Neural Networks for Prediction of 3D Printing Parameters for Reducing Particulate Matter Emissions and Enhancing Sustainability
[ 1 ] Instytut Technologii Materiałów, Wydział Inżynierii Mechanicznej, Politechnika Poznańska | [ P ] employee
2024
scientific article
english
- 3D printing
- additive manufacturing
- particle matter emission
- sustainable development of new technologies
- neural networks
- environmental impact
EN This study focuses on the application of neural networks to optimize 3D printing parameters in order to reduce particulate matter (PM) emissions and enhance sustainability. This research identifies key parameters, such as head temperature, bed temperature, print speed, nozzle diameter, and cooling, that significantly impact particle matter emissions. Quantitative analysis reveals that higher head temperatures (225 °C), faster print speeds (50 mm/s), and larger nozzle diameters (0.8 mm) result in elevated PM emissions, while lower settings (head temperature at 190 °C, print speed at 30 mm/s, nozzle diameter of 0.4 mm) help minimize these emissions. Using multilayer perceptron (MLP) neural networks, predictive models with an accuracy of up to 95.6% were developed, allowing for a precise optimization of 3D printing processes. The MLP 7-19-6 model showed a strong correlation (0.956) between input parameters and emissions, offering a robust tool for reducing the environmental footprint of additive manufacturing. By optimizing 3D printing settings, this study contributes to more sustainable practices by lowering harmful emissions. These findings are crucial for advancing sustainable development goals by providing actionable strategies for minimizing health risks and promoting eco-friendly manufacturing processes. Ultimately, this research supports the transition to greener technologies in the field of additive manufacturing.
04.10.2024
8616-1 - 8616-20
CC BY (attribution alone)
open journal
final published version
at the time of publication
100
3,3 [List 2023]