27
5. 12. 1996.
Neural network application in sliding mode control systems
Application of neural network controller design in dynamical systems with sliding mode motion is introduced to improve performance of the discrete-time sliding mode system. Neural network controller with learning rule based on sliding mode algorithm, is proposed to assure calculation of unknown part of the equivalent control in the presence of the plant uncertainties. Developed algorithm is robust to parameter variations and external disturbances. The effectiveness of the neural network sliding mode controllers is verified by experiments.