STUDY ON PREDICTION OF FRP STRENGTHENED REINFORCED CONCRETE BEAM’S MOMENT BEARING CAPACITY BASED ON ENSEMBLE LEARNING ALGORITHM
-
摘要: 为解决当前纤维增强复合材料(FRP)加固钢筋混凝土梁抗弯承载力预测中模型不统一、计算繁琐、精度有限等问题,建立了统一化的抗弯承载力预测模型。根据既有文献收集外贴式、端锚式和嵌入式3种FRP典型加固方式加固钢筋混凝土梁试验数据,确定影响加固梁承载力的关键因素,通过XGBoost(极限梯度提升树)算法训练回归各影响因素与加固后梁抗弯承载力间的非线性映射关系,得到统一化的FRP加固钢筋混凝土梁抗弯承载力预测模型。随后在测试样本集上对该模型的预测精度进行了验证,与基于支持向量回归(SVR)和人工神经网络(ANN)两种代表性机器学习算法得到的预测模型进行了横向对比,并分析了不同加固方式下的预测精度。研究结果表明:该文得到的基于XGBoost的抗弯承载力预测模型拟合优度R2=0.9417,可见整体精度较高,有良好的性能;相比基于传统机器学习算法SVR和ANN建立的预测模型,基于集成学习算法XGBoost的拟合优度分别提升了8.00%及6.70%,均方根误差减少了33.94%和30.72%,平均绝对误差减少了32.38%和30.51%,表明基于XGBoost的模型精度更高,远优于SVR和ANN;基于XGBoost的模型在外贴式、端锚式和嵌入式加固方式下拟合优度分别达到0.9472、0.9631和0.9278,可见预测精度均表现优良,精度相当,说明该模型可以统一考虑三种不同加固方式;通过分析输入参数的特征重要性,说明了该模型的合理性。研究成果可为实际桥梁工程中FRP加固设计应用提供参考。Abstract: A unified moment bearing capacity prediction model is established in order to solve the issues of various models, difficult calculations, and limited accuracy in predicting the moment bearing capacity of reinforced concrete beams strengthened with fiber reinforced polymer (FRP) materials. By collecting the experimental data associated with three typical FRP strengthening types including externally bonded, end anchorage and near-surface mounted FRP from the existing literature, the key factors which affect the bearing capacity of the reinforced beam are determined, and XGBoost (eXtreme Gradient Boosting) algorithm is trained to obtain regressionally the nonlinear relationship between the influencing factors and the moment bearing capacity of the reinforced beam calculated with a unified FRP strengthened reinforced concrete beam moment bearing capacity prediction model. The prediction accuracy of the model is verified through the testing sample set. It is compared with the prediction models based on two representative machine learning algorithms: support vector regression (SVR) and artificial neural network (ANN). The prediction accuracy under different strengthening types is also analyzed. The results illustrate that the R2 of the XGBoost-based moment bearing capacity prediction model reaches 0.9417, indicating that the overall accuracy is high. Compared with the prediction model based on SVR and ANN, the R2 of the model based on the ensemble learning algorithm XGBoost is increased by 8.00% and 6.70%, the root mean square error is reduced by 33.94% and 30.72%, and the mean absolute error is reduced by 32.38% and 30.51%. It shows that the XGBoost based model has higher accuracy, which is far better than SVR and ANN based model. The R2 of the XGBoost based model reaches 0.9472, 0.9631, and 0.9278, respectively under the externally bonded, end anchorage and near-surface mounted strengthening types. It can be seen that the prediction accuracy is relatively good, and the accuracy is at the same level indicating that this model can uniformly considers three different strengthening types. By analyzing the feature importance of the input parameters, the rationality of the model is explained. The research outcome could provide references for the design and application of actual bridge strengthening with FRP.
