基于PSO-SVR算法的钢板-混凝土组合连梁承载力预测

PDF(2570 KB)

振动与冲击 ›› 2025, Vol. 44 ›› Issue (7) : 155-162.

土木工程

基于PSO-SVR算法的钢板-混凝土组合连梁承载力预测

田建勃*1，闫靖帅1，王晓磊2，赵勇1，史庆轩3

作者信息 +

Prediction of load-bearing capacity of steel plate-RC composite coupling beam based on PSO-SVR algorithm

TIAN Jianbo*1, YAN Jingshuai1, WANG Xiaolei2, ZHAO Yong1, SHI Qingxuan3

Author information +

文章历史 +

摘要

为准确预测钢板-混凝土组合（PRC）连梁承载力，本文分别通过支持向量机回归算法（SVR）、极端梯度提升算法（XGBoost）和粒子群优化的支持向量机回归算法（PSO-SVR）进行了PRC连梁试验数据的回归训练，此外，通过使用Sobol敏感性分析方法分析了数据特征参数对PRC连梁承载力的影响。结果表明，基于SVR、XGBoost和PSO-SVR的预测模型平均绝对百分比误差分别为5.48%、7.65%和4.80%，其中，基于PSO-SVR算法的承载力预测模型具有最高的预测精度，模型的鲁棒性和泛化能力更强。此外，特征参数钢板率（ρp）、截面高度（h）和连梁跨高比（ln/h）对PRC连梁承载力影响最大，三者全局影响指数总和超过0.75，其中，钢板率（ρp）是对PRC连梁承载力影响最大的单一因素，一阶敏感性指数和全局敏感性指数分别为0.3423和0.3620，以期为PRC连梁在实际工程中的设计及应用提供参考。

Abstract

In order to accurately predict the bearing capacity of plate-reinforced composite (PRC) coupling beams, the regression training of PRC coupling beam test data was carried out by support vector regression (SVR), extreme gradient boosting algorithm (XGBoost) and particle swarm optimization support vector regression machine (PSO-SVR). In addition, the influence of data characteristic parameters on the bearing capacity of PRC coupling beams was analyzed by using Sobol sensitivity analysis method. The results show that the average absolute percentage errors of the prediction models based on SVM, XGBoost and PSO-SVR are 5.48 %, 7.65 % and 4.80 %, respectively. Among them, the bearing capacity prediction model based on PSO-SVR algorithm has the highest prediction accuracy, and the robustness and generalization ability of the model are stronger. In addition, the characteristic parameters of steel plate ratio (ρp), section height (h) and span-depth ratio (ln/h) have the greatest influence on the bearing capacity of PRC coupling beams, and the total global influence index of the three is more than 0.75. Among them, the steel plate ratio (ρp) is the single factor that has the greatest influence on the bearing capacity of PRC coupling beams. The first-order sensitivity index and global sensitivity index are 0.3423 and 0.3620, respectively. This paper aims to provide reference for the design and application of PRC coupling beams in practical engineering.

导出引用

田建勃1, 闫靖帅1, 王晓磊2, 赵勇1, 史庆轩3. 基于PSO-SVR算法的钢板-混凝土组合连梁承载力预测[J]. 振动与冲击, 2025, 44(7): 155-162

TIAN Jianbo1, YAN Jingshuai1, WANG Xiaolei2, ZHAO Yong1, SHI Qingxuan3. Prediction of load-bearing capacity of steel plate-RC composite coupling beam based on PSO-SVR algorithm[J]. Journal of Vibration and Shock, 2025, 44(7): 155-162

