基于决策树的劣化瓷质绝缘子的判定阈值选择方法与诊断
|
摘要
通过观察辨识不同电压等级下输电线路中瓷质绝缘子的原始红外图像的特征,提出了一种基于决策树的劣化瓷质绝缘子的识别与判定的方法。在不同湿度温度下,传统的检测阈值变化较大,通过提取原始红外图像的数据,选取绝缘子串中单片绝缘子的钢帽温度、最大温度、钢帽瓷件温度差、绝缘子瓷件环境温度差、单片绝缘子的最大温升百分比及单片绝缘子温度方差这6个变量作为输入参数,以绝缘子绝缘程度的优劣作为输出,利用决策树,选择了最优检测阈值组合,建立了裂化绝缘子的智能检测模型。得出钢帽瓷件温度差及瓷件环境温度差为最优检测阈值组合这一结论,并利用这一阈值组合对红外图片进行了检测,测试结果显示平均正确率达到98.2%。该方法为劣化绝缘子的智能检测提供了新的思路,并通过实际实验证明了其可行性。
By discerning the original infrared pictures of insulator strings under transmission lines of different voltage level, a deteriorated insulator diagnose model based on decision tree is proposed. As the traditional threshold changes a lot under different weather conditions, by utilizing decision tree, this paper selects the premium threshold combination and builds the deteriorated insulator diagnose model, choosing from the six alternative thresholds: the max temperature of single piece of insulator, the temperature of insulators steel-cap, the temperature difference between insulator steel-cap and porcelain, the temperature difference between insulator porcelain and environment,the temperature variance of single piece of insulator and the max temperature rise percentage of single piece of insulator. A conclusion that the temperature difference between insulator steel-cap and porcelain and the temperature difference between insulator porcelain and environment consist the premium threshold combination is obtained. The average accuracy reaches up to 98.2%. This method provides new approach for further research in detecting deteriorated insulator and tests in the laboratory attest the feasibility of the model.
By discerning the original infrared pictures of insulator strings under transmission lines of different voltage level, a deteriorated insulator diagnose model based on decision tree is proposed. As the traditional threshold changes a lot under different weather conditions, by utilizing decision tree, this paper selects the premium threshold combination and builds the deteriorated insulator diagnose model, choosing from the six alternative thresholds: the max temperature of single piece of insulator, the temperature of insulators steel-cap, the temperature difference between insulator steel-cap and porcelain, the temperature difference between insulator porcelain and environment,the temperature variance of single piece of insulator and the max temperature rise percentage of single piece of insulator. A conclusion that the temperature difference between insulator steel-cap and porcelain and the temperature difference between insulator porcelain and environment consist the premium threshold combination is obtained. The average accuracy reaches up to 98.2%. This method provides new approach for further research in detecting deteriorated insulator and tests in the laboratory attest the feasibility of the model.
引文
[1]张重远,闫康,汪佛池,等.基于图像特征提取与BP神经网络的绝缘子憎水性识别方法[J].高电压技术,2014,40(5):1446-1452.ZHANG Zhongyuan, YAN Kang, WANG Fochi.et al. Insulator hydrophobic identification based on image feature extraction and BP neural network[J]. High Voltage Engineering, 2014,40(5):1446-1452.
[2]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.SUN Caixin, BI Weimin,ZHOU Quan, et al. New gray prediction parameter model and its application in electrical insulation fault prediction[J]. Control Theory and Application, 2003,20(5):797-801.
[3]司马文霞,施健,袁涛,等.特高压复合绝缘子电场计算及基于神经网络遗传算法的均压环结构优化设计[J].高电压技术,2012 38(2):257-265.SIMA Wenxia, SHI Jian, YUAN Tao, et al. Electric field calculation of ultra-high voltage composite insulator and optimization design of corona ring structure based on neural network and genetic algorithm[J]. High Voltage Engineering, 2012 38(2):257-265.
