基于油中气体分析的多种人工智能技术在变压器故障诊断中的应用
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
变压器作为电力系统的枢纽设备,其运行可靠性直接关系到电力系统的安全与稳定。变压器由计划检修转变为状态检修是提高其可靠性的重要手段之一。对于电力变压器这个电力系统重要的电气设备的状态维修,是国内外研究的重点,而变压器内部故障的在线诊断是实现其状态检修的前提条件之一。
     本文针对应用油中溶解气体分析法(Dissolved Gases Analysis,简称DGA)进行变压器绝缘诊断时所遇到的主要技术难点,提出了提高变压器故障诊断的准确性、可靠性的几种方法。
     国内外研究电力变压器内部故障诊断方法很多,如神经网络方法、模糊集理论方法、专家系统方法、综合人工智能技术以及变压器故障在线监测技术的应用等。然而要想准确、及时地诊断出变压器内部故障性质和故障部位,必须基于变压器油中溶解气体分析,综合多种人工智能技术、结合电气试验参数,利用在线监测才能诊断实施。
     当变压器内部局部过热或放电时,产生氢气(H_2)、甲烷(CH_4)、乙烷(C_2H_6)、乙烯(G_2H_4)、乙炔(C_2H_2)、一氧化碳(CO)、二氧化碳(CO_2)等特征气体。
     当内部潜伏性故障加重时,它们产生速度加快,其油中溶解的组分和含量可以被看作诊断变压器故障的特征参数,因此通过对油中溶解气体进行气相色谱分析,可发现变压器内部故障。
     当固体绝缘局部过热时,会产生大量一氧化碳(CO)和二氧化碳(CO_2);当油局部过热时,会产生大量乙烯和甲烷。电弧放电的特征气体主要是氢气和乙炔。一般乙炔(C_2H_2)占总烃20~70%,氢气(H_2)占氢烃的30~90%,乙炔(C_2H_2)大多高于甲烷(CH_4)。
     火花放电的特征气体也是以氢气(H_2)、乙炔(C_2H_2)为主,一般总烃含量不高。局部放电时,特征气体主要成份是氢气(H_2)和甲烷(CH_4)。乙炔(C_2H_2)在总烃中所占比例一般小于2%,这是和上述两种放电现象区别的主要标志。
     无论何种放电,只要有固体绝缘介入时,就都会产生一氧化碳(CO)和二氧化
    
    郑州大学工学硕士论文摘要
    碳(COZ)。
     特征气体法是根据变压器各种故障所产生的特征气体来判断故障的性质。三比
    值法是用油中溶解气体色谱法测得油中气体浓度后,用三个比值大小(C热/C2比、
    CH扩HZ、CZH扩CZ氏)来判断变压器内部故障情况。四比值法是根据5种不同气体组分
    产生的四个比值(C比/HZ、CZH6/CH。、CZH。/C儿、CZHZ/CZH4)的大小范围来判定故障类
    型。
     本文基于电力变压器油中气体的产生和溶解原理,深入分析了油中溶解气体与变
    压器故障类型之间的关系,进而把油中溶解气体的组分和含量作为变压器故障诊断的
    特征量。通过对判断变压器故障常用的特征气体法、三比值法的深入分析,其诊断准
    确率较高,但对故障原因、故障现象和故障机理间同时存在不确定性和随机性的变压
    器等电气设备的故障诊断,经典法难于满足工程应用的需要;
     应用专家系统、人工神经网络和智能型系统综合人工智能技术诊断变压器故障
    时,专家系统模拟人类的逻辑思维,即人类专家处理问题时的思考过程;而人工神经
    网络模拟人类的形象思维,注重的是人类专家的结论。
     本文提出的人工智能型系统利用了人工神经网络自组织、自学习的特点,克服了
    传统专家系统知识获取的“瓶颈”及知识库维护等难点,再加上利用专家系统的逻辑
    推理功能,弥补了人工神经网络的不足之处。
     在理论研究的基础上,本文运用上述方法和技术对河南省南阳电业局近10年来
    电力变压器异常及故障的离线数据进行分析、诊断,针对每种方法的不足,提出了相
    应的解决措施。
     大量的诊断实例表明:离线气相色谱法对电力变压器绝缘故障诊断是有效的,它
    能够分析出变压器的绝缘状况,正确识别绝缘故障类型并能给出故障发生的大致部
    位,但是它必须经过油样采集一油样运输一油气分离一色谱分析的过程,会对判断故障
    类型及其严重程度造成很大误差,而且对于发展较快的故障不能连续在线监测。
     为更及时、准确地发现变压器故障,缩短检测周期,逐步实现变压器的状态检修,
    变压器的在线监测应运而生,并逐步得到推广应用。
     论文在探讨了气相色谱在线监测和故障诊断等技术在国内外发展的现状的基
    础上,对变压器应用在线监测装置的重要性进行了论证。
    
