混合动力汽车动力总成多智能体集成控制策略

Hybrid Electric Vehicle Integrated Control Strategy Based on Multi-agent

为提高混合动力电动汽车(Hybrid electric vehicle, HEV)整车性能,结合等效燃油消耗最小模型,提出一种多智能体(Agent)控制的动力总成集成控制策略。系统Agent实时分解整车动力总成任务并将其分配给发动机Agent、电机Agent和蓄电池Agent,各部件Agent计算完成任务所需付出的油耗(或等效油耗)、排放与蓄电池能量损耗成本,采用多目标拟合优化算法求取综合成本最小的动力分配关系,得到初步请求响应转矩指令。各部件Agent以自身工作效率优化为目标对请求响应转矩进行限制,并与其他Agent交互补偿转矩信息,协调协作完成HEV动力总成的集成控制。在Simulink中建立各Agent模型和集成控制策略模型,嵌入到ADVISOR整车模型中进行不同仿真循环工况下的联合仿真。研究结果表明,集成控制策略能够能实时合理权衡动力性、排放性和燃油经济性,在未损失较多动力性的前提下能够提高HEV节能减排能力。

Combined with the minimum equivalent fuel consumption model, an integrated control strategy of hybrid electric vehicle(HEV) powertrain based on multi-agent theory is proposed. The system agent decomposes the vehicle powertrain task in real time and distributes the sub-tasks to the engine agent, the motor agent and the battery agent. Each component agent calculates the cost for completion of tasks of fuel consumption(or equivalent fuel consumption), emissions and battery energy loss. The multi-objective fitting optimization algorithm is used to obtain the dynamic allocation relation of engine and motor with minimum integrated cost, and the initial request response torque command is obtained. Aiming at its own efficiency optimization, each component agent interacts with others for the limitation of torque command and exchanging compensation torque information for the completion coordination control task of the HEV powertrain. The Simulink model of each agent is established and Multi-agents(MA) integrated control strategy model is then built. These models are integrated into the vehicle model of ADVISOR and simulations are carried out under different driving cycles. The Simulation results show that by the means of the coordination of each agent and the integrated control of the powertrain components, the MA integrated control strategy can reasonably weigh the dynamic, emissions and fuel consumption economy to improve the capacity of energy-saving and emission reduction without losing too much power.