[4] LUO Z, YU X, YUAN C. A new approach of constructing decision tree based on shortest path methods[C]//International Conference on Audio, Language and Image Process-ing(ICALIP).[S.l.]:IEEE, 2016:630-634.
[5] WANG Q D, ZHONG Z F, WANG X P. Design and implementation of insulators material hydrophobicity measure system by support vector machine decision tree learning[C]//2005 International Conference on Machine Learning and Cybernetics.[S.l]:IEEE, 2005:4328-4334.
[6] REDDY B S, NAGABHUSHANA G R. Study of temperature distribution along an artificially polluted insulator string[J]. Plasma Science&Technology, 2003, 5(2):1715-1720.
[7]陈永辉,蔡葵,刘勇军,等.供电设备红外诊断技术[M].北京:中国水利水电出版社,2006:69-75.CHEN Yonghui, CAI Kui, LIU Yongjun, et al. Infrared diagnostic technology for power supply equipment[M]. Beijing:China Water Conservancy and Hydroelectricity Publishing House, 2006:69-75.
[8]王康,孙宏斌,张伯明,等.基于二维组合属性决策树的暂态稳定评估[J].中国电机工程学报,2009,29(1):17-24.WANG Kang, SUN Hongbin, ZHANG Boming, et al. Transient stability assessment based on 2D combined attribute decision tree[J]. Proceeding of the CSEE, 2009,29(1):17-24.
[9] QUINLAN J R. Induction of decision trees[J]. Machine Learning, 1986,1(1):81-106.
[10]何洪英,姚建刚,蒋正龙,等.基于支持向量机的高压绝缘子污秽等级红外热像检测[J].电力系统自动化,2005, 29(24):70-74.HE Hongying, YAO Jiangang, JIANG Zhenglong et al.Infrared thermal image detecting of high voltage insulator contamination grades based on support vector machine[J].Automation of Electric Power Systems, 2005, 29(24):70-74.
[11]王英英,罗毅,涂光瑜.基于粗糙集与决策树的配电网故障诊断方法[J].高电压技术,2008,34(4):794-798.WANG Yingying, LUO Yi, TU Guangyu. Fault diagnosis method for distribution networks based on the rough sets and decision tree theory[J]. High Voltage Engineering,2008, 34(4):794-798.
[12]于希宁,牛成林,李建强.基于决策树和专家系统的短期电力负荷预测系统[J].华北电力大学学报,2005,32(5):57-61.YU Xining, NIU Chenglin, LI Jianqiang. Electrical load forecast based on decision tree and expert system[J]. Journal of North China Electric Power University, 2005,32(5):57-61.
[13]金光熙,权光日.故障绝缘子的发热机理及其红外热像检测[J].电瓷避雷器,2011(5):12-15.JIN Guangxi, QUAN Guangri. Heating mechanism and infrared thermography detection of failure insulators[J].Insulators and Surge Arresters, 2011(5):12-15.
[14]李唐兵,陈国锋.一种改进的劣化盘形悬式瓷绝缘子红外热像诊断方法[J].电瓷避雷器,2014(6):8-13.LI Tangbing, CHEN Guofeng. A improved method of detecting deterioration insulator based on infrared thermal im-age[J]. Insulators and Surge Arresters, 2014(6):8-13.
[15]汪佛池,马建桥,律方成,等.污秽和水分对瓷支柱绝缘子发热的影响[J].高电压技术,2015,41(9):3054-3060.WANG Fochi, MA Jianqiao, LYU Fangcheng, et al. Pollution and water molecule effects on porcelain post insulator heating[J]. High Voltage Engineering, 2015, 41(9):3054-3060.
[16]金立军,田治仁,高凯,等.基于红外与可见光图像信息融合的绝缘子污秽等级识别[J].中国电机工程学报,2016,36(13):3682-3691.JIN Linjun, TIAN Zhiren, GAO Kai, et al. Discrimination of insulator contamination grades using information fusion of infrared and visible images[J]. Proceeding of the CSEE,2016, 36(13):3682-3691.
