Modeling the mechanical properties of recycled aggregate concrete using hybrid machine learning algorithms

Peng, Y. and Unluer, C. (2023) Modeling the mechanical properties of recycled aggregate concrete using hybrid machine learning algorithms. Resources, Conservation and Recycling, 190, 106812. (doi: 10.1016/j.resconrec.2022.106812)

Abstract

To explore the complicated functional relationship between key parameters such as the recycled aggregate properties, mix proportion and compressive strength of recycled aggregate concrete (RAC), a complete database involving 607 records from relevant published literature was built. Two standard algorithms (artificial neural network (ANN) and support vector regression (SVR)) and two optimized hybrid models (Particle Swarm Optimization based SVR (PSO-SVR) and grey Wolf optimizer based SVR (GWO-SVR)) were adopted. Furthermore, two interpretable algorithms (Partial Dependence Plot (PDP) and SHapley Additive exPlanations (SHAP)) were utilized to assess the global and local approaches independent of machine learning models, contributing towards decision-making rationales. Results indicated that the coefficient of determination (R2) of ANN, SVR, PSO-SVR and GWO-SVR were 0.7569, 0.5914, 0.8995 and 0.9056 respectively, showing that hybrid models outperformed the conventional models. However, GWO-SVR was the most problematic with overfitting when analyzing its three subsets. The two feature importance analyses revealed cement content, water content, natural fine aggregates, and water absorption as significant characteristics that affect mechanical performance.

• Item Type: Articles
• Additional Information: This work was funded by The Royal Society (project ref: ICA\R1\201310) and China Scholarship Council (grant number: 202006370082).
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Unluer, Dr Cise

Creator Roles

Unluer, C.: Resources, Writing – review and editing, Supervision, Project administration

• Authors: Peng, Y., and Unluer, C.
• College/School: College of Science and Engineering > School of Engineering > Infrastructure and Environment
• Journal Name: Resources, Conservation and Recycling
• Publisher: Elsevier
• ISSN: 0921-3449
• ISSN (Online): 1879-0658
• Published Online: 11 December 2022
• Copyright Holders: Copyright © 2022 The Authors
• First Published: First published in Resources, Conservation and Recycling 190: 106812
• Publisher Policy: Reproduced under a Creative Commons License

Project Code	Award No	Project Name	Principal Investigator	Funder's Name	Funder Ref	Lead Dept
310985		The integration of permanent storage of CO2 and industrial wastes in construction materials: Towards a sustainable built environment with reduced carbon emissions	Cise Unluer	The Royal Society (ROYSOC)	ICA\R1\201310	ENG - Infrastructure & Environment