Transfer Models and Standard Models for Predicting Wear-Rates on the Basis of Friction Noise: A Comparative Study

Abstract

Under varying working conditions, friction between polymers and metals leads to surface wear of materials, accompanied by significant energy dissipation, part of which transforms into friction noise. Despite their high nonlinearity, friction noises share certain commonalities in their generation mechanisms. This study proposes a novel transfer mapping model, which, after modeling a specific pair, can predict the behavior of other pairs. We simplify the model through Pearson feature selection and employ decision tree-based algorithms (decision tree, extreme gradient boosting, categorical boosting) to model the transfer mapping. By comparing the performance of standard models with transfer models, we identify the optimal approach for constructing the transfer model by using the categorical boosting algorithm.