Machine Learning Model for Predicting Tensile Strength of Aluminium Alloy 5083

Aluminium alloy 5083 is widely employed in various industries owing to its exceptional corrosion resistance, weld-ability, and high strength-to-weight ratio. Accurate prediction of its tensile strength is crucial for improving manufacturing processes and guaranteeing material performance under diverse conditions. This study presents a machine learning (ML) model designed to predict the tensile strength of aluminium alloy 5083, utilizing experimental data as input elements, such as material composition, processing parameters, and environmental variables. Various ML techniques, including Random Forest (RF), Support Vector Machine (SVM), and Gradient Boosting (GB), were evaluated to identify the most efficient predictor. Methods for feature selection were utilized to enhance model performance and clarity. The proposed model exhibited enhanced predictive accuracy, attaining a Mean Absolute Error (MAE) of 2.33 MPa, a Root Mean Squared Error (RMSE) of 2.83 MPa, and a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$R^{2}$</tex> score of 0.94, surpassing traditional regression models. This technology offers a dependable and efficient instrument for manufacturers to forecast and control the tensile strength of aluminium alloy 5083, thereby lowering costs and enhancing product quality.