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

Wei Dong

Research output: ThesisDoctoral Thesis

289 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 languageEnglish
QualificationDoctor of Philosophy
Awarding Institution
  • The University of Western Australia
Supervisors/Advisors
  • Huang, Yimiao, Supervisor
  • Lehane, Barry, Supervisor
  • Ma, Guowei, Supervisor
Award date4 Mar 2023
DOIs
Publication statusUnpublished - 2023

Fingerprint

Dive into the research topics of 'A machine learning based design optimization method for electrically conductive cementitious composites'. Together they form a unique fingerprint.

Cite this