Machine learning assisted investigation of defect influence on the mechanical properties of additively manufactured architected materials
Additive manufacturing techniques can introduce defects that worsen the mechanical properties of 3D printed parts. Current techniques for quantifying the detrimental effects of these defects can only provide detailed analysis for a small number of geometries. Here, we investigate the effect of each...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/156164 |
| _version_ | 1826111944172503040 |
|---|---|
| author | Hu, Erhai Seetoh, Ian Lai, Chang Quan |
| author2 | School of Mechanical and Aerospace Engineering |
| author_facet | School of Mechanical and Aerospace Engineering Hu, Erhai Seetoh, Ian Lai, Chang Quan |
| author_sort | Hu, Erhai |
| collection | NTU |
| description | Additive manufacturing techniques can introduce defects that worsen the mechanical properties of 3D printed parts. Current techniques for quantifying the detrimental effects of these defects can only provide detailed analysis for a small number of geometries. Here, we investigate the effect of each defect feature (surface roughness and void position, number density and size) on the mechanical properties of a large number of truss lattices belonging to the stretch-dominated and bending-dominated topology. This is done by reducing each truss lattice into a single-beam sub-unit cell and conducting finite element simulations on it. The generated data is subjected to machine learning algorithms to identify the most important defect and design features that determine the mechanical properties of the overall structure. Our results indicate that surface roughness, Rmax (i.e. peak-to-trough height), exceeding 10% of the beam diameter strongly reduces the specific modulus and strength of lattice structures, especially for bending-dominated geometries. Interior voids, on the other hand, adversely affect stretch-dominated geometries but improve the specific properties of bending-dominated structures by removing under-stressed material in the core of the beams and causing them to become more “tube-like”. These insights are supported by first-principles analytical modeling and experimental data of additively manufactured metal lattices in the literature. |
| first_indexed | 2024-10-01T02:59:09Z |
| format | Journal Article |
| id | ntu-10356/156164 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:59:09Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1561642022-09-17T23:31:55Z Machine learning assisted investigation of defect influence on the mechanical properties of additively manufactured architected materials Hu, Erhai Seetoh, Ian Lai, Chang Quan School of Mechanical and Aerospace Engineering School of Materials Science and Engineering Temasek Laboratories @ NTU Engineering::Materials Engineering::Mechanical engineering Additive Manufacturing Architected Materials Additive manufacturing techniques can introduce defects that worsen the mechanical properties of 3D printed parts. Current techniques for quantifying the detrimental effects of these defects can only provide detailed analysis for a small number of geometries. Here, we investigate the effect of each defect feature (surface roughness and void position, number density and size) on the mechanical properties of a large number of truss lattices belonging to the stretch-dominated and bending-dominated topology. This is done by reducing each truss lattice into a single-beam sub-unit cell and conducting finite element simulations on it. The generated data is subjected to machine learning algorithms to identify the most important defect and design features that determine the mechanical properties of the overall structure. Our results indicate that surface roughness, Rmax (i.e. peak-to-trough height), exceeding 10% of the beam diameter strongly reduces the specific modulus and strength of lattice structures, especially for bending-dominated geometries. Interior voids, on the other hand, adversely affect stretch-dominated geometries but improve the specific properties of bending-dominated structures by removing under-stressed material in the core of the beams and causing them to become more “tube-like”. These insights are supported by first-principles analytical modeling and experimental data of additively manufactured metal lattices in the literature. Nanyang Technological University Submitted/Accepted version This work was partially funded by the Temasek Labs Innovation Grant (TLIG21-02) for which the authors are grateful for. 2022-04-07T07:56:00Z 2022-04-07T07:56:00Z 2022 Journal Article Hu, E., Seetoh, I. & Lai, C. Q. (2022). Machine learning assisted investigation of defect influence on the mechanical properties of additively manufactured architected materials. International Journal of Mechanical Sciences, 221, 107190-. https://dx.doi.org/10.1016/j.ijmecsci.2022.107190 0020-7403 https://hdl.handle.net/10356/156164 10.1016/j.ijmecsci.2022.107190 2-s2.0-85126300734 221 107190 en TLIG21-02 International Journal of Mechanical Sciences © 2022 Elsevier Ltd. All rights reserved. This paper was published in International Journal of Mechanical Sciences and is made available with permission of Elsevier Ltd. application/pdf |
| spellingShingle | Engineering::Materials Engineering::Mechanical engineering Additive Manufacturing Architected Materials Hu, Erhai Seetoh, Ian Lai, Chang Quan Machine learning assisted investigation of defect influence on the mechanical properties of additively manufactured architected materials |
| title | Machine learning assisted investigation of defect influence on the mechanical properties of additively manufactured architected materials |
| title_full | Machine learning assisted investigation of defect influence on the mechanical properties of additively manufactured architected materials |
| title_fullStr | Machine learning assisted investigation of defect influence on the mechanical properties of additively manufactured architected materials |
| title_full_unstemmed | Machine learning assisted investigation of defect influence on the mechanical properties of additively manufactured architected materials |
| title_short | Machine learning assisted investigation of defect influence on the mechanical properties of additively manufactured architected materials |
| title_sort | machine learning assisted investigation of defect influence on the mechanical properties of additively manufactured architected materials |
| topic | Engineering::Materials Engineering::Mechanical engineering Additive Manufacturing Architected Materials |
| url | https://hdl.handle.net/10356/156164 |
| work_keys_str_mv | AT huerhai machinelearningassistedinvestigationofdefectinfluenceonthemechanicalpropertiesofadditivelymanufacturedarchitectedmaterials AT seetohian machinelearningassistedinvestigationofdefectinfluenceonthemechanicalpropertiesofadditivelymanufacturedarchitectedmaterials AT laichangquan machinelearningassistedinvestigationofdefectinfluenceonthemechanicalpropertiesofadditivelymanufacturedarchitectedmaterials |