Model and analysis of flexural properties of Al_2O_3 ceramic prepared by centrifugal slip casting using BP neural network model

摘要

BP neural network model was developed for prediction of the flexural properties of Al_2O_3 ceramic prepared by centrifugal slip casting. In this paper, the model can well reflect the relationship between the process parameters including solid content of Al_2O_3 ceramic slurries (w), centrifugal acceleration (v), sintering temperature (T) and flexural properties of sintered products including fracture strength (σ) and fracture toughness (K_(IC)). According to the registered BP model, the effects of w, v and T on σ and K_(IC) were analyzed. The predicted results agree with the actual data within reasonable experimental error, which shows that the BP model is a practically very useful tool in the flexural properties prediction of the Al_2O_3 ceramic prepared by centrifugal slip casting. The system reduces the time required for planning and optimizing of centrifugal process parameters.