Abstract：The fatigue damage and life prediction of additively manufactured metal material is a hot topic of current research. In this paper, the fatigue life prediction is carried out using a data-driven approach with the typical application of additive manufacturing AlSi10Mg. Considering the limited fatigue test data, a reliable theoretical model and numerical method verified by experiments are used to obtain sufficient fatigue data to make up for the lack of test data. First, a fatigue damage model based on the defect characteristic parameters is proposed, and second, the numerical implementation of the theoretical model is established, and the numerical results are compared with the test results to verify the reliability of the proposed method. Then, the training and prediction of the data-driven model are carried out, and the fatigue life of the additively manufactured AlSi10Mg was predicted by the K nearest neighbor data-driven algorithm. Finally, the variation law of the fatigue life with the internal defects of the additively manufactured and fatigue loads is analyzed in depth, and the influence of the number of the training data and parameters of data-driven model on the prediction accuracy is studied.
2023, Vol. 44 
