An improved BP neural network PID controller system was designed for high precision requirement of actual brushless DC motor position control; the position of brushless DC motor can be precisely controlled. This system combines the merits of neural network and PID controller, and is suitable for complicated brushless DC motor system which contains non-linear and time variable characteristics. The result of simulation illustrate that the improved BP neural network PID controller is better than the traditional BP neural network PID controller and the traditional PID controller. This method's feasibility was testified