参考文献

[1] 刘阳，郭子雄，陈海，等.钢连梁-钢板混凝土组合剪力墙组合件抗震性能试验研究[J]. 建筑结构学报, 2021,42(03):41-49. (LIU Yang, GUO Zixiong, CHEN Hai, et al. Experimental study on seismic performance of subassemblies composed of steel coupling beam and steel plate-concrete composite shear wall piers [J]. Journal of Building Structures, 2021, 42(03): 41-49. (in Chinese))
[2] Tegos I A, Penelis G Gr. Seismic resistance of short columns and coupling beams reinforced with inclined bars[J]. ACI Structural Journal, 1988,85(01): 82-88.
[3] 孙占国，林宗凡，戴瑞同. 菱形配筋剪内墙连梁的受力性能 [J]. 建筑结构学报，1994, 15(5): 14-23.(SUN Zhanguo, LIN Zongfan, DAI Ruitong. Behavior of coupling beam of shear wall reinforced with inclined rhomboidal bars [J]. Journal of Building Structures, 1994, 15(5): 14-23. (in Chinese))
[4] 傅剑平，皮天祥，韦锋，等. 钢筋混凝土联肢墙小跨高比复合斜筋连梁抗震性能试验研究[J]. 土木工程学报，2011, 44(2): 57-64. (FU Jianping, PI Tianxiang, WEI Feng, et al. Experimental study on seismic behaviors of small-aspect-ratio coupling beams in RC structure walls proportioned with combined slanting reinforcements [J]. China Civil Engineering Journal, 2011, 44(2): 57-64. (in Chinese))
[5] 梁兴文，刘贞珍，刑朋涛，等. 纤维增强混凝土对角斜筋小跨高比连梁抗震性能试验研究及受剪承载力分析[J]. 土木工程学报，2017, 50(2): 27-35. (LIANG Xingwen, LIU Zhenzhen, XING Pengtao, et al. Experimental study on seismic behavior and shear capacity of diagonally reinforced fiber-reinforced concrete coupling beams with small span-to-depth ratio [J]. China Civil Engineering Journal, 2017, 50(2): 27-35. (in Chinese))
[6] 周巧玲，赵仕兴，苏明周，等. 混合联肢PEC墙结构基于合理失效模式的性能化设计方法研究[J]. 振动与冲击，2024，43(7): 266-277+289. (Zhou Qiaoling, Zhao Shixing, Su Mingzhou, et al. Performance-based design method for hybrid coupled PEC wall structure based on reasonable failure modes [J]. Journal of Vibration and Shock, 2024,43 (7) : 255-289. (in Chinese))
[7] 田建勃，王梦梦，张俊发，等. 钢板-纤维增强混凝土组合双连梁抗震性能试验研究[J]. 工程科学与技术, 2021, 53(3): 1-10. (TIAN Jianbo, WANG Mengmeng, ZHANG Junfa, et al. Seismic behavior of plate–fiber reinforced concrete composite double coupling beams [J]. Advanced Engineering Sciences, 2021, 53(3): 1-10. (in Chinese))
[8] 丁永君，于敬海，李端，等. 高强钢筋高强混凝土双连梁剪力墙抗震性能试验研究[J]. 建筑结构学报, 2015, 36(03): 56-63. (Experimental study on seismic behavior of high strength reinforced concrete double coupling beam shear wall [J]. Journal of Building Structures, 2015 36(03): 56-63. (in Chinese))
[9] 刘晓刚，樊健生，聂建国. 剪切型消能连梁的循环屈曲特性研究[J]. 工程力学, 2020, 37 (07): 89-98.(LIU Xiaogang, FAN Jiansheng, NIE Jianguo. Research on cyclic web bucking behavior of energy dissipation shear links [J]. Engineering Mechanics, 2020, 37(07): 89-98. (in Chinese))
[10] 纪晓东，王彦栋，马琦峰，等. 可更换钢连梁抗震性能试验研究[J]. 建筑结构学报，2015, 36(10): 1-10. (JI Xiaodong, WANG Yandong, MA Qifeng, et al. Experimental study on seismic behavior of replaceable steel coupling beams [J]. Journal of Building Structures, 2015, 36(10): 1-10. (in Chinese))
[11] 王宇航，刘元九，周绪红. 腹板屈曲约束钢连梁抗震性能研究[J]. 工程力学, 2019, 36 (06): 49-59. (WANG Yuhang, LIU Yuanjiu, ZHOU Xuhong. Study on seismic property of steel coupling beam with restrained web[J]. Engineering Mechanics, 2019, 36(06): 49-59. (in Chinese))
[12] 李国强，顾福霖，孙飞飞. 钢连梁与混凝土剪力墙内埋钢暗柱式连接节点受力性能——试验研究[J]. 土木工程学报，2017，50(02): 44-54. (LI Guoqiang, GU Fulin, SUN Feifei. Mechanical behaviors of embedded steel column connections between steel coupling beams and concrete shear walls——Experimental study[J]. China Civil Engineering Journal, 2017, 50(02): 44-54. (in Chinese))
