Sustainable Polyurethane-Based Polymer Concrete: Mechanical and Non-destructive Properties with Machine Learning Technique

Abstract Polyurethane-based polymer concrete (PUC) has become a popular material for pavement repair. However, its compressive strength (f c) is essential to achieve effective repair work. This study predicted the compressive strength and evaluated the non-destructive test (NDT) properties of the PU...

Full description

Saved in:
Bibliographic Details
Main Authors: S. I. Haruna, Han Zhu, Yasser E. Ibrahim, Jian Yang, AIB Farouk, Jianwen Shao, Musa Adamu, Omar Shabbir Ahmed
Format: Article
Language:English
Published: SpringerOpen 2025-08-01
Series:International Journal of Concrete Structures and Materials
Subjects:
Online Access:https://doi.org/10.1186/s40069-025-00803-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333642493427712
author S. I. Haruna
Han Zhu
Yasser E. Ibrahim
Jian Yang
AIB Farouk
Jianwen Shao
Musa Adamu
Omar Shabbir Ahmed
author_facet S. I. Haruna
Han Zhu
Yasser E. Ibrahim
Jian Yang
AIB Farouk
Jianwen Shao
Musa Adamu
Omar Shabbir Ahmed
author_sort S. I. Haruna
collection DOAJ
description Abstract Polyurethane-based polymer concrete (PUC) has become a popular material for pavement repair. However, its compressive strength (f c) is essential to achieve effective repair work. This study predicted the compressive strength and evaluated the non-destructive test (NDT) properties of the PUC mixtures, prepared by mixing aggregate-to-polyurethane (PU) at 80/20, 85/15, and 90/10 ratios by weight. The experimental datasets from mechanical and NDT tests were utilized to train machine learning (ML) models, including multilinear regression (MLR), artificial neural network (ANN), support vector machine (SVM), Gaussian regression process (GPR), and stepwise regression (SWR) models for estimating the f c. Moreover, scanning electron microscopy (SEM) was employed to evaluate the microstructure of PUC. Feature selection tools were used to explore optimal input variables for estimating the (f c) of the PUC samples. The PUC-10 specimen revealed a maximum ultrasonic pulse velocity (UPV) value of 3.05 km/h. The microstructure analysis shows micro-voids with crack propagation between the aggregate and PU binder in the specimen containing 10% PU after testing. All the developed models showed high prediction accuracy. In addition, SVM outperformed other models at the training phase with R 2 values of 0.9614, and ANN demonstrated the highest performance at the testing phase with R 2 values of 0.9502.
format Article
id doaj-art-63bcfe73c99e4fd78e8f388b1ce78992
institution Kabale University
issn 2234-1315
language English
publishDate 2025-08-01
publisher SpringerOpen
record_format Article
series International Journal of Concrete Structures and Materials
spelling doaj-art-63bcfe73c99e4fd78e8f388b1ce789922025-08-20T03:45:48ZengSpringerOpenInternational Journal of Concrete Structures and Materials2234-13152025-08-0119112310.1186/s40069-025-00803-2Sustainable Polyurethane-Based Polymer Concrete: Mechanical and Non-destructive Properties with Machine Learning TechniqueS. I. Haruna0Han Zhu1Yasser E. Ibrahim2Jian Yang3AIB Farouk4Jianwen Shao5Musa Adamu6Omar Shabbir Ahmed7Engineering Management Department, College of Engineering, Prince Sultan UniversitySchool of Civil Engineering, Tianjin UniversityEngineering Management Department, College of Engineering, Prince Sultan UniversitySchool of Civil Engineering, Tianjin UniversityInterdisciplinary Research Center for Construction and Building Materials, King Fahd University of Petroleum and MineralsSchool of Civil Engineering, Ludong UniversityEngineering Management Department, College of Engineering, Prince Sultan UniversityEngineering Management Department, College of Engineering, Prince Sultan UniversityAbstract