In this article, new nonlinear control techniques based on dynamic neural networks are presented. The authors discuss the implementation of a modified identification algorithm using dynamic neural networks as well as a control law, based on the neural identifier, which eliminates modeling error effects via sliding mode techniques. Simulation and real time results are presented for systems like an inverted pendulum and a full actuated robot manipulator
Published in:
Neural Networks, 1999. IJCNN '99. International Joint Conference on
(Volume:3
)
Date of Conference: 1999