A machine learning based design optimization method for electrically conductive cementitious composites

Wei Dong

doi:10.26182/971h-2e02

A machine learning based design optimization method for electrically conductive cementitious composites

Wei Dong

School of Engineering

Research output: Thesis › Doctoral Thesis

158 Downloads (Pure)

Abstract

The thesis conducts a comprehensive study on the electrical resistivity of cementitious composites. It aims at providing efficient and reliable modelling and design methods for electrically conductive cementitious composites. First, an XGBoost-based calculation model is developed to normalize the electrical resistivity measurement results of cementitious composites. Then, an integrated machine learning modelling method is proposed for the resistivity prediction of electrically conductive cementitious composites. A novel multi-objective design optimization method is presented for cementitious composites reinforced by graphite-based nanomaterials. Finally, a composite graphene nanoplatelet is investigated in producing a more efficient electrically conductive cementitious composite by the presented design method.

Original language	English
Qualification	Doctor of Philosophy
Awarding Institution	The University of Western Australia
Supervisors/Advisors	Huang, Yimiao, Supervisor Lehane, Barry, Supervisor Ma, Guowei, Supervisor
Award date	4 Mar 2023
DOIs	https://doi.org/10.26182/971h-2e02
Publication status	Unpublished - 2023

Access to Document

10.26182/971h-2e02

THESIS - DOCTOR OF PHILOSOPHY - DONG Wei - 2023
This work is protected by Copyright. You may print or download ONE copy of this document for the purpose of your own non-commercial research or study. Any other use requires permission from the copyright owner. The Copyright Act requires you to attribute any copyright works you quote or paraphrase.

3 Finished

Development of 3D printing conductive concrete for EMP shielding
Aslani, F. & Ma, G.
Australian Research Council
1/07/18 → 1/10/21
Project: Research
ARC Research Hub for Nanoscience-Based Construction Material Manufacturing
Hu, Y.
Australian Research Council
1/01/17 → 31/12/21
Project: Research
Development of nano reinforced concrete using boron nitride nanosheets
Ma, G.
Australian Research Council
1/01/16 → 31/12/19
Project: Research

4 Article

An artificial intelligence-based conductivity prediction and feature analysis of carbon fiber reinforced cementitious composite for non-destructive structural health monitoring
Dong, W., Huang, Y., Lehane, B. & Ma, G., 1 Sept 2022, In: Engineering Structures. 266, 114578.
Research output: Contribution to journal › Article › peer-review
6 Citations (Scopus)
Multi-objective design optimization for graphite-based nanomaterials reinforced cementitious composites: A data-driven method with machine learning and NSGA-Ⅱ
Dong, W., Huang, Y., Lehane, B. & Ma, G., 9 May 2022, In: Construction and Building Materials. 331, 127198.
Research output: Contribution to journal › Article › peer-review
15 Citations (Scopus)
Mechanical and electrical properties of concrete incorporating an iron-particle contained nano-graphite by-product
Dong, W., Huang, Y., Lehane, B., Aslani, F. & Ma, G., 8 Feb 2021, In: Construction and Building Materials. 270, 121377.
Research output: Contribution to journal › Article › peer-review

Open Access
File
18 Citations (Scopus)

32 Downloads (Pure)

Cite this

@phdthesis{def41d7d2ec2481696728b6b61e2e064,

title = "A machine learning based design optimization method for electrically conductive cementitious composites",

abstract = "The thesis conducts a comprehensive study on the electrical resistivity of cementitious composites. It aims at providing efficient and reliable modelling and design methods for electrically conductive cementitious composites. First, an XGBoost-based calculation model is developed to normalize the electrical resistivity measurement results of cementitious composites. Then, an integrated machine learning modelling method is proposed for the resistivity prediction of electrically conductive cementitious composites. A novel multi-objective design optimization method is presented for cementitious composites reinforced by graphite-based nanomaterials. Finally, a composite graphene nanoplatelet is investigated in producing a more efficient electrically conductive cementitious composite by the presented design method.",

keywords = "Electrically conductive cementitious composite, Electrical resistivity prediction, Machine learning modelling, Quantitative analysis on factor influence, Multi-objective design optimization, Composite graphite-based nanomaterial",

author = "Wei Dong",

year = "2023",

doi = "10.26182/971h-2e02",

language = "English",

school = "The University of Western Australia",

}

TY - THES

T1 - A machine learning based design optimization method for electrically conductive cementitious composites

AU - Dong, Wei

PY - 2023

Y1 - 2023

N2 - The thesis conducts a comprehensive study on the electrical resistivity of cementitious composites. It aims at providing efficient and reliable modelling and design methods for electrically conductive cementitious composites. First, an XGBoost-based calculation model is developed to normalize the electrical resistivity measurement results of cementitious composites. Then, an integrated machine learning modelling method is proposed for the resistivity prediction of electrically conductive cementitious composites. A novel multi-objective design optimization method is presented for cementitious composites reinforced by graphite-based nanomaterials. Finally, a composite graphene nanoplatelet is investigated in producing a more efficient electrically conductive cementitious composite by the presented design method.

AB - The thesis conducts a comprehensive study on the electrical resistivity of cementitious composites. It aims at providing efficient and reliable modelling and design methods for electrically conductive cementitious composites. First, an XGBoost-based calculation model is developed to normalize the electrical resistivity measurement results of cementitious composites. Then, an integrated machine learning modelling method is proposed for the resistivity prediction of electrically conductive cementitious composites. A novel multi-objective design optimization method is presented for cementitious composites reinforced by graphite-based nanomaterials. Finally, a composite graphene nanoplatelet is investigated in producing a more efficient electrically conductive cementitious composite by the presented design method.

KW - Electrically conductive cementitious composite

KW - Electrical resistivity prediction

KW - Machine learning modelling

KW - Quantitative analysis on factor influence

KW - Multi-objective design optimization

KW - Composite graphite-based nanomaterial

U2 - 10.26182/971h-2e02

DO - 10.26182/971h-2e02

M3 - Doctoral Thesis

ER -

A machine learning based design optimization method for electrically conductive cementitious composites

Abstract

Access to Document

Fingerprint

Projects

Development of 3D printing conductive concrete for EMP shielding

ARC Research Hub for Nanoscience-Based Construction Material Manufacturing

Development of nano reinforced concrete using boron nitride nanosheets

Research output

An artificial intelligence-based conductivity prediction and feature analysis of carbon fiber reinforced cementitious composite for non-destructive structural health monitoring

Multi-objective design optimization for graphite-based nanomaterials reinforced cementitious composites: A data-driven method with machine learning and NSGA-Ⅱ

Mechanical and electrical properties of concrete incorporating an iron-particle contained nano-graphite by-product

Cite this