Polyurethane-based polymer concrete (PUC) has become a popular material for pavement repair. However, its compressive strength (f c) is essential to achieve effective repair work. This study predicted the compressive strength and evaluated the non-destructive test (NDT) properties of the PUC mixtures, prepared by mixing aggregate-to-polyurethane (PU) at 80/20, 85/15, and 90/10 ratios by weight. The experimental datasets from mechanical and NDT tests were utilized to train machine learning (ML) models, including multilinear regression (MLR), artificial neural network (ANN), support vector machine (SVM), Gaussian regression process (GPR), and stepwise regression (SWR) models for estimating the f c. Moreover, scanning electron microscopy (SEM) was employed to evaluate the microstructure of PUC. Feature selection tools were used to explore optimal input variables for estimating the (f c) of the PUC samples. The PUC-10 specimen revealed a maximum ultrasonic pulse velocity (UPV) value of 3.05 km/h. The microstructure analysis shows micro-voids with crack propagation between the aggregate and PU binder in the specimen containing 10% PU after testing. All the developed models showed high prediction accuracy. In addition, SVM outperformed other models at the training phase with R 2 values of 0.9614, and ANN demonstrated the highest performance at the testing phase with R 2 values of 0.9502.https://doi.org/10.1186/s40069-025-00803-2Machine learningPolyurethanePolymer concreteRepairCompressive strengthPavement
spellingShingle S. I. Haruna
Han Zhu
Yasser E. Ibrahim
Jian Yang
AIB Farouk
Jianwen Shao
Musa Adamu
Omar Shabbir Ahmed
Sustainable Polyurethane-Based Polymer Concrete: Mechanical and Non-destructive Properties with Machine Learning Technique
International Journal of Concrete Structures and Materials
Machine learning
Polyurethane
Polymer concrete
Repair
Compressive strength
Pavement
title Sustainable Polyurethane-Based Polymer Concrete: Mechanical and Non-destructive Properties with Machine Learning Technique
title_full Sustainable Polyurethane-Based Polymer Concrete: Mechanical and Non-destructive Properties with Machine Learning Technique
title_fullStr Sustainable Polyurethane-Based Polymer Concrete: Mechanical and Non-destructive Properties with Machine Learning Technique
title_full_unstemmed Sustainable Polyurethane-Based Polymer Concrete: Mechanical and Non-destructive Properties with Machine Learning Technique
title_short Sustainable Polyurethane-Based Polymer Concrete: Mechanical and Non-destructive Properties with Machine Learning Technique
title_sort sustainable polyurethane based polymer concrete mechanical and non destructive properties with machine learning technique
topic Machine learning
Polyurethane
Polymer concrete
Repair
Compressive strength
Pavement
url https://doi.org/10.1186/s40069-025-00803-2
work_keys_str_mv AT siharuna sustainablepolyurethanebasedpolymerconcretemechanicalandnondestructivepropertieswithmachinelearningtechnique
AT hanzhu sustainablepolyurethanebasedpolymerconcretemechanicalandnondestructivepropertieswithmachinelearningtechnique
AT yassereibrahim sustainablepolyurethanebasedpolymerconcretemechanicalandnondestructivepropertieswithmachinelearningtechnique
AT jianyang sustainablepolyurethanebasedpolymerconcretemechanicalandnondestructivepropertieswithmachinelearningtechnique
AT aibfarouk sustainablepolyurethanebasedpolymerconcretemechanicalandnondestructivepropertieswithmachinelearningtechnique
AT jianwenshao sustainablepolyurethanebasedpolymerconcretemechanicalandnondestructivepropertieswithmachinelearningtechnique
AT musaadamu sustainablepolyurethanebasedpolymerconcretemechanicalandnondestructivepropertieswithmachinelearningtechnique
AT omarshabbirahmed sustainablepolyurethanebasedpolymerconcretemechanicalandnondestructivepropertieswithmachinelearningtechnique