APPLICATION OF MACHINE LEARNING METHODS TO 3D PRINTER CONTROL

DOI: 10.31673/2412-4338.2024.010415

Abstract

The article discusses important aspects of using machine learning methods to optimize 3D printer control. As 3D printing technology becomes more widespread in modern manufacturing and design, there is a need to improve the processes of setting up and controlling printing. The authors investigate the impact of using machine learning algorithms to improve product quality, as well as reduce printing time and material consumption.
The article discusses the possibilities of using machine learning algorithms to automate printer setup processes. This includes the selection of optimal printing parameters, such as print speed, ingredient temperature, and others. The authors consider the possibility of creating prediction models that can predict the optimal printing conditions for specific tasks and materials.
The main focus is on identifying and eliminating printing defects by analyzing a large amount of data collected during the printing process. The use of machine learning methods allows automated detection of problems and suggestions of optimal solutions. This not only improves the quality of manufactured products, but also reduces the reject rate and ensures the stability of production processes.
The article also discusses aspects of ensuring the controllability and safety of the printing process. Machine learning methods are used to implement systems for the automatic detection and management of risks associated with production on 3D printers.
The general conclusion of the article is that the application of machine learning methods to 3D printer control has great potential to improve the efficiency of production processes and product quality. Further research in this direction may open up new opportunities for industry and design, contributing to the development of digital manufacturing.

Keywords: 3D printer, neural networks, machine learning, computer vision, information technology, information system, model, algorithm.

References
1. About software for Raspberry Pi [Electronic resource] - Mode of access to the resource: https://raspberrypi.org/software.
2. Using OctoPrint with Raspberry Pi to Control 3D Printers [Electronic resource] - Resource access mode: https://www.raspberrypi.com/news/octoprint/.
3. Machine Learning with PyTorch and Scikit-Learn / Sebastian Raschka., 2022. – 770 p.
4. Python programming [Electronic resource] - Resource access mode: https://diveinto.org/python3/.
5. EfficientNet-Lite [Electronic resource] – Resource access mode: https://blog.tensorflow.org/2020/03/higher-accuracy-on-vision-models-with-efficientnet-lite.html.
6. Using deep learning for defect detection [Electronic resource] - Resource access mode: https://www.mdpi.com/2571-5577/4/2/34.
7. Deep learning for defect detection [Electronic resource] - Resource access mode: https://www.emerald.com/insight/content/doi/10.1108/RPJ-05-2023-0157/full/html
8. Zhurakovskyi B., Toliupa S., Druzhynin V., Bondarchuk A., Stepanov M. Calculation of Quality Indicators of the Future Multiservice Network. Lecture Notes in Electrical Engineering, 2022, 831, p. 197–209
9. Shevchenko O., Bondarchuk A., Polonevych O., Zhurakovskyi B., Korshun N. Methods of the objects identification and recognition research in the networks with the IoT concept support. CEUR Workshop ProceedingsThis link is disabled., 2021, 2923, p. 277–282
10. Zhebka V., Gertsiuk M., Sokolov V., Malinov V., Sablina M. Optimization of Machine Learning Method to Improve the Management Efficiency of Heterogeneous Telecommunication Network // CEUR Workshop Proceedings, 2022, 3288, p. 149–155