| 基于DE优化SVR的锂离子电池剩余容量预测 |
| |
| 引用本文： | 唐超,曹龙汉,赵泽鑫,何俊强,吴珍毅.基于DE优化SVR的锂离子电池剩余容量预测[J].重庆工学院学报,2011(3). |
| |
| 作者姓名： | 唐超 曹龙汉 赵泽鑫 何俊强 吴珍毅 |
| |
| 作者单位： | 重庆通信学院控制工程重点实验室;煤炭科学研究总院重庆研究院; |
| |
| 基金项目： | 国防科研项目(TZ-CQTY-Y-A-2010-002); 2010年重庆高校优秀成果转化项目(Kjzh10219) |
| |
| 摘 要： | 在分析了支持向量机回归算法(SVR)对剩余容量模型非线性回归基础上,针对SVR参数选择难的问题,提出了一种基于微分进化(DE)算法优化SVR的算法。DE具有强劲的全局搜索能力,将其应用到SVR的参数寻优当中去,可以寻找到SVR的最优参数。将该方法应用于锂离子电池剩余容量的预测模型,并将生成的模型和基于粒子群优化(PSO)算法的SVR锂离子电池容量预测模型比较。仿真结果表明,基于DE优化的SVR剩余容量预测的精准度高于PSO优化的SVR剩余容量预测精准度,为锂离子电池容量预测提供了一种新的方法。
|
| 关 键 词： | 支持向量机回归 微分进化算法 粒子群优化算法 参数选择 锂离子电池 容量预测 |
SVR Optimized by DE Optimization Algorithm for Remaining Capacity Forecasting |
| |
| TANG Chao,CAO Long-han,ZHAO Ze-xin,HE Jun-jiang,WU Zhen-yi.SVR Optimized by DE Optimization Algorithm for Remaining Capacity Forecasting[J].Journal of Chongqing Institute of Technology,2011(3). |
| |
| Authors: | TANG Chao CAO Long-han ZHAO Ze-xin HE Jun-jiang WU Zhen-yi |
| |
| Affiliation: | TANG Chao1,CAO Long-han1,ZHAO Ze-xin2,HE Jun-jiang1,WU Zhen-yi1 (1.Control Engineering Key Laboratory,Chongqing Communication Institute,Chongqing 400035,China,2.Chongqing Institute,Coal Science Academy,Congqing 400039,China) |
| |
| Abstract: | In the analysis of support vector machine for regression(SVR) on the model of remaining capacity with nonlinearity,aimed at the puzzle of selection of SVR's parameters,the paper proposed a predictive model for remaining capacity of lithium ion batteries.The model was based on the SVR with parameter optimized by differential evolution(DE) algorithm.DE has powerful global searching ability,which would be applied to the optimization of SVR's parameters,and the predictive precision of the lithium ion batteries ... |
| |
| Keywords: | support vector machine for regression differential evolution algorithm particle swarm optimization(PSO) algorithm parameter selection lithium ion batteries capacity prediction |
| 本文献已被 CNKI 等数据库收录！ |
|
