基于电力变压器故障特征气体分层特性的诊断与预测方法研究
|
摘要
电力变压器是电网中能量转换、传输的核心,是电网中最重要和最关键的电气设备之一,其运行状态直接影响系统的安全运行水平,变压器一旦发生事故,导致电网不能正常供电,将带来巨大的经济损失。变压器故障诊断和故障预测是确保变压器正常运行的基础,也是实施状态维修的基础。本文对变压器故障诊断和故障预测方法进行了深入研究,主要研究内容如下:
①针对变压器故障诊断的特点,提出分层诊断模型,依据特征气体对各层诊断所提供的有效信息量大小,选择信息量大,冗余度小的特征量集合作为最优诊断特征量,建立分层诊断模型。
②应用互信息理论实现变压器故障诊断的特征量选择,针对互信息理论计算方法中不合理的地方,改进了互信息的计算方法;针对互信息理论不适合用于衡量特征量与类变量之间互信息的问题,提出用卡方距离计算特征量与类变量之间的互信息,并修改卡方距离的计算公式,使之与互信息计算具有相同的数量级。用修正的卡方距离度量特征量提供的有效分类信息量,用互信息衡量各个特征量之间的冗余度,为各层故障诊断选择出最优的诊断特征量集合。
③用模糊数学解释故障诊断模型中神经网络各层节点的作用,基于此提出了一种自动设计神经网络结构,初始化神经网络权重矩阵的方法。该方法首先按卡方距离的计算思想,分析特征子空间与各个故障类别之间的关系,定义了卡方关系,然后依据子空间与各个类别之间的卡方关系,初始化神经网络连接权重。
④为了进一步提高故障诊断的正判率和抗干扰能力,将神经网络群方法应用于变压器故障诊断领域,分析了分层诊断的神经网络群结构,为了提高分类器之间的差异,提出用核主成分分析方法增加特征量,详细分析比较了经过核主成分分析,所得的核特征值、核特征量与分类之间的关系,实验结果表明,核特征值大小不能反映核特征量所提供的有效分类信息量的多少,依据修正的卡方距离和互信息大小选择合适的核特征量,建立分层神经网络群是有效的。
⑤分析变压器油中溶解气体组分预测的特点,认为气体组分预测问题的实质是对气体组分变化情况的预测,基于此,提出用气体组分的差值序列建立预测模型,并用气体组分序列的偏差对差值序列进行预处理,消除气体组分大小差异带来的影响,使不同特征气体的差值序列幅值相近,便于后续建立预测模型。
⑥由于变压器内部各特征气体组分之间存在互相影响,为每个特征气体单独建立预测模型增加了建模和预测的计算量,不能反映气体变化的实际情况,也会影响预测精度。针对这个问题,提出用模糊认知图方法建立变压器特征气体的统一预测模型,该方法能够从历史数据中学习系统内在的变化规律,在一定程度上实现了对变压器特征气体的长期预测,其短期预测和长期预测效果均达到了一定的预测精度。
Power transformer is the crucial device of energy conversion and transmission in the power grid, it’s also the most important electric device, its in-service state directly affects the safety and stability of the power system. The failure of power transformer may cause huge economic loss. The transformer fault diagnosis and fault prediction is the basis of keeping it running normally and carrying out the condition based maintenance, which was studied in-depth in this paper. The main contribution of this thesis was the following.
①the layered fault diagnosis model was proposed based on the analysis of the character of transformer fault diagnosis, the layered diagnosis model should be constructed with the optimal features which are selected according to the effective information amount. The optimal features are the feature subset which may provide the most classification information with the least redundancy.
②application of mutual information to feature selection for transformer fault diagnosis, to overcome the drawbacks in the calculation method of mutual information, an improved calculation method was proposed. As mutual information is not suited to evaluate the mutual information between a feature and a class variable, mutual information was replaced with chi-square distance, which was modified to have the same order of magnitude as mutual information. The feature selection method proposed here used modified chi-square distance to evaluate the effective information provided by the feature, used mutual information to evaluate the redundancy degree between features, selected the optimal feature subset for each layer.
③a fuzzy mathematic interpretation of neural networks was given, and based on this interpretation, a automatic design and initialization of neural networks was proposed. First this approach analyzed the relationships between feature subsapces and fault types, gave the definition of the chi-square relation, then constructed and initialized the neural network based on the chi-square relations.
④to improve the performance and the anti-noise ability of transformer fault diagnosis, neural network ensemble method was applied, this paper analyzed the ensemble structure of layered fault diagnosis, applied kernel PCA to increase the number of features, compared the kernel eigen value, eigen feature and its classification information, the experiment results showed that the eigen value didn’t reflect the amount of effective information, the neural network ensemble was constructed by optimal kernel features which were selected according to modified chi-square distance and mutual information.
⑤analyzed the characters of the prediction of DGA gas concentrations in transformer, the key issue of gas concentration prediction is the prediction of the change of gas concentrations, so the change series was used to construct prediction model, the change series was pre-processed with the deviation of gas concentration series, this pre-precession eliminated the influence to the prediction brought by the magnitude differences among concentrations of different gases,
⑥As in a transformer, there are mutual affections among feature gases, so individually developing prediction models for each gas is not appropriate, fuzzy cognitive map method was applied to construct a universal prediction model for all feature gases in a transformer. This method could learn the behavior rules of a given system from its history data, to some extent this prediction model achieved the long tern prediction.
