Application of ANN Back-Propagation for Residual Stress in an Alloy Reinforced Ceramics/Metal Composite

Abstract

Artificial neural network (ANN) back-propagation model was developed to predict the thermal expansion behavior and internal residual strains in reinforced ceramic matrix composites (CMCS).The ANN training model has been used to predict the thermal expansion behavior and internal residual strains, exhibiting excellent comparison with the experimental results. It was concluded that predicted thermal expansion behavior and internal residual strains by the trained neural network model seem more reasonable compared to approximate methods. It is possible to claim that, ANN is fairly promising prediction technique if properly used. Training ANN model was introduced at first. And then the neural network architecture is designed. The performance of system is summarized at last. In order to facilitate the comparisons of predicted values, the error evaluation and mean relative error are obtained. The result shows that the training model has good performance, and the experimental data and predicted data from ANN are in good coherence.