基于AdaBoost-RBF算法与DSmT的变压器故障诊断技术
|
摘要
针对目前浅层机器学习理论在变压器故障诊断上精度不高以及大多数诊断方法参考的信息特征量单一的现状,提出一种基于AdaBoost-RBF算法与Dezert-Smarandache理论(DSmT)的变压器故障诊断方法。选择反映变压器故障信息的油中溶解气体、试验及产气率数据构成诊断参量空间,利用AdaBoost算法改进RBF神经网络算法,应用AdaBoost-RBF算法搭建并行的训练单元构造变压器故障诊断识别框架的基本信度赋值(BBA)。基于多源信息融合的思想,应用DSmT对基本信度赋值进行融合得到最终诊断结论,该理论克服了D-S证据理论无法融合高冲突性证据的局限性。对110 kV变压器进行仿真实例分析,结果表明所提方法具有良好的实用性。
Aiming at the low accuracy of shallow machine learning theory in transformer fault diagnosis and the fact that most diagnostic methods only refer to a single information feature,a transformer fault diagnosis method based on AdaBoost-RBF algorithm and DSmT(Dezert-Smarandache Theory) is proposed. The dissolved gas in oil,test and gas production rate data,which can reflect the transformer fault information,are used to form the diagnostic parameter space. AdaBoost algorithm is applied to improve the RBF neural network algorithm. A parallel training unit is cons-tructed with AdaBoost-RBF algorithm to construct the BBA(Basic Belief Assignment) for the transformer fault recognition framework. Based on the idea of multi-source information fusion,the final diagnosis conclusion can be achieved by applying DSmT to fuse the BBA,which overcomes the limitations of D-S evidence theory that it is unable to solve the fusion problem of high conflict evidences. The case study of 110 kV transformer is carried out,the result shows that the proposed method has good practicability.
Aiming at the low accuracy of shallow machine learning theory in transformer fault diagnosis and the fact that most diagnostic methods only refer to a single information feature,a transformer fault diagnosis method based on AdaBoost-RBF algorithm and DSmT(Dezert-Smarandache Theory) is proposed. The dissolved gas in oil,test and gas production rate data,which can reflect the transformer fault information,are used to form the diagnostic parameter space. AdaBoost algorithm is applied to improve the RBF neural network algorithm. A parallel training unit is cons-tructed with AdaBoost-RBF algorithm to construct the BBA(Basic Belief Assignment) for the transformer fault recognition framework. Based on the idea of multi-source information fusion,the final diagnosis conclusion can be achieved by applying DSmT to fuse the BBA,which overcomes the limitations of D-S evidence theory that it is unable to solve the fusion problem of high conflict evidences. The case study of 110 kV transformer is carried out,the result shows that the proposed method has good practicability.
引文
[1] 谷凯凯,郭江.紧致融合模糊集和故障树的变压器故障诊断[J].高电压技术,2014,40(5):1507-1513.GU Kaikai,GUO Jiang.Transformer fault diagnosis method based on compact fusion of fuzzy set and fault tree[J].High Voltage Engineering,2014,40(5):1507-1513.
[2] 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:GB/T 7252—2001[S].北京:国家标准局,2001.
[3] 国家能源局.变压器油中溶解气体分析和判断导则:DL/T 722—2014[S].北京:中国电力出版社,2014.
[4] 程加堂,艾莉,段志梅.改进证据理论与神经网络集成的变压器故障诊断[J].电力系统保护与控制,2013,41(14):92-96.CHENG Jiatang,AI Li,DUAN Zhimei.Transformer fault diagnosis based on improved evidence theory and neural network integrated method[J].Power System Protection and Control,2013,41(14):92-96.
[5] 司马莉萍,舒乃秋,李自品,等.基于SVM和D-S证据理论的电力变压器内部故障部位识别[J].电力自动化设备,2012,32(11):72-77.SIMA Liping,SHU Naiqiu,LI Zipin,et al.Identification of interior fault position based on SVM and D-S evidence theory for electric transformer[J].Electric Power Automation Equipment,2012,32(11):72-77.
[6] 张重远,林志锋,刘栋,等.基于正态云模型与改进贝叶斯分类器的变压器故障诊断[J].电测与仪表,2017,54(4):50-56.ZHANG Zhongyuan,LIN Zhifeng,LIU Dong,et al.Transformer fault diagnosis based on normal cloud model and improved Bayesian classifier[J].Electrical Measurement & Instrumentation,2017,54(4):50-56.
