Radial basis function neural network–based adaptive sliding mode suspension control for maglev yaw system of wind turbines

Abstract

The maglev yaw system of wind turbines adopts maglev-driving technology instead of traditional gear-driving technology. It has many advantages, such as no lubrication, simple structure, and high reliability. However, the stable suspension control of maglev yaw system is difficult to achieve due to the unknown disturbance caused by crosswind in a practical environment. In this article, an adaptive sliding mode cascade controller based on radial basis function neural network is proposed for the stable suspension control of maglev yaw system. First, the dynamic mathematical model of maglev yaw system is established. Second, an adaptive sliding mode robust controller using radial basis function neural network is designed as the outer loop air gap tracking controller for precise position control, where radial basis function neural network is employed to estimate the unknown parameter containing disturbance. To eliminate the limitation of the traditional exponential approach law based on sign function in the sliding mode control, an exponential reaching law based on hyperbolic tangent function is introduced to guarantee the smooth suspension control of maglev yaw system. Third, an adaptive controller as the inner loop current tracking controller is designed. Finally, the corresponding simulations and analysis are carried out. The simulation results show that the proposed controller can guarantee the suspension stability of maglev yaw system and suppress the disturbance effectively. Compared with the cascade proportional–integral–derivative controller and improved double power reaching law integral sliding mode controller, the proposed controller has a faster dynamic response and stronger robustness in the presence of unknown external disturbance.