Integrration of a camera into an FDM printing system to improve print quality

DOI: 10.31673/2412-4338.2024.049908

Abstract

This article explores the possibilities of improving the quality of FDM (Fused Deposition Modeling) printing through the integration of a camera into the print process control system. FDM is one of the most widely used methods in additive manufacturing due to its accessibility and broad range of applications. However, the printing process is often accompanied by various defects such as layer shifting, under-extrusion, overheating or underheating of the material, and adhesion issues with the print bed. These problems not only degrade the quality of the final product but also lead to increased time and material costs. Integrating a camera into the FDM printing system offers a solution for early defect detection during the printing process, enabling automated adjustments of printing parameters in real time. Cameras allow for continuous monitoring of the print process at each stage, analyzing material layers, their alignment, and surface quality. Image processing algorithms and machine learning techniques facilitate the rapid and accurate identification of defects, predict potential deviations, and automatically modify print parameters to prevent quality deterioration. In addition to automatic parameter correction, the system can provide users with specific recommendations for improving equipment settings if issues are detected that cannot be addressed automatically. This approach significantly enhances the precision and reliability of the printing process, reducing the number of defective products and improving production efficiency. The article also discusses the future prospects of this technology, including the use of more powerful machine learning algorithms to increase the accuracy of defect analysis and prediction, the integration of cloud technologies for remote monitoring of printing processes, and the use of advanced camera types (such as infrared or 3D cameras) for even more precise quality control. Thus, integrating a camera into the FDM printing system represents a crucial step in the evolution of additive manufacturing technologies, offering significant improvements in the quality of printed products and optimization of the production process.

Keywords: FDM printing, additive technologies, camera integration, image processing, machine learning, quality control, automation, print defects, 3D printing, print parameter correction.

References

1. Boschetto, A., Bottini, L., & Veniali, F. (2013). Surface roughness prediction in fused deposition modeling by neural networks. The International Journal of Advanced Manufacturing Technology, 67(9), 2727-2742.
2. Valino, A. D., et al. (2019). Fused Deposition Modeling 3D printing: Effect of printing parameters on mechanical properties of wood PLA. Polymers, 11(4), 755.
3. Górski, F., et al. (2021). Application of artificial intelligence algorithms for quality control in 3D printing. Procedia CIRP, 104, 1695-1700.
4. Wang, T., et al. (2022). Computer vision-based defect detection for FDM 3D printing using convolutional neural networks. Journal of Manufacturing Systems, 63, 11-21.
5. Ahn, S., et al. (2002). Anisotropic material properties of fused deposition modeling ABS. Rapid Prototyping Journal, 8(4), 248-257.
6. Coogan, T., & Kazmer, D. (2017). In-line rheological monitoring of fused deposition modeling. Journal of Rheology, 61(1), 141-152.
7. Rahman, A. U., et al. (2021). Recent trends in 3D printing: A review on its applications and research. Materials Today: Proceedings, 47(9), 152-162. doi:10.1016/j.matpr.2021.09.172
8. Paul, J., et al. (2020). Fused deposition modeling-based additive manufacturing: Influence of printing parameters. 3D Printing and Additive Manufacturing, 7(2), 63-78.
9. Tian, X., et al. (2021). Overview of recent advances in fused filament fabrication 3D printing technology. Polymer Reviews, 61(4), 679-746.
10. Yang, J., et al. (2023). AI-driven defect detection and correction in additive manufacturing. International Journal of Mechanical Sciences, 241, 107926.