Predicting the ultimate tensile strength of AISI 1045 steel and 2017-T4 aluminum alloy joints in a laser-assisted rotary friction welding process using machine learning: a comparison with response surface methodology

Welding metal alloys with dissimilar melting points makes conventional welding processes not feasible to be used. Friction welding, on the other hand, has proven a promising technology. However, obtaining welded joint’s mechanical properties characteristics similar base materials remains challenge. In development of this work, several machine learning (ML) regressors (e.g., Gaussian process, decision tree, random forest, support vector machines, gradient boosting, and multi-layer perceptron) were evaluated for prediction ultimate tensile strength (UTS) in joints AISI 1045 steel 2017-T4 aluminum alloy produced by rotary friction laser assistance. A mixed design experiments was employed assess effect rotation speed, pressure, power over UTS. Furthermore, response surface methodology (RSM) determine an empirical equation predicting UTS, contours maps main interactions. total 48 specimens train regressors; 5-fold cross-validation used find algorithm greater precision. The boosting regressor (GBR), (SVR), present highest precision less than 3% percentage error laser-assisted process. GBR SVR capability exceed RSM’s accuracy coefficient determination (R2) 90.9 versus 83.2%, respectively.