基于可解释机器学习方法的RC深受弯构件开裂剪力预测

马财龙; 王文虎; 侯宪龙; 谢晨曦; 鲁成凤

doi:10.13568/j.cnki.651094.651316.2023.02.28.0001

您当前的位置：

首页 >

文章列表页 >

基于可解释机器学习方法的RC深受弯构件开裂剪力预测

工程技术 | 更新时间：2026-01-21

- 基于可解释机器学习方法的RC深受弯构件开裂剪力预测
- 基于可解释机器学习方法的RC深受弯构件开裂剪力预测
- 新疆大学学报（自然科学版中英文） 2023年40卷第5期页码：621-629
- 作者机构：
  
  1. 新疆大学建筑工程学院
  2. 新疆大学新疆建筑结构与抗震重点实验室
- 作者简介：
- 基金信息：
  
  新疆天山青年计划-青年博士科技人才培养项目“钢筋混凝土深受弯构件的受剪性能状态划分及机理模型”（2020Q069）;新疆大学引进博士科研启动项目“钢筋混凝土框架节点基于性能的受剪设计方法”（620312396）
- DOI：10.13568/j.cnki.651094.651316.2023.02.28.0001
  中图分类号： TU375
- 纸质出版：2023
- 稿件说明：
移动端阅览
[1]马财龙,王文虎,侯宪龙,等.基于可解释机器学习方法的RC深受弯构件开裂剪力预测[J].新疆大学学报(自然科学版)(中英文),2023,40(05):621-629.
[1]马财龙,王文虎,侯宪龙,等.基于可解释机器学习方法的RC深受弯构件开裂剪力预测[J].新疆大学学报(自然科学版)(中英文),2023,40(05):621-629. DOI： 10.13568/j.cnki.651094.651316.2023.02.28.0001.

DOI：10.13568/j.cnki.651094.651316.2023.02.28.0001.

摘要

钢筋混凝土（Reinforced Concrete

RC）深受弯构件易发生脆性剪切破坏，斜裂缝产生及发展伴随全过程，开裂剪力是关键指标之一．建立了276根含开裂荷载信息的RC深受弯构件受剪试验数据库，采用机器学习XGBoost集成算法预测其开裂剪力，并采用5项统计指标评估机器学习模型的预测性能．从无腹筋和双向腹筋两类工况，对比了所建机器学习模型与5个半经验半理论计算公式的预测结果，表明所建预测模型的预测精度较高且离散性小，其R2为91%，预测值与试验值比值的均值为0.99，标准差为0.27．此外，采用SHAP(SHapley Additive ex Planations)可解释性方法对机器学习模型预测结果进行全局解释和局部解释，特征重要性排序由重要到一般依次为：加载板宽度、截面高度、混凝土抗压强度，表明所建模型及可解释性方法是符合机理的．

Abstract

Reinforced Concrete(RC) is susceptible to brittle shear failure

and diagonal cracking occurs and develops throughout the process

and cracking shear is one of the key indicators. In this paper

a database of276 shear tests with cracking load information of RC deep beams was established

and the machine learning XGBoost ensemble algorithm was used to predict their cracking strength

and five statistical indicators were used to evaluate the prediction performance of the machine learning model. The prediction results of the proposed machine learning model were compared with five semi-empirical and semi-theoretical formulations according to the case of the deep beam without web reinforcement and with web reinforcement

indicating that the prediction accuracy of the proposed prediction model is high and the dispersion is small. The R2is 91%

the mean value of the ratio of predicted to tested values is 0.99

and the standard deviation is 0.27. In addition

SHAP(SHapley Additive ex Planations) interpretable method was used to globally and locally interpret the prediction results of the machine learning model

and the ranking of feature importance from important to general is: loading slab width

section height

and concrete compressive strength. The results show that the proposed model and interpretable method are consistent with the mechanism.

关键词

Keywords

references

中华人民共和国住房和城乡建设部.混凝土结构设计规范:GB 50010―2010[S].中国建筑工业出版社, 2016.

郭杨东. 600 MPa级钢筋混凝土深梁受剪承载力试验研究及有限元分析[D].郑州:华北水利水电大学, 2020.

TAN K H, KONG F K, TENG S, et al. High-strength concrete deep beams with effective span and shear span variations[J]. ACI Structural Journal, 1995, 92(4):395-405.

