DocumentCode
2074815
Title
Prediction method for the deformation of deep foundation pit based on neural network algorithm optimized by particle swarm
Author
Tan, Guojin ; Liu, Hanbing ; Cheng, Yongchun ; Liu, Bin ; Zhang, Yin
Author_Institution
Coll. of Transp., Jilin Univ., Changchun, China
fYear
2011
fDate
16-18 Dec. 2011
Firstpage
1407
Lastpage
1410
Abstract
Prediction of the deformation is an important means of the construction parameter adjustment and the construction safety of deep foundation pit. Combining particle swarm optimization with neural network algorithm, The prediction method for the deformation of deep foundation pit based on neural network algorithm optimized by particle swarm is established. In order to improve the prediction accuracy and prediction efficiency of the neural network algorithm, The initial weights and the initial threshold value of neural network model are optimized by using particle swarm optimization. In the neural network model, the deformation of foundation pit is predicted by the optimized initial weights and the optimized initial threshold value. Relying on the practical engineering, the effectiveness and practicality of the method proposed in this paper are verified.
Keywords
deformation; foundations; neural nets; particle swarm optimisation; structural engineering computing; construction parameter adjustment; construction safety; deep foundation pit; deformation prediction method; initial threshold value; initial weight; neural network algorithm; particle swarm optimization; prediction accuracy; prediction efficiency; Deformable models; Monitoring; Optimization; Particle swarm optimization; Prediction algorithms; Predictive models; Training; deformation prediction; foundation pit; neural network; particle swarm optimization;
fLanguage
English
Publisher
ieee
Conference_Titel
Transportation, Mechanical, and Electrical Engineering (TMEE), 2011 International Conference on
Conference_Location
Changchun
Print_ISBN
978-1-4577-1700-0
Type
conf
DOI
10.1109/TMEE.2011.6199470
Filename
6199470
Link To Document