Vehicle collision simulation optimization method based on machine learning

The invention discloses a vehicle collision simulation optimization method based on machine learning. The method comprises the following steps: S1, establishing a whole vehicle collision simulation analysis model; s2, establishing a parameterized file of a design variable, and establishing a corresponding data acquisition workflow; s3, obtaining a calculation result file and sampling data; s4, acquiring collision sampling data containing a collision deformation label; s5, determining value ranges of deformation labels, sample points and design variables participating in machine learning model training; s6, performing machine learning model training; s7, judging whether the prediction precision of the trained machine learning model meets a set threshold value or not and judging whether the number of sample points meets a requirement or not, and if both are met, performing a step S8; otherwise, returning to the step S3; s8, establishing a corresponding numerical optimization workflow; s9, performing numerical o