摘要
离线的变压器油中溶解气体分析(DGA),由于操作复杂、试验周期长、人为影响的误差大,所以无法做到实时了解变压器的内部绝缘状况,很难尽早地发现设备内部存在的潜伏性故障。因此无法采取防范措施以避免突发性事故的发生。而在线监测可以克服传统方法的不足,实现真正的在线检测、分析和诊断一体化,为管理者提供及时、准确、连续的决策依据。目前在我国已经有大量的变压器在线监测装置投入使用了。但是据统计,已安装的在线监测装置有很多发挥的作用不大。不少装置不仅自身的事故率很高,而且其故障诊断的准确率很低。这些都为变压器的在线监测带来了很多负面的影响。因而增强变压器在线监测设备的可靠性和提高变压器故障诊断的准确率,已成为目前变压器在线监测系统所面临的主要任务。
本文在深入分析变压器故障征兆与故障机理的复杂关系的基础上,不仅对于变压器故障诊断的方法进行了研究和分析,还基于光谱吸收原理设计了一套光纤气体传感器用于变压器油中溶解气体的在线监测。论文主要包括以下几个方面的内容:
第2章针对变压器单一故障诊断方法的局限性,提出了基于Borda模型的多种比值法组合诊断专家系统,将Rogers三比值法、日本电协研法、无编码比值法、改良三比值法、IEC-60599、大卫三角形法这六种成熟的比值法组合起来对变压器故障进行综合诊断。该方法积极的探索了多种方法综合诊断变压器绝缘故障的合作结构和机制,实现了六种比值诊断方法的诊断有机组合,消除了单个方法的诊断偏好对最终诊断和评估结果所产生的影响,解决了多种诊断方法的诊断结果相融合的问题。该方法实现了多种方法协同合作的诊断模式,比单一的诊断方法更可靠。从变压器故障实例的诊断结果来看,该方法比六种单项方法诊断的故障诊断准确率更高。其诊断效果也远优于该六种单项比值诊断法。
为了更完整、更充分地利用变压器原始诊断数据中蕴含的有利信息,并考虑到模糊因素对故障诊断的影响,第3章把模糊理论引入到变压器的故障诊断中。将改良三比值法与模糊C-均值聚类算法结合起来对变压器进行故障诊断。并建立了新型的变压器故障聚类诊断模型。还利用Matlab进行了实例仿真和测试。仿真结果表明了该方法基本上解决了比值法中关于“编码缺失”以及边界绝对化的问题。
第4章将支持向量机回归理论引入到变压器油中气体浓度预测中,建立了基于支持向量机回归理论的预测模型,以实现变压器故障报警和绝缘故障预报。实验结果表明了该方法能够满足工程实践的要求,有助于变压器运行状态的预测。
第5章将BP神经网络、灰色理论、线性回归预测算法和基于支持向量机回归模型这四种单项预测算法综合起来,采用最优加权组合预测模型,对油中溶解气体浓度的发展趋势进行精确的组合预测,为变压器油中溶解气体浓度的预测提供了新的途径。该组合预测方法能很好的综合各种单项预测方法的优势,与四种单项预测方法相比具有更高的预测精度。其可以有效地降低单项预测算法的预测误差,增强预测的稳健性,克服单项预测方法信息缺失以及考虑角度片面性的劣势。实例分析也表明了该组合预测方法比单项预测方法具有更高的准确性、可靠性和有效性。
由于变压器传统的在线监测系统一般采用色谱柱,需要消耗氧气和载气,而且色谱柱和传感器需定期标定,装置可靠性不高,检测气体成分过程繁琐,因此第6章根据比尔-朗伯特(Beer-Lambert)定律,按照光纤气体差分吸收的原理,设计了一套基于光纤气体传感器的变压器在线监测系统。该系统主要用于监测乙炔,甲烷,乙烯和一氧化碳四种变压器油中溶解气体的浓度,以判断变压器的故障状况。该系统不需要消耗载气和色谱柱等易耗品,且灵敏度高,方便,可靠,快速。并具有环保以及抗电磁干扰能力强的特性。该系统也不需复杂的气路和油路控制回路,能实现多组分气体在线实时分离和检测。
第7章总结全文,并提出了有待进一步研究的主要问题。
As an important means of fault diagnosis, dissolved gas-in-oil analysis (DGA) is one of the most important items in the preventive test code for electric power equipment at present. Because of a lot of problems such as complex operation, long periodic test and big artificial error, the method of off-line dissolved gas-in-oil analysis (DGA) can not monitor transformer inner insulation in real time. Therefore, there is no way to timely find out incipient fault of power transformers. And nothing consequently can stop the accident fault. Online monitoring of dissolved gas in transformer oil can conquer the shortage of traditional method and realize online detection, analysis and diagnosis. Thus operators can be given right, continuous and operational decision in time. Today, there are a lot of transformer online monitoring equipments put into service in our country. But according to the statistic, a lot of equipments in use can hardly bring the advantages into play because the accident rate of equipments is high and the accuracy rate of fault diagnosis is low. So how to strengthen reliability of transformer online monitoring devices and improve accuracy of fault diagnosis methods become the key problems that transformer online monitoring systems face.