-
表 1 FRP加固样本集参数统计特征
Table 1. Statistical characteristics of FRP strengthened sample parameters
参数 最大值 最小值 中位数 均值 标准差 输入 fc/MPa 63.47 17.50 39.50 39.24 11.83 fy/MPa 608.00 242.20 413.70 418.05 69.33 ff/MPa 4510.00 512.00 2100.00 2268.84 1099.42 Efr/GPa 299.40 22.00 116.00 136.31 75.15 rs/(%) 2.45 0.35 0.66 0.76 0.45 rf/(%) 0.93 0.02 0.09 0.16 0.17 b/mm 200.00 100.00 150.00 156.27 33.38 h/mm 400.00 180.00 280.00 270.13 46.20 输出 M/(kN·m) 141.00 6.78 40.8 42.67 24.34 表 2 XGBoost参数
Table 2. Parameters of XGBoost
参数 调节范围 取值 意义 α [0, 1] 0.2 学习率 s [0, ∞] 10 树的棵树 D [0, ∞] 2 树的最大深度 W [0, ∞] 0 最小叶子节点权重和 γ [0, ∞] 0.001 节点分裂的最小损失函数下降值 表 3 不同模型评估指标
Table 3. Evaluation of different models
基础算法 拟合优度
R2均方根误差
RMSE/(kN·m)平均绝对误差
MAE/(kN·m)XGBoost 0.9417 5.9692 4.2076 SVR 0.8664 9.0366 6.2228 ANN 0.8786 8.6163 6.0549 表 4 不同加固方式评估指标
Table 4. Evaluation of different strengthening methods
加固方式 拟合优度
R2均方根误差
RMSE/(kN·m)平均绝对误差
MAE/(kN·m)外贴式 0.9472 4.2144 3.2194 端锚式 0.9631 3.2522 2.7482 嵌入式 0.9278 9.0925 6.3868 -
[1] 吴智深, 汪昕, 史健喆. 玄武岩纤维复合材料性能提升及其新型结构[J]. 工程力学, 2020, 37(5): 1 − 14. doi: 10.6052/j.issn.1000-4750.2019.07.ST10Wu Zhishen, Wang Xin, Shi Jianzhe. Advancement of basalt fiber-reinforced polymers (BFRP) and the novel structures reinforced with BFRPS [J]. Engineering Mechanics, 2020, 37(5): 1 − 14. (in Chinese) doi: 10.6052/j.issn.1000-4750.2019.07.ST10 [2] Siddika A, Mamun M, Alyousef R, et al. Strengthening of reinforced concrete beams by using fiber-reinforced polymer composites: A review [J]. Journal of Building Engineering, 2019, 25(September): 100798. [3] 叶华文, 唐诗晴, 段智超, 等. 纤维增强复合材料桥梁结构2019年度研究进展[J]. 土木与环境工程学报(中英文), 2020, 42(5): 192 − 200.Ye Huawen, Tang Shiqing, Duan Zhichao, et al. State-of-the-art review of the application of fiber reinforced polymer in bridge structures in 2019 [J]. Journal of Civil and Environmental Engineering, 2020, 42(5): 192 − 200. (in Chinese) [4] 金浏, 夏海, 蒋轩昂, 等. 剪跨比对CFRP加固无腹筋混凝土梁剪切破坏及尺寸效应的影响研究[J]. 工程力学, 2021, 38(3): 50 − 59, 85. doi: 10.6052/j.issn.1000-4750.2020.01.0028Jin Liu, Xia Hai, Jiang Xuanang, et al. Effect of shear-span ratio on shear failure and size effect of concrete beams without web reinforcement strengthened by CFRP [J]. Engineering Mechanics, 2021, 38(3): 50 − 59, 85. (in Chinese) doi: 10.6052/j.issn.1000-4750.2020.01.0028 [5] 董坤, 郝建文, 李鹏, 等. 环境温差下FRP-混凝土界面粘结行为分析[J]. 工程力学, 2020, 37(11): 117 − 126. doi: 10.6052/j.issn.1000-4750.2019.12.0783Dong Kun, Hao Jianwen, Li Peng, et al. Studies on the bond performance of FRP-to-concrete interfaces under environmental temperature difference [J]. Engineering Mechanics, 2020, 37(11): 117 − 126. (in Chinese) doi: 10.6052/j.issn.1000-4750.2019.12.0783 [6] 刘兴喜, 徐荣桥. FRP加固混凝土梁粘结层剪应力分析[J]. 工程力学, 2019, 36(增刊): 149 − 153. doi: 10.6052/j.issn.1000-4750.2018.05.S028Liu Xingxi, Xu Rongqiao. Interfacial shear stress in FRP-strengthened RC beams [J]. Engineering Mechanics, 2019, 36(Suppl): 149 − 153. (in Chinese) doi: 10.6052/j.issn.1000-4750.2018.05.S028 [7] 王文炜, 赵国藩, 黄承逵, 等. 