Prediction of permeability and unconfined compressive strength of pervious concrete using evolved support vector regression

Junbo Sun, Junfei Zhang, Yunfan Gu, Yimiao Huang, Yuantian Sun, Guowei Ma

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Pervious concrete is a widely used construction material thanks to its good drainage characteristics. Before application, its most important properties, i.e. the permeability coefficient (PC) and 28-day unconfined compressive strength (UCS) are required to be tested. However, conducting PC and UCS tests with multiple influencing variables is time-consuming and costly. To address this issue, this paper proposed, for the first time, an evolved support vector regression (ESVR) tuned by beetle antennae search (BAS) to accurately and effectively predict the PC and UCS of pervious concrete. To prepare the dataset of the ESVR model, 270 specimens in total were prepared and casted in a controlled environment in the laboratory. The water-to-cement (w/c) ratio, aggregate-to-cement (a/c) ratio, and aggregate size were selected as the crucial influencing variables for the inputs, while PC and UCS were the outputs of this model. The results indicate that both the PC and UCS firstly increased and then decreased with increasing w/c ratio. As the a/c ratio increased, PC increased, while UCS decreased. Moreover, BAS is more reliable and efficient than random hyper-parameter selection for hyper-parameter tuning. A low root-mean-square error (RMSE) and high correlation coefficient (R) indicate a relatively high predictive capability of the proposed ESVR model. The sensitivity analysis (SA) suggests the a/c ratio and aggregate size were the most sensitive variables for UCS and PC, respectively. This pioneering work provides a simple and convenient method for evaluating PC and UCS of pervious concrete.

Original languageEnglish
Pages (from-to)440-449
Number of pages10
JournalConstruction and Building Materials
Volume207
DOIs
Publication statusPublished - 20 May 2019

Fingerprint

Hydraulic conductivity
Compressive strength
Concretes
Cements
Antennas
Water
Mean square error
Drainage
Sensitivity analysis
Tuning

Cite this

@article{932aa2897002410b8586a433eba9cb37,
title = "Prediction of permeability and unconfined compressive strength of pervious concrete using evolved support vector regression",
abstract = "Pervious concrete is a widely used construction material thanks to its good drainage characteristics. Before application, its most important properties, i.e. the permeability coefficient (PC) and 28-day unconfined compressive strength (UCS) are required to be tested. However, conducting PC and UCS tests with multiple influencing variables is time-consuming and costly. To address this issue, this paper proposed, for the first time, an evolved support vector regression (ESVR) tuned by beetle antennae search (BAS) to accurately and effectively predict the PC and UCS of pervious concrete. To prepare the dataset of the ESVR model, 270 specimens in total were prepared and casted in a controlled environment in the laboratory. The water-to-cement (w/c) ratio, aggregate-to-cement (a/c) ratio, and aggregate size were selected as the crucial influencing variables for the inputs, while PC and UCS were the outputs of this model. The results indicate that both the PC and UCS firstly increased and then decreased with increasing w/c ratio. As the a/c ratio increased, PC increased, while UCS decreased. Moreover, BAS is more reliable and efficient than random hyper-parameter selection for hyper-parameter tuning. A low root-mean-square error (RMSE) and high correlation coefficient (R) indicate a relatively high predictive capability of the proposed ESVR model. The sensitivity analysis (SA) suggests the a/c ratio and aggregate size were the most sensitive variables for UCS and PC, respectively. This pioneering work provides a simple and convenient method for evaluating PC and UCS of pervious concrete.",
keywords = "Beetle antennae search algorithm, Evolved support vector regression, Permeability, Pervious concrete, Prediction, Unconfined compressive strength",
author = "Junbo Sun and Junfei Zhang and Yunfan Gu and Yimiao Huang and Yuantian Sun and Guowei Ma",
year = "2019",
month = "5",
day = "20",
doi = "10.1016/j.conbuildmat.2019.02.117",
language = "English",
volume = "207",
pages = "440--449",
journal = "Construction and Building Materials",
issn = "0950-0618",
publisher = "Elsevier",

}

Prediction of permeability and unconfined compressive strength of pervious concrete using evolved support vector regression. / Sun, Junbo; Zhang, Junfei; Gu, Yunfan; Huang, Yimiao; Sun, Yuantian; Ma, Guowei.

