Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
409935 | Neurocomputing | 2014 | 8 Pages |
Abstract
In this paper, we propose a LSSVR-based time series method (LTSM) to predict dynamic lateral deformation of retaining structure and ground surface settlement in deep foundation pit engineering. After reconstructing phase space, time-varying lateral displacement of each observation point on retaining structure can be predicted using its historic unary time series data. And then, the ground settlement nearby the deep foundation pit can be predicted using all the observed values of lateral deformation which were collected at the same time from different depths on the retaining structure. The experimental results show that LTSM achieved a high accuracy when predicting the lateral deformation and ground settlement.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Zhiwei Ji, Bing Wang, SuPing Deng, Zhuhong You,