PSO-IGWO优化混合KELM的变压器故障诊断方法
|
摘要
对变压器进行智能化故障诊断是促进智能电网发展的主要环节,但传统的单一智能诊断算法不能对变压器的大量不完备信息进行有效处理,导致故障诊断精度不高。为此,给出一种基于粒子群混合改进灰狼算法(PSO-IGWO)优化混合核极限学习机(KELM,kernal extreme learning machine)的变压器故障诊断方法。通过混合KELM建立故障诊断模型,采用粒子群算法对混合KELM的结构参数进行寻优,利用改进灰狼算法在局部和全局之间良好的平衡能力改善粒子群算法的缺陷,结合油中溶解气体分析(DGA,dissolved gas analysis)样本数据进行仿真实验。结果表明,相对于BPNN,ELM算法,诊断准确率分别提高了16.24%,5.71%,能够为变压器的安全稳定运行提供决策支持。
Intelligent fault diagnosis of transformer is the main link to promote the development of the smart grid. However, the traditional single intelligent diagnosis algorithm can not deal with a large amount of incomplete information of transformer, resulting in low accuracy of fault diagnosis. Therefore, a transformer fault diagnosis method based on improved gray wolf optimization algorithm(PSO-IGWO) with optimized hybrid kernel extreme learning machine(KELM) was proposed. The fault diagnosis model was established by the hybrid KELM, and the structural parameters of hybrid KELM were optimized by particle swarm optimization algorithm. The simulated experiment was made, combined with the dissolved gas analysis(DGA) sample data. The results show that compared with BPNN and ELM, the diagnostic accuracy of this algorithm is improved by 16.24% and 5.71% respectively, which can provide decision support for the safe and stable operation of transformers.
Intelligent fault diagnosis of transformer is the main link to promote the development of the smart grid. However, the traditional single intelligent diagnosis algorithm can not deal with a large amount of incomplete information of transformer, resulting in low accuracy of fault diagnosis. Therefore, a transformer fault diagnosis method based on improved gray wolf optimization algorithm(PSO-IGWO) with optimized hybrid kernel extreme learning machine(KELM) was proposed. The fault diagnosis model was established by the hybrid KELM, and the structural parameters of hybrid KELM were optimized by particle swarm optimization algorithm. The simulated experiment was made, combined with the dissolved gas analysis(DGA) sample data. The results show that compared with BPNN and ELM, the diagnostic accuracy of this algorithm is improved by 16.24% and 5.71% respectively, which can provide decision support for the safe and stable operation of transformers.
引文
[1] 黄新波,李文君子,宋桐,等.采用遗传算法优化装袋分类回归树组合算法的变压器故障诊断[J].高电压技术,2016,42(5):1617-1623.HUANG X B,LI W J Z,SONG T,et al.Application of bagging-CART algorithm optimized by genetic algorithm in transformer fault diagnosis[J].High Voltage Engineering,2016,42(5):1617-1623.(in Chinese)
[2] 魏雪倩,黄新波,李文君子,等.基于AdaBoost多分类算法变压器故障诊断[J].西安工程大学学报,2016,30(2):207-211.WEI X Q,HUANG X B,LI W J Z,et al.Fault diagnosis of transformer based on multi-classification algorithm AdaBoost[J].Journal of X'an Polytechnic University,2016,30(2):207-211.(in Chinese)
[3] HUANG X B,LI H B,ZHU Y C.Short-term ice accretion forecasting model for transmission lines with modified time-series analysis by fireworks algorithm[J].IET Generation Transmission & Distribution,2018,12(5):1074-1080.
[4] 陈欢,彭辉,舒乃秋,等.基于鲁棒能量模型LS-TSVM和DGA的变压器故障诊断[J].电力系统保护与控制,2017,45(21):134-139.CHEN H,PENG H,SHU N Q,et al.Fault diagnosis of power transformer based on RELS-TSVM and DGA[J].Power System Protection and Control,2017,45(21):134-139.(in Chinese)
[5] 赵旭彤,沈倩,许家响,等.基于IEC三比值法与融合权重法的变压器可拓关联故障诊断[J].电网与清洁能源,2013,29(8):18-22.ZHAO X T,SHEN Q,XU J X,et al.Fault diagnosis for power transformer based on IEC three-ratio and extension association with combined weights[J].Advances of Power System & Hydroelectric Engineering,2013,29(8):18-22.(in Chinese)
[6] AI-JANABI S,RAWAT S,PATEL A,et al.Design and evaluation of a hybrid system for detection and prediction of faults in electrical transformers[J].International Journal of Electrical Power & Energy Systems,2015,67:324-335.
