Support Vector Machine based Differential Pulse-width Pair Brillouin Optical Time Domain Analyzer
Support vector machine (SVM) based differential pulse-width pair Brillouin optical time domain analyzer (DPP-BOTDA) has been proposed and experimentally demonstrated. With only one SVM model, temperature distribution along 5 km fiber under test has been successfully extracted from differe...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2018-01-01
|
| Series: | IEEE Photonics Journal |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8417908/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850109100970475520 |
|---|---|
| author | Huan Wu Liang Wang Zhiyong Zhao Chester Shu Chao Lu |
| author_facet | Huan Wu Liang Wang Zhiyong Zhao Chester Shu Chao Lu |
| author_sort | Huan Wu |
| collection | DOAJ |
| description | Support vector machine (SVM) based differential pulse-width pair Brillouin optical time domain analyzer (DPP-BOTDA) has been proposed and experimentally demonstrated. With only one SVM model, temperature distribution along 5 km fiber under test has been successfully extracted from differential Brillouin gain spectrum (BGS) measured under different spatial resolution in DPP-BOTDA. The temperature accuracy by SVM is better than that by Lorentzian curve fitting (LCF), especially when the pump pulse width difference and the number of trace averaging used in the measurement are small, indicating larger tolerance of SVM to high spatial resolution and low signal-to-noise ratio. SVM is also more robust to a wide range of frequency scanning steps and has less accuracy degradation under large frequency scanning step. To extract temperature from 50 000 differential BGSs, 133.17 and 1.12 s are consumed by SVM-0.1 and SVM-1 °C, respectively, both of which are much shorter than that by LCF. The data processing time of SVM is further shortened with the help of principle component analysis for data dimension reduction. SVM for measurand extraction would be especially helpful in the scenario of DPP-BOTDA where high data sampling rate is required to resolve plenty of submeter scale sensing points. |
| format | Article |
| id | doaj-art-a943ae06189a47569ea2380a75b728e5 |
| institution | OA Journals |
| issn | 1943-0655 |
| language | English |
| publishDate | 2018-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Photonics Journal |
| spelling | doaj-art-a943ae06189a47569ea2380a75b728e52025-08-20T02:38:11ZengIEEEIEEE Photonics Journal1943-06552018-01-0110411110.1109/JPHOT.2018.28582358417908Support Vector Machine based Differential Pulse-width Pair Brillouin Optical Time Domain AnalyzerHuan Wu0Liang Wang1https://orcid.org/0000-0001-5179-7943Zhiyong Zhao2https://orcid.org/0000-0001-5541-9173Chester Shu3https://orcid.org/0000-0003-0020-6431Chao Lu4https://orcid.org/0000-0002-9469-6672Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong KongDepartment of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong KongDepartment of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong KongDepartment of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong KongDepartment of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong KongSupport vector machine (SVM) based differential pulse-width pair Brillouin optical time domain analyzer (DPP-BOTDA) has been proposed and experimentally demonstrated. With only one SVM model, temperature distribution along 5 km fiber under test has been successfully extracted from differential Brillouin gain spectrum (BGS) measured under different spatial resolution in DPP-BOTDA. The temperature accuracy by SVM is better than that by Lorentzian curve fitting (LCF), especially when the pump pulse width difference and the number of trace averaging used in the measurement are small, indicating larger tolerance of SVM to high spatial resolution and low signal-to-noise ratio. SVM is also more robust to a wide range of frequency scanning steps and has less accuracy degradation under large frequency scanning step. To extract temperature from 50 000 differential BGSs, 133.17 and 1.12 s are consumed by SVM-0.1 and SVM-1 °C, respectively, both of which are much shorter than that by LCF. The data processing time of SVM is further shortened with the help of principle component analysis for data dimension reduction. SVM for measurand extraction would be especially helpful in the scenario of DPP-BOTDA where high data sampling rate is required to resolve plenty of submeter scale sensing points.https://ieeexplore.ieee.org/document/8417908/Brillouin optical time domain analyzerdifferential pulse-width pairsupport vector machinetemperature extractiondata processing time. |
| spellingShingle | Huan Wu Liang Wang Zhiyong Zhao Chester Shu Chao Lu Support Vector Machine based Differential Pulse-width Pair Brillouin Optical Time Domain Analyzer IEEE Photonics Journal Brillouin optical time domain analyzer differential pulse-width pair support vector machine temperature extraction data processing time. |
| title | Support Vector Machine based Differential Pulse-width Pair Brillouin Optical Time Domain Analyzer |
| title_full | Support Vector Machine based Differential Pulse-width Pair Brillouin Optical Time Domain Analyzer |
| title_fullStr | Support Vector Machine based Differential Pulse-width Pair Brillouin Optical Time Domain Analyzer |
| title_full_unstemmed | Support Vector Machine based Differential Pulse-width Pair Brillouin Optical Time Domain Analyzer |
| title_short | Support Vector Machine based Differential Pulse-width Pair Brillouin Optical Time Domain Analyzer |
| title_sort | support vector machine based differential pulse width pair brillouin optical time domain analyzer |
| topic | Brillouin optical time domain analyzer differential pulse-width pair support vector machine temperature extraction data processing time. |
| url | https://ieeexplore.ieee.org/document/8417908/ |
| work_keys_str_mv | AT huanwu supportvectormachinebaseddifferentialpulsewidthpairbrillouinopticaltimedomainanalyzer AT liangwang supportvectormachinebaseddifferentialpulsewidthpairbrillouinopticaltimedomainanalyzer AT zhiyongzhao supportvectormachinebaseddifferentialpulsewidthpairbrillouinopticaltimedomainanalyzer AT chestershu supportvectormachinebaseddifferentialpulsewidthpairbrillouinopticaltimedomainanalyzer AT chaolu supportvectormachinebaseddifferentialpulsewidthpairbrillouinopticaltimedomainanalyzer |