[7] 王永强,律方成,李和明.基于粗糙集理论和贝叶斯网络的电力变压器故障诊断方法[J].中国电机工程学报,2006,26(8):137-141.WANG Yongqiang,Lü Fangcheng,LI Heming.Synthetic fault diagnosis method of power transformer based on rough set theory and Bayesian network[J].Proceedings of the CSEE,2006,26(8):137-141.
[8] 钱国超,邹德旭,颜冰,等.集成证据推理与多神经网络的电力变压器故障综合诊断[J].高压电器,2015,51(9):71-76.QIAN Guochao,ZOU Dexu,YAN Bing,et al.Synthetic fault diagnosis for power transformers based on integration of evidence reasoning and neural network[J].High Voltage Apparatus,2015,51(9):71-76.
[9] 姜有泉,黄良,王波,等.基于DGA和深度置信网络的变压器内部故障诊断[J].武汉大学学报(工学版),2017,50(5):749-753.JIANG Youquan,HUANG Liang,WANG Bo,et al.Transformer internal fault diagnosis based on DGA and deep belief network[J].Journal of Wuhan University(Engineering Science),2017,50(5):749-753.
[10] 陈伟根,刘娟,曹敏.基于信息融合的变压器内部故障诊断方法[J].高电压技术,2015,41(11):3797-3803.CHEN Weigen,LIU Juan,CAO Min.Diagnosis method of internal fault for transformers based on information fusion[J].High Voltage Engineering,2015,41(11):3797-3803.
[11] 李新德,潘锦东,DEZERT Jean.一种基于DSmT和HMM的序列飞机目标识别算法[J].自动化学报,2014,40(12):2862-2876.LI Xinde,PAN Jindong,DEZERT Jean.A target recognition algorithm for sequential aircraft based on DSmT and HMM[J].Acta Automatica Sinica,2014,40(12):2862-2876.
[12] 李新德,杨伟东,DEZERT Jean.一种飞机图像目标多特征信息融合识别方法[J].自动化学报,2012,38(8):1298 -1307.LI Xinde,YANG Weidong,DEZERT Jean.An airplane image target’s multi-feature fusion recognition method[J].Acta Automatica Sinica,2012,38(8):1298-1307.
[13] 翟旭升,胡金海,谢寿生,等.基于DSmT的航空发动机早期振动故障融合诊断方法[J].航空动力学报,2012,27(2):301-306.ZHAI Xusheng,HU Jinhai,XIE Shousheng,et al.Diagnosis of aero-engine with early vibration fault symptom using DSmT[J].Journal of Aerospace Power,2012,27(2):301-306.
[14] 周湶,王时征,廖瑞金,等.基于AdaBoost优化云理论的变压器故障诊断方法[J].高电压技术,2015,41(11):3804 -3811.ZHOU Yu,WANG Shizheng,LIAO Ruijin,et al.Power transformer fault diagnosis method based on cloud model of AdaBoost algorithm[J].High Voltage Engineering,2015,41(11):3804-3811.
[15] 吴俊利,张步涵,王魁.基于AdaBoost的BP神经网络改进算法在短期风速预测中的应用[J].电网技术,2012,36(9):221-225.WU Junli,ZHANG Buhan,WANG Kui.Application of AdaBoost-based BP neural network for short-term wind speed forecast[J].Power System Technology,2012,36(9):221-225.
[16] 王文豪,严云洋.基于AdaBoost RBF神经网络的火灾烟雾检测[J].河南理工大学学报(自然科学版),2014,33(2):132-138.WANG Wenhao,YAN Yunyang.Fire smoke detection based on Ada-Boost and RBF neural network[J].Journal of Henan Polytechnic University(Natural Science),2014,33(2):132-138.
[17] 刘景艳,王福忠,杨占山.基于RBF神经网络和自适应遗传算法的变压器故障诊断[J].武汉大学学报(工学版),2016,49(1):88-93.LIU Jingyan,WANG Fuzhong,YANG Zhanshan.Transformer fault diagnosis based on RBF neural network and adaptive genetic algorithm[J].Journal of Wuhan University(Engineering Science),2016,49(1):88-93.
[18] FREUND Y,SCHAPIRE R E.Game theory,on-line prediction and boosting[C]//Proceedings of the Ninth Annual Conference on Computational Learning Theory.Desenzano del Garda,Italy:[s.n.],1996:325-332.
