In this paper a novel neural network based intelligent adaptive controller, which consists of an online growing dynamic Radial Basis Function Neural Network (RBFNN) along with a Model Reference Adaptive Control (MRAC), is proposed. RBFNN controller is used to approximate a nonlinear function and the MRAC controller adapts when plant parametric set changes. Both these controllers augment each other working in a modular manner. Moreover, the adaptive laws are derived based on a Lyapunov function candidate making the algorithms unique in nature. Tuning of the RBFNN width, centers and weights are derived in order to ensure the error reduction and for improved tracking accuracy. Main advantage and uniqueness of the proposed scheme evolves from controller's ability to complement each other in case of parametric and functional uncertainty. Theoretical results are validated by conducting simulation studies on a nonlinear fighter aircraft model for pitch rate control of continuously changing reference pattern.
Stable intelligent adaptive controller design for pitch-rate command control
2007
6 Seiten, 13 Quellen
Aufsatz (Konferenz)
Englisch
Design of Pitch Angle Rate Control Law Based on L1 Adaptive Control Theory
Springer Verlag | 2023
|A Direct Adaptive Neural Command Controller Design for an Unstable Helicopter
British Library Conference Proceedings | 2005
|