3 January 2018 Pattern recognition based on time-frequency analysis and convolutional neural networks for vibrational events in φ-OTDR
Author Affiliations +
Abstract
Based on vibration signals detected by a phase-sensitive optical time-domain reflectometer distributed optical fiber sensing system, this paper presents an implement of time-frequency analysis and convolutional neural network (CNN), used to classify different types of vibrational events. First, spectral subtraction and the short-time Fourier transform are used to enhance time-frequency features of vibration signals and transform different types of vibration signals into spectrograms, which are input to the CNN for automatic feature extraction and classification. Finally, by replacing the soft-max layer in the CNN with a multiclass support vector machine, the performance of the classifier is enhanced. Experiments show that after using this method to process 4000 vibration signal samples generated by four different vibration events, namely, digging, walking, vehicles passing, and damaging, the recognition rates of vibration events are over 90%. The experimental results prove that this method can automatically make an effective feature selection and greatly improve the classification accuracy of vibrational events in distributed optical fiber sensing systems.
© 2018 Society of Photo-Optical Instrumentation Engineers (SPIE)
Chengjin Xu, Chengjin Xu, Junjun Guan, Junjun Guan, Ming Bao, Ming Bao, Jiangang Lu, Jiangang Lu, Wei Ye, Wei Ye, } "Pattern recognition based on time-frequency analysis and convolutional neural networks for vibrational events in φ-OTDR," Optical Engineering 57(1), 016103 (3 January 2018). https://doi.org/10.1117/1.OE.57.1.016103 . Submission: Received: 13 July 2017; Accepted: 7 December 2017
Received: 13 July 2017; Accepted: 7 December 2017; Published: 3 January 2018
JOURNAL ARTICLE
7 PAGES


SHARE
Back to Top