①针对变压器故障诊断的特点,提出分层诊断模型,依据特征气体对各层诊断所提供的有效信息量大小,选择信息量大,冗余度小的特征量集合作为最优诊断特征量,建立分层诊断模型。
②应用互信息理论实现变压器故障诊断的特征量选择,针对互信息理论计算方法中不合理的地方,改进了互信息的计算方法;针对互信息理论不适合用于衡量特征量与类变量之间互信息的问题,提出用卡方距离计算特征量与类变量之间的互信息,并修改卡方距离的计算公式,使之与互信息计算具有相同的数量级。用修正的卡方距离度量特征量提供的有效分类信息量,用互信息衡量各个特征量之间的冗余度,为各层故障诊断选择出最优的诊断特征量集合。
③用模糊数学解释故障诊断模型中神经网络各层节点的作用,基于此提出了一种自动设计神经网络结构,初始化神经网络权重矩阵的方法。该方法首先按卡方距离的计算思想,分析特征子空间与各个故障类别之间的关系,定义了卡方关系,然后依据子空间与各个类别之间的卡方关系,初始化神经网络连接权重。
④为了进一步提高故障诊断的正判率和抗干扰能力,将神经网络群方法应用于变压器故障诊断领域,分析了分层诊断的神经网络群结构,为了提高分类器之间的差异,提出用核主成分分析方法增加特征量,详细分析比较了经过核主成分分析,所得的核特征值、核特征量与分类之间的关系,实验结果表明,核特征值大小不能反映核特征量所提供的有效分类信息量的多少,依据修正的卡方距离和互信息大小选择合适的核特征量,建立分层神经网络群是有效的。
⑤分析变压器油中溶解气体组分预测的特点,认为气体组分预测问题的实质是对气体组分变化情况的预测,基于此,提出用气体组分的差值序列建立预测模型,并用气体组分序列的偏差对差值序列进行预处理,消除气体组分大小差异带来的影响,使不同特征气体的差值序列幅值相近,便于后续建立预测模型。
⑥由于变压器内部各特征气体组分之间存在互相影响,为每个特征气体单独建立预测模型增加了建模和预测的计算量,不能反映气体变化的实际情况,也会影响预测精度。针对这个问题,提出用模糊认知图方法建立变压器特征气体的统一预测模型,该方法能够从历史数据中学习系统内在的变化规律,在一定程度上实现了对变压器特征气体的长期预测,其短期预测和长期预测效果均达到了一定的预测精度。
Power transformer is the crucial device of energy conversion and transmission in the power grid, it’s also the most important electric device, its in-service state directly affects the safety and stability of the power system. The failure of power transformer may cause huge economic loss. The transformer fault diagnosis and fault prediction is the basis of keeping it running normally and carrying out the condition based maintenance, which was studied in-depth in this paper. The main contribution of this thesis was the following.
①the layered fault diagnosis model was proposed based on the analysis of the character of transformer fault diagnosis, the layered diagnosis model should be constructed with the optimal features which are selected according to the effective information amount. The optimal features are the feature subset which may provide the most classification information with the least redundancy.
②application of mutual information to feature selection for transformer fault diagnosis, to overcome the drawbacks in the calculation method of mutual information, an improved calculation method was proposed. As mutual information is not suited to evaluate the mutual information between a feature and a class variable, mutual information was replaced with chi-square distance, which was modified to have the same order of magnitude as mutual information. The feature selection method proposed here used modified chi-square distance to evaluate the effective information provided by the feature, used mutual information to evaluate the redundancy degree between features, selected the optimal feature subset for each layer.
③a fuzzy mathematic interpretation of neural networks was given, and based on this interpretation, a automatic design and initialization of neural networks was proposed. First this approach analyzed the relationships between feature subsapces and fault types, gave the definition of the chi-square relation, then constructed and initialized the neural network based on the chi-square relations.
④to improve the performance and the anti-noise ability of transformer fault diagnosis, neural network ensemble method was applied, this paper analyzed the ensemble structure of layered fault diagnosis, applied kernel PCA to increase the number of features, compared the kernel eigen value, eigen feature and its classification information, the experiment results showed that the eigen value didn’t reflect the amount of effective information, the neural network ensemble was constructed by optimal kernel features which were selected according to modified chi-square distance and mutual information.
⑤analyzed the characters of the prediction of DGA gas concentrations in transformer, the key issue of gas concentration prediction is the prediction of the change of gas concentrations, so the change series was used to construct prediction model, the change series was pre-processed with the deviation of gas concentration series, this pre-precession eliminated the influence to the prediction brought by the magnitude differences among concentrations of different gases,
⑥As in a transformer, there are mutual affections among feature gases, so individually developing prediction models for each gas is not appropriate, fuzzy cognitive map method was applied to construct a universal prediction model for all feature gases in a transformer. This method could learn the behavior rules of a given system from its history data, to some extent this prediction model achieved the long tern prediction.
引文
[1]王梦云,薛辰东. 1995~1999年全国变压器类设备事故统计与分析[J].电力设备. 2001, 2(1):11-19.
[2]王梦云. 2004年度110 kV及以上变压器事故统计分析[J].电力设备. 2005, 6(11):31-37.
[3]孙才新.重视和加强防止复杂气候环境及输变电设备故障导致电网大面积事故的安全技术研究[J].中国电力. 2004, 37(6):1-8.
[4]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.
[5]中华人民共和国电力工业部.电力变压器检修导则[M], 1995.
[6]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. 2008.
[7]李燕青,律方成,刘国平等.我国电气设备状态维修的发展与实现[J]. 36. 2003, 2(16-19).
[8] A. Garnitschnig. Transformer performance assessment[C]. Dielectric Liquids, 2002. ICDL 2002. Proceedings of 2002 IEEE 14th International Conference on. 2002:317-320.
[9]王昌长,李福祺,高胜友.电力设备的在线监测与故障诊断[M],北京:清华大学出版社, 2006.
[10]中华人民共和国国家质量监督检验检疫总局.变压器油中溶解气体分析和判断导则[J].北京:中国标准出版社. 2002.
[11] Y. Zhang, X. Ding, Y. Liu等. An artificial neural network approach to transformer fault diagnosis[J]. Power Delivery, IEEE Transactions on. 1996, 11(4):1836-1841.
[12]黄鞠铭,朱子述,胡文华等. BP网络在基于DGA变压器故障诊断中的应用[J].高电压技术. 1996, 22(2):21-23.
