|Table of Contents|

Research on prediction of compressive strength of cable grouts based on SSA-BP(PDF)

《建筑科学与工程学报》[ISSN:1673-2049/CN:61-1442/TU]

Issue:
2025年03期
Page:
115-125
Research Field:
建筑材料
Publishing date:

Info

Title:
Research on prediction of compressive strength of cable grouts based on SSA-BP
Author(s):
BU Liangtao1;  YE Haoyan1;  DU Guoqiang2;  HOU Qi3
(1. College of Civil Engineering, Hunan University, Changsha 410082, Hunan, China; 2. Department of Civil Engineering, The University of Hong Kong, Hong Kong 999077, China; 3. Hunan Hongli Civil Engineering Inspection and Testing Co., Ltd., Changsha 410082, Hunan, China)
Keywords:
cable grout;  sparrow search algorithm;  BP neural network;  compressive strength prediction;  ultrasonic method;  surface hardness method
PACS:
TU528
DOI:
10.19815/j.jace.2023.12056
Abstract:
In order to achieve accurate prediction of compressive strength of grout, sparrow search algorithm(SSA)was introduced to optimize the initial weights and thresholds of BP neural network. Surface hardness method and ultrasonic testing experiments were designed and carried out using 108 sets of test data as samples, and a SSA-BP neural network prediction model for compressive strength of grout containing 2-node input layer, 9-node hidden layer, and 1-node output layer was established. The prediction results were compared with BP neural network, optimized BP neural network by genetic algorithm(GA)and strength measurement formula. The effects of different combinations of input parameters on the prediction effect of SSA-BP model were discussed. The results show that the mean square error(MSE)of SSA-BP model is reduced by 53.23% and 26.86% compared with BP model and GA-BP model, and the single training time is reduced by 34.40% compared with GA-BP model. Compared to the strength formula, the coefficient of determination R2 between predicted and measured values is increased from 0.937 to 0.975, and the MSE and mean absolute error(MAE)are decreased by 19.81% and 7.20%, respectively. Although the error accuracy of SSA-BP model with a single input parameter is reduced, it still has good generalization ability. SSA-BP model is able to better mine the data information of input and output parameters, and it is more advantageous than the traditional method in terms of the goodness of fit and prediction accuracy, which can accurately predict the compressive strength of grouts, and it provides a new method for predicting the performance of cable grouts.

References:

