top of page


Mr. John Smith

Job title



Research and/or Engineering Questions/Objective With the help of automated manual transmission (AMT), the power demand and size of the traction motor of electric vehicles (EVs) could be reduced and such EVs will have more chances to work within the high efficiency area of motor. To further improve the performance and intelligent level of EVs equipped with AMT, the drivability, energy economy and driver’s performance expectation need to be considered together, and meanwhile, the efficiency of the motor and the gearbox should be taken into account. This investigation aims to optimize the gearshift schedule for EVs considering multi-performance, driver’s intention and efficiency of the whole drivetrain. Methodology An efficiency model of the drivetrain including the traction motor and the gearbox is established using neural network, which consists of one sub-efficiency model for the motor, and one sub-efficiency model for each gear. The latter takes the input torque and the input speed of gearbox as input, and the efficiency of gearbox as output. Based on a linear decreasing weight particle swarm optimization (LDWPSO) algorithm, a new gearshift schedule optimization method considering the drivability, energy economy, and driver’s performance expectation, in which the efficiency model of the whole drivetrain is used to calculate the vehicle performance indexes and the efficiency constraint, is put forward. The proposed method is then used to optimize the personalized intelligent multi-performance optimal gearshift schedules for a test EV equipped with AMT. The proposed method and the vehicle performance using the optimized gearshift schedules have also been evaluated via simulation experiments. Results The neural network-based efficiency model of the drivetrain of electric vehicle could build a precise mathematic mapping between the operating conditions and the efficiency of the drivetrain. The optimized gearshift schedule considering multi-performance, driver’s performance expectation and efficiency of drivetrain could make the electric vehicle have better energy economy and driving range and meanwhile maintain good drivability in line with the driver’s intention. Limitations of this study The energy conversion efficiency of the EV battery has not been included in the efficiency model of the drivetrain in this investigation. Further investigation regarding this issue based on battery performance test, will be part of our future work. What does the paper offer that is new in the field including in comparison to other work by the authors? The efficiency model of EV drivetrain including traction motor and gearbox, as well as the proposed optimization method for the personalized intelligent gearshift schedule for EVs equipped with AMT are new. Conclusions A neural network-based efficiency model of EV drivetrain including traction motor and gearbox has been established, and a novel optimization method based on a linear decreasing weight particle swarm optimization algorithm for personalized intelligent gearshift schedule for EVs equipped with AMT has been proposed. Simulation results show that the proposed method is applicable to improve the comprehensive performance of EVs including drivability and energy economy according to driver’s performance expectation.

Prof. Dr. Xiaofeng Yin, Xihua University, CHINA Mr. Kexu Chen, Xihua University, CHINA Mr. Chao Sun, Zhitong Testing Technology Co., Ltd, CHINA Mr. Chang Dou, Xihua University, CHINA Dr. Xiaohua Wu, Xihua University, CHINA Prof. Dr. Yulong Lei, Jilin University, CHINA

Personalized Intelligent Gearshift Schedule Optimization for Electric Vehicles with AMT Considering Multi-performance and Drivetrain Efficiency

F2020-ADM-007 • Paper + Video • FISITA World Congress 2021 • ADM - Advanced Vehicle Driveline and Energy Management


Sign up or login to the ICC to download this item and access the entire FISITA library.

Upgrade your ICC subscription to access all Library items.

Congratulations! Your ICC subscription gives you complete access to the FISITA Library.


Retrieving info...

Available for purchase on the FISITA Store


bottom of page