Equal-diameter porous plate structure parameter prediction and optimization method based on deep learning

The invention discloses an equal-diameter porous pore plate structure parameter prediction and optimization method based on deep learning. The method mainly comprises the following steps: S100, analyzing parameter independence of two layers of equal-diameter porous pore plates; s200, performing a large amount of CFD simulation to obtain performance parameters of the equal-diameter porous plate; s300, input and output parameters of the deep learning model are determined, and original data are subjected to normalization processing and then divided into a training set and a verification set; s400, constructing a multi-layer deep learning network model; s500, training and verifying the deep learning model; and S600, parameters of the equal-diameter porous plate are optimized in combination with a genetic algorithm. According to the method, the performance parameters of the equal-diameter porous pore plate under different measurement working conditions and structure parameter conditions are obtained through a larg