Sensorless control of Brushless DC motor using Adaptive Neuro Fuzzy Inference algorithm

In this work sensorless control of BLDC Motor is investigated. In conventional control, it is generally required to measure the speed and position of rotor by using the sensors because the inverter phases, acting at any time, must be commutated depending on the rotor position. Sensorless control BLDC Motor involves estimation of parameters of BLDC drive system using Adaptive Neuro Fuzzy Inference system (ANFIS) algorithm. It involves the usage of adaptive neural networks and fuzzy logic for the estimation of rotor position. This method is like a fuzzy inference system with this different that here by using a back propagation tries to minimize the error. The performance of this method is like both Artificial Neural Networks (ANN) and Fuzzy Logic (FL). In both ANN and FL case, the input pass through the input layer (by input membership function) and the output could be seen in output layer. Therefore, ANFIS uses a combination of least squares estimation and back propagation for membership function parameter estimation. The validity of the proposed approach is shown through simulation.