Machine Learning-Based Prediction of Mechanical Properties in Fused Deposition Modeling Through Optimization of Process Parameters

Abstract

Additive Manufacturing (AM), particularly Fused Deposition Modeling (FDM), has gained significant attention due to its ability to fabricate complex geometries with reduced material waste and production time. However, the mechanical properties of FDM-manufactured components are highly influenced by process parameters such as nozzle temperature, infill density, layer height, printing pattern, and material type. Determining the optimal combination of these parameters through conventional experimental approaches is time-consuming and costly.This study presents a Machine Learning-based framework for predicting the mechanical properties of FDM printed components manufactured using PLA+ and PLA Pro+ materials. A comprehensive experimental dataset was generated by varying critical process parameters and conducting standardized mechanical tests to evaluate Young’s Modulus, Tensile Strength, Compressive Strength, Flexural Strength, Impact Strength, and Hardness. Advanced feature engineering techniques and data preprocessing methods were applied to improve model performance.Multiple machine learning algorithms, including Random Forest Regressor, XGBoost Regressor, Gradient Boosting Regressor, Extra Trees Regressor, and CatBoost Regressor, were developed and evaluated using R² Score, Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). Experimental results demonstrate that ensemble learning models provide reliable prediction capability, with the best-performing model achieving an R² score of approximately 0.67 for multi-output mechanical property prediction. The developed system enables rapid estimation of mechanical properties without extensive physical testing, thereby reducing experimental cost, material consumption, and development time.The proposed approach offers an effective decision-support tool for process optimization, material selection, and quality enhancement in additive manufacturing environments. The integration of machine learning with FDM process parameter optimization contributes toward intelligent manufacturing and Industry 4.0 applications.