Automatic Generation Fuzzy Neural Network Speed Controller for Permanent-Magnet Synchronous Motor Drive

Abstract

The paper presents an Automatic Generation Fuzzy Neural Network (AGFNN) with improved particle swarm optimization controller suitable for real-time control of the speed control of the permanent magnet synchronous motor (PMSM) to track sinusoidal reference inputs. The parameters learning are done automatic and online, which is based on the supervised gradient decent method using a delta law. Moreover, an improved particle swarm optimization (IPSO) is adopted to adapt the learning rates to improve the learning capability and increase the speed of constringency. The control performance of the proposed method is verified by simulated results.