Design of Back Propagation Neural Network PID Control for Boost Converter

The PID controller is possibly the most widely used controller in the power conversion system. The reason is that it does not depend on the mathematical model of the controlled object, and it has the advantages of good stability, easy implementation, strong anti-interference ability. However, with the controlled object becoming more and more complex, the traditional PID is difficult to achieve the ideal control performances. With the development of artificial intelligence, the artificial neural network technology is getting increasingly mature, and the adaptive PID control gradually gives play to its unique advantages. It can automatically adjust the system according to the changes of the measured parameters, so that the system could be in its best state at any time. In this paper, a type of on-line tuning controller with nonlinear function based on Back Propagation (BP) neural network combined with PID, defined as BP-PID control, is proposed and studied, setting Boost converter as an example. System modeling and detailed controller design are provided. Finally, the theoretical analysis and controller design are validated by simulation results.