基于多尺度一维卷积神经网络的光纤振动事件识别  

Vibration events recognition of optical fiber based on multi-scale 1-D CNN

作　　者：吴俊 管鲁阳[2] 鲍明[2] 许耀华[1] 叶炜[3] Wu Jun;Guan Luyang;Bao Ming;Xu Yaohua;Ye Wei(Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Hefei, Anhui 230039,China;Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190,China;College of Control Science and Engineering, Zhejiang University, Hangzhou, Zhejiang 310058,China)

机构地区：[1]安徽大学计算智能与信号处理教育部重点实验室,安徽合肥230039 [2]中国科学院声学研究所,北京100190 [3]浙江大学控制科学与工程学院,浙江杭州310058

出　　处：《光电工程》2019年第5期76-83,共8页Opto-Electronic Engineering

基　　金：中国科学院战略性先导科技专项(XDC02040600)~~

摘　　要：针对相位敏感光时域反射(Φ-OTDR)分布式光纤振动传感系统如何对振动事件进行高效准确识别的问题,本文提出了一种基于多尺度一维卷积神经网络(MS 1-D CNN)的振动事件识别方法。该方法将原始振动信号经过预加重、归一化和谱减降噪的预处理操作后得到的一维信号,直接通过MS 1-D CNN实现端到端的振动信号特征的提取和识别。MS1-DCNN在提取入侵振动信号特征时可兼顾信号时间和频率尺度,利用全连接层(FClayer)和Softmax层完成最终的识别过程,与二维卷积神经网络(2-D CNN)和一维卷积神经网络(1-D CNN)相比减少了待定参数数量。对破坏、敲击和干扰三类目标振动事件的光纤振动传感信号识别结果表明,MS 1-D CNN的识别正确率与2-D CNN相近,达到了96%以上,而处理速度提升一倍,在保持识别性能的前提下,有利于提高振动事件识别的实时性。A new CNN-based deep neural network, multi-scale one-dimensional convolutional neural network(MS1-D CNN) was proposed to improve the efficiency and accuracy of vibration event recognition for a phase-sensitive optical time-domain reflectometry(Φ-OTDR) distributed optical fiber vibration sensing system. The raw vibration signals are pre-processed first to remove noise as far as possible. The pre-processing operations include pre-emphasis filtering, normalization and spectral subtraction. The pre-processed signals are used as the inputs of MS 1-D CNN directly. MS 1-D CNN realizes the end-to-end feature extraction of vibration signals and finally recognizes the vibration events by using a fully-connected layer(FC layer) and a Softmax layer. In comparison with two-dimensional convolutional neural network(2-D CNN) and one-dimensional convolutional neural network(1-D CNN), the proposed method balances the time and frequency scales better during feature extraction and reduces the pending parameters of the whole neural network. A vibration recognition experiment was designed to classify the three types of the vibration events including damaging, knocking and interference. The recognition results show that MS 1-D CNN achieves similar recognition performance, over 96 percent, at twice processing speed compared to 2-D CNN. Therefore, it is beneficial to improve the real-timing of vibration monitoring while maintaining the recognition performance.

关 键 词：分布式光纤振动传感 多尺度一维卷积神经网络 相位敏感光时域反射 振动事件识别 模式识别 

分 类 号：TB872[一般工业技术—摄影技术] TN253[电子电信—物理电子学]