Support vector regression applied to materials optimization of sialon ceramics

Partial Least Squares (PLS) and Back Propagation Artificial Neural Network (BP-ANN) are widely known machine learning techniques for materials optimization, whereas Support Vector Machine (SVM) is seldom used in materials science. In this paper, Support Vector Regression (SVR), a machine learning technology based on statistical learning theory (SLT), was applied to predict the cold modulus of sialon ceramic with satisfactory results. In a benchmark test, the performances of SVR were compared with those of PLS and BP-ANN. The prediction accuracies of the different models were discussed on the basis of the leave-one-out cross-validation. The results showed that the prediction accuracy of SVR model was higher than those of BP-ANN and PLS models.