp.sas.com/pub/neural/FAQ2.html.
[169]李烨.基于支持向量机的集成学习研究[D].上海交通大学博士学位论文,2007.
[170]V. N. Vapnki, A. Chervonenkis. On the uniform convergence of relative frequencies of eventsto their probabilities[J]. Theory Probab. Apl.,1971,16:264-280.
[171]段华.支持向量机的增量学习算法研究[D].上海交通大学博士学位论文,2008.
[172]J. Weston, C. Watkins. Multi-class support vector machines[C]. Proc. ESANN99, M. Verleysen,Ed., Brussels, Belgium,1999.
[173]T. VAN. Gestel, J. A. K. Suykens, B. Baesens, et al. Benchmarking least squares support vectormachine classifiers[J]. Machine Learning,2004,54,(1):5-32.
[174]A. Mathur, G. M. Foody. Multiclass and binary SVM classification: Implications for trainingand classification users[J]. IEEE Geos. Remote Sens. Letters,2008,5,(2):241-245.
[175]A. Passerini, M. Pontil, P. Frasconi. New results on error correcting output codes of kernelmachines[J]. IEEE Trans. Neural Networks,2004,15,(1):45-54.
[176]C. W. Hsu, C. J. LIN. A comparison of methods for multiclass support vector machines[J].IEEE Trans. Neural Networks,2002,13,(2):415-425.
[177]T. G. Dietterich, G. Bakiri. Solving multiclass learning problems via error-correcting outputcodes[J]. Journal of Artificial Intelligence Research,1995,2:263-286.
[178]T. Van Gestel, J. A. K. Suykens, G. Lanckriet. Multiclass LS-SVMs: moderated outputs andcoding-decoding schemes[J]. Neural Processing Letters,2002,15(1):45-48.
[179]甘良志.核学习算法与集成方法研究[D].浙江大学博士学位论文,2010.
[180]J. C. Platt. Fast training of support vector machines using sequential minimal optimization[M].Advances in Kernel Methods-Support Vector Learning, Cambridge, MA:MIT Press,1998.
[181]J. A. K. Suykens, T. Van Gestel, J. De Brabanter, et al. Least Squares Support VectorMachines[M]. World Scientific, Singapore,2002.
[182]S. S. Keerthi, C. J. Lin. Asymptotic behaviors of support vector machines with Gaussiankernel[J]. Neural Computation,2003,15(7):1667-1689.
[183]甘良志.核学习算法与集成方法研究[D].浙江大学博士学位论文,2005.
[184]张丽平.粒子群优化算法的理论及实践[D].浙江大学博士学位论文,2005.
[185]J. Kennedy, R. C. Eberhart. Particle swarm optimization[C]. Proc. IEEE Int. Conf. NeuralNetworks,1995,4:1942-1948.
[186]A. Frank, A. Asuncion. UCI machine learning repository.[Online]. Available:http://archive.ics.uci.edu/ml.2010.
[187]K. Meng, Z. Y. Dong, D. H. Wang, et al. A self-adaptive RBF neural network classifier fortransformer fault analysis[J]. IEEE Trans. Power Syst.,2010,25,(3):1350-1360.
[188]Y. Shi, R. C. Eberhart. Empirical study of particle swarm optimization[J]. Proc. IEEE Int.Congr. Evolut. Comput.,1999,3,(1):101-106.
[189]A. Ratnaweera, S. K. Halgamuge, H. C. Watson. Self-organizing hierarchical particle swarmoptimizer with time-varying acceleration coefficients[J]. IEEE Trans. Evolut. Comput.,2004,8,(3):240-255.
[190]A. J. Smola, B. Scholkopf. A tutorial on support vector regression[J]. Statistics and Computing,2004,14,(3):199-222.
[191]C. de Boor. A practical guide to splines[M]. New York, Springer-Verlag,1978.
[192]A. J. Smola, B. Sch lkopf, K. Müller. The connection between regularization operators andsupport vector kernels[J]. Neural Networks,1998,11(4):637-649.
[193]Q. H. Zhang, A. Benveniste. Wavelet networks[J]. IEEE Trans. Neural Networks,1992,3(6):889-898.
[194]L. Zhang, W. D. Zhou, L. C. Jiao. Wavelet support vector machine[J]. IEEE Trans. Syst., Man,Cybern., Part B: Cybernetics,2004,34(1):34-39.
[195]董克强.时间序列的信息粒化及基于粒化的聚类分析[D].北京师范大学硕士学位论文,2005.
[196]C. Kao, C. L. Chyu. A fuzzy linear regression model with better explanatory power[J]. FuzzySets Syst.,2002,126,(3):401-409.
[197]Y. S. Ding, X. P. Song, Y. M. Zen. Forecasting financial condition of Chinese listed companiesbased on support vector machine[J]. Expert Syst. Appl.,2008,34,(4):3081-3089.
[198]W. Q. Lin, J. H. Jiang, Y. P. Zhou, et al. Support vector machine based training of multilayerfeedforward nueral networks as optimized by particle swarm algorithm: application in QSARstudies of bioactivity of organic compounds[J]. J. Comput. Chem.,2007,28,(2):519-527.
[199]L. A. Zadeh. Toward a theory of fuzzy information granulation and its centrality in humanreasoning and fuzzy logic[J]. Fuzzy Sets Syst.,1997,90,(1):111-127.
[200]W. Z. Wu, M. Zhang, H. Z. Li. Knowledge reduction in random information systems viaDempster-Shafer theory of evidence[J]. Inform. Sciences,2005,174,(3-4):143-164.
[201]Z. Pawlak, A. Skowron. Rudiments of rough sets[J]. Inform. Sciences,2007,177,(1):3-27.
[202]R. Xu, D. Wunsch. Survey of clustering algorithms[J]. IEEE Trans. Neural Networks,2005,16,(3):645-678.
[203]W. Pedrycz, A. Gacek. Temporal granulation and its application to signal analysis[J]. Inform.Sciences,2002,143,(1-4):47-71.
[204]F. S. Yu, W. Pedrycz. The design of fuzzy information granules: tradeoffs between specificityand experimental evidence[J]. Appl. Soft Comput.,2009,9,(1):264-273.