Quaternion Wavelet Transform and a Feedforward Neural Network-Aided Intelligent Distributed Optical Fiber Sensing System
In this paper, aiming at a large infrastructure structural health monitoring network, a quaternion wavelet transform (QWT) image denoising algorithm is proposed to process original data, and a depth feedforward neural network (FNN) is introduced to extract physical information from the denoised data...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/7/3637 |
| _version_ | 1827746409949954048 |
|---|---|
| author | Lei Fan Yongjun Wang Hongxin Zhang Chao Li Xingyuan Huang Qi Zhang Xiangjun Xin |
| author_facet | Lei Fan Yongjun Wang Hongxin Zhang Chao Li Xingyuan Huang Qi Zhang Xiangjun Xin |
| author_sort | Lei Fan |
| collection | DOAJ |
| description | In this paper, aiming at a large infrastructure structural health monitoring network, a quaternion wavelet transform (QWT) image denoising algorithm is proposed to process original data, and a depth feedforward neural network (FNN) is introduced to extract physical information from the denoised data. A Brillouin optical time domain analysis (BOTDA)-distributed sensor system is established, and a QWT denoising algorithm and a temperature extraction scheme using FNN are demonstrated. The results indicate that when the frequency interval is less than 4 MHz, the temperature error is kept within ±0.11 °C, but is ±0.15 °C at 6 MHz. It takes less than 17 s to extract the temperature distribution from the FNN. Moreover, input vectors for the Brillouin gain spectrum with a frequency interval of no more than 6 MHZ are unified into 200 input elements by linear interpolation. We hope that with the progress in technology and algorithm optimization, the FNN information extraction and QWT denoising technology will play an important role in distributed optical fiber sensor networks for real-time monitoring of large-scale infrastructure. |
| first_indexed | 2024-03-11T05:24:53Z |
| format | Article |
| id | doaj.art-83f6c6533b3c4bd4bd57e9a587d58fd0 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T05:24:53Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-83f6c6533b3c4bd4bd57e9a587d58fd02023-11-17T17:35:30ZengMDPI AGSensors1424-82202023-03-01237363710.3390/s23073637Quaternion Wavelet Transform and a Feedforward Neural Network-Aided Intelligent Distributed Optical Fiber Sensing SystemLei Fan0Yongjun Wang1Hongxin Zhang2Chao Li3Xingyuan Huang4Qi Zhang5Xiangjun Xin6State Key Laboratory of Information Photonics and Optical Communications, School of Electronic Engineering, Beijing University of Posts and Telecommunications (BUPT), Beijing 100876, ChinaState Key Laboratory of Information Photonics and Optical Communications, School of Electronic Engineering, Beijing University of Posts and Telecommunications (BUPT), Beijing 100876, ChinaState Key Laboratory of Information Photonics and Optical Communications, School of Electronic Engineering, Beijing University of Posts and Telecommunications (BUPT), Beijing 100876, ChinaState Key Laboratory of Information Photonics and Optical Communications, School of Electronic Engineering, Beijing University of Posts and Telecommunications (BUPT), Beijing 100876, ChinaState Key Laboratory of Information Photonics and Optical Communications, School of Electronic Engineering, Beijing University of Posts and Telecommunications (BUPT), Beijing 100876, ChinaState Key Laboratory of Information Photonics and Optical Communications, School of Electronic Engineering, Beijing University of Posts and Telecommunications (BUPT), Beijing 100876, ChinaState Key Laboratory of Information Photonics and Optical Communications, School of Electronic Engineering, Beijing University of Posts and Telecommunications (BUPT), Beijing 100876, ChinaIn this paper, aiming at a large infrastructure structural health monitoring network, a quaternion wavelet transform (QWT) image denoising algorithm is proposed to process original data, and a depth feedforward neural network (FNN) is introduced to extract physical information from the denoised data. A Brillouin optical time domain analysis (BOTDA)-distributed sensor system is established, and a QWT denoising algorithm and a temperature extraction scheme using FNN are demonstrated. The results indicate that when the frequency interval is less than 4 MHz, the temperature error is kept within ±0.11 °C, but is ±0.15 °C at 6 MHz. It takes less than 17 s to extract the temperature distribution from the FNN. Moreover, input vectors for the Brillouin gain spectrum with a frequency interval of no more than 6 MHZ are unified into 200 input elements by linear interpolation. We hope that with the progress in technology and algorithm optimization, the FNN information extraction and QWT denoising technology will play an important role in distributed optical fiber sensor networks for real-time monitoring of large-scale infrastructure.https://www.mdpi.com/1424-8220/23/7/3637distributed optical fiber sensor networkBrillouin optical time-domain analysisquaternion wavelet transformdepth feedforward neural networkBrillouin frequency shift retrieval |
| spellingShingle | Lei Fan Yongjun Wang Hongxin Zhang Chao Li Xingyuan Huang Qi Zhang Xiangjun Xin Quaternion Wavelet Transform and a Feedforward Neural Network-Aided Intelligent Distributed Optical Fiber Sensing System Sensors distributed optical fiber sensor network Brillouin optical time-domain analysis quaternion wavelet transform depth feedforward neural network Brillouin frequency shift retrieval |
| title | Quaternion Wavelet Transform and a Feedforward Neural Network-Aided Intelligent Distributed Optical Fiber Sensing System |
| title_full | Quaternion Wavelet Transform and a Feedforward Neural Network-Aided Intelligent Distributed Optical Fiber Sensing System |
| title_fullStr | Quaternion Wavelet Transform and a Feedforward Neural Network-Aided Intelligent Distributed Optical Fiber Sensing System |
| title_full_unstemmed | Quaternion Wavelet Transform and a Feedforward Neural Network-Aided Intelligent Distributed Optical Fiber Sensing System |
| title_short | Quaternion Wavelet Transform and a Feedforward Neural Network-Aided Intelligent Distributed Optical Fiber Sensing System |
| title_sort | quaternion wavelet transform and a feedforward neural network aided intelligent distributed optical fiber sensing system |
| topic | distributed optical fiber sensor network Brillouin optical time-domain analysis quaternion wavelet transform depth feedforward neural network Brillouin frequency shift retrieval |
| url | https://www.mdpi.com/1424-8220/23/7/3637 |
| work_keys_str_mv | AT leifan quaternionwavelettransformandafeedforwardneuralnetworkaidedintelligentdistributedopticalfibersensingsystem AT yongjunwang quaternionwavelettransformandafeedforwardneuralnetworkaidedintelligentdistributedopticalfibersensingsystem AT hongxinzhang quaternionwavelettransformandafeedforwardneuralnetworkaidedintelligentdistributedopticalfibersensingsystem AT chaoli quaternionwavelettransformandafeedforwardneuralnetworkaidedintelligentdistributedopticalfibersensingsystem AT xingyuanhuang quaternionwavelettransformandafeedforwardneuralnetworkaidedintelligentdistributedopticalfibersensingsystem AT qizhang quaternionwavelettransformandafeedforwardneuralnetworkaidedintelligentdistributedopticalfibersensingsystem AT xiangjunxin quaternionwavelettransformandafeedforwardneuralnetworkaidedintelligentdistributedopticalfibersensingsystem |