[13]徐文,王大忠,周泽存等.人工神经网络在变压器特征气体法故障诊断中的应用[J].高电压技术. 1996, 22(227-30).
[14]丁晓群,孙军,袁宇波等.基于BP网络的故障诊断方法的改进[J].电网技术. 1998, 22(11):62-64.
[15]王雪梅,李文申,严璋. BP网络在电力变压器故障诊断中的应用[J].高电压技术. 2005, 31(7):12-14.
[16] J. L. Guardado, J. L. Naredo, P. Moreno等. A comparative study of neural network efficiency in power transformers diagnosis using dissolved gas analysis[J]. Power Delivery, IEEE Transactions on. 2001, 16(4):643-647.
[17]周建华,胡敏强,周鹗.基于共轭梯度方向的CP-BP算法在变压器油中溶解气体诊断法中的应用[J].中国电机工程学报. 1999, 19(3):41-45.
[18]王少芳,蔡金锭,刘庆珍.基于改进GA-BP混合算法的电力变压器故障诊断[J].电网技术. 2004, 28(4):30-33.
[19]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.
[20]魏星,舒乃秋,张霖等.基于改进PSO - BP混合算法的电力变压器故障诊断[J].电力自动化设备. 2006, 26(5):35-38.
[21]吕干云,董立新,程浩忠.基于最小二乘加权融合集成神经网络的电力变压器故障识别[J].电网技术. 2004, 28(16):52-55.
[22]高宁,高文胜,严璋.基于模糊理论与自适应共振网络的油中气体分析诊断[J].高电压技术. 1997, 23(4):22-25.
[23]张慧媛,丁扬,宋林.基于模糊神经网络的变压器故障诊断新方法[J].华北电力大学学报. 1998, 25(2):6-11.
[24]乐晓东,施文康.一种基于模糊神经网络的变压器故障检测[J].上海交通大学学报. 1999, 33(12):1578-1580.
[25]倪远平,李彬华,李一民等.基于模糊神经网络的故障诊断方法及应用[J].仪器仪表学报. 2003, 24(4):31-34.
[26]厉劼翀,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(supp):125-128.
[27] A. R. G. Castro, V. Miranda. Knowledge discovery in neural networks with application to transformer failure diagnosis[J]. Power Systems, IEEE Transactions on. 2005, 20(2):717-724.
[28] D. R. Morais, J. G. Rolim. A Hybrid Tool for Detection of Incipient Faults in Transformers Based on the Dissolved Gas Analysis of Insulating Oil[J]. Power Delivery, IEEE Transactions on. 2006, 21(2):673-680.
[29] V. Miranda, A. R. G. Castro. Improving the IEC table for transformer failure diagnosis with knowledge extraction from neural networks[J]. Power Delivery, IEEE Transactions on. 2005, 20(4):2509-2516.
[30]钱政,罗承沐,严璋等.范例推理结合神经网络诊断变压器故障[J].高电压技术. 2000, 26(4):6-8.
[31]钱政,黄兰,严璋等.集成模糊数学与范例推理的变压器故障诊断方法[J].电网技术. 2001, 25(9):24-27.
[32]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.
[33]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.
[34] Q. Su, C. Mi, L. L. Lai等. A Fuzzy Dissolved Gas Analysis Method for the Diagnosis of Multiple Incipient Faults in a Transformer[J]. Power Systems, IEEE Transactions on. 2000, 15(2):593-598.
[35]王道勇.变压器故障检测方法的改进——模糊识别阈值原则法[J].电力系统自动化. 1998, 22(11):44-46,84.
[36]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.
[37] K. Tomsovic, M. Tapper, T. Ingvarsson. A FUZZY INFORMATION APPROACH TO INTEGRATING DIFFERENT TRANSFORMER DIAGNOSTIC METHODS[J]. Power Delivery, IEEE Transactions on. 1993, 8(3):1638-1646.
[38]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.
[39]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.
[40]李俭,孙才新,廖瑞金等.以模糊聚类标准谱与灰色关联序诊断变压器内部故障的方法研究[J].仪器仪表学报. 2004, 25(5):587-589.
[41]熊浩,孙才新,廖瑞金等.基于核可能性聚类算法和油中溶解气体分析的电力变压器故障诊断研究[J].中国电机工程学报. 2005, 25(20):162-166.
[42]董立新,肖登明,王俏华等.模糊粗糙集数据挖掘方法在电力变压器故障诊断中的应用研究—基于油中溶解气体的分析诊断[J].电力系统及其自动化学报. 2004, 16(5):1-4,19.
[43]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.
[44]钱政,杨莉,张冠军等.基于模糊推理与覆盖集理论的电力变压器故障诊断方法[J].电工电能新技术. 1999, (3):36-39,49.
[45]温熙森,胡茑庆,邱静.模式识别与状态监控[M],长沙:国防科技大学出版社, 1997.
[46]邓聚龙.灰理论基础[M],武汉:华中科技大学出版社, 2002:122-150.
[47]宋斌,罗运柏,于萍等.灰色关联分析在变压器故障诊断中的应用研究[J].水利电力机械. 2003, 25(1):47-50.
[48]孙才新,李俭,郑海平等.基于灰色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):24-28.
[49] D. Lixin, X. Dengming, L. Yilu. Insulation fault diagnosis based on group grey relationa l grade analysis method for power transformers[J]. Journal of Southeast University (English Edition) 2005, 21(2):175-179.
[50]李俭,孙才新,陈伟根等.基于灰色聚类分析的充油电力变压器绝缘故障诊断的研究[J].电工技术学报. 2002, 17(4):80-83.
[51]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.
[52]吴晓辉,刘炯,梁永春等.支持向量机在电力变压器故障诊断中的应用[J].西安交通大学学报. 2007, 41(6):722-726.
[53]贾嵘,徐其惠,李辉等.最小二乘支持向量机多分类法的变压器故障诊断[J].高电压技术. 2007, 33(6):110-113.
