Adaptive neural network control of unknown nonlinear affine systems with input deadzone and output constraint

Wei He; Yiting Dong; Changyin Sun

doi:10.1016/j.isatra.2015.05.014

Adaptive neural network control of unknown nonlinear affine systems with input deadzone and output constraint

ISA Trans. 2015 Sep:58:96-104. doi: 10.1016/j.isatra.2015.05.014. Epub 2015 Jul 2.

Authors

Wei He¹, Yiting Dong², Changyin Sun³

Affiliations

¹ School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China.
² School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China.
³ School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China. Electronic address: cys@ustb.edu.cn.

PMID: 26142983
DOI: 10.1016/j.isatra.2015.05.014

Abstract

In this paper, we aim to solve the control problem of nonlinear affine systems, under the condition of the input deadzone and output constraint with the external unknown disturbance. To eliminate the effects of the input deadzone, a Radial Basis Function Neural Network (RBFNN) is introduced to compensate for the negative impact of input deadzone. Meanwhile, we design a barrier Lyapunov function to ensure that the output parameters are restricted. In support of the barrier Lyapunov method, we build an adaptive neural network controller based on state feedback and output feedback methods. The stability of the closed-loop system is proven via the Lyapunov method and the performance of the expected effects is verified in simulation.

Keywords: Barrier Lyapunov Function; Input deadzone; Output constraint; Radial Basis Function Neural Network (RBFNN); Unknown nonlinear affine system.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms
Computer Simulation
Feedback
Neural Networks, Computer*
Nonlinear Dynamics