摘要
针对目前燃料电池热管理系统在变载时存在温度波动较大、调节时间较长和响应速度较慢等问题,本文提出了流量同时跟随电流及功率方式和神经网络自抗扰方法两种热管理控制策略。结果表明:流量同时跟随电流及功率控制策略能够有效地削弱水泵和散热器风扇的耦合作用,明显减少电堆进出口冷却水温度及其温差的超调量和调节时间。此外,虽然神经网络自抗扰控制策略在最大功率工况下的控制效果较差,但总体控制效果比流量跟随电流控制策略好。
In order to solve the problems of large temperature fluctuation,long regulation time and slow response speed in the current fuel cell thermal management system,this paper proposes two thermal management control strategies:flow following current and power mode and neural network auto disturbance rejection method.The results show that the flow following current and power control strategy can effectively reduce the coupling effect of water pump and radiator fan,and significantly reduce the overshoot and regulation time of the temperature and the temperature difference of the cooling water at the inlet and outlet of the stack.In addition,although the neural network auto-disturbance control strategy has a poor control effect at the maximum power condition,the overall control effect is better than the flow following current control strategy.
作者
赵洪波
刘杰
马彪
郭强
刘晓辉
潘凤文
ZHAO Hongbo;LIU Jie;MA Biao;GUO Qiang;LIU Xiaohui;PAN Fengwen(Department of Power Mechanical Engineering,Beijing Jiaotong University,Beijing 100044,China;Weichai New Energy Technology Co.,Ltd.,Weifang 261041,Shandong,China)
出处
《化工学报》
EI
CAS
CSCD
北大核心
2020年第5期2139-2150,共12页
CIESC Journal
基金
国家自然科学基金青年科学基金项目(51406007)
国家重点研发计划项目“面向重卡用燃料电池系统集成与控制”。
关键词
燃料电池
控制策略
神经网络
热管理系统
fuel cell
control strategy
neural network
thermal management system