碳纤维布加固已承受荷载的钢筋混凝土梁抗弯性能试验研究及抗弯承载力计算[J]. 工程力学, 2004, 21(4): 172 − 178. doi: 10.3969/j.issn.1000-4750.2004.04.031Wang Wenwei, Zhao Guofan, Huang Chengkui, et al. An experimental study of strengthening of initially loaded reinforced concrete beams using CFRP sheets [J]. Engineering Mechanics, 2004, 21(4): 172 − 178. (in Chinese) doi: 10.3969/j.issn.1000-4750.2004.04.031 [8] 吴刚, 安琳, 吕志涛. 碳纤维布用于钢筋混凝土梁抗弯加固的试验研究[J]. 建筑结构, 2000, 30(7): 3 − 6, 10.Wu Gang, An Lin, Lü Zhitao. Experimental investigation and analysis on the flexural strengthening for RC beams bonded with carbon fiber sheet [J]. Building Structure, 2000, 30(7): 3 − 6, 10. (in Chinese) [9] 王文炜. 纤维复合材料加固钢筋混凝土梁抗弯性能研究 [D]. 大连: 大连理工大学土木水利学院, 2003.Wang Wenwei. Study on flexural behavior of reinforced concrete beams strengthened with fiber reinforced plastics [D]. Dalian: College of Civil Engineering, Dalian University of Technology, 2003. (in Chinese) [10] Daghash S M, Ozbulut O E. Flexural performance evaluation of NSM basalt FRP-strengthened concrete beams using digital image correlation system [J]. Composite Structures, 2017, 176: 748 − 756. doi: 10.1016/j.compstruct.2017.06.021 [11] 杨勇, 谢标云, 聂建国, 等. 表层嵌贴碳纤维筋加固钢筋混凝土梁受力性能试验研究[J]. 工程力学, 2009, 26(3): 106 − 112.Yang Yong, Xie Biaoyun, Nie Jianguo, et al. Experiment study on mechanical behavior of reinforced concrete beams strengthened with near surface mounted (NSM) CFRP rods [J]. Engineering Mechanics, 2009, 26(3): 106 − 112. (in Chinese) [12] 谢建和, 孙明炜, 郭永昌, 等. FRP加固受损RC梁受弯剥离承载力预测模型[J]. 中国公路学报, 2014, 27(12): 73 − 79. doi: 10.3969/j.issn.1001-7372.2014.12.009Xie Jianhe, Sun Mingwei, Guo Yongchang, et al. Prediction model for debonding bearing capacity of damaged reinforced concrete beam flexurally strengthened with fiber reinforced polymer [J]. China Journal of Highway and Transport, 2014, 27(12): 73 − 79. (in Chinese) doi: 10.3969/j.issn.1001-7372.2014.12.009 [13] 丁亚红, 王兴国, 曾宪桃, 等. 持续荷载作用下外贴FRP片材加固混凝土梁承载力影响因素分析[J]. 工程力学, 2007, 24(增刊 1): 154 − 158.Ding Yahong, Wang Xingguo, Zeng Xiantao, et al. Preloading effect on load-capacity of RC beams strengthened with FRP laminate [J]. Engineering Mechanics, 2007, 24(Suppl 1): 154 − 158. (in Chinese) [14] Naser M Z. Machine learning assessment of FRP-strengthened and reinforced concrete members [J]. Aci Structural Journal, 2020, 117(6): 237 − 251. [15] Dias S, Barros J, Worajak J. Behavior of RC beams flexurally strengthened with NSM CFRP laminates [J]. Composite Structures, 2018, 201(10): 363 − 376. [16] Ceroni F. Experimental performances of RC beams strengthened with FRP materials [J]. Construction & Building Materials, 2010, 24(9): 1547 − 1559. [17] 唐煜, 卢宏宇, 邹友泉, 等. 组合加固钢筋混凝土梁抗弯性能试验研究[J]. 