基于LSSVM的电动汽车驱动电动机的Willans模型

发布时间：2018-07-01 16:29

本文选题：Willans模型 + 最小二乘支持向量机　；参考：《江苏大学学报(自然科学版)》2016年04期

【摘要】：电动汽车驱动电动机的MAP图是传动系统构件选择与优化的重要依据,其直接影响整车动力性和经济性评价.在分析发动机统一模型(Willans模型)的基础上,通过变量映射将发动机Willans模型应用于电动机模型,建立了电动汽车驱动电动机的Willans模型.针对多重多项式拟合精度不高的问题,提出采用最小二乘支持向量机(LSSVM)方法拟合电动机的Willans模型,并利用粒子群算法优化LSSVM关键参数.计算结果表明:在较低可用平均有效压力区域,基于LSSVM的电动机Willans模型与多项式电动机Willans模型差别不大;在较高可用平均有效压力区域,基于LSSVM的电动机Willans模型明显优于多项式电动机Willans模型.
[Abstract]:The MAP diagram of the electric motor driving motor is an important basis for the selection and optimization of the transmission system components, which directly affects the dynamic and economic evaluation of the whole vehicle. On the basis of the analysis of the unified model of the engine (Willans model), the engine Willans model is applied to the motor model by variable mapping, and the driving motor of the electric vehicle is established. Willans model. Aiming at the problem that the precision of multiple polynomial fitting is not high, the least squares support vector machine (LSSVM) is used to fit the Willans model of the motor, and the key parameters of the LSSVM are optimized by particle swarm optimization. The results show that the Willans model of motor based on LSSVM in the lower available effective pressure region and the LSSVM based motor Willans model The Willans model of the term motor is not very different. The Willans model of motor based on LSSVM is obviously superior to the polynomial motor Willans model in the area with high available average effective pressure.
【作者单位】：江苏大学汽车与交通工程学院;
【基金】：中国博士后科学基金资助项目(2015M571680) 江苏省“六大人才高峰”项目(2014-JXQC-004) 江苏省普通高校研究生科研创新计划项目(CXLX13_677)
【分类号】：U469.72

【相似文献】