汽车工程 ›› 2025, Vol. 47 ›› Issue (5): 839-850.doi: 10.19562/j.chinasae.qcgc.2025.05.005

• • 上一篇    下一篇

基于能耗预测的网联电动公交车生态驾驶优化策略

潘应久,郗毅,刘延森,房文鹏,张文珊()   

  1. 长安大学汽车学院,西安 710018
  • 收稿日期:2024-10-16 修回日期:2024-12-19 出版日期:2025-05-25 发布日期:2025-05-20
  • 通讯作者: 张文珊 E-mail:zhangwenshan@chd.edu.cn
  • 基金资助:
    国家自然科学基金(52402417);陕西省自然科学基础研究计划项目(2023-JC-QN-0385);长安大学中央高校基本科研业务专项资金(300102223107)

An Energy Consumption Prediction-Based Optimization Strategy for Eco-driving of Connected Electric Buses

Yingjiu Pan,Yi Xi,Yansen Liu,Wenpeng Fang,Wenshan Zhang()   

  1. School of Automobile,Chang’an University,Xi’an 710018
  • Received:2024-10-16 Revised:2024-12-19 Online:2025-05-25 Published:2025-05-20
  • Contact: Wenshan Zhang E-mail:zhangwenshan@chd.edu.cn

摘要:

电动公交车的动力系统及能耗特性与传统内燃机公交车存在显著差异,传统公交车的节能驾驶策略并不完全适用于电动公交车。本文综合考虑电动公交车经过信号交叉口时的信号配时、前车信息能耗特性和乘客舒适性,提出一种基于能耗预测的网联电动公交车生态驾驶深度强化学习模型。首先,采集纯电动公交车自然驾驶数据,考虑电动公交车的制动能量回收特性,利用车辆动力学建立能耗基本模型,构建系统辨识模型对能耗基本模型中的未知参数进行辨识和估计;其次,剖析车辆进出信号交叉口时不同信号相位对速度模式的影响,确定能够精确描述交通环境信息的状态变量,以构建的能耗模型为基础,综合考虑安全、效率、节能和舒适性构建奖励函数,基于SAC(soft actor critic)算法构建电动公交车进出信号交叉口的生态驾驶策略优化模型;最后,将本文构建的生态驾驶策略与经典交叉口通行策略GLOSA进行对比验证。结果表明,本文提出的生态驾驶策略在划分的4种交通情境下均可保证车辆的安全性,在通行时间平均仅增长7.29%的情况下,舒适性平均提高21.96%,能耗平均降低24.47%。

关键词: 生态驾驶策略, 网联电动公交车, 深度强化学习, 乘客舒适性, 能耗预测, 信号交叉口

Abstract:

The power system and energy consumption characteristics of electric buses significantly differ from those of traditional buses with internal combustion engines, and conventional eco-driving strategies cannot fully adapt to electric buses. An energy consumption prediction-based deep reinforcement learning model is proposed for eco-driving of connected electric buses, taking into account of signal timing, information from preceding vehicles, energy consumption characteristics and comfort of passengers. Firstly, natural driving data from battery electric buses is collected, and a basic energy consumption model is established using vehicle dynamics, considering the regenerative braking characteristics of electric buses. A system identification model is then constructed to identify and estimate the unknown parameters in the basic energy consumption model. Next, the impact of different signal phases on speed patterns when entering and exiting signalized intersections is analyzed, and state variables that accurately describe traffic environment information are determined. Based on the constructed energy consumption model, a reward function is developed, considering safety, efficiency, energy conservation, and comfort. An optimization model for eco-driving strategies at signalized intersections for electric buses is established using the SAC(soft actor critic) algorithm. Finally, the proposed strategy is compared with the classic intersection passage strategy GLOSA. The results show that the proposed eco-driving strategy ensures vehicle safety across the four defined traffic scenarios. Despite an average increase in travel time of only 7.29%, the strategy enhances comfort by an average of 21.96% and reduces energy consumption by an average of 24.47%.

Key words: eco-driving strategy, connected electric bus, deep reinforcement learning, passenger comfort, energy consumption prediction, signalized intersection