基于遗传算法优化BP神经网络的接触电阻预测
|
摘要
接触电阻是反应导体间电接触性能的重要参数,在实际的工程中往往采用经验公式对接触电阻进行计算,精度难以满足要求。为解决这一问题,将遗传算法(GA)与BP神经网络相结合对接触电阻进行预测。通过实验得到数据,分别利用遗传算法优化BP神经网络、BP神经网络以及回归分析模型进行训练和测试,并将各算法所得误差进行对比。误差对比结果表明:遗传算法优化BP神经网络的收敛效果优于其他两种算法,且遗传算法优化BP神经网络所得接触电阻模型的相对误差平均值比BP神经网络减少了4. 01%,比回归分析减少了4. 72%,且预测效果较稳定。利用遗传算法与BP神经网络相结合的接触电阻预测模型,较单独使用BP神经网络预测模型具有更好的非线性拟合能力和更高的预测精度。
The contact resistance is an important parameter of the electrical contact performance between the reaction conductors. In practice,the empirical formula is often used to calculate the contact resistance,which is difficult to meet the accuracy requirements. In order to solve this problem,the genetic algorithm (GA) combined with BP neural network is adopted to predict the contact resistance. The data are obtained through experiment,the optimized BP neural network of genetic algorithm,the BP neural network and regression analysis model are respectively used for training and testing,and the errors obtained by each algorithm are compared. The results of error comparison show that genetic algorithm optimizes the convergence effect of BP neural network better than the other two algorithms,and the average relative error of the contact resistance model obtained by genetic algorithm optimization BP neural network is reduced by 4. 01% compared with BP neural network,which is lower than the regression analysis 4. 72%,and the forecasting effect is more stable. The contact resistance prediction model using genetic algorithm and BP neural network has better nonlinear fitting ability and higher prediction accuracy than the BP neural network prediction model alone.
The contact resistance is an important parameter of the electrical contact performance between the reaction conductors. In practice,the empirical formula is often used to calculate the contact resistance,which is difficult to meet the accuracy requirements. In order to solve this problem,the genetic algorithm (GA) combined with BP neural network is adopted to predict the contact resistance. The data are obtained through experiment,the optimized BP neural network of genetic algorithm,the BP neural network and regression analysis model are respectively used for training and testing,and the errors obtained by each algorithm are compared. The results of error comparison show that genetic algorithm optimizes the convergence effect of BP neural network better than the other two algorithms,and the average relative error of the contact resistance model obtained by genetic algorithm optimization BP neural network is reduced by 4. 01% compared with BP neural network,which is lower than the regression analysis 4. 72%,and the forecasting effect is more stable. The contact resistance prediction model using genetic algorithm and BP neural network has better nonlinear fitting ability and higher prediction accuracy than the BP neural network prediction model alone.
引文
[1]王刚,谭盛武,何子博,等.梯度下降优化模糊系统的接触电阻预测方法[J].华侨大学学报(自然版),2017,38(1):86-90.
[2]王刚,王之军,杨欣可,等.接触电阻建模新方法[J].昆明理工大学学报(自然科学版),2017,42(1):39-43.
[3]陈允,徐伟东,袁伟群,等.电磁发射中铝电枢与不同材料导轨间的滑动电接触特性[J].高电压技术,2013,39(4):937-942.
[4]Ren W,Wang P,Song J,et al.Effects of current load on wear and fretting corrosion of gold-plated electrical contacts[J].Tribology International,2014,70(70):75-82.
[5]杨文英,任万滨,翟国富,等.工频磁场对电磁继电器动态特性影响的三维有限元分析[J].电工技术学报,2011,26(1):51-56.
[6]金向朝,黄松波,谢志杨,等.考虑粗糙表面接触的气体绝缘开关设备接头接触电阻数值计算与影响因素分析[J].电网技术,2015,39(6):1725-1730.
[7]李奎,张冠生,陆俭国.含膜触头静态接触下接触电阻有限元模型及其分析[J].电工技术学报,1998,13(1):27-31.
[8]Greenwood J A.Constriction resistance and the real area of contact[J].British Journal of Applied Physics,1966,17(12):1621-1632.
[9]Jackson R L,Malucci R D,Angadi S,et al.A Simplified Model of Multiscale Electrical Contact Resistance and Comparison to Existing Closed.
[10]陈伟根,奚红娟,苏小平,等.广义回归神经网络在变压器绕组热点温度预测中的应用[J].高电压技术,2012,38(1):16-21.
[11]雷成华,刘刚,李钦豪.BP神经网络模型用于单芯电缆导体温度的动态计算[J].高电压技术,2011,37(1):184-189.
[12]程礼椿.电接触理论及应用[M].北京:机械工业出版社,1988.
[13]孙立军.触点电接触失效预测理论的研究[D].天津:河北工业大学,2002.
