Machine Learning Driven Fluidity and Rheological Properties Prediction of Fresh Cement-Based Materials

被引:0
|
作者
Liu, Yi [1 ,2 ]
Mohammed, Zeyad M. A. [1 ,2 ]
Ma, Jialu [1 ,2 ]
Xia, Rui [1 ,2 ]
Fan, Dongdong [3 ]
Tang, Jie [3 ]
Yuan, Qiang [1 ,2 ]
机构
[1] Cent South Univ, Sch Civil Engn, Changsha 410075, Peoples R China
[2] Natl Engn Res Ctr High speed Railway Construct Tec, Changsha 410075, Peoples R China
[3] Anhui Engineer Mat Technol Co Ltd, CTCE Grp, Hefei 230041, Peoples R China
基金
国家重点研发计划;
关键词
machine learning; workability; rheological property; feature importance analysis; PLASTIC VISCOSITY; OPTIMIZATION; PERFORMANCE; CONCRETE; MIXTURE;
D O I
10.3390/ma17225400
中图分类号
O64 [物理化学(理论化学)、化学物理学];
学科分类号
070304 ; 081704 ;
摘要
Controlling workability during the design stage of cement-based material mix ratios is a highly time-consuming and labor-intensive task. Applying artificial intelligence (AI) methods to predict and optimize the workability of cement-based materials can significantly enhance the efficiency of mix design. In this study, experimental testing was conducted to create a dataset of 233 samples, including fluidity, dynamic yield stress, and plastic viscosity of cement-based materials. The proportions of cement, fly ash (FA), silica fume (SF), water, superplasticizer (SP), hydroxypropyl methylcellulose (HPMC), and sand were selected as inputs. Machine learning (ML) methods were employed to establish predictive models for these three early workability indicators. To improve prediction capability, optimized hybrid models, such as Particle Swarm Optimization (PSO)-based CatBoost and XGBoost, were adopted. Furthermore, the influence of individual input variables on each workability indicator of the cement-based material was examined using Shapley Additive Explanations (SHAP) and Partial Dependence Plot (PDP) analyses. This study provides a novel reference for achieving rapid and accurate control of cement-based material workability.
引用
收藏
页数:21
相关论文
共 50 条
  • [31] Molecular Simulation of Cement-Based Materials and Their Properties
    Bahraq, Ashraf A.
    Al-Osta, Mohammed A.
    Al-Amoudi, Omar S. Baghabra
    Obot, I. B.
    Maslehuddin, Mohammed
    Ahmed, Habib-Ur-Rehman
    Saleh, Tawfik A.
    ENGINEERING, 2022, 15 : 165 - 178
  • [32] The interaction of sodium citrate and polycarboxylate-based superplasticizer on the rheological properties and viscoelasticity of cement-based materials
    Liu, Yu
    Zhang, Zengqi
    Jing, Rui
    Yan, Peiyu
    CONSTRUCTION AND BUILDING MATERIALS, 2021, 293
  • [33] The study of effect of carbon nanotubes on the compressive strength of cement-based materials based on machine learning
    Li, Yue
    Li, Hongwen
    jin, Caiyun
    Shen, Jiale
    Construction and Building Materials, 2022, 358
  • [34] PREDICTION OF THE RAM EXTRUSION FORCE OF CEMENT-BASED MATERIALS
    Perrot, Arnaud
    Rangeard, Davien
    Melinge, Yannick
    APPLIED RHEOLOGY, 2014, 24 (05)
  • [35] The study of effect of carbon nanotubes on the compressive strength of cement-based materials based on machine learning
    Li, Yue
    Li, Hongwen
    Jin, Caiyun
    Shen, Jiale
    CONSTRUCTION AND BUILDING MATERIALS, 2022, 358
  • [36] Rheological Properties and Flow Behaviour of Cement-Based Materials Modified by Carbon Nanotubes and Plasticising Admixtures
    Skripkiunas, Gintautas
    Karpova, Ekaterina
    Bendoraitiene, Joana
    Barauskas, Irmantas
    FLUIDS, 2020, 5 (04)
  • [37] Assess the interaction of water reducers and accelerators on the rheological and early hydration properties of cement-based materials
    Song, Pengfei
    Wang, Xuhao
    Wang, Yuan
    Zhou, Jie
    Qiu, Heping
    Rahimi, Arezoo
    Ingham, Jason
    JOURNAL OF MATERIALS RESEARCH AND TECHNOLOGY-JMR&T, 2025, 36 : 806 - 822
  • [38] New biopolymers as viscosity-modifying admixtures to improve the rheological properties of cement-based materials
    Gonzalez-Avina, J. V.
    Hosseinpoor, Masoud
    Yahia, Ammar
    Durran-Herrera, A.
    CEMENT & CONCRETE COMPOSITES, 2024, 146
  • [39] Cement-based materials
    Young, JF
    CURRENT OPINION IN SOLID STATE & MATERIALS SCIENCE, 1998, 3 (05): : 505 - 509
  • [40] Assessing the fresh properties of printable cement-based materials: High potential tests for quality control
    Nicolas, Roussel
    Richard, Buswell
    Nicolas, Ducoulombier
    Irina, Ivanova
    Temitope, Kolawole John
    Dirk, Lowke
    Viktor, Mechtcherine
    Romain, Mesnil
    Arnaud, Perrot
    Ursula, Pott
    Lex, Reiter
    Dietmar, Stephan
    Timothy, Wangler
    Rob, Wolfs
    Wenqiang, Zuo
    CEMENT AND CONCRETE RESEARCH, 2022, 158