Crack propagation model establishment method and equipment based on data driving and medium

Abstract

The invention discloses a crack propagation model building method and device based on data driving and a medium, and relates to the field of aviation structure fatigue safety design, and the method comprises the steps: obtaining multi-source crack propagation experiment data, and carrying out the data classification; obtaining an initial crack propagation model containing an unknown correction term; randomly constructing a plurality of function expression forms of the primary function in the correction term according to a preset operator and a terminator; substituting the constructed primary function into the initial crack propagation model to obtain an alternative crack propagation model; forming an initial crack propagation model population by using the alternative crack propagation models; and carrying out evolution on individuals in the initial crack propagation model population by adopting gene crossover and mutation behaviors, fitting model parameters of each individual according to the crack propagation experimental data of each category, and calculating an evaluation index of each individual so as to screen out an optimal crack propagation model. According to the method, reliable learning can be carried out based on multi-source crack propagation experimental data to obtain a unified crack propagation model meeting requirements.

Images