[1] 密士文,朱自强,彭凌星,等.T梁预应力波纹管压浆密实度超声检测试验研究[J].中南大学学报(自然科学版),2013,44(6):2378-2384.
MI Shiwen, ZHU Ziqiang, PENG Lingxing, et al. Experimental study of detecting grouting density of pre-stressed tendon ducts through ultrasonic[J]. Journal of Central South University(Science and Technology), 2013, 44(6): 2378-2384.
[2]邵旭东,曹君辉.面向未来的高性能桥梁结构研发与应用[J].建筑科学与工程学报,2017,34(5):41-58.
SHAO Xudong, CAO Junhui. Research and application of high performance bridge structures toward future[J]. Journal of Architecture and Civil Engineering, 2017, 34(5): 41-58.
[3]冯小伟,毛云程.预应力孔道压浆试件破坏的力学性能分析[J].混凝土,2014(1):155-158.
FENG Xiaowei, MAO Yuncheng. Mechanics property analysis on specimen damage of the prestressed duct grouting[J]. Concrete, 2014(1): 155-158.
[4]何聪岩.波纹管内钢绞线粘结性能试验与理论研究[D].天津:河北工业大学,2021.
HE Congyan. Theoretical and experimental research on bonding performance of steel strand in corrugated pipe[D]. Tianjin: Hebei University of Technology, 2021.
[5]李 鑫.核电用预应力钢绞线粘结滑移性能和锚固长度研究[D].大连:大连理工大学,2020.
LI Xin. Study on bond-slip properties and anchorage length of prestressing strand used in nuclear power plant[D]. Dalian: Dalian University of Technology, 2020.
[6]公路桥涵施工技术规范:JTG/T 3650—2020[S].北京:人民交通出版社,2020.
Technical specifications for construction of highway bridges and culverts: JTG/T 3650—2020[S]. Beijing: China Communications Press, 2020.
[7]张竞男,孙福洋,王 浩.基于BP神经网络的超声-回弹-钻芯综合测强法[J].建筑科学与工程学报,2009,26(1):68-74.
ZHANG Jingnan, SUN Fuyang, WANG Hao. Ultrasonic-rebound and core-drilling synthetic method in strength testing based on BP neural network[J]. Journal of Architecture and Civil Engineering, 2009, 26(1): 68-74.
[8]马 高,刘 康.基于BP神经网络CFRP约束混凝土抗压强度预测[J].湖南大学学报(自然科学版),2021,48(9):88-97.
MA Gao, LIU Kang. Prediction of compressive strength of CFRP-confined concrete columns based on BP neural network[J]. Journal of Hunan University(Natural Sciences), 2021, 48(9): 88-97.
[9]TENZA-ABRIL A J, VILLACAMPA Y, SOLAK A M, et al. Prediction and sensitivity analysis of compressive strength in segregated lightweight concrete based on artificial neural network using ultrasonic pulse velocity[J]. Construction and Building Materials, 2018, 189: 1173-1183.
[10]焦 莉,刘 明,李宏男.利用改进的BP神经网络预测烧结砖的抗压强度[J].建筑材料学报,2005,8(3):284-288.
JIAO Li, LIU Ming, LI Hongnan. Forecast about the compressive strength of clay brick based on improved BP neural network[J]. Journal of Building Materials, 2005, 8(3): 284-288.
[11]KEWALRAMANI M A, GUPTA R. Concrete compressive strength prediction using ultrasonic pulse velocity through artificial neural networks[J]. Automation in Construction, 2006, 15(3): 374-379.
[12]JIN L B, DUAN J, FAN T, et al. Using GA-BP coupling algorithm to predict the high-performance concrete mechanical property[J]. KSCE Journal of Civil Engineering, 2023, 27(2): 684-697.
[13]CHEN G, ZHU D L, WANG X, et al. Prediction of concrete compressive strength based on the BP neural network optimized by random forest and ISSA[J]. Journal of Function Spaces, 2022, 2022: 8799429.
[14]陈 庆,马 瑞,蒋正武,等.基于GA-BP神经网络的UHPC抗压强度预测与配合比设计[J].建筑材料学报,2020,23(1):176-183,191.
CHEN Qing, MA Rui, JIANG Zhengwu, et al. Compressive strength prediction and mix proportion design of UHPC based on GA-BP neural network[J]. Journal of Building Materials, 2020, 23(1): 176-183, 191.
[15]周 中,邓卓湘,陈 云,等.基于GA-BP神经网络的泡沫轻质土强度预测[J].华南理工大学学报(自然科学版),2022,50(11):125-132.
ZHOU Zhong, DENG Zhuoxiang, CHEN Yun, et al. Strength prediction of foam light soil based on GA-BP neural network[J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(11): 125-132.
[16]DU G Q, BU L T, HOU Q, et al. Prediction of the compressive strength of high-performance self-compacting concrete by an ultrasonic-rebound method based on a GA-BP neural network[J]. PLOS One, 2021, 16(5): e0250795.
