Adaptive structure control framework based on machine learning

YeQing Gu; BaoFu Tang; JinWei Wang

doi:10.1117/12.2661018

16 December 2022 Adaptive structure control framework based on machine learning

YeQing Gu, BaoFu Tang, JinWei Wang

Proceedings Volume 12500, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022); 1250061 (2022) https://doi.org/10.1117/12.2661018
Event: 5th International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 2022, Chongqing, China

Abstract

A two-stage control framework is designed by using classification and regression methods of machine learning. Considering the pitch, azimuth motion and wind load of the antenna array, the sample conditions were established, and the training sample library was established. According to the different types of stage tasks, a variety of machine learning algorithms were selected to compare the prediction accuracy, so as to establish the prediction model respectively, and design the profile control framework. The evaluation set was established by random working conditions to evaluate the method of the control framework. The ACC of active control accuracy was more than 100%, and the control errors of the evaluation set were all less than 2%, demonstrating the effectiveness and feasibility of the adaptive surface control framework.

Citation Download Citation

YeQing Gu, BaoFu Tang, and JinWei Wang "Adaptive structure control framework based on machine learning", Proc. SPIE 12500, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 1250061 (16 December 2022); https://doi.org/10.1117/12.2661018

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