|本期目录/Table of Contents|

[1]刘文博,杨喜娟,王力,等.基于SSA-RBFNN的钢管混凝土界面粘结强度研究*[J].中国安全生产科学技术,2025,21(3):148-155.[doi:10.11731/j.issn.1673-193x.2025.03.019]
　LIU Wenbo,YANG Xijuan,WANG Li,et al.Study on interfacial bond strength of concrete-filled steel tube based on SSA-RBFNN[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2025,21(3):148-155.[doi:10.11731/j.issn.1673-193x.2025.03.019]
点击复制

基于SSA-RBFNN的钢管混凝土界面粘结强度研究*
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
21
期数:
2025年3期
页码:
148-155
栏目:
职业安全卫生管理与技术
出版日期:
2025-03-31

文章信息/Info

Title:
Study on interfacial bond strength of concrete-filled steel tube based on SSA-RBFNN
文章编号:
1673-193X(2025)-03-0148-08
作者:
刘文博; 杨喜娟; 王力; 李子奇
（1.兰州交通大学 土木工程学院，甘肃 兰州 730070；
2.白银矿冶职业技术学院 建筑工程学院，甘肃 白银 730900）
Author(s):
LIU Wenbo;  YANG Xijuan;  WANG Li;  LI Ziqi
(1.School of Civil Engineering,Lanzhou Jiaotong University,Lanzhou Gansu 730070,China;
2.School of Architectural Engineering,Baiyin Vocational College of Mining and Metallurgy,Baiyin Gansu 730900,China)
关键词:
RBF神经网络; 麻雀搜索算法; 钢管混凝土; 界面粘结强度; 机器学习模型
Keywords:
RBF neural network;  sparrow search algorithm;  concrete-filled steel tube;  interfacial bond strength;  machine learning model
分类号:
X947
DOI:
10.11731/j.issn.1673-193x.2025.03.019
文献标志码:
A
摘要:
为了改善传统径向基神经网络（RBFNN）存在对样本数据依赖性强、参数选择复杂、收敛速度慢等缺陷。将麻雀搜索算法（SSA）应用于RBFNN预测模型，提出基于SSA-RBFNN的CFST界面粘结强度预测模型，收集319组数据建立数据库，选取8种影响因素作为输入层参数和界面粘结强度作为输出层参数，分别建立RBFNN和SSA-RBFNN模型。通过平均绝对百分比误差（MAPE）和决定系数（R2）等指标，将2种机器学习模型与6种现有公式进行比较，评估它们在预测精度和稳定性方面的表现。研究结果表明：2种机器学习模型比公式精度更高。其中，SSA-RBFNN模型有更好的预测性能，更有助于高效预测CFST的界面粘结强度。研究结果可为CFST结构工程设计提供相应的预测方法和技术支持，可以帮助工程师在设计和施工过程中更好地评估结构的承载能力和安全性。
Abstract:
To address the shortcomings of traditional radial basis function neural networks (RBFNN),such as strong dependence on sample data,complex parameter selection,and slow convergence speed,the sparrow search algorithm (SSA) was applied to RBFNN prediction model,and a prediction model for the interfacial bond strength of concrete-filled steel tube (CFST) based on SSA-RBFNN was proposed.A database consisting of 319 sets of data was established,then eight types of influencing factors were selected as the input layer parameters,and the interfacial bond strength was selected as the output layer parameter.Both the RBFNN and SSA-RBFNN models were developed accordingly.By using metrics such as mean absolute percentage error (MAPE) and coefficient of determination (R2),two machine learning models are compared with six existing formulas to evaluate their performance in terms of prediction accuracy and stability.The results show that both the machine learning models outperform the formulas in terms of accuracy.The SSA-RBFNN model has the better prediction performance,and it is more helpful to predict the interfacial bond strength of CFST efficiently.The research results can provide corresponding prediction methods and technical support for CFST structural engineering design,and can help engineers better evaluate the bearing capacity and safety of the structure during design and construction.

参考文献/References:

