基于贝叶斯神经网络的钢筋与混凝土黏结强度预测模型研究

王海波

doi:10.13204/j.gyjzg22031516

基于贝叶斯神经网络的钢筋与混凝土黏结强度预测模型研究

doi: 10.13204/j.gyjzg22031516

王海波

西安长安大学工程设计研究院有限公司, 西安 710064

详细信息

作者简介:
王海波,男,1972年出生,工程师。电子信箱:642560953@qq.com

计量
- 文章访问数: 90
- HTML全文浏览量: 14
- PDF下载量: 4
- 被引次数: 0
出版历程
- 收稿日期: 2022-03-15
- 网络出版日期: 2023-02-06

A Prediction Model for Bond Strength Between Concrete and Steel Bars Based on Bayesian Neural Networks

WANG Hai-bo

The Engineering Design Academy of Chang'an University Co., Ltd., Xi'an 710064, China

摘要

摘要: 提出一种新的钢筋与不同种类骨料混凝土间黏结强度的计算方法。结合748组试验数据,引入神经网络动态更新理论,建立了基于神经网络方法的黏结强度多参数预测模型,通过对黏结强度影响因素显著性的分析,利用神经网络参数剔除法简化了预测模型,并提出了临界锚固长度计算式。结果表明:钢筋与混凝土黏结强度主要受混凝土抗拉强度、锚固长度、钢筋直径和混凝土保护层厚度等因素的影响;建议模型具有较高预测精度,模型预测值与试验值比值的平均值和变异系数分别为1.052和0.337,为预测钢筋与混凝土黏结强度提供了新思路。
- 骨料种类 /
- 黏结强度 /
- 贝叶斯神经网络 /
- 参数显著性分析 /
- 预测模型
Abstract: A new calculation method of bond strength between steel bars and concrete with different aggregate types was proposed. Combined with 748 groups of test data and the introduction to dynamic renewal theories of the neural network, a prediction model with multi parameters for bond strength based on neural network method was established, the significance analysis of influencing factors of bond strength was conducted, the prediction model was simplified by the parameter elimination method of the neural network, and the formula for critical anchorage length was put forward. Important factors that influenced bond performances were tensile strength, anchorage length, diameters of steel bars, and thickness of concrete covers. The proposed model was of higher prediction accuracy and the mean value and coefficient of variation for the ratio of the prediction values to test values were 1.056 and 0.377 respectively. It provided a new method to predict bond strength between steel bars and concrete.
- aggregate type /
- bond strength /
- bayesian ANNs /
- significance analysis for parameter /
- prediction model

HTML全文

参考文献(42)

