کنترل حالت کشویی عصبی برای موتورهای القایی با استفاده از نمونه سازی سریع کنترل

This paper presents a discrete-time sliding mode control synthesis based on a neural network model for a 5 HP induction motor. A recurrent high order neural network (RHONN), trained with an extended Kalman filter (EKF) is used to identify the motor model, which is robust to disturbances and parameter variations. Sliding mode controller is used to force the system to track a speed reference and a flux magnitude. A super-twisting observer is implemented to estimate the magnetic fluxes. The neural control is implemented on a rapid control prototyping (RCP) system, which is composed of a TMS320F28069M MCU and provides an easy transition from the model-based control system synthesis in MATLAB/Simulink to embedded code-based target implementation. Experimental results illustrate the performance of the neural control scheme.