Adaptive neural network-based active disturbance rejection servo control of a phase change energy storage device

Tong Liu

doi:10.1117/12.2685465

15 August 2023 Adaptive neural network-based active disturbance rejection servo control of a phase change energy storage device

Tong Liu

Author Affiliations +

Proceedings Volume 12719, Second International Conference on Electronic Information Technology (EIT 2023); 1271947 (2023) https://doi.org/10.1117/12.2685465
Event: Second International Conference on Electronic Information Technology (EIT 2023), 2023, Wuhan, China

Abstract

To minimize the impact of servo system variable load disturbance on position control accuracy in phase change energy storage device, an active disturbance rejection controller based on adaptive radial basis function neural network (RBFNN-ADRC) is proposed. The mathematical model of servo system position is derived, and the classical ADRC is designed. The ADRC structure is analysed, and the actual physical meaning of the parameters is given for adjustment. Subsequently, in order to address the problem of low disturbance estimation accuracy of ESO with classical ADRC fixed parameters, RBFNN is introduced to adjust ESO parameters online and embed adaptive ESO into ADRC. Also, the learning speed of RBFNN is promoted to exponential decay to ensure that the global optimal value can be found. The simulation results exhibit that the RBFNN-ADRC control law has better anti-interference ability, robustness and tracking accuracy compared with the classical PID and ADRC control methods.

Citation Download Citation

Tong Liu "Adaptive neural network-based active disturbance rejection servo control of a phase change energy storage device", Proc. SPIE 12719, Second International Conference on Electronic Information Technology (EIT 2023), 1271947 (15 August 2023); https://doi.org/10.1117/12.2685465

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