Intelligent Prediction of Stability Bearing Capacity of New-Type Modular Assembled Latticed Shells with Flange Connections
-
摘要: 模块化装配式网壳结构具有施工效率高、节点质量好等优点,其具有广泛的应用前景。基于机器学习方法,建立了新型法兰节点模块化装配式网壳结构的稳定承载力智能化预测模型。首先,针对影响稳定极限承载力的一系列参数,分析了864个模块化装配式网壳的有限元模型,从而生成机器学习算法所需的数据库。其次,基于开源平台Scikit-learn建立了6种机器学习算法模型,使用生成的数据库对所有算法模型进行训练和测试,并且对深度神经网络模型(ANN)、XGBoost和梯度增强算法模型进行了过拟合检验,对ANN模型进行了鲁棒性和可靠性检验。结果表明,在测试集中ANN、XGBoost和梯度增强算法模型预测极限承载力的决定系数(R2)均大于0.95,预测稳定承载力的精度很高。采用ANN模型预测稳定承载力的鲁棒性和精度均最好,平均绝对百分比误差(MAPE)为7.1%,R2为0.982,具有很高的预测准确性和泛化能力,能够很好地捕捉稳定承载力和输入参数之间的复杂映射关系。Abstract: Modular assembled reticulated shell structures have the advantages of high construction efficiency and good join quality, and have a wide application prospect. Based on machine learning method, an intelligent prediction model for the bearing capacity of modular prefabricated reticulated shell structures was established. Firstly, 864 finite element models of modular assembled reticulated shells were analyzed for a series of parameters that affect the stable ultimate bearing capacity, thus generating the database required for the machine learning algorithm. Secondly, six machine learning algorithm models were established based on the open source platform Scikit-learn, and all algorithm models were trained and tested by using the generated database. In addition, the artificial neural network model (ANN), XGBoost and gradient enhancement algorithm models were overfitted, and the reliability of ANN model was tested. The results showed that the determination coefficients (R2) of ANN, XGBoost and gradient enhancement algorithm models in the test set were all greater than 0.95, and the prediction accuracy of bearing capacity was very high. The ANN model had the best robustness and accuracy in predicting the stable ultimate bearing capacity, with an average absolute percentage error (MAPE) of 7.1% and an R2 of 0.982. It showed high prediction accuracy and generalization capacity, and could well capture the complex mapping relations between the ultimate bearing capacity and input parameters.
-
[1] 张爱林,刘廷勇,张艳霞,等. 基于智能建造的快速全装配大跨度预应力空间钢结构体系创新研究展望[J]. 北京工业大学学报, 2020, 46(6): 591-603. [2] 张爱林. 工业化装配式高层钢结构体系创新、标准规范编制及产业化关键问题[J]. 工业建筑, 2014, 44(8): 1-6. [3] 范峰,马会环,马越洋. 半刚性节点网壳结构研究进展及关键问题[J]. 工程力学, 2019, 36(7): 1-7. [4] 施刚,罗翠,王元清,等. 铝合金网壳结构中新型铸铝节点承载力设计方法研究[J]. 空间结构, 2012, 18(1): 78-84. [5] 董石麟,郑晓清. 节点刚、铰接时环向折线形单层球面网壳静力和稳定性能的分析研究[J]. 建筑钢结构进展, 2013, 15(6): 1-11. [6] 张爱林,孙超,姜子钦.联方型双撑杆索穹顶考虑自重的预应力计算方法[J].工程力学,2017,34(3):211-218. [7] MEEK J L, TAN T H. Geometrically nonlinear analysis of space frames by an incremental iterative technique[J]. Computer Methods in Applied Mechanics and Engineering, 1984, 47(3): 261-282. [8] 陈昕,沈世钊. 网壳结构的几何非线性分析[J]. 土木工程学报, 1990(3): 1-7. [9] 王元清,柳晓晨,石永久,等. 铝合金网壳结构盘式节点受力性能有限元分析[J]. 天津大学学报(自然科学与工程技术版), 2015, 48(增刊1): 1-8. [10] SALEHI H, BURGUENO R. Emerging artificial intelligence methods in structural engineering[J]. Engineering Structures, 2018, 171: 170-189. [11] 徐阳,金晓威,李惠. 土木工程智能科学与技术研究现状及展望[J]. 建筑结构学报, 2022, 43(9): 23-35. [12] 苏宁,孙瑛,杨林,等. 基于广义回归神经网络的大跨度球面屋盖风荷载预测及其应用[J]. 建筑结构学报, 2016, 37(6): 101-106. [13] VITALIY V D. Neural networks for predicting shear strength of CFS channels with slotted webs[J]. Journal of Constructional Steel Research, 2021, 177: 1-18. [14] ZHU S, OHSAKI M, GUO X. Prediction of non-linear buckling load of imperfect reticulated shell using modified consistent imperfection and machine learning[J]. Engineering Structures, 2021, 226:1-8. [15] 兰涛,丁敏,底绍涵,等. 基于TensorFlow的单层球面网壳结构极限承载力预测[J]. 工业建筑, 2022, 52(4): 70-73. [16] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521: 436-444. [17] 张爱林,张雪峰,姜子钦,等. 外加盖板的T形板装配式网壳节点抗弯性能研究[J]. 工业建筑, 2024, 54(1): 68-75. [18] 中华人民共和国住房和城乡建设部.空间网格结构技术规程:JGJ 7—2010 [S].北京:中国建筑工业出版社,2010. [19] 蔡健,贺盛,姜正荣,等. 单层网壳结构稳定性分析方法研究[J]. 工程力学, 2015, 32(7): 103-110. [20] 支旭东,李文亮,范峰,等. 初始缺陷模式对单层球面网壳静力稳定性的影响[J]. 空间结构, 2021, 27(1): 9-15.
点击查看大图
计量
- 文章访问数: 31
- HTML全文浏览量: 4
- PDF下载量: 2
- 被引次数: 0