Study on the calculation of surface subsidence coefficient based on principal component analysis and neural networks

DOI

10.2991/eesed-16.2017.6How to use a DOI?

Keywords

subsidence coefficient; principal component analysis; artificial neural networks

Abstract

In order to study the effect of geological factors on the surface subsidence coefficient. Based on the analysis of all influential geological factors of subsidence coefficient and the typical mobile surface observation station data of China, the influence of each factor and the influence difference were analyzed comprehensively by means of principal component analysis. Then the first and second principal component values, as inputting parameters, were used to build up a calculation model of subsidence coefficient on the basis of a principal component and artificial neural networks. And the calculation results and measured values were also compared. The results show that calculation model, which is based on principal component analysis and artificial neural networks, takes every factors into account comprehensively and produces reliable results which are much closer the reality. This new calculation model provides a new attempt to the calculation of surface subsidence coefficient.

Copyright

© 2017, 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  - Ming-Hua Wu
AU  - Xiao-Gang Xia
PY  - 2016/08
DA  - 2016/08
TI  - Study on the calculation of surface subsidence coefficient based on principal component analysis and neural networks
BT  - 2nd Annual International Conference on Energy, Environmental & Sustainable Ecosystem Development (EESED 2016)
PB  - Atlantis Press
SP  - 36
EP  - 41
SN  - 2352-5401
UR  - https://doi.org/10.2991/eesed-16.2017.6
DO  - 10.2991/eesed-16.2017.6
ID  - Wu2016/08
ER  -