The fault diagnosis methods of power transformer are studied and analyzed with analysis of complicated relationship between fault symptoms and fault mechanisms. And a new system of monitoring dissolved gas in transformer oil by fiber optic gas sensors is designed based on spectrum absorption theory. The main content of this thesis includes several aspects as follows:
Chapter 2 proposes an expert system of combination fault diagnosis with several codes methods such as Rogers three-ratio codes, Japan cooperative study group, non-code ratio method, the improved IEC three-ratio codes method, IEC-60599 method and Duval triangle method based on Borda model to overcome the limitation of one single fault diagnosis method. This system can realize collaborative diagnosis for transformer fault by integrating the six methods to improve the accuracy of transformer fault diagnosis. This system actively explores a good cooperative structure and mechanism of synthetic methods for transformer fault diagnosis. The organic combination of six methods can eliminate diagnosis preference influences of one single method on the last diagnosis and assessment result, which solves the decision fusion problem of various results. This system has more reliability than one single method and can thoroughly reflect the real fault features. Diagnosis results show this system has much higher accuracy rate than a single method with better diagnosis effect.
Chapter 3 makes full use of the favorable information of transformer original fault data and introduces fuzzy theory into transformer fault diagnosis according to the influences of fuzzy factors on fault. The improved IEC three-ratio codes method is combined with Fuzzy C-Means (FCM) clustering algorithm to diagnose transformer faults. A new fault diagnosis model of combining the two methods is proposed. The instance simulation and test are performed by Matlab. Results show the problems of absolute boundary and deletion codes about codes methods are basically solved and better fault diagnosis effects are obtained by this new way.
Chapter 4 introduces regression theory of support vector machines into prediction of dissolved gas in transformer oil and establishes prediction model of gas concentration based on the egression theory for transformer fault alarm and prediction. Test results show this new method can meet the requirement of project practice and is helpful to predict the operation state of power transformer.
In order to improve fault prediction for power transformer, chapter 5 brings forward a new combination forecasting model of optimal weights with BP neural network, Gray theory, linear regression model and regression model of support vector machines synthesized to predict the operation state of power transformer and provides a new way of prediction. This new model can give full play to the integral superiority of the four methods and has higher precision than one single method. This new method can effectively decrease the prediction error of one single method and strengthen prediction robust. The disadvantages of unilateral information and consideration for one single method can be avoided. The examples analysis also shows higher accuracy, reliability and effectiveness by this combination forecasting model are obtained than every single method.
The traditional transformer online monitoring system generally adopts oxygen carrier gas, chromatographic column. And the equipment is not simple with many shortages such as periodic calibration of chromatography column and sensor, low reliability of equipments and overelaborate detection procedure of gas composition. Therefore, chapter 6 proposes a transformer online monitoring system with fiber optic gas sensors according to differential fiber optic gas absorption principle based on Beer-Lambert’s law. This system is mainly used for monitoring the four dissolved gases in transformer oil such as acetylene, methane, ethylene and carbon monoxide to evaluate and identify fault status of transformer. This system dose not need any carrier gas and chromatographic column but can realize online separation and testing of different gases. It has a lot of abilities such as high sensitivity, high reliability, fast acquisition, convenience, environmental protection and anti-electromagnetic interference without complex gas path and oil control path.
Chapter 7 concludes the thesis and points out some directions for future research.
