PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 25, 20260 citations

Optimization of 3D FDM Printing Parameters Using Deep Learning to Improve Surface Quality and Reduce Print Failures

View Full Paper
NNuryantoAPAndy Alfian Wahyu Pratama

Key Points

  • This research aims to improve surface quality and minimize print failures in FDM printing through deep learning optimization of parameters.
  • Implemented a deep learning framework using Vision Transformer and Swin Transformer models.
  • Collected a dataset of 500 PLA-printed samples integrating surface images and numerical printing parameters.
  • Optimized parameters such as nozzle temperature, layer height, print speed, and infill density.
  • Swin Transformer achieved accuracy of 94.8% with a surface roughness MAE of 0.033.
  • Print failures reduced by 41.2%, trial-and-error time decreased by 55%, and material usage decreased by approximately 32%.

Abstract

Fused Deposition Modeling (FDM) is one of the most widely adopted additive manufacturing technologies due to its low cost, flexibility, and ease of use. However, achieving consistent surface quality and minimizing print failures remain major challenges because printing outcomes are highly sensitive to parameter settings such as nozzle temperature, layer height, print speed, and infill density. Conventional optimization approaches rely heavily on trial-and-error and empirical tuning, which are inefficient and ineffective and struggle to model complex nonlinear parameter interactions. This study proposes a deep learning–based framework for optimizing FDM printing parameters using Vision Transformer (ViT) and Swin Transformer models. A dataset of 500 PLA-printed samples was collected by combining surface images and numerical printing parameters through a multimodal fusion strategy. Experimental results show that the Swin Transformer achieved superior performance with an accuracy of 94.8%, surface roughness MAE of 0.033, and a failure detection rate of 97.1%. Furthermore, the proposed approach reduced surface roughness by 28.6%, print failures by 41.2%, trial-and-error time by 55%, and material usage by approximately 32%.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Nuryanto et al. (2026) studied this question.

synapsesocial.com/papers/69ec5a8888ba6daa22dac069https://doi.org/10.1051/e3sconf/202670603001/pdf
Ask AI
Helpful
Bookmark
Share
View Full Paper