Neural Networks for Prediction of 3D Printing Parameters for Reducing Particulate Matter Emissions and Enhancing Sustainability DOI Open Access
Ewa Dostatni,

Filip Osiński,

Dariusz Mikołajewski

и другие.

Sustainability, Год журнала: 2024, Номер 16(19), С. 8616 - 8616

Опубликована: Окт. 4, 2024

This study focuses on the application of neural networks to optimize 3D printing parameters in order reduce particulate matter (PM) emissions and enhance sustainability. research identifies key parameters, such as head temperature, bed print speed, nozzle diameter, cooling, that significantly impact particle emissions. Quantitative analysis reveals higher temperatures (225 °C), faster speeds (50 mm/s), larger diameters (0.8 mm) result elevated PM emissions, while lower settings (head temperature at 190 °C, speed 30 mm/s, diameter 0.4 help minimize these Using multilayer perceptron (MLP) networks, predictive models with an accuracy up 95.6% were developed, allowing for a precise optimization processes. The MLP 7-19-6 model showed strong correlation (0.956) between input offering robust tool reducing environmental footprint additive manufacturing. By optimizing settings, this contributes more sustainable practices by lowering harmful These findings are crucial advancing development goals providing actionable strategies minimizing health risks promoting eco-friendly manufacturing Ultimately, supports transition greener technologies field

Язык: Английский

Data-driven analysis in 3D concrete printing: predicting and optimizing construction mixtures DOI Creative Commons

Rodrigo Teixeira Schossler,

Shafi Ullah,

Zaid Alajlan

и другие.

AI in Civil Engineering, Год журнала: 2025, Номер 4(1)

Опубликована: Янв. 3, 2025

Язык: Английский

Процитировано

0
Neural Networks for Prediction of 3D Printing Parameters for Reducing Particulate Matter Emissions and Enhancing Sustainability DOI Open Access
Ewa Dostatni,

Filip Osiński,

Dariusz Mikołajewski

и другие.

Sustainability, Год журнала: 2024, Номер 16(19), С. 8616 - 8616

Опубликована: Окт. 4, 2024

This study focuses on the application of neural networks to optimize 3D printing parameters in order reduce particulate matter (PM) emissions and enhance sustainability. research identifies key parameters, such as head temperature, bed print speed, nozzle diameter, cooling, that significantly impact particle emissions. Quantitative analysis reveals higher temperatures (225 °C), faster speeds (50 mm/s), larger diameters (0.8 mm) result elevated PM emissions, while lower settings (head temperature at 190 °C, speed 30 mm/s, diameter 0.4 help minimize these Using multilayer perceptron (MLP) networks, predictive models with an accuracy up 95.6% were developed, allowing for a precise optimization processes. The MLP 7-19-6 model showed strong correlation (0.956) between input offering robust tool reducing environmental footprint additive manufacturing. By optimizing settings, this contributes more sustainable practices by lowering harmful These findings are crucial advancing development goals providing actionable strategies minimizing health risks promoting eco-friendly manufacturing Ultimately, supports transition greener technologies field

Язык: Английский

Процитировано

1