Design of Extended Kalman Filter Speed Estimator and Single Neuron-Fuzzy Speed Controller for Sensorless Brushless DC Motor

Abstract

Methods of estimation and control of BLDC presented in this paper. Because BLDCM is a motor without a brush then BLDC requires the sensor position to rotate the rotor and this is a weakness of the BLDC. A sensorless algorithm of Extended Kalman Filter (EKF) was proposed to cover this weakness. Additionally, BLDC is also a non-linear system. Thus, it is difficult to obtain accurate and good value PID parameter controller with a conventional PID method. In this paper, a single neural network - Fuzzy PID for BLDC developed. The experimental results show that the EKF is able to estimate the speed of the BLDC and single neural networks - Fuzzy PID controller makes BLDC system faster.