Fading Discrimination and Suppression of DAS System Based on FAM-MAE
Mingyang Sun, Miao Yu, Haoran Wang, Kaiwen Song, Xinyu Guo, Songfeng Xue, Yanbin Shao, Hongwei Zhang, Tianyu Zhang
Abstract
Optical distributed acoustic sensing (DAS) based on phase-sensitive optical time-domain reflectometry ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\Phi $ </tex-math></inline-formula> -OTDR) can realize the distributed monitoring of multipoint disturbances along the optical fiber, which has wide-ranging applications in various fields; however, owing to the fading phenomenon in the DAS, the signal strength is greatly attenuated, thereby causing the phase signal to jump and complicating the continuous and effective collection of the disturbance signal. Considering the amplitude, we propose a fading adaptive mask and masked autoencoders (FAM-MAE) algorithm for fading discrimination and suppression of DAS system. The differential calculation and analysis of the amplitude signal are performed, and the nondifferentiable point is the fading point. The density-based spatial clustering of applications with noise (DBSCAN) is used to determine the position of the phase fading point. The MAE were used to reconstruct these positions to achieve fading suppression. The experimental results indicate that the average signal-to-noise ratio (SNR) of the vibration signal of the piezoelectric transducer (PZT) is improved from 4.81 to 21.92 dB after fading suppression. The SNR of the underwater acoustic disturbance signal is improved by 12.68 dB after fading suppression; therefore, the proposed method can suppress the signal distortion caused by fading and recover the disturbance signal completely.