东南大学学报(自然科学版), 2020, 50(5): 822 − 830. doi: 10.3969/j.issn.1001-0505.2020.05.005Tang Yu, Lu Hongyu, Zou Youquan, et al. Experimental study on the flexural performance of reinforced concrete beams strengthened by composite method [J]. Journal of Southeast University (Natural Science Edition), 2020, 50(5): 822 − 830. (in Chinese) doi: 10.3969/j.issn.1001-0505.2020.05.005 [18] GB 50367−2013, 混凝土结构加固设计规范 [S]. 北京: 中国建筑工业出版社, 2013.GB 50367−2013, Code for design of strengthening concrete structure [S]. Beijing: China Architecture & Building Press, 2013.(in Chinese) [19] 吴刚, 吕志涛. 外贴CFRP加固混凝土结构的抗弯设计方法[J]. 建筑结构, 2000, 30(7): 7 − 10.Wu Gang, Lü Zhitao. Flexural design for RC beams strengthened with CFRP [J]. Building Structure, 2000, 30(7): 7 − 10. (in Chinese) [20] Ha S K, Khalid H R, Park S M, et al. Interfacial crack-induced debonding behavior of sprayed FRP laminate bonded to RC beams [J]. Composite Structures, 2015, 128(sep.): 176 − 187. [21] 贺学军, 周朝阳, 徐玲. 内嵌CFRP板条加固混凝土梁的抗弯性能试验研究[J]. 土木工程学报, 2008, 41(12): 14 − 20. doi: 10.3321/j.issn:1000-131X.2008.12.003He Xuejun, Zhou Chaoyang, Xu Ling. Experimental study on the flexural behavior of reinforced concrete beams strengthened with near-surface mounted CFRP laminates [J]. China Civil Engineering Journal, 2008, 41(12): 14 − 20. (in Chinese) doi: 10.3321/j.issn:1000-131X.2008.12.003 [22] 李荣, 滕锦光, 岳清瑞. FRP材料加固混凝土结构应用的新领域——嵌入式(NSM)加固法[J]. 工业建筑, 2004, 34(4): 5 − 10. doi: 10.3321/j.issn:1000-8993.2004.04.002Li Rong, Teng Jinguang, Yue Qingrui. A new technique for strengthening concrete structures——Near-surface mounted FRP reinforcement [J]. Industrial Construction, 2004, 34(4): 5 − 10. (in Chinese) doi: 10.3321/j.issn:1000-8993.2004.04.002 [23] Adeli H. Neural networks in civil engineering: 1989–2000 [J]. Computer-Aided Civil and Infrastructure Engineering, 2001, 16(2): 126 − 142. doi: 10.1111/0885-9507.00219 [24] Amezquita-Sanchez P, Valtierra-Rodriguez M, Adeli H. Machine learning in structural engineering [J]. Scientia Iranica, 2020, 27(6): 2645 − 2656. [25] 郑秋怡, 周广东, 刘定坤. 基于长短时记忆神经网络的大跨拱桥温度-位移相关模型建立方法[J]. 工程力学, 2021, 38(4): 68 − 79. doi: 10.6052/j.issn.1000-4750.2020.05.0323Zheng Qiuyi, Zhou Guangdong, Liu Dingkun. Method of modeling temperature-displacement correlation for long-span arch bridges based on long short-term memory neural networks [J]. Engineering Mechanics, 2021, 38(4): 68 − 79. (in Chinese) doi: 10.6052/j.issn.1000-4750.2020.05.0323 [26] 赵林鑫, 江守燕, 杜成斌. 基于SBFEM和机器学习的薄板结构缺陷反演[J]. 工程力学, 2021, 38(6): 36 − 46. doi: 10.6052/j.issn.1000-4750.2020.06.0416Zhao Linxin, Jiang Shouyan, Du Chengbin. Flaws detection in thin plate structures based on SBFEM and machine learning [J]. Engineering Mechanics, 2021, 38(6): 36 − 46. (in Chinese) doi: 10.6052/j.issn.1000-4750.2020.06.0416 [27] 许斌, 龚安苏, 贺佳, 等. 基于神经网络模型的结构参数提取新方法[J]. 工程力学, 2011, 28(4): 35 − 41.Xu Bin, Gong Ansu, He Jia, et al. A novel structural parameter extraction methodology with neural network based nonparametric model [J]. Engineering Mechanics, 2011, 28(4): 35 − 41. (in Chinese) [28] 何定桥, 王鹏军, 杨军. 