In: Construction and Building Materials, Vol. 207, 20.05.2019, p. 440-449.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Prediction of permeability and unconfined compressive strength of pervious concrete using evolved support vector regression

AU - Sun, Junbo

AU - Zhang, Junfei

AU - Gu, Yunfan

AU - Huang, Yimiao

AU - Sun, Yuantian

AU - Ma, Guowei

PY - 2019/5/20

Y1 - 2019/5/20

N2 - Pervious concrete is a widely used construction material thanks to its good drainage characteristics. Before application, its most important properties, i.e. the permeability coefficient (PC) and 28-day unconfined compressive strength (UCS) are required to be tested. However, conducting PC and UCS tests with multiple influencing variables is time-consuming and costly. To address this issue, this paper proposed, for the first time, an evolved support vector regression (ESVR) tuned by beetle antennae search (BAS) to accurately and effectively predict the PC and UCS of pervious concrete. To prepare the dataset of the ESVR model, 270 specimens in total were prepared and casted in a controlled environment in the laboratory. The water-to-cement (w/c) ratio, aggregate-to-cement (a/c) ratio, and aggregate size were selected as the crucial influencing variables for the inputs, while PC and UCS were the outputs of this model. The results indicate that both the PC and UCS firstly increased and then decreased with increasing w/c ratio. As the a/c ratio increased, PC increased, while UCS decreased. Moreover, BAS is more reliable and efficient than random hyper-parameter selection for hyper-parameter tuning. A low root-mean-square error (RMSE) and high correlation coefficient (R) indicate a relatively high predictive capability of the proposed ESVR model. The sensitivity analysis (SA) suggests the a/c ratio and aggregate size were the most sensitive variables for UCS and PC, respectively. This pioneering work provides a simple and convenient method for evaluating PC and UCS of pervious concrete.

AB - Pervious concrete is a widely used construction material thanks to its good drainage characteristics. Before application, its most important properties, i.e. the permeability coefficient (PC) and 28-day unconfined compressive strength (UCS) are required to be tested. However, conducting PC and UCS tests with multiple influencing variables is time-consuming and costly. To address this issue, this paper proposed, for the first time, an evolved support vector regression (ESVR) tuned by beetle antennae search (BAS) to accurately and effectively predict the PC and UCS of pervious concrete. To prepare the dataset of the ESVR model, 270 specimens in total were prepared and casted in a controlled environment in the laboratory. The water-to-cement (w/c) ratio, aggregate-to-cement (a/c) ratio, and aggregate size were selected as the crucial influencing variables for the inputs, while PC and UCS were the outputs of this model. The results indicate that both the PC and UCS firstly increased and then decreased with increasing w/c ratio. As the a/c ratio increased, PC increased, while UCS decreased. Moreover, BAS is more reliable and efficient than random hyper-parameter selection for hyper-parameter tuning. A low root-mean-square error (RMSE) and high correlation coefficient (R) indicate a relatively high predictive capability of the proposed ESVR model. The sensitivity analysis (SA) suggests the a/c ratio and aggregate size were the most sensitive variables for UCS and PC, respectively. This pioneering work provides a simple and convenient method for evaluating PC and UCS of pervious concrete.

KW - Beetle antennae search algorithm

KW - Evolved support vector regression

KW - Permeability

KW - Pervious concrete

KW - Prediction

KW - Unconfined compressive strength

UR - http://www.scopus.com/inward/record.url?scp=85062107500&partnerID=8YFLogxK

U2 - 10.1016/j.conbuildmat.2019.02.117

DO - 10.1016/j.conbuildmat.2019.02.117

M3 - Article

VL - 207

SP - 440

EP - 449

JO - Construction and Building Materials

JF - Construction and Building Materials

SN - 0950-0618

ER -