Parking Maps Based on Momentum BP Neural Network Modeling and Prediction of 3S

DOI

10.2991/iccet-15.2015.333How to use a DOI?

Keywords

Complex structures, Neural Networks, Full model, Mapping model, Parking garage

Abstract

In order to quickly and accurately determine the location and extent of the instability of complex steel structures, the method has been proposed which is to build a full model based ANSYS finite element analysis software and mapping model based add momentum BP neural network to achieve predictive. The structure is modeled by finite element analysis software, and through which could get the full model structure. The von-mises stress and structure of different layers of maximum deformation has been regarded as the training samples. The nonlinear relations could be got by neural network. Ultimately generalization mapping model could be got. The examples show that the data obtained by artificial neural network to predict with high accuracy, compared with the full-model, the error is only 5.28% maximum, the average error is 3%, which proved the feasibility of the method and laid the foundation for the subsequent optimization.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Gening Xu
AU  - Jiarong Chen
AU  - Bin Zuo
AU  - Kun An
AU  - Yaoyao Wang
PY  - 2015/11
DA  - 2015/11
TI  - Parking Maps Based on Momentum BP Neural Network Modeling and Prediction of 3S
BT  - Proceedings of the 5th International Conference on Civil Engineering and Transportation 2015
PB  - Atlantis Press
SP  - 1792
EP  - 1796
SN  - 2352-5401
UR  - https://doi.org/10.2991/iccet-15.2015.333
DO  - 10.2991/iccet-15.2015.333
ID  - Xu2015/11
ER  -