Phase sensitive optical time domain reflectometer (φ-OTDR) can retrieve vibration waveforms based on linear relationship between phase change and external events. Yet, it is difficult to identify different events due to the complexity of working environment. How to accurately determine the type of vibration events and thus reduce false alarm rate is important in many practical engineering applications. The existing deep learning (DL) algorithm can directly extract the original data feature, without manual extraction. Hence, DL is usually used to classify and recognize multiple events in φ-OTDR. In this work, a dual input deep convolutional neural network (Di-DCNN) is applied to distinguish six kinds of actual vibration events (including walking, tapping, blowing and raining, vehicle passing, digging and background noise). The features of these two inputs are extracted, respectively, and fused together to identify six vibration events. For comparison, network models with other five inputs are employed for event recognition, including single input of 1D time-demain or 2D image of phase (amplitude) data, and dual input of 1D time-demain and 2D image of amplitude data. Here, the 2D image denotes the transformation of 1D data by Markov Transition Field (MTF). Experimental results show that the Di-DCNN with 1D time-domain phase waveforms and its 2D MTF image being the two inputs considerably improve the recognition accuracy. The average recognition rate of six kinds of vibration events is higher than 94%.
Phase-sensitive optical time-domain reflectometry (φ-OTDR) is highly sensitive to strain changes of sensing fiber caused by external vibration, by which we are able to locate the vibration. In practice, interference fading will inevitably occur in backscattered Rayleigh traces of φ-OTDR due to the use of highly coherent light source, which increase the possibility of failure detection. In order to reduce the influence of interference fading on vibration detection, both frequency-division multiplexing (FDM) and rotated-vector-sum (RVS) over both time-and frequency-domain are employed in our method. Based on the method, we perform φ-OTDR experiment to locate vibrations. By extracting 3 frequency components of the beating signals (~200 MHz) and carrying out dual rotation, interference fading can be suppressed to a large extent, the vibration-induced phase changes are precisely recovered. One point should be noted is that we found that there is a certain correlation between each frequency component extracted from the beating signal, resulting in interference fading points cannot be completely removed.
Phase-sensitive optical time domain reflectometer (φ-OTDR) has been extensively investigated in fields of intrusion detection and structural health monitoring. It should be noted that phase noises would keep accumulating during pulse transmission. By subtracting an initial phase at the input point from demodulated phases at other positions, the noises related to the laser itself except random noises can be considerably reduced. In order to further decrease the impact of random noises on waveform retrieval of external vibrations, it is necessary to eliminate the accumulated noises before vibration position as much as possible. In this work, a sliding root mean square method (SRMS) is firstly applied to locate vibration events. By the SRMS, the demodulated phase at ~10 m before vibration point is regarded as the modified reference. Then, the vibration waveform can be retrieved after phase subtraction. For comparison purpose, both the input and modified references are employed to retrieve temporal vibration signals. Experimental results show that the SRMS shows good noise performance for vibration location. In terms of signal retrieval, the vibration waveform can be recovered with better noise suppression by the modified reference compared to the input one.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.