[14]程礼椿,李震彪.接触电阻模型发展与应用[J].电器与能效管理技术,1993,(5):10-14.
[15]Malucci R D.Multispot model of contacts based on surface features[C]//Electrical Contacts,1990.Proceedings of the Thirty-Sixth IEEEHolm Conference on.and the Fifteenth International Conference on E-lectrical Contacts.IEEE,1990:625-634.
[16]王志斌,孔亚楠,刘永成,等.遗传算法优化BP神经网络的大功率LED结温预测[J].光电子激光,2014,25(7):1303-1309.
[17]王元章,李智华,吴春华,等.基于BP神经网络的光伏组件在线故障诊断[J].电网技术,2013,37(8):2094-2100.
[18]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.
[19]闫超,倪福佳,等.基于改进FOA优化BP神经网络算法的光伏系统MPPT研究[J].电测与仪表,2018,55(8):24-29,130.Yan Chao,Ni Fujia,et al.Research of the photovoltaic system MPPTbased on improved IFOA-BP neural network algorithm[J].Electrical Measurement&Instrumentation,2018,55(8):24-29,130.
[20]刘灿.遗传算法优化模糊神经网络在肺癌诊断中的应用[D].郑州:郑州大学,2011.
[21]李松,刘力军,解永乐.遗传算法优化BP神经网络的短时交通流混沌预测[J].控制与决策,2011,26(10):1581-1585.
[22]王刚,谭盛武,林生军,等.基于模糊系统的接触电阻建模方法[J].高电压技术,2017,43(3):940-945.
[2]王刚,王之军,杨欣可,等.接触电阻建模新方法[J].昆明理工大学学报(自然科学版),2017,42(1):39-43.
[3]陈允,徐伟东,袁伟群,等.电磁发射中铝电枢与不同材料导轨间的滑动电接触特性[J].高电压技术,2013,39(4):937-942.
[4]Ren W,Wang P,Song J,et al.Effects of current load on wear and fretting corrosion of gold-plated electrical contacts[J].Tribology International,2014,70(70):75-82.
[5]杨文英,任万滨,翟国富,等.工频磁场对电磁继电器动态特性影响的三维有限元分析[J].电工技术学报,2011,26(1):51-56.
[6]金向朝,黄松波,谢志杨,等.考虑粗糙表面接触的气体绝缘开关设备接头接触电阻数值计算与影响因素分析[J].电网技术,2015,39(6):1725-1730.
[7]李奎,张冠生,陆俭国.含膜触头静态接触下接触电阻有限元模型及其分析[J].电工技术学报,1998,13(1):27-31.
[8]Greenwood J A.Constriction resistance and the real area of contact[J].British Journal of Applied Physics,1966,17(12):1621-1632.
[9]Jackson R L,Malucci R D,Angadi S,et al.A Simplified Model of Multiscale Electrical Contact Resistance and Comparison to Existing Closed.
[10]陈伟根,奚红娟,苏小平,等.广义回归神经网络在变压器绕组热点温度预测中的应用[J].高电压技术,2012,38(1):16-21.
[11]雷成华,刘刚,李钦豪.BP神经网络模型用于单芯电缆导体温度的动态计算[J].高电压技术,2011,37(1):184-189.
[12]程礼椿.电接触理论及应用[M].北京:机械工业出版社,1988.
[13]孙立军.触点电接触失效预测理论的研究[D].天津:河北工业大学,2002.
[14]程礼椿,李震彪.接触电阻模型发展与应用[J].电器与能效管理技术,1993,(5):10-14.
[15]Malucci R D.Multispot model of contacts based on surface features[C]//Electrical Contacts,1990.Proceedings of the Thirty-Sixth IEEEHolm Conference on.and the Fifteenth International Conference on E-lectrical Contacts.IEEE,1990:625-634.
[16]王志斌,孔亚楠,刘永成,等.遗传算法优化BP神经网络的大功率LED结温预测[J].光电子激光,2014,25(7):1303-1309.
[17]王元章,李智华,吴春华,等.基于BP神经网络的光伏组件在线故障诊断[J].电网技术,2013,37(8):2094-2100.
[18]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.
[19]闫超,倪福佳,等.基于改进FOA优化BP神经网络算法的光伏系统MPPT研究[J].电测与仪表,2018,55(8):24-29,130.Yan Chao,Ni Fujia,et al.Research of the photovoltaic system MPPTbased on improved IFOA-BP neural network algorithm[J].Electrical Measurement&Instrumentation,2018,55(8):24-29,130.
[20]刘灿.遗传算法优化模糊神经网络在肺癌诊断中的应用[D].郑州:郑州大学,2011.
[21]李松,刘力军,解永乐.遗传算法优化BP神经网络的短时交通流混沌预测[J].控制与决策,2011,26(10):1581-1585.
[22]王刚,谭盛武,林生军,等.基于模糊系统的接触电阻建模方法[J].高电压技术,2017,43(3):940-945.