[13] 史庆轩，田建勃，王秋维，等. 小跨高比钢板-混凝土组合连梁受力与变形性能研究[J]. 建筑结构学报，2016, 37(12): 83-96. (TIAN Jianbo, SHI Qingxuan, TAO Yi, et al. Research on mechanics and deformation performance of plate-reinforced composite coupling beams with small span to depth ratio [J]. Journal of Building Structures, 2016, 37(12): 83-96. (in Chinese))
[14] 侯炜，陈彬，郭子雄，等. 内嵌钢板混凝土组合连梁抗震性能试验研究[J]. 土木工程学报，2017, 50(2): 9-18. (Hou Wei, Chen Bin, Guo Zixiong, et al. Experimental study on seismic behaviors of embedded steel plate reinforced concrete coupling beams [J]. China Civil Engineering Journal, 2017, 50(2): 9-19. (in Chinese))
[15] 田建勃，史庆轩，陶毅，等. 小跨高比钢板-混凝土组合连梁受力与变形性能研究[J]. 建筑结构学报，2016, 37(12): 83-96. (TIAN Jianbo, SHI Qingxuan, TAO Yi, et al. Research on mechanics and deformation performance of plate-reinforced composite coupling beams with small span to depth ratio [J]. Journal of Building Structures, 2016, 37(12): 83-96. (in Chinese))
[16] 赵唯以，陈沛涵. 基于机器学习的单钢板混凝土组合板冲击响应预测及优化[J]. 振动与冲击，2023，42(30): 28-37. (Zhao Weiyi, Chen Peihan. Impact response prediction and optimization of half steel-concrete composite slabs based on machine learning [J]. Journal of Vibration and Shock, 2023,42 (30) : 28-37.(in Chinese))
[17] 李祥秀，宋笑彦，李小军，等. 基于机器学习的巨-子结构隔震体系地震损伤等级预测研究[J]. 振动与冲击，2023，42(20): 40-47+68. (Li Xiangxiu, Song Xiaoyan, Li Xiaojun et al. Research on earthquake damage level prediction of mega-sub isolation system based on machine learning [J]. Journal of Vibration and Shock, 2023,42 (20) : 40-48. (in Chinese))
[18] Xu D H, Xu X, Forde MC. Concrete and steel bridge Structural Health Monitoring—Insight into choices for machine learning applications[J]. Construction and Building Materials, 2023, 402: 132596.
[19] Zhang J X, Lei X M, Chan P W, et al. Integrating physics-informed machine learning with resonance effect for structural dynamic performance modeling[J]. Journal of Building Engineering, 2024, 84: 108627.
[20] Motsa S M, Stavroulakis G E, Drosopoulos G A. A data-driven, machine learning scheme used to predict the structural response of masonry arches[J]. Engineering Structures, 2023, 296: 116912.
[21] Arsiwala A, Elghaish F, Zoher M. Digital twin with Machine learning for predictive monitoring of CO2 equivalent from existing buildings. Energy Buildings, 2023, 248: 112851.
[22] Mazni M, Husain A R, Shapiai M I, et al. An investigation into real-time surface crack classification and measurement for structural health monitoring using transfer learning convolutional neural networks and Otsu method[J]. Alexandria Engineering Journal, 2024, 92: 310-320.
[23] Chen T Q, Guestrin C. XGBoost: a scalable tree boosting system, in: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, USA, 2016, p. 785-794.
[24] Chou J S, Liu C Y, Prayogo H, et al. Predicting nominal shear capacity of reinforced concrete wall in building by metaheuristics-optimized machine learning[J]. Journal of Building Engineering, 2022, 61: 105046.
