Energy Consumption Prediction for Fused Deposition Modelling 3D Printing Using Machine Learning

Additive manufacturing (AM) technologies are growing more and in the industry; increase world energy consumption encourages quantification optimization of use additive processes. Orientation part to be printed is very important for reducing consumption. Our work focuses on defining most appropriate direction minimizing In this paper, twelve machine learning (ML) algorithms applied model fused deposition modelling (FDM) process using a database FDM 3D printing isovolumetric mechanical components. The adequate predicted was selected four performance criteria: mean absolute error (MAE), root squared (RMSE), R-squared (R2), explained variance score (EVS). It clearly seen that Gaussian regressor (GPR) estimates with high accuracy: R2 > 99%, EVS MAE < 3.89, RMSE 5.8.