[19] 娄生超.基于RBF核函数的集成分类AdaBoost算法研究[J].科学技术与工程,2012,12(34):9207-9210.LOU Shengchao.Research on AdaBoost integrated classification algorithm based on RBF kernel function[J].Science Technology and Engineering,2012,12(34):9207-9210.
[20] 文成林,徐晓斌.多源不确定信息融合理论及应用[M].北京:科学出版社,2012:128-130.
[21] SMARANDACHE F,DEZERT J.Advances and applications of DSmT for information fusion[M].Rehoboth,USA:American Research Press,2004:2-4.
[22] 李刚,于长海,范辉,等.基于多级决策融合模型的电力变压器故障深度诊断方法[J].电力自动化设备,2017,37(11):138-144.LI Gang,YU Changhai,FAN Hui,et al.Deep fault diagnosis of power transformer based on multilevel decision fusion model[J].Electric Power Automation Equipment,2017,37(11):138-144.
[23] 谢红玲,律方成.基于信息融合的变压器状态评估方法研究[J].华北电力大学学报,2006(2):8-11.XIE Hongling,Lü Fangcheng.Transformer condition evaluation based on information fusion[J].Journal of North China Electric Power University,2006(2):8-11.
[24] 陈法法,汤宝平,姚金宝.基于DSmT与小波网络的齿轮箱早期故障融合诊断[J].振动与冲击,2013,32(9):40-45.CHEN Fafa,TANG Baoping,YAO Jinbao.Gearbox incipient fault fusion diagnosis based on DSmT and wavelet neural network[J].Journal of Vibration and Shock,2013,32(9):40-45.
[2] 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:GB/T 7252—2001[S].北京:国家标准局,2001.
[3] 国家能源局.变压器油中溶解气体分析和判断导则:DL/T 722—2014[S].北京:中国电力出版社,2014.
[4] 程加堂,艾莉,段志梅.改进证据理论与神经网络集成的变压器故障诊断[J].电力系统保护与控制,2013,41(14):92-96.CHENG Jiatang,AI Li,DUAN Zhimei.Transformer fault diagnosis based on improved evidence theory and neural network integrated method[J].Power System Protection and Control,2013,41(14):92-96.
[5] 司马莉萍,舒乃秋,李自品,等.基于SVM和D-S证据理论的电力变压器内部故障部位识别[J].电力自动化设备,2012,32(11):72-77.SIMA Liping,SHU Naiqiu,LI Zipin,et al.Identification of interior fault position based on SVM and D-S evidence theory for electric transformer[J].Electric Power Automation Equipment,2012,32(11):72-77.
[6] 张重远,林志锋,刘栋,等.基于正态云模型与改进贝叶斯分类器的变压器故障诊断[J].电测与仪表,2017,54(4):50-56.ZHANG Zhongyuan,LIN Zhifeng,LIU Dong,et al.Transformer fault diagnosis based on normal cloud model and improved Bayesian classifier[J].Electrical Measurement & Instrumentation,2017,54(4):50-56.
[7] 王永强,律方成,李和明.基于粗糙集理论和贝叶斯网络的电力变压器故障诊断方法[J].中国电机工程学报,2006,26(8):137-141.WANG Yongqiang,Lü Fangcheng,LI Heming.Synthetic fault diagnosis method of power transformer based on rough set theory and Bayesian network[J].Proceedings of the CSEE,2006,26(8):137-141.
[8] 钱国超,邹德旭,颜冰,等.集成证据推理与多神经网络的电力变压器故障综合诊断[J].高压电器,2015,51(9):71-76.QIAN Guochao,ZOU Dexu,YAN Bing,et al.Synthetic fault diagnosis for power transformers based on integration of evidence reasoning and neural network[J].High Voltage Apparatus,2015,51(9):71-76.
[9] 姜有泉,黄良,王波,等.基于DGA和深度置信网络的变压器内部故障诊断[J].武汉大学学报(工学版),2017,50(5):749-753.JIANG Youquan,HUANG Liang,WANG Bo,et al.Transformer internal fault diagnosis based on DGA and deep belief network[J].Journal of Wuhan University(Engineering Science),2017,50(5):749-753.
[10] 陈伟根,刘娟,曹敏.基于信息融合的变压器内部故障诊断方法[J].高电压技术,2015,41(11):3797-3803.CHEN Weigen,LIU Juan,CAO Min.Diagnosis method of internal fault for transformers based on information fusion[J].High Voltage Engineering,2015,41(11):3797-3803.
