Statistical Modeling of Wire Arc Additive Manufacturing Parameters Using Regression Analysis

Wire Arc Additive Manufacturing (WAAM) is gaining prominence for fabricating large metal components due to its high deposition rate and cost-effectiveness. However, the quality and performance of WAAM-fabricated parts are strongly influenced by process parameters such as wire feed rate, travel speed, arc voltage, and current. This study presents a statistical modeling approach using regression analysis to predict the effects of these key parameters on critical output responses, including bead geometry, surface roughness, and material deposition rate. Experiments were designed using a structured methodology, and the collected data were analyzed to develop linear and multiple regression models. The accuracy and reliability of the models were evaluated using statistical metrics such as R² and p-values. The results demonstrate that regression-based models can effectively predict WAAM outcomes, enabling process optimization and quality control. This approach provides a valuable tool for manufacturers to fine-tune WAAM parameters for consistent and high-quality part fabrication.