基于改进PSO-BP网络的配电网故障选线与测距
|
摘要
针对人工智能算法在解决配电网故障选线和测距问题时容易陷入局部最优解并难以满足精确性和鲁棒性要求的问题,提出了一种基于改进粒子群优化神经网络的配电网故障选线与测距算法.该算法结合混沌优化算法和粒子群优化算法得到收敛能力更强的粒子群优化算法,通过提取配电网的零序电压与电流的暂态及稳态特征来构成特征向量,并分别使用训练集训练改进粒子群优化神经网络算法,从而能更精确地预测配电网的故障线路及其距离.仿真测试结果表明,所提出的算法能获得更精确的选线和测距结果,具有一定的实用性.
In order to solve the problems that during the fault line selection and location for the distribution network,the artificial intelligence algorithms are easily trapped into the local optimal solutions and are difficult to meet the requirements in both accuracy and robustness,a fault line selection and location algorithm for distribution network based on the improved particle swarm optimization( PSO) neural network was proposed. The proposed algorithm combines the chaos optimization and PSO algorithms to obtain a new PSO algorithm with stronger convergence ability. Through extracting the characteristics of both transient and steady states of zero-sequence voltage and current of distribution network,the feature vector was formed,and the PSO neural network algorithm was trained and improved with the training set. Therefore,the fault line and location of distribution network can be predicted more accurately. The results of simulation test show that the proposed algorithm can obtain more accurate line selection and location results,and has certain practicality.
In order to solve the problems that during the fault line selection and location for the distribution network,the artificial intelligence algorithms are easily trapped into the local optimal solutions and are difficult to meet the requirements in both accuracy and robustness,a fault line selection and location algorithm for distribution network based on the improved particle swarm optimization( PSO) neural network was proposed. The proposed algorithm combines the chaos optimization and PSO algorithms to obtain a new PSO algorithm with stronger convergence ability. Through extracting the characteristics of both transient and steady states of zero-sequence voltage and current of distribution network,the feature vector was formed,and the PSO neural network algorithm was trained and improved with the training set. Therefore,the fault line and location of distribution network can be predicted more accurately. The results of simulation test show that the proposed algorithm can obtain more accurate line selection and location results,and has certain practicality.
引文
[1]杨德昌,魏向向,温渤婴,等.基于稀疏分解与综合测度值的配电网故障选线方法[J].高电压技术,2017,43(5):1526-1534.(YANG De-chang,WEI Xiang-xiang,WEN Bo-ying,et al.Fault line selection method of distribution network based on sparse decomposition and synthetic measure[J].High Voltage Technology,2017,43(5):1526-1534.)
[2]王磊,曹现峰,骆玮.基于改进PSO优化模糊神经网络的配电网故障选线研究[J].电气技术,2016,17(3):30-35.(WANG Lei,CAO Xian-feng,LUO Wei.Research on fault line selection of distribution network based on improved PSO optimization fuzzy neural network[J].Electrical Technology,2016,17(3):30-35.)
[3]孟安波,葛佳菲,李德强,等.基于纵横交叉算法的神经网络配电网故障选线研究[J].电力系统保护与控制,2016,44(21):90-95.(MENG An-bo,GE Jia-fei,LI De-qiang,et al.The line selection of neural network based on fault crossing algorithm[J].Power System Protection and Control,2016,44(21):90-95.)
[4]张雷,黄奕宏,翁胜龙.基于GA-DS的多神经网络故障诊断方法[J].电子设计工程,2015,23(10):14-17.(ZHANG Lei,HUANG Yi-hong,WENG Sheng-long.GA-DS based multi neural network fault diagnosis method[J].Electronic Design Engineering,2015,23(10):14-17.)
[5]龚水清,王崴.基于虚拟仪器和BP神经网络液压系统故障诊断[J].电子科技,2011,24(9):128-132.(GONG Shui-qing,WANG Wei.Hydraulic system fault diagnosis based on virtual instrument and BPneural network[J].Electronic Science and Technology,2011,24(9):128-132.)
[6]何晓,雷勇,周聪聪,等.消除零模波速影响的配电网单端行波故障测距算法[J].电力系统保护与控制,2016,44(23):39-45.(HE Xiao,LEI Yong,ZHOU Cong-cong,et al.The single end traveling wave fault location algorithm of distribution network to eliminate the influence of zero mode wave speed[J].Power System Protection and Control,2016,44(23):39-45.)