[17]XUE J K, SHEN B. A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems Science & Control Engineering, 2020, 8(1): 22-34.
[18]段妹玲,张 单,袁锦虎,等.基于ISSA-GRU的混凝土抗压强度预测[J].硅酸盐通报,2023,42(7):2392-2400.
DUAN Meiling, ZHANG Dan, YUAN Jinhu, et al. Prediction of compressive strength of concrete based on ISSA-GRU[J]. Bulletin of the Chinese Ceramic Society, 2023, 42(7): 2392-2400.
[19]WANG K W, REN J, YAN J W, et al. Research on a concrete compressive strength prediction method based on the random forest and LCSSA-improved BP neural network[J]. Journal of Building Engineering, 2023, 76: 107150.
[20]LI G B, HU T Y, BAI D W. BP neural network improved by sparrow search algorithm in predicting debonding strain of FRP-strengthened RC beams[J]. Advances in Civil Engineering, 2021, 2021(1): 9979028.
[21]王庆荣,王俊杰,朱昌锋,等.融合VMD和SSA-LSSVM的交通运输业碳排放预测研究[J].环境工程,2023, 41(10): 124-132.
WANG Qingrong, WANG Junjie, ZHU Changfeng, et al. Carbon emission prediction of transportation industry based on VMD and SSA-LSSVM[J]. Environmental Engineering, 2023, 41(10): 124-132.
[22]金爱兵,张静辉,孙 浩,等.基于SSA-SVM的边坡失稳智能预测及预警模型[J].华中科技大学学报(自然科学版),2022,50(11):142-148.
JIN Aibing, ZHANG Jinghui, SUN Hao, et al. Intelligent prediction and alert model of slope instability based on SSA-SVM[J]. Journal of Huazhong University of Science and Technology(Natural Science Edition), 2022, 50(11): 142-148.
[23]装配整体式混凝土结构检测技术规程: DB32/T 3754—2020[S].南京:江苏科学技术出版社,2020.
Technical specification for testing of assembled monolithic concrete structures: DB32/T 3754—2020[S]. Nanjing: Jiangsu Science and Technology Press, 2020.
[24]吴 瑞.桥梁预应力管道灌浆密实度综合检测试验研究[D].成都:西华大学,2019.
WU Rui. Experimental study on comprehensive test of grouting density of bridge prestressed pipeline in bridge[D]. Chengdu: Xihua University, 2019.
[25]超声回弹综合法检测混凝土强度技术规程:CECS 02—2005[S].北京:中国计划出版社,2005.
Technical specification for detecting strength of concrete by ultrasonic-rebound combined method: CECS 02—2005[S]. Beijing: China Planning Press, 2005.
[26]李秀春,邓 亚,张春良,等.超声回弹综合法检测混凝土结构强度平测修正方法技术研究[J].建筑结构,2019,49(增1):875-877.
LI Xiuchun, DENG Ya, ZHANG Chunliang, et al. Technology research on the method of ultrasonic-rebound synthesis method for testing concrete structure strength[J]. Building Structure, 2019, 49(S1): 875-877.
[27]吴 楠,韩爱民,孙春霞,等.超声回弹法平测声速修正系数计算及可靠性检验[J].中外公路,2008,28(5): 243-246.
WU Nan, HAN Aimin, SUN Chunxia, et al. Calculation and reliability test of correction coefficient for flat measurement of sound velocity by ultrasonic rebound method[J]. Journal of China & Foreign Highway, 2008, 28(5): 243-246.
[28]薛建凯.一种新型的群智能优化技术的研究与应用:麻雀搜索算法[D].上海:东华大学,2020.
XUE Jiankai. Research and application of a new swarm intelligence optimization technology: sparrow search algorithm[D]. Shanghai: Donghua University, 2020.
[29]王双双.基于GABP神经网络的智能变电站成熟度模型构建及评价研究[D].郑州:郑州大学,2020.
WANG Shuangshuang. Maturity model establishment and evaluation of smart substation based on GABP neural network[D]. Zhengzhou: Zhengzhou University, 2020.
[30]赵建华,凌良建,吕 嘉,等.表面硬度法检测灌浆料实体强度试验研究[J].混凝土与水泥制品,2022(8):78-82.
ZHAO Jianhua, LING Liangjian, LYU Jia, et al. Experimental study on testing solid strength of grouting materials by surface hardness method[J]. China Concrete and Cement Products, 2022(8): 78-82.
[31]吴玉龙,顾 盛,赵建华,等.基于孔道条件的表面硬度法检测灌浆料抗压强度试验研究[J].混凝土,2022(3):186-192.
WU Yulong, GU Sheng, ZHAO Jianhua, et al. Experimental study on testing compressive strength of grouting material by surface hardness method based on pore condition[J]. Concrete, 2022(3): 186-192.

Memo

Memo:
-
Last Update: 2025-06-01