Predicting the abrasion loss of open-graded friction course mixes with EAF steel slag aggregates using machine learning algorithms

Madhu Lisha Pattanaik, Sanjit Kumar, Rajan Choudhary, Mayank Agarwal, Bimlesh Kumar

Research output: Contribution to journalArticlepeer-review

4 Scopus citations

Abstract

This study presents a comparative assessment of machine learning techniques for modeling the abrasion loss (AL) of open-graded friction course (OGFC) mixes. The proposed approach is Orthogonal Matching Pursuit (OMP), Huber Regressor (HR), Lasso Lars CV (LLCV), Lars CV (LCV), and Ridge Regressor (RR). To construct and validate the proposed models, a sum of 228 experiments of OGFC mixes with different proportions of natural aggregates and electric arc furnace (EAF) steel slag were performed. Based on the analyses with 4 different combinations of input parameters, the proposed OMP model exhibits the most accurate prediction of AL of OGFC mix in both training and validation phases. Comparison of results of the developed models indicated that the OMP model has the potential to be a new alternative to assist engineers/practitioners in estimating the AL of OGFC mixes. In addition, the effect of % replacement of natural aggregates with electric arc furnace steel slag can also be studied.

Original languageEnglish
Article number126408
JournalConstruction and Building Materials
Volume321
DOIs
StatePublished - 28 Feb 2022
Externally publishedYes

Keywords

  • Abrasion loss
  • Aggregate characteristics
  • Machine learning
  • Modified binder
  • Open-graded friction course

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction
  • General Materials Science

Fingerprint

Dive into the research topics of 'Predicting the abrasion loss of open-graded friction course mixes with EAF steel slag aggregates using machine learning algorithms'. Together they form a unique fingerprint.

Cite this