The chemical vapor infiltration(CVI) process in fabrication of carbon-carbon composites is very complex and highly inefficient, which adds considerably to the cost of fabrication and limits the application of the mate...The chemical vapor infiltration(CVI) process in fabrication of carbon-carbon composites is very complex and highly inefficient, which adds considerably to the cost of fabrication and limits the application of the material. This paper tries to use a supervised artificial neural network(ANN) to model the nonlinear relationship between parameters of isothermal CVI(ICVI) processes and physical properties of C/C composites. A model for preprocessing dataset and selecting its topology is developed using the Levenberg-Marquardt training algorithm and trained with comprehensive dataset of tubal C/C components collected from experimental data and abundant simulated data obtained by the finite element method. A basic repository on the domain knowledge of CVI processes is established via sufficient data mining by the network. With the help of the repository stored in the trained network, not only the time-dependent effects of parameters in CVI processes but also their coupling effects can be analyzed and predicted. The results show that the ANN system is effective and successful for optimizing CVI processes in fabrication of C/C composites.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.50072019)the Aeronautical Foundation of China under Grant No.99G53092
文摘The chemical vapor infiltration(CVI) process in fabrication of carbon-carbon composites is very complex and highly inefficient, which adds considerably to the cost of fabrication and limits the application of the material. This paper tries to use a supervised artificial neural network(ANN) to model the nonlinear relationship between parameters of isothermal CVI(ICVI) processes and physical properties of C/C composites. A model for preprocessing dataset and selecting its topology is developed using the Levenberg-Marquardt training algorithm and trained with comprehensive dataset of tubal C/C components collected from experimental data and abundant simulated data obtained by the finite element method. A basic repository on the domain knowledge of CVI processes is established via sufficient data mining by the network. With the help of the repository stored in the trained network, not only the time-dependent effects of parameters in CVI processes but also their coupling effects can be analyzed and predicted. The results show that the ANN system is effective and successful for optimizing CVI processes in fabrication of C/C composites.