    郑州大学工学硕士论文摘要
     在线油中溶解气体分析的含义首先要求连续地监测变压器全部油中溶解气体,
    其检测灵敏度和范围最好达到或超过离线气相色谱分析;其次,应将检测结果实时
    远传给监测中心的故障诊断专家系统,由专家系统给出变压器的实际运行状态,并
    建议应采取的措施。
     电力变压器早期故障在线监测装置,是一种将变压器油中的溶解气体经选择性的
    渗透膜进入电化学气体传感器内,并在传感器内与氧气进行化学反应,产生与反应速
    率成比例的电信号,实时在线测量气体浓度变化数值的装置。
     在线故障诊断系统是比较新的课题。本文展示了该课题的原理和可行性,结合河
    南省南阳、新乡电业局应用实例,介绍了HYDRAN 201R Modeh在线监测系统的配置、
    性能、安装调试方案,并在实际运行中采取了相应的措施,监测的准确性高于前面的
    方法。具体事例说明该?
The reliability of power transformers, as the major equipment in power systems, directly affects the safety and stability of power system operation. An important measure to improve the operation reliability is the translation from time- maintenance to status maintenance for transformers. The status maintenance of the power transformers is put a important station at home and abroad. Moreover, on-line fault diagnosis for transformer is one of the precondition to carry status maintenance out.
    In accordance with the technological difficulties encountered in the process of insulation supervision based on the Dissolved Gases Analysis (DGA) , several kinds of method are presented to improve the reliability and precision of fault diagnosis of the power transformer.
    There are many methods applied to study the faults inside the power transformers, such as the neural network (NN) method, the fuzzy set theory method, the expert system (ES) method, the application, of synthetical artificial intelligence (AI) technique, the transformer fault on-line monitoring technique, etc. However, in order to detect the faults precisely and timely, only the on-line monitoring technique can be used, starting from the study of Dissolved Gases Analysis (DGA), synthesising various artificial intelligence (AI) technique and electric testing parameters.
    The characteristic gases , such as hydrogen (H2) , methane (CH4) , hexane (C2H6), ethene(C2H4), ethine(C2H2), carbon monoxide (CO), carbon dioxide (C02), etc are produced, when partial heat or discharge takes place in the transformers.
    The more serious hidden faults become, the faster these gases are
    
    
    
    
    produced. The contents and constituents of oil-dissolved gas can be considered as the character parameter for diagnosing transformer faults. So transformer inner faults can be detected with dissolved gases chromatographic analysis. A amount of carbon monoxide (CO) and carbon dioxide (C02) can give out with solid insulating materials' partial overheat. A quantity of ethene
    (C2H4) and methane (CRi) can be produced with the oil partial overheat. The main characteristic gases are hydrogen (H2) and ethine(C2H2) for electric arc discharge. Generally, the content of ethine(C2H2) is 20~70% of that of total hydrocarbon, the content of hydrogen (H2) is 30~90% of that of total hydrogen and hydrocarbon. In general, ethine(C2H2) is much more than methane
    (CH4) .
    The main characteristic gases are also hydrogen (H2) and ethine(C2H2) for sparkle discharge. Generally, the content of ethine(C2H2) of total hydrocarbon is little.
    Whichever discharge is , carbon monoxide (CO) and dioxide (C02) can be produced for solid insulating materials faults.
    The characteristic gas methods determine the fault types with the characteristic gases produced by various transformer faults. The three-ratio methods determine the fault types with three ratioes of the gases content measured with the dissolved gases chromatographic analysis. The four-ratio methods determine the fault types with four ratioes (CH4/H2, C2H6/CH4, C2H4/C2H6, C2H2/C2H4) of five kinds of different gases content.
    Starting from the study of occurring and resolving theory for gases in transformer oil, the relationships between oil-dissolved gases and the transformer fault types are further analyzed, all of which contribute to the final conclusion that the contents and constituents of oil-dissolved gas can be considered as the character parameter for diagnosing transformer faults. By deeply studying the common transformer faults diagnosing methods, such as character gas methods and three-ratio methods, the diagnosing precision is
    
    
    
    much high, while several shortcomings such as uncertainness judgment when the fault reasons, phenomenon and principles come out together while can not consistent to each other etc. the classical methods can not fully meet the need to engineering practical application.
    The expert system , artificial neural network, synthetical artificial intelligence (AI) technique are applied to diagnose the transformer faults, Expert system s
引文
[1]李晓勇.全国变压器运行情况及事故统计分析,变压器早期故障在线监测技术及用户报告汇编.2003,10.
    [2]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.电工技术学报.1998.1(3):51-54
    [3]孙才新,郭俊峰,廖瑞金,杜林,陈伟根.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.中国电机工程学报2001.21(2):37-41.
    [4]王财胜,孙财新,廖瑞金.变压器色谱监测中的BPNN故障诊断法[J].中国电机工程学报,1997,17(5):322-325.
    [5]R.Malewskiet.al.Insulation diagnostic system for HV power transformer in service.CIGRE, 1986 Session, No.12-01.
    [6]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.
    [7]李红雪,肖登明等.神经网络诊断变压器故障的新方法[J].高压电器,2000,6:12-17.
    [8]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):1758-1760.
    [9]Tomsovic K, Tapper M.A Fuzzy Information Approch to Integrating Different Transformer Diagnostic methods[J].IEEE Trans.on Power Delivery, 1993, 8(3):1638-1646.
    [10]Lin CE, Ling JM.An Expert System for Transformer Fault Diagnosis using Dissolved Gas analysis[J].IEEETrans.on Power Delivery, 1993, 8(1): 231-238.
    [11]HUANG Yah-chang.Developing an new transformer fault diagnosis system through evolutionary fuzzy logic[J].IEEE Trans.on Power Delivery, 1997, 12(2): 761-767.
    
