Machine learning driven forward prediction and inverse design for 4D printed hierarchical architecture with arbitrary shapes
dc.contributor.author | Jin, L | |
dc.contributor.author | Yu, S | |
dc.contributor.author | Cheng, J | |
dc.contributor.author | Ye, H | |
dc.contributor.author | Zhai, X | |
dc.contributor.author | Jiang, J | |
dc.contributor.author | Zhang, K | |
dc.contributor.author | Jian, B | |
dc.contributor.author | Bodaghi, M | |
dc.contributor.author | Ge, Q | |
dc.contributor.author | Liao, W-H | |
dc.date.accessioned | 2024-08-08T14:04:37Z | |
dc.date.issued | 2024-08-07 | |
dc.date.updated | 2024-08-08T08:37:47Z | |
dc.description.abstract | The forward prediction and inverse design of 4D printing have primarily focused on 2D rectangular surfaces or plates, leaving the challenge of 4D printing parts with arbitrary shapes underexplored. This gap arises from the difficulty of handling varying input sizes in machine learning paradigms. To address this, we propose a novel machine learning-driven approach for forward prediction and inverse design tailored to 4D printed hierarchical architectures with arbitrary shapes. Our method encodes non-rectangular shapes with special identifiers, transforming the design domain into a format suitable for machine learning analysis. Using Residual Networks (ResNet) for forward prediction and evolutionary algorithms (EA) for inverse design, our approach achieves accurate and efficient predictions and designs. The results validate the effectiveness of our proposed method, with the forward prediction model achieving a loss below 10−2 mm, and the inverse optimization model maintaining an error near 1 mm, which is low relative to the entire shape of the optimized model. These outcomes demonstrate the capability of our approach to accurately predict and design complex hierarchical structures in 4D printing applications | en_GB |
dc.description.sponsorship | Research Grants Council | en_GB |
dc.description.sponsorship | Hong Kong Special Administrative Region, China | en_GB |
dc.description.sponsorship | Chinese University of Hong Kong | en_GB |
dc.description.sponsorship | National Natural Science Foundation of China | en_GB |
dc.description.sponsorship | Key Talent Recruitment Program of Guangdong Province, China | en_GB |
dc.description.sponsorship | Science, Technology and Innovation Commission of Shenzhen Municipality, China | en_GB |
dc.description.sponsorship | Engineering and Physical Sciences Research Council (EPSRC) | en_GB |
dc.format.extent | 102373-102373 | |
dc.identifier.citation | Vol. 40, article 102373 | en_GB |
dc.identifier.doi | 10.1016/j.apmt.2024.102373 | |
dc.identifier.grantnumber | C4074-22G | en_GB |
dc.identifier.grantnumber | 3110174 | en_GB |
dc.identifier.grantnumber | 12072142 | en_GB |
dc.identifier.grantnumber | 2019QN01Z438 | en_GB |
dc.identifier.grantnumber | ZDSYS20210623092005017 | en_GB |
dc.identifier.grantnumber | EP/Y011457/1 | en_GB |
dc.identifier.uri | http://hdl.handle.net/10871/137081 | |
dc.identifier | ORCID: 0000-0002-0446-3454 (Jiang, Jingchao) | |
dc.identifier | ScopusID: 57201681409 (Jiang, Jingchao) | |
dc.identifier | ResearcherID: R-1303-2019 (Jiang, Jingchao) | |
dc.language.iso | en | en_GB |
dc.publisher | Elsevier | en_GB |
dc.rights | © 2024 the author(s). For the purpose of open access, the author has applied a ‘Creative Commons Attribution (CC BY) licence to any Author Accepted Manuscript version arising from this submission. | en_GB |
dc.subject | 4D printing | en_GB |
dc.subject | Machine learning | en_GB |
dc.subject | Inverse design | en_GB |
dc.subject | Hierarchical architecture | en_GB |
dc.subject | Design optimization | en_GB |
dc.subject | Residual network | en_GB |
dc.subject | Evolutionary algorithm | en_GB |
dc.title | Machine learning driven forward prediction and inverse design for 4D printed hierarchical architecture with arbitrary shapes | en_GB |
dc.type | Article | en_GB |
dc.date.available | 2024-08-08T14:04:37Z | |
dc.identifier.issn | 2352-9407 | |
exeter.article-number | 102373 | |
dc.description | This is the author accepted manuscript. The final version is available from Elsevier via the DOI in this record | en_GB |
dc.description | Data availability: The data supporting the findings of this study are available within the article. | en_GB |
dc.identifier.journal | Applied Materials Today | en_GB |
dc.relation.ispartof | Applied Materials Today, 40 | |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | en_GB |
dcterms.dateAccepted | 2024-07-27 | |
rioxxterms.version | AM | en_GB |
rioxxterms.licenseref.startdate | 2024-08-07 | |
rioxxterms.type | Journal Article/Review | en_GB |
refterms.dateFCD | 2024-08-08T13:59:19Z | |
refterms.versionFCD | AM | |
refterms.dateFOA | 2024-08-08T14:04:46Z | |
refterms.panel | B | en_GB |
Files in this item
This item appears in the following Collection(s)
Except where otherwise noted, this item's licence is described as © 2024 the author(s). For the purpose of open access, the author has applied a ‘Creative Commons Attribution (CC BY) licence to any Author Accepted Manuscript version arising from this submission.