As biocompatible metallic materials, titanium and its alloys have been widely used in the orthopedic field due to their superior strength, low density, and ease of processing. However, further improvement in biological response is still required for rapid osseointegration. Here, various Ti surface-treatment technologies were applied: hydroxyapatite blasting, sand blasting and acid etching, anodic oxidation, and micro-arc oxidation. The surface characteristics of specimens subjected to these techniques were analyzed in terms of structure, elemental composition, and wettability. The adhesion strength of the coating layer was also assessed for the coated specimens. Biocompatibility was compared via tests of in vitro attachment and proliferation of pre-osteoblast cells.

In aluminum casting, the temperature of liquid aluminum and the dissolved hydrogen density are crucial factors to be controlled for the purpose of both quality control of molten metal and cost efficiency. However, the empirical and numerical approaches to predict these parameters are quite complex and time consuming, and it is necessary to develop an alternative method for rapid prediction with a small number of experiments. In this study, the machine learning models were developed to predict the temperature of liquid aluminum and the dissolved hydrogen content in liquid aluminum. The obtained experimental data was preprocessed to be used for constructing the machine learning models by the sliding time window method. The machine learning models of linear regression, regression tree, Gaussian process regression (GPR), Support vector machine (SVM), and ensembles of regression trees were compared to find the model with the highest performance to predict the target properties. For the prediction of the temperature of liquid aluminum and the dissolved hydrogen content in liquid aluminum, the linear regression and GPR models were selected with the high accuracy of prediction, respectively. In comparison to the numerical modeling, the machine learning modeling had better performance, and was more effective for predicting the target property even with the limited data set when the characteristics of the data were properly considered in data preprocessing.