An artificial neural network (ANN) can easily detect and adapt variations in complex and nonlinear systems. This ability enhances the robustness of the estimation model. On the other hand, the sliding mode controller (SMC) ensures that the system stays on a predefined sliding surface, making it less sensitive to uncertainties, disturbances, and nonlinear changes. Thus, an ANN observer–based SMC is proposed and analyzed for a category of nonlinear systems. The ANN observer is designed to estimate unknown states and unknown disturbances. The observer is developed using the structure of a neural network comprising three layers. The ANN observer precisely estimated the states, and the estimation error converges to 0. The SMC controller is developed based on an ANN observer, and convergence of the law is also demonstrated through the Lyapunov theorem. The presented law improves the system's performance. The effectiveness of the controller is demonstrated through simulations on a single‐link robot dynamical model.
Artificial Neural Network–Based Sliding Mode Controller for a Class of Nonlinear System
2025-06-24
14 pages
Article/Chapter (Book)
Electronic Resource
English
Nonlinear Flight Neuro-Controller Design Using Sliding Mode Based Neural Network
British Library Conference Proceedings | 2000
|British Library Online Contents | 2014
|A neural network based sliding mode controller for active vehicle suspension
SAGE Publications | 2007
|A neural network based sliding mode controller for active vehicle suspension
Tema Archive | 2007
|A neural network based sliding mode controller for active vehicle suspension
Online Contents | 2007
|