Machine learning prediction of fiber pull-out and bond-slip in fiber-reinforced cementitious composites

被引:18
作者
Hemmatian, Abolfazl [1 ]
Jalali, Meysam [1 ]
Naderpour, Hosein [2 ]
Nehdi, Moncef L. [3 ]
机构
[1] Shahrood Univ Technol, Fac Civil Engn, Shahrood, Iran
[2] Semnan Univ, Fac Civil Engn, Semnan, Iran
[3] McMaster Univ, Dept Civil Engn, 1280 Main St West, Hamilton, ON L8S 4L7, Canada
来源
JOURNAL OF BUILDING ENGINEERING | 2023年 / 63卷
关键词
Machine learning; Artificial neural network; Predictive model; Fiber pull-out; Fiber bond-slip; END STEEL FIBERS; COMPRESSIVE STRENGTH; CONCRETE; BEHAVIOR; PERFORMANCE; RESISTANCE; STRAIGHT; MODEL;
D O I
10.1016/j.jobe.2022.105474
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Single fiber pull-out and fiber-matrix interfacial interaction play an essential role in under-standing the mechanical behavior of fiber-reinforced cementitious composites. The present study introduces a computational model for predicting the maximum fiber pull-out force and corre-sponding bond slip. An extensive literature survey was performed to create a pertinent compre-hensive experimental database. A total of 382 experimental data were utilized to develop and train the Artificial Neural Network (ANN) models. The model input parameters included the fiber embedded length, fiber inclination angle, fiber tensile strength, fiber length-to-diameter ratio, loading rate, water-to-cement ratio, concrete compressive strength, and fiber geometry. The model output consisted of the maximum pull-out force and corresponding slip. The results indicate that ANN with two hidden layers and 12 neurons was adequate for predicting the outputs with a mean absolute percentage error (MAPE) of less than 10%. To obtain the importance of the inputs on the outputs (the maximum fiber pull-out force and the corresponding slip), a sensitivity analysis was done based on the Milne formula on the proposed ANN. According to the results, it was found that among the eight inputs, the parameters of the geometric shape of the fibers (straight, hooked-end and spiral fibers) and fiber tensile strength have the highest effect on the outputs, with an impact percentage of 16.1 and 15.1, respectively. The mean square error (MSE) was 0.9 for the maximum pull-out force and 0.14 for slip, respectively. Overall, the proposed executed model attained reasonable predictions and could offer a data driven approach to opti-mizing fiber-reinforced cementitious composites.
引用
收藏
页数:18
相关论文
共 52 条
  • [1] Predicting pull-out behaviour of 4D/5D hooked end fibres embedded in normal-high strength concrete
    Abdallah, Sadoon
    Fan, Mizi
    Rees, David W. A.
    [J]. ENGINEERING STRUCTURES, 2018, 172 : 967 - 980
  • [2] Pull-Out Behaviour of Hooked End Steel Fibres Embedded in Ultra-high Performance Mortar with Various W/B Ratios
    Abdallah, Sadoon
    Fan, Mizi
    Zhou, Xiangming
    [J]. INTERNATIONAL JOURNAL OF CONCRETE STRUCTURES AND MATERIALS, 2017, 11 (02) : 301 - 313
  • [3] Analysis and modelling of mechanical anchorage of 4D/5D hooked end steel fibres
    Abdallah, Sadoon
    Fan, Mizi
    Rees, David W. A.
    [J]. MATERIALS & DESIGN, 2016, 112 : 539 - 552
  • [4] Abu-Lebdeh Taher, 2010, American Journal of Engineering and Applied Sciences, V3, P454, DOI 10.3844/ajeassp.2010.454.463
  • [5] Effect of matrix strength on pullout behavior of steel fiber reinforced very-high strength concrete composites
    Abu-Lebdeh, Taher
    Hamoush, Sameer
    Heard, William
    Zornig, Brian
    [J]. CONSTRUCTION AND BUILDING MATERIALS, 2011, 25 (01) : 39 - 46
  • [6] Reliability analysis of strength models for short-concrete columns under concentric loading with FRP rebars through Artificial Neural Network
    Ahmad, Afaq
    Elchalakani, Mohamed
    Elmesalami, Nouran
    El Refai, Ahmed
    Abed, Farid
    [J]. JOURNAL OF BUILDING ENGINEERING, 2021, 42
  • [7] A Proposed Model for Axial Strength Estimation of Non-compact and Slender Square CFT Columns
    Ahmadi, Masoud
    Naderpour, Hosein
    Kheyroddin, Ali
    [J]. IRANIAN JOURNAL OF SCIENCE AND TECHNOLOGY-TRANSACTIONS OF CIVIL ENGINEERING, 2019, 43 (Suppl 1) : 131 - 147
  • [8] [Anonymous], ACI5449R17
  • [9] [Anonymous], 1989, Final Report
  • [10] Modeling of fiber pull-out in continuous fiber reinforced ceramic composites using finite element method and artificial neural networks
    Bheemreddy, V.
    Chandrashekhara, K.
    Dharani, L. R.
    Hilmas, G. E.
    [J]. COMPUTATIONAL MATERIALS SCIENCE, 2013, 79 : 663 - 673