Prediction of the Ultimate Impact Response of Concrete Strengthened with Polyurethane Grout as the Repair Material

The monolithic composite action of structures relies on the interface bond strength between concrete and the repair material. This study uses explainable deep learning techniques to evaluate the ultimate strength capacity (<i>U</i>s) of U-shaped normal concrete (NC) strengthened with pol...

Full description

Saved in:
Bibliographic Details
Main Authors: Sadi I. Haruna, Yasser E. Ibrahim, Sani I. Abba
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Infrastructures
Subjects:
Online Access:https://www.mdpi.com/2412-3811/10/6/128
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849432569653755904
author Sadi I. Haruna
Yasser E. Ibrahim
Sani I. Abba
author_facet Sadi I. Haruna
Yasser E. Ibrahim
Sani I. Abba
author_sort Sadi I. Haruna
collection DOAJ
description The monolithic composite action of structures relies on the interface bond strength between concrete and the repair material. This study uses explainable deep learning techniques to evaluate the ultimate strength capacity (<i>U</i>s) of U-shaped normal concrete (NC) strengthened with polyurethane grouting (PUG) materials. Machine learning algorithms (ML) such as Long Short-Term Memory (LSTM), Random Forest (RF), and Wide Neural Network (WNN) models were developed to estimate <i>U</i>s by considering five input parameters: the initial crack strength (<i>C</i>s), thickness of the grouting materials (<i>T</i>), mid-span deflection (<i>λ</i>), and peak applied load (<i>P</i>). The results indicated that LSTM models, particularly LSTM-M2 and LSTM-M3, demonstrated superior predictive accuracy and consistency in both the calibration and verification phases, as evidenced by high Pearson’s correlation coefficients (PCC = 0.9156 for LSTM-M2) and Willmott indices (WI = 0.7713 for LSTM-M2), and low error metrics (MSE = 0.0017, RMSE = 0.0418). The SHAP (SHapley Additive exPlanations) analysis showed that the thickness of the grouting materials and maximum load were the most significant parameters affecting the ultimate capacity of the composite U-shaped specimen. The RF model showed moderate improvements, with RF-M3 performing better than RF-M1 and RF-M2. The WNN models displayed varied performance, with WNN-M2 performing poorly due to significant scatter and deviation. The findings highlight the potential of LSTM models for the accurate and reliable prediction of the ultimate strength of composite U-shaped specimens.
format Article
id doaj-art-818ddbdf6cb74ce4a0236f08eb96799f
institution Kabale University
issn 2412-3811
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Infrastructures
spelling doaj-art-818ddbdf6cb74ce4a0236f08eb96799f2025-08-20T03:27:19ZengMDPI AGInfrastructures2412-38112025-05-0110612810.3390/infrastructures10060128Prediction of the Ultimate Impact Response of Concrete Strengthened with Polyurethane Grout as the Repair MaterialSadi I. Haruna0Yasser E. Ibrahim1Sani I. Abba2Engineering Management Department, College of Engineering, Prince Sultan University, Riyadh 11586, Saudi ArabiaEngineering Management Department, College of Engineering, Prince Sultan University, Riyadh 11586, Saudi ArabiaDepartment of Civil Engineering, Prince Mohammad Bin Fahd University, Al Khobar 31952, Saudi ArabiaThe monolithic composite action of structures relies on the interface bond strength between concrete and the repair material. This study uses explainable deep learning techniques to evaluate the ultimate strength capacity (<i>U</i>s) of U-shaped normal concrete (NC) strengthened with polyurethane grouting (PUG) materials. Machine learning algorithms (ML) such as Long Short-Term Memory (LSTM), Random Forest (RF), and Wide Neural Network (WNN) models were developed to estimate <i>U</i>s by considering five input parameters: the initial crack strength (<i>C</i>s), thickness of the grouting materials (<i>T</i>), mid-span deflection (<i>λ</i>), and peak applied load (<i>P</i>). The results indicated that LSTM models, particularly LSTM-M2 and LSTM-M3, demonstrated superior predictive accuracy and consistency in both the calibration and verification phases, as evidenced by high Pearson’s correlation coefficients (PCC = 0.9156 for LSTM-M2) and Willmott indices (WI = 0.7713 for LSTM-M2), and low error metrics (MSE = 0.0017, RMSE = 0.0418). The SHAP (SHapley Additive exPlanations) analysis showed that the thickness of the grouting materials and maximum load were the most significant parameters affecting the ultimate capacity of the composite U-shaped specimen. The RF model showed moderate improvements, with RF-M3 performing better than RF-M1 and RF-M2. The WNN models displayed varied performance, with WNN-M2 performing poorly due to significant scatter and deviation. The findings highlight the potential of LSTM models for the accurate and reliable prediction of the ultimate strength of composite U-shaped specimens.https://www.mdpi.com/2412-3811/10/6/128concretepolyurethane-based polymer groutmachine learningexplainable AI
spellingShingle Sadi I. Haruna
Yasser E. Ibrahim
Sani I. Abba
Prediction of the Ultimate Impact Response of Concrete Strengthened with Polyurethane Grout as the Repair Material
Infrastructures
concrete
polyurethane-based polymer grout
machine learning
explainable AI
title Prediction of the Ultimate Impact Response of Concrete Strengthened with Polyurethane Grout as the Repair Material
title_full Prediction of the Ultimate Impact Response of Concrete Strengthened with Polyurethane Grout as the Repair Material
title_fullStr Prediction of the Ultimate Impact Response of Concrete Strengthened with Polyurethane Grout as the Repair Material
title_full_unstemmed Prediction of the Ultimate Impact Response of Concrete Strengthened with Polyurethane Grout as the Repair Material
title_short Prediction of the Ultimate Impact Response of Concrete Strengthened with Polyurethane Grout as the Repair Material
title_sort prediction of the ultimate impact response of concrete strengthened with polyurethane grout as the repair material
topic concrete
polyurethane-based polymer grout
machine learning
explainable AI
url https://www.mdpi.com/2412-3811/10/6/128
work_keys_str_mv AT sadiiharuna predictionoftheultimateimpactresponseofconcretestrengthenedwithpolyurethanegroutastherepairmaterial
AT yassereibrahim predictionoftheultimateimpactresponseofconcretestrengthenedwithpolyurethanegroutastherepairmaterial
AT saniiabba predictionoftheultimateimpactresponseofconcretestrengthenedwithpolyurethanegroutastherepairmaterial