[7]陈时飞.基于行波的配电网的故障测距技术研究[D].北京:华北电力大学,2016.(CHEN Shi-fei.Research on fault location technology of traveling wave based distribution network[D].Beijing:North China Electric Power University,2016.)
[8]范静雅,陈亚,赵志,等.基于馈线终端设备的电网故障定位算法[J].计算机与数字工程,2017(9):1708-1712.(FAN Jing-ya,CHEN Ya,ZHAO Zhi,et al.Power grid fault location algorithm based on feeder terminal equipment[J].Computer and Digital Engineering,2017(9):1708-1712.)
[9]严凤,李双双.基于C型行波与SVM的配电线路故障定位[J].电力系统及其自动化学报,2016,28(1):86-90.(YAN Feng,LI Shuang-shuang.Fault location of distribution lines based on C traveling wave and SVM[J].Power System and Automation Journal,2016,28(1):86-90.)
[10]Shen L X.Single terminal traveling wave fault location method based on SVM[J].Research Gate,2016,6(4):242-251.
[11]满蔚仕,宋超,张志禹.基于Hilbert-Huang变换的多端配电网行波故障定位[J].微型机与应用,2017,36(3):12-15.(MAN Wei-shi,SONG Chao,ZHANG Zhi-yu.Multi terminal distribution network traveling wave fault location based on Hilbert-Huang transform[J].Microcomputer and Application,2017,36(3):12-15.)
[12]朱建刚,魏佩瑜,刘澍存,等.基于时差比较的配电网含分支混合线路行波故障定位研究[J].山东电力技术,2017,44(9):78-85.(ZHU Jian-gang,WEI Pei-yu,LIU Shu-cun,et al.Distribution network with branch mixed line traveling wave fault location based on time difference comparison[J].Shandong Electric Power Technology,2017,44(9):78-85.)
[13]苏凤,王选诚,董云云,等.一种基于自由振荡主频实现故障测距的方法[J].电网与清洁能源,2016,32(3):68-71.(SU Feng,WANG Xuan-cheng,DONG Yun-yun,et al.A method of fault location based on free oscillating main frequency[J].Power Grid and Clean Energy,2016,32(3):68-71.)
[14]Margarita R S,Carlos A,Coello C.Improving PSO-based multi-objective optimization using crow ding,mutation and dominance[J].Lecture Notes in Computer Science,2005,34(6):505-519.
[15]栗青,杨璐,刘一芳,等.神经网络技术在设备故障诊断中的应用进展[J].沈阳工业大学学报,2004,26(2):174-178.(LI Qing,YANG Lu,LIU Yi-fang,et al.Application of neural network technology in equipment fault diagnosis[J].Journal of Shenyang University of Technology,2004,26(2):174-178.)
[16]魏江涛,陈方涛,姜美雷.BP神经网络在设备故障诊断方面的应用[J].现代电子技术,2012,35(19):131-134.(WEI Jiang-tao,CHEN Fang-tao,JIANG Mei-lei.Application of BP neural network in fault diagnosis[J].Modern Electronic Technique,2012,35(19):131-134.)
[17]夏琳琳,文磊,刘惠敏,等.改进PSO-BPNN的电力变压器故障诊断与模式识别[J].沈阳工业大学学报,2016,38(6):606-611.(XIA Lin-lin,WEN Lei,LIU Hui-min,et al.Fault diagnosis and pattern recognition of power transformer based on improved PSO-BPNN[J].Journal of Shenyang University of Technology,2016,38(6):606-611.)
[2]王磊,曹现峰,骆玮.基于改进PSO优化模糊神经网络的配电网故障选线研究[J].电气技术,2016,17(3):30-35.(WANG Lei,CAO Xian-feng,LUO Wei.Research on fault line selection of distribution network based on improved PSO optimization fuzzy neural network[J].Electrical Technology,2016,17(3):30-35.)
[3]孟安波,葛佳菲,李德强,等.基于纵横交叉算法的神经网络配电网故障选线研究[J].电力系统保护与控制,2016,44(21):90-95.(MENG An-bo,GE Jia-fei,LI De-qiang,et al.The line selection of neural network based on fault crossing algorithm[J].Power System Protection and Control,2016,44(21):90-95.)
