A Representation-Enhanced Vibration Signal Imaging Method Based on MTF-NMF for Φ-OTDR Recognition
- 20 June 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Journal of Lightwave Technology
- Vol. 42 (18) , 6395-6401
Abstract
The phase signals, combined with time-domain signal processing methods, are often used for recognition with the phase-sensitive optical time-domain reflectometer (Φ-OTDR). Considering the advanced and sophisticated algorithms prevalent in the field of image processing, a vibration signal imaging method is proposed to enhance the adaptability of phase signals for learning by image network. The phase time series is converted to a Markov Transition Fields (MTF) matrix, from which the based matrix is extracted by Non-negative Matrix Factorization (NMF) and saved as an RGB image. One-dimensional (1-D) Convolutional Neural Network (CNN) and 2-D CNN are applied in the experiment to classify the phase signals and images, respectively. The experimental results show that the training convergence efficiency of 2-D CNN using NMF-MTF images is significantly higher than that of 1-D CNN, demonstrating the effectiveness of converting phase signals into images. In addition, the average recognition accuracy for the four fence events is improved by more than 13% by introducing the NMF algorithm on the MTF matrix.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFF0708400)
- Science and Technology Commission of Shanghai Municipality (22ZR1423000, 22ZR1424800, 22010500100)
- National Natural Science Foundation of China (62022053, 62027818)
- Higher Education Discipline Innovation Project (D20031)
- Advanced Optical Waveguide Intelligent Manufacturing and Testing Professional Technical Service Platform of Shanghai (19DZ2294000)
This publication has 27 references indexed in Scilit:
- An event recognition method based on MFCC, superposition algorithm and deep learning for buried distributed optical fiber sensorsOptics Communications, 2022
- Quickly build a high-precision classifier for Φ-OTDR sensing system based on transfer learning and support vector machineOptical Fiber Technology, 2022
- Structural damage identification under nonstationary excitations through recurrence plot and multi-label convolutional neural networkMeasurement, 2021
- Deep learning-based detection of structural damage using time-series dataStructure and Infrastructure Engineering, 2020
- Event identification based on random forest classifier for Φ-OTDR fiber-optic distributed disturbance sensorInfrared Physics & Technology, 2019
- Application of distributed optical fiber sensors for the health monitoring of two real structures in BarcelonaStructure and Infrastructure Engineering, 2018
- Pattern recognition based on enhanced multifeature parameters for vibration events in φ‐OTDR distributed optical fiber sensing systemMicrowave and Optical Technology Letters, 2017
- Novel feature extraction method for cough detection using NMFIET Signal Processing, 2017
- Deep learningNature, 2015
- Learning the parts of objects by non-negative matrix factorizationNature, 1999