|本期目录/Table of Contents|

[1]沈袁协,梁诗雪.基于BP神经网络的FRP筋混凝土板抗冲切承载力预测模型[J].浙江理工大学学报,2022,47-48(自科三):441-451.
 SHEN Yuanxie,LIANG Shixue.The punching shear capacity prediction model for FRP reinforced concrete slabs based on BP neural network[J].Journal of Zhejiang Sci-Tech University,2022,47-48(自科三):441-451.
点击复制

基于BP神经网络的FRP筋混凝土板抗冲切承载力预测模型()
分享到:

浙江理工大学学报[ISSN:1673-3851/CN:33-1338/TS]

卷:
第47-48卷
期数:
2022年自科第三期
页码:
441-451
栏目:
出版日期:
2022-05-10

文章信息/Info

Title:
The punching shear capacity prediction model for FRP reinforced concrete slabs based on BP neural network
文章编号:
1673-3851 (2022) 05-0441-11
作者:
沈袁协梁诗雪
浙江理工大学建筑工程学院,杭州310018
Author(s):
SHEN Yuanxie LIANG Shixue
School of Civil Engineering and Architecture, Zhejiang  Sci-Tech University, Hangzhou 310018, China
关键词:
BP神经网络FRP筋混凝土板机器学习抗冲切承载力Garson算法
分类号:
TU377-9
文献标志码:
A
摘要:
为了改善现有FRP筋混凝土板抗冲切承载力预测模型因影响因素考虑不全而导致泛化性能较差的问题,建立了以数据驱动为核心的FRP筋混凝土板抗冲切承载力预测模型。首先收集了121组FRP筋混凝土板柱节点抗冲切承载力数据,采用BP神经网络建立了FRP筋混凝土板抗冲切承载力预测模型;然后采用Garson算法对影响FRP筋混凝土板抗冲切承载力的因素进行敏感性分析。将该模型与其他传统承载力计算公式的预测结果进行对比,结果表明该模型的预测结果最好,误差更小。与英国规范相比,均方根误差降低了29-7%,平均绝对百分比误差降低了21-5%,判定系数提升了3-6%。敏感性分析的结果验证了输入参数选取的合理性并得出了各参数的影响性排序,发现板的有效高度对冲切承载力的影响最为显著。该研究可为FRP筋板柱节点抗冲切性能的分析模型和精细化设计提供帮助。

参考文献/References:

[1]叶列平,冯鹏.FRP在工程结构中的应用与发展[J].土木工程学报,2006,39(3):24-36.
[2]韦锋,任子华,张俊华.钢筋混凝土板柱节点抗冲切性能研究综述[J].建筑结构,2020,50(S2):499-505.
[3]OspinaCE,AlexanderSDB,ChengJJR.Punchingoftwo-wayconcreteslabswithfiber-reinforcedpolymerreinforcingbarsorgrids[J].ACIStructuralJournal,2003,100(5):589-598.
[4]EbeadU,MarzoukH.Fiber-reinforcedpolymerstrengtheningoftwo-wayslabs[J].ACIStructuralJournal,2004,101(5):650-659.
[5]BouguerraK,AhmedEA,El-GamalS,etal.Testingoffull-scaleconcretebridgedeckslabsreinforcedwithfiber-reinforcedpolymer(FRP)bars[J].ConstructionandBuildingMaterials,2011,25(10):3956-3965.
[6]El-GamalSE.FiniteElementanalysisofconcretebridgeslabsreinforcedwithfiberreinforcedpolymerbars[J].TheJournalofEngineeringResearch,2014,11(2):50.
[7]HarajliMH,SoudkiKA.Shearstrengtheningofinteriorslab-columnconnectionsusingcarbonfiber-reinforcedpolymersheets[J].JournalofCompositesforConstruction,2003,7(2):145-153.
[8]ElsayedW,EbeadUA,NealeKW.InterfacialbehavioranddebondingfailuresinFRP-strengthenedconcreteslabs[J].JournalofCompositesforConstruction,2007,11(6):619-628.
[9]MosallamAS,MosalamKM.Strengtheningoftwo-wayconcreteslabswithFRPcompositelaminates[J].ConstructionandBuildingMaterials,2003,17(1):43-54.
[10]AbdullahA,BaileyCG.Punchingbehaviourofcolumn-slabconnectionstrengthenedwithnon-prestressedorprestressedFRPplates[J].EngineeringStructures,2018,160:229-242.

相似文献/References:

[1]李翔,顾宗栋,薛元,等.基于两种BP神经网络的精纺毛纱性能预测模型的比较[J].浙江理工大学学报,2011,28(03):347.
 LI Xiang,GU Zong dong,XUE Yuan,et al. Comparison of Prediction Models of Worsted Yarns Performances Based on Two Kinds of BP Neural Network[J].Journal of Zhejiang Sci-Tech University,2011,28(自科三):347.
[2]谭立章,王莹,高君.基于BP神经网络的大学生创业评价体系研究[J].浙江理工大学学报,2015,33-34(社科5):442.
 TAN Li zhang,WANG Ying,GAO Jun.Research on Entrepreneurial Evaluation System ofCollege Students Based on BP Neural Network[J].Journal of Zhejiang Sci-Tech University,2015,33-34(自科三):442.
[3]郭亮,郑俊娜.电磁悬浮高精密工作平台建模研究[J].浙江理工大学学报,2017,37-38(自科1):71.
 GUO Liang,ZHENG Junna.Research on Modeling of Electromagnetic Suspension HighPrecision Working Platform[J].Journal of Zhejiang Sci-Tech University,2017,37-38(自科三):71.
[4]骆桦,刘兴.基于主成分分析的神经网络算法对期权价格预测研究[J].浙江理工大学学报,2017,37-38(自科1):122.
 LUO Hua,LIU Xing.Study on Option Price Forecasting with Neural Network AlgorithmBased on Principal Component Analysis[J].Journal of Zhejiang Sci-Tech University,2017,37-38(自科三):122.
[5]李伯齐,郭建军,胡万哉,等.基于GA-BPNN优化铁皮石斛多糖提取工艺[J].浙江理工大学学报,2021,45-46(自科五):697.
 LI Boqi,GUO Jianjun,HU Wanzai,et al.Optimization of the extraction process of  Dendrobium officinale  polysaccharide based on GABPNN[J].Journal of Zhejiang Sci-Tech University,2021,45-46(自科三):697.

备注/Memo

备注/Memo:
收稿日期:2021-11-12
网络出版日期:2022-01-06
基金项目:浙江省自然科学基金项目(LY22E080016,LGF20E080019)
作者简介:沈袁协(1998-),男,宁波人,硕士研究生,主要从事混凝土结构方面的研究
通信作者:梁诗雪,E-mail:liangshixue0716@126.com
更新日期/Last Update: 2022-05-27