玻璃纤维增强聚合物筋增强混凝土柱的轴压承载力评估

doi:10.19936/j.cnki.2096-8000.20241028.010

摘要/Abstract

摘要： 玻璃纤维增强聚合物(GFRP)筋对混凝土柱承载力的影响十分关键,为深入评估GFRP筋设计应用于增强混凝土柱的承载力性能,利用随机森林(RF)、人工神经网络(ANN)、AdaBoost和XGBoost算法,分别建立了各自的GFRP筋增强混凝土柱承载力模型。建立了GFRP筋增强混凝土柱的试验数据库,对已有的GFRP筋增强混凝土柱承载力理论公式进行了初步评估,并进一步对比分析GFRP筋增强混凝土柱承载力的RF模型、ANN模型、AdaBoost模型和XGBoost模型的预测精度。结果表明:已有的GFRP筋增强混凝土柱承载力理论公式的判定系数(0.70左右)均小于RF模型(0.82)、AdaBoost模型(0.80)和XGBoost模型(0.80)的制定系数,且平均绝对误差和均方根误差基本都大于RF模型、ANN模型、AdaBoost模型和XGBoost模型的相应值,表明现有理论公式的准确性低于RF模型、ANN模型、AdaBoost模型和XGBoost模型准确性。与ANN模型相比,RF模型、AdaBoost模型和XGBoost模型均可较为准确地评估GFRP筋增强混凝土柱的实际承载力性能(尤其是RF模型)。研究可为GFRP筋设计应用于增强混凝土结构时的承载力设计和分析提供参考。

关键词: 玻璃纤维增强聚合物筋, 混凝土柱, 轴压承载力, 复合材料, 随机森林

Abstract: The influence of glass fiber reinforced polymer (GFRP) bars on the axial compression capacity of concrete columns is crucial. To thoroughly evaluate the performance of GFRP bars in strengthening concrete columns, prediction models for the load-bearing capacity were established using the Random Forest (RF), Artificial Neural Network (ANN), AdaBoost, and XGBoost algorithms. A database containing experimental data from 256 GFRP-reinforced concrete columns was created. The existing theoretical formulas for the axial compression capacity of GFRP-reinforced concrete columns were preliminarily evaluated, and the predictive accuracy of the RF, ANN, AdaBoost, and XGBoost models for the axial compression capacity of GFRP-reinforced concrete columns was further analyzed. The results showed that the determination coefficient of the existing theoretical formulas for the axial compression capacity of GFRP-reinforced concrete columns (around 0.70) was lower than that of the RF model (0.82), AdaBoost model (0.80), and XGBoost model (0.80). Moreover, the average absolute error and root mean square error were generally higher for the existing theoretical formulas compared to the RF, ANN, AdaBoost, and XGBoost models, indicating that the accuracy of the existing theoretical formulas was inferior to that of the RF, ANN, AdaBoost, and XGBoost models. In comparison to the ANN model, the RF, AdaBoost, and XGBoost models could accurately evaluate the actual axial compression capacity performance of GFRP-reinforced concrete columns, especially the RF model. This research provides a reference for the axial compression capacity design and analysis when designing GFRP bars for strengthening concrete structures.

Key words: glass fiber reinforced polymer bar, concrete column, axial compression capacity, composites, random forest

中图分类号:

TB332

冉黎, 吴文, 周磊. 玻璃纤维增强聚合物筋增强混凝土柱的轴压承载力评估[J]. 复合材料科学与工程, 2024, 0(10): 72-78.

RAN Li, WU Wen, ZHOU Lei. Axial compression capacity evaluation of concrete columns reinforced with glass fiber reinforced polymer bars[J]. COMPOSITES SCIENCE AND ENGINEERING, 2024, 0(10): 72-78.

