EUVIMEDEUVIMED entdecken
Open Access

Anomaly Detection in Fused Filament Fabrication Using Machine Learning

Guo Dong Goh iD, Nur Muizzu Bin Hamzah, Wai Yee Yeong

3D Printing and Additive Manufacturing · 01.06.2023 · 10 (3) · 428-437

DOI: 10.1089/3dp.2021.0231 ↗

Kurz gefasst

Fachartikel in der Zeitschrift 3D Printing and Additive Manufacturing, erschienen am 01.06.2023. Verfasst von Guo Dong Goh und 2 weiteren Autor:innen. Beteiligte Einrichtung: Singapore Centre for 3D Printing, School of Mechanical & Aerospace Engineering, Nanyang Technological University Singapore, Singapore, Singapore. Die Arbeit wurde bisher 80-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fused filament fabrication (FFF) has been widely used in various industries, and the adoption of technology is growing significantly. However, the FFF process has several disadvantages like inconsistent part quality and print repeatability. The occurrence of manufacturing-induced defects often leads to these shortcomings. This study aims to develop and implement an on-site monitoring system, which consists of a camera attached to the print head and the laptop that processes the video feed, for the extrusion-based 3D printers incorporating computer vision and object detection models to detect defects and make corrections in real-time. Image data from two classes of defects were collected to train the model. Various YOLO architectures were evaluated to study the ability to detect and classify printing anomalies such as under-extrusion and over-extrusion. Four of the trained models, YOLOv3 and YOLOv4 with "Tiny" variation, achieved a mean average precision score of >80% using the AP50 metric. Subsequently, two of the models (YOLOv3-Tiny 100 and 300 epochs) were optimized using Open Neural Network Exchange (ONNX) model conversion and ONNX Runtime to improve the inference speed. A classification accuracy rate of 89.8% and an inference speed of 70 frames per second were obtained. Before implementing the on-site monitoring system, a correction algorithm was developed to perform simple corrective actions based on defect classification. The G-codes of the corrective actions were sent to the printers during the printing process. This implementation successfully demonstrated real-time monitoring and autonomous correction during the FFF 3D printing process. This implementation will pave the way for an on-site monitoring and correction system through closed-loop feedback from other additive manufacturing (AM) processes.

Schlagwörter

Stichwörter der Autor:innen

3D printingartificial intelligentfused deposition modelingin situ monitoringsupervised learning

Autor:innen und Institutionen

  • Singapore Centre for 3D Printing, School of Mechanical & Aerospace Engineering, Nanyang Technological University Singapore, Singapore, Singapore.
  • HP-NTU Digital Manufacturing Corporate Lab, Nanyang Technological University, Singapore, Singapore.
  • NTU Institute for Health Technologies, Nanyang Technological University, Singapore, Singapore.

ORCID-Profile: Guo Dong Goh

Zitieren

APA

Goh, G. D., Hamzah, N. M. B., & Yeong, W. Y. (2023). Anomaly Detection in Fused Filament Fabrication Using Machine Learning. 3D Printing and Additive Manufacturing, 10(3), 428-437. https://doi.org/10.1089/3dp.2021.0231

Vancouver

Goh GD, Hamzah NMB, Yeong WY. Anomaly Detection in Fused Filament Fabrication Using Machine Learning. 3D Printing and Additive Manufacturing. 2023;10(3):428-437. doi:10.1089/3dp.2021.0231

BibTeX
@article{Goh2023,
  author = {Goh, Guo Dong and Hamzah, Nur Muizzu Bin and Yeong, Wai Yee},
  title = {Anomaly Detection in Fused Filament Fabrication Using Machine Learning},
  journal = {3D Printing and Additive Manufacturing},
  year = {2023},
  volume = {10},
  number = {3},
  pages = {428--437},
  doi = {10.1089/3dp.2021.0231}
}
Kostenlos starten →