DAS dynamic range improving method and device based on self-supervised signal fusion

The invention relates to a DAS dynamic range improving method and device based on self-supervised signal fusion, and the method comprises the steps: obtaining double-path optical fiber sensing data in parallel, namely, a DAS signal with an unlimited dynamic range but a low signal-to-noise ratio and a DAS phase signal with a phase unwrapping error due to the limited dynamic range; and inputting the second optical fiber sensing signal into a self-designed self-supervised signal fusion model, solving a phase winding coefficient, rounding, and constructing and outputting an unwound phase estimation value according to the rounded phase winding coefficient and the second optical fiber sensing signal. Compared with the prior art, the phase unwrapping error caused by the limited dynamic range of the DAS phase signal can be effectively corrected in real time, the real phase can be recovered, the dynamic range can be improved, and the cost of sacrificing the signal-to-noise ratio is avoided. 本发明涉及一种基于自监督式信号融合的DAS动态范围提升