Selection of additive manufacturing process parameters by using ANOVA and regression analysis

The importance of additive manufacturing is increasing in day-to-day industrial applications due to its versatile uses. Process parameter selection is a tedious trial-and-error task. Supervised machine learning helps researchers use decision models to predict process parameters based on existing process data. The dataset is prepared from the literature, and the collected data are classified into training and testing datasets before the model is developed. The dataset is analyzed for variations using ANOVA, and it is found that there is no significant variation in the data. The dataset has three process parameters: average pressure, temperature, and speed. Regression analysis is performed, regression coefficients are calculated, and the intercept is determined. This analysis is helpful for researchers and 3D printing manufacturers when selecting process parameters effectively. ANOVA isolates statistically significant factors, while regression analysis models their relationships, facilitating the prediction of optimal parameter values for improved additive manufacturing efficiency. This approach streamlines the parameter selection process, reduces trial-and-error iterations, and contributes to consistent quality in additive manufacturing.