参考文献

[1] 刘海双. 玻璃纤维增强聚合物筋力学性能及耐久性能研究[D]. 郑州: 郑州大学, 2015.
[2] 王振华, 杨正, 鲁世科, 等. 玻璃纤维增强聚合物基复合材料阻燃改性研究进展[J]. 塑料工业, 2022, 50(12): 8-15.
[3] 高永红, 彭梦蜜, 金清平. 温度对玻璃纤维增强聚合物筋与混凝土黏结性能影响试验研究[J]. 中国塑料, 2022, 36(9): 16-23.
[4] 程杰, 齐玉军, 谢志锦. 玻璃纤维增强聚合物复合材料约束壁式钢管混凝土短柱轴压性能试验[J]. 复合材料学报, 2021, 38(6): 1825-1837.
[5] 闫邦平, 连春明. 混凝土碱性环境下玻璃纤维增强聚合物筋力学性能研究[J]. 工业建筑, 2016, 46(12): 152-156.
[6] 高丹盈, 李士会, 朱海堂, 等. 玻璃纤维增强聚合物筋压缩和剪切性能试验研究[J]. 玻璃钢/复合材料, 2009(3): 28-32.
[7] JAFARI A, BAZLI M, ASHRAFI H, et al. Effect of fibers configuration and thickness on tensile behavior of GFRP laminates subjected to elevated temperatures[J]. Construction and Building Materials, 2019, 202: 189-207.
[8] Design and construction of building structures with fiber-reinforced polymer: CAN/CSA S806-12[S]. Canada: 2012.
[9] HADI M N S, YOUSSEF J. Experimental investigation of GFRP-reinforced and GFRP-encased square concrete specimens under axial and eccentric load, and four-point bending test[J]. Journal of Composites for Construction, 2016, 20(5): 04016020.
[10] ELCHALAKANI M, MA G, ASLANI F, et al. Design of GFRP-reinforced rectangular concrete columns under eccentric axial loading[J]. Magazine of Concrete Research, 2017, 69(17): 865-877.
[11] AFIFI M Z, MOHAMED H M, BENMOKRANE B. Axial capacity of circular concrete columns reinforced with GFRP bars and spirals[J]. Journal of Composites for Construction, 2014, 18(1): 04013017.
[12] KARIM H, SHEIKH M N, HADI M N S. Axial load-axial deformation behaviour of circular concrete columns reinforced with GFRP bars and helices[J]. Construction and Building Materials, 2016, 112: 1147-1157.
[13] ALAJARMEH O S, MANALO A C, BENMOKRANE B, et al. Compressive behavior of axially loaded circular hollow concrete columns reinforced with GFRP bars and spirals[J]. Construction and Building Materials, 2019, 194: 12-23.
[14] KHORRAMIAN K, SADEGHIAN P. Experimental investigation of short and slender rectangular concrete columns reinforced with GFRP bars under eccentric axial loads[J]. Journal of Composites for Construction, 2020, 24(6): 04020072.
[15] XUE W, HU X, FANG Z. Experimental studies of GFRP reinforced concrete columns under static eccentric loading[C]//7th International Conference on Fiber Reinforced Polymer (FRP) Composites in Civil Engineering (CICE 2014). Canada: International institute for FRP in Construction (IIFC), 2014: 236-242.
[16] RAZA A, El OUNI M H, BERRADIA M. Structural assessment of eccentrically loaded GFRP reinforced circular concrete columns: Experiments and finite element analysis[J]. Composite Structures, 2021, 275: 114528.
[17] LO S H, KWAN A K H, OUYANG Y, et al. Finite element analysis of axially loaded FRP-confined rectangular concrete columns[J]. Engineering Structures, 2015, 100: 253-263.
[18] MAMARI A H S A, GHAFRI R S H H A, ARAVIND N, et al. Experimental study and development of machine learning model using random forest classifier on shear strength prediction of RC beam with externally bonded GFRP composites[J]. Asian Journal of Civil Engineering, 2023, 24(1): 267-286.
[19] GO C, KWAK Y J, KWAG S, et al. On developing accurate prediction models for residual tensile strength of GFRP bars under alkaline-concrete environment using a combined ensemble machine learning methods[J]. Case Studies in Construction Materials, 2023, 18: e02157.
[20] LI H, YANG D, HU T. Data-driven model for predicting the compressive strengths of GFRP-confined reinforced concrete columns[J]. Buildings, 2023(5): 1309.
[21] RAZA A, El OUNI M H, BAILI J. Data-driven analysis on axial strength of GFRP-NSC columns based on practical artificial neural network tool[J]. Composite Structures, 2022, 291: 115598.
[22] Concrete structures standards: AS 3600—2018[S]. Australia: 2018.
[23] MOHAMED H M, AFIFI M Z, BENMOKRANE B. Performance evaluation of concrete columns reinforced longitudinally with FRP bars and confined with FRP hoops and spirals under axial load[J]. Journal of Bridge Engineering, 2014, 19(7): 04014020.
[24] HADHOOD A, MOHAMED H M, BENMOKRANE B. Axial load-moment interaction diagram of circular concrete columns reinforced with CFRP bars and spirals: Experimental and theoretical investigations[J]. Journal of Composites for Construction, 2017, 21(2):04016092.
[25] RODRIGUEZ G V, SANCHEZ C M, CHICA O M, et al. Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines[J]. Ore Geology Reviews, 2015, 71: 804-818.
[26] YILMAZ I, KAYNAR O. Multiple regression, ANN (RBF, MLP) and ANFIS models for prediction of swell potential of clayey soils[J]. Expert Systems with Applications, 2011, 38(5): 5958-5966.
[27] SHANMUGASUNDAR G, VANITHA M, CˇEP R, et al. A comparative study of linear, random forest and ada boost regressions for modeling non-traditional machining[J]. Processes, 2021, 9(11): 2015.
[28] SHEHADEH A, ALSHBOUL O, Al MAMLOOK R E, et al. Machine learning models for predicting the residual value of heavy construction equipment: An evaluation of modified decision tree, Light GBM, and XGBoost regression[J]. Automation in construction, 2021, 129: 103827.