混合动力耦合系统神经网络油耗模型构建
A neural network fuel consumption model hybrid of EVT system

为了基于燃油经济性快速对混合动力耦合系统（EVT，electric variable transmission）构型进行筛选，在混合动力EVT构型图论分层图画模型的基础上提出混合动力EVT图论构型矩阵，并对混合动力EVT系统构型进行动力学建模；结合GRNN神经网络算法与动态规划算法，建立混合动力EVT系统神经网络油耗模型；通过对比测试构型的神经网络油耗模型计算结果和DP仿真结果，验证了该油耗模型的有效性。
In order to quickly screen the hybrid electric vehicle powertrain (EVT, electric variable transmission) configurations based on their fuel economy, a configuration matrix of hybrid EVT system is proposed and the dynamic model of hybrid EVT system is established on the basis of graph theory hierarchical drawing model of hybrid EVT system. A fuel consumption model of hybrid EVT system that combines general regression neural network and dynamic programming algorithm is established and its effectiveness is verified by comparing the calculation results of GRNN fuel consumption model and that of the DP simulation of the test configurations