Utility pole integrity assessment by distributed acoustic sensing and machine learning
A method of utility pole integrity assessment by distributed fiber optic sensing/distributed acoustic sensing (DFOS/DAS) employing existing telecommunications fiber optic cable as a sensor. The fiber optic cable is suspended aerially from a plurality of utility poles and a machine learning model is developed during training by mechanically exciting the utility poles. Once developed, and in sharp contrast to the prior art, the machine learning model—in conjunction with DFOS/DAS operation—determines an integrity assessment for a plurality of the utility poles aerially suspending the fiber optic cable from a mechanical impact of a single pole.
1. A method for operating a utility pole integrity assessment system including a distributed a distributed fiber optic sensing/distributed acoustic sensing (DFOS/DAS) system having a length of optical sensing fiber suspended from a plurality of utility poles and in optical communication with a DFOS/DAS interrogator/analyzer, said method comprising:
operating the DFOS/DAS system while mechanically impacting/exciting individual ones of the plurality of utility poles, each of the impacted/excited utility poles having known integrity conditions to obtain DFOS/DAS response signals of the excited utility poles having known integrity conditions;
training a neural network model with the DFOS/DAS response signals of the excited utility poles having known integrity conditions such that DFOS/DAS signals are classified into the known integrity conditions;
operating the DFOS/DAS system while mechanically impacting/exciting one of the plurality of utility poles, the impacted/excited utility pole having unknown integrity conditions and collecting DFOS/DAS response signals of the plurality of utility poles having unknown integrity conditions;
classifying, using the trained neural network model, the DFOS/DAS response signals of the plurality of utility poles having unknown integrity conditions to known integrity conditions; and
generating a report of the known integrity conditions of the plurality of utility poles classified.