Abstract :
A robust control system using a fuzzy neural network (FNN) is proposed to control a nonlinear toggle mechanism that is driven by a permanent magnet (PM) synchronous servo motor. First, the dynamic model of a motor-toggle servomechanism is introduced. Then, a robust control system is proposed to control the motor-mechanism coupling system for periodic motion. In the robust control system, the FNN controller is the main tracking controller, which is used to mimic a perfect control law, and the compensated controller is proposed to compensate the difference between the perfect control law and the FNN controller. Moreover, an online parameter training methodology, which is derived using the Lyapunov stability theorem and the backpropagation method, is proposed to increase the teaming capability of the FNN. In addition, to relax the requirement for the bound of minimum approximation error, a simple bound estimation algorithm is investigated to control the motor-mechanism coupling system. The effectiveness of the proposed control scheme is verified by both the simulated and experimental results.
Keywords :
Runge-Kutta methods; backpropagation; fuzzy control; fuzzy neural nets; machine control; neurocontrollers; permanent magnet motors; robust control; servomotors; synchronous motors; Lyapunov stability theorem; backpropagation method; compensated controller; dynamic model; fuzzy neural network; learning capability; minimum approximation error; motor-mechanism coupling system; motor-toggle servomechanism; nonlinear toggle mechanism; perfect control law; periodic motion; permanent magnet synchronous servo motor; robust control; tracking controller; Control systems; Couplings; Fuzzy control; Fuzzy neural networks; Nonlinear control systems; Permanent magnet motors; Robust control; Servomechanisms; Servomotors; Synchronous motors;