引文
[1]陈中涛.“十一五”期间我国能源市场供需前景研究[J].中国能源, 2006, 5(28): 16-23
[2]严璋.电气绝缘在线检测技术[M].北京:中国电力出版社, 1995: 30-75
[3]许婧.电力设备状态检修技术研究综述[J].电网技术, 2000, 24(8): 48-52
[4]赵文彬.油浸式电力变压器绝缘状态的在线监测系统[硕士论文].西安:西安交通大学, 2003: 30-60
[5]程鹏,俘来生,吴广宁等.大型变压器油中溶解气体在线监测技术进展[J].电力自动化设备, 2004, 24(11): 90-93
[6]陈化钢.电力设备预防性试验技术问答[M].北京:中国水利水电出版社, 2004: 2-10
[7] Weigen Chen, Caixin Sun. Study on fault diagnosis methods of transformer DGA with fuzzy model hierarchy classification [J]. ICMEP, 2000, (09): 167-171
[8]莫娟,严璋,李华等.基于多种智能方法的变压器故障综合诊断模型.电力系统自动化, 2005, 29(18): 85-89
[9] B. H. Ward. A survey of new techniques in insulation monitoring of power transformers. Electrical Insulation Magazine, IEEE, 2001, 17(3): 16–23.
[10] IEC60599-1999. Mineral oil-impregnated electrical equipment in service--guide to the interpretation of dissolved and free gases analysis [J].IEEEE, 1999, 1(1): 1-6
[11]赵家礼,张庆达.变压器故障诊断与修理[M].北京:机械工业出版社, 1998: 7-60
[12] Duval M. A review of faults detectable by gas-in-oil analysis in transformers [J]. Electrical Insulation Magazine, IEEE, 2002, 18(3): 8-17
[13] Rogers R. R. IEEE and IEC codes to interpret incipient faults in transformers using gas in oil analysis, IEEE Trans. on Elect. Insul., 1978, 13(5): 348-354
[14]黄建华,全零三.变电站高压电气设备状态检修的现状及其发展(J).电力系统自动化, 2001, 25(16): 56-61
[15] M. Wang, A. J. Vandermaar, K. D. Srivastava. Review of condition assessment of power transformers in service. Electrical Insulation Magazine, IEEE, 2002, 18(6):12–25
[16]王吕长,李福祺,高胜友.电力设备的在线监测与故障诊断.北京:清华大学出版社, 2006: 10-30
[17] Huang Y C. Condition assessment of power transformers using genetic-based neural networks. IEE Proceedings Science, Measurement and Technology, 2003, 150(1): 19-24
[18] Y. C. Huang, Huang Chaoming. Evolving wavelet networks for power transformer condition monitoring. IEEE Trans. Power Delivery, 2002, 17(2): 412-416
[19]胡怡妍,方巍.变压器故障诊断的专家系统研究.东北电力技术, 2000, 21(7): 12-14
[20] Wang Manghui. A novel extension method for transformer fault diagnosis [J]. Power Delivery, 2003, 18(1): 164-169
[21] Islam S M, Wu T, Ledwich G. A novel fuzzy logic approach to transformer fault diagnosis [J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2000, 7(2): 177-186
[22] J. L. Guardado, J. L. Naredo, P.Moreno et al. A comparative study of neural network efficiency in power transformers diagnosis using dissolved gas analysis. IEEE Trans. Power Delivery, 2001, 16(4): 643-647
[23] Adriana Rosa Garcez Castro, Vladimiro Miranda. Knowledge discovery in neural networks with application to transformer failure diagnosis [J]. Power Systems, 2005, 20(2): 717-724
[24] Booth, J. R. McDonald. The use of artificial neural networks for condition monitoring of electrical power transformers [J]. Neurocomputing, 1998, 23(3): 97-109
[25] Huang Yannchang, Yang Hongtzer, Huang Chinglien. Developing a new transformer fault diagnosis system through evolutionary fuzzy logic [J]. IEEE Trans. on Power Delivery, 1997, 12(2): 761-767
[26] Su Q, Mi C, Lai L et al. A fuzzy dissolved gas analysis method for the diagnosis of multiple faults in a transformer [J]. IEEE Transactions on Power System, 2000, 15(2): 593-598
