Explainable Artificial Intelligence (XAI) and Supervised Machine Learning-based Algorithms for Prediction of Surface Roughness of Additively Manufactured Polylactic Acid (PLA) Specimens

Structural integrity is a crucial aspect of engineering components, particularly in the field additive manufacturing (AM). Surface roughness vital parameter that significantly influences structural additively manufactured parts. This research work focuses on prediction surface additive-manufactured polylactic acid (PLA) specimens using eight different supervised machine learning regression-based algorithms. For first time, explainable AI techniques are employed to enhance interpretability models. The nine algorithms used this study Support Vector Regression, Random Forest, XGBoost, AdaBoost, CatBoost, Decision Tree, Extra Tree Regressor, Explainable Boosting Model (EBM), and Gradient Regressor. analyzes performance these predict PLA specimens, while also investigating impacts individual input parameters through methods. experimental results indicate XGBoost algorithm outperforms other with highest coefficient determination value 0.9634. demonstrates provides most accurate predictions for compared comparative analysis all study, along insights derived from techniques.