Open AccessParametric modeling program of single-layer spherical reticulated shell structure and prediction program of global stability ultimate bearing capacity
Author(s) -
Huachun Qi,
X R Wang,
Zhoushen Huang,
Xianhe Dai,
Jing Zhuang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1777/1/012034
Subject(s) - shell (structure) , artificial neural network , parametric statistics , parameterized complexity , spherical shell , parametric model , bearing (navigation) , layer (electronics) , nonlinear system , process (computing) , computer science , structural engineering , bearing capacity , stability (learning theory) , algorithm , engineering , mechanical engineering , materials science , artificial intelligence , machine learning , mathematics , composite material , physics , statistics , quantum mechanics , operating system
In this paper, the “battery” program was compiled based on the parametric tool Rhino+Grasshopper and the parameterized modeling function of K-type single-layer spherical reticulated shell structure was realized. At the same time, based on BP neural network algorithm and considering the complex mapping relationship in nonlinear analysis, a neural network model and program was established to predict the ultimate bearing capacity of K8 single-layer spherical reticulated shell structure. The results show that the program can realize the modeling process efficiently and the reliability of the neural network to predict the ultimate bearing capacity of single-layer reticulated shells is verified, which provides an effective tool for improving the parametric modeling and structural optimization of single-layer reticulated shell structure.