APPLICATION OF SOFT COMPUTING METHODOLOGIES TO PREDICT THE 28-DAY COMPRESSIVE STRENGTH OF SHOTCRETE: A COMPARATIVE STUDY OF INDIVIDUAL AND HYBRID MODELS

Shotcreting is a popular construction technique with wide-ranging applications in mining and civil engineering. Compressive strength is a primary mechanical property of shotcrete with particular importance for project safety, which highly depends on its mix design. But in practice, there is no relia...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Mahtab Torkan, Hamid Kalhori, Mohammad Hossein Jalalian
Formato: article
Lenguaje:EN
HR
Publicado: Faculty of Mining, Geology and Petroleum Engineering 2021
Materias:
Acceso en línea:https://doaj.org/article/f5be8c1eb965412db7e306d40fa05da6
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:f5be8c1eb965412db7e306d40fa05da6
record_format dspace
spelling oai:doaj.org-article:f5be8c1eb965412db7e306d40fa05da62021-12-05T20:13:12ZAPPLICATION OF SOFT COMPUTING METHODOLOGIES TO PREDICT THE 28-DAY COMPRESSIVE STRENGTH OF SHOTCRETE: A COMPARATIVE STUDY OF INDIVIDUAL AND HYBRID MODELS1849-0409https://doaj.org/article/f5be8c1eb965412db7e306d40fa05da62021-01-01T00:00:00Zhttps://hrcak.srce.hr/file/386657https://doaj.org/toc/1849-0409Shotcreting is a popular construction technique with wide-ranging applications in mining and civil engineering. Compressive strength is a primary mechanical property of shotcrete with particular importance for project safety, which highly depends on its mix design. But in practice, there is no reliable and accurate method to predict this strength. In this study, existing experimental data related to shotcretes with 59 different mix designs are used to develop a series of soft computing methodologies, including individual artificial neural network, support vector regression, and M5P model tree and their hybrids with the fuzzy c-means clustering algorithm so as to predict the 28-day compressive strength of shotcrete. Analysis of the results shows the superiority of the hybrid model over the individual models in predicting the compressive strength of shotcrete. Overall, data clustering prior to use of machine learning techniques leads to certain improvement in their performance and reliability and generalizability of their results. In particular, the M5P model tree exhibits excellent capability in anticipating the compressive strength of shotcrete.Mahtab TorkanHamid KalhoriMohammad Hossein JalalianFaculty of Mining, Geology and Petroleum EngineeringarticleShotcreteCompressive StrengthMachine learning techniquesHybrid modelMining engineering. MetallurgyTN1-997GeologyQE1-996.5ENHRRudarsko-geološko-naftni Zbornik, Vol 36, Iss 5, Pp 33-48 (2021)
institution DOAJ
collection DOAJ
language EN
HR
topic Shotcrete
Compressive Strength
Machine learning techniques
Hybrid model
Mining engineering. Metallurgy
TN1-997
Geology
QE1-996.5
spellingShingle Shotcrete
Compressive Strength
Machine learning techniques
Hybrid model
Mining engineering. Metallurgy
TN1-997
Geology
QE1-996.5
Mahtab Torkan
Hamid Kalhori
Mohammad Hossein Jalalian
APPLICATION OF SOFT COMPUTING METHODOLOGIES TO PREDICT THE 28-DAY COMPRESSIVE STRENGTH OF SHOTCRETE: A COMPARATIVE STUDY OF INDIVIDUAL AND HYBRID MODELS
description Shotcreting is a popular construction technique with wide-ranging applications in mining and civil engineering. Compressive strength is a primary mechanical property of shotcrete with particular importance for project safety, which highly depends on its mix design. But in practice, there is no reliable and accurate method to predict this strength. In this study, existing experimental data related to shotcretes with 59 different mix designs are used to develop a series of soft computing methodologies, including individual artificial neural network, support vector regression, and M5P model tree and their hybrids with the fuzzy c-means clustering algorithm so as to predict the 28-day compressive strength of shotcrete. Analysis of the results shows the superiority of the hybrid model over the individual models in predicting the compressive strength of shotcrete. Overall, data clustering prior to use of machine learning techniques leads to certain improvement in their performance and reliability and generalizability of their results. In particular, the M5P model tree exhibits excellent capability in anticipating the compressive strength of shotcrete.
format article
author Mahtab Torkan
Hamid Kalhori
Mohammad Hossein Jalalian
author_facet Mahtab Torkan
Hamid Kalhori
Mohammad Hossein Jalalian
author_sort Mahtab Torkan
title APPLICATION OF SOFT COMPUTING METHODOLOGIES TO PREDICT THE 28-DAY COMPRESSIVE STRENGTH OF SHOTCRETE: A COMPARATIVE STUDY OF INDIVIDUAL AND HYBRID MODELS
title_short APPLICATION OF SOFT COMPUTING METHODOLOGIES TO PREDICT THE 28-DAY COMPRESSIVE STRENGTH OF SHOTCRETE: A COMPARATIVE STUDY OF INDIVIDUAL AND HYBRID MODELS
title_full APPLICATION OF SOFT COMPUTING METHODOLOGIES TO PREDICT THE 28-DAY COMPRESSIVE STRENGTH OF SHOTCRETE: A COMPARATIVE STUDY OF INDIVIDUAL AND HYBRID MODELS
title_fullStr APPLICATION OF SOFT COMPUTING METHODOLOGIES TO PREDICT THE 28-DAY COMPRESSIVE STRENGTH OF SHOTCRETE: A COMPARATIVE STUDY OF INDIVIDUAL AND HYBRID MODELS
title_full_unstemmed APPLICATION OF SOFT COMPUTING METHODOLOGIES TO PREDICT THE 28-DAY COMPRESSIVE STRENGTH OF SHOTCRETE: A COMPARATIVE STUDY OF INDIVIDUAL AND HYBRID MODELS
title_sort application of soft computing methodologies to predict the 28-day compressive strength of shotcrete: a comparative study of individual and hybrid models
publisher Faculty of Mining, Geology and Petroleum Engineering
publishDate 2021
url https://doaj.org/article/f5be8c1eb965412db7e306d40fa05da6
work_keys_str_mv AT mahtabtorkan applicationofsoftcomputingmethodologiestopredictthe28daycompressivestrengthofshotcreteacomparativestudyofindividualandhybridmodels
AT hamidkalhori applicationofsoftcomputingmethodologiestopredictthe28daycompressivestrengthofshotcreteacomparativestudyofindividualandhybridmodels
AT mohammadhosseinjalalian applicationofsoftcomputingmethodologiestopredictthe28daycompressivestrengthofshotcreteacomparativestudyofindividualandhybridmodels
_version_ 1718371097871646720