[54]肖燕彩,陈秀海.改进的M2ary支持向量机模型及其在变压器故障诊断中的应用[J].上海交通大学学报. 2008, 42(12):2033-2036.
[55]费胜巍,苗玉彬,刘成良等.基于粒子群优化支持向量机的变压器故障诊断[J].高电压技术. 2009, 35(3):509-513.
[56]郑海平,孙才新,李俭等.诊断电力变压器故障的一种灰色关联度分析模式及方法[J].中国电机工程学报. 2001, 21(10):106-109.
[57]罗运柏,于萍,宋斌等.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.
[58]袁保奎,郭基伟,唐国庆.应用灰色理论预测变压器等充油设备内的油中气体浓度[J].电力系统及其自动化学报. 2001, 13(3):40-42.
[59]孙才新,毕为民,周湶等.灰色预测参数模型新模式及其在电气绝缘故障预测中的应用[J].控制理论与应用. 2003, 20(5):797-801.
[60]廖瑞金.王有元,陈伟根,杜林.基于油色谱分析的变压器故障在线预测方法[J].重庆大学学报(自然科学版). 2005, 28(7):34-37.
[61]王晶,刘建新.基于灰色新预测模式的变压器故障预测[J].华北电力大学学报. 2007, 34(1):10-14.
[62]周利军,吴广宁,张星海等.基于加权模糊度时间序列分析的大型变压器故障预报[J].电力系统自动化. 2005, 29(13):53-55.
[63]孙丽萍,杨江天.基于离散灰色模型的变压器油中溶解气体浓度预测[J].电力自动化设备. 2006, 26(9):58-60.
[64]肖燕彩,朱衡君,陈秀海.用灰色多变量模型预测变压器油中溶解的气体浓度[J].电力系统自动化. 2006, 30(13):64-67.
[65]肖燕彩,陈秀海,朱衡君.用改进的灰色多变量模型预测变压器油中溶解气体的浓度[J].电网技术. 2006, 30(10):86-89.
[66]王鹏,许涛.用统计学习理论预测变压器油中溶解气体浓度[J].高电压技术. 2003, 29(11):13-14.
[67]肖燕彩,陈秀海,朱衡君.基于最小二乘支持向量机的变压器油中气体浓度预测[J].电网技术. 2006, 30(11):91-94.
[68]张小奇,朱永利,王芳.基于支持向量机的变压器油中溶解气体浓度预测[J].华北电力大学学报. 2006, 33(6):6-9.
[69]费胜巍,孙宇.用SVRM预测变压器油中溶解气体量[J].高电压技术. 2007, 33(8):81-84.
[70]汪成亮,彭锦文,陈娟娟.模糊认知图在智能控制中的应用研究[J].计算机应用研究. 2009, 26(11):4205-4208.
[71]汪成亮,彭锦文.基于产生式系统的模糊认知图建模方法及其在控制中的应用[J].计算机系统应用. 2009, 2009(9):89-93,139.
[72]林春梅,何跃,汤兵勇等.模糊认知图在股票市场预测中的应用研究[J].计算机应用. 2006, 26(1):195-197,201.
[73] W. Stach, L. A. Kurgan, W. Pedrycz. Numerical and Linguistic Prediction of Time Series With the Use of Fuzzy Cognitive Maps[J]. Fuzzy Systems, IEEE Transactions on. 2008, 16(1):61-72.
[74] C. M. Grinstead, J. L. Snell. Introduction to probability[J]. AMS bookstore. 1997.
[75] A. K. Jain, R. P. W. Duin, M. Jianchang. Statistical pattern recognition: a review[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 2000, 22(1):4-37.
[76]谢勤岚,胡晓勤.一种基于类内类间距离的ICA特征选择方法[J].现代电子技术. 2009, 21(3):105-108.
[77]任江涛,黄焕宇孙婧昊,印鉴.基于相关性分析及遗传算法的高维数据特征选择[J].计算机应用. 2006, 26(6):1403-1405.
[78]王卫玲,刘培玉,初建崇.一种改进的基于条件互信息的特征选择算法[J].计算机应用. 2007, 27(2):433-435.
[79] R. Battiti. Using mutual information for selecting features in supervised neural net learning[J]. Neural Networks, IEEE Transactions on. 1994, 5(4):537-550.
[80] N. Kwak, C. Chong-Ho. Input feature selection by mutual information based on Parzen window[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 2002, 24(12):1667-1671.
[81] A. M. Fraser, H. L. Swinney. Independent coordinates for strange attractors from mutual information[J]. Physical Review A. 1986, 33(2):1134-1140.
[82] M. Tesmer, P. A. Estevez. AMIFS: adaptive feature selection by using mutual information[C]. Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on. 2004:308.
[83] W. Zhenyuan, L. Yilu, P. J. Griffin. A combined ANN and expert system tool for transformer fault diagnosis[J]. Power Delivery, IEEE Transactions on. 1998, 13(4):1224-1229.
[84] H. Yann-Chang. Evolving neural nets for fault diagnosis of power transformers[J]. Power Delivery, IEEE Transactions on. 2003, 18(3):843-848.
[85]彭祖赠,孙韫玉.模糊(Fuzzy)数学及其应用[M], 2002.
[86] A. J. C. Sharkey. On Combining Artificial Neural Nets[J]. Connection Science. 1996, 8(3-4):299-299.
[87] A. J. C. Sharkey, N. E. Sharkey. Combining diverse neural nets[J]. Knowledge Engineering Review. 1997, 12(3):231-247.
[88] L. K. Hansen, P. Salamon. Neural network ensembles[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 1990, 12(10):993-1001.
[89] S. Hashem, B. Schmeiser. Improving model accuracy using optimal linear combinations of trained neural networks[J]. Neural Networks, IEEE Transactions on. 1995, 6(3):792-794.
[90] D. W. Opitz, J. W. Shavlik. Actively Searching for an Effective Neural Network Ensemble[J]. Connection Science. 1996, 8(3-4):337-337.
