本发明公开了一种燃料电池混合动力汽车的能量管理优化方法及系统,其方法包括:对目标车辆的历史行驶数据进行特征提取得到行车数据集;利用行车数据集对车速预测模型进行训练后重新学习相邻工况间的非线性关联,得到全局工况;根据车辆控制模型和全局工况计算动力电池的全局SOC变化轨迹;将每一个工况的行驶数据和行车数据集输入训练好的车速预测模型,得到每一个工况在未来短时域内的预测车速信息;根据全局SOC变化轨迹和每一个工况的预测车速信息,求解每一个工况在未来短时域内的能量最优控制序列,再将其中的第一个控制量反馈至车辆控制模型进行关联参数更新。本发明提出的局部优化策略可以确保整车能量在线管理分配的实时性。
The invention discloses an energy management optimization method and system for a fuel cell hybrid electric vehicle. The method comprises the steps that feature extraction is conducted on historical driving data of a target vehicle to obtain a driving data set; training the vehicle speed prediction model by using the driving data set, and then re-learning nonlinear correlation between adjacent working conditions to obtain a global working condition; calculating a global SOC change track of the power battery according to the vehicle control model and the global working condition; inputting the driving data and the driving data set of each working condition into a trained vehicle speed prediction model to obtain predicted vehicle speed information of each working condition in a future short time domain; and according to the global SOC change track and the predicted vehicle speed information of each working condition, solving an energy optimal control sequence of each working condition in a future short-time domain, and then feeding back a first control quantity to the vehicle control model for associated parameter updating. The local optimization strategy provided by the invention can ensure the real-time performance of online management and distribution of the energy of the whole vehicle.
一种燃料电池混合动力汽车的能量管理优化方法及系统
2024-06-25
Patent
Electronic Resource
Chinese
IPC: | B60L PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES , Antrieb von elektrisch angetriebenen Fahrzeugen |