Effect of welding parameters and artificial intelligence-based prediction of maximum temperature in friction stir welding of AA3003 alloy

The maximum temperature generated during FSW welding is a key parameter, as it influences microstructural changes and directly impacts the mechanical properties and final quality of the welded joint. The present study highlights the influence of feed rate, rotational speed, and tool inclination angle on the evolution of the maximum temperature generated during friction stir welding (FSW) of aluminum AA3003. Based on 64 experimental trials, six machine learning models were developed, including an SVM, Gaussian process regressions, and neural networks, and used to predict the maximum measured welding temperature. The models were evaluated using standard statistical indicators (RMSE, MAE, R²). The results demonstrate the superiority of the GPR model with a Matérn 5/2 kernel, with an RMSE of less than 0.02 °C and an R² coefficient of determination close to unity. This model proved robust during validation on separate configurations of the 64 learning trials, with a relative error of less than 1.6%. The proposed approach demonstrates the potential of machine learning techniques to model the complex thermal phenomena of FSW accurately and represents a step towards intelligent predictive control of welding processes.