Degree
Bachelor of Science (B.S.)
Major(s)
Industrial Engineering
Document Type
Immediate Open Access
Abstract
Additive manufacturing (AM) has seen increasing popularity in recent times, owing to its efficiency and high speeds, particularly with processes such as Fused Filament Fabrication (FFF). Input process parameters have large impacts on the final part. Incomplete process parameters, which can occur for a variety of reasons, make tasks such as replicating AM studies difficult. A machine learning model can be trained on in-situ layer-wise images collected during a print to combat this issue, predicting process parameters with sufficient data. In this study, two parameters were tested: infill pattern orientation and extrusion width. Twelve parts were produced per parameter and layer-wise images were collected with a Raspberry Pi camera. Random Forest and Multi-Layer Perceptron classification models were tested, as well as Principal Component Analysis for data preprocessing, using these images as the dataset. The results were analyzed to demonstrate the viability of image analysis and machine learning for parameter prediction.
DOI
https://doi.org/10.54718/EIRX8799
Date Defended
5-1-2025
Funding Source
Bagley College of Engineering Undergraduate Student Research Award
Thesis Director
Dr. Wenmeng Tian
Second Committee Member
Dr. Seunghan Lee
Third Committee Member
Dr. Matthew Peaple
Recommended Citation
Smith, Owen Davis, "FFF Process Parameter Identification with Machine Learning Models" (2025). Honors Theses. 150.
https://scholarsjunction.msstate.edu/honorstheses/150
Rights Statement
"FFF Process Parameter Identification with Machine Learning Models", Copyright 2025 by Owen Smith. This work is licensed under CC BY-NC-ND. Note that in addition to my own works of authorship, this thesis may contain and provide citations to third party content. If your use goes beyond fair use, you would need to contact those rights holders for additional licensing/permissions.
