基于TensorFlow的单层球面网壳结构极限承载力预测

兰涛; 丁敏; 底绍涵; 郑飞鸿; 庄金钊

doi:10.13204/j.gyjzG20060112

基于TensorFlow的单层球面网壳结构极限承载力预测

doi: 10.13204/j.gyjzG20060112

1. 中国船舶重工集团国际工程有限公司, 北京 100121;
2. 中国农业大学水利与土木工程学院, 北京 100083

详细信息

作者简介:
兰涛,男,1976年出生,研究员。电子信箱:qd_lantao@163.com

计量
- 文章访问数: 76
- HTML全文浏览量: 10
- PDF下载量: 0
- 被引次数: 0
出版历程
- 收稿日期: 2020-06-01
- 网络出版日期: 2022-07-25

Prediction of Ultimate Bearing Capacity of Single-Layer Spherical Reticulated Shell Based on TensorFlow

1. China Shipbuilding Industry Corporation International Engineering Co., Ltd., Beijing 100121, China;
2. College of Water Resources and Civil Engineering, China Agricultural University, Beijing 100083, China

摘要

摘要: 为研究单层球面网壳结构极限承载力问题,基于TensorFlow下的BP神经网络算法,考虑非线性分析中的复杂映射关系,建立神经网络模型,对K8型单层球面网壳结构的极限承载力进行预测。在此基础上,考虑结构网格形式的不同,建立新的神经网络模型,预测Kn型单层球面网壳结构的极限承载力;将预测结果与有限元和文献回归公式的计算结果进行对比分析。研究结果表明:预测的K8型单层球面网壳结构的极限承载力与有限元结果误差均值为1.666%,文献回归公式计算的结果与有限元的计算结果误差均值为3.994%;预测的Kn型单层球面网壳结构的极限承载力与有限元结果误差均值为4.774%,文献回归公式计算的结果与有限元的计算结果误差均值为5.163%。可见利用神经网络对单层网壳结构极限承载力进行预测是可行的。
- 单层球面网壳结构 /
- 极限承载力 /
- 神经网络 /
- 预测
Abstract: In order to study the ultimate bearing capacity of the single-layer spherical reticulated shell structure, based on the BP neural network algorithm of TensorFlow, a neural network model was established to predict the ultimate bearing capacity of the K8 single-layer spherical reticulated shell structure by considering the complex mapping relationship in the nonlinear analysis. Moreover, another new neural network model was established to predict the ultimate bearing capacity of the Kn-type single-layer spherical reticulated shell structure. The prediction results were compared with the calculation results of the finite element and literature regression formulas. The results showed that the error mean between the predicted ultimate bearing capacity of the K8 single-layer spherical reticulated shell structure and the finite element calculation results was 1.666%, and that between the formula calculation results and the finite element calculation results was 3.994%; the error mean between the predicted ultimate bearing capacity of the Kn-type single-layer spherical reticulated shell structure and the finite element calculation was 4.774%, and that between the formula calculation results and the finite element calculation results was 5.163%. The feasibility of using neural network to predict the ultimate bearing capacity of single-layer reticulated shell structure is demonstrated.
- single-layer spherical reticulated shell structure /
- ultimate bearing capacity /
- neural network /
- prediction

HTML全文

参考文献(10)

[1]	KAMARTHI S V,SANVIDO V E,KUMARA S R T.Neuroform-neural network system for vertical formwork selection[J]].Journal of Computing in Civil Engineering,1992,6(2):178-199.
[2]	HAJELA P,BERKE L.Neurobiological computational models in structural analysis and design[J].Computers& Structures,1991,41(4):657-667.
[3]	吴剑国,俞铭华,徐昌文.散货船中剖面结构的模糊神经网络评估系统[J].中国造船,1997(1):73-79.
[4]	沈世钊,陈昕.网壳结构稳定性[M].北京:科学技术出版社,1999.
[5]	吴剑国,李红明,张其林.网壳稳定性拟合的神经网络方法[J].钢结构,2001,16(6):19-21.
[6]	贺拥军,张丰盛.基于神经网络的网壳结构强震失效模式分类判别[J].铁道科学与工程学报,2018,15(2):458-465. DOI: 10.19713/j.cnki.43-1423/u.2018.02.025.
[7]	颜卫亨,黄政,吴东红,等.折叠网壳结构风压分布特性的神经网络预测研究[J].应用力学学报,2015,32(5):845-851 ,901.
[8]	徐菁,郭稳,王秀丽,等.基于AR模型与BP神经网络的网壳结构损伤识别方法研究[J].空间结构,2015,21(2):66-71. DOI: 10.13849/j.issn.1006-6578.2015.02.066.
[9]	崔胜红,徐菁.基于时间序列与神经网络的空间网壳结构损伤检测方法[J].青岛理工大学学报,2013,34(4):27-33.
[10]	陈世英,郭玉霞,鹿晓阳.单层球面网壳结构选型优化设计[J].建筑钢结构进展,2010,12(4):46-50.