Neural network control of electric vehicle based on position-sensorless brushless DC motor

Based on analyzing the principle of position- sensorless control for brushless DC motor (BLDCM), a control system employing back-EMF method was designed for the position-sensorless electric vehicle (EV). In order to eliminate the influence on back-EMF detection circuit from motor neutral point and RC filter, the system disconnected the reference point of detection circuit from battery cathode, and did the phase- shifting compensation of back-EMF. To improve the stability and reliability of the system, neural network PID (NNPID) control algorithm was researched and applied to the system. The controller comprises a back propagation (BP) NN and a radial basis function (RBF) NN. The former is used to adaptively adjust the parameters of the PED controller on-line. The later is used to establish nonlinear prediction model and perform parameter prediction. The experimental results show that the control system of position-sensorless EV can overcome the disturbance of phase shifting, successfully achieve position-sensorless commutation control and replace Hall sensors. In addition, when using NNPID controller, the control system is superior to that using traditional PID controller at response speed, steady-state tracking error and resisting perturbation in the driving process.