DESIGN, DSP IMPLEMENTATION, AND PERFORMANCE OF ARTIFICIAL-INTELLIGENCE-BASED SPEED ESTIMATORS FOR ELECTROMECHANICAL DRIVES

The paper discusses the design and DSP implementation of artificial-in telligence-based (AIB) speed estimators for control applications in el ectromechanical drives. The design and performance of AIB estimators b ased on feedforward and recursive artificial neural networks (ANNs), a ssociative memory networks (AMNs) and neuro-fuzzy networks (NFNs) are compared and discussed. Emphasis is placed on the development of minim al configuration estimators with a view to reducing DSP requirements. It is shown that it is an advantage of the AIB approach to estimator d esign that neither a conventional drive model nor a knowledge of any d rive parameters are required and that an estimate of rotor speed can b e obtained using only measurements of supply voltages and/or currents. The DSP system used is based on the Texas Instruments TMS320C31 mount ed in a host PC. Results are presented for the real-time application t o the speed control of a small DC drive and the estimators are shown t o provide a sufficiently accurate speed estimate resulting in stable, robust, speed control. The DSP requirements and performances of each o f the estimator forms are presented and compared and it is shown that the overheads imposed by implementation of these estimators is small.