Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence
Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence
Fast learning in networks of locally-tuned processing units
Neural Computation
Hi-index | 0.00 |
This paper presents a method based on neural networks for achieving fault tolerant control in the PM spherical actuator control scheme. The model of a PM spherical actuator was developed. Tuning rules of the RBF networks which guarantees the stability of the fault system were derived and the on-line fault tolerant control scheme was developed. The control scheme does not need fault detection and diagnosis modules. An application tracking control problem for the tracking errors and Euler angles of an actuator driven by independent stator and rotor pairs is solved by using the controller. The effectiveness of the proposed method is illustrated by performing the simulation of a space trajectory tracking control.