In order to obtain the stable speed and fast regulation output of brushless DC motor (BLDCM), the control and drive system of BLDCM is designed. The operation principle of BLDCM and the cause of torque ripple are analyzed, and the problem of torque ripple is solved by buck circuit. To solve the problems of slow speed, low precision and difficult parameter adjustment of traditional PID, the BP neural network is used to adjust the parameters of PID. Each module of the system is built and simulated on the MATLAB/Simulink simulation platform. The results show that the designed system has the advantages of fast regulation, small overshoot in the control process, stable speed and less torque fluctuation.