[27]徐文,王大忠,周泽存.基于模糊理论的变压器故障诊断专家系统.电力系统自动化, 1995, 19(6): 32-37
[28]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
[29]邓宏贵,曹建,罗安.一种新的遗传算法及其在变压器故障诊断中的应用[J].中南大学学报, 2005, 36(3): 481-485
[30]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.中国电机工程学报, 1997, 17(2): 109-112
[31]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: 10-60
[32]高文胜.基于油中溶解气体分析的电力变压器绝缘故障诊断方法[博士学位论文].西安:西安交通大学, 1998: 10 60
[33]邹思轶.电力变压器油色谱在线监测信息系统的研究硕士[硕士论文].成都:西南交通大学, 2003: 10-50
[34]臧宏志.基于信息融合的大型电力变压器故障诊断[硕士论文].济南:山东大学, 2002: 10 40
[35]钱之银,陆志浩,楼其民等.变压器油中溶解气体判断方法综述.高压电器, 2002, 38(6): 4-7
[36]刘宜平,沈毅.一种基于多级信息融合技术的系统故障诊断方法[J].系统工程与电子技术, 2000, 22(12): 97-100
[37]中华人民共和国水利电力部,变压器油中溶解气体分析和判断导则.北京:水利电力出版社, 2001: 1-5
[38]王晓敏,胡毓达.群体决策的模糊Borda数规则.系统工程理论方法应用, 2003, 12(1): 14-19
[39]许晓东,赵勇,岳超源.用Borda法求解AHP中的群决策问题.华中理工大学学报, 1999, 27(8): 39-41
[40] D. F. Hsu, I. Taksa. Comparing rank and score combination methods for data fusion in information retrieval [J]. Information Retrieval, 2005, 8(3): 449-480
[41]齐演峰.多准则决策引论[M].北京:兵器工业出版社, 1989: 5-35
[42]陈挺.决策分析[M].北京:科学出版社, 1997: 4-20
[43]冯尚友.多目标决策理论方法与应用[M].武汉:华中理工大学出版社, 1990: 8-33
[44]徐南荣,仲伟俊.科学决策理论与方法[M].南京:东南大学出版社, 1995: 3-18
[45]魏世孝,周献中.多属性决策理论方法及其在系统中的应用[M].北京:国防工业出版社, 1998: 10-20
[46]姜青舫.实用决策分析[M].贵阳:贵州人民出版社, 1985: 10-30
[47]李怀祖.决策理论导引[M].北京:机械工业出版社, 1993: 8-20
[48]卫民堂,王宏毅,梁磊.决策理论与技术[M].西安:西安交通大学出版社, 2000: 5-36
[49] Pierre Favardin, Dominique Lepelley, Jerome Serais. Borda rule, Copeland method and strategic manipulation. Review of Economic Design [J], 2002, 7(2): 213-228
[50] Michael Dummett. The Borda count and agenda manipulation. Social Choice and Welfare[J], 1998, 15(2): 289-296
[51]陈国宏,陈衍泰,李美娟.组合评价系统综合研究[J].复旦学报:自然科学版, 2003, 42(5): 667-672
[52]宁自军.多种评价方法的综合应用[J].数理统计与管理, 2000, 19(3): 13-16
[53] Manimay Sen. Strategy-proofness of a class of Borda rules. Public Choice [J], 1984, 43(3): 251-285
[54] Thomas C. Ratliff. A comparison of Dodgson’s method and the Borda count. Economic Theory [J], 2002, 20(2): 357-372
[55]魏存平,邱莞华.群体决策基本理论评述[J].北京航空航天大学学报, 2000, 13(2): 24-28
[56] Christian Klamler. On the closeness aspect of three voting rules: Broda-Copeland-Maximin [J]. Group Decision and Negotiation, 2005, 14(3): 233-240
[57]杨以涵.专家系统及其在电力系统中的应用[M].北京:水利电力出版社, 1995:8-18
[58] Xu Wen, Wang Dazhong, Zhou Zecun. Expert system for faults diagnosis of transformer based on fuzzy set theory [J]. Automation of Electric Power Systems, 1995, 19(6): 32-37
[59]孟大伟,温祥龙,程杰英.电力变压器的故障诊断专家系统[J].黑龙江电力技术, 1999, 21(2): 33-37
[60]刘铭.电力系统设备故障诊断专家系统的研制[硕士论文].西安:西安交通大学, 2000: 10-50
[61]杜剑光.变压器故障诊断专家系统[硕士论文].北京:华北电力大学, 2003: 10-45
[62] B. Sparling, J. Aubin, A. Glodjo. Field experience with multi-gas on-line monitoring of power transformers [J]. Transmission and Distribution Conference, IEEE, 1999, 2(2): 895-900
[63] A. Basak. Condition monitoring of power transformers [J]. Engineering Science and Education Journal, 1999, 8(1): 41–46
[64]孙才新,陈伟根,李俭.电气设备油中气体在线监测与故障诊断技术[M].北京:科学技术出版社, 2003: 10-50
[65]丁晓群,孙军,王大忠.模糊诊断电力变压器故障点部位的应用研究[J].电网技术, 2000, 24(5): 48-51
