Gear-shift decision-making is the key to affect the power, economy and comfort of the vehicle. At present, gear-shift decision-making mostly relies on manual calibration, and it is impossible to make reasonable decisions based on real-time changes in driving intentions. The degree of intelligence needs to be improved. This paper proposes an online gear-shift decision-making method considering the driving intention. Based on the theoretical framework of model predictive control, in the predicting horizon, the multi-layer perception machine is used to predict the short-term vehicle states, and K-means clustering and deep belief network method are used to classify and recognize driving intentions. A gear-shift decision-making optimization model considering the fuel consumption and the driving intention is built in the predicting horizon, and the optimal gear-shift decision-making sequence is solved by the dynamic programming algorithm. The simulation and experiments show that the proposed online gear-shift decision-making method can improve the vehicle’s adaptability to driving behavior while saving fuel, so as to improve the intelligence of the gear-shift decision-making of the vehicle.
Online Intelligent Gear-Shift Decision of Vehicle Considering Driving Intention Using Moving Horizon Strategy
Mechan. Machine Science
IFToMM Asian conference on Mechanism and Machine Science ; 2021 ; Hanoi, Vietnam December 15, 2021 - December 18, 2021
2021-12-15
11 pages
Article/Chapter (Book)
Electronic Resource
English
Moving horizon shared steering strategy for intelligent vehicle based on potential-hazard analysis
IET | 2018
|Moving horizon shared steering strategy for intelligent vehicle based on potential‐hazard analysis
Wiley | 2019
|Driving control method for gear shift of electric vehicle
European Patent Office | 2021
|