深度神经网络在EMD虚假分量识别中的应用[J]. 工程力学, 2021, 38(增刊): 195 − 201.He Dingqiao, Wang Pengjun, Yang Jun. Application of deep neural networks in EMD false component identification [J]. Engineering Mechanics, 2021, 38(Suppl): 195 − 201. (in Chinese) [29] 邓露, 钟玉婷, 杨远亮, 等. 冷弯薄壁型钢受弯构件承载力与延性优化研究[J]. 工程力学, 2021, 38(4): 93 − 101. doi: 10.6052/j.issn.1000-4750.2020.05.0327Deng Lu, Zhong Yuting, Yang Yuanliang, et al. Optimization on bearing capacity and ductility of cold-formed thin-walled steel flexural member [J]. Engineering Mechanics, 2021, 38(4): 93 − 101. (in Chinese) doi: 10.6052/j.issn.1000-4750.2020.05.0327 [30] 潘兆东, 刘良坤, 谭平, 等. 大型结构自适应学习率RBF神经网络滑模分散控制研究[J]. 工程力学, 2019, 36(9): 120 − 127.Pan Zhaodong, Liu Liangkun, Tan Ping, et al. Research on sliding mode decentralized control based on adaptive learning rate RBF neural network for large-scale engineering structures [J]. Engineering Mechanics, 2019, 36(9): 120 − 127. (in Chinese) [31] 冯德成, 吴刚. 混凝土结构基本性能的可解释机器学习建模[J/OL]. 建筑结构学报: 1 − 15[2021-05-11]. https://doi.org/10.14006/j.jzjgxb.2020.0491.Feng Decheng, Wu Gang. Interpretable machine learning-based modeling approach for fundamental properties of concrete structures [J/OL]. Journal of Building Structures: 1 − 15[2021-05-11]. https://doi.org/10.14006/j.jzjgxb.2020.0491. (in Chinese) [32] Hadzima-Nyarko M, Nyarko K, Lu H, et al. Machine learning approaches for estimation of compressive strength of concrete [J]. European Physical Journal Plus, 2020, 135(8): 682. doi: 10.1140/epjp/s13360-020-00703-2 [33] 王佳. 智能算法在碳纤维布加固钢筋混凝土梁承载力预测中的应用研究 [D]. 西安: 西安理工大学, 2010.Wang Jia. Research and application about intelligent algorithms for predicting bearing capacity of RC beams strengthened by carbon fiber sheets [D]. Xi’an: Xi’an University of Technology, 2010. (in Chinese) [34] 杨勇新. 预应力CFRP加固RC梁承载力的神经网络预测[J]. 华侨大学学报(自然科学版), 2007, 28(3): 304 − 307.Yang Yongxin. Neural network prediction of bearing capacity of RC beams strengthened with prestressed CFRP sheets [J]. Journal of Huaqiao University (Natural Science), 2007, 28(3): 304 − 307. (in Chinese) [35] Tang W C, Balendran R V, Nadeem A, et al. Flexural strengthening of reinforced lightweight polystyrene aggregate concrete beams with near-surface mounted GFRP bars [J]. Building & Environment, 2006, 41(10): 1381 − 1393. [36] Jung W T, Park Y H, Park J S, et al. Experimental investigation on flexural behavior of RC beams strengthened by NSM CFRP reinforcements [J]. ACI Special Publication, 2005, 230: 795 − 806. [37] Lorenzis L D, Micelli F, Tegola A L. Passive and active near-surface mounted FRP rods for flexural strengthening of RC beams [C]// Proceedings of the Third International Conference on Composites in Infrastructure. San Francisco, 2002. [38] Sharaky I A, Torres L, Comas J, et al. Flexural response of reinforced concrete (RC) beams strengthened with near surface mounted (NSM) fibre reinforced