[1]	魏慧, 吴涛, 杨雪, 等.纤维增韧轻骨料混凝土单轴受压应力-应变全曲线试验研究[J].工程力学, 2019, 36(7):126-135 , 173.
[2]	肖建庄, 林壮斌, 朱军.再生骨料级配对混凝土抗压强度的影响[J].四川大学学报(工程科学版), 2014, 46(4):154-160.
[3]	American Concrete Institute (ACI).Bond and development of straight reinforcing bars in tension:ACI 408R-03.[S].Farmington Hills:ACI, 2003.
[4]	张凯甲.高性能混凝土和钢筋黏结本构关系的分析研究[D].合肥:合肥工业大学, 2010.
[5]	MELO J, FERNANDES C, VARUM H, et al.Numerical modelling of the cyclic behaviour of RC elements built with plain reinforcing bars[J].Eng.Struct., 2011, 33(2):273-286.
[6]	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].北京:中国建筑工业出版社, 2010.
[7]	British Standards Institution (BSI).Eurocode 2:design of concrete structures:EN 1992-1-1:2004[S].London:BSI, 2004.
[8]	MARTIN H.Bond performance of ribbed bars-influence of concrete composition and consistency[C]//Proceedings of the International Conference on Bond in Concrete.1982:289-299.
[9]	CHEN H J, HUANG C H, KAO Z Y.Experimental investigation on steel-concrete bond in lightweight and normal weight concrete[J].Structural Engineering and Mechanics, 2004, 17(2):141-152.
[10]	陆春阳, 王卫玉, 李丕宁.陶粒混凝土与变形钢筋黏结锚固性能的试验研究[J].广西大学学报(自然科学版), 2007, 32(1):6-9.
[11]	李渝军, 叶列平, 程志军, 等.高强陶粒混凝土与变形钢筋黏结锚固强度的试验研究[J].建筑科学, 2006, 22(4):51-55.
[12]	TEPFERS R.Cracking of concrete cover along anchored deformed reinforcing bars[J].Magazine of Concrete Research, 1979, 31(106):3-12.
[13]	曹万林, 林栋朝, 乔崎云, 等.钢筋与再生混凝土黏结性能及影响因素研究[J].自然灾害学报, 2017, 26(5):36-44.
[14]	牛建刚, 边钰, 谢承斌.再生混凝土与锈蚀钢筋界面黏结性能[J].科学技术与工程, 2020, 20(19):7845-7851.
[15]	SEARA-PAZ S, GONZÁLEZ-FONTEBOA B, EIRAS-LÓPEZ J, et al.Bond behavior between steel reinforcement and recycled concrete[J].Mater.Struct., 2014, 47(1):323-334.
[16]	王毅红, 张建雄, 兰官奇, 等.压制生土砖强度的人工神经网络预测模型[J].华南理工大学学报(自然科学版), 2020, 48(7):115-121.
[17]	陈祝云, 钟琪, 黄如意, 等.基于增强迁移卷积神经网络的机械智能故障诊断[J].机械工程学报, 2021, 57(21):96-105.
[18]	朱文慧, 邹浩, 何明明, 等.基于BP神经网络的地质灾害易发性分区方法研究:以蕲春县为例[J].资源环境与工程, 2020, 35(6):878-888.
[19]	郝彤, 刘斌, 于秋波, 等.全轻混凝土的钢筋黏结锚固性能试验研究[J].建筑科学, 2018, 34(3):69-752.
[20]	顾聪.钢筋-页岩陶粒混凝土黏结性能的梁式试验研究[D].南京:南京林业大学, 2017.
[21]	陈旭.纤维增韧高强轻骨料混凝土力学性能及黏结锚固性能研究[D].西安:长安大学, 2017.
[22]	姚瑞.高强陶粒混凝土与高强钢筋的黏结锚固性能试验研究[D].郑州:郑州大学, 2017.
[23]	王卫玉.陶粒混凝土与钢筋黏结锚固性能的试验研究[D].南宁:广西大学, 2005.
[24]	刘玲利.变形钢筋与钢纤维全轻混凝土黏结性能试验研究[D].郑州:华北水利水电大学, 2019.
[25]	朱明涛.全轻混凝土与HRB500钢筋黏结锚固性能试验研究[D].郑州:郑州大学, 2017.
[26]	平乐.钢筋与再生混凝土黏结性能的试验研究[D].佛山:佛山科学技术学院, 2019.
[27]	胡琼, 陈伟伟, 邹超英.再生混凝土黏结性能试验研究[J].哈尔滨工业大学学报, 2010, 42(12):1849-1854.
[28]	李鹏程, 彭有开, 李峰, 等.再生粗骨料对钢筋混凝土之间黏结性能的影响[J].土木建筑与环境工程, 2016, 38(增刊1):6-12.
[29]	任访春.再生混凝土与钢筋黏结性能试验研究[D].郑州:华北水利水电大学, 2016.
[30]	PRINCE M J R, SINGH B.Bond behaviour of deformed steel bars embedded in recycled aggregate concrete[J].Construction and Building Materials, 2013, 49:852-862.
[31]	PRINCE M J R, SINGH B.Bond behaviour between recycled aggregate concrete and deformed steel bars[J].Materials and Structures, 2014, 47(3):503-516.
[32]	PRINCE M, SINGH B.Bond strength of deformed steel bars in high-strength recycled aggregate concrete[J].Materials and Structures, 2015, 48(12):3913-3928.
[33]	HUANG Q F, WANG D F.Experimental study on bond-slip between steel bar and recycled aggregate concrete[J].Concrete, 2011, 250/251/252/253:1651-1656.
[34]	XIAO J, FALKNER H.Bond behaviour between recycled aggregate concrete and steel rebars[J].Construction and Building Materials, 2007, 21(2):395-401.
[35]	秦帅.钢筋混凝土间黏结滑移关系的解析模型及试验研究[D].南宁:广西大学, 2021.
[36]	王树钧.变形钢筋与后掺骨料混凝土黏结性能试验研究[D].大连:大连理工大学, 2019.
[37]	AREL H, EMSI YAZICI.Concrete-reinforcement bond in different concrete classes[J].Construction and Building Materials, 2012, 36:78-83.
[38]	ESFAHANI M R, RANGAN B V.Local bond strength of reinforcing bars in normal strength and high-strength concrete (HSC)[J].ACI Structural Journal, 1998, 95(2):96-106.
[39]	李海涛, ANDREW J D, 苏小卒, 等.保护层厚度对受拉与受压黏结强度的影响[J].华中科技大学学报(自然科学版), 2012, 40(5):80-83.
[40]	毛达岭.HRB500钢筋黏结锚固性能的试验研究[D].郑州:郑州大学, 2004.
[41]	DOMBI G W, NANDI P, SAXE J M, et al.Prediction of rib fracture injury outcome by an artificial neural network[J].Journal of Trauma and Acute Care Surgery, 1995, 39(5):915-921.
[42]	徐有邻.钢筋混凝土黏结滑移本构关系的简化模型[J].工程力学, 1997(增刊):34-38.