Explainable artificial intelligence framework for FRP composites design

dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorYossef, Mostafaen_US
dc.contributor.authorNoureldin, Mohameden_US
dc.contributor.authorAl Kabbani, Aghyaden_US
dc.contributor.departmentDepartment of Civil Engineeringen
dc.contributor.groupauthorStructures – Structural Engineering, Mechanics and Computationen
dc.contributor.organizationDepartment of Civil Engineeringen_US
dc.date.accessioned2024-05-29T05:14:43Z
dc.date.available2024-05-29T05:14:43Z
dc.date.issued2024-08-01en_US
dc.description.abstractFiber-reinforced polymer (FRP) materials are integral to various industries, from automotive and aerospace to infrastructure and construction. While FRP composite design guidelines have been established, the process of obtaining the desired strength of an FRP composite demands considerable time and resources. Despite recent advancements in Machine Learning (ML) models which are commonly used as predictive models, the inherent 'black box' nature of those models poses challenges in understanding the relationship between input design parameters and output strength of the composite. Moreover, these models do not provide tools to facilitate the designing process of the composite. The current study introduces an explainable Artificial Intelligence (XAI) framework that will provide understanding for the input–output relationships of the model through SHapley Additive exPlanations (SHAP) and Partial Dependence Plots (PDPs). In addition, the framework provides for the first time a designing approach for adjusting the important design parameters to obtain the desired composite strength by the designer through utilizing an explainability technique called Counterfactual (CF). The framework is evaluated through the design of a 14-ply composite, successfully identifying critical design parameters, and specifying necessary adjustments to meet strength requirements.en
dc.description.versionPeer revieweden
dc.format.extent13
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationYossef, M, Noureldin, M & Al Kabbani, A 2024, ' Explainable artificial intelligence framework for FRP composites design ', Composite Structures, vol. 341, 118190 . https://doi.org/10.1016/j.compstruct.2024.118190en
dc.identifier.doi10.1016/j.compstruct.2024.118190en_US
dc.identifier.issn0263-8223
dc.identifier.otherPURE UUID: 565f7735-3e04-40ad-8cc2-55c6f83f3bcaen_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/565f7735-3e04-40ad-8cc2-55c6f83f3bcaen_US
dc.identifier.otherPURE LINK: http://www.scopus.com/inward/record.url?scp=85193621586&partnerID=8YFLogxKen_US
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/146943127/1-s2.0-S0263822324003180-main-2.pdfen_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/128345
dc.identifier.urnURN:NBN:fi:aalto-202405293947
dc.language.isoenen
dc.publisherElsevier Science Ltd.
dc.relation.ispartofseriesComposite Structures
dc.relation.ispartofseriesVolume 341
dc.rightsopenAccessen
dc.subject.keywordCasual AIen_US
dc.subject.keywordComposite designen_US
dc.subject.keywordCounterfactualen_US
dc.subject.keywordExplainable artificial intelligenceen_US
dc.subject.keywordFRPen_US
dc.subject.keywordPartial Dependence Plotsen_US
dc.subject.keywordSHapley Additive exPlanationsen_US
dc.subject.keywordmachine learningen_US
dc.subject.keywordMachine Learningen_US
dc.titleExplainable artificial intelligence framework for FRP composites designen
dc.typeA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessäfi
dc.type.versionpublishedVersion
Files