An Extraction and Recognition Method of the Distributed Optical Fiber Vibration Signal Based on EMD-AWPP and HOSA-SVM Algorithm
ZHANG Yan-jun1, 2, LIU Wen-zhe1, FU Xing-hu1, 2*, BI Wei-hong1, 2
1. School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, China 2. The Key Laboratory for Special Fiber and Fiber Sensor of Hebei Province, Qinhuangdao 066004, China
Abstract:Given that the traditional signal processing methods can not effectively distinguish the different vibration intrusion signal, a feature extraction and recognition method of the vibration information is proposed based on EMD-AWPP and HOSA-SVM, using for high precision signal recognition of distributed fiber optic intrusion detection system. When dealing with different types of vibration, the method firstly utilizes the adaptive wavelet processing algorithm based on empirical mode decomposition effect to reduce the abnormal value influence of sensing signal and improve the accuracy of signal feature extraction. Not only the low frequency part of the signal is decomposed, but also the high frequency part the details of the signal disposed better by time-frequency localization process. Secondly, it uses the bispectrum and bicoherence spectrum to accurately extract the feature vector which contains different types of intrusion vibration. Finally, based on the BPNN reference model, the recognition parameters of SVM after the implementation of the particle swarm optimization can distinguish signals of different intrusion vibration, which endows the identification model stronger adaptive and self-learning ability. It overcomes the shortcomings, such as easy to fall into local optimum. The simulation experiment results showed that this new method can effectively extract the feature vector of sensing information, eliminate the influence of random noise and reduce the effects of outliers for different types of invasion source. The predicted category identifies with the output category and the accurate rate of vibration identification can reach above 95%. So it is better than BPNN recognition algorithm and improves the accuracy of the information analysis effectively.
张燕君1, 2,刘文哲1,付兴虎1, 2*,毕卫红1, 2 . 基于EMD-AWPP和HOSA-SVM算法的分布式光纤振动入侵信号的特征提取与识别 [J]. 光谱学与光谱分析, 2016, 36(02): 577-582.
ZHANG Yan-jun1, 2, LIU Wen-zhe1, FU Xing-hu1, 2*, BI Wei-hong1, 2 . An Extraction and Recognition Method of the Distributed Optical Fiber Vibration Signal Based on EMD-AWPP and HOSA-SVM Algorithm . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(02): 577-582.
[1] Wu Huijuan, Rao Yunjiang, Tang Cheng, et al. Sensors and Actuators A: Physical, 2011, 167(2): 548. [2] Zhou Zhengxian, Zhuang Songlin. Optics Communications, 2014, 33: 1. [3] Wei Pu, Shan Xuekang, Sun Xiaohan. Optical Fiber Technology, 2013, 19(1): 47. [4] Mahmoud S S, Visagathilagar Y, Katsifolis J. Photonic Sensors, 2012, 2(3): 225. [5] RAO Yun-jiang, WU Min, RAN Zeng-ling, et al(饶云江,吴 敏,冉曾令,等). Chinese Journal of Sensors and Actuators(传感技术学报), 2007, 20(5): 45. [6] YU Xiao-mang, LUO Guang-ming, ZHU Zhen-min, et al(喻骁芒,罗光明,朱珍民,等). Opto-Electronic Engineering(光电工程), 2014, 41(1): 36. [7] Marco Leo, David Looney, Tiziana D’Orazio et al. IEEE Transactions on Instrumentation and Measurement,2012, 61(1): 221. [8] David Looney, Danilo P. IEEE Transactions on Signal Processing. 2009, 57(4): 1626. [9] Shao Renping, Hu Wentao, Wang Yayun,et al. Measurement, 2014, 54: 118. [10] Hu Qiao, He Zhengjia, Zhang Zhousuo et al. Mechanical Systems and Signal Processing, 2007, 21: 688. [11] LIU Heng-bing, HAN Shi-qin, LIU Jing(刘恒冰,韩世勤,刘 晶). Computer Engineering and Applications(计算机工程与应用), 2007, 43(24): 72. [12] Jia Xiaoning, Yang Hang, Ma Siliang,et al. Optics and Lasers in Engineering, 2014, 57: 28. [13] Kuang Chua Chuaa, Vinod Chandran, U Rajendra Acharyaa,et al. Medical Engineering & Physics, 2010, 32: 679. [14] Liang B, Iwnicki S D, Zhao Y. Mechanical Systems and Signal Processing, 2013, 39: 342. [15] QIU Su, JIN Wei-qi, SONG Zheng(裘 溯,金伟其,宋 铮). Optical Technique(光学技术), 2011, 37(3): 351. [16] Helena G Ramos, Tiago Rocha, Jakub Král,et al. Measurement, 2014, 54: 201. [17] Cheng Weifei, Guang Chenbai. Mechanical Systems and Signal Processing,2014, 49: 196. [18] Sun Jiedi, Xiao Qiyang, Wenb Jiangtao,et al. Measurement, 2014, 55: 434. [19] Behrang M A, Assareh E, Noghrehabadi A R,et al. Energy, 2011, 36: 3036.