考虑多层作业工况预测的燃料电池拖拉机分层节能协同优化策略  

Co-optimization Hierarchical Energy Saving Strategy for Fuel Cell Tractor Considering Multi-layer Working Condition Prediction

作　　者：徐宏扬 赵静慧 李梦林 尹龙 闫梅 XU Hongyang;ZHAO Jinghui;LI Menglin;YIN Long;YAN Mei(College of Vehicle and Energy,Yanshan University,Qinhuangdao 066000,China;National Key Laboratory of Intelligent Agricultural Power Equipment,Luoyang 471039,China;Hebei Provincial Key Laboratory of Special Transport Equipment,Qinhuangdao 066000,China)

机构地区：[1]燕山大学车辆与能源学院燕山大学车辆与能源学院,河北秦皇岛066000 [2]智能农业动力装备全国重点实验室,河南洛阳471003 [3]河北省特种运载装备重点实验室,河北秦皇岛066000

出　　处：《拖拉机与农用运输车》2024年第6期43-49,64,共8页Tractor & Farm Transporter

基　　金：智能农业动力装备全国重点实验室开放课题(SKLIAPE 2023018);国家自然科学基金资助项目(52202484);河北省自然科学基金资助项目(F2024203111);河北省高等学校科学技术研究项目-青年拔尖人才项目(BJK2024156)。

摘　　要：燃料电池因其无污染、高效率的优势,被认为是实现绿色农机的发展方向。目前,制约燃料电池拖拉机发展的主要挑战是构建动力系统能量分配与不稳定作业工况间的紧密联系。因此,本文设计了一种燃料电池拖拉机分层节能优化策略,通过预测多层未来作业工况,降低拖拉机能量消耗和动力系统寿命损耗带来的成本。具体地,基于真实拖拉机作业工况,求解最优动力分配序列,建立基于深度学习的车辆状态和SOC参考轨迹映射模型,为下层的功率分配策略提供参考。结果表明,与没有工况预测的策略相比,所提出的策略节约了约56.8%的总等效氢气消耗、约8.8%的总成本。Fuel cells are considered to be the development direction for realizing green agricultural machinery due to their non-pollution and high efficiency advantages.Currently,the main challenge constraining the development of fuel cell tractors is to construct a strong link between power system energy distribution and unstable operating conditions.Therefore,in this paper,a hierarchical energy-saving optimization strategy for fuel cell tractors is designed to reduce the costs associated with tractor energy consumption and power system lifetime loss by predicting multi-layer future operating conditions.Specifically,the optimal power allocation sequence is solved based on real tractor operating conditions,and a deep learning-based mapping model of vehicle states and SOC reference trajectories is established to provide a reference for the power allocation strategy in the lower layers.The results show that the proposed strategy saves about 57.38%of the total equivalent hydrogen consumption,and about 8.74%of the total cost,compared with the strategy without working condition prediction.

关 键 词：燃料电池动力系统 混合动力拖拉机 能量管理策略 拖拉机犁耕工况 深度学习模型 工况预测 

分 类 号：U469.72[机械工程—车辆工程]