[66]胡晓晖,屈梁材,蒲晓红.基于模糊知识库的电力变压器故障树分析[J].湖南大学学报, 1998, 25(5): 95-99
[67] Hongtzer Yang, Chiungchou Liao. Adaptive fuzzy diagnosis systems for dissolved gas analysis of power transformer [J]. IEEE Transactions on Power Delivery, 1999, 14(4): 1342-1350
[68] J. J. Dukarm. Transformer oil diagnosis using fuzzy logic and neural network [J], Can. Conf. Electr. Comput. Eng., 1993, 1(1): 329–332
[69] Chen Anpin, Lin Changchun. Fuzzy approaches for fault diagnosis of transformers [J]. Fuzzy Sets and Systems, 2001, 118(1): 139-151
[70] Kosko B. Fuzzy systems as universal approximators [J]. IEEE Trans. on Computers, 1994, 43(11): 1329-1333
[71]灵方向,史忠科,戴冠中. T-S型模糊系统的稳定性分析及其应用[J].控制与决策, 1999, 14(1): 65-68
[72]杨光松.多级模糊综合评判技术的研究及其OOP实现[硕士论文].贵阳:贵州大学, 2001: 10-45
[73]胡淑礼.模糊数学及应用[M].成都:四川大学出版社, 1994: 10-21
[74] Bezdek J C. Pattern recognition with fuzzy objective function algorithms [M]. NewYork: Plenum Press, 1981: 1-8
[75]张媛祥.一种稳健的聚类方法[J].数学的实践与认识, 2003, 33(8): 8-10
[76]彭春华,程乾生.一种基于最小张树的属性聚类算法[J].系统工程理论与实践, 2001, 21(2): 30–34
[77]贺仁亚,程乾生.一种新的分类方法[J].数学的实践与认识, 2002, 32(5): 830-834
[78]程乾生.属性均值聚类[J].系统工程理论与实践, 1998, 18(9): 124–126
[79]张莉,周伟达,焦李成.核聚类算法.计算机学报, 2002, 25(6): 587-590
[80]伍忠东,高新波,谢维信.基于核方法的模糊聚类算法[J].西安电子科技大学学报, 2004, 31(4): 533-537
[81] Girolami M. Mercer kernel-based clustering in feature space. IEEE Trans. Neural Networks, 2002, 13(3): 780-784
[82]高新波.模糊聚类分析及其应用[M].西安:西安电子科技大学出版社, 2004: 10-21
[83]王耀南.智能信息处理技术[M].北京:高等教育出版社, 2003: 10-30
[84]张兴华.模糊聚类分析的新算法[J].数学的实践与认识, 2005,(3): 138-141
[85] Chen S C, Zhang D Q. Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure. IEEE Trans. SMC PART B: CYBERNETICS, 2004, 34(4): 1907-1916
[86]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, 1(13): 51-54
[87] Pal N R, Bezdek J C. On clustering for the fuzzy C-means model. IEEE Trans. Fuzzy Systems, 1995, 3(3): 370-379
[88]范九伦.模糊聚类有效性研究[博士学位].西安:西安电子科技大学, 1998: 20-70
[89] Menard M, Courboulay V, Dardignac P. Possibilistic and probabilistic fuzzy clustering: unification within the framework of the non-extensive thermostatistics. Pattern Recognition, 2003, 36(6): 1325-1342
[90] Kaymak U, Setne M. Fuzzy clustering with volume prototypes and adaptive cluster merging. IEEE Trans. on Fuzzy Systems, 2002, 10(6): 706-712
[91] K. L. Wu, M. S. Yang. Alternative C-means clustering algorithms. PatternRecognition, 2002, 35(10): 2267-2278
[92] Hathaway R J, Bezdek J C, Hu Y K. Generalized fuzzy c-means clustering strategies using Lp norm distances. IEEE Trans. on Fuzzy Systems, 2000, 8(5): 576-582
[93] Yu J. General c-means clustering model and its applications, In: Proc. of the 2003 IEEE Computer Society Conference on CVPR. Madison: IEEE, 2003, 2: 122-127
[94]于剑.聚类有效性及其应用[博士学位论文].北京:北京大学数学科学学院, 2000:30-70
[95] Jian Yu, Qiansheng Cheng, Houkuan Huang. Analysis of the weighting exponent in the FCM [J]. IEEE Transactions on Systems, 2004, 34(1): 634-639
[96] Jiangshe Zhang, Yiuwing Leung. Improved possibilistic c-means clustering algorithms. IEEE Trans. on Fuzzy Systems, 2004, 12(2): 209-217.
