CVT插电式混合动力汽车全局优化控制策略  

Global optimization control strategy of CVT plug-in hybrid electric vehicle

作　　者：杨官龙[1] 秦大同[1] 刘永刚[1] 林毓培[1] 

机构地区：[1]重庆大学机械传动国家重点实验室,重庆400044

出　　处：《中南大学学报（自然科学版）》2014年第12期4194-4200,共7页Journal of Central South University:Science and Technology

基　　金：国家科技支撑计划项目(2013BAG12B01);国家自然科学基金资助项目(51305468)~~

摘　　要：针对一款无级变速器(CVT)插电式混合动力汽车,采用瞬时优化算法对CVT的速比进行实时优化,将优化结果嵌套在动态规划算法中进行全局优化,获得发动机与电机的功率分配;采用误差反向传播(BP)神经网络对发动机与电机的工作点进行训练拟合,得到优化控制MAP图,用于循环工况的实时控制。在Matlab/Simulink仿真平台下建立模型进行仿真,结果表明:采用BP控制策略的能耗经济性在新欧洲行驶循环(NEDC)、城市测功器驾驶进程(UDDS)和高速路燃油经济测试(HWFET)循环工况下与门限值控制策略得到的结果相比,都有不同程度的提高。Aiming at a continuously variable transmission（CVT） plug-in hybrid electric vehicles, the real-time optimization results of CVT speed ratio are obtained by using the instantaneous optimization algorithm, which have been embedded in a dynamic programming algorithm for global optimization getting power distribution rules of engine and motor. The control MAPs for real-time control of the driving cycle have been obtained by using BP neural network training fitting. On the matlab/simulink platform, the optimization mode was built and simulated. Simulation results indicate that the energy consumption economy of BP control strategy have different degrees of improvement comparing with threshold control strategy under New European Driving Cycle（NEDC）, Urban Dynamometer Driving Schedule（UDDS） and Highway Fuel Economy Test（HWFET） cycle conditions.

关 键 词：插电式混合动力汽车 无级变速器 全局优化 BP神经网络 能耗经济性 

分 类 号：U461.8[机械工程—车辆工程]