[4]张雷,黄奕宏,翁胜龙.基于GA-DS的多神经网络故障诊断方法[J].电子设计工程,2015,23(10):14-17.(ZHANG Lei,HUANG Yi-hong,WENG Sheng-long.GA-DS based multi neural network fault diagnosis method[J].Electronic Design Engineering,2015,23(10):14-17.)
[5]龚水清,王崴.基于虚拟仪器和BP神经网络液压系统故障诊断[J].电子科技,2011,24(9):128-132.(GONG Shui-qing,WANG Wei.Hydraulic system fault diagnosis based on virtual instrument and BPneural network[J].Electronic Science and Technology,2011,24(9):128-132.)
[6]何晓,雷勇,周聪聪,等.消除零模波速影响的配电网单端行波故障测距算法[J].电力系统保护与控制,2016,44(23):39-45.(HE Xiao,LEI Yong,ZHOU Cong-cong,et al.The single end traveling wave fault location algorithm of distribution network to eliminate the influence of zero mode wave speed[J].Power System Protection and Control,2016,44(23):39-45.)
[7]陈时飞.基于行波的配电网的故障测距技术研究[D].北京:华北电力大学,2016.(CHEN Shi-fei.Research on fault location technology of traveling wave based distribution network[D].Beijing:North China Electric Power University,2016.)
[8]范静雅,陈亚,赵志,等.基于馈线终端设备的电网故障定位算法[J].计算机与数字工程,2017(9):1708-1712.(FAN Jing-ya,CHEN Ya,ZHAO Zhi,et al.Power grid fault location algorithm based on feeder terminal equipment[J].Computer and Digital Engineering,2017(9):1708-1712.)
[9]严凤,李双双.基于C型行波与SVM的配电线路故障定位[J].电力系统及其自动化学报,2016,28(1):86-90.(YAN Feng,LI Shuang-shuang.Fault location of distribution lines based on C traveling wave and SVM[J].Power System and Automation Journal,2016,28(1):86-90.)
[10]Shen L X.Single terminal traveling wave fault location method based on SVM[J].Research Gate,2016,6(4):242-251.
[11]满蔚仕,宋超,张志禹.基于Hilbert-Huang变换的多端配电网行波故障定位[J].微型机与应用,2017,36(3):12-15.(MAN Wei-shi,SONG Chao,ZHANG Zhi-yu.Multi terminal distribution network traveling wave fault location based on Hilbert-Huang transform[J].Microcomputer and Application,2017,36(3):12-15.)
[12]朱建刚,魏佩瑜,刘澍存,等.基于时差比较的配电网含分支混合线路行波故障定位研究[J].山东电力技术,2017,44(9):78-85.(ZHU Jian-gang,WEI Pei-yu,LIU Shu-cun,et al.Distribution network with branch mixed line traveling wave fault location based on time difference comparison[J].Shandong Electric Power Technology,2017,44(9):78-85.)
[13]苏凤,王选诚,董云云,等.一种基于自由振荡主频实现故障测距的方法[J].电网与清洁能源,2016,32(3):68-71.(SU Feng,WANG Xuan-cheng,DONG Yun-yun,et al.A method of fault location based on free oscillating main frequency[J].Power Grid and Clean Energy,2016,32(3):68-71.)
[14]Margarita R S,Carlos A,Coello C.Improving PSO-based multi-objective optimization using crow ding,mutation and dominance[J].Lecture Notes in Computer Science,2005,34(6):505-519.
[15]栗青,杨璐,刘一芳,等.神经网络技术在设备故障诊断中的应用进展[J].沈阳工业大学学报,2004,26(2):174-178.(LI Qing,YANG Lu,LIU Yi-fang,et al.Application of neural network technology in equipment fault diagnosis[J].Journal of Shenyang University of Technology,2004,26(2):174-178.)
[16]魏江涛,陈方涛,姜美雷.BP神经网络在设备故障诊断方面的应用[J].现代电子技术,2012,35(19):131-134.(WEI Jiang-tao,CHEN Fang-tao,JIANG Mei-lei.Application of BP neural network in fault diagnosis[J].Modern Electronic Technique,2012,35(19):131-134.)
[17]夏琳琳,文磊,刘惠敏,等.改进PSO-BPNN的电力变压器故障诊断与模式识别[J].沈阳工业大学学报,2016,38(6):606-611.(XIA Lin-lin,WEN Lei,LIU Hui-min,et al.Fault diagnosis and pattern recognition of power transformer based on improved PSO-BPNN[J].Journal of Shenyang University of Technology,2016,38(6):606-611.)