[91] J. J. Rodriguez, L. I. Kuncheva, C. J. Alonso. Rotation Forest: A New Classifier Ensemble Method[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 2006, 28(10):1619-1630.
[92] L. Breiman. Bagging predictors[J]. Machine Learning. 1996, 24(2):123-140.
[93] Y. Freund, R. E. Schapire. Decision-theoretic generalization of on-line learning and an application to boosting[J]. Journal of Computer and System Sciences. 1997, 55(1):119-139.
[94] M. M. Islam, X. Yao, K. Murase. A Constructive Algorithm for Training Cooperative Neural Network Ensembles[J]. Neural Networks, IEEE Transactions on. 2003, 14(4):820-834.
[95] B. E. Rosen. Ensemble learning using decorrelated neural network[J]. Connect Science. 1996, 8:373-383.
[96] L. Yong, Y. Xin. Simultaneous training of negatively correlated neural networks in an ensemble[J]. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on. 1999, 29(6):716-725.
[97] Z. S. H. Chan, N. Kasabov. Fast neural network ensemble learning via negative-correlation data correction[J]. Neural Networks, IEEE Transactions on. 2005, 16(6):1707-1710.
[98] B. Sch?lkopf, A. Smola, K.-R. Müller. Nonlinear Component Analysis as a Kernel Eigenvalue Problem[J]. neural computation. 1998, 10(5):1299-1319.
[99]李俭,孙才新,陈伟根等.基于灰色聚类分析的充油电力变压器绝缘故障诊断的研究[J].电工技术学报. 2002, 17(4):80-83.
[100]常涛,张晓星,熊浩等.动态隧道模糊C均值算法用于变压器油中溶解气体分析[J].高电压技术. 2009, 35(9):2181-2185.
[101]杨丽君,郑绳楦.基于RS和多类SVM的变压器故障诊断[J].仪器仪表学报. 2005, 26(8):613-615.
[102]张学工.关于统计学习理论与支持向量机[J].自动化学报. 2000, 26(1):32-42.
[103]王有元,廖瑞金,孙才新等.变压器油中溶解气体浓度灰色预测模型的改进[J].高电压技术. 2003, 29(4):24-26.
[104]刘思峰,郭天榜,党耀国.灰色系统理论及其应用[M],北京:科学出版社, 1999.
[105] B. Kosko. Fuzzy cognitive maps[J]. Int J Man-Mach Studies. 1986, 24:65-75.
[106] M. Yuan, L. Zhi-Qiang. On causal inference in fuzzy cognitive maps[J]. Fuzzy Systems, IEEE Transactions on. 2000, 8(1):107-119.
[107] W. Stach, L. Kurgan, W. Pedrycz等. Genetic learning of fuzzy cognitive maps[J]. Fuzzy Sets and Systems. 2005, 153(3):371-401.
[108] J. A. Dickerson, B. Kosko. Virtual worlds as fuzzy cognitive maps[C]. Virtual Reality Annual International Symposium, 1993., 1993 IEEE. 1993:471-477.
[109] D. E. Koulouriotis, I. E. Diakoulakis, D. M. Emiris. Learning fuzzy cognitive maps using evolution strategies: a novel schema for modeling and simulating high-level behavior[C]. Evolutionary Computation, 2001. Proceedings of the 2001 Congress on. 2001:364-371 vol. 361.
[110] F. HERRERA, M. LOZANO, J. L. VERDEGAY. Tackling Real-Coded Genetic Algorithms: Operators and Tools for Behavioural Analysis[J]. Artificial Intelligence Review. 1998, 12(4):265-319.
[111]周明,孙树栋.遗传算法原理及应用[M],北京:国防工业出版社, 1999.
[112] Z. Michalewicz, C. Z. Janikow, J. B. Krawczyk. A modified genetic algorithm for optimal control problems[J]. Computers & Mathematics with Applications. 1992, 23(12):83-94.
[113] M. Heinz, hlenbein, S.-V. Dirk. Predictive models for the breeder genetic algorithm i. continuous parameter optimization[J]. Evol Comput. 1993, 1(1):25-49.
[114] W. Stach, L. Kurgan, W. Pedrycz (2005). Linguistic Signal Prediction with the use of Fuzzy Cognitive Maps. In Proceedings of the Symposium on Human-Centric Computing (Banff, Alberta, Canada), pp. 64-71.
[115] S. Hengjie, M. Chunyan, W. Roel等. Implementation of Fuzzy Cognitive Maps Based on Fuzzy Neural Network and Application in Prediction of Time Series[J]. Fuzzy Systems, IEEE Transactions on. 2010, 18(2):233-250.
[116] W. Pedrycz, A. Gacek. Temporal granulation and its application to signal analysis[J]. Information Sciences. 2002, 143(1-4):47-71.
[117] W. Pedrycz. Why triangular membership functions?[J]. Fuzzy Sets and Systems. 1994,64(1):21-30.
[118] S. Roychowdhury, W. Pedrycz. A Survey of Defuzzification Strategies[J]. INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS. 2001, 16:679-695.
[119]肖燕彩.支持向量机在变压器状态评估中的应用[D].北京交通大学博士学位论文. 2008.
[120]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.
[2]王梦云. 2004年度110 kV及以上变压器事故统计分析[J].电力设备. 2005, 6(11):31-37.
[3]孙才新.重视和加强防止复杂气候环境及输变电设备故障导致电网大面积事故的安全技术研究[J].中国电力. 2004, 37(6):1-8.
[4]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.
[5]中华人民共和国电力工业部.电力变压器检修导则[M], 1995.
[6]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. 2008.
[7]李燕青,律方成,刘国平等.我国电气设备状态维修的发展与实现[J]. 36. 2003, 2(16-19).
[8] A. Garnitschnig. Transformer performance assessment[C]. Dielectric Liquids, 2002. ICDL 2002. Proceedings of 2002 IEEE 14th International Conference on. 2002:317-320.
