基于聚类和时间序列分析的变压器状态评价方法
|
摘要
传统的电力变压器DGA故障诊断方法,仅能二值化地判断设备处于健康或故障状态,无法表征变压器的潜在故障情况,也无法确定变压器向故障状态转化的趋势。对此,提出了一种基于聚类和时间序列分析的变压器状态评价方法。首先,基于点密度判据进行数据预处理,消除噪声影响。其次,基于大数据聚类思想,计算采样数据和历史故障数据簇的相对邻近度,根据计算结果将设备状态划分为健康、潜伏故障或故障。在此基础上判断故障设备的故障类型,基于故障类型关联权重计算健康设备的健康得分,通过时间序列相似性分析方法获取潜伏故障设备的预测故障发展时间。算例分析验证了该方法的可行性与有效性。
Conventional DGA fault diagnosis methods of power transformer can only judge whether the equipment is in normal or fault condition, but they can neither characterize the potential failure of the normal transformer nor identify the trend of transformer converted into fault state. In order to solve this problem, this paper proposes a transformer state evaluation method based on clustering and time series analysis method. Firstly, the data preprocessing method is carried out to prevent the influence of noise. Then, based on big data clustering method, the proximity of sampled data and historical fault data clusters is calculated. Based on the result, the equipment condition is sorted into healthy, incipient faulty or faulty. For equipment in faulty state, the fault type is identified. For healthy equipment, the health score is calculated based on related weights of fault types. For incipient faulty equipment, the time series similarity analysis method is used to further predict the time span for the equipment changing from current state to fault state. The example analysis verifies the feasibility and effectiveness of the proposed method.
Conventional DGA fault diagnosis methods of power transformer can only judge whether the equipment is in normal or fault condition, but they can neither characterize the potential failure of the normal transformer nor identify the trend of transformer converted into fault state. In order to solve this problem, this paper proposes a transformer state evaluation method based on clustering and time series analysis method. Firstly, the data preprocessing method is carried out to prevent the influence of noise. Then, based on big data clustering method, the proximity of sampled data and historical fault data clusters is calculated. Based on the result, the equipment condition is sorted into healthy, incipient faulty or faulty. For equipment in faulty state, the fault type is identified. For healthy equipment, the health score is calculated based on related weights of fault types. For incipient faulty equipment, the time series similarity analysis method is used to further predict the time span for the equipment changing from current state to fault state. The example analysis verifies the feasibility and effectiveness of the proposed method.
引文
[1]郭创新,何迪,张金江,等.考虑热老化的油浸式变压器比例风险模型[J].电力科学与技术学报,2014,29(2):14-20.GUO Chuangxin,HE Di,ZHANG Jinjiang,et al.Aproportional hazard model for oil-immersed transformer concerning thermal aging[J].Journal of Electric Power Science&Technology,2014,29(2):14-20.
[2]郭学梅.基于ZigBee的变压器在线监测系统设计[J].河南师范大学学报(自然科学版),2010,38(1):167-169.GUO Xuemei.Design of transformer online monitoring system based on Zig Bee[J].Journal of Henan Normal University(Natural Science),2010,38(1):167-169.
[3]宋斌,刘志雄,李恩文,等.DGA中三比值缺码研究初探[J].电力自动化设备,2015,35(12):60-65.SONG Bin,LIU Zhixiong,LI Enwen,et al.Preliminary study of undefined three-ratio code in DGA[J].Electric Power Automation Equipment,2015,35(12):60-65.
[4]汪可,李金忠,张书琦,等.变压器故障诊断用油中溶解气体新特征参量[J].中国电机工程学报,2016,36(23):6570-6578.WANG Ke,LI Jinzhong,ZHANG Shuqi,et al.New features derived from dissolved gas analysis for fault diagnosis of power transformers[J].Proceedings of the CSEE,2016,36(23):6570-6578.
[5]潘超,马成廉,郑玲峰,等.一种结合模糊TOPSIS法和BP神经网络的变压器故障诊断方法[J].电力系统保护与控制,2009,37(9):20-24,29.PAN Chao,MA Chenglian,ZHENG Lingfeng,et al.Anew method based on fuzzy TOPSIS and BP neural network for power transformer fault diagnosis[J].Power System Protection and Control,2009,37(9):20-24,29.
