Stainless steel has unique material properties that made these materials ideal in many areas such as in tanks and storage vessels for corrosive liquids, in the chemical and petrochemical industry, in steam boilers, in the paint industry, in food plants, in mining. Such types of materials require final operations (finish process) for precise dimensions and good surface quality. Machining is one of the most effective methods for shaping the long-lasting materials used in common area. This paper focuses on the machinability study of 316L steels in both experimental and machine learning based data evaluation approach. A series of turning experiments were conducted under dry and MQL environments with different cutting parameter (cutting Speed, feed rate and depth of cut) combinations. The outcomes of this study were cutting forces, cutting temperatures and energy consumption. Machine learning-based models (decision tree and prediction model) have predicted cutting force and cutting temperature with high accuracy in dry and MQL environments using cutting speed, feed rate, and depth of cut. The lower error values and higher R² coefficients obtained, particularly under MQL conditions, demonstrate the model's stability and effectiveness in machinability analysis. In the developed machine learning models, the R² value for cutting force reached 0.975, and for temperature it reached 0.957. RMSE values were obtained in the range of 4.03–4.87 and 2.76–3.32, respectively. Because the study combines both experimental and machine learning methods, it will be helpful for future research in machinability experiments.
Kartal et al. (Wed,) studied this question.