电控自动变速器档位决策神经网络方法

A NEURAL NETWORK APPROACH TO OPTIMAL GEAR POSITION DECISION FOR AN ELECTRONICALLY CONTROLLED MECHANICAL AUTOMATIC TRANSMISSION

电控机械式自动变速器的最佳换档规律是车辆状态与最佳档位间的一个非线性关系，往往以数据表的形式给出。用这些数据去训练一个神经网络，就可使表中反映的换档规律存到网络中；在线应用时，就可用其计算最佳档位。本文介绍了一个基于这种思想的最佳档位判别方案，并以两参数换档规律为例进行了网络训练的过程。

Optimal shifting in an electronically controlled automatic transmission turns out to be a nonlinear function between the vehicle state and gear position, and is usually described through a data table. It is proper to train a neural network based on the data, and to store the rules of shifting in the network. When used online the network can calculate the optimal gear position. An approach based on this concept is introduced and a neural network training course is illustrated.