Perpendicular distance prediction of vibrations by distributed fiber optic sensing
Distributed fiber optic sensing (DFOS) systems, methods and structures for determining the proximity of vibration sources located perpendicular to a sensor fiber that is part of the DFOS system that may potentially threaten/damage or otherwise compromise the sensor fiber itself. Systems, methods, and structures according to aspects of the present disclosure employ Artificial Intelligence (AI) methodology(ies) that use as input a fundamental physical understanding of wave propagation and attenuation in the ground along with Bayesian inference and Maximum Likelihood Estimation (MLE) techniques for estimating/determining the proximity of potentially damaging vibration sources to the optical sensor fiber.
1. A method of operating a distributed fiber optic sensing (DFOS)/distributed acoustic sensing (DAS) system to determine perpendicular distance(s) from a DAS sensing fiber to vibration sources said method comprising:
operating the DAS system to measure baseline vibration levels and event characteristics at different perpendicular distances from locations along a length of sensing optical fiber that is part of the DAS system and collect a training dataset to establish canonical joint probability distribution of perpendicular distances from the sensing optical fiber and observed intensity;
integrating the measured baseline vibration levels and respective perpendicular distances from locations along the length of the sensing optical fiber to a geographic map;
generating a database of vibration intensity profiles for each perpendicular distance and location along the length of the sensing optical fiber;
determining background traffic vibrations in the database of vibration intensity profiles and removing same according to a median filtering methodology;
detecting a vibration through the effect of the DAS and determining a perpendicular distance from the sensing optical fiber of a source of the detected vibration; and
wherein the perpendicular distance determination is made from a DFOS stream of waterfall plots resulting from operation of the DAS system;
wherein the perpendicular distance determination includes an image binarization of the stream of waterfall plots; and
wherein the perpendicular distance determination includes generating an intensity profile at each perpendicular location using a join probability map by a Kernel Density or Gaussian Process Regression (GPR) process.
2. The method of claim 1 , further comprising generating and outputting an alarm when the determined perpendicular distance satisfies a pre-determined alarm threshold condition.