[25] 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. (CHEN Xize, JIA Junfeng, BAI Yulei, et al. Prediction model of axial bearing capacity of concrete-filled steel tube columns based on XGBoost-SHAP[J]. Journal of Zhejiang University (Engineering Science), 2023, 57(6): 1061-1070 (in Chinese))
[26] Ma C L, Wang S X, Zhao J P, et al. Prediction of shear strength of RC deep beams based on interpretable machine learning[J]. Construction and Building Materials, 2023, 387: 131640.
[27] Yaseen Z M, Tran M T, Kim S, et al. Shear strength prediction of steel fiber reinforced concrete beam using hybrid intelligence models: A new approach. Eng Struct 2018;177:244–255[J]. Engineering Structures, 2018, 177: 244-255.
[28] Song K, Yan F, Ding T, et al. A steel property optimization model based on the XGBoost algorithm and improved PSO[J]. Computational Materials Science, 2020, 174: 109472.
[29] Han G M, Li H B, Wang G, et al. Prediction and control of profile for silicon steel strip in the whole tandem cold rolling based on PSO-BP algorithm[J]. Journal of Manufacturing Processes, 2024, 120: 250-259.
[30] Khatti J, Grover K S, Kim H J, et al. Prediction of ultimate bearing capacity of shallow foundations on cohesionless soil using hybrid LSTM and RVM approaches: An extended investigation of multicollinearity[J]. Computers and Geotechnics, 2024, 165: 105912.
[31] Zhu H, Su K, Luo GJ. Effective foundation damping prediction of monopile-supported offshore wind turbines based on integrated fitting equation and PSO–SVM algorithm. Ocean Engineering, 2023, 258: 115306.
[32] CHENG P C. Shear capacity of steel-plate reinforced concrete coupling beams [D]. Hong Kong: The Hong Kong University of Science and Technology, 2004: 11-84.
[33] Suen P C. Stee-plate encased concrete coupling beams[D]. Hong Kong: Hong Kong University of Science and Technology, 2012.
[34] Tian J B, Zhao Y, Tian P G, et al. Seismic behaviour of plate-reinforced composite coupling beams with RC slabs[J]. Soil Dynamics and Earthquake Engineering, 2023, 171: 107984.
[35] Tian J B, Zhao Y, Wang Y C, et al. Seismic performance and numerical analysis of steel plate-fiber reinforced concrete composite coupling beams[J]. Structures, 2023, 48: 258-274.
[36] Lam W Y，Su R，Pam H J. Experimental study on embedded steel plate composite coupling beams[J]. Journal of Structural Engineering. 2005, 131: 1294-1302.
[37] Su R, Pam H J, Lam W Y. Effects of shear connectors on plate-reinforced composite coupling beams of short and medium-length spans[J]. Journal of Constructional Steel Research, 2006, 62: 178-188.
[38] Su R, Lam W Y. A unified design approach for plate-reinforced composite coupling beams[J]. Journal of Constructional Steel Research, 2009, 65: 675-686.
[39] Hou W, Xu S L, Ji D S, et al. Cyclic Performance of Steel Plate–Reinforced High Toughness–Concrete Coupling Beams with Different Span-to-Depth Ratios[J]. Journal of Structural Engineering. 2018, 144: 1-11.
[40] Hou W, Xu S L, Ji D S, et al. Seismic performance of steel plate reinforced high toughness concrete coupling beams with different steel plate ratios. Composites Part B: Engineering, 2019, 159: 199-210.
[41] 张刚. 钢板混凝土连梁抗震性能试验研究[D]. 北京：清华大学，2005:4-27. (ZHANG Gang. Experimental study on seismic behavior of steel plate reinforced concrete coupling beams [D]. Beijing: Tsinghua University, 2005: 4-27. (in Chinese))