polymer (FRP) bars [J]. Composite Structures, 2014, 109: 8 − 22. doi: 10.1016/j.compstruct.2013.10.051 [39] Teng J G, Lorenzis L D, Bo W, et al. Debonding failures of RC beams strengthened with near surface mounted CFRP strips [J]. Journal of Composites for Construction, 2006, 10(2): 92 − 105. doi: 10.1061/(ASCE)1090-0268(2006)10:2(92) [40] Haddad R H, Almomani O A. Recovering flexural performance of thermally damaged concrete beams using NSM CFRP strips [J]. Construction and Building Materials, 2017, 154: 632 − 643. doi: 10.1016/j.conbuildmat.2017.07.211 [41] 宾羽飞. 表面嵌贴CFRP板条加固混凝土梁抗弯性能试验研究[D]. 南京: 南京理工大学, 2007.Bin Yufei. Study on flexural performance of RC beam reinforced with near surface mounted CFRP [D]. Nanjing: Nanjing University of Science & Technology, 2007. (in Chinese) [42] 陈西龙. FRP复合加固钢筋混凝土梁的抗弯抗剪性能研究 [D]. 深圳: 深圳大学, 2017.Chen Xilong. Research on flexural and shear performance of reinforced concrete beams strengthened by FRP composite [D]. Shenzhen: Shenzhen University, 2017. (in Chinese) [43] 陈绪军, 杨勇新, 邢建英, 等. 玄武岩纤维布加固钢筋混凝土梁抗弯试验研究[J]. 郑州大学学报(工学版), 2009, 30(2): 61 − 65.Chen Xujun, Yang Yongxin, Xing Jianying, et al. Experimental study on flexural performance of RC beams strengthened with basalt fiber sheet [J]. Journal of Zhengzhou University (Engineering Science), 2009, 30(2): 61 − 65. (in Chinese) [44] 陈绪军, 李华锋, 杨勇新. BFRP与CFRP加固混凝土梁抗弯性能试验研究[J]. 人民长江, 2011, 42(19): 83 − 87. doi: 10.3969/j.issn.1001-4179.2011.19.023Chen Xujun, Li Huafeng, Yang Yongxin. Comparative study on flexural performance of RC beams reinforced with BFRP and CFRP [J]. Yangtze River, 2011, 42(19): 83 − 87. (in Chinese) doi: 10.3969/j.issn.1001-4179.2011.19.023 [45] 黄俊豪, 钱永久, 杨华平, 等. CFRP布加固损伤RC梁抗弯性能试验研究[J]. 铁道建筑, 2021, 61(5): 17 − 21. doi: 10.3969/j.issn.1003⁃1995.2021.05.05Huang Junhao, Qian Yongjiu, Yang Huaping, et al. Experimental study on flexural behavior of damaged reinforced concrete beams strengthened with CFRP sheets [J]. Railway Engineering, 2021, 61(5): 17 − 21. (in Chinese) doi: 10.3969/j.issn.1003⁃1995.2021.05.05 [46] 蒋鑫. 表层嵌入式预应力CFRP板条加固RC梁抗弯能力试验研究[D]. 长沙: 长沙理工大学, 2011.Jiang Xin. Experimental study of bending resistance of RC beams strengthened with near surface mounted prestressed CFRP strips [D]. Changsha: Changsha University of Science and Technology, 2011. (in Chinese) [47] 李浩. 玄武岩纤维布加固钢筋混凝土梁抗弯性能试验研究[D]. 天津: 天津城建大学, 2014.Li Hao. Experimental research on flexural behavior of RC beams strengthened with BFRP sheets [D]. Tianjin: Tianjin Chengjian University, 2014. (in Chinese) [48] 李荷美. 不同程度损伤RC梁内嵌FRP材料抗弯性能试验研究[D]. 石家庄: 河北科技大学, 2014.Li Hemei. Experimental study on flexural behavior of RC beams strengthened with near-surface mounted FRP under different damages [D]. Shijiazhuang: Hebei University of Science and Technology, 2014. (in Chinese) [49] 李正佳. FRP筋嵌入式抗弯加固RC梁试验研究[D]. 