Automotive Gear-Shifting Decision Making Based on Neural Network Computation Model

Abstract

Precise description of the engine dynamic characteristics plays a crucial role in automatic gear-shifting decision making for the performance match and optimization of vehicle power-train system. In this paper, a multi-layer feed forward neural network was proposed to identify the dynamic torque and fuel consumption models of engine. Based on the neural network models, algorithms to calculate the optimal dynamic and economical gear-shifting rules were constructed respectively. Comparative tests show that the gear-shifting decision based on neural network computation models is better than that based on traditional computation model using curve approximation, and improves the dynamic performance and fuel economy of vehicle power-train system significantly.