Research of signal recognition of distributed optical fiber vibration sensors

ZOU Dongbo; LIU Hai; ZHAO Liang; KANG Yingjie

doi:10.7510/jgjs.issn.1001-3806.2016.01.019

In order to identify the invasion of vibration signal, a recognition algorithm based on Mel frequency cepstral coefficients (MFCC) was introduced according to the feature of vibration signal, taking processing method of voice signal as a reference and comparing with original spectrum analysis algorithm based on fast Fourier transform (FFT) after the investigation of distributed optical fiber vibration sensor and vibration signal recognition technology.。In the new algorithm, the vibration signal was analyzed in frequency domain. MFCC under different conditions was extracted and was taken as a new characteristic parameter. After comparing the experimental results, false alarm rates of both the algorithms are 27.5% and 7.5% respectively. The results show that false alarm rate of the algorithm based on MFCC can be reduced by 20% or more compared with the algorithm based on FFT. Obviously, under the premise of not omitting, MFCC algorithm with lower false alarm rate is more suitable for security systems.

Research of signal recognition of distributed optical fiber vibration sensors

Corresponding author: LIU Hai, hailiu@hust.edu.cn;

1. School of Optical and Electronic Information, Huazhong University of Science and Technology, Wuhan 430074, China

Received Date: 2014-10-22

Accepted Date: 2014-11-20

Available Online: 2016-01-25

Abstract: In order to identify the invasion of vibration signal, a recognition algorithm based on Mel frequency cepstral coefficients (MFCC) was introduced according to the feature of vibration signal, taking processing method of voice signal as a reference and comparing with original spectrum analysis algorithm based on fast Fourier transform (FFT) after the investigation of distributed optical fiber vibration sensor and vibration signal recognition technology.。In the new algorithm, the vibration signal was analyzed in frequency domain. MFCC under different conditions was extracted and was taken as a new characteristic parameter. After comparing the experimental results, false alarm rates of both the algorithms are 27.5% and 7.5% respectively. The results show that false alarm rate of the algorithm based on MFCC can be reduced by 20% or more compared with the algorithm based on FFT. Obviously, under the premise of not omitting, MFCC algorithm with lower false alarm rate is more suitable for security systems.

HTML

Reference (15)

[1]	WANG H, SUN Q Zh, LI X L, et al. Progress in optical fiber interferometer based distributed vibration sensing technology[J].Laser Optoelectronics Progress, 2013, 50(2):30-41(in Chinese).
[2]	LI X L, SUN Q Zh, WO J H, et al. Hybrid TDM/WDM-based fiber-optic sensor network for perimeter intrusion detection[J]. Journal of Lightwave Technology, 2012, 30(8):1113-1120.
[3]	SUN Q Zh, LIU D M, WANG J. Recent progress in distributed optical fiber stress sensor[J].Semiconductor Optoelectronics, 2007, 28(1):10-15(in Chinese).
[4]	HU Zh S, YANG Q H, QIAO B. Design of interference distributed fiber-optic underwater long gas pipeline leakage detection system[J]. Laser Optoelectronics Progress, 2012, 49(7):73-77(in Chinese).
[5]	SUN Q Zh, LIU D M, WANG J, et al. Distributed fiber-optic vibration sensor using a ring Mach-Zehnder interferometer[J]. Optics Communications, 2008, 281(6):1538-1544.
[6]	HE C F, ZHENG X Q, LUO J W, et al. Research on a pipeline leakage detection system and its stability based on depolarized Sagnac fiber interferometer[J]. Chinese Journal of Lasers, 2012, 39(2):148-152(in Chinese).
[7]	HANG L J, HE C F, WU B. A new pipeline leakage detection system based on linear optical fiber Sagnac interferometer and its location technology[J].Chinese Journal of Lasers, 2007,34(6):820-824(in Chinese).
[8]	GE S X. Research on distributed fiber optic vibration sensor[D].Hangzhou:Zhejiang University, 2012:1-13(in Chinese).
[9]	WAN X, DU T T, ZHANG Zh M, et al. Positioning approach based on Mach-Zehnder fiber sensors and a DSP processor[J].Proceedings of the SPIE, 2013, 9044:90440T.
[10]	GUO Ch Y, ZHENG K. Denoising optical interferometry signal based on wavelet transform threshold[J].Laser Technology, 2009, 33(5):506-508(in Chinese).
[11]	SU X F. Data acquisition and processing of distributed optical fiber vibration sensor system[D].Beijing:Beijing University of Posts and Telecommunications, 2010:1-56(in Chinese).
[12]	LV X Y, WANG H X. Abnormal audio recognition algorithm based on MFCC and short-term energy[J].Journal of Computer Applications, 2010, 30(3):796-798(in Chinese).
[13]	HAN Y, WANG G Y, YANG Y. Speech emotion recognition based on MFCC[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2008, 20(5):597-602(in Chinese).
[14]	HOSSEINZADEH D, KRISHNAN S. Combining vocal source and MFCC features for enhanced speaker recognition performance using GMMs[C]//Proceedings of the IEEE 9th Workshop on Multimedia Signal Processing.New York,USA:IEEE,2007:365-368.
[15]	TIAN Sh Sh, TANG W, SHE W. Research of improved MFCC parameters in signer-independent speech recognition[J].Bulletin of Science and Technology, 2013, 29(3):139-142(in Chinese).

Research of signal recognition of distributed optical fiber vibration sensors

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Proportional views