基于机器学习的模块间节点受剪性能多目标优化
邓恩峰 , 李羽辰 , 高焌栋 , 张哲 , 廉俊逸 , 李伟
建筑钢结构进展 ›› 2026, Vol. 28 ›› Issue (03) : 114 -123.
基于机器学习的模块间节点受剪性能多目标优化
Multi-Objective Optimization of Shear Performance of Inter-Module Joints Based on Machine Learning
模块化钢结构建筑凭借工业化程度高、施工效率快等优势,已成为推动绿色低碳建筑发展的重要方向。模块间连接对模块化建筑的力学性能具有关键影响,然而当前针对模块间连接受剪性能及优化设计方法的研究仍较为缺陷。文中基于课题组前期完成的全装配可吊装节点(fully prefabricated liftable connection, FPLC)受剪性能试验研究,建立了精细化有限元模型并开展了参数分析,从而得到了包含1 000组不同参数的FPLC受剪性能数据库。运用了六种常用机器学习算法对FPLC受剪性能进行评估,结果表明:基于遗传算法优化的神经网络(GANN)对FPLC承载力的预测精度较高,支持向量机(SVR)对于FPLC位移的预测效果更优。将这两种高预测精度的算法进行堆栈并构建代理模型,结合非支配遗传算法(NSGA-Ⅱ)提出了FPLC受剪性能多目标优化方法,并给出了优化后的节点构造形式。通过建立四层模块化钢结构有限元模型,在竖向荷载和风荷载作用下开展静力分析,对比四层模块化钢结构优化前后的受剪性能指标及层间位移响应,验证了该方法的工程适用性。
Modular steel structure buildings have become an important development trend for green and low-carbon construction due to their advantages of a high degree of industrialization and high construction efficiency. The Inter-module connections have significant effects on the mechanical performance of modular buildings. However, the shear performance of the inter-module connections has not been fully investigated in existing studies. Based on the previous experimental study on fully prefabricated liftable connection (FPLC) of modular steel structures, this paper established a refined finite element model and conducted parametric analysis to obtain a shear performance database of FPLC with 1000 different parameters. Six mainstream machine learning algorithms were utilized to predict the shear performance of the FPLC. The results indicated that the neural network optimized by genetic algorithm (GANN) provides better prediction accuracy for the shear load bearing capacity, and the support vector machine stacking algorithm (SVR) shows higher prediction accuracy for the ultimate displacement. By stacking the two algorithms with higher prediction accuracy as a proxy model and linking this model with the non-dominated sorting genetic algorithm II (NSGA-Ⅱ), a multi-objective optimization method for the shear performance of the FPLC was established, and the optimized joint configuration was proposed. The finite element model of a four-story modular steel structure was established, and the static analysis was carried out under vertical load and wind load. The shear performance and inter-story drift rations of the four-story modular steel structure before and after optimization were compared to verify the reliability of the optimization method.
| [1] |
SRISANGEERTHANAN S,HASHEMI M J,RAJEEV P,et al.Review of performance requirements for inter-module connections in multi-story modular buildings[J].Journal of Building Engineering,2020,28:101087.DOI:10.1016/j.jobe.2019.101087. |
| [2] |
岳清瑞,吴朝昀,刘晓刚,多高层模块化结构及建造技术研究进展与未来趋势[J].建筑结构学报,2024,45(8):1-19.DOI:10.14006/j.jzjgxb.2023.0619. |
| [3] |
YUE Qingrui,WU ZhaoYun,LIU Xiaogang,et al.Progress and future trends in development of multi-story and high-rise modular structures and construction technology[J].Journal of Building Structures,2024,45(8):1-19.DOI:10.14006/j.jzjgxb.2023.0619.(in Chinese) |
| [4] |
郝际平,孙晓岭,薛强,绿色装配式钢结构建筑体系研究与应用[J].工程力学,2017,34(1):1-13..DOI:10.6052/j.issn.1000-4750.2016.08.ST14 |
| [5] |
HAO Jiping,SUN Xiaoling,XUE Qiang,et al.Research and applications of prefabricated steel structure building systems[J].Engineering Mechanics,2017,34(1):1-13.DOI:10.6052/j.issn.1000-4750.2016.08.ST14(in Chinese) |
| [6] |
LIU X L,HOU C,PENG J H,et al.Recent advancements of inter-module connections for modular buildings:An overview and multi-dimensional assessment[J].Engineering Structures,2025,335:120378.DOI:10.1016/j.engstruct.2025.120378. |
| [7] |
LACEY A W,CHEN W S,HAO H,et al.Review of bolted inter-module connections in modular steel buildings[J].Journal of Building Engineering,2019,23:207-219.DOI:10.1016/j.jobe.2019.01.035. |
| [8] |
SHI F W,DING Y,ZONG L,et al.Shear behaviour of vertical inter-module connection with bolts and shear keys for MSCs[J].Structures,2023,47:260-281.DOI:10.1016/j.istruc.2022.11.046. |
