Quick-return servomechanism with adaptive fuzzy neural network control

The dynamic response of an adaptive fuzzy neural network (FNN) controlled q uick-return mechanism, which is driven by a permanent magnet (PM) synchrono us servo motor, is described in this study. The crank and disk of the quick -return mechanism are assumed to be rigid. First, Hamilton's principle and Lagrange multiplier method are applied to formulate the mathematical model of motion. Then, based on the principle of computed torque, an adaptive con troller is developed to control the position of a slider of the quick-retur n servomechanism Moreover, since the selection of control gain of the adapt ive controller has a significant effect on the system performance, an adapt ive FNN controller is proposed to control the quick-return servomechanism I n the proposed adaptive FNN controller, an FNN is adopted to facilitate the adjustment of control gain on line. Simulated and experimental results due to periodic step and sinusoidal commands show that the dynamic behavior of the proposed adaptive FNN control system are robust with regard to paramet ric variations and external disturbances.