Related Experiment Videos
Adaptive neural control for a class of nonlinearly parametric time-delay systems
Daniel W C Ho1, Junmin Li, Yugang Niu
1Department of Mathematics, City University of Hong Kong, Kowloon, Hong Kong. madaniel@cityu.edu.hk
IEEE Transactions on Neural Networks
|June 9, 2005
Summary
This study introduces an adaptive neural controller for time-delay nonlinear systems. The novel approach ensures system stability and overcomes common control issues, demonstrating reliable performance.
Area of Science:
- Control Systems Engineering
- Nonlinear Dynamics
- Artificial Intelligence in Engineering
Background:
- Time-delay nonlinear systems present significant control challenges due to their complex dynamics and inherent instabilities.
- Unknown nonlinearities and potential controller singularities complicate the design of effective control strategies for these systems.
Purpose of the Study:
- To propose a novel adaptive neural controller for a class of time-delay nonlinear systems with unknown nonlinearities.
- To address and overcome the controller singularity problem inherent in such systems.
- To guarantee the semiglobal boundedness of signals within the adaptive closed-loop system.
Main Methods:
- Utilized a wavelet neural network (WNN) for online approximation of system nonlinearities.
- Developed a state feedback adaptive controller.
- Constructed a novel integral-type Lyapunov-Krasovskii functional to ensure stability and overcome singularity issues.
Main Results:
- The proposed adaptive neural controller effectively handles unknown nonlinearities in time-delay systems.
- The integral-type Lyapunov-Krasovskii functional successfully circumvents controller singularity.
- Demonstrated semiglobal boundedness of all signals in the adaptive closed-loop system.
Conclusions:
- The developed adaptive neural control strategy provides a robust solution for time-delay nonlinear systems.
- The method ensures system stability and performance, validated by theoretical guarantees and an illustrative example.