Prediction of rubber fatigue life using an assimilation-based learning approach and incremental crack propagation model

Abstract

Accurately and efficiently predicting the fatigue life of rubber materials has beena long-standing challenge due to limited understanding of the fatigue mechanism.In this study, a variational assimilation-based machine learning method assistedwith incremental crack propagation model is proposed to predict the fatigue lifeof rubber materials. Firstly, according to the fracture mechanics theory, a newrubber fatigue life prediction model based on incremental crack propagation andsparse experimental data is established, which owns higher accuracy than theclassical crack energy density model. Further, a rubber fatigue life solver coupled incremental crack propagation model and nonlinear finite element method isintroduced to generate a dense fatigue life dataset of rubber materials with highaccuracy. Finally, the artificial neural network model is trained, cross-validatedand tested using the dense dataset, and the three-dimensional variational assimilation model is employed to merge the predicted values of artificial neural networkwith experimental data. By comparing against the experimental data, the effectiveness of the proposed method was verified, thereby we offer an accurate andefficient approach to predict the rubber fatigue life.