Machine learning approach for the prediction of mixed lubrication parameters for different surface topographies of non-conformal rough contacts

Abstract

Purpose This study aims to use a machine learning (ML) model for the prediction of traction coefficient and asperity load ratio for different surface topographies of non-conformal rough contacts. Design/methodology/approach The input data set for the ML model is generated using a mixed-lubrication model. Surface topography parameters (skewness, kurtosis and pattern ratio), rolling speed and hardness are used as input features in the multi-layer perceptron (MLP) model. The hyperparameter tuning and fivefold cross-validation are also performed to minimize the overfitting. Findings From the results, it is shown that the MLP model shows excellent accuracy (R2 > 90%) on the test data set for making the prediction of mixed lubrication parameters. It is also observed that engineered rough surfaces with high negative skewness, low kurtosis and isotropic surface patterns exhibit a significant low traction coefficient. It is also concluded that the MLP model gives better accuracy in comparison to the random forest regression model based on the training and testing data sets. Originality/value Mixed lubrication parameters are predicted by developing a regression-based MLP model. The machine learning model is trained using several topography parameters, which are vital in the mixed-EHL regime because of the lack of regression-fit expressions in previous works. The accuracy of MLP with random forest models is also compared.

An assessment of the effect of surface topography on coefficient of friction for lubricated non-conformal contacts

“…It is believed that understanding the surface topography effect on the CoF by developing a simple and accurate numerical model will helps designing advanced machining processes for producing desired surface topography to achieve significant reduction in the CoF. Also, the present numerical model can be used to generate huge data sets for training of artificial neural network models considering different surface topography as an input, and to predict the optimum surface topography (Prajapati et al, 2023). In the present work, the extensive rheological properties of SQL facilitate the use of advance rheological relations and accurate value of Eyring stress for specified load and temperature (Xu et al, 2023).…”