[97] J. C. Bezdek. A convergence theorem for the fuzzy ISODATA clustering algorithms [J]. IEEE Trans on Pattern Anal Mach Intel, 1980, 2(1): 1-8
[98]高新波,裴继红,谢维信.模糊C-均值聚类算法中加权指数m的研究[J].电子学报, 2000, 28(4): 80–83
[99]李常禧.电气设备诊断技术概论[M].北京:水利电力出版社, 1994:20-40
[100] Maizun BintiAhmad, Zulkefli bin Yaacob. Dissolved gas analysis using expert system [J]. Student Conference on Research and Development Proceedings, 2002, 1(1): 313-316
[101]常文平,范峥,王晓敏.变压器故障在现监测系统及其应用[J].微计算机信息, 2005, 21(8): 125-127
[102]王昌长,李福祺.电力设备的在线监测与故障诊断.北京:清华大学出版社, 1992: 10-50
[103]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气体的浓度[J].电力系统自动化, 2006, 30(13): 64-67
[104]李华,胡奇英.预测与决策[M].西安:西安电子科技大学出版社, 2005: 8-20
[105] Anuj Goel, Robert J. Graves. Electronic system reliability collating prediction models [J]. IEEE Transactions on Device and Materials Reliability, 2006, 6(2):255-265
[106] Michel Duvel. A review of faults detectable by gas-in-oil analysis in transformers [J]. IEEE Electrical Insulation Magazine, 2002, 18(3): 8-17
[107]周利军,吴广宁,宿冲等.变压器油中故障气体的复合预测方法[J].西南交通大学学报, 2006, 41(2): 150-153
[108]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
[109] Yuan Baokui, Guo Jiwei, Tang Guoqing et al. Using grey theory to predict the gas-in-oil concentrations in oil-filled transformer [C]. Proceeding of the 6th International Conference on Properties and Applications of Dielectric Materials, 2000, (6): 21-26
[110]刘思峰,党耀国.预测方法与技术[M].北京:高等教育出版社, 2005: 10-46
[111] T. Hastie, R. Tibshirani, J. H. Friedman. The elements of statistical learning: Data Mining, Inference, Prediction. New York: Springer, 2001: 2-5
[112]邓乃扬,田英杰.数据挖掘中的新方法-支持向量机[M].北京:科学出版社, 2004: 10-40
[113]张学工.关于统计学习理论与支持向量机.自动化学报, 2000, 26(1): 32-42
[114]胡国胜.支持向量机算法及应用[[J].现代电子技术, 2005, 28(3): 106-109
[115] Vapnik V, Chapelle O. Bounds on error expectation for support vector machines. Neural Computation, 2000, 12(9): 2013-2036
[116] O. Chapelle, V. Vapnik. Choosing multiple parameters for support vector machines. Machine Learning, 2002, 46(1): 131-159
[117] Lin C J. On the convergence of the decomposition method for support vector machines. IEEE Trans on Neural Networks, 2001, 12(6): 1288-1298
[118] Keerthi S, Gilbert E G. Convergence of a generalized SMO algorithm for SVM classifier design. Machine Learning, 2002, 46(1): 351-360
[119]马笑箫,黄席越,柴毅.基于支持向量机的故障过程趋势预测研究.系统仿真学报, 2002, 14(11): 1548-1551
[120]王定成,方廷健.高理富等.支持向量机回归在线建模及应用.控制与决策, 2003, 18(1): 89-95
[121]王宇红,黄德先.基于支持向量机的非线性预测控制技术.信息与控制, 2004, 33(2): 134-140
[122] Qi Miao, Wang Shifu. Nonlinear model predictive control based on support vector regression [J]. Proceedings of the First International Conference on Machine Learning and Cybemetics, Beijing, 2002, 1(1): 1657-1667
[123]刘江华,程君实,陈佳品.支持向量机训练算法综述[J].信息与控制, 2002, 31(1): 45-50
[124] V. N. Vapnik. The nature of statistical learning theory [M]. New York: Springer-Verlag, 1995: 138-167
[125] Gunn S. Support vector machines for classification and regression [R]. Technical Report of University of Southampton, 1998, 1(1): 1-66
[126] Vapnik V N. An overview of statistical Learning Theory [J]. IEEE Trans. Neural Network, 1999, 10 (5):988-999.
