Data-driven machine learning forecasting and design models for the tensile stress-strain response of UHPC

被引:0
|
作者
Barkhordari, Mohammad Sadegh [1 ]
Jaaz, Hussein Abad Gazi [2 ]
Jawdhari, Akram [2 ]
机构
[1] Amirkabir Univ Technol, Tehran Polytech, Dept Civil & Environm Engn, Tehran, Iran
[2] South Dakota State Univ, Dept Civil & Environm Engn, Brookings, SD 57007 USA
关键词
Ultra-high performance concrete; Stress strain behavior; Tension; Machine learning; Ensemble methods; Interpretation; Regression; FIBER-REINFORCED CONCRETE; HIGH-PERFORMANCE CONCRETE; STRENGTH; BEHAVIOR; FRC;
D O I
10.1016/j.istruc.2024.107965
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
The tensile behavior of ultra-high performance concrete (UHPC) is distinctive from conventional concrete (CC) and is typically included in design. This study leverages machine learning (ML) techniques and regression analysis to predict the full stress-strain behavior of UHPC in tension and characterizes the effects of various parameters. A comprehensive database comprising 500 data points from 24 experimental programs was assembled. Multiple ensemble learning algorithms, including gradient boosting, extreme gradient boosting (XGBoost), bagging regressor, and extremely randomized trees (ExtraTrees), were evaluated and compared against traditional multiple linear regression. The ExtraTrees model outperformed others, resulting in a mean absolute error (MAE) of 0.524 MPa, a root mean square error (RMSE) of 1.140 MPa, and a coefficient of determination (R2) of 0.80 for predicting the first cracking stress (FCS). For strain at first cracking (SFC), ExtraTrees achieved an MAE of 0.0175 mu epsilon and an R2 of 0.953. The model also performed well for post-cracking stress (PCS) and post-cracking strain (SPC). Of the six feature inputs considered -compressive strength (fc') of UHPC matrix, fiber reinforcement index (RI), fiber length (Lf), fiber volume (Vf), fiber diameter (Df), and fiber type-interpretation by SHAP values revealed that fc', Vf, and RI are the most influential. Additionally, a webbased interface was developed using the ML models, allowing users to predict FCS, SFC, PCS, and SPC and generate a bilinear tensile stress-strain curve, applicable for both softening and hardening UHPC types. The interface is intended for design purposes.
引用
收藏
页数:22
相关论文
共 50 条
  • [1] Existing Inverse Analysis Approaches for Tensile Stress-Strain Relationship of UHPC with Treated Steel Fibers
    Zhu, Yanping
    Zhang, Yang
    Hussein, Husam H.
    Qu, Shaoqin
    JOURNAL OF MATERIALS IN CIVIL ENGINEERING, 2021, 33 (06)
  • [2] Data-driven machine learning prediction models for the tensile capacity of anchors in thin concrete
    Momani, Yazan
    Alawadi, Roaa
    Majdalaweyh, Sereen
    Tarawneh, Ahmad
    Jweihan, Yazeed S.
    INNOVATIVE INFRASTRUCTURE SOLUTIONS, 2022, 7 (05)
  • [3] A Data-Driven Machine Learning Model for the Stress-Strain Behavior of Single Grain SAC305 Solder Joints
    Mondal, Debabrata
    Suhling, Jeffrey C.
    Mirkoohi, Elham
    Lall, Pradeep
    PROCEEDINGS OF THE IEEE 74TH ELECTRONIC COMPONENTS AND TECHNOLOGY CONFERENCE, ECTC 2024, 2024, : 670 - 677
  • [4] The data-driven research on the autogenous shrinkage of ultra-high performance concrete (UHPC) based on machine learning
    Li, Yaqiang
    Shen, Jiale
    Li, Yue
    Wang, Kai
    Lin, Hui
    JOURNAL OF BUILDING ENGINEERING, 2024, 82
  • [5] Data-Driven Load Forecasting Using Machine Learning and Meteorological Data
    Alrashidi A.
    Qamar A.M.
    Computer Systems Science and Engineering, 2023, 44 (03): : 1973 - 1988
  • [6] A physics-informed and data-enhanced tensile stress-strain model for UHPFRC
    Liu, Wei-He
    Zhang, Lu-Wen
    Dai, Jian-Guo
    ENGINEERING STRUCTURES, 2023, 285
  • [7] Data-driven moment-carrying capacity prediction of hybrid beams consisting of UHPC-NSC using machine learning-based models
    Katlav, Metin
    Ergen, Faruk
    STRUCTURES, 2024, 59
  • [8] A data-driven machine learning model for forecasting delivery positions in logistics for workforce planning
    Eichenseer, Patrick
    Hans, Lukas
    Winkler, Herwig
    SUPPLY CHAIN ANALYTICS, 2025, 9
  • [9] Machine learning predictions on the compressive stress-strain response of lattice-based metamaterials
    Xiao, Lijun
    Shi, Gaoquan
    Song, Weidong
    INTERNATIONAL JOURNAL OF SOLIDS AND STRUCTURES, 2024, 300
  • [10] Tensile stress-strain models for high strength steels
    Wang, Xing-Qiang
    Tao, Zhong
    Katwal, Utsab
    Hou, Chao
    JOURNAL OF CONSTRUCTIONAL STEEL RESEARCH, 2021, 186