模糊神经网络算法Plug in电动车能量管理控制器

Research and design of a novel PHEV energy management controller

针对Plug in混合动力汽车研究设计基于模糊神经网络算法的整车能量管理控制器。将驾驶行为用神经网络进行建模,驾驶模式、踏板(油门和刹车)位置以及当前车轮力矩作为神经网络输入,目标力矩作为输出;并将道路类型、目标力矩、电池SOC、当前车轮力矩为模糊输入变量,以满足整车动力性能、燃油经济型和极限边界极值为约束条件,对混合动力汽车的能量进行分配与管理,用advsior软件进行了仿真,基于该算法在DSP硬件平台设计实现能量管理控制器,通过算法仿真和样车测试表明:在行驶里程60 km等价燃油经济型最好,随着行驶里程增加燃油经济型下降,整个测试过程中样车动力性能以及各部件工况良好。

An energy management controller of plug in hybrid electric vehicle（PHEV） based on fuzzy neural network algorithm was proposed.With driving mode,pedal（throttle and brake） position and current wheel torque as input,and the target torque as output,driving behavior was modeling by neural network algorithm.With the type of road,the target torque,battery SOC,and the current wheel torque for the fuzzy input variable,the vehicle power performance and the fuel economy as constraint condition,the power was distributed between the motor and the engine by fuzzy algorithm.The algorithm was simulated by the advsior software.The energy distribution and management controller was designed based on the algorithm on DSP hardware platform.The result of simulation and prototype test shows：in the mileage 50 km equivalent fuel economy is the best,and with the increase of the mileage,fuel economic declines.In the whole testing process,the power performance is good,and every parts of the hybrid electric vehicle are in good working condition.