Modeling the Friction Behavior of Low-Carbon Steel Sheets Using Various Machine Learning Algorithms Based on Strip Drawing Test Data

The application of machine learning (ML) methods enables the modeling of sheet metal friction phenomena based on experimental data, allowing for the prediction of the coefficient of friction (CoF) under various operating conditions. The aim of this article is to compare the predictive capability of a wide range of ML algorithms trained on the results of the strip drawing test. The variable parameters in the strip drawing test were sheet orientation, load, sample orientation relative to the sheet rolling direction, and the drawing quality of the low-carbon steel sheet metal. Based on the coefficient of determination (R²) and the root mean squared error (RMSE), it was determined that the best predictive performance was achieved by a trilayer neural network (R² = 0.986, RMSE = 0.0025). It was found that the CoF decreased with increasing countersample surface roughness and load. Meanwhile, the orientation of strip samples relative to the sheet rolling direction had a statistically insignificant effect on the CoF. Based on SHapley Additive exPlanations (SHAP) values, it was shown that the average roughness of the countersamples and the load had the most significant influence on the friction coefficient. This was also confirmed using the F-test and permutation importance analysis of the friction process parameters.