Adaptive Backstepping Control of Dual-Motor Driving Servo System Based on RBF Neural Network

Zhao, Haibo; Gao, Peng Fei

doi:10.1109/rcae56054.2022.9995855

Cited by 2 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the equation, is the speed before braking, is the braking acceleration, and is the braking displacement. Replace with speed, maximum acceleration, and error , The equation has become , calculate the speed as: (6) To mitigate high-frequency flutter near the zero position, we propose a fractional-order nonlinear control function as follows: (7) In the equation, is the interval length of the linear segment, sgn() is signum function.…”

Section: First-order Disturbance Extended State Observer (Eso)mentioning

confidence: 99%

“…Other methods use radial basis function neural networks (RBFNNs) combined with serial parallel estimation models and dynamic surface design control laws, as in GUO's work [4], or BP neural networks to adjust PID control parameters and to learn the nonlinear part of a state observer, such as in Ding Shuguang's and Zhang Rong's studies [5][6]. Zhao Yan proposed a control strategy based on fuzzy PID and RBF neural networks, which reduces overshoot and improves control accuracy [7]. Li Kuangcheng used RBF neural networks to learn key parameters of ADRC online, improving low-speed control performance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Model Reduction and Neural Network Adaptive Control of Nonlinear Hydraulic System Based on Extended State Observer

Xiang

Cheng

2023

Preprint

View full text Add to dashboard Cite

Hydraulic servo control systems pose significant challenges for controller design due to their nonlinear, time-varying of parameters, inertial force, and susceptibility to external disturbances. Traditional PID control methods struggle to set optimal control parameters, necessitating new approaches. In this study, we construct an Expanded State Observer(ESO) to estimate the external disturbance and uncertainty of modeling, a BP neural network to adaptively adjust PID control parameters and an RBF neural network to identify input and output Jacobian information. Our simulations demonstrate superior disturbance rejection and accurate dynamic tracking capabilities, as well as robust stability under inaccurate hydraulic system parameters and models. By regarding the controlled object as an open-loop basic type, we offer a new, effective approach for adaptive control of these challenging systems.

show abstract

Section: First-order Disturbance Extended State Observer (Eso)mentioning

confidence: 99%