Research and validation of intelligent control strategy for car seat comfort

Changjiang Du; Yunpeng Cong; Yu Qiao

doi:10.1117/12.2644599

10 November 2022 Research and validation of intelligent control strategy for car seat comfort

Changjiang Du, Yunpeng Cong, Yu Qiao

Proceedings Volume 12301, 6th International Conference on Mechatronics and Intelligent Robotics (ICMIR2022); 1230128 (2022) https://doi.org/10.1117/12.2644599
Event: 6th International Conference on Mechatronics and Intelligent Robotics, 2022, Kunming, China

Abstract

Based on Chinese human body characteristics and seat comfort evaluation model, this paper investigates the intelligent regulation model and validation method of car seat comfort applicable to Chinese human body. Consumers input the basic human characteristics parameters (height, weight, gender, age), and the seat position information (slide position, high adjustment position, angle position) can be calculated by using the regulation algorithm, so that the system can control the adjustment state of the seat. In the model building stage, the BP neural network algorithm, Gaussian regression algorithm and SVM prediction algorithm are studied in this paper, and the comparative analysis reveals that the prediction error and the stability of the prediction results can be optimized by using SVM algorithm for the prediction of the three position parameters, which can achieve the optimal prediction effect. In order to verify and optimize the model, a universal body platform is developed in this paper, which combines software and hardware together to verify the effectiveness of the regulation algorithm, and also feeds back and records the micro-secondary regulation data of consumers for subsequent optimization of the model.

Citation Download Citation

Changjiang Du, Yunpeng Cong, and Yu Qiao "Research and validation of intelligent control strategy for car seat comfort", Proc. SPIE 12301, 6th International Conference on Mechatronics and Intelligent Robotics (ICMIR2022), 1230128 (10 November 2022); https://doi.org/10.1117/12.2644599

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available