Minimizing thermal residual stresses in ceramic matrix composites by using DE and ANN-based response surface method

The thermal residual stresses (TRS) induced in ceramic matrix composites (CMCs) with multi-layered interphases when cooling down from the processing temperature, have a significant influence on the mechanical behavior and lifetime of CMCs. The objective of this work is to minimize the TRS of the unidirectional CMCs with multi-layered interphases by controlling the interphases thicknesses. A hybrid strategy incorporating finite element computation, artificial neural network (ANN)-based response surface method (RSM) and differential evolution (DE) algorithm is proposed to predict the TRS of CMCs. The finite element method is adopted to calculate the TRS distribution within CMCs and the ANN-based RSM (ANNRSM) is employed to approximate the non-linear relationship between the design parame ters and the TRS of the designed CMCs. The well-trained ANNRSM is finally used to find the minimum TRS. The results show the proposed methodology could estimate the TRS of different design solutions and identify the best one.