High quality phase demodulation method for direct detection Φ-OTDR.

This article discovers that the excessive correlation between the selected temporal sensing sequences will lead to phase demodulation failure in the demodulation process of direct detection Φ-OTDR in certain duration, which reduces the quality of demodulated phase. Besides, we also first discover a phase polarity flipping phenomenon in the demodulation process, which will introduce additional errors and further degrade the quality of demodulated phase. In order to obtain the real phase change caused by external intrusion, a high-quality phase demodulation strategy with multi-position compensation based on leveraging the information redundancy between each Rayleigh back-scattered temporal sequence is proposed. The optimal demodulation position is selected by calculating the cross-correlation between temporal sensing sequences. The phase demodulation failure is then compensated by phase demodulation results from multiple positions. At the same time, the phase polarity change is also determined and corrected. The experimental results show that this strategy can effectively suppress the waveform distortion and improve the signal-to-noise ratio of the demodulated phase. This scheme can effectively improve the demodulation effect and detection performance of direct detection Φ-OTDR and may promote its application.

Event recognition method based on feature synthesizing for a zero-shot intelligent distributed optical fiber sensor.

Phase-sensitive optical time domain reflectometer (Φ-OTDR) is an emergent distributed optical sensing system with the advantages of high localization accuracy and high sensitivity. It has been widely used for intrusion identification, pipeline monitoring, under-ground tunnel monitoring, etc. Deep learning-based classification methods work well for Φ-OTDR event recognition tasks with sufficient samples. However, the lack of training data samples is sometimes a serious problem for these data-driven algorithms. This paper proposes a novel feature synthesizing approach to solve this problem. A mixed class approach and a reinforcement learning-based guided training method are proposed to realize high-quality feature synthesis. Experiment results in the task of eight event classifications, including one unknown class, show that the proposed method can achieve an average classification accuracy of 42% for the unknown class and obtain its event type, meanwhile achieving a 74% average overall classification accuracy. This is 29% and 7% higher, respectively, than those of the ordinary instance synthesizing method. Moreover, this is the first time that the Φ-OTDR system can recognize a specific event and tell its event type without collecting its data sample in advance.