长春: 吉林建筑工程学院, 2012.Li Zhengjia. The study of the NSM FRP bars strengthening of the RC beams [D]. Changchun: Jilin Architecture and Civil Engineering Institute, 2012. (in Chinese) [50] 蔺建廷. 玄武岩纤维布加固钢筋混凝土梁抗弯性能的试验研究[D]. 大连: 大连理工大学, 2009.Lin Jianting. Experimental research of reinforced concrete beams strengthened with basalt fiber polymer [D]. Dalian: Dalian University of Technology, 2009. (in Chinese) [51] 刘乐, 秦子鹏, 李刚, 等. BFRP加固钢筋混凝土梁抗弯性能试验研究[J]. 工程抗震与加固改造, 2017, 39(2): 53 − 58, 66.Liu Le, Qin Zipeng, Li Gang, et al. Experimental study on bending resistance properties of RC beams strengthened with BFRP [J]. Earthquake Resistant Engineering and Retrofitting, 2017, 39(2): 53 − 58, 66. (in Chinese) [52] 刘立刚. 碳纤维布加固钢筋混凝土梁抗弯力学性能研究 [D]. 济南: 山东大学, 2005.Liu Ligang. Study on the flexural mechanical properties of reinforced concrete beams strengthened with CFRP sheets [D]. Jinan: Shandong University, 2005. (in Chinese) [53] 刘沐宇, 刘其卓, 骆志红, 等. CFRP加固不同损伤度钢筋砼梁的抗弯试验[J]. 华中科技大学学报(自然科学版), 2005(3): 13 − 16.Liu Muyu, Liu Qizhuo, Luo Zhihong, et al. Flexural performance of different damages reinforced concrete beams strengthened with CFRP sheets [J]. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2005(3): 13 − 16. (in Chinese) [54] 刘其卓. 碳纤维布加固不同损伤混凝土梁抗弯性能的试验研究[D]. 武汉: 武汉理工大学, 2004.Liu Qizhuo. Flexural performance of different damages reinforced concrete beams strengthened with CFRP sheets [D]. Wuhan: Wuhan University of Technology, 2004. (in Chinese) [55] 宋力, 王文源, 樊成. BFRP布加固RC梁抗弯性能研究[J]. 四川建筑科学研究, 2018, 44(3): 1 − 5. doi: 10.3969/j.issn.1008-1933.2018.03.001Song Li, Wang Wenyuan, Fan Cheng. Study on bending resistance properties of RC beams strengthened with BFRP [J]. Sichuan Building Science, 2018, 44(3): 1 − 5. (in Chinese) doi: 10.3969/j.issn.1008-1933.2018.03.001 [56] 宋丽娟, 梁玉国, 张学士. 不同内嵌材料加固钢筋混凝土梁抗弯性能试验研究[J]. 河北工业科技, 2014, 31(1): 57 − 61. doi: 10.7535/hbgykj.2014yx0113Song Lijuan, Liang Yuguo, Zhang Xueshi. Experimental investigation of flexural behavior of the RC beams strengthened with different near-surface mounted material [J]. Hebei Journal of Industrial Science and Technology, 2014, 31(1): 57 − 61. (in Chinese) doi: 10.7535/hbgykj.2014yx0113 [57] 孙轶. 玄武岩纤维布加固钢筋混凝土梁抗弯性能试验研究[D]. 合肥: 合肥工业大学, 2015.Sun Yi. Experimental study on flexural behavior of RC beams strengthened with BFRP [D]. Hefei: Hefei University of Technology, 2015. (in Chinese) [58] 孙志洋, 张智梅, 刘涛. 内嵌CFRP板加固已损伤RC梁抗弯性能的试验研究[J]. 四川建筑科学研究, 2013, 39(4): 112 − 116, 122. doi: 10.3969/j.issn.1008-1933.2013.04.025Sun Zhiyang, Zhang Zhimei, Liu Tao. Experimental study on the flexural behavior of damaged reinforced concrete beams strengthened with near-surface mounted CFRP laminates [J]. Sichuan Building Science, 2013, 39(4): 112 − 116, 122. (in Chinese) doi: 10.3969/j.issn.1008-1933.2013.04.025 [59] 王海良, 张静, 杨新磊. 玄武岩纤维布加固受损钢筋混凝土梁抗弯性能试验研究[J]. 工业建筑, 2015, 45(5): 152 − 156, 173.Wang Hailiang, Zhang Jing, Yang Xinlei. Experimental study of flexural performance of damaged RC beams strengthened with BFRP sheets [J]. Industrial Construction, 2015, 45(5): 152 − 156, 173. (in Chinese) [60] 王苏岩, 杨玫. 