Machine Learning-Based Prediction of Tensile Strength and Hardness in GTAW-Welded IS 2062 E250 Mild Steel Under Varying Heat Input

Abstract

Gas Tungsten Arc Welding (GTAW) joints in structural mild steel exhibit a nonlinear, current-dominated relationship between tensile strength, hardness, and heat input that is difficult to capture using classical linear regression. A 16-run Taguchi L16 experimental design was conducted on IS 2062 Grade E250 mild steel (current: 120–150 A; voltage: 10–16 V), with heat input for each run (1.20–2.40 kJ/mm) calculated using the standard heat-input equation. Six regression algorithms Linear Regression, Decision Tree, Random Forest, Support Vector Regression (SVR), XGBoost, and Artificial Neural Network (ANN) were trained and evaluated using leave-one-out cross-validation (LOOCV), which is statistically appropriate for the limited sample size. XGBoost produced the most accurate tensile-strength predictions (R² = 0.953, RMSE = 19.71 MPa), while the ANN achieved the best hardness predictions (R² = 0.992, RMSE = 0.63 HB). In contrast, linear regression performed poorly for tensile strength (R² = −0.099) because the relationship peaked at 130 A rather than varying monotonically with current. ANOVA identified welding current as the statistically dominant factor influencing both responses (p < 0.001). The findings demonstrate that tree-based and neural-network models substantially outperform conventional linear regression for modelling nonlinear GTAW response surfaces, even with a limited dataset, providing a practical and cost-effective approach for pre-screening welding parameters prior to experimental validation, while highlighting the need for future validation using larger, replicated datasets.