An energy ratio feature extraction method for optical fiber vibration signal

Abstract

The intrusion events in the optical fiber pre-warning system (OFPS) are divided into two types which are harmful intrusion event and harmless interference event. At present, the signal feature extraction methods of these two types of events are usually designed from the view of the time domain. However, the differences of time-domain characteristics for different harmful intrusion events are not obvious, which cannot reflect the diversity of them in detail. We find that the spectrum distribution of different intrusion signals has obvious differences. For this reason, the intrusion signal is transformed into the frequency domain. In this paper, an energy ratio feature extraction method of harmful intrusion event is drawn on. Firstly, the intrusion signals are pre-processed and the power spectral density (PSD) is calculated. Then, the energy ratio of different frequency bands is calculated, and the corresponding feature vector of each type of intrusion event is further formed. The linear discriminant analysis (LDA) classifier is used to identify the harmful intrusion events in the paper. Experimental results show that the algorithm improves the recognition rate of the intrusion signal, and further verifies the feasibility and validity of the algorithm.

Keywords

OFPS / energy ratio / LDA classification

References

[1] Yang Y., Feng H., Wang Z. H., Sha Z., Wang G. Q., Jia Z. N., . Application and development of distributed optical fiber sensing technology in pipeline detection. Electro-Optic Technology Application, 2016, 31(6): 1-9.

[2] Qu Z. G.. Study on the leakage detection and pre-warning techniques based on the distributed optical fiber for the long-distance oil and gas pipelines, 2007

[3] Chen J. M.. Research on fiber perimeter protection system based on Mach-Zehnder interferometer, 2012

[4] Zhu F.. Research on performance enhancement of phase sensitive time-domain reflection sensor system, 2015

[5] An Y., Jin S. J., Feng X., Feng H., Zeng Z. M.. Optical fiber pipeline security pre warning system based on coherent Rayleigh scattering. Journal of Tianjin University (Science and Technology), 2015, 48(1): 70-75.

[6] Yin L. P., Lei G.. Joint stochastic distribution tracking control for multivariate descriptor systems with non-Gaussian variables. International Journal of Systems Science, 2012, 43(1): 192-200.

[7] Qu H. Q., Zheng T., Bi F. K., Pang L. P.. Vibration detection method for optical fiber pre-warning system. IET^Signal Processing, 2016, 10(6): 692-698.

[8] Yang B., Gao W., Xi G.. The key technologies for Φ-OTDR-based distributed fiber-optic sensing systems. Study On Optical Communications, 2012, 38(4): 19-22.

[9] Qu H. Q., Zheng T., Pang L. P., Li X. L.. A new two-dimensional method to detect harmful intrusion vibrations for optical fiber pre-warning system. Optik, 2016, 127(10): 4461-4469.

[10] Zheng T.. Theoretical basis research on detection and recognition method for Φ-OTDR optical fiber intrusion, 2017

[11] Lu N., An B. W., Li Y. L., Li Y. L., Lu X. J.. Signal recognition algorithm of fiber-optic security system based on time-domain features. Transducer and Microsystem Technologies, 2017, 36(4): 150-152.

[12] Lu Y., Han Z. K., Chen Y.. FFT narrow band filtering method based on energy-ratio pretreatment. Journal of Southeast University (Natural Science Edition), 2010, 40(5): 948-951.

[13] Mahmoud S. S., Visagathilagar Y., Katsifolis J.. Real-time distributed fiber optic sensor for security systems: performance, event classification and nuisance mitigation. Photonic Sensors, 2012, 2(3): 225-236.

[14] Lv Y. X., Sun S. X., Gu X. H.. Battlefield acoustic target classification and recognition based on EMD and power ratio. Journal of Vibration and Shock, 2008, 27(11): 51-55.

[15] Chen J. Y.. A K-MEANS and LDA based discriminative and compact dictionary learning method, 2015

[16] Theodoridis S., Koutroumbas K.. Pattern recognition, 2010, Beijing, China: Publishing House of Electronics Industry, 191-193.