[17]律方成,马建桥,汪佛池,等.基于红外成像的瓷支柱绝缘子发热规律研究[J].电工技术学报,2013, 28(12):130-135.LYU Fangcheng, MA Jianqiao, WANG Fochi, et al. Study of porcelain post insulator heating law based on infrared imaging[J]. Transactions of China Electrotechnical Society,2013, 28(12):130-135.
[18]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.DONG Ming, QU Yanming, ZHOU Mengge, et al. Fault diagnosis of oil-immersed power transformer using combinatorial decision tree[J]. Proceeding of the CSEE, 2005, 25(16):35-41.
[19]顾伟,丁涛,杨自群,等.在线电压安全评估的多重动态决策树方法[J].中国电机工程学报,2011,31(31):142-148.GU Wei,DING Tao, YANG Ziqun,et al. Online voltagesecurity assessmentusing multiple dynamic decision tree[J]. Proceeding of the CSEE, 2011, 31(31):142-148.
[20] CHAUDHARI N, HINGE T, DAMBHARE S. Dynamic security analysis for voltage security using decision trees[C]//Region 10 Conference(TENCON).[S.l.]:IEEE,2016:888-892.
[21] MISHRA A P, GORUR R S, VENKATARAMAN S. Evaluation of porcelain and toughened glass suspension insulators removed from service[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2008, 15(2):467-475.
[22]陈林华,梁曦东.特高压交流瓷绝缘子串电压分布的计算分析[J].高电压技术,2012,38(2):376-381.CHE Linhua, LIANG Xidong. Computational analysis on voltage distribution along ceramic insulator strings of UHV AC transmission line[J]. High Voltage Engineering, 2012,38(2):376-381.
[2]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.SUN Caixin, BI Weimin,ZHOU Quan, et al. New gray prediction parameter model and its application in electrical insulation fault prediction[J]. Control Theory and Application, 2003,20(5):797-801.
[3]司马文霞,施健,袁涛,等.特高压复合绝缘子电场计算及基于神经网络遗传算法的均压环结构优化设计[J].高电压技术,2012 38(2):257-265.SIMA Wenxia, SHI Jian, YUAN Tao, et al. Electric field calculation of ultra-high voltage composite insulator and optimization design of corona ring structure based on neural network and genetic algorithm[J]. High Voltage Engineering, 2012 38(2):257-265.
[4] LUO Z, YU X, YUAN C. A new approach of constructing decision tree based on shortest path methods[C]//International Conference on Audio, Language and Image Process-ing(ICALIP).[S.l.]:IEEE, 2016:630-634.
[5] WANG Q D, ZHONG Z F, WANG X P. Design and implementation of insulators material hydrophobicity measure system by support vector machine decision tree learning[C]//2005 International Conference on Machine Learning and Cybernetics.[S.l]:IEEE, 2005:4328-4334.
[6] REDDY B S, NAGABHUSHANA G R. Study of temperature distribution along an artificially polluted insulator string[J]. Plasma Science&Technology, 2003, 5(2):1715-1720.
[7]陈永辉,蔡葵,刘勇军,等.供电设备红外诊断技术[M].北京:中国水利水电出版社,2006:69-75.CHEN Yonghui, CAI Kui, LIU Yongjun, et al. Infrared diagnostic technology for power supply equipment[M]. Beijing:China Water Conservancy and Hydroelectricity Publishing House, 2006:69-75.
[8]王康,孙宏斌,张伯明,等.基于二维组合属性决策树的暂态稳定评估[J].中国电机工程学报,2009,29(1):17-24.WANG Kang, SUN Hongbin, ZHANG Boming, et al. Transient stability assessment based on 2D combined attribute decision tree[J]. Proceeding of the CSEE, 2009,29(1):17-24.
[9] QUINLAN J R. Induction of decision trees[J]. Machine Learning, 1986,1(1):81-106.
[10]何洪英,姚建刚,蒋正龙,等.基于支持向量机的高压绝缘子污秽等级红外热像检测[J].电力系统自动化,2005, 29(24):70-74.HE Hongying, YAO Jiangang, JIANG Zhenglong et al.Infrared thermal image detecting of high voltage insulator contamination grades based on support vector machine[J].Automation of Electric Power Systems, 2005, 29(24):70-74.
