Open AccessA prediction model of ground vibration considering the local amplification of vibration
Author(s) -
Hong Zhao,
Ming Zhou,
Fang Yang,
Wenxiu Dong
Publication year - 2020
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.179
H-Index - 26
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/580/1/012031
Subject(s) - vibration , attenuation , artificial neural network , convergence (economics) , computer science , ground vibrations , acoustics , physics , artificial intelligence , optics , economics , economic growth
The ground environmental vibration caused by traffic load will attenuate monotonously with the increase of the distance from the load source. However, considering the complexity of stratum factors, the attenuation of ground vibration will have local amplification of ground vibration instead of monotonous attenuation. This article is based on RBF neural network. The method can predict the ground environment vibration of the local amplification phenomenon of the ground vibration. This paper selects the theoretical solution of the complex theoretical model to perform the fitting approximation and the numerical approximation with the measured discrete data. The results show that the numerical approximation is better. Since the RBF neural network does not require other neural network models to perform supervised learning training, the numerical convergence speed is also relatively fast.