BOTDA temperature extraction method based on kernel extreme learning machine

Abstract

The invention discloses a temperature extraction method of a Brillouin optical time domain analysis system (BOTDA) based on a kernel extreme learning machine. The method comprises the following stepsthat Brillouin gain spectrum parameters of a test optical fiber are acquired by using a Brillouin optical time domain analysis system; a kernel extreme learning machine is adopted to analyze parameters collected by a Brillouin optical time domain analysis system, an obtained real matrix serves as training data of the kernel extreme learning machine, the training data is used for training the kernel extreme learning machine, the accurate temperature information is extracted, and system performance is improved through the higher processing speed. The method is advantaged in that a kernel extremelearning machine algorithm is introduced, so temperature extraction precision and kernel efficiency of the Brillouin light starting from an analysis system are improved, and the application of the Brillouin light time domain analysis system in actual detection is facilitated.

Description

technical field [0001] The invention belongs to the field of optical fiber distributed sensing and machine learning, and relates to a distributed optical fiber sensing system, in particular to a Brillouin optical time-domain analysis technology based on stimulated Brillouin scattering of a nuclear extreme learning machine. Background technique [0002] In civil engineering, building construction, power distribution and other fields, in order to measure the temperature, stress and other parameters of long-distance facilities (such as: bridges, tunnels, oil and gas pipelines, power transmission cables, etc.) For safety monitoring), it is often used to lay out test optical fibers, and indirectly test parameters such as temperature or stress of the facility in a long-distance range by testing the temperature or stress of the test optical fiber. [0003] At present, the laying length of the test optical fiber is usually several kilometers, or tens of kilometers or hundreds of kil...

AI Technical Summary

Problems solved by technology

[0007] In the past, the main research was to extract the temperature of the Brillouin optical time domain analysis system based on the traditional fitting method, such as using the Lorenz curve fitting algorithm to extract the temperature of the Brillouin optical time domain analysis system. However, this The data processing speed of the data processing method is slow

Images