基于Bayesian-Bagging-XGBoost算法的GFRP增强混凝土柱轴向承载力预测

doi:10.19936/j.cnki.2096-8000.20250928.013

摘要/Abstract

摘要： 由于钢筋与玻璃纤维增强聚合物(Glass Fiber Reinforced Polymer,GFRP)筋力学特性的差异,GFRP筋增强混凝土柱轴压承载力计算不能简单套用钢筋混凝土柱计算方法。为提高GFRP筋增强混凝土柱轴压承载力预测模型的准确性,以253组试验数据作为极限梯度提升(XGBoost)算法建模的数据基础,并采用Bayesian优化算法、Bagging算法对XGBoost算法进行了优化,以提高模型的预测精度、稳定性和训练效率。采用决定系数(R²)、平均绝对误差(MAE)和相对根均方误差(RRSE)等指标对模型进行评价,并将其与现有预测模型进行对比分析。研究发现,Bayesian优化算法和Bagging算法可有效提高模型的训练效率、预测精度。所提出的Bayesian-Bagging-XGBoost模型的R²,MAE,RRSE值分别为0.691 6,418.162 9,0.555 3,远优于现有预测模型指标,可为GFRP筋增强混凝土柱的工程应用提供更加准确的参考。

关键词: Bayesian优化, XGBoost算法, GFRP增强混凝土柱, 轴向承载力, 预测

Abstract: Due to the differences in mechanical properties between steel bars and glass fiber reinforced polymer (GFRP) bars, the axial bearing capacity of GFRP bar-reinforced concrete columns cannot be simply calculated using the methods for reinforced concrete columns. To improve the accuracy of the predictive model for the axial bearing capacity of GFRP bar-reinforced concrete columns, this study used 253 sets of experimental data as the basis for modeling with the extreme gradient boosting (XGBoost) algorithm. Bayesian optimization and Bagging algorithms were employed to optimize the XGBoost algorithm to enhance the model’s predictive accuracy, stability, and training efficiency. The model was evaluated using the coefficient of determination (R²), mean absolute error (MAE), and relative root mean square error (RRSE) and compared with existing predictive models. The study found that Bayesian optimization and Bagging algorithms effectively improved the training efficiency and predictive accuracy of the model. The proposed Bayesian-Bagging-XGBoost model achieved R², MAE, and RRSE values of 0.691 6, 418.162 9, and 0.555 3, respectively, which are significantly better than those of existing predictive models. This model provides a more accurate reference for the engineering application of GFRP bar-reinforced concrete columns.

Key words: Bayesian optimization, XGBoost algorithm, GFRP-reinforced concrete columns, axial bearing capacity, prediction

中图分类号:

TB332

唐培根, 李小亮, 何鑫, 马国辉, 张祥. 基于Bayesian-Bagging-XGBoost算法的GFRP增强混凝土柱轴向承载力预测[J]. 复合材料科学与工程, 2025, 0(9): 98-109.

TANG Peigen, LI Xiaoliang, HE Xin, MA Guohui, ZHANG Xiang. Prediction of axial bearing capacity of GFRP-reinforced concrete columns based on Bayesian-Bagging-XGBoost algorithm[J]. COMPOSITES SCIENCE AND ENGINEERING, 2025, 0(9): 98-109.

参考文献

[1] 刘洋, 李明明. 基于压电陶瓷的内嵌工字型钢GFRP管混凝土柱的抗震损伤监测研究[J]. 施工技术(中英文), 2023, 52(5): 115-119, 145.
[2] ZHANG Q, XIAO J, LIAO Q, et al. Structural behavior of seawater sea-sand concrete shear wall reinforced with GFRP bars[J]. Engineering Structures, 2019, 189: 458-470.
[3] 张健新, 张鑫, 陈庞, 等. GFRP杆连接预制夹心保温墙板受弯性能试验[J]. 沈阳建筑大学学报(自然科学版), 2024, 40(2): 203-211.
[4] 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.
[5] 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.
[6] 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.
[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] 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.
[9] 汪光波. GFRP筋增强混凝土柱的抗压性能试验研究[D]. 武汉: 武汉科技大学, 2018.
[10] Standards Australia. Concrete Structures: AS-3600: 2018[S]. Sydney: Standards Australia, 2018.
[11] 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.
[12] 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(10): 72-78.
[13] 马春辉, 侯媛媛, 杨杰, 等. 基于RUN-XGBoost算法的土石坝渗流预测模型[J]. 水利水电科技进展, 2024, 44(2): 72-78.
[14] 许秋鸿, 刘晓青. 基于VMD-XGBoost-GRU模型的危岩体变形预测[J]. 水利水电科技进展, 2024, 44(2): 92-98.
[15] 王彦海, 李书炀, 邓德慧, 等. 基于改进IAVOA-BP算法的GFRP布加固角钢极限承载力预测模型研究[J]. 国外电子测量技术, 2023, 42(11): 65-73.
[16] 高旭, 黄丽华. 冻融循环下FRP筋混凝土界面黏结强度预测[J]. 大连理工大学学报, 2024, 64(1): 57-63.
[17] 张书颖, 陈适之, 韩万水, 等. 基于集成学习的FRP加固混凝土梁抗弯承载力预测研究[J]. 工程力学, 2022, 39(8): 245-256.
[18] 陈曦泽, 贾俊峰, 白玉磊, 等. 基于XGBoost-SHAP的钢管混凝土柱轴向承载力预测模型[J]. 浙江大学学报(工学版), 2023, 57(6): 1061-1070.
[19] LI W, YIN Y B, QUAN X W, et al. Gene expression value prediction based on XGBoost algorithm[J]. Frontiers in Genetics, 2019, 10: 1077.
[20] 王永生, 李海龙, 关世杰, 等. 基于变换域分析和XGBoost算法的超短期风电功率预测模型[J]. 高电压技术, 2024, 50(9): 3860-3870.
[21] 刘新宇, 蒲欣雨, 李继方, 等. 基于贝叶斯优化的VMD-GRU短期风电功率预测[J]. 电力系统保护与控制, 2023, 51(21): 158-165.
[22] ALI R, HECHMI M O E, JAMEL B, et al. Data-driven analysis on axial strength of GFRP-NSC columns based on practical artificial neural network tool[J]. Composite Structures, 2022, 291: 115598.
[23] CSA Group. Design and construction of building components with fibre-reinforced polymers: CAN/CSA S806-02(R2007)[S]. Tornto: CSA Group, 2002.
[24] 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.
[25] 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, 2016, 21(2):04016092.