[7] 王娅娜,黄新波,宋桐,等.基于改进粒子群算法的模糊神经网络变压器油色谱监测故障诊断策略[J].广东电力,2013,26(5):82-86.WANG Y N,HUANG X B,SONG T,et al.Fault diagnosis strategy for transformer oil chromatography monitoring of fuzzy neural network based on improved PSO[J].Guangdong Electric Power,2013,26(5):82-86.(in Chinese)
[8] 苗长新,申坤,钟世华,等.基于优化神经网络和DGA的变压器故障诊断[J].高压电器,2016,52(11):163-168.MIAO C X,SHEN K,ZHONG S H,et al.Power transformer fault diagnosis based on improved neutral network and DGA[J].High Voltage Apparatus,2016,52(11):163-168.(in Chinese)
[9] 谢荣斌,张霖,鄢小虎,等.模拟退火优化SVM参数的变压器故障诊断[J].计算机测量与控制,2015,23(5):1495-1498.XIE R B,ZHANG L,YAN X H,et al.Optimized parameters by simulated annealing of SVM in power transformer diagnosis[J].Computer Measurement & Control,2015,23(5):1495-1498.(in Chinese)
[10] BENMAHAMED Y,TEGUAR M,BOUBAKEUR A.Application of SVM and KNN to Duval Pentagon 1 for transformer oil diagnosis[J].IEEE Transactions on Dielectrics & Electrical Insulation,2018,24(6):3443-3451.
[11] HUANG G B.An insight into extreme learning machines:Random neurons,random features and kernels[J].Cognitive Computation,2014,6(3):376-390.
[12] CHENG C,TAY W P,HUANG G B.Extreme learning machines for intrusion detection[C]//International Joint Conference on Neural Networks.IEEE,2012:1-8.
[13] 刘晓乐,刘艳.基于极限学习机的变压器故障快速识别[J].微型机与应用,2015,34(2):52-54.LIU X L,LIU Y.Power transformer fault fast recognition based on extreme learning machine[J].Microcomputer & its Applications,2015,34(2):52-54.(in Chinese)
[14] 袁海满,吴广宁,高波.基于DGA的粒子群极限学习机电力变压器故障诊断[J].高压电器,2016,52(11):176-180.YUAN H M,WU G N,GAO B.Fault diagnosis of power transformer using particle swarm optimization and extreme learning machine based on DGA[J].High Voltage Apparatus,2016,52(11):176-180.(in Chinese)
[15] 裴飞,陈雪振,朱永利,等.粒子群优化核极限学习机的变压器故障诊断[J].计算机工程与设计,2015,36(5):1327-1331.PEI F,CHEN X Z,ZHU Y L,et al.Transformer fault diagnosis based on particle swarm optimization and kernel-based extreme learning machine[J].Computer Engineering and Design,2015,36(5):1327-1331.(in Chinese)
[16] MIRJALILI S,MIRJALILI S M,LEWIS A.Grey wolf optimizer[J].Advances in Engineering Software,2014,69(3):46-61.
[17] 滕志军,吕金玲,郭力文,等.一种基于Tent映射的混合灰狼优化的改进算法[J].哈尔滨工业大学学报,2018,50(11):40-49.TENG Z J,LYU J L,GUO L W,et al.An improved hybrid grey wolf optimization algorithm based on Tent mapping[J].Journal of Harbin Institute of Technology,2018,50(11):40-49.(in Chinese)
[18] TURABIEH H.A hybrid ANN-GWO algorithm for prediction of heart disease[J].American Journal of Operations Research,2016,6(2):136-146.
[19] 郭振洲,刘然,拱长青,等.基于灰狼算法的改进研究[J].计算机应用研究,2017,34(12):3603-3606.GUO Z Z,LIU R,GONG C Q,et al.Study on improvement of gray wolf algorithm[J].Application Research of Computers,2017,34(12):3603-3606.(in Chinese)
[20] KAMBOJ V K.A novel hybrid PSO-GWO approach for unit commitment problem[J].Neural Computing and Applications,2016,27(6):1643-1655.
[21] 尹金良.基于相关向量机的油浸式电力变压器故障诊断方法研究[D].保定:华北电力大学,2013:109-131.YIN J L.Study on oil-immersed power transformer fault diagnosis based on relevance vector machine[D].Baoding:North China Electric Power University,2013:109-131.(in Chinese)
[2] 魏雪倩,黄新波,李文君子,等.基于AdaBoost多分类算法变压器故障诊断[J].西安工程大学学报,2016,30(2):207-211.WEI X Q,HUANG X B,LI W J Z,et al.Fault diagnosis of transformer based on multi-classification algorithm AdaBoost[J].Journal of X'an Polytechnic University,2016,30(2):207-211.(in Chinese)
[3] HUANG X B,LI H B,ZHU Y C.Short-term ice accretion forecasting model for transmission lines with modified time-series analysis by fireworks algorithm[J].IET Generation Transmission & Distribution,2018,12(5):1074-1080.
