Neural networks-based adaptive output-feedback control design for nonlinear systems with dead zone output and uncertain disturbances

Abstract

This work focuses on the issue of neural networks-based adaptive output-feedback control for nonlinear systems with dead zone output and immeasurable states. Radial basis function neural networks (RBFNN) are utilised to approximate the unknown functions and an input-driven filter is used to estimate the immeasurable states. Nussbaum function is employed to address the issue of uncertain virtual control coefficient, which is brought by the dead zone in the output mechanism, and the presented control scheme requires only one adaptive law, making the structure of the controllers very realistic. Based on the approximation capabilities of NNs and the backstepping method, an adaptive controller is designed. Based on the Lyapunov stability theory, all signals in closed-loop systems are semi-globally uniformly ultimately bounded (SGUUB), and the tracking error converges to a small area near the origin. The effectiveness of the proposed adaptive control method is proved with the help of two examples.

Keywords:

• Nonlinear systems
• adaptive control
• radial basis function neural network
• Nussbaum function
• Lyapunov function
• dead zone

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data availability statement

Not applicable.

Additional information

Funding

This work was supported by MATRICS project Grant No. MTR/2021/000478 from the Science and Engineering Research Board (SERB), India.