[11]王英英,罗毅,涂光瑜.基于粗糙集与决策树的配电网故障诊断方法[J].高电压技术,2008,34(4):794-798.WANG Yingying, LUO Yi, TU Guangyu. Fault diagnosis method for distribution networks based on the rough sets and decision tree theory[J]. High Voltage Engineering,2008, 34(4):794-798.
[12]于希宁,牛成林,李建强.基于决策树和专家系统的短期电力负荷预测系统[J].华北电力大学学报,2005,32(5):57-61.YU Xining, NIU Chenglin, LI Jianqiang. Electrical load forecast based on decision tree and expert system[J]. Journal of North China Electric Power University, 2005,32(5):57-61.
[13]金光熙,权光日.故障绝缘子的发热机理及其红外热像检测[J].电瓷避雷器,2011(5):12-15.JIN Guangxi, QUAN Guangri. Heating mechanism and infrared thermography detection of failure insulators[J].Insulators and Surge Arresters, 2011(5):12-15.
[14]李唐兵,陈国锋.一种改进的劣化盘形悬式瓷绝缘子红外热像诊断方法[J].电瓷避雷器,2014(6):8-13.LI Tangbing, CHEN Guofeng. A improved method of detecting deterioration insulator based on infrared thermal im-age[J]. Insulators and Surge Arresters, 2014(6):8-13.
[15]汪佛池,马建桥,律方成,等.污秽和水分对瓷支柱绝缘子发热的影响[J].高电压技术,2015,41(9):3054-3060.WANG Fochi, MA Jianqiao, LYU Fangcheng, et al. Pollution and water molecule effects on porcelain post insulator heating[J]. High Voltage Engineering, 2015, 41(9):3054-3060.
[16]金立军,田治仁,高凯,等.基于红外与可见光图像信息融合的绝缘子污秽等级识别[J].中国电机工程学报,2016,36(13):3682-3691.JIN Linjun, TIAN Zhiren, GAO Kai, et al. Discrimination of insulator contamination grades using information fusion of infrared and visible images[J]. Proceeding of the CSEE,2016, 36(13):3682-3691.
[17]律方成,马建桥,汪佛池,等.基于红外成像的瓷支柱绝缘子发热规律研究[J].电工技术学报,2013, 28(12):130-135.LYU Fangcheng, MA Jianqiao, WANG Fochi, et al. Study of porcelain post insulator heating law based on infrared imaging[J]. Transactions of China Electrotechnical Society,2013, 28(12):130-135.
[18]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.DONG Ming, QU Yanming, ZHOU Mengge, et al. Fault diagnosis of oil-immersed power transformer using combinatorial decision tree[J]. Proceeding of the CSEE, 2005, 25(16):35-41.
[19]顾伟,丁涛,杨自群,等.在线电压安全评估的多重动态决策树方法[J].中国电机工程学报,2011,31(31):142-148.GU Wei,DING Tao, YANG Ziqun,et al. Online voltagesecurity assessmentusing multiple dynamic decision tree[J]. Proceeding of the CSEE, 2011, 31(31):142-148.
[20] CHAUDHARI N, HINGE T, DAMBHARE S. Dynamic security analysis for voltage security using decision trees[C]//Region 10 Conference(TENCON).[S.l.]:IEEE,2016:888-892.
[21] MISHRA A P, GORUR R S, VENKATARAMAN S. Evaluation of porcelain and toughened glass suspension insulators removed from service[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2008, 15(2):467-475.
[22]陈林华,梁曦东.特高压交流瓷绝缘子串电压分布的计算分析[J].高电压技术,2012,38(2):376-381.CHE Linhua, LIANG Xidong. Computational analysis on voltage distribution along ceramic insulator strings of UHV AC transmission line[J]. High Voltage Engineering, 2012,38(2):376-381.