基于模型预测控制的电动车辆换挡策略研究  

Electric Vehicle Shift Strategy Based on Model Predictive Control

作　　者：秦杭 何洪文[1] 韩陌 QIN Hang;HE Hongwen;HAN Mo(National Engineering Laboratory for Electric Vehicles,School of Mechanical Engineering,Beijing Institute of Technology,Beijing 100081,China)

机构地区：[1]北京理工大学机械与车辆学院电动车辆工程国家重点实验室,北京100081

出　　处：《重庆理工大学学报（自然科学）》2021年第2期90-95,104,共7页Journal of Chongqing University of Technology：Natural Science

基　　金：国家重点研发计划项目(2018YFB0106200)。

摘　　要：基于模型预测控制框架,提出了一种考虑未来工况变化趋势的智能换挡策略。建立循环神经网络,以过去一段时间工况为输入,对未来5 s的车速序列进行预测。以训练好的神经网络作为模型预测控制的预测模型。采用动态规划方法构建基准策略,并作为模型预测换挡策略的滚动优化部分,建立了模型预测换挡策略。构建了基于C-WTVC的复合工况并仿真。设计了双参数经济性换挡规律作为对照。结果表明:模型预测换挡策略可以节约能源消耗,降低换挡频率。Based on the model predictive control framework,an intelligent shift strategy that takes into account the changing trend of future velocity was proposed.A recurrent neural network was established to predict velocity sequences in the 5-second horizon by using the velocity in the past.The trained neural network was used as the predictive model for model predictive control.Dynamicprogramming is adopted to construct a benchmark strategy and also to act as the rolling optimization part of the MPC shift strategy.A composite working condition based on C-WTVC is constructed and simulated.A two-parameter economic schedule was built as control reference.The simulation results showed that this shift strategy can reduce the shift frequency while saving energy consumption.

关 键 词：换挡策略 电动车辆 循环神经网络 模型预测控制 

分 类 号：U462.2[机械工程—车辆工程]