Aiming at the problem of traditional PID control algorithm is difficult to get ideal control effect, an adaptive PID control algorithm based on BP neural network is proposed. According to the structure and characteristic of BP neural network, introduces the description of improved BP neural network algorithm and the construction of PID controller, then simulates and analyses by example at last. The simulation shows that improved BP neural network PID controller has good control effect, reduces overshoot, has strong anti-interference and increase system robustness, improved BP neural network PID controller is better than traditional PID controller.