Prediction System for Solid Solubility Limits of Ag-, Cu-, Al-, and Mg-Based Alloys Using Artificial Neural Networks and First-Principles Calculations

抄録

A solid solubility prediction system using Hume-Rothery parameters and first-principles calculation to obtain explanatory variables was devised, and the resulting coefficients of determination, R², were compared. When we used the Hume-Rothery parameter, R² was 0.715, and when we used the first-principles calculation results, R² was 0.900, indicating the improved accuracy of prediction. We tested 10-fold cross validation to evaluate the generalization performance of the network. The number of explanatory variables was optimized using the stepwise method. R² was maximized when eight explanatory variables were used. As a result of 10-fold cross-validation, R² of the constructed solid solubility prediction system which uses eight explanatory variables was 0.6993. The mean absolute error for this network was 0.45. The common logarithm value was used as the explained variable. Thus, the solid solubility limit predicted from this network was on an average 0.35 to 2.85 times the true value.

Fig. 9 Comparison between experimental data and the predicted data using 8 explanatory variables after 10-fold cross validation.