Sensorless control for brushless DC motor using support vector machine based on Particle swarm optimization

Motor system with mechanical position sensor has lower reliability and higher cost. Sensorless control of brushless DC motor (BLDCM) has been focused recently and many intelligent methods are being tried to realize sensorless control. In this paper, the relationship between rotor position of BLDCM and phase voltages is analyzed firstly. Then, a sensorless control method using support vector machine (SVM) is proposed. In this model, phase voltages are non-linearly mapped to commutation signals. At the same time, the parameters of SVM model are optimized by particle swarm optimization (PSO). Sensorless control of BLDCM was achieved according to the non-linear map relationship established by SVM and got better performance. Experiment results have verified the feasibility and effectiveness of the method proposed in this paper.