A Data-Driven Approach to Evaluate the Compressive Strength of Recycled Aggregate Concrete

Henry Barth, Srishti Banerji, Matthew P. Adams, Mohsen Zaker Esteghamati

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper examines the application of machine learning (ML) techniques in the prediction of the compressive strength of recycled aggregate concrete (RAC). The ML models are trained on a comprehensive dataset composed of 981 different RAC test results. Four algorithms of multiple linear regression, lasso regression, random forest, and histogram-based gradient boosting are investigated. The ML training workflow consists of careful feature selection and rigorous hyperparameter tuning based on cross-validation on the training set. The prediction accuracy of ML models was measured by calculating R-squared and root mean squared error metrics. Lastly, sensitivity analysis was performed to measure the impact of input features on the RAC compressive strength. The results indicate that histogram-based gradient boosting model results in the highest accuracy among the studied ML algorithms where water to cement ratio and cement content were found to be the most influential parameters.

Original languageEnglish (US)
Title of host publicationASCE Inspire 2023
Subtitle of host publicationInfrastructure Innovation and Adaptation for a Sustainable and Resilient World - Selected Papers from ASCE Inspire 2023
EditorsBilal M. Ayyub
PublisherAmerican Society of Civil Engineers (ASCE)
Pages433-441
Number of pages9
ISBN (Electronic)9780784485163
StatePublished - 2023
EventASCE Inspire 2023: Infrastructure Innovation and Adaptation for a Sustainable and Resilient World - Arlington, United States
Duration: Nov 16 2023Nov 18 2023

Publication series

NameASCE Inspire 2023: Infrastructure Innovation and Adaptation for a Sustainable and Resilient World - Selected Papers from ASCE Inspire 2023

Conference

ConferenceASCE Inspire 2023: Infrastructure Innovation and Adaptation for a Sustainable and Resilient World
Country/TerritoryUnited States
CityArlington
Period11/16/2311/18/23

All Science Journal Classification (ASJC) codes

  • Civil and Structural Engineering
  • Mechanics of Materials
  • Building and Construction
  • Architecture

Fingerprint

Dive into the research topics of 'A Data-Driven Approach to Evaluate the Compressive Strength of Recycled Aggregate Concrete'. Together they form a unique fingerprint.

Cite this