[127] N Cristianini, J S Taylor. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods [J]. Cambridge University Press, 2000, (40): 30-80
[128] Meeker W Q, Escobar L A. Statistical methods for reliability data [J]. New York: John Wiley & Sons, 1998: 12-30
[129] Hongyu Sun, Chunming Zhang, Bin Ran. Interval prediction for traffic time series using local linear predictor [A]. 2004 IEEE Intelligent Transportation Systems Conference [C]. Washington, D. C., USA: 2004, 1(1): 410-415
[130] M. H. Wang. Grey-extension method for incipient fault forecasting of oil-immersed power transformer [J]. Electric Power Components and Systems, 2004, 32(10): 59-975
[131] Youyuan Wang, Ruijin Liao, Caixin Sun et al. A GA-based grey prediction model for predicting the gas-in-oil concentrations in oil-filled transformer [C]. Conference Record of the 2004 IEEE International Symposium on Electrical Insulation, 2004, (9): 74-77
[132]李应红,尉询楷,刘建勋,支持向量机的工程应用[M].北京:兵器工业出版社, 2004: 10-30
[133]董其国.电力变压器故障与诊断[M].北京:中国电力出版, 2002: 20-50
[134]朱德恒,谈克雄.电气设备状态检测与故障诊断技术的现状与展望[J].电力设备, 2003, 4(6): 1-8
[135] C. H. Yann, Evolving neural nets for fault diagnosis of power transformers [J]. IEEE Trans. on Power Delivery, 2003, 18(3): 843-848
[136] Y. Han, Y. H. Song. Condition monitoring techniques for electrical equipment-a literature survey [J]. IEEE Trans. on Power Delivery, 2003, 18(1): 4-13
[137] Motoo Tsuchie. Recent diagnostic technology on oil-immersed power transformers in Japan. IEEE/PES Transmission and Distribution Conference and Exhibition, 2002, 2(1): 1496-1499
[138] Dual M. New techniques for dissolved gas-in-oil analysis [J]. Electrical Insulation Magazine, IEEE, 2003, 19(2): 6-15
[139]陈华友.组合预测方法及其应用研究[博士学位].合肥:中国科学技术大学, 2002: 10-60
[140] S. Gupta, P. C. Wilton. Combination of forecasts: an extension [J]. Management Science, 1987, 33(3): 356-372
[141] Bunn D W. Forecasting with more than one model [J]. Journal of Forecasting, 1989, 8(3): 161-166
[142]杨建刚.人工神经网络实用教程[M].杭州:浙江大学出版社, 2001: 10-43
[143]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
[144]顾雪平,盛四清,张文勤等.电力系统故障诊断神经网络专家系统的一种实现方式[J].电力系统自动化, 1995, 19(9): 26-29
[145] A. S. Farag, M. Mohandes, Ali Al-Shaikh. Diagnosing failed distribution transformers using neural networks. IEEE Transactions on Power Delivery, 2001, 16(4) :631-636
[146] Mohammad S Obaidat. Artificial neural networks to systems, Man and Cybernetics: Characteristics, Structures, and Applications [J]. IEEE Transactions on System, 1998, 28(4): 489-495
[147] H. M. Yao, H. B. Vuthaluru, M. O. Tade, D. Djukanovic. Artificial neural network-based prediction of hydrogen content of coal in power station boilers [J].Fuel, 2005, (84): 1535-1542
[148]邓聚龙.灰色控制系统[M.]武汉:华中理工大学出版社, 1993: 10-40
[149] M. H. Wang, C. P Hung. Novel grey model for the prediction of trend of dissolved gases in oil-filled power apparatus [J]. Electric Power Systems Research, 2003, 67(1): 53-58
[150]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
[151] W. L. Yao, S. C. Chi, J. H. Chen. An improved grey-based approach for electricity demand forecasting [J]. Elsevier Science B. V., 2003, 67(3): 217-224
[152]王有元,廖瑞金,孙才新,杜林等.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
