Computation of the Thermal Residual Stresses in SiC/SiC Composites with Multi-Layered Interphases by Using ANN with the Structure of Random Forest

In this paper, a hybrid strategy incorporating finite element computation, artificial neural network (ANN) method and Random Forest (RF) algorithm is proposed for computation of the thermal residual stresses (TRS) in SiC/SiC composites with multi-layered interphases. The finite element method is adopted to calculate the TRS of the unidirectional SiC/SiC composites. The ANN with the structure of Random Forest (RFANN) is employed to approximate the non-linear relationship between the multi-layered interphases thicknesses and the TRS of the SiC/SiC composites. The well-trained RFANN is finally used to compute the TRS of a unidirectional SiC/SiC composite with six layers of interphases.