Journal
NEUROCOMPUTING
Volume 314, Issue -, Pages 169-176Publisher
ELSEVIER
DOI: 10.1016/j.neucom.2018.04.023
Keywords
Prandtl-Ishlinskii hysteresis; Adaptive neural control; Stochastic pure-feedback systems; Backstepping
Categories
Funding
- National Natural Science Foundation of China [61773072, 61773051, 61673242, 61773073]
- Innovative Talents Project of Liaoning Province of China [LR2016040]
- Taishan Scholar Project of Shandong Province of China
- Shandong Provincial Natural Science Foundation of China [ZR2016FM10]
Ask authors/readers for more resources
This work considers robust adaptive neural-based control of pure-feedback stochastic nonlinear systems with the generalized Prandtl-Ishlinskii hysteresis. The mean-value theorem is employed to handle the non-affine difficulties from the generalized Prandtl-Ishlinskii hysteresis and the pure-feedback systems. By using the radial basis function (RBF) neural networks' universal approximation capability and back-stepping technique, an adaptive neural control scheme with minimum adaptive parameter is developed. The presented controller can guarantee the semi-global boundedness in fourth-moment of all signals of the resulting closed-loop system. Furthermore, the system output is ensured to converge to a small domain of the given trajectories. Simulation results are presented to demonstrate the effectiveness of the scheme. (C) 2018 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available