[4] 陈欢,彭辉,舒乃秋,等.基于鲁棒能量模型LS-TSVM和DGA的变压器故障诊断[J].电力系统保护与控制,2017,45(21):134-139.CHEN H,PENG H,SHU N Q,et al.Fault diagnosis of power transformer based on RELS-TSVM and DGA[J].Power System Protection and Control,2017,45(21):134-139.(in Chinese)
[5] 赵旭彤,沈倩,许家响,等.基于IEC三比值法与融合权重法的变压器可拓关联故障诊断[J].电网与清洁能源,2013,29(8):18-22.ZHAO X T,SHEN Q,XU J X,et al.Fault diagnosis for power transformer based on IEC three-ratio and extension association with combined weights[J].Advances of Power System & Hydroelectric Engineering,2013,29(8):18-22.(in Chinese)
[6] AI-JANABI S,RAWAT S,PATEL A,et al.Design and evaluation of a hybrid system for detection and prediction of faults in electrical transformers[J].International Journal of Electrical Power & Energy Systems,2015,67:324-335.
[7] 王娅娜,黄新波,宋桐,等.基于改进粒子群算法的模糊神经网络变压器油色谱监测故障诊断策略[J].广东电力,2013,26(5):82-86.WANG Y N,HUANG X B,SONG T,et al.Fault diagnosis strategy for transformer oil chromatography monitoring of fuzzy neural network based on improved PSO[J].Guangdong Electric Power,2013,26(5):82-86.(in Chinese)
[8] 苗长新,申坤,钟世华,等.基于优化神经网络和DGA的变压器故障诊断[J].高压电器,2016,52(11):163-168.MIAO C X,SHEN K,ZHONG S H,et al.Power transformer fault diagnosis based on improved neutral network and DGA[J].High Voltage Apparatus,2016,52(11):163-168.(in Chinese)
[9] 谢荣斌,张霖,鄢小虎,等.模拟退火优化SVM参数的变压器故障诊断[J].计算机测量与控制,2015,23(5):1495-1498.XIE R B,ZHANG L,YAN X H,et al.Optimized parameters by simulated annealing of SVM in power transformer diagnosis[J].Computer Measurement & Control,2015,23(5):1495-1498.(in Chinese)
[10] BENMAHAMED Y,TEGUAR M,BOUBAKEUR A.Application of SVM and KNN to Duval Pentagon 1 for transformer oil diagnosis[J].IEEE Transactions on Dielectrics & Electrical Insulation,2018,24(6):3443-3451.
[11] HUANG G B.An insight into extreme learning machines:Random neurons,random features and kernels[J].Cognitive Computation,2014,6(3):376-390.
[12] CHENG C,TAY W P,HUANG G B.Extreme learning machines for intrusion detection[C]//International Joint Conference on Neural Networks.IEEE,2012:1-8.
[13] 刘晓乐,刘艳.基于极限学习机的变压器故障快速识别[J].微型机与应用,2015,34(2):52-54.LIU X L,LIU Y.Power transformer fault fast recognition based on extreme learning machine[J].Microcomputer & its Applications,2015,34(2):52-54.(in Chinese)
[14] 袁海满,吴广宁,高波.基于DGA的粒子群极限学习机电力变压器故障诊断[J].高压电器,2016,52(11):176-180.YUAN H M,WU G N,GAO B.Fault diagnosis of power transformer using particle swarm optimization and extreme learning machine based on DGA[J].High Voltage Apparatus,2016,52(11):176-180.(in Chinese)
[15] 裴飞,陈雪振,朱永利,等.粒子群优化核极限学习机的变压器故障诊断[J].计算机工程与设计,2015,36(5):1327-1331.PEI F,CHEN X Z,ZHU Y L,et al.Transformer fault diagnosis based on particle swarm optimization and kernel-based extreme learning machine[J].Computer Engineering and Design,2015,36(5):1327-1331.(in Chinese)
[16] MIRJALILI S,MIRJALILI S M,LEWIS A.Grey wolf optimizer[J].Advances in Engineering Software,2014,69(3):46-61.
[17] 滕志军,吕金玲,郭力文,等.一种基于Tent映射的混合灰狼优化的改进算法[J].哈尔滨工业大学学报,2018,50(11):40-49.TENG Z J,LYU J L,GUO L W,et al.An improved hybrid grey wolf optimization algorithm based on Tent mapping[J].Journal of Harbin Institute of Technology,2018,50(11):40-49.(in Chinese)
[18] TURABIEH H.A hybrid ANN-GWO algorithm for prediction of heart disease[J].American Journal of Operations Research,2016,6(2):136-146.
[19] 郭振洲,刘然,拱长青,等.基于灰狼算法的改进研究[J].计算机应用研究,2017,34(12):3603-3606.GUO Z Z,LIU R,GONG C Q,et al.Study on improvement of gray wolf algorithm[J].Application Research of Computers,2017,34(12):3603-3606.(in Chinese)
[20] KAMBOJ V K.A novel hybrid PSO-GWO approach for unit commitment problem[J].Neural Computing and Applications,2016,27(6):1643-1655.
[21] 尹金良.基于相关向量机的油浸式电力变压器故障诊断方法研究[D].保定:华北电力大学,2013:109-131.YIN J L.Study on oil-immersed power transformer fault diagnosis based on relevance vector machine[D].Baoding:North China Electric Power University,2013:109-131.(in Chinese)