[153] Liu Sifeng, Zhu Yongda. Grey econometrics combined model [J]. The Journal of Grey System, 1996, 8(1): 103-110
[154]宋慧明,韦来生.线性模型中回归系数混合估计的相对效率[J].中国科学技术大学学报, 2006, 36(9): 338-342
[155] Norman R. Draper, Harry Smith. Applied regression analysis[M]. New York: John Wiley & Sons, 2003: 10-33
[156]何晓群,刘文卿.应用回归分析[M].北京:中国人民大学出版社, 2001: 4-32
[157] Samprit Chartterjee, Bertram Price, Regression analysis by example [M]. New York: John Wiley & Sons, 1991: 10-43
[158]王松桂,陈敏,陈立萍.线性统计模型[M].北京:高等教育出版社, 1999: 20-43
[159] Douglas C. Montgomery, E. A. Peck, G. G. Vining. Introduction to linear regression analysis [M]. New York: John Wiley & Sons, 2001: 10-34
[160] Bates J M, Granger C W J. Combination of forecasts [J]. Operations Research Quarterly, 1969, 20(4): 451-468
[161]唐小我.组合预测计算方法研究[J].预测, 1991, 10(4): 35-40
[162]谢开贵,何斌,杨万年.组合预测权系数的确定[J].预测, 1998, 17(7): 151-154
[163] Chatfield C. Model uncertainty and forecast accuracy [J]. Journal of Forecasting, 1996, 15(7): 495-508
[164]唐小我,曹长修,金德运.组合预测最优加权系数向量的进一步研究.预测[J], 1994, 13(2): 48-49
[165] Tang Xiaowo, Zhou Zongfang, Shi Y. The error bounds of combined forecasting [J]. Mathematical and Computer Modelling, 2002, 36(9): 997-1005
[166]李红雷.油浸电力设备在线色谱监测及诊断系统的研究[博士学位论文].上海:上海交通大学, 2000: 20-80
[167] Jianpo Lin, Jiyin Zhao, Ruirui Zheng et al. Fault diagnosis system of transformer based on gas chromatography [C]. Proceedings of the Fifth International Conference on Machine Learning and Cybernetics, Dalian ,China, 2006, 2(1): 809-813
[168] Arakelian, V. G. The long way to the automatic chromatographic analysis gases dissolved in insulating oil. IEEE Electrical Insulation Magazine, 2004, 20(6): 8-25
[169]刘先勇,周方洁.用傅立叶红外变换实现在线溶解气体分析的研究[J].变压器, 2002, 39(6): 29-32
[170] Yu F T, Yin S. Fiber optic sensor [M]. New York: Marcel Dekker, 2002: 5-45
[171]靳伟,廖延彪,张志鹏.导波光学传感器原理与技术.北京:科学出版社, 1998: 254-255
[172] Yu Hongbo, Liao Yanbiao, Jin Wei. Review of the optical fiber sensor[J]. Laser and Infrared, 2002, 32(3): 193-l96
[173] W. Jin, G. Stewart, B. Culshaw. Absorption measurement of methane gas with a broadband light source and interferometric signal processing. Optics Letters, 1993, 18(6): 1364-1366
[174] Shimose Y, Okamoto T, Maruyama A et al. Remote sensing of methane gas by differential absorption measurement using a wavelength tunable DFB LD. IEEE Photonics Technology Letters, 1999, 3(1): 178-181
[175]王艳菊,王玉田,张玉燕.差分吸收式甲烷气体传感系统的研究[J].仪器仪表学报, 2006, 27(12): 1647-1650
[176]王艳菊.基于光谱吸收的光纤式有害气体测量技术的研究[博士学位论文].秦皇岛:燕山大学, 2006:10-65.
[177]王艳菊,王玉田,王忠东.用于气体差分检测的微弱信号处理电路的研究.传感器与微系统, 2006, 6(25): 13-15
[178] Sano Y, Yoshino T. Fast optical wavelength interrogator employing arrayed waveguide grating for distributed fiber bragg grating sensors. Journal of Light wave Technology, 2003, 21(1): 132-13
[179] Chen P K C, Wei Jin, Demokan S. FMCW multiplexing of fiber Bragg Grating sensors. IEEE Journal of Selected Topic in Quantum Electronics, 2000, 6(5): 756-763
[180] Valente L C G, Braga A M B, Ribeiro A S A et al. Combined time and wavelength multiplexing technique of optical fiber grating sensor arrays using commercial OTDR equipment. IEEE Sensors Journal, 2003, 3(1): 31-35