Brushless DC motor speed control based on extreme learning machine (ELM) neural network algorithm

Abstract

Along with the development of electric vehicle technology which is currently increasingly sophisticated and growing very fast. The efforts to develop electric vehicles continue. One of which is using BLOC motors to improve efficiency. This article proposes the Extreme Learning Machine (ELM) method for controlling the BLOC Motor. ELM is a single hidden layer artificial neural networks. The experimental results of the sensor measurement indicated an error value compared to the measurement tool. The average error of RPM measurement reaches 2.63%, the average error of the current measurement reaches 1.19% and the average error of voltage measurement reaches 1.59%. Acceleration testing by traveling a distance of 200 meters the average current is 1.05 amperes. The average power efficiency test is 101 watts. The results of the efficiency of testing with a track length of 3.3km with a travel time of 10 minutes obtained the results of the efficiency of the vehicle system of 179.34km / kwh.