Air cylinder cover structure size determination method based on BP neural network

The invention discloses a method for determining the structural size of a cylinder cover based on a BP neural network, and belongs to the field of cylinder covers for energy and power engineering and internal combustion engines. A limited number of cylinder cover structure size combinations are obtained through an experimental design method; changing the structure size combinations, obtaining the performance of the cylinder cover under each structure size combination through finite element calculation, and constructing a sample set; dividing the sample set into a training set and a test set; performing forward transmission and reverse transmission cross training on the neural network based on the constructed training set, so as to improve the prediction precision of the neural network on the performance of the cylinder cover; the mapping relation between the cylinder cover structure size and the cylinder cover performance is constructed through a BP neural network, and when the neural network precision is ver