[9]王昌长,李福祺,高胜友.电力设备的在线监测与故障诊断[M],北京:清华大学出版社, 2006.
[10]中华人民共和国国家质量监督检验检疫总局.变压器油中溶解气体分析和判断导则[J].北京:中国标准出版社. 2002.
[11] Y. Zhang, X. Ding, Y. Liu等. An artificial neural network approach to transformer fault diagnosis[J]. Power Delivery, IEEE Transactions on. 1996, 11(4):1836-1841.
[12]黄鞠铭,朱子述,胡文华等. BP网络在基于DGA变压器故障诊断中的应用[J].高电压技术. 1996, 22(2):21-23.
[13]徐文,王大忠,周泽存等.人工神经网络在变压器特征气体法故障诊断中的应用[J].高电压技术. 1996, 22(227-30).
[14]丁晓群,孙军,袁宇波等.基于BP网络的故障诊断方法的改进[J].电网技术. 1998, 22(11):62-64.
[15]王雪梅,李文申,严璋. BP网络在电力变压器故障诊断中的应用[J].高电压技术. 2005, 31(7):12-14.
[16] J. L. Guardado, J. L. Naredo, P. Moreno等. A comparative study of neural network efficiency in power transformers diagnosis using dissolved gas analysis[J]. Power Delivery, IEEE Transactions on. 2001, 16(4):643-647.
[17]周建华,胡敏强,周鹗.基于共轭梯度方向的CP-BP算法在变压器油中溶解气体诊断法中的应用[J].中国电机工程学报. 1999, 19(3):41-45.
[18]王少芳,蔡金锭,刘庆珍.基于改进GA-BP混合算法的电力变压器故障诊断[J].电网技术. 2004, 28(4):30-33.
[19]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.
[20]魏星,舒乃秋,张霖等.基于改进PSO - BP混合算法的电力变压器故障诊断[J].电力自动化设备. 2006, 26(5):35-38.
[21]吕干云,董立新,程浩忠.基于最小二乘加权融合集成神经网络的电力变压器故障识别[J].电网技术. 2004, 28(16):52-55.
[22]高宁,高文胜,严璋.基于模糊理论与自适应共振网络的油中气体分析诊断[J].高电压技术. 1997, 23(4):22-25.
[23]张慧媛,丁扬,宋林.基于模糊神经网络的变压器故障诊断新方法[J].华北电力大学学报. 1998, 25(2):6-11.
[24]乐晓东,施文康.一种基于模糊神经网络的变压器故障检测[J].上海交通大学学报. 1999, 33(12):1578-1580.
[25]倪远平,李彬华,李一民等.基于模糊神经网络的故障诊断方法及应用[J].仪器仪表学报. 2003, 24(4):31-34.
[26]厉劼翀,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(supp):125-128.
[27] A. R. G. Castro, V. Miranda. Knowledge discovery in neural networks with application to transformer failure diagnosis[J]. Power Systems, IEEE Transactions on. 2005, 20(2):717-724.
[28] D. R. Morais, J. G. Rolim. A Hybrid Tool for Detection of Incipient Faults in Transformers Based on the Dissolved Gas Analysis of Insulating Oil[J]. Power Delivery, IEEE Transactions on. 2006, 21(2):673-680.
[29] V. Miranda, A. R. G. Castro. Improving the IEC table for transformer failure diagnosis with knowledge extraction from neural networks[J]. Power Delivery, IEEE Transactions on. 2005, 20(4):2509-2516.
[30]钱政,罗承沐,严璋等.范例推理结合神经网络诊断变压器故障[J].高电压技术. 2000, 26(4):6-8.
[31]钱政,黄兰,严璋等.集成模糊数学与范例推理的变压器故障诊断方法[J].电网技术. 2001, 25(9):24-27.
[32]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.
[33]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.
[34] Q. Su, C. Mi, L. L. Lai等. A Fuzzy Dissolved Gas Analysis Method for the Diagnosis of Multiple Incipient Faults in a Transformer[J]. Power Systems, IEEE Transactions on. 2000, 15(2):593-598.
[35]王道勇.变压器故障检测方法的改进——模糊识别阈值原则法[J].电力系统自动化. 1998, 22(11):44-46,84.
[36]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.
[37] K. Tomsovic, M. Tapper, T. Ingvarsson. A FUZZY INFORMATION APPROACH TO INTEGRATING DIFFERENT TRANSFORMER DIAGNOSTIC METHODS[J]. Power Delivery, IEEE Transactions on. 1993, 8(3):1638-1646.
[38]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.
[39]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.
[40]李俭,孙才新,廖瑞金等.以模糊聚类标准谱与灰色关联序诊断变压器内部故障的方法研究[J].仪器仪表学报. 2004, 25(5):587-589.
[41]熊浩,孙才新,廖瑞金等.基于核可能性聚类算法和油中溶解气体分析的电力变压器故障诊断研究[J].中国电机工程学报. 2005, 25(20):162-166.
[42]董立新,肖登明,王俏华等.模糊粗糙集数据挖掘方法在电力变压器故障诊断中的应用研究—基于油中溶解气体的分析诊断[J].电力系统及其自动化学报. 2004, 16(5):1-4,19.
[43]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.
[44]钱政,杨莉,张冠军等.基于模糊推理与覆盖集理论的电力变压器故障诊断方法[J].电工电能新技术. 1999, (3):36-39,49.
[45]温熙森,胡茑庆,邱静.模式识别与状态监控[M],长沙:国防科技大学出版社, 1997.
[46]邓聚龙.灰理论基础[M],武汉:华中科技大学出版社, 2002:122-150.
[47]宋斌,罗运柏,于萍等.灰色关联分析在变压器故障诊断中的应用研究[J].水利电力机械. 2003, 25(1):47-50.
[48]孙才新,李俭,郑海平等.基于灰色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):24-28.
