当前位置: X-MOL 学术Opt. Fiber Technol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Vehicle identification based on Variational Mode Decomposition in phase sensitive optical time-domain reflectometer
Optical Fiber Technology ( IF 2.6 ) Pub Date : 2020-12-01 , DOI: 10.1016/j.yofte.2020.102374
Song Chen , Yingchun Li , Liangliang Huang , Han Yin , Junjie Zhang , Yingxiong Song , Min Wang

Abstract In this paper, aiming at the problem of vibration event classification based on phase sensitive optical time-domain reflectometer (Φ-OTDR), we propose an efficient multi class event recognition scheme based on Variational Mode Decomposition (VMD). The signals collected by optical fiber sensors are preprocessed by the VMD algorithm, and then the features of the signals are extracted by Mel Frequency Cepstral Coefficients (MFCC). Finally, the extracted features are classified and identified by using machine learning algorithm. In order to improve the reliability of identification, the VMD algorithm can be used to decompose the signal into different modes. We extract and identify the features of each mode signal. Finally, the result with the highest number of occurrences is taken as the identification result. Six different vehicle vibration signals are classified and identified, and the recognition accuracy is 97.7%.

中文翻译:

基于变模分解的相敏光时域反射仪车辆识别

摘要 本文针对基于相敏光时域反射仪(Φ-OTDR)的振动事件分类问题,提出了一种基于变分模式分解(VMD)的高效多类事件识别方案。光纤传感器采集到的信号通过VMD算法进行预处理,然后通过梅尔频率倒谱系数(MFCC)提取信号特征。最后,利用机器学习算法对提取的特征进行分类识别。为了提高识别的可靠性,可以使用VMD算法将信号分解为不同的模式。我们提取并识别每个模式信号的特征。最后,将出现次数最多的结果作为识别结果。
更新日期:2020-12-01
down
wechat
bug