[6]吕守国,崔玉新,冯迎春,等.基于综合分析方法的变压器故障诊断技术与软件开发[J].电力系统保护与控制,2017,45(10):123-128.LüShouguo,CUI Yuxin,FENG Yingchun,et al.Transformer fault diagnosis method based on comprehensive analysis and its software development[J].Power System Protection and Control,2017,45(10):123-128.
[7]曹松彦,杨俊,柯于进.变压器油中含气量超标原因分析及对策[J].热力发电,2018,47(8):138-142.CAO Songyan,YANG Jun,KE Yujin.Cause analysis and countermeasures of excessive gas content in transformer oil[J].Thermal Power Generation,2018,47(8):138-142.
[8]王少芳,蔡金锭.GA-BP混合算法在变压器色谱诊断法中的应用[J].高电压技术,2003,29(7):3-6.WANG Shaofang,CAI Jinding.Application of hybrid algorithm based on GA-BP in transformer diagnosis using GAS chromatographic method[J].High Voltage Engineering,2003,29(7):3-6.
[9]施恂山,马宏忠,张琳,等.PSO改进RBPNN在变压器故障诊断中的应用[J].电力系统保护与控制,2016,44(17):39-44.SHI Xunshan,MA Hongzhong,ZHANG Lin,et al.Application of RBPNN improved by PSO in fault diagnosis of transformers[J].Power System Protection and Control,2016,44(17):39-44.
[10]潘翀,陈伟根,云玉新,等.基于遗传算法进化小波神经网络的电力变压器故障诊断[J].电力系统自动化,2007,31(13):88-92.PAN Chong,CHEN Weigen,YUN Yuxin,et al.Fault diagnosis of power transformers based on genetic algorithm evolving wavelet neural network[J].Automation of Electric Power Systems,2007,31(13):88-92.
[11]石鑫,朱永利,王刘旺,等.基于深度信念网络的电力变压器故障分类建模[J].电力系统保护与控制,2016,44(1):71-76.SHI Xin,ZHU Yongli,WANG Liuwang,et al.Power transformer fault classifying model based on deep belief network[J].Power System Protection and Control,2016,44(1):71-76.
[12]尹玉娟,王媚,张金江,等.一种自主核优化的二值粒子群优化-多核学习支持向量机变压器故障诊断方法[J].电网技术,2012,36(7):249-254.YIN Yujuan,WANG Mei,ZHANG Jinjiang,et al.An autonomic kernel optimization method to diagnose transformer faults by multi-kernel learning support vector classifier based on binary particle swarm optimization[J].Power System Technology,2012,36(7):249-254.
[13]杨洪,古世甫,陶加贵,等.自适应分级多分类支持向量机在变压器故障诊断中的应用[J].高压电器,2010,46(5):49-52.YANG Hong,GU Shifu,TAO Jiagui,et al.Application of adaptive hierarchical multi-class SVM to transformer fault diagnosis[J].High Voltage Apparatus,2010,46(5):49-52.
[14]郭创新,朱承治,张琳,等.应用多分类多核学习支持向量机的变压器故障诊断方法[J].中国电机工程学报,2010,30(13):128-134.GUO Chuangxin,ZHU Chengzhi,ZHANG Lin,et al.Afault diagnosis method for power transformer based on multiclass multiple-kernel learning support vector machine[J].Proceedings of the CSEE,2010,30(13):128-134.
[15]杜正聪,牛高远.基于加权模糊聚类算法的变压器故障诊断方法[J].高压电器,2014,50(4):42-48.DU Zhengcong,NIU Gaoyuan.Transformer fault diagnosis based on weighted fuzzy clustering algorithm[J].High Voltage Apparatus,2014,50(4):42-48.
[16]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.XIONG Hao,SUN Caixin,LIAO Ruijin,et al.Study on kernel-based possibilistic clustering and dissolved gas analysis for fault diagnosis of power transformer[J].Proceedings of the CSEE,2005,25(20):162-166.
[17]刘卫华,廖瑞金,杨丽君.基于点密度加权核模糊聚类的变压器故障诊断方法[J].电力自动化设备,2012,32(6):66-69,79.LIU Weihua,LIAO Ruijin,YANG Lijun.Power transformer fault diagnosis based on dot density weighted fuzzy kernel clustering[J].Electric Power Automation Equipment,2012,32(6):66-69,79.