[49] D. Lixin, X. Dengming, L. Yilu. Insulation fault diagnosis based on group grey relationa l grade analysis method for power transformers[J]. Journal of Southeast University (English Edition) 2005, 21(2):175-179.
[50]李俭,孙才新,陈伟根等.基于灰色聚类分析的充油电力变压器绝缘故障诊断的研究[J].电工技术学报. 2002, 17(4):80-83.
[51]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.
[52]吴晓辉,刘炯,梁永春等.支持向量机在电力变压器故障诊断中的应用[J].西安交通大学学报. 2007, 41(6):722-726.
[53]贾嵘,徐其惠,李辉等.最小二乘支持向量机多分类法的变压器故障诊断[J].高电压技术. 2007, 33(6):110-113.
[54]肖燕彩,陈秀海.改进的M2ary支持向量机模型及其在变压器故障诊断中的应用[J].上海交通大学学报. 2008, 42(12):2033-2036.
[55]费胜巍,苗玉彬,刘成良等.基于粒子群优化支持向量机的变压器故障诊断[J].高电压技术. 2009, 35(3):509-513.
[56]郑海平,孙才新,李俭等.诊断电力变压器故障的一种灰色关联度分析模式及方法[J].中国电机工程学报. 2001, 21(10):106-109.
[57]罗运柏,于萍,宋斌等.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.
[58]袁保奎,郭基伟,唐国庆.应用灰色理论预测变压器等充油设备内的油中气体浓度[J].电力系统及其自动化学报. 2001, 13(3):40-42.
[59]孙才新,毕为民,周湶等.灰色预测参数模型新模式及其在电气绝缘故障预测中的应用[J].控制理论与应用. 2003, 20(5):797-801.
[60]廖瑞金.王有元,陈伟根,杜林.基于油色谱分析的变压器故障在线预测方法[J].重庆大学学报(自然科学版). 2005, 28(7):34-37.
[61]王晶,刘建新.基于灰色新预测模式的变压器故障预测[J].华北电力大学学报. 2007, 34(1):10-14.
[62]周利军,吴广宁,张星海等.基于加权模糊度时间序列分析的大型变压器故障预报[J].电力系统自动化. 2005, 29(13):53-55.
[63]孙丽萍,杨江天.基于离散灰色模型的变压器油中溶解气体浓度预测[J].电力自动化设备. 2006, 26(9):58-60.
[64]肖燕彩,朱衡君,陈秀海.用灰色多变量模型预测变压器油中溶解的气体浓度[J].电力系统自动化. 2006, 30(13):64-67.
[65]肖燕彩,陈秀海,朱衡君.用改进的灰色多变量模型预测变压器油中溶解气体的浓度[J].电网技术. 2006, 30(10):86-89.
[66]王鹏,许涛.用统计学习理论预测变压器油中溶解气体浓度[J].高电压技术. 2003, 29(11):13-14.
[67]肖燕彩,陈秀海,朱衡君.基于最小二乘支持向量机的变压器油中气体浓度预测[J].电网技术. 2006, 30(11):91-94.
[68]张小奇,朱永利,王芳.基于支持向量机的变压器油中溶解气体浓度预测[J].华北电力大学学报. 2006, 33(6):6-9.
[69]费胜巍,孙宇.用SVRM预测变压器油中溶解气体量[J].高电压技术. 2007, 33(8):81-84.
[70]汪成亮,彭锦文,陈娟娟.模糊认知图在智能控制中的应用研究[J].计算机应用研究. 2009, 26(11):4205-4208.
[71]汪成亮,彭锦文.基于产生式系统的模糊认知图建模方法及其在控制中的应用[J].计算机系统应用. 2009, 2009(9):89-93,139.
[72]林春梅,何跃,汤兵勇等.模糊认知图在股票市场预测中的应用研究[J].计算机应用. 2006, 26(1):195-197,201.
[73] W. Stach, L. A. Kurgan, W. Pedrycz. Numerical and Linguistic Prediction of Time Series With the Use of Fuzzy Cognitive Maps[J]. Fuzzy Systems, IEEE Transactions on. 2008, 16(1):61-72.
[74] C. M. Grinstead, J. L. Snell. Introduction to probability[J]. AMS bookstore. 1997.
[75] A. K. Jain, R. P. W. Duin, M. Jianchang. Statistical pattern recognition: a review[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 2000, 22(1):4-37.
[76]谢勤岚,胡晓勤.一种基于类内类间距离的ICA特征选择方法[J].现代电子技术. 2009, 21(3):105-108.
[77]任江涛,黄焕宇孙婧昊,印鉴.基于相关性分析及遗传算法的高维数据特征选择[J].计算机应用. 2006, 26(6):1403-1405.
[78]王卫玲,刘培玉,初建崇.一种改进的基于条件互信息的特征选择算法[J].计算机应用. 2007, 27(2):433-435.
[79] R. Battiti. Using mutual information for selecting features in supervised neural net learning[J]. Neural Networks, IEEE Transactions on. 1994, 5(4):537-550.
[80] N. Kwak, C. Chong-Ho. Input feature selection by mutual information based on Parzen window[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 2002, 24(12):1667-1671.
[81] A. M. Fraser, H. L. Swinney. Independent coordinates for strange attractors from mutual information[J]. Physical Review A. 1986, 33(2):1134-1140.
[82] M. Tesmer, P. A. Estevez. AMIFS: adaptive feature selection by using mutual information[C]. Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on. 2004:308.
[83] W. Zhenyuan, L. Yilu, P. J. Griffin. A combined ANN and expert system tool for transformer fault diagnosis[J]. Power Delivery, IEEE Transactions on. 1998, 13(4):1224-1229.
[84] H. Yann-Chang. Evolving neural nets for fault diagnosis of power transformers[J]. Power Delivery, IEEE Transactions on. 2003, 18(3):843-848.
[85]彭祖赠,孙韫玉.模糊(Fuzzy)数学及其应用[M], 2002.
