Prediction of building damage induced by tunnelling through an optimized artificial neural network
Ground surface movement due to tunnelling in urban areas imposes strains to the adjacent buildings through distortion and rotation, and may consequently cause structural damage. The methods of building damage estimation are generally based on a two-stage procedure in which ground movement in the gre...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Published: |
Springer London
2019
|
| Online Access: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85047161551&doi=10.1007%2fs00366-018-0615-5&partnerID=40&md5=4e9c58609aa02661f6811a269626fd58 http://eprints.utp.edu.my/21567/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Teknologi Petronas |
| Summary: | Ground surface movement due to tunnelling in urban areas imposes strains to the adjacent buildings through distortion and rotation, and may consequently cause structural damage. The methods of building damage estimation are generally based on a two-stage procedure in which ground movement in the greenfield condition is estimated empirically, and then, a separate method based on structural mechanic principles is used to assess the damage. This paper predicts the building damage based on a model obtained from artificial neural network and a particle swarm optimization algorithm. To develop the model, the input and output parameters were collected from Line No. 2 of the Karaj Urban Railway Project in Iran. Accordingly, two case studies of damaged buildings were used to assess the ability of this model to predict the damage. Comparison with the measured data indicated that the model achieved the satisfactory results. © 2018 Springer-Verlag London Ltd., part of Springer Nature |
|---|