    
    [12]何跃英,王荣汉.基于模糊理论的电力设备故障诊断专家系统[J].电工技术学报,1994,3:43-46.
    [13]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.
    [14]丁晓群,孙军等.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.
    [15]张冠军,钱政,严璋.变压器绝缘诊断中的模糊ISODATA法[J].高电压技术,1999,3,25(1):1-3.
    [16]王道勇.变压器故障检测方法的改进[J].电力系统自动化,1998,22(11):44—84.
    [17]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):32-35.
    [18]张建文,赵大光.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.
    [19]廖瑞金,姚陈果,孙才新,顾乐观.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.
    [20]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):122-125.
    [21]杨启平,薛五德,蓝之达.变压器故障人工智能系统的研究[J]高电压技术,2003,29(3):10-12.
    [22]钱政,严璋,罗承沐.范例推理与模糊数学的变压器故障诊断方法[J].高电压技术,2001,27(6):1-5.
    [23]Zhengkao Zhang and M.R.Raghuveer, On-line Insulation Condition Monitoring Technique for High Voltage Apparatus, 10th ISH'97.
    [24]杨莉,尚勇,严璋等.综合智能技术在网络化的绝缘在线诊断专家系统中的应用[J].电工电能新技术,2001,2:64-68.
    [25]秦仁炎.变压器在线监测的现状和将来.第一届全国电力行业电气设备状态监测与故障诊断技术研讨会资料汇编,2003,3:82-96.
    [26]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.1996.
    [27]潘正君,康立山.演化计算[M].北京:清华大学出版社,1998.
    [28]国家标准局.GB7252-87变压器油中溶解气体分析和判断导则.北京:中国标准出版社.1987.
    [29]赵家礼,张庆达.变压器故障诊断与修理.北京:机械工业出版社,1998.
    [30]电力部电力科学研究院,1990年全国110KV及以上电压等级变压器类设备事故统计分析,1991.
    [31]中华人民共和国国家经济贸易委员会.中华人民共和国电力行业标准DL/T722-2000变压器油中溶解气体分析和判断导则.
    [32]杨启平,薛五德,符杨,蓝之达.专家系统在变压器故障诊断中的应用.变压器,1996(6):35-38.
    [33]河南省南阳电业局检修公司化验班河南省南阳电业局近10年来电力设备油质缺陷统计,NDYX/QR-YH-06.
    [34]杨启平,薛五德,蓝之达.变压器故障诊断技术的研究.变压器,2002(10):38-42.
    [35]刘先勇.在线油中气体分析技术及其实现途径.第一届全国电力行业电气设备状态监测与故障诊断技术研讨会资料汇编,2003,3:205-210.
    [36]赵来红,张宏敏,方志民.变压器早期故障在线监测的实际应用.第一届全国电力行业电气设备状态监测与故障诊断技术研讨会资料汇编,2003,3:141-144.
    [37]王尧,张晨曦.变压器油中溶解气体在线监测技术及其应用.第一届全国电力行业电气设备状态监测与故障诊断技术研讨会资料汇编,2003,3:105-111.
    [38]林礼清.大型变压器早期故障在线监测技术应用.第一届全国电力行业电气设备状态监测与故障诊断技术研讨会资料汇编,2003,3:211-214.
    [39]International Electrotechnical Commision.Internation for the analysis in transformer and other on-filled electrical equipment in service.IEC Publication 599,1978.
    [40]IEC60599.Mineral oil-impregnated electrical equipment in service-guide to the interpretation of dissolved and free gases! Analysis, second edition.1999.
    
    
    [41]魏守智,王刚,王金东等.基于信息融合方法的电力变压器网络在线监测与故障诊断研究[J].计算机工程与应用,2002,22:51-55.
    [42]J.L.Guardado, J.L.Naredo, Member, IEEE, P.Moreno, andC.R.Fuerte, Member, IEE E.a comparative study of neural network efficiency in power transformers diagnosis using dissovlved gas analysis.IEEE transactions on power Delivery ,vol.16, no.4, October 2001.
    [43]D.M.Allanet al:A Continuous Insulation Monitor for High Voltage Transformer Bushing, ISH-7, No.74.01, Aug.1991.
    [44]C.E.Lin, An expert system for transformer fault diagnosis using dissolvedgas analysis, IEEE Trans.On Power Delivery, 1993(1).
    [45]H.Tsukioka et.al New apparatus for detecting transformer faults, IEEE, Trans.1986, Vol.EI-21(2):221-229.
    [46]Yanari T.Development and Future Aspects of Large Power Transformers.T.IEE Japan.Vol.115-B, No.4,1995:308-311.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700