A neural network controller for indirect field orientation control

This paper presents the design of a neural network controller for the stator current command in an indirect field oriented system. A particular three layer neural network structure is studied in some detail. This neural network controller has two outputs, stationary frame q and d axis current commands i_qs^s and i_ds ^s. The input to the neural network are synchronous frame q and d axis current commands, delayed stationary frame q and d axis terminal voltage, rotor speed and delayed values of these parameters. The neural network structure, training and input output selection are discussed. A computer simulation of the closed loop indirect field oriented system with the neural network controller is also presented to verify the feasibility of such a controller