Exploring the Elastic Properties of Interfacial Transition Zone in Concrete Materials Using an Ensemble Learning Approach

被引：0
作者：
Xue, Jing [1 ,2 ]
Cao, Yajun [3 ]
Zhao, Xiaolong [4 ]
Shao, Jianfu [5 ,6 ]
机构：
[1] Beijing Res Inst Uranium Geol, Beijing, Peoples R China
[2] CAEA Innovat Ctr Geol Disposal High Level Radioact, Beijing, Peoples R China
[3] Hohai Univ, Coll Civil & Transportat Engn, Nanjing, Peoples R China
[4] Shandong Agr Univ, Coll Water Conservancy & Civil Engn, Tai An, Peoples R China
[5] Univ Lille, CNRS, Cent Lille, LaMcube, Lille, France
[6] Inst Univ France, Paris, France
来源：
INTERNATIONAL JOURNAL FOR NUMERICAL AND ANALYTICAL METHODS IN GEOMECHANICS | 2025年
关键词：
artificial neural network; concrete; composites; deep learning; ensemble learning approach; interfacial transition zone; MECHANICAL-PROPERTIES; COMPRESSIVE STRENGTH; NUMERICAL-METHOD; BULK MODULUS; AGGREGATE; MODEL; ROCK; COMPOSITES; ITZ;
D O I：
10.1002/nag.4009
中图分类号：
P5 [地质学];
学科分类号：
0709 ; 081803 ;
摘要：
Concrete materials consist of multiple phases with distinct mechanical properties, making it essential to accurately identify the mechanical behavior of both constituent phases and their interfaces for effective multiscale modeling. This study estimates the elastic properties of the interfacial transition zone using a machine learning (ML) approach. A dataset is generated from numerical simulations based on a Fast Fourier Transform method, validated against experimental data. Seven ML models are developed and trained, including four independent artificial neural networks and three ensemble models. The best-performing ensemble model is identified and described in detail. Further analysis, including over-fitting analysis, parameter investigation, and sensitivity study, confirms the model's validity and practical applicability.
引用
收藏
页数：20
相关论文
共 72 条
[1]   Prediction of Compressive Strength of Fly Ash Based Concrete Using Individual and Ensemble Algorithm [J].
Ahmad, Ayaz ;
Farooq, Furqan ;
Niewiadomski, Pawel ;
Ostrowski, Krzysztof ;
Akbar, Arslan ;
Aslam, Fahid ;
Alyousef, Rayed .
MATERIALS, 2021, 14 (04) :1-21
[2]   Analysis and prediction of the effect of Nanosilica on the compressive strength of concrete with different mix proportions and specimen sizes using various numerical approaches [J].
Ali, Reyam ;
Muayad, Maryam ;
Mohammed, Ahmed Salih ;
Asteris, Panagiotis G. .
STRUCTURAL CONCRETE, 2023, 24 (03) :4161-4184
[3]   Prediction of mechanical and durability characteristics of concrete including slag and recycled aggregate concrete with artificial neural networks (ANNs) [J].
Amiri, Mostafa ;
Hatami, Farzad .
CONSTRUCTION AND BUILDING MATERIALS, 2022, 325
[4]   Predicting the unconfined compressive strength of granite using only two non-destructive test indexes [J].
Armaghani, Daniel J. ;
Mamou, Anna ;
Maraveas, Chrysanthos ;
Roussis, Panayiotis C. ;
Siorikis, Vassilis G. ;
Skentou, Athanasia D. ;
Asteris, Panagiotis G. .
GEOMECHANICS AND ENGINEERING, 2021, 25 (04) :317-330
[5]   Predicting uniaxial compressive strength of rocks using ANN models: Incorporating porosity, compressional wave velocity, and schmidt hammer data [J].
Asteris, Panagiotis G. ;
Karoglou, Maria ;
Skentou, Athanasia D. ;
Vasconcelos, Graca ;
He, Mingming ;
Bakolas, Asterios ;
Zhou, Jian ;
Armaghani, Danial Jahed .
ULTRASONICS, 2024, 141
[6]   Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models [J].
Asteris, Panagiotis G. ;
Skentou, Athanasia D. ;
Bardhan, Abidhan ;
Samui, Pijush ;
Pilakoutas, Kypros .
CEMENT AND CONCRETE RESEARCH, 2021, 145 (145)
[7]   Prediction of cement-based mortars compressive strength using machine learning techniques [J].
Asteris, Panagiotis G. ;
Koopialipoor, Mohammadreza ;
Armaghani, Danial J. ;
Kotsonis, Evgenios A. ;
Lourenco, Paulo B. .
NEURAL COMPUTING & APPLICATIONS, 2021, 33 (19) :13089-13121
[8]   Feed-Forward Neural Network Prediction of the Mechanical Properties of Sandcrete Materials [J].
Asteris, Panagiotis G. ;
Roussis, Panayiotis C. ;
Douvika, Maria G. .
SENSORS, 2017, 17 (06)
[9]   Predicting the shear strength of rectangular RC beams strengthened with externally-bonded FRP composites using constrained monotonic neural networks [J].
Benzaamia, Ali ;
Ghrici, Mohamed ;
Rebouh, Redouane ;
Zygouris, Nikos ;
Asteris, Panagiotis G. .
ENGINEERING STRUCTURES, 2024, 313
[10]   Numerical study of rock and concrete behaviour by discrete element modelling [J].
Camborde, F ;
Mariotti, C ;
Donzé, FV .
COMPUTERS AND GEOTECHNICS, 2000, 27 (04) :225-247
12345678