Exploring the process—structure–property relationship of nylon aramid 3D printed composites and parameter optimization using supervised machine learning techniques
The main goals of this research are to identify the significant input parameters using supervised machine learning methods and investigate the relationship between the process, structure, and properties of components created using fused deposition modeling utilizing nylon aramid composite filaments....
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2025-02-01
|
| Series: | Journal of Engineered Fibers and Fabrics |
| Online Access: | https://doi.org/10.1177/15589250241293883 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The main goals of this research are to identify the significant input parameters using supervised machine learning methods and investigate the relationship between the process, structure, and properties of components created using fused deposition modeling utilizing nylon aramid composite filaments. To develop an experimental layout using Taguchi’s L 18 orthogonal array, six different FDM parameters such as infill pattern, infill density, layer thickness, component orientation, print temperature, and raster angle have been taken into consideration.Using an Ultimaker FDM printer, rectangular samples were created, and the values of face hardness, thickness regions, printing time, and component weight were assessed. ANOVA and the signal to noise ratio method are two techniques that have been used to find the significant influencing parameter and the ideal combination of parameters. When comparing thickly layered samples with a suitable increase in time and weight, thin-layered samples are shown to have greater hardness values at both tested areas. With a 50.09% contribution to face hardness and a 30.11% contribution to hardness at the thickness area, raster angle is found to be significant over hardness.Layer thickness is an important element that contributes 81.95% to printing time and 42.09% to part weight, respectively. In an 80:20 train-test split, the decision tree approach outperformed the k -nearest neighbor algorithm for all four output responses, with classification accuracy ranging from 83.33% to 100%. Infill density is recommended by the decision tree method to be extremely significant over face hardness and component weight, and layer thickness is similarly recommended to be highly significant over printing time and hardness at the thickness region. The presence of surface pores, interior voids, and layer abnormalities is confirmed by FESEM images. |
|---|---|
| ISSN: | 1558-9250 |