Shifting control optimisation of automatic transmission with congested conditions identification based on the support vector machine
by Shang Peng; Guangqiang Wu; Kaixuan Chen; Minkai Jiang; Lijuan Ju
International Journal of Vehicle Performance (IJVP), Vol. 9, No. 2, 2023

Abstract: Vehicles in congested conditions are often accompanied by frequent acceleration and deceleration, but also cause the phenomenon of frequent transmission shifting. In this paper, state parameters such as speed, accelerator pedal opening, and brake pedal opening are selected and preprocessed to obtain the relevant features of the vehicle state. Principal component analysis (PCA) is used to reduce the dimension of these features to simplify the computation. Then, a support vector machine (SVM) optimised by the genetic algorithm is used to identify congested conditions. Finally, based on the identification results and vehicle dynamics, the shift curve was corrected to reduce the frequent shifting phenomenon in congested conditions. Through the classification test of the training set and test set, the method used in this paper can effectively identify congested conditions, and the simulation test results show that use of the corrected shift curve can effectively reduce frequent shifting in congested conditions.

Online publication date: Tue, 04-Apr-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Vehicle Performance (IJVP):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com