Real-Time Optimal Control of the Gearshift Schedule for Dual Clutch Transmissions

Abstract

In order to improve the fuel economy of vehicles equipped with a dual clutch transmission, this paper proposes a real-time gearshift schedule optimization method based on dynamic programming (DP) and future vehicle speed prediction. The global condition information is necessary for DP algorithm, which makes it difficult to be applied to the real-time control of vehicles. Therefore, BP neural network optimized by genetic algorithm (GA-BP) is utilized to predict future speed information in the research, and the results of speed prediction are introduced into DP problem solving process to realize real-time application of DP optimization in gear decision-making. Simulation results on a fuel vehicle with seven-speed dual clutch transmission using different gear decision-making methods under multiple driving cycles are presented. The results indicate that compared with the case of an empirical economy gearshift strategy, additional fuel can be saved. Furthermore, computational effort for the proposed method is little enough, which guarantees the real-time performance of DP gearshift schedule optimization.