[11] 李新德,潘锦东,DEZERT Jean.一种基于DSmT和HMM的序列飞机目标识别算法[J].自动化学报,2014,40(12):2862-2876.LI Xinde,PAN Jindong,DEZERT Jean.A target recognition algorithm for sequential aircraft based on DSmT and HMM[J].Acta Automatica Sinica,2014,40(12):2862-2876.
[12] 李新德,杨伟东,DEZERT Jean.一种飞机图像目标多特征信息融合识别方法[J].自动化学报,2012,38(8):1298 -1307.LI Xinde,YANG Weidong,DEZERT Jean.An airplane image target’s multi-feature fusion recognition method[J].Acta Automatica Sinica,2012,38(8):1298-1307.
[13] 翟旭升,胡金海,谢寿生,等.基于DSmT的航空发动机早期振动故障融合诊断方法[J].航空动力学报,2012,27(2):301-306.ZHAI Xusheng,HU Jinhai,XIE Shousheng,et al.Diagnosis of aero-engine with early vibration fault symptom using DSmT[J].Journal of Aerospace Power,2012,27(2):301-306.
[14] 周湶,王时征,廖瑞金,等.基于AdaBoost优化云理论的变压器故障诊断方法[J].高电压技术,2015,41(11):3804 -3811.ZHOU Yu,WANG Shizheng,LIAO Ruijin,et al.Power transformer fault diagnosis method based on cloud model of AdaBoost algorithm[J].High Voltage Engineering,2015,41(11):3804-3811.
[15] 吴俊利,张步涵,王魁.基于AdaBoost的BP神经网络改进算法在短期风速预测中的应用[J].电网技术,2012,36(9):221-225.WU Junli,ZHANG Buhan,WANG Kui.Application of AdaBoost-based BP neural network for short-term wind speed forecast[J].Power System Technology,2012,36(9):221-225.
[16] 王文豪,严云洋.基于AdaBoost RBF神经网络的火灾烟雾检测[J].河南理工大学学报(自然科学版),2014,33(2):132-138.WANG Wenhao,YAN Yunyang.Fire smoke detection based on Ada-Boost and RBF neural network[J].Journal of Henan Polytechnic University(Natural Science),2014,33(2):132-138.
[17] 刘景艳,王福忠,杨占山.基于RBF神经网络和自适应遗传算法的变压器故障诊断[J].武汉大学学报(工学版),2016,49(1):88-93.LIU Jingyan,WANG Fuzhong,YANG Zhanshan.Transformer fault diagnosis based on RBF neural network and adaptive genetic algorithm[J].Journal of Wuhan University(Engineering Science),2016,49(1):88-93.
[18] FREUND Y,SCHAPIRE R E.Game theory,on-line prediction and boosting[C]//Proceedings of the Ninth Annual Conference on Computational Learning Theory.Desenzano del Garda,Italy:[s.n.],1996:325-332.
[19] 娄生超.基于RBF核函数的集成分类AdaBoost算法研究[J].科学技术与工程,2012,12(34):9207-9210.LOU Shengchao.Research on AdaBoost integrated classification algorithm based on RBF kernel function[J].Science Technology and Engineering,2012,12(34):9207-9210.
[20] 文成林,徐晓斌.多源不确定信息融合理论及应用[M].北京:科学出版社,2012:128-130.
[21] SMARANDACHE F,DEZERT J.Advances and applications of DSmT for information fusion[M].Rehoboth,USA:American Research Press,2004:2-4.
[22] 李刚,于长海,范辉,等.基于多级决策融合模型的电力变压器故障深度诊断方法[J].电力自动化设备,2017,37(11):138-144.LI Gang,YU Changhai,FAN Hui,et al.Deep fault diagnosis of power transformer based on multilevel decision fusion model[J].Electric Power Automation Equipment,2017,37(11):138-144.
[23] 谢红玲,律方成.基于信息融合的变压器状态评估方法研究[J].华北电力大学学报,2006(2):8-11.XIE Hongling,Lü Fangcheng.Transformer condition evaluation based on information fusion[J].Journal of North China Electric Power University,2006(2):8-11.
[24] 陈法法,汤宝平,姚金宝.基于DSmT与小波网络的齿轮箱早期故障融合诊断[J].振动与冲击,2013,32(9):40-45.CHEN Fafa,TANG Baoping,YAO Jinbao.Gearbox incipient fault fusion diagnosis based on DSmT and wavelet neural network[J].Journal of Vibration and Shock,2013,32(9):40-45.