矿用动力电池荷电状态预测
|
摘要
针对最小二乘支持向量机(LSSVM)用于预测矿用动力电池荷电状态(SOC)时正则化参数和核函数参数难以优化选择,灰狼优化(GWO)算法在单独求解约束优化问题时出现早熟、稳定性差、易陷入局部最优等问题,在差分进化灰狼优化(DE-GWO)算法的基础上,采用指数函数形式的非线性收敛因子对DEGWO算法进行改进。该非线性收敛因子在迭代过程前段衰减速率低,能更好地寻找全局最优解,在迭代过程后段衰减速率高,能更精确地寻找局部最优解,有效平衡全局搜索能力和局部搜索能力。实验结果表明,利用改进DE-GWO算法优化LSSVM参数后建立的矿用动力电池SOC预测模型最大绝对误差为3.7%,最大相对误差为5.3%。
It was difficult to optimize parameters of regularization and kernel function when least squares support vector machine(LSSVM)was used to predict state of charge(SOC)of mine-used power battery,and grey wolf optimization(GWO)algorithm was prone to early maturity,poor stability and local optimization when solving constraint optimization problem alone.In view of above problems,on the basis of differential evolution GWO(DE-GWO)algorithm,non-linear convergence factor in the form of exponential function is used to improve the DE-GWO algorithm.The non-linear convergence factor has low attenuation rate in the early stage of iterative process and the global optimal solution can better be found,while it has high attenuation rate at the end of iterative process and the local optimal solution can be found more accurately,which effectively balances global search ability and local search ability.The experimental results show that the maximum absolute error and the maximum relative error of SOC prediction model for mine-used power battery are 3.7% and 5.3% respectively after LSSVM parameters are optimized by the improved DE-GWO algorithm.
It was difficult to optimize parameters of regularization and kernel function when least squares support vector machine(LSSVM)was used to predict state of charge(SOC)of mine-used power battery,and grey wolf optimization(GWO)algorithm was prone to early maturity,poor stability and local optimization when solving constraint optimization problem alone.In view of above problems,on the basis of differential evolution GWO(DE-GWO)algorithm,non-linear convergence factor in the form of exponential function is used to improve the DE-GWO algorithm.The non-linear convergence factor has low attenuation rate in the early stage of iterative process and the global optimal solution can better be found,while it has high attenuation rate at the end of iterative process and the local optimal solution can be found more accurately,which effectively balances global search ability and local search ability.The experimental results show that the maximum absolute error and the maximum relative error of SOC prediction model for mine-used power battery are 3.7% and 5.3% respectively after LSSVM parameters are optimized by the improved DE-GWO algorithm.
引文
[1]陈健美,钱承,李玉强,等.基于LS-SVM的混合动力镍氢电池组SOC预测[J].中南大学学报(自然科学版),2013,44(1):135-139.CHEN Jianmei,QIAN Cheng,LI Yuqiang,et al.SOC prediction of MH/Ni battery in hybrid vehicle based on LS-SVM[J].Journal of Central South University(Science and Technology),2013,44(1):135-139.
[2] MIRJALILI S,MIRJALILI S M,LEWIS A.Grey wolf optimization[J].Advances in Engineering Software,2014,69(7):46-61.
[3]龙文,赵东泉,徐松金.求解约束优化问题的改进灰狼优化算法[J].计算机应用,2015,35(9):2590-2595.LONG Wen, ZHAODongquan, XUSongjin.Improved grey wolf optimization algorithm for constrained optimization problem[J].Journal of Computer Applications,2015,35(9):2590-2595.
[4]金星,邵珠超,王盛慧.一种基于差分进化和灰狼算法的混合优化算法[J].科学技术与工程,2017,17(16):266-269.JIN Xing,SHAO Zhuchao,WANG Shenghui.A hybrid optimization algorithm based on differential evolution and grey wolf optimizer[J].Science Technology and Engineering,2017,17(16):266-269.