[18]HE J,LIU L,LI W,et al.Development and research on integrated protection system based on redundant information analysis[J].Protection and Control of Modern Power Systems,2017,2(2):102-110.DOI:10.1186/s41601-017-0043-3.
[19]MENG J,ZHANG W.Volume measure in 2DPCA-based face recognition[J].Pattern Recognition Letters,2007,28(10):1203-1208.
[20]国家电网公司生产技术部.油浸式变压器(电抗器)状态评价导则:Q/GDW 169-2008[S].北京:中国电力出版社,2008.Production and Technology Department of State Grid Corporation of China.Guide for condition evaluation of oil-immersed power transformers(reactors):Q/GDW169-2008[S].Beijing China Electric Power Press,2008.
[21]RISTAD E S,YIANILOS P N.Learning string-edit distance[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,1998,20(5):522-532.
[22]钟锦源,张岩,文福拴,等.基于时间序列相似性匹配的输电系统故障诊断方法[J].电力系统自动化,2015,39(6):60-67.ZHONG Jinyuan,ZHANG Yan,WEN Fushuan,et al.Afault diagnosing method in power transmission systems based on time series similarity matching[J].Automation of Electric Power Systems,2015,39(6):60-67.
[2]郭学梅.基于ZigBee的变压器在线监测系统设计[J].河南师范大学学报(自然科学版),2010,38(1):167-169.GUO Xuemei.Design of transformer online monitoring system based on Zig Bee[J].Journal of Henan Normal University(Natural Science),2010,38(1):167-169.
[3]宋斌,刘志雄,李恩文,等.DGA中三比值缺码研究初探[J].电力自动化设备,2015,35(12):60-65.SONG Bin,LIU Zhixiong,LI Enwen,et al.Preliminary study of undefined three-ratio code in DGA[J].Electric Power Automation Equipment,2015,35(12):60-65.
[4]汪可,李金忠,张书琦,等.变压器故障诊断用油中溶解气体新特征参量[J].中国电机工程学报,2016,36(23):6570-6578.WANG Ke,LI Jinzhong,ZHANG Shuqi,et al.New features derived from dissolved gas analysis for fault diagnosis of power transformers[J].Proceedings of the CSEE,2016,36(23):6570-6578.
[5]潘超,马成廉,郑玲峰,等.一种结合模糊TOPSIS法和BP神经网络的变压器故障诊断方法[J].电力系统保护与控制,2009,37(9):20-24,29.PAN Chao,MA Chenglian,ZHENG Lingfeng,et al.Anew method based on fuzzy TOPSIS and BP neural network for power transformer fault diagnosis[J].Power System Protection and Control,2009,37(9):20-24,29.
[6]吕守国,崔玉新,冯迎春,等.基于综合分析方法的变压器故障诊断技术与软件开发[J].电力系统保护与控制,2017,45(10):123-128.LüShouguo,CUI Yuxin,FENG Yingchun,et al.Transformer fault diagnosis method based on comprehensive analysis and its software development[J].Power System Protection and Control,2017,45(10):123-128.
[7]曹松彦,杨俊,柯于进.变压器油中含气量超标原因分析及对策[J].热力发电,2018,47(8):138-142.CAO Songyan,YANG Jun,KE Yujin.Cause analysis and countermeasures of excessive gas content in transformer oil[J].Thermal Power Generation,2018,47(8):138-142.
[8]王少芳,蔡金锭.GA-BP混合算法在变压器色谱诊断法中的应用[J].高电压技术,2003,29(7):3-6.WANG Shaofang,CAI Jinding.Application of hybrid algorithm based on GA-BP in transformer diagnosis using GAS chromatographic method[J].High Voltage Engineering,2003,29(7):3-6.
[9]施恂山,马宏忠,张琳,等.PSO改进RBPNN在变压器故障诊断中的应用[J].电力系统保护与控制,2016,44(17):39-44.SHI Xunshan,MA Hongzhong,ZHANG Lin,et al.Application of RBPNN improved by PSO in fault diagnosis of transformers[J].Power System Protection and Control,2016,44(17):39-44.