[86] A. J. C. Sharkey. On Combining Artificial Neural Nets[J]. Connection Science. 1996, 8(3-4):299-299.
[87] A. J. C. Sharkey, N. E. Sharkey. Combining diverse neural nets[J]. Knowledge Engineering Review. 1997, 12(3):231-247.
[88] L. K. Hansen, P. Salamon. Neural network ensembles[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 1990, 12(10):993-1001.
[89] S. Hashem, B. Schmeiser. Improving model accuracy using optimal linear combinations of trained neural networks[J]. Neural Networks, IEEE Transactions on. 1995, 6(3):792-794.
[90] D. W. Opitz, J. W. Shavlik. Actively Searching for an Effective Neural Network Ensemble[J]. Connection Science. 1996, 8(3-4):337-337.
[91] J. J. Rodriguez, L. I. Kuncheva, C. J. Alonso. Rotation Forest: A New Classifier Ensemble Method[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 2006, 28(10):1619-1630.
[92] L. Breiman. Bagging predictors[J]. Machine Learning. 1996, 24(2):123-140.
[93] Y. Freund, R. E. Schapire. Decision-theoretic generalization of on-line learning and an application to boosting[J]. Journal of Computer and System Sciences. 1997, 55(1):119-139.
[94] M. M. Islam, X. Yao, K. Murase. A Constructive Algorithm for Training Cooperative Neural Network Ensembles[J]. Neural Networks, IEEE Transactions on. 2003, 14(4):820-834.
[95] B. E. Rosen. Ensemble learning using decorrelated neural network[J]. Connect Science. 1996, 8:373-383.
[96] L. Yong, Y. Xin. Simultaneous training of negatively correlated neural networks in an ensemble[J]. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on. 1999, 29(6):716-725.
[97] Z. S. H. Chan, N. Kasabov. Fast neural network ensemble learning via negative-correlation data correction[J]. Neural Networks, IEEE Transactions on. 2005, 16(6):1707-1710.
[98] B. Sch?lkopf, A. Smola, K.-R. Müller. Nonlinear Component Analysis as a Kernel Eigenvalue Problem[J]. neural computation. 1998, 10(5):1299-1319.
[99]李俭,孙才新,陈伟根等.基于灰色聚类分析的充油电力变压器绝缘故障诊断的研究[J].电工技术学报. 2002, 17(4):80-83.
[100]常涛,张晓星,熊浩等.动态隧道模糊C均值算法用于变压器油中溶解气体分析[J].高电压技术. 2009, 35(9):2181-2185.
[101]杨丽君,郑绳楦.基于RS和多类SVM的变压器故障诊断[J].仪器仪表学报. 2005, 26(8):613-615.
[102]张学工.关于统计学习理论与支持向量机[J].自动化学报. 2000, 26(1):32-42.
[103]王有元,廖瑞金,孙才新等.变压器油中溶解气体浓度灰色预测模型的改进[J].高电压技术. 2003, 29(4):24-26.
[104]刘思峰,郭天榜,党耀国.灰色系统理论及其应用[M],北京:科学出版社, 1999.
[105] B. Kosko. Fuzzy cognitive maps[J]. Int J Man-Mach Studies. 1986, 24:65-75.
[106] M. Yuan, L. Zhi-Qiang. On causal inference in fuzzy cognitive maps[J]. Fuzzy Systems, IEEE Transactions on. 2000, 8(1):107-119.
[107] W. Stach, L. Kurgan, W. Pedrycz等. Genetic learning of fuzzy cognitive maps[J]. Fuzzy Sets and Systems. 2005, 153(3):371-401.
[108] J. A. Dickerson, B. Kosko. Virtual worlds as fuzzy cognitive maps[C]. Virtual Reality Annual International Symposium, 1993., 1993 IEEE. 1993:471-477.
[109] D. E. Koulouriotis, I. E. Diakoulakis, D. M. Emiris. Learning fuzzy cognitive maps using evolution strategies: a novel schema for modeling and simulating high-level behavior[C]. Evolutionary Computation, 2001. Proceedings of the 2001 Congress on. 2001:364-371 vol. 361.
[110] F. HERRERA, M. LOZANO, J. L. VERDEGAY. Tackling Real-Coded Genetic Algorithms: Operators and Tools for Behavioural Analysis[J]. Artificial Intelligence Review. 1998, 12(4):265-319.
[111]周明,孙树栋.遗传算法原理及应用[M],北京:国防工业出版社, 1999.
[112] Z. Michalewicz, C. Z. Janikow, J. B. Krawczyk. A modified genetic algorithm for optimal control problems[J]. Computers & Mathematics with Applications. 1992, 23(12):83-94.
[113] M. Heinz, hlenbein, S.-V. Dirk. Predictive models for the breeder genetic algorithm i. continuous parameter optimization[J]. Evol Comput. 1993, 1(1):25-49.
[114] W. Stach, L. Kurgan, W. Pedrycz (2005). Linguistic Signal Prediction with the use of Fuzzy Cognitive Maps. In Proceedings of the Symposium on Human-Centric Computing (Banff, Alberta, Canada), pp. 64-71.
[115] S. Hengjie, M. Chunyan, W. Roel等. Implementation of Fuzzy Cognitive Maps Based on Fuzzy Neural Network and Application in Prediction of Time Series[J]. Fuzzy Systems, IEEE Transactions on. 2010, 18(2):233-250.
[116] W. Pedrycz, A. Gacek. Temporal granulation and its application to signal analysis[J]. Information Sciences. 2002, 143(1-4):47-71.
[117] W. Pedrycz. Why triangular membership functions?[J]. Fuzzy Sets and Systems. 1994,64(1):21-30.
[118] S. Roychowdhury, W. Pedrycz. A Survey of Defuzzification Strategies[J]. INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS. 2001, 16:679-695.
[119]肖燕彩.支持向量机在变压器状态评估中的应用[D].北京交通大学博士学位论文. 2008.
[120]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.