基于广义回归神经网络的纤维增强聚合物复合材料约束损伤混凝土强度预测

曹玉贵; 赵国旭; 尹亚运

doi:10.13801/j.cnki.fhclxb.20200804.001

基于广义回归神经网络的纤维增强聚合物复合材料约束损伤混凝土强度预测

doi: 10.13801/j.cnki.fhclxb.20200804.001

1.
武汉理工大学　道路桥梁与结构工程湖北省重点实验室，武汉 430070
2.
武汉理工大学　土木工程与建筑学院，武汉 430070

基金项目: 国家自然科学基金(51808419)；湖北省自然科学基金(2019CFB217)；湖北省重大专项研发计划(2018AAA001)；武汉理工大学自主创新基金(2019IVA089)

详细信息

通讯作者:
尹亚运，硕士，实验师，研究方向为FRP约束混凝土结构　E-mail：yin16103@163.com

中图分类号: TU375
计量
- 文章访问数: 1454
- HTML全文浏览量: 579
- PDF下载量: 85
- 被引次数: 0
出版历程
- 收稿日期: 2020-05-21
- 录用日期: 2020-07-19
- 网络出版日期: 2020-08-04
- 刊出日期: 2021-05-01

Strength prediction of fiber reinforced polymer composite confined damaged concrete using general regression neural network

CAO Yugui¹,
ZHAO Guoxu^1
,,
YIN Yayun^{2
, ,}

1.
Hubei Key Laboratory of Roadway Bridge and Structure Engineering, Wuhan University of Technology, Wuhan 430070, China
2.
School of Civil Engineering and Architecture, Wuhan University of Technology, Wuhan 430070, China

摘要

摘要: 纤维增强聚合物复合材料(FRP)约束损伤混凝土抗压强度模型对于混凝土柱类构件的修复和加固具有重要指导意义。现有FRP修复混凝土的强度模型适用条件有限，同一模型不能同时应用于不同强弱约束、不同强度混凝土、不同倒角混凝土的强度预测。本文根据广义回归神经网络(GRNN)的特点，基于46个FRP强约束损伤混凝土方柱、210个FRP强约束损伤混凝土圆柱和35个FRP弱约束损伤混凝土圆柱的试验数据，建立了GRNN抗压强度模型，对FRP约束损伤混凝土的强度进行预测，并与现有模型的预测结果进行对比分析，结果表明，新建立的GRNN模型能够准确地预测FRP约束损伤混凝土的强度。
- 广义回归神经网络(GRNN) /
- FRP约束损伤混凝土 /
- 抗压强度 /
- 强弱约束 /
- 不同截面形状
Abstract: The compressive strength of damaged concrete reinforced with fiber reinforced polymer composite (FRP) has an important guiding significance in repairing of concrete columns. However, the existing model cannot capture the compressive strength of FRP hardening and softening confined damaged concrete with circular and square cross section. In order to fill this gap, an experimental database of 46 FRP hardening confined square damaged concrete, 210 FRP hardening confined circular damaged concrete and 35 FRP softening confined circular damaged concrete was established. Based on the characteristics of generalized regression neural network (GRNN) and database, the GRNN compressive strength model of FRP confined damaged concrete was developed. The GRNN model was compared with the existing model. The results show that the GRNN model can accurately predict the strength of FRP confined damaged concrete columns.
- generalized regression neural network (GRNN) /
- FRP confined damaged concrete /
- compressive strength /
- hardening and softening confinement /
- different cross sections

HTML全文

图 1 广义回归神经网络结构(GRNN)

Figure 1. General regression neural network structure (GRNN)

下载: 全尺寸图片幻灯片

图 2 平滑因子σ与GRNN模型预测误差指标R_RMSE的关系

Figure 2. Relationship between smooth factor σ value and GRNN model prediction error index R_RMSE

下载: 全尺寸图片幻灯片

图 3 GRNN模型预测结果

Figure 3. GRNN model prediction results

下载: 全尺寸图片幻灯片

图 4 现有抗压强度模型预测结果

Figure 4. Prediction results of existing compressive strength models

下载: 全尺寸图片幻灯片

表 1 纤维增强聚合物复合材料(FRP)约束损伤混凝土数据

Table 1. Database of fiber reinforced polymer composite (FRP) confined damaged concrete

