Neural networks for control systems: a survey
Automatica (Journal of IFAC)
A course in fuzzy systems and control
A course in fuzzy systems and control
Smooth trajectory tracking of three-link robot: a self-organizingCMAC approach
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Identification and control of dynamic systems using recurrent fuzzy neural networks
IEEE Transactions on Fuzzy Systems
| Hi-index | 0.00 |
The maim idea proposed in this paper is integrating sliding mode control (SMC) theory and cerebellar model articulation controller (CMAC) neural network into fuzzy controller design and the fuzzy control rules can be determined systematically by the sliding condition of the SMC. The advantages of using fuzzy model into CMAC are to improve function approximation accuracy in terms of the weighting coefficients of CMAC. The proposed slide-mode-based fuzzy CMAC (SFCMAC), which results from the direct adaptive approach, has the ability to tune the adaptation parameters in the THEN-part of each fuzzy rule during real-time operation. The weight-update law is derived using a Lyapunov stability analysis that guarantees the stability of the closed-loop system. Simulation results show a satisfactory performance of the proposed control scheme.