Open AccessPrediction of Horizontal Displacement of Foundation Pit Based on NAR Dynamic Neural Network
Author(s) -
Zongjun Sun,
Kai Li,
Zhongyi Li
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/782/4/042032
Subject(s) - displacement (psychology) , artificial neural network , foundation (evidence) , series (stratigraphy) , computer science , engineering , artificial intelligence , geology , geography , psychology , paleontology , archaeology , psychotherapist
Absrtact. NAR dynamic neural network has the function of feedback and memory, which can be effectively used in time series data modeling. Taking the actual horizontal displacement of a foundation pit in Qingdao as the experimental data, the time series prediction model of the horizontal displacement of the foundation pit is established by NAR dynamic neural network. The model is applied to predict the horizontal displacement of foundation pit, and compared with grey prediction, support vector machine and BP neural network. The results show that the prediction accuracy of NAR dynamic neural network model is high. It has strong stability and can be effectively applied to the prediction of foundation pit displacement.