[42] 邓明科，张敏，张阳玺，等. 内置钢板-高延性混凝土组合连梁抗震性能试验研究[J]. 工程力学，2020，37(7): 47-56. (DENG Mingke, ZHANG Min, ZHANG Yangxi, et al. Experimental study seismic behavior of steel plate-high ductile concrete composite coupling beam[J]. Engineering Mechanics, 2020, 37: 47-56. (in Chinese))
[43] 田建勃，史庆轩，王南，等. 基于软化拉-压杆模型的小跨高比钢板-混凝土组合连梁受剪承载力分析[J]. 工程力学，2016，33(5): 142-149 . (TIAN Jianbo, SHI Qingxuan, WANG Nan, et al. Shear strength of plate-reinforced composite coupling beams with samll span-to-depth ratio using softened strut-and-tie model[J]. Engineering Mechanics, 2016, 35(5): 142-149. (in Chinese))
[44] YB 9082-2006 钢骨混凝土结构技术规程[S]. 北京: 冶金工业出版社, 2007. (YB 9082-2006 Technical specification of steel-reinforced concrete structures [S]. Beijing: Metallurgical Industry Press, 2007. (in Chinese) )
[45] Shen Y X, Wu L F, Liang S X. Explainable machine learning-based model for failure mode identification of RC flat slabs without transverse reinforcement[J]. Engineering Failure Analysis, 2022, 141: 106647.
[46] Gao X L, Lin C. Prediction model of the failure mode of beam-column joints using machine learning methods[J]. Engineering Failure Analysis, 2021, 120: 105072.
[47] Jiang C S, Liang G Q. Modeling shear strength of medium- to ultra-high-strength concrete beams with stirrups using SVR and genetic algorithm[J]. Soft Computing, 2021, 25: 0661–10675.
[48] Keshtegar B, Bagheri M, Yaseen Z M. Shear strength of steel fiber-unconfined reinforced concrete beam simulation: Application of novel intelligent model[J]. Composite Structures, 2019, 212: 230–242.
[49] Tan M J, Song X D, Yang X, et al. Support-vector-regression machine technology for total organic carbon content prediction from wireline logs in organic shale: a comparative study[J]. Journal of Natural Gas Science and Engineering, 2015, 26: 792–802.
[50] Priya G V, Ganguly S. Multi-swarm surrogate model assisted PSO algorithm to minimize distribution network energy losses[J]. Applied Soft Computing, 2024, 159: 111616.
[51] Shi Y, Eberhart R. A modified particle swarm optimizer[C]. 1998 IEEE international conference on evolutionary computation proceedings, 1998, 69-73.
[52] Sethi M R, Subba A B, Faisal M, Sahoo S, Raju D K. Fault diagnosis of wind turbine blades with continuous wavelet transform based deep learning model using vibration signal[J]. Engineering Applications of Artificial Intelligence, 2024, 138: 109372.
[53] Sun G R, Shi J, Deng Y. Predicting the capacity of perfobond rib shear connector using an ANN model and GSA method[J]. Journal of Alloys and Compounds, 2022, 16: 1233–1248.
[54] Oladyshkin S, Barros F P J D, Nowak W. Global sensitivity analysis: A flexible and efficient framework with an example from stochastic hydrogeology[J]. Advances in Water Resources, 2012, 37: 10-22.
[55] Chang X D, Xu Z X, Zhao G, et al. Sensitivity analysis on SWMM model parameters based on Sobol method[J]. Journal of Hydraulic Engineering, 2018, 37: 59-68.
[56] Zhang X Y, Trame M N, Lesko L J, et al. Sobol Sensitivity Analysis: A Tool to Guide the Development and Evaluation of Systems Pharmacology Models[J]. CPT: Pharmacometrics and Systems Pharmacology, 2015, 26: 69-79.