碳纤维布加固高强钢筋混凝土梁抗弯性能试验研究[J]. 建筑科学, 2006, 22(5): 34 − 38, 70. doi: 10.3969/j.issn.1002-8528.2006.05.008Wang Suyan, Yang Mei. Experimental Study of flexural behavior of high-strength RC beams strengthened with CFRP sheets [J]. Building Science, 2006, 22(5): 34 − 38, 70. (in Chinese) doi: 10.3969/j.issn.1002-8528.2006.05.008 [61] 吴亚玲. 预应力CFRP加固梁的抗弯试验研究及有限元数值模拟分析[D]. 长沙: 长沙理工大学, 2018.Wu Yaling. Research on flexural test and finite element numerical simulation of prestressed CFRP reinforced beams [D]. Changsha: Changsha University of Science and Technology, 2018. (in Chinese) [62] 闫一彪. BFRP筋嵌入式加固混凝土梁受弯性能试验研究与有限元模拟[D]. 西安: 长安大学, 2019.Yan Yibiao. Experimental study and finite element simulation on flexural performance of reinforced concrete beams strengthened with near surface mounted BFRP bars [D]. Xi’an: Chang’an University, 2019. (in Chinese) [63] 杨峰亮, 郑七振. 碳纤维布加固钢筋混凝土梁抗弯性能试验研究[J]. 上海理工大学学报, 2006(4): 351 − 354, 358. doi: 10.3969/j.issn.1007-6735.2006.04.011Yang Fengliang, Zheng Qizhen. Experimental research on flexural behavior of reinforced concrete beam strengthened with CFS [J]. Journal of University of Shanghai for Science and Technology, 2006(4): 351 − 354, 358. (in Chinese) doi: 10.3969/j.issn.1007-6735.2006.04.011 [64] 张浩. 不同配筋率下CFRP加固再生混凝土梁抗弯性能研究[D]. 成都: 西华大学, 2016.Zhang Hao. Flexural properties of CFRP strengthened recycling concrete beams under different reinforcement ratio [D]. Chengdu: Xihua University, 2016. (in Chinese) [65] 张自荣, 张素梅, 李九阳. 碳纤维加固钢筋混凝土梁抗弯性能试验研究[J]. 长春工程学院学报(自然科学版), 2001, 2(4): 13 − 15.Zhang Zirong, Zhang Sumei, Li Jiuyang. Experimental research of RC beams strengthened by carbon fiber reinforced plastic [J]. Journal of Changchun Institute of Technology (Natural Sciences Edition), 2001, 2(4): 13 − 15. (in Chinese) [66] 赵彤, 谢剑, 戴自强. 碳纤维布加固钢筋混凝土梁的受弯承载力试验研究[J]. 建筑结构, 2000, 30(7): 11 − 15.Zhao Tong, Xie Jian, Dai Ziqiang. Experimental research on the flexural bearing capacity of reinforced concrete beams strengthened with CFRP sheets [J]. Building Structure, 2000, 30(7): 11 − 15. (in Chinese) [67] Dietterich T G. Ensemble learning [M]. Cambridge: The MIT Press, 2002. [68] Chen T Q, Guestrin C. XGBoost: A scalable tree boosting system [C]// ACM. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016: 785 − 794. [69] Chakraborty D, Elzarka H. Early detection of faults in HVAC systems using an XGBoost model with a dynamic threshold [J]. Energy and Buildings, 2019, 185(FEB.): 326 − 344. [70] 赵良科, 黄靓, 曾令宏, 等. 聚酯纤维FRP加固钢筋混凝土梁抗弯性能[J]. 结构工程师, 2018, 34(4): 160 − 166. doi: 10.3969/j.issn.1005-0159.2018.04.022Zhao Liangke, Huang Liang, Zeng Linghong, et al. The bending bearing capacity of polyester FRP strengthened RC beams [J]. Structural Engineers, 2018, 34(4): 160 − 166. (in Chinese) doi: 10.3969/j.issn.1005-0159.2018.04.022 -