Probabilistic selection and design of concrete using machine learning
Development of robust concrete mixes with a lower environmental impact is challenging due to natural variability in constituent materials and a multitude of possible combinations of mix proportions. Making reliable property predictions with machine learning can facilitate performance-based specifica...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Cambridge University Press
2023-01-01
|
| Series: | Data-Centric Engineering |
| Subjects: | |
| Online Access: | https://www.cambridge.org/core/product/identifier/S2632673623000059/type/journal_article |
| _version_ | 1797843597339394048 |
|---|---|
| author | Jessica C. Forsdyke Bahdan Zviazhynski Janet M. Lees Gareth J. Conduit |
| author_facet | Jessica C. Forsdyke Bahdan Zviazhynski Janet M. Lees Gareth J. Conduit |
| author_sort | Jessica C. Forsdyke |
| collection | DOAJ |
| description | Development of robust concrete mixes with a lower environmental impact is challenging due to natural variability in constituent materials and a multitude of possible combinations of mix proportions. Making reliable property predictions with machine learning can facilitate performance-based specification of concrete, reducing material inefficiencies and improving the sustainability of concrete construction. In this work, we develop a machine learning algorithm that can utilize intermediate target variables and their associated noise to predict the final target variable. We apply the methodology to specify a concrete mix that has high resistance to carbonation, and another concrete mix that has low environmental impact. Both mixes also fulfill targets on the strength, density, and cost. The specified mixes are experimentally validated against their predictions. Our generic methodology enables the exploitation of noise in machine learning, which has a broad range of applications in structural engineering and beyond. |
| first_indexed | 2024-04-09T17:07:56Z |
| format | Article |
| id | doaj.art-bf308ade944744ce8125f0f2605e53c5 |
| institution | Directory Open Access Journal |
| issn | 2632-6736 |
| language | English |
| last_indexed | 2024-04-09T17:07:56Z |
| publishDate | 2023-01-01 |
| publisher | Cambridge University Press |
| record_format | Article |
| series | Data-Centric Engineering |
| spelling | doaj.art-bf308ade944744ce8125f0f2605e53c52023-04-20T10:30:38ZengCambridge University PressData-Centric Engineering2632-67362023-01-01410.1017/dce.2023.5Probabilistic selection and design of concrete using machine learningJessica C. Forsdyke0https://orcid.org/0000-0001-8466-3917Bahdan Zviazhynski1https://orcid.org/0000-0002-3862-8093Janet M. Lees2https://orcid.org/0000-0002-8295-8321Gareth J. Conduit3https://orcid.org/0000-0003-3807-6361Department of Engineering, University of Cambridge, Cambridge, United KingdomCavendish Laboratory, University of Cambridge, Cambridge, United KingdomDepartment of Engineering, University of Cambridge, Cambridge, United KingdomCavendish Laboratory, University of Cambridge, Cambridge, United KingdomDevelopment of robust concrete mixes with a lower environmental impact is challenging due to natural variability in constituent materials and a multitude of possible combinations of mix proportions. Making reliable property predictions with machine learning can facilitate performance-based specification of concrete, reducing material inefficiencies and improving the sustainability of concrete construction. In this work, we develop a machine learning algorithm that can utilize intermediate target variables and their associated noise to predict the final target variable. We apply the methodology to specify a concrete mix that has high resistance to carbonation, and another concrete mix that has low environmental impact. Both mixes also fulfill targets on the strength, density, and cost. The specified mixes are experimentally validated against their predictions. Our generic methodology enables the exploitation of noise in machine learning, which has a broad range of applications in structural engineering and beyond.https://www.cambridge.org/core/product/identifier/S2632673623000059/type/journal_articleCarbonationconcretemachine learningperformance-based specification |
| spellingShingle | Jessica C. Forsdyke Bahdan Zviazhynski Janet M. Lees Gareth J. Conduit Probabilistic selection and design of concrete using machine learning Data-Centric Engineering Carbonation concrete machine learning performance-based specification |
| title | Probabilistic selection and design of concrete using machine learning |
| title_full | Probabilistic selection and design of concrete using machine learning |
| title_fullStr | Probabilistic selection and design of concrete using machine learning |
| title_full_unstemmed | Probabilistic selection and design of concrete using machine learning |
| title_short | Probabilistic selection and design of concrete using machine learning |
| title_sort | probabilistic selection and design of concrete using machine learning |
| topic | Carbonation concrete machine learning performance-based specification |
| url | https://www.cambridge.org/core/product/identifier/S2632673623000059/type/journal_article |
| work_keys_str_mv | AT jessicacforsdyke probabilisticselectionanddesignofconcreteusingmachinelearning AT bahdanzviazhynski probabilisticselectionanddesignofconcreteusingmachinelearning AT janetmlees probabilisticselectionanddesignofconcreteusingmachinelearning AT garethjconduit probabilisticselectionanddesignofconcreteusingmachinelearning |