PROJECT TITLE :
Classical work in model reference adaptive control for unsure nonlinear dynamical systems with a radial basis operate (RBF) neural network adaptive part does not guarantee that the network weights keep bounded in a compact neighborhood of the ideal weights when the system signals are not persistently exciting (PE). Recent work has shown, however, that an adaptive controller using specifically recorded information concurrently with instantaneous knowledge guarantees boundedness without PE signals. However, the work assumes fastened RBF network centers, which needs domain data of the uncertainty. Motivated by reproducing kernel Hilbert space theory, we have a tendency to propose an online algorithm for updating the RBF centers to remove the belief. Over and above proving boundedness of the resulting neuro-adaptive controller, a association is made between PE signals and kernel methods. Simulation results show improved performance.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here