Decision Tree Methods for Predicting Surface Roughness in Fused Deposition Modeling Parts.

Barrios Barrios,Romero Romero

doi:10.3390/ma12162574

Abstract

3D printing using fused deposition modeling (FDM) includes a multitude of control parameters. It is difficult to predict a priori what surface finish will be achieved when certain values are set for these parameters. The objective of this work is to compare the models generated by decision tree algorithms (C4.5, random forest, and random tree) and to analyze which makes the best prediction of the surface roughness in polyethylene terephthalate glycol (PETG) parts printed in 3D using the FDM technique. The models have been created using a dataset of 27 instances with the following attributes: layer height, extrusion temperature, print speed, print acceleration, and flow rate. In addition, a dataset has been created to evaluate the models, consisting of 15 additional instances. The models generated by the random tree algorithm achieve the best results for predicting the surface roughness in FDM parts.

Highlights

Additive manufacturing or 3D printing techniques allow small batches of parts to be produced directly, economically, and flexibly [1]
fused deposition modeling (FDM) printers offer a large number of print parameters: print temperature, layer height, print speed, print acceleration, and flow rate, among others
Data mining techniques are used to improve the quality of processes and products based on data gathered from previous experiences [7,8,9]: they are used to find out which parameters are most influential in surface finishing in electrical discharge machining (EDM) processes [10]

Summary

Introduction

Additive manufacturing or 3D printing techniques allow small batches of parts to be produced directly, economically, and flexibly [1]. Data mining techniques are used to improve the quality of processes and products based on data gathered from previous experiences [7,8,9]: they are used to find out which parameters are most influential in surface finishing in electrical discharge machining (EDM) processes [10]. They are used to predict the wear of a tool in milling processes [11] or to increase the accuracy of high-speed machining of titanium alloys [12]

Objectives

Methods

Results

Discussion

Conclusion