BIRRCHER D, TUCHSCHERER R, HUIZINGA M, et al. Strength and serviceability design of reinforced concrete deep beam[D].Austin:University of Texas at Austin, 2009.

仇一颗,刘霞,林云.钢筋混凝土简支深梁压杆-拉杆模型试验对比分析[J].建筑结构, 2012, 42(1):91-96.

ALCOCER S M, URIBE C M. Monolithic and cyclic behavior of deep beams designed using strut-and-tie models[J]. ACI Structural Journal, 2008, 105:327-337.

TUCHSCHERER R G, BIRRCHER D B, HUIZINGA M, et al. Confinement of deep beam nodal regions[J]. ACI Structural Journal, 2010, 107:709-717.

ACI-ASCE C. Shear and diagonal tension[J]. ACI Structural Journal, 1962, 59(3):1-7.

ZSUTTY T C. Beam shear strength prediction by analysis of existing data[J]. ACI Structural Journal&Proceedings, 1968, 65:138-143.

PLACAS A, REGAN P E. Shear failure of reinforced concrete beams[J]. Am Concrete Inst Journal&Proceedings, 1971, 68(10):763-773.

CHANG T S, KESLER C E. Static and fatigue strength in shear of beams with tensile reinforcement[J]. ACI Structural Journal,1958, 54:115-121.

SHIN S W, LEE K S, MOON J I, et al. Shear strength of reinforced high-strength concrete beams with shear span-to-depth ratios between 1.5 and 2.5[J]. ACI Structural Journal, 1999, 96(4):549-556.

南京工学院第五系.钢筋混凝土及预应力混凝土受弯构件斜截面开裂性能实用计算方法[R].南京:南京工学院, 1977.

郑州工学院水利系. RC简支弯筋梁抗剪性能报告（阶段报告）[R].郑州:郑州工学院, 1978.

何淅淅,徐积善.混凝土拉、压强度尺寸效应的研究[J].河海大学学报, 1997, 25(4):47-52.

彭天明.钢筋混凝土梁斜截面抗裂剪力计算[J].华东水利学院学报, 1981, 4:37-49.

李朋,郑鸿飞,张宪堂,等.基于模型试验的高强度钢筋混凝土梁斜向开裂研究[J].工业建筑, 2015, 45(1):73-79.

SOLHMIRZAEI R, SALEHI H, KODUR V R, et al. Machine learning framework for predicting failure mode and shear capacity of ultra high performance concrete beams[J]. Engineering Structures, 2020, 224:111221.

OLALUSI O B, AWOYERA P. Shear capacity prediction of slender reinforced concrete structures with steel fibers using machine learning[J]. Engineering Structures, 2021, 227:111470.

FENG D C, WANG W J, MANGALATHU S, et al. Implementing ensemble learning methods to predict the shear strength of RC deep beams with/without web reinforcements[J]. Engineering Structures, 2021, 235:111979.

于晓辉,王猛,宁超列.基于机器学习的钢筋混凝土柱失效模式两阶段判别方法[J].建筑结构学报, 2022, 43(8):220-231.

LUNDBERG S M, LEE S I. A unified approach to interpreting model predictions[C]//Advances in Neural Information Processing Systems. Long Beach:Statistics, 2017.

MANGALATHU S, HWANG S H, JEON J S. Failure mode and effects analysis of RC members based on machine-learning-based SHapley Additive exPlanations(SHAP)approach[J]. Engineering Structures, 2020, 219:110927.

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].建筑结构学报, 2022, 43(4):228-238.

SMITH K N, VANTSIOTIS A S. Shear strength of deep beams[J]. ACI Structural Journal, 1982, 79(3):201-213.

DEMIR A, CAGLAR N, OZTURK H. Parameters affecting diagonal cracking behavior of reinforced concrete deep beams[J].Engineering Structures, 2019, 184:217-231.

WALRAVEN J, LEHWALTER N. Size effects in short beams loaded in shear[J]. ACI Structural Journal, 1994, 91(5):585-593.

龚绍熙.钢筋混凝土深梁在对称集中荷载下抗剪强度的研究[J].郑州大学学报, 1982, 1:52-68.

ZHANG N, TAN K H. Size effect in RC deep beams:experimental investigation and STM verification[J]. Engineering Structures,2007, 29(12):3241-3254.

TUCHSCHERER R, KETTELKAMP J. Estimating the service-level cracking behavior of deep beams[J]. ACI Structural Journal,2018, 115(3):875-883.