Reference	Number of specimen	FRP type	Crosssection	Confinement state	2r/b	f_l/MPa	δ/%	f_co/MPa	f_cc/MPa
Wu^[15]	102	CFRP	Circle	Hard	1	3.74−21.7	0−58	29.3−53.6	12.8−121.1
Li^[23]	46	CFRP	Square	Hard	0.2−0.6	3.7−14.1	0−35	43.8	39.0−49.2
Guo^[24]	60	CFRP	Circle	Hard	1	5.6−25.8	0−32.7	34.2−70.2	57.6−146.4
Cao^[25]	12	CFRP	Circle	Hard	1	10.1−20.3	0.68−29.5	25.0−29.0	54.0−78.0
Ma^[26]	12	BFRP	Circle	Hard	1	3.0−15.0	0−26.9	38.0	45.7−172.3
Cui^[27]	6	GFRP	Circle	Hard	1	5.3−33.4	2.28	46.0−48.0	56.3−157
Cui^[27]	18	CFRP	Circle	Hard	1	5.3−33.4	2.28	46.0−48.0	56.3−157
Own data	35	CFRP	Circle	Soft	1	0.4−2.9	0−67.8	22.7−56.8	10.8−56.9
Notes: 2r/b—Ratio of corner radius ratio; f_l—Confinement pressure; δ—Degree of damage; f_co—Compressive strength of plain concrete; f_cc—Compressive strength of FRP confined damaged concrete; CFRP—Carbon fiber reinforced polymer composite; GFRP—Glass fiber reinforced polymer composite; BFRP—Basalt fiber reinforced polymer composite.

下载: 导出CSV

参考文献(30)