[5]张新明,涂强,康强,等.灰狼优化与差分进化的混合算法及函数优化[J].计算机科学,2017,44(9):93-98.ZHANG Xinming,TU Qiang,KANG Qiang,et al.Hybrid optimization algorithm based on grey wolf optimization and differential evolution for function optimization[J].Computer Science,2017,44(9):93-98.
[6]孙闽红,邵章义,秦源,等.基于差分进化狼群算法的GNSS欺骗干扰检测[J].计算机工程,2016,42(9):89-93.SUN Minhong,SHAO Zhangyi,QIN Yuan,et al.GNSSspoofingjammingdetectionbasedon differential evolution-wolf pack algorithm[J].Computer Engineering,2016,42(9):89-93.
[7]郭振洲,刘然,拱长青,等.基于改进灰狼算法的RBF神经网络研究[J].微电子学与计算机,2017,34(7):7-10.GUO Zhenzhou,LIU Ran,GONG Changqing,et al.Study on RBF neural network based on gray wolf optimization algorithm[J]. Microelectronics&Computer,2017,34(7):7-10.
[8]罗佳,唐斌.基于收敛因子非线性动态变化的灰狼优化算法[J].中国科技论文,2016,11(17):1991-1997.LUO Jia, TANG Bin. Grey wolf optimization algorithm based on nonlinear convergence factor dynamic changing[J].China Sciencepaper,2016,11(17):1991-1997.
[9]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 Zhenzhou,LIU Ran,GONG Changqing,et al.Study on improvement of gray wolf algorithm[J].Application Research of Computers,2017,34(12):3603-3606.
[10]于洋,纪世忠,魏克新.基于LS-SVM算法动力电池SOC估计方法的研究[J].电源技术,2012,36(3):349-351.YU Yang,JI Shizhong, WEI Kexin.Estimating method for power battery state of charge based on LS-SVM[J].Chinese Journal of Power Sources,2012,36(3):349-351.
[11]吕鹏飞,陈学华.基于PSO优化LSSVM模型的回采巷道顶底板移近量预测[J].安全与环境学报,2017,17(6):2045-2049.LYU Pengfei, CHENXuehua. PSOoptimized LSSVM model by predicting the convergence between the roof and the floor in the gateways[J].Journal of Safety and Environment,2017,17(6):2045-2049.
[12]童刘伟.基于LS-SVM的蓄电池荷电状态监测方法的研究与设计[D].南宁:广西大学,2013.
[13]牛家彬,王辉.一种基于混合策略的灰狼优化算法[J].齐齐哈尔大学学报(自然科学版),2018,34(1):16-19.NIU Jiabin,WANG Hui.A hybrid strategy-based grey wolf optimization algorithm[J].Journal of Qiqihar University(Natural Science Edition),2018,34(1):16-19.
[14]杨红光,刘建生.一种结合灰狼优化和K-均值的混合聚类算法[J].江西理工大学学报,2015,36(5):85-89.YANG Hongguang, LIUJiansheng. Ahybrid clustering algorithm based on grey wolf optimizer and K-means algorithm[J].Journal of Jiangxi University of Science and Technology,2015,36(5):85-89.
[15]王琪,孙玉坤,倪福银,等.混合动力汽车电池内部状态预测的贝叶斯极限学习机方法[J].中国机械工程,2016,27(22):3118-3123.WANG Qi,SUN Yukun,NI Fuyin,et al.Prediction of internal states of battery in HEV by BELM[J].China Mechanical Engineering,2016,27(22):3118-3123.
[2] MIRJALILI S,MIRJALILI S M,LEWIS A.Grey wolf optimization[J].Advances in Engineering Software,2014,69(7):46-61.
[3]龙文,赵东泉,徐松金.求解约束优化问题的改进灰狼优化算法[J].计算机应用,2015,35(9):2590-2595.LONG Wen, ZHAODongquan, XUSongjin.Improved grey wolf optimization algorithm for constrained optimization problem[J].Journal of Computer Applications,2015,35(9):2590-2595.
