The Prediction of Self-Healing Capacity of Bacteria-Based Concrete Using Machine Learning Approaches

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autoren

  • Xiaoying Zhuang
  • Shuai Zhou

Organisationseinheiten

Externe Organisationen

  • Ton Duc Thang University
  • Chongqing University
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Seiten (von - bis)57-77
Seitenumfang21
FachzeitschriftComputers, Materials and Continua
Jahrgang59
Ausgabenummer1
PublikationsstatusVeröffentlicht - 2019

Abstract

Advances in machine learning (ML) methods are important in industrial engineering and attract great attention in recent years. However, a comprehensive comparative study of the most advanced ML algorithms is lacking. Six integrated ML approaches for the crack repairing capacity of the bacteria-based self-healing concrete are proposed and compared. Six ML algorithms, including the Support Vector Regression (SVR), Decision Tree Regression (DTR), Gradient Boosting Regression (GBR), Artificial Neural Network (ANN), Bayesian Ridge Regression (BRR) and Kernel Ridge Regression (KRR), are adopted for the relationship modeling to predict crack closure percentage (CCP). Particle Swarm Optimization (PSO) is used for the hyper-parameters tuning. The importance of parameters is analyzed. It is demonstrated that integrated ML approaches have great potential to predict the CCP, and PSO is efficient in the hyper-parameter tuning. This research provides useful information for the design of the bacteria-based self-healing concrete and can contribute to the design in the rest of industrial engineering.

ASJC Scopus Sachgebiete

Zitieren

The Prediction of Self-Healing Capacity of Bacteria-Based Concrete Using Machine Learning Approaches. / Zhuang, Xiaoying; Zhou, Shuai.
in: Computers, Materials and Continua, Jahrgang 59, Nr. 1, 2019, S. 57-77.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Download
@article{35aad46c165f4d228829e75d239a55b3,
title = "The Prediction of Self-Healing Capacity of Bacteria-Based Concrete Using Machine Learning Approaches",
abstract = "Advances in machine learning (ML) methods are important in industrial engineering and attract great attention in recent years. However, a comprehensive comparative study of the most advanced ML algorithms is lacking. Six integrated ML approaches for the crack repairing capacity of the bacteria-based self-healing concrete are proposed and compared. Six ML algorithms, including the Support Vector Regression (SVR), Decision Tree Regression (DTR), Gradient Boosting Regression (GBR), Artificial Neural Network (ANN), Bayesian Ridge Regression (BRR) and Kernel Ridge Regression (KRR), are adopted for the relationship modeling to predict crack closure percentage (CCP). Particle Swarm Optimization (PSO) is used for the hyper-parameters tuning. The importance of parameters is analyzed. It is demonstrated that integrated ML approaches have great potential to predict the CCP, and PSO is efficient in the hyper-parameter tuning. This research provides useful information for the design of the bacteria-based self-healing concrete and can contribute to the design in the rest of industrial engineering.",
keywords = "Bacteria, Crack closure percentage, Machine learning, Prediction, Self-healing concrete",
author = "Xiaoying Zhuang and Shuai Zhou",
note = "Funding information: Acknowledgement: This work was supported by Sofa-Kovalevskaja-Award of Alexander von Humboldt-Foundation.",
year = "2019",
doi = "10.32604/cmc.2019.04589",
language = "English",
volume = "59",
pages = "57--77",
journal = "Computers, Materials and Continua",
issn = "1546-2218",
publisher = "Tech Science Press",
number = "1",

}

Download

TY - JOUR

T1 - The Prediction of Self-Healing Capacity of Bacteria-Based Concrete Using Machine Learning Approaches

AU - Zhuang, Xiaoying

AU - Zhou, Shuai

N1 - Funding information: Acknowledgement: This work was supported by Sofa-Kovalevskaja-Award of Alexander von Humboldt-Foundation.

PY - 2019

Y1 - 2019

N2 - Advances in machine learning (ML) methods are important in industrial engineering and attract great attention in recent years. However, a comprehensive comparative study of the most advanced ML algorithms is lacking. Six integrated ML approaches for the crack repairing capacity of the bacteria-based self-healing concrete are proposed and compared. Six ML algorithms, including the Support Vector Regression (SVR), Decision Tree Regression (DTR), Gradient Boosting Regression (GBR), Artificial Neural Network (ANN), Bayesian Ridge Regression (BRR) and Kernel Ridge Regression (KRR), are adopted for the relationship modeling to predict crack closure percentage (CCP). Particle Swarm Optimization (PSO) is used for the hyper-parameters tuning. The importance of parameters is analyzed. It is demonstrated that integrated ML approaches have great potential to predict the CCP, and PSO is efficient in the hyper-parameter tuning. This research provides useful information for the design of the bacteria-based self-healing concrete and can contribute to the design in the rest of industrial engineering.

AB - Advances in machine learning (ML) methods are important in industrial engineering and attract great attention in recent years. However, a comprehensive comparative study of the most advanced ML algorithms is lacking. Six integrated ML approaches for the crack repairing capacity of the bacteria-based self-healing concrete are proposed and compared. Six ML algorithms, including the Support Vector Regression (SVR), Decision Tree Regression (DTR), Gradient Boosting Regression (GBR), Artificial Neural Network (ANN), Bayesian Ridge Regression (BRR) and Kernel Ridge Regression (KRR), are adopted for the relationship modeling to predict crack closure percentage (CCP). Particle Swarm Optimization (PSO) is used for the hyper-parameters tuning. The importance of parameters is analyzed. It is demonstrated that integrated ML approaches have great potential to predict the CCP, and PSO is efficient in the hyper-parameter tuning. This research provides useful information for the design of the bacteria-based self-healing concrete and can contribute to the design in the rest of industrial engineering.

KW - Bacteria

KW - Crack closure percentage

KW - Machine learning

KW - Prediction

KW - Self-healing concrete

UR - http://www.scopus.com/inward/record.url?scp=85064869529&partnerID=8YFLogxK

U2 - 10.32604/cmc.2019.04589

DO - 10.32604/cmc.2019.04589

M3 - Article

AN - SCOPUS:85064869529

VL - 59

SP - 57

EP - 77

JO - Computers, Materials and Continua

JF - Computers, Materials and Continua

SN - 1546-2218

IS - 1

ER -