摘要
为延长电动汽车的续驶里程,对电动汽车进行再生制动控制是一种有效方法。对电动汽车进行再生制动控制研究,设计一种基于T-S模糊神经网络控制策略的控制器。该控制器以反馈电流与给定电流的差值和转速为输入,以PWM脉宽调节量为输出,采用BP神经网络算法自适应调整输入隶属度函数和模糊规则。最后,搭建了电动汽车再生制动控制系统模型,对设计的控制器进行仿真实验研究,结果显示,设计的T-S模糊神经网络控制策略能量回收率比模糊控制策略能量回收率最高提高了14.5%,验证了T-S模糊神经网络控制策略的有效性。
In order to increase the driving range of electric vehicles,regenerative braking control can be carried out on electric vehicles.A controller based on T-S fuzzy neural network control strategy was designed.For the controller,the difference of the feedback current,the given current and speed were selected as inputs,and the PWM pulse width adjustment amount was selected as output,and the BP neural network was used to adjust the controller input membership functions and fuzzy rules adaptively.An electric vehicle regenerative braking control system model was designed and the simulation experiments were done with the controller.The results show that the designed T-S fuzzy neural network control strategy has more energy recovery rate than the fuzzy control strategy,and the maximum increase rate achieves to 14.5%,so the T-S fuzzy neural network control strategy is effective and it can be used to improve the regenerative braking control system of electric vehicles.
作者
向楠
张向文
XIANG Nan;ZHANG Xiangwen(Guangxi Key Laboratory of Automatic Detecting Technology,Guilin University of Electronic Technology,Guilin 541004,Guangxi,China;School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,Guangxi,China)
出处
《电气传动》
北大核心
2020年第7期86-91,共6页
Electric Drive
基金
国家自然科学基金资助项目(51465011)
桂林电子科技大学研究生教育创新计划资助项目(2017YJCX98)。
关键词
电动汽车
再生制动
T-S模糊神经网络
electric vehicle
regenerative braking
Takagi-Sugeno(T-S)fuzzy neural network