[1]	WU Y, ZHOU Y. Unified strength model based on Hoek-Brown failure criterion for circular and square concrete columns confined by FRP[J]. Journal of Composites for Construction,2010,14(2):175-184. doi: 10.1061/(ASCE)CC.1943-5614.0000062
[2]	PELED A. Confinement of damaged and nondamaged structural concrete with FRP and TRC sleeves[J]. Journal of Composites for Construction,2007,11(5):514-522. doi: 10.1061/(ASCE)1090-0268(2007)11:5(514)
[3]	THERMOU G E, PANTAZOPOULOU S J. Fiber-reinforced polymer retrofitting of predamaged substandard RC prismatic members[J]. Journal of Composites for Construction,2009,13(6):535-546. doi: 10.1061/(ASCE)CC.1943-5614.0000057
[4]	欧阳利军, 许峰, 陆洲导. 玄武岩纤维布增强树脂基复合材料约束高温损伤混凝土轴压力学性能[J]. 复合材料学报, 2018, 35(8):2002-2013. OUYANG L J, XU F, LU Z D. Axial compressive behavior of basalt fiber reinforced polymer confined damaged concrete after exposed to elevated temperatures[J]. Acta Materiae Compositae Sinica,2018,35(8):2002-2013(in Chinese).
[5]	焦楚杰, 李松, 崔力仕, 等. CFRP约束钢管-活性粉末混凝土短柱轴压性能[J]. 复合材料学报, 2021, 38(2):439-448. JIAO C J, LI S, CUI L S, et al. Axial compression behaviour of CFRP confined reactive power concrete filled steel tube stub columns[J]. Acta Materiae Compositae Sinica,2021,38(2):439-448(in Chinese).
[6]	李趁趁, 于爱民, 高丹盈, 等. 侵蚀环境下FRP条带加固锈蚀钢筋混凝土圆柱轴心受压试验[J]. 复合材料学报, 2020, 37(8):2015-2028. LI C C, YU A M, GAO D Y, et al. Experimental study on axial compression of corroded reinforced concrete columns strengthened with FRP strips under erosion environment[J]. Acta Materiae Compositae Sinica,2020,37(8):2015-2028(in Chinese).
[7]	高鹏, 赵元鸿, 洪丽, 等. 圆角半径对碳纤维增强聚合物复合材料布约束型钢混凝土矩形短柱轴压性能的影响[J]. 复合材料学报, 2020, 37(4):775-785. GAO P, ZHAO Y H, HONG L, et al. Effect of corner radius on axial compressive performance of steel reinforced concrete rectangular short columns confined by carbon fiber reinforced polymer composite[J]. Acta Materiae Compositae Sinica,2020,37(4):775-785(in Chinese).
[8]	MA G, LI H, DUAN Z. Repair effects and acoustic emission technique-based fracture evaluation for predamaged concrete columns confined with fiber-reinforced polymers[J]. Journal of Composites for Construction,2012,16(6):626-639. doi: 10.1061/(ASCE)CC.1943-5614.0000309
[9]	LI Y, LIN Y, CHEN C, et al. Theoretical and experimental studies on repaired and rehabilitated reinforced concrete frames[J]. Canadian Journal of Civil Engineering,2007,34(8):923-933. doi: 10.1139/l07-012
[10]	LENWARI A, RUNGAMORNRAT J, WOONPRASERT S. Axial compression behavior of fire-damaged concrete cylinders confined with CFRP sheets[J]. Journal of Composites for Construction,2016,20(5):04016027. doi: 10.1061/(ASCE)CC.1943-5614.0000683
[11]	CAO Y, LI X, HU J. Compressive strength estimation for the fiber-reinforced polymer (FRP)-confined concrete columns with different shapes using artificial neural networks[J]. Journal of Donghua University (English Edition),2015,32(3):395-400.
[12]	SAADATMANESH H, EHSANI M R, JIN L. Repair of earthquake-damaged RC columns with FRP wraps[J]. ACI Structural Journal,1997,94(2):206-214.
[13]	MA C K, LEE Y H, AWANG A Z, et al. Artificial neural network models for FRP-repaired concrete subjected to pre-damaged effects[J]. Neural Computing and Applications,2019,31(3):711-717. doi: 10.1007/s00521-017-3104-7
[14]	尤杰, 车轶, 仲伟秋. 基于BP神经网络的既有建筑混凝土强度预测[J]. 建筑科学与工程学报, 2011, 28(1):70-75. YOU J, CHE Y, ZHONG W Q. Predition of concrete strength of existing buildings based on BP neural networks[J]. Journal of Architecture and Civil Engineering,2011,28(1):70-75(in Chinese).
[15]	WU Y, YUN Y, WEI Y, et al. Effect of predamage on the stress-strain relationship of confined concrete under monotonic loading[J]. Journal of Structural Engineering,2014,140(12):4014093. doi: 10.1061/(ASCE)ST.1943-541X.0001015
[16]	ÖZTAŞ A, PALA M, ÖZBAY E, et al. Predicting the compressive strength and slump of high strength concrete using neural network[J]. Construction and Building Materials,2006,20(9):769-775. doi: 10.1016/j.conbuildmat.2005.01.054
[17]	LI P, WU Y, GRAVINA R. Cyclic response of FRP-confined concrete with post-peak strain softening behavior[J]. Construction and Building Materials,2016,123:814-828. doi: 10.1016/j.conbuildmat.2016.07.065
[18]	WANG L, WU Y. Effect of corner radius on the performance of CFRP confined square concrete columns: Test[J]. Engineering Structures,2008,30(2):493-505. doi: 10.1016/j.engstruct.2007.04.016
[19]	张扬, 曹玉贵, 胡志礼. 基于Griffith破坏准则的FRP约束未损伤混凝土和损伤混凝土的抗压强度统一模型[J]. 复合材料学报, 2020, 37(9):2358-2366. ZHANG Y, CAO Y G, HU Z L. Unified strength model based on Griffith failure criterion for FRP-confined undamaged and damaged concrete[J]. Acta Materiae Compositae Sinica,2020,37(9):2358-2366(in Chinese).
[20]	REN S, YANG D, JI F, et al. Application of generalized regression neural network in prediction of cement properties[C]//2010 International Conference On Computer Design and Applications. Qinhuangdao: IEEE, 2010.
[21]	何正风. MATLAB R2015b神经网络技术[M]. 北京: 清华大学出版社, 2016. HE Z F. MATLAB R2015b neural network technology[M]. Beijing: Tsinghua University Press, 2016(in Chinese).
[22]	陈涛, 郭卫卫, 孟令智, 等. 基于广义回归神经网络的路面摩擦系数预测模型[J]. 公路, 2014, 59(6):1-6. CHEN T, GUO W W, MENG L Z, et al. Prediction model of road friction coefficient based on GRNN network[J]. High Way,2014,59(6):1-6(in Chinese).
[23]	LI P, SUI L, XING F, et al. Stress-strain relation of FRP-confined predamaged concrete prisms with square sections of different corner radii subjected to monotonic axial compression[J]. Journal of Composites for Construction,2019,23(2):04019001. doi: 10.1061/(ASCE)CC.1943-5614.0000921
[24]	GUO Y, XIE J, XIE Z, et al. Experimental study on compressive behavior of damaged normal and high strength concrete confined with CFRP laminates[J]. Construction and Building Materials,2016,107:411-425. doi: 10.1016/j.conbuildmat.2016.01.010
[25]	CAO Y G, LIU M, ZHANG Y, et al. Effect of strain rates on the stress-strain behavior of FRP-confined pre-damaged concrete[J]. Materials,2020,13(5):1078. doi: 10.3390/ma13051078
[26]	MA G, LI H, YAN L, et al. Testing and analysis of basalt FRP-confined damaged concrete cylinders under axial compression loading[J]. Construction and Building Materials,2018,169:762-774. doi: 10.1016/j.conbuildmat.2018.02.172
[27]	CUI C. Behaviour of normal and high strength concrete confined with fibre reinforced polymers (FRP)[D]. Toronto: University of Toronto, 2009.
[28]	LAM L, TENG J G. Design-oriented stress-strain model for FRP-confined concrete in rectangular columns[J]. Journal of Reinforced Plastics and Composites,2003,22(13):1149-1186. doi: 10.1177/0731684403035429
[29]	LAM L, TENG J G. Strength models for fiber-reinforced plastic-confined concrete[J]. Journal of Structural Engineering,2002,128(5):612-623. doi: 10.1061/(ASCE)0733-9445(2002)128:5(612)
[30]	OZBAKKALOGLU T, LIM J C. Axial compressive behavior of FRP-confined concrete: Experimental test database and a new design-oriented model[J]. Composites Part B: Engineering,2013,55:607-634. doi: 10.1016/j.compositesb.2013.07.025