| [9] |
CHEN Z H,WANG J,LIU J D,et al.Seismic behavior and moment transfer capacity of an innovative self-locking inter-module connection for modular steel building[J].Engineering Structures,2021,245:112978.DOI:10.1016/j.engstruct. 2021.112978. |
| [10] |
陈红磊,陈琛,李国强.模块化建筑钢结构模块间新型节点及其承载性能[J].建筑钢结构进展,2022,24(4):15-23.DOI:10.13969/j.cnki.cn31-1893.2022.04.003. |
| [11] |
CHEN Honglei,CHEN Chen,LI Guoqiang.Load-bearing capacity of a new joint for connecting modules in modular steel buildings[J].Progress in Steel Building Structures,2022,24(4):15-23.DOI:10.13969/j.cnki.cn31-1893.2022.04.003.(in Chinese) |
| [12] |
JIANG K,LIANG Y T,ZHAO O.Machine-learning-based design of high strength steel bolted connections[J].Thin-Walled Structures,2022,179:109575.DOI:10.1016/j.tws. 2022.109575. |
| [13] |
TU X,HE Z,JIANG B W,et al.Strength reserve-based seismic optimization for precast concrete frames with hybrid semi-rigid connections[J].Structural and Multidisciplinary Optimization,2022,65(4):109.DOI:10.1007/s00158-022-03203-2. |
| [14] |
FANG C,PING Y W,GAO Y Q,et al.Machine learning-aided multi-objective optimization of structures with hybrid braces-Framework and case study[J].Engineering Structures,2022,269:114808.DOI:10.1016/j.engstruct.2022.114808. |
| [15] |
廉俊逸.模块化钢结构全装配可吊装节点受剪性能与设计方法研究[D].郑州:郑州大学,2023. |
| [16] |
LIAN Junyi.Investigation on shear performance and design method of the fully prefabricated liftable connection for modular steel construction[D].Zhengzhou:Zhengzhou University,2023.(in Chinese) |
| [17] |
CHEN Z H,LIU Y,ZHONG X,et al.Rotational stiffness of inter-module connection in mid-rise modular steel buildings[J].Engineering Structures,2019,196:109273.DOI:10.1016/j.engstruct.2019.06.009. |
| [18] |
邓恩峰,廉亚杰,张平萍,模块化钢结构全装配可吊装节点设计[J].绿色建筑,2024,16(6):8-13.DOI:10.3969/j.issn.1004-1672.2024.06.002. |
| [19] |
DENG Enfeng,LIAN Yajie,ZHANG Pingping,et al.Design of fully prefabricated liftable connections for modular steel structures[J].Green Building,2024,16(6):8-13.DOI:10.3969/j.issn.1004-1672.2024.06.002.(in Chinese) |
| [20] |
DENG E F,LIAN J Y,ZHANG Z,et al.Axial mechanical behavior of an innovative liftable connection for modular steel construction[J].Thin-Walled Structures,2023,182:110256.DOI:10.1016/j.tws.2022.110256. |
| [21] |
赵均海,华林炜,王昱.基于粒子群优化BP神经网络的中空夹层钢管混凝土柱轴压承载力研究[J].建筑钢结构进展,2024,26(9):45-52.DOI:10.13969/j.cnki.cn31-1893.2024.09.005. |
| [22] |
ZHAO Junhai,HUA Linwei,WANG Yu.Study on axial compressive load bearing capacity of concrete-filled double-skin steel tubular columns based on particle swarm optimization BP neural network[J].Progress in Steel Building Structures,2024,26(9):45-52.DOI:10.13969/j.cnki.cn31-1893.2024.09.005.(in Chinese) |
| [23] |
MURPHY K,SCHÖLKOPF B,SRIVASTAVA N,et al.Dropout:A simple way to prevent neural networks from overfitting[J].Journal of Machine Learning Research,2014,15(1):1929-1958.DOI:10.5555/2627435.2670313. |
| [24] |
BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32.DOI:10.1023/A:1010933404324. |
| [25] |
CORTES C,VAPNIK V.Support-vector networks[J].Machine Learning,1995,20(3):273-297.DOI:10.1007/BF00994018. |
| [26] |
周俊文,刘界鹏.基于多种群遗传算法的钢框架结构优化设计[J].土木与环境工程学报(中英文),2024,46(1):71-81.DOI:10.11835/j.issn.2096-6717.2022.071. |
| [27] |
ZHOU Junwen,LIU Jiepeng.Optimization design of steel frame structure based on multi-population genetic algorithm[J].Journal of Civil and Environmental Engineering,2024,46(1):71-81.DOI:10.11835/j.issn.2096-6717.2022.071.(in Chinese) |
| [28] |
GB 55001—2021 工程结构通用规范[S]. |
| [29] |
GB 55001—2021 General code for engineering structures[S]. (in Chinese) |
| [30] |
GB 50009—2012 建筑结构荷载规范[S]. |
| [31] |
GB 50009—2012 Load code for the design of building structures[S].(in Chinese) |
| [32] |
T/CECS 507—2018 钢结构模块建筑技术规程[S]. |
| [33] |
T/CECS 507—2018 Technical specification for steel modular buildings[S].(in Chinese) |
国家自然科学基金(52378206)
河南省自然科学基金(242300421177)
河南省科技研发计划联合基金(235200810013)
河南省高校科技创新人才支持计划项目(25HASTIT017)
河南省科技攻关计划项目(252102321146)
/
| 〈 |
|
〉 |