Prediction of Coefficient of Friction and Wear Rate of Stellite 6 Coatings Manufactured by LMD Using Machine Learning

Laser Metal Deposition (LMD) is a Direct Energy Deposition (DED) technique, which uses a laser source to melt the input material layer by layer, creating the desired geometry with high deposition volume.s Due to its ability to produce exceptional surface properties, LMD is widely used in coatings. The present work presents a comparative study of different Machine Learning (ML) architectures derived from the information of the monitoring process of Stellite-6 coatings on AISI 304 substrates, for the prediction of friction coefficient and wear rate. Random Forest (RF), Support Vector Regressor (SVR), and Artificial Neural Networks (ANN) were compared, where RF obtained a score performance of 0.93 for the wear rate and 0.82 for the friction coefficient. The results show that the geometry of the melt pool, i.e. width, length, and eccentricity, has the greatest influence on the forecast.