DSP-based real-time implementation of a neural network observer and hybrid H∞ Adaptive Controller for servo-motor drives

This paper presents a method for sensorless speed control of a non-salient permanent magnetic synchronous motor (PMSM). Special attention is put on the neural-based strategies and applied to the sensorless PMSM. An embedded hybrid H_infin adaptive controller is implemented for trajectory tracking control of a PMSM servo drive system. The proposed control structure employs neural observer (DRNN) and H_infin tracking controller algorithm to run on the hardware processor of the DSP. The result is a powerful tested for the rapid design and implementation of the controller for a low speed operation conditions. Experimental results are provided to verify the effectiveness of the proposed observer and controller.