Communication science et technologie

Artificial Intelligence Predicted Maximum Temperature In Friction Stir Welding Of Aa3003

2026-11-08

Auteurs : Belaribi Amina . Chekalil Ismail . Miloudi Abdelkader . Adjoudj Réda .

Résumé

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. To predict these thermal variations, six machine learning models were developed and trained using a dataset composed of 64 experimental trials covering a wide range of process parameters. The models include an SVM, Gaussian process regression, and neural networks. 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. This model achieved an excellent fit on the model development dataset (training + validation + testing), with an RMSE of less than 0.02 °C and an R² close to unity. On the independent external validation sets used for extrapolation assessment, the same model yielded the lowest RMSE of 1.57 °C. This model also stood out for its robustness on unprecedented configurations, 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.

Mots clés

FSW ; AA3003 ; Maximum Temperature