Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Electronic and Information Engineering | en_US |
| dc.contributor.advisor | Yu, Changyuan (EIE) | en_US |
| dc.creator | Lai, Ho Yin Koey | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/10764 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | en_US |
| dc.rights | All rights reserved | en_US |
| dc.title | The applications of deep learning in BOTDA sensing system | en_US |
| dcterms.abstract | Two deep learning algorithms were applied on the experimental raw data from the Brillouin optical time-domain Analyzer (BOTDA) sensing system respectively. Deep neural network (DNN) was used for estimating the temperatures at each of time step from the raw Brillouin gain spectrum (BGS) profile. The mean absolute error is very small with lesser than 1°C and the network structure of 3 hidden layers outperform at the error of lesser than 0.1°C relatively to the traditional Lorentzian curve fitting (LCF) results. New study was also conducted in the application of deep learning on the pattern recognition for the BOTDA sensing data. The Long short-term memory (LSTM) models were successfully implemented with high accuracy. The dataset used in the study is small and homogeneous. It may not be representative enough. However, several LSTM network structures were studied to explore the direction of adjusting the LSTM model in future studies. Both adding an additional hidden layer with nodes relatively to the input dimension and bidirectional network return better performance than the single LSTM layer model. Further works can add on the strain data or conduct on the on-site data to verify the model performance. It is believed that the deep learning application on BOTDA has good potential in the development of automatic structure health monitoring (SHM). | en_US |
| dcterms.extent | vii, 55 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2020 | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.LCSH | Detectors | en_US |
| dcterms.LCSH | Machine learning | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 5166.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 2.52 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/10764