Total sliding-mode controller for PM synchronous servo motor drive using recurrent fuzzy neural network

In this paper, the dynamic responses of a recurrent-fuzzy-neural-network (R FNN) sliding-mode-controlled permanent-magnet (PM) synchronous servo motor are described. First, a newly designed total sliding-mode control system, w hich is insensitive to uncertainties, including parameter variations and ex ternal disturbance in the whole control process, is introduced. The total s liding-mode control comprises the baseline model design and the curbing con troller design. In the baseline model design, a computed torque controller is designed to cancel the nonlinearity of the nominal plant. In the curbing controller design, an additional controller is designed using a new slidin g surface to ensure the sliding motion through the entire state trajectory. Therefore, in the total sliding-mode control system, the controlled system has a total sliding motion without a reaching phase. Then, to overcome the two main problems with sliding-mode control, i.e., the assumption of known uncertainty bounds and the chattering phenomena in the control effort, an RFNN sliding-mode control system is investigated to control the PM synchron ous servo motor. In the RFNN sliding-mode control system, an RFNN bound obs erver is utilized to adjust the uncertainty bounds in real time. To guarant ee the convergence of tracking error, analytical methods based on a discret e-type Lyapunov function are proposed to determine the varied learning rate s of the RFNN. Simulated and experimental results due to periodic step and sinusoidal commands show that the dynamic behaviors of the proposed control systems are robust with regard to uncertainties.