[4]金星,邵珠超,王盛慧.一种基于差分进化和灰狼算法的混合优化算法[J].科学技术与工程,2017,17(16):266-269.JIN Xing,SHAO Zhuchao,WANG Shenghui.A hybrid optimization algorithm based on differential evolution and grey wolf optimizer[J].Science Technology and Engineering,2017,17(16):266-269.
[5]张新明,涂强,康强,等.灰狼优化与差分进化的混合算法及函数优化[J].计算机科学,2017,44(9):93-98.ZHANG Xinming,TU Qiang,KANG Qiang,et al.Hybrid optimization algorithm based on grey wolf optimization and differential evolution for function optimization[J].Computer Science,2017,44(9):93-98.
[6]孙闽红,邵章义,秦源,等.基于差分进化狼群算法的GNSS欺骗干扰检测[J].计算机工程,2016,42(9):89-93.SUN Minhong,SHAO Zhangyi,QIN Yuan,et al.GNSSspoofingjammingdetectionbasedon differential evolution-wolf pack algorithm[J].Computer Engineering,2016,42(9):89-93.
[7]郭振洲,刘然,拱长青,等.基于改进灰狼算法的RBF神经网络研究[J].微电子学与计算机,2017,34(7):7-10.GUO Zhenzhou,LIU Ran,GONG Changqing,et al.Study on RBF neural network based on gray wolf optimization algorithm[J]. Microelectronics&Computer,2017,34(7):7-10.
[8]罗佳,唐斌.基于收敛因子非线性动态变化的灰狼优化算法[J].中国科技论文,2016,11(17):1991-1997.LUO Jia, TANG Bin. Grey wolf optimization algorithm based on nonlinear convergence factor dynamic changing[J].China Sciencepaper,2016,11(17):1991-1997.
[9]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 Zhenzhou,LIU Ran,GONG Changqing,et al.Study on improvement of gray wolf algorithm[J].Application Research of Computers,2017,34(12):3603-3606.
[10]于洋,纪世忠,魏克新.基于LS-SVM算法动力电池SOC估计方法的研究[J].电源技术,2012,36(3):349-351.YU Yang,JI Shizhong, WEI Kexin.Estimating method for power battery state of charge based on LS-SVM[J].Chinese Journal of Power Sources,2012,36(3):349-351.
[11]吕鹏飞,陈学华.基于PSO优化LSSVM模型的回采巷道顶底板移近量预测[J].安全与环境学报,2017,17(6):2045-2049.LYU Pengfei, CHENXuehua. PSOoptimized LSSVM model by predicting the convergence between the roof and the floor in the gateways[J].Journal of Safety and Environment,2017,17(6):2045-2049.
[12]童刘伟.基于LS-SVM的蓄电池荷电状态监测方法的研究与设计[D].南宁:广西大学,2013.
[13]牛家彬,王辉.一种基于混合策略的灰狼优化算法[J].齐齐哈尔大学学报(自然科学版),2018,34(1):16-19.NIU Jiabin,WANG Hui.A hybrid strategy-based grey wolf optimization algorithm[J].Journal of Qiqihar University(Natural Science Edition),2018,34(1):16-19.
[14]杨红光,刘建生.一种结合灰狼优化和K-均值的混合聚类算法[J].江西理工大学学报,2015,36(5):85-89.YANG Hongguang, LIUJiansheng. Ahybrid clustering algorithm based on grey wolf optimizer and K-means algorithm[J].Journal of Jiangxi University of Science and Technology,2015,36(5):85-89.
[15]王琪,孙玉坤,倪福银,等.混合动力汽车电池内部状态预测的贝叶斯极限学习机方法[J].中国机械工程,2016,27(22):3118-3123.WANG Qi,SUN Yukun,NI Fuyin,et al.Prediction of internal states of battery in HEV by BELM[J].China Mechanical Engineering,2016,27(22):3118-3123.