The invention discloses a hybrid electric vehicle energy management method and device. The method comprises the following steps: by adopting a gating circulation unit deep learning prediction model, data of working conditions in a prediction time domain can be effectively predicted, a deep learning network can meanwhile carry out an offline training by combing with a large amount of data, and a better effect can be achieved; secondly, dynamic planning is embedded through a model prediction control framework, and a discretization calculation is carried out on state variables and control variables in a prediction time domain to solve a target function, so that an optimal control variable sequence is obtained, a situation that the dynamic planning needs to predict working conditions of a whole driving process is avoided, and calculation amount is reduced.
本发明提供了一种混合动力汽车能量管理方法及装置,本发明方法通过采用门控循环单元深度学习预测模型能够有效地对预测时域内的工况数据进行预测,同时深度学习网络可以结合大量的数据进行离线训练,能够达到更好的效果;其次通过模型预测控制框架嵌合动态规划,在预测时域内对状态变量与控制变量进行离散化计算求解目标函数,进而得到最优控制变量序列,避免了动态规划需要预知整个行车过程工况的情况,减少了计算量。
Hybrid electric vehicle energy management method and device
一种混合动力汽车能量管理方法及装置
2021-10-12
Patent
Electronic Resource
Chinese
IPC: | B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion |
European Patent Office | 2023
|Hybrid electric vehicle energy management device and method
European Patent Office | 2022
|Tandem type hybrid electric vehicle energy management method and device and hybrid electric vehicle
European Patent Office | 2020
|Energy management method and device for hybrid electric vehicle
European Patent Office | 2024
|Intelligent hybrid electric vehicle energy management method
European Patent Office | 2022
|