PID Control in the Reactor Temperature Control System Based on BP Neural Network

It is hard to find parameters of proportional, integral and derivative in conventional PID arithmetic and it depends on the accurate mathematical model of the plant. Its adaptability is worse, so the control accuracy of complex process can not be guaranteed. A new method of PID control method based on BP neural network is proposed aiming at the non-linear, strong coupling and uncertainty in reaction kettle temperature control. The algorithm of PID neural network controller and the selection of classical PID parameters are introduced and analyzed. This method is shown to be effective and simple for implementation.