YANG K, CHUNG H, LEE E, et al. Shear characteristics of high-strength concrete deep beams without shear reinforcements[J].Engineering Structures, 2003, 25(10):1343-1352.

ZHANG N, TAN K. Effects of support settlement on continuous deep beams and STM modeling[J]. Engineering Structures, 2010,32(2):361-372.

TAN K H, LU H Y. Shear behavior of large reinforced concrete deep beams and code comparisons[J]. ACI Structural Journal,1999, 96(5):836-846.

MATHEY R G. Shear strength of beams without web reinforcement containing deformed bars of different yield strengths[J]. ACI Journal Proceedings, 1963, 60(2):183-206.

MORROW J, VIEST I M. Shear strength of reinforced concrete frame members without web reinforcement[J]. ACI Journal Proceedings, 1957, 54:833-869.

BIRRCHER D B, TUCHSCHERER R G, HUIZINGA M, et al. Minimum web reinforcement in deep beams[J]. ACI Structural Journal, 2013, 110(2):297-306.

HASSAN T K, SELIEM H M, DAWIRI H, et al. Shear behavior of large concrete beams reinforced with high-strength steel[J].ACI Structural Journal, 2008, 105(2):173-179.

TAN K, KONG F, TENG S, et al. Effect of web reinforcement on high-strength concrete deep beams[J]. ACI Structural Journal,1997, 94(5):572-582.

OH J, SHIN S. Shear strength of reinforced high-strength concrete deep beams[J]. ACI Structural Journal, 2001, 98(2):164-173.

AGUILAR G, MATAMOROS A B, PARRA-MONTESINOS G J. Experimental evaluation of design procedures for shear strength of deep reinforced concrete beams[J]. ACI Structural Journal, 2002, 99(4):539-548.

PARRA-MONTESINOS G, WIGHT J K, QUINTERO-FEBRES C G. Strength of struts in deep concrete members designed using strut-and-tie method[J]. ACI Structural Journal, 2006, 103(4):577-586.

KONG P Y L, RANGAN B V. Shear strength of high performance concrete beams[J]. ACI Structural Journal, 1998, 95(6):677-688.

王宁宁.高强轻质混凝土深受弯构件抗剪性能试验研究[D].西安:长安大学, 2013.

WEI H, WU T, SUN L X, et al. Evaluation of cracking and serviceability performance of lightweight aggregate concrete deep beams[J]. KSCE Journal of Civil Engineering, 2020, 24(11):3342-3355.

林云.钢筋混凝土简支深梁的试验研究[D].长沙:湖南大学, 2011.

BRENA S F, ROY N C. Evaluation of load transfer and strut strength of deep beams with short longitudinal bar anchorages[J].ACI Structural Journal, 2009, 106(5):678-689.

BIRRCHER D B, TUCHSCHERER R G, HUIZINGA M, et al. Depth effect in deep beams[J]. ACI Structural Journal, 2014,111(4):731-740.

TUCHSCHERER R G, BIRRCHER D B, HUIZINGA M, et al. Distribution of stirrups across web of deep beams[J]. ACI Structural Journal, 2011, 108(1):108-115.

SAHOO D K, SAGI M S V, SINGH B, et al. Effect of detailing of web reinforcement on the behavior of bottle-shaped struts[J].Journal of Advanced Concrete Technology, 2010, 8(3):303-314.

SAFAVIAN S R, LANDGREBE D. A survey of decision tree classifier methodology[J]. IEEE Transactions on Systems, 1991,21(3):660-674.

SCHAATHUN H G. Support vector machines[J]. Machine Learning in Image Steganalysis, 1998, 13(4):18-28.

BREIMAN L. Bagging predictors[J]. Machine Learning, 1996, 24(2):123-140.

DRUCKER H, CORTES C, JACKEL L D, et al. Boosting and other ensemble methods[J]. Neural Computation, 1994, 6(6):1289-1301.

FREUND Y, SCHAPIRE R E. A decision-theoretic generalization of on-line learning and an application to boosting[J]. Journal of Computer and System Sciences, 1997, 55(1):119-139.

MCGUIRE T. Artificial neural networks[J]. Computer Audit Update, 1997, 1997(7):25-29.

CHEN T Q, GUESTRIN C. XGBoost:a scalable tree boosting system[C]//Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:Association for Computing Machinery, 2016.

浏览量

265

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

RC柱受剪承载力神经网络预测模型及其可解释性