Buck converter conduction mode switching control method based on neural network

The invention discloses a Buck converter conduction mode switching control method based on a neural network, and the method comprises the steps: building a state space averaging model of a Buck converter, collecting the output voltage and inductive current of the Buck converter under DCM and CCM, substituting the output voltage and inductive current into a state equation, and obtaining precise state models under different working conditions through the back propagation characteristics of the neural network; carrying out EMPC design according to the state model, and generating a visual control law distribution diagram; visual control laws of the DCM and the CCM are collected to serve as training data of a second neural network, neural network output is obtained through forward propagation, and the neural network output is compared with the optimal duty ratio obtained through EMPC to obtain an error; carrying out the high fitting of the EMPC through a second neural network, and completing the offline training;