Title: Automated quality detection of resource efficient 3D printing

Authors: Purvee Bhatia; Donald McCleeary; Nancy Diaz-Elsayed

Addresses: Smart and Sustainable Systems Laboratory (S3 Lab), Department of Mechanical Engineering, University of South Florida, 4202 E. Fowler Avenue, ENG 030, Tampa, FL 33620-5350, USA ' Smart and Sustainable Systems Laboratory (S3 Lab), Department of Mechanical Engineering, University of South Florida, 4202 E. Fowler Avenue, ENG 030, Tampa, FL 33620-5350, USA ' Smart and Sustainable Systems Laboratory (S3 Lab), Department of Mechanical Engineering, University of South Florida, 4202 E. Fowler Avenue, ENG 030, Tampa, FL 33620-5350, USA

Abstract: Image processing and machine learning were applied to detect production quality characteristics of parts printed via fused deposition modelling. The influence of the nozzle temperature, infill density, and feed rate on the surface roughness and energy consumption of the printed parts was analysed. The surface roughness of the printed parts was predicted using a fine tree machine learning model; the infill density and feed rate were positively correlated to energy consumption, while temperature had little effect on energy consumption. Process parameters for 3D printing are recommended to achieve the desired surface quality, while avoiding print failure and excess energy consumption.

Keywords: additive manufacturing; sustainability; image processing; energy consumption.

DOI: 10.1504/IJSM.2022.134549

International Journal of Sustainable Manufacturing, 2022 Vol.5 No.2/3/4, pp.200 - 216

Received: 02 Jan 2022
Received in revised form: 13 Oct 2022
Accepted: 31 Jan 2023
Published online: 27 Oct 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article