［1］韩林海.钢管混凝土结构:理论与实践［M］.北京:科学出版社,2016.
［2］HAN L H,LI W,BJORHOVDE R.Developments and advanced applications of concrete-filled steel tubular (CFST) structures:Members［J］.Journal of Constructional Steel Research,2014(100):211-228.
［3］潘启仁,陈云峰,韩云,等.考虑环境温度的钢管混凝土轴压承载力试验与计算方法研究［J］.中国安全生产科学技术,2024,20(12):97-104. PAN Qiren,CHEN Yunfeng,HAN Yun,et al.Experimental study and calculation method for axial compression capacity of concrete-filled steel tubes considering ambient temperature［J］.Journal of Safety Science and Technology,2024,20(12): 97-104.
［4］薛立红,蔡绍怀.钢管混凝土柱组合界面的粘结强度（上）［J］.建筑科学,1996(3):22-28. XUE Lihong,CAI Shaohuai.Bond strength at interface of concrete-filled steel tube columns (a)［J］.Building Science,1996(3):22-28.
［5］薛立红,蔡绍怀.钢管混凝土柱组合界面的粘结强度（下）［J］.建筑科学,1996(4):19-23. XUE Lihong,CAI Shaohuai.Bond strength at interface of concrete-filled steel tube columns (b) ［J］.Building Science,1996(4):19-23.
［6］ROEDER C W,CAMERON B,BROWN C B.Composite action in concrete filled tubes［J］.Journal of Structural Engineering,1999,125(5):477-484.
［7］LYU W,HAN L.Investigation on bond strength between recycled aggregate concrete (RAC) and steel tube in RAC-filled steel tubes［J］.Journal of Constructional Steel Research,2019(155):438-459.
［8］YAN J,XIE W,ZHANG L,et al.Bond behaviour of concrete-filled steel tubes at the Arctic low temperatures［J］.Construction and Building Materials,2019,210118-131.
［9］康希良.钢管混凝土组合力学性能及粘结滑移性能研究［D］.西安:西安建筑科技大学,2008.
［10］刘玉茜.钢管混凝土粘结滑移性能的理论分析及ANSYS程序验证［D］.西安:西安建筑科技大学,2006.
［11］胡波,王建国.钢管与混凝土粘结-滑移相互作用的数值模拟［J］.中国公路学报,2009,22(4):84-91. HU Bo,WANG Jianguo.Numerical simulation of bond-slip interaction between steel tubeand concrete［J］.China Journal of Highway and Transport,2009,22(4):84-91.
［12］Architectural Institute of Japan.Recommendations for design and construction of concrete-filled steel tubular structures ［S］.Tokyo:Architectural Institute of Japan,2008.
［13］福建省住房和城乡建设厅.钢管混凝土结构技术规程:DBJ/T 13-51-2020 ［S］.福州:福建省住房和城乡建设厅,2020.
［14］Design of composite steel and concrete structures-part1-1:general rules and rules for buildings:EUROCODE 4 (EC4) ［S］.CEN:Brussels,Commission of European Communities,2004.
［15］Steel concrete and composite bridges-part 5:code of practice for the design of composite bridges:BS 5400-5［S］.Britain:British Standard Institute，2005.
［16］Bridge Design Part 6:Steel and composite construction:AS 5100.6-2004［S］.Sydney:Standards Australia,2004.
［17］Specification for Structural Steel Buildings:ANSI/AISC 360-16［S］.Chicago:American Institute of Steel Construction,2016.
［18］TRAN V,THAI D,NGUYEN D.Practical artificial neural network tool for predicting the axial compression capacity of circular concrete-filled steel tube columns with ultra-high-strength concrete［J］.Thin-Walled Structures,2020,151.
［19］HOU C,ZHOU XG.Strength prediction of circular CFST columns through advanced machine learning methods［J］.Journal of Building Engineering,2022,51.
［20］WANG L,YANG X J,LI Z Q,et al.Investigation of interfacial bond strength of circular CFST columns based on ordinary and inorganic polymers through advanced machine learning methods ［J］.Structures,2024,69107252.
［21］刘金琨.RBF神经网络自适应控制MATLAB仿真［M］.北京:清华大学出版社,2014.
［22］中华人民共和国住房和城乡建设部.混凝土结构设计规范(2024版)：GB/T 50010—2010［S］.北京：中国建筑工业出版社，2015.
［23］中华人民共和国住房和城乡建设部.混凝土物理力学性能试验方法标准:GB/T 50081—2019 ［S］.北京:中国建筑工业出版社,2019.
［24］XUE J,SHEN B.A novel swarm intelligence optimization approach:sparrow searchalgorithm ［J］.Systems Science & Control Engineering,2020,8(1):22-34.
［25］尚尚,杨童,王召斌,等.1种基于改进麻雀搜索算法的RBF神经网络优化算法:CN202011287057.6［P］.2021-02-05.
［26］武斌,谭卓英,王先伟,等.钢管混凝土极限粘结强度统一计算方法［J］.沈阳工业大学学报,2022,44(6):714-720. WU Bin,TAN Zhuoying,WANG Xianwei,et al.Unified calculation method for ultimate bondstrength of steel pipe concrete ［J］.Journal of Shenyang University of Technology,2022,44(6):714-720.

相似文献/References:

[1]冯莉,樊燕燕,王力,等.基于F-R-M法的刚构-连续梁桥施工期结构强度风险分析[J].中国安全生产科学技术,2019,15(9):135.[doi:10.11731/j.issn.1673-193x.2019.09.022]
　FENG Li,FAN Yanyan,WANG Li,et al.Risk analysis on structural strength of rigid framecontinuous beam bridge during construction based on F-R-M method[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2019,15(3):135.[doi:10.11731/j.issn.1673-193x.2019.09.022]
[2]丁莹莹,尹尚先,连会青,等.基于CEEMDAN和改进的混合时间序列模型工作面涌水量预测研究*[J].中国安全生产科学技术,2024,20(3):110.[doi:10.11731/j.issn.1673-193x.2024.03.016]
　DING Yingying,YIN Shangxian,LIAN Huiqing,et al.Research on water inflow prediction of working face based on CEEMDAN and improved hybrid time series model[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2024,20(3):110.[doi:10.11731/j.issn.1673-193x.2024.03.016]
[3]郭凤香,马传戬,蔡晶,等.不同冲突情境下老年驾驶人焦虑水平预测分析*[J].中国安全生产科学技术,2024,20(9):219.[doi:10.11731/j.issn.1673-193x.2024.09.027]
　GUO Fengxiang,MA Chuanjian,CAI Jing,et al.Predictive analysis on anxiety level of elderly drivers in different conflict situations[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2024,20(3):219.[doi:10.11731/j.issn.1673-193x.2024.09.027]

备注/Memo

备注/Memo:
收稿日期： 2024-10-14
* 基金项目： 甘肃省自然科学基金青年项目（25JRRA207）；兰州铁路局集团公司科技研究开发计划项目（LZJKY2024041-1）；山西交通控股集团科技创新项目（23-JKKJ-6）
作者简介： 刘文博，本科，讲师，主要研究方向为土木工程建造。
通信作者： 李子奇，博士，副教授，主要研究方向为组合结构桥梁理论。
更新日期/Last Update: 2025-03-28