Optimizing Femtosecond Texturing Process Parameters Through Advanced Machine Learning Models in Tribological Applications

Abstract

Surface texturing plays a vital role in enhancing tribological performance, reducing friction and wear, and improving durability in industrial applications. This study introduces an innovative approach by employing machine learning models—specifically, decision trees, support vector machines, and artificial neural networks—to predict optimal femtosecond laser surface texturing parameters for tungsten carbide tested with WS2 and TiCN coatings. Traditionally, the selection of laser parameters has relied heavily on a trial-and-error method, which is both time-consuming and inefficient. By integrating machine learning, this study advances beyond conventional methods to accurately predict the depth and quality of textured features. The ANN demonstrated superior predictive accuracy among the models tested, outperforming SVM and Decision Trees. This machine learning-based approach not only optimizes the surface texturing process by reducing experimental effort but also enhances the resultant surface performance, making it well-suited for applications in sectors such as automotive and oil and gas.