Soft computing-based prediction models for compressive strength of concrete
The complexity of concrete's composition makes it difficult to predict its compressive strength, which is a highly valuable and desired characteristic. Traditional methods for prediction are expensive and time-consuming, resulting in limited data availability. However, modern soft-computing mod...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-12-01
|
Series: | Case Studies in Construction Materials |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2214509523005016 |
_version_ | 1797454665790521344 |
---|---|
author | Manish Kumar Rahul Biswas Divesh Ranjan Kumar Pijush Samui Mosbeh R. Kaloop Mohamed Eldessouki |
author_facet | Manish Kumar Rahul Biswas Divesh Ranjan Kumar Pijush Samui Mosbeh R. Kaloop Mohamed Eldessouki |
author_sort | Manish Kumar |
collection | DOAJ |
description | The complexity of concrete's composition makes it difficult to predict its compressive strength, which is a highly valuable and desired characteristic. Traditional methods for prediction are expensive and time-consuming, resulting in limited data availability. However, modern soft-computing models have emerged as a reliable solution for accurately forecasting concrete's compressive strength. The research proposes a novel Deep Neural Network (DNN), Multivariate Adaptive Regression Splines (MARS) and Extreme Learning Machine (ELM) based machine learning (ML) models for forecasting the compressive strength of concrete added with various proportions of fly ash and silica fume. For this purpose, a dataset of 144 trials, having 8 input parameters is taken from the literature. The performance of the models is confirmed using various statistical parameters. Rank Analysis reveals that DNN is the best-performing model (Rank =52, RTR2 =0.983 and RTs2 =0.954), closely followed by MARS (Rank =38, RTR2 =0.974 and RTs2 =0.956); while ELM lags behind the other two counterparts. The results are further confirmed using an error matrix, external validation and AIC criteria. The visual interpretation is provided using the Taylor diagram. MARS has the edge over the other two models in terms of providing a user-friendly solution. |
first_indexed | 2024-03-09T15:40:23Z |
format | Article |
id | doaj.art-e951474f091d43ce9926a6eb8c698105 |
institution | Directory Open Access Journal |
issn | 2214-5095 |
language | English |
last_indexed | 2024-03-09T15:40:23Z |
publishDate | 2023-12-01 |
publisher | Elsevier |
record_format | Article |
series | Case Studies in Construction Materials |
spelling | doaj.art-e951474f091d43ce9926a6eb8c6981052023-11-25T04:48:17ZengElsevierCase Studies in Construction Materials2214-50952023-12-0119e02321Soft computing-based prediction models for compressive strength of concreteManish Kumar0Rahul Biswas1Divesh Ranjan Kumar2Pijush Samui3Mosbeh R. Kaloop4Mohamed Eldessouki5Department of Civil Engineering, SRM Institute of Science and Technology (SRMIST) Tiruchirappalli, India,Department of Applied Mechanics, Visvesvaraya National Institute of Technology, Nagpur, IndiaDepartment of Civil Engineering NIT Patna, IndiaDepartment of Civil Engineering NIT Patna, IndiaDepartment of Civil and Environmental Engineering, Incheon National University, Incheon, South Korea; Public Works Engineering Department, Mansoura University, Mansoura, Egypt; DigInnoCent s.r.o., Liberec, Czech Republic; Digital InnoCent Ltd., London, United Kingdom; Corresponding author at: Department of Civil and Environmental Engineering, Incheon National University, Incheon, South Korea.DigInnoCent s.r.o., Liberec, Czech Republic; Faculty of Engineering, Mansoura University, Mansoura, Egypt; Digital InnoCent Ltd., London, United KingdomThe complexity of concrete's composition makes it difficult to predict its compressive strength, which is a highly valuable and desired characteristic. Traditional methods for prediction are expensive and time-consuming, resulting in limited data availability. However, modern soft-computing models have emerged as a reliable solution for accurately forecasting concrete's compressive strength. The research proposes a novel Deep Neural Network (DNN), Multivariate Adaptive Regression Splines (MARS) and Extreme Learning Machine (ELM) based machine learning (ML) models for forecasting the compressive strength of concrete added with various proportions of fly ash and silica fume. For this purpose, a dataset of 144 trials, having 8 input parameters is taken from the literature. The performance of the models is confirmed using various statistical parameters. Rank Analysis reveals that DNN is the best-performing model (Rank =52, RTR2 =0.983 and RTs2 =0.954), closely followed by MARS (Rank =38, RTR2 =0.974 and RTs2 =0.956); while ELM lags behind the other two counterparts. The results are further confirmed using an error matrix, external validation and AIC criteria. The visual interpretation is provided using the Taylor diagram. MARS has the edge over the other two models in terms of providing a user-friendly solution.http://www.sciencedirect.com/science/article/pii/S2214509523005016Machine learningConcreteELMMARSDNN |
spellingShingle | Manish Kumar Rahul Biswas Divesh Ranjan Kumar Pijush Samui Mosbeh R. Kaloop Mohamed Eldessouki Soft computing-based prediction models for compressive strength of concrete Case Studies in Construction Materials Machine learning Concrete ELM MARS DNN |
title | Soft computing-based prediction models for compressive strength of concrete |
title_full | Soft computing-based prediction models for compressive strength of concrete |
title_fullStr | Soft computing-based prediction models for compressive strength of concrete |
title_full_unstemmed | Soft computing-based prediction models for compressive strength of concrete |
title_short | Soft computing-based prediction models for compressive strength of concrete |
title_sort | soft computing based prediction models for compressive strength of concrete |
topic | Machine learning Concrete ELM MARS DNN |
url | http://www.sciencedirect.com/science/article/pii/S2214509523005016 |
work_keys_str_mv | AT manishkumar softcomputingbasedpredictionmodelsforcompressivestrengthofconcrete AT rahulbiswas softcomputingbasedpredictionmodelsforcompressivestrengthofconcrete AT diveshranjankumar softcomputingbasedpredictionmodelsforcompressivestrengthofconcrete AT pijushsamui softcomputingbasedpredictionmodelsforcompressivestrengthofconcrete AT mosbehrkaloop softcomputingbasedpredictionmodelsforcompressivestrengthofconcrete AT mohamedeldessouki softcomputingbasedpredictionmodelsforcompressivestrengthofconcrete |