Skip to main content

Research Repository

Advanced Search

A deep learning approach to concrete water-cement ratio prediction

Oyedele, Lukumon; Bello, Sururah; Olaitan, Olakunle Kazeem; Olonade, Kolawole Adisa; Olajumoke, Akinropo Musiliu; Ajayi, Anuoluwapo; Akanbi, Lukman; Akinade, Olugbenga; Sanni, Mistura Laide; Bello, Abdul Lateef

A deep learning approach to concrete water-cement ratio prediction Thumbnail


Authors

Lukumon Oyedele L.Oyedele@uwe.ac.uk
Professor in Enterprise & Project Management

Sururah Bello Sururah.Bello@uwe.ac.uk
Senior Research Fellow - Redistributed Manufacturing in Deployed Operations

Olakunle Kazeem Olaitan

Kolawole Adisa Olonade

Akinropo Musiliu Olajumoke

Anuoluwapo Ajayi Anuoluwapo.Ajayi@uwe.ac.uk
Associate Professor - Big Data Application

Dr Lukman Akanbi Lukman.Akanbi@uwe.ac.uk
Associate Professor - Big Data Application Developer

Olugbenga Akinade Olugbenga.Akinade@uwe.ac.uk
Associate Professor - AR/VR Development with Artificial Intelligence

Mistura Laide Sanni

Abdul Lateef Bello



Abstract

Concrete is a versatile construction material, but the water content can greatly influence its quality. However, using the trials and error method to determine the optimum water for the concrete mix results in poor quality concrete structures, which often end up in landfills as construction wastes, thus threatening environmental safety. This paper develops deep neural networks to predict the required water for a normal concrete mix. Standard data samples obtained from certified/leading laboratories were fed into a deep learning model (multilayers feedforward neural network) to automate the calibration of mixing power of the concrete water content for improved water control accuracy. We randomly split the data into 70%, 15% and 15%, respectively, to train, validate and test the model. The developed DNN model was subjected to relevant statistical metrics and benchmarked against the random forest, gradient boosting machines, and support vector machines. The performance indices obtained by the DNN model have the highest reliability compared to other models for concrete water prediction.

Journal Article Type Article
Acceptance Date Jul 3, 2022
Online Publication Date Jul 8, 2022
Publication Date Sep 1, 2022
Deposit Date Aug 18, 2022
Publicly Available Date Aug 18, 2022
Journal Results in Materials
Electronic ISSN 2590-048X
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 15
Issue September 2022
Article Number 100300
DOI https://doi.org/10.1016/j.rinma.2022.100300
Keywords concrete water-cement ratio, prediction, concrete, deep neural networks, neural networks, concrete structures, buildings
Public URL https://uwe-repository.worktribe.com/output/9703733
Publisher URL https://www.sciencedirect.com/science/article/pii/S2590048X22000486?via%3Dihub

Files





You might also like



Downloadable Citations