STUDY OF THE APPLICATION OF 2D-CONVOLUTIONAL NEURAL NETWORK WITH ABSOLUTE CHANGE IN MODE SHAPE CURVATURE DAMAGE INDEX IN DETECTING AND QUANTIFYING DAMAGE ON A BRIDGE
The damage detection system plays a crucial role in ensuring the safety and functionality of civil infrastructure such as bridges. This research investigates the effectiveness of a CNN method combines with the absolute change in mode shape curvature index in detecting and quantifying damage in bridg...
Saved in:
| Main Author: | |
|---|---|
| Format: | Theses |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/87147 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | The damage detection system plays a crucial role in ensuring the safety and functionality of civil infrastructure such as bridges. This research investigates the effectiveness of a CNN method combines with the absolute change in mode shape curvature index in detecting and quantifying damage in bridge structures. The bridge structure is first modeled using the finite element method in the MIDAS Civil software. Suitable modes are then analyszed and selected as damage indicators in the form of the absolute change in mode shape curvature.
A Python automation program is designed to define damage scenarios and collect a large amount of mode shape data. Once sufficient data is collected, A CNN is built using these datas, and its performance is numerically and experimentally tested. The research results indicate CNN method is capable of the classifying task with adequate accuracy. |
|---|