[10]潘翀,陈伟根,云玉新,等.基于遗传算法进化小波神经网络的电力变压器故障诊断[J].电力系统自动化,2007,31(13):88-92.PAN Chong,CHEN Weigen,YUN Yuxin,et al.Fault diagnosis of power transformers based on genetic algorithm evolving wavelet neural network[J].Automation of Electric Power Systems,2007,31(13):88-92.
[11]石鑫,朱永利,王刘旺,等.基于深度信念网络的电力变压器故障分类建模[J].电力系统保护与控制,2016,44(1):71-76.SHI Xin,ZHU Yongli,WANG Liuwang,et al.Power transformer fault classifying model based on deep belief network[J].Power System Protection and Control,2016,44(1):71-76.
[12]尹玉娟,王媚,张金江,等.一种自主核优化的二值粒子群优化-多核学习支持向量机变压器故障诊断方法[J].电网技术,2012,36(7):249-254.YIN Yujuan,WANG Mei,ZHANG Jinjiang,et al.An autonomic kernel optimization method to diagnose transformer faults by multi-kernel learning support vector classifier based on binary particle swarm optimization[J].Power System Technology,2012,36(7):249-254.
[13]杨洪,古世甫,陶加贵,等.自适应分级多分类支持向量机在变压器故障诊断中的应用[J].高压电器,2010,46(5):49-52.YANG Hong,GU Shifu,TAO Jiagui,et al.Application of adaptive hierarchical multi-class SVM to transformer fault diagnosis[J].High Voltage Apparatus,2010,46(5):49-52.
[14]郭创新,朱承治,张琳,等.应用多分类多核学习支持向量机的变压器故障诊断方法[J].中国电机工程学报,2010,30(13):128-134.GUO Chuangxin,ZHU Chengzhi,ZHANG Lin,et al.Afault diagnosis method for power transformer based on multiclass multiple-kernel learning support vector machine[J].Proceedings of the CSEE,2010,30(13):128-134.
[15]杜正聪,牛高远.基于加权模糊聚类算法的变压器故障诊断方法[J].高压电器,2014,50(4):42-48.DU Zhengcong,NIU Gaoyuan.Transformer fault diagnosis based on weighted fuzzy clustering algorithm[J].High Voltage Apparatus,2014,50(4):42-48.
[16]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.XIONG Hao,SUN Caixin,LIAO Ruijin,et al.Study on kernel-based possibilistic clustering and dissolved gas analysis for fault diagnosis of power transformer[J].Proceedings of the CSEE,2005,25(20):162-166.
[17]刘卫华,廖瑞金,杨丽君.基于点密度加权核模糊聚类的变压器故障诊断方法[J].电力自动化设备,2012,32(6):66-69,79.LIU Weihua,LIAO Ruijin,YANG Lijun.Power transformer fault diagnosis based on dot density weighted fuzzy kernel clustering[J].Electric Power Automation Equipment,2012,32(6):66-69,79.
[18]HE J,LIU L,LI W,et al.Development and research on integrated protection system based on redundant information analysis[J].Protection and Control of Modern Power Systems,2017,2(2):102-110.DOI:10.1186/s41601-017-0043-3.
[19]MENG J,ZHANG W.Volume measure in 2DPCA-based face recognition[J].Pattern Recognition Letters,2007,28(10):1203-1208.
[20]国家电网公司生产技术部.油浸式变压器(电抗器)状态评价导则:Q/GDW 169-2008[S].北京:中国电力出版社,2008.Production and Technology Department of State Grid Corporation of China.Guide for condition evaluation of oil-immersed power transformers(reactors):Q/GDW169-2008[S].Beijing China Electric Power Press,2008.
[21]RISTAD E S,YIANILOS P N.Learning string-edit distance[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,1998,20(5):522-532.
[22]钟锦源,张岩,文福拴,等.基于时间序列相似性匹配的输电系统故障诊断方法[J].电力系统自动化,2015,39(6):60-67.ZHONG Jinyuan,ZHANG Yan,WEN Fushuan,et al.Afault diagnosing method in power transmission systems based on time series similarity matching[J].Automation of Electric Power Systems,2015,39(6):60-67.