A OTDR Fault Feature Judgment Method Based on Differential Evolutionary Neural Network

Abstract

The invention relates to an OTDR fault feature judgment method based on a differential evolution neural network. Firstly, sufficient OTDR fault feature diagnosis data are collected, the diagnosis dataare input into the neural network to be trained after being denoised and cut off, and the trained neural network can be applied to OTDR fault point judgment. According to the method, the fault pointjudgment problem of the OTDR is converted into the mode recognition of the neural network, and the position and type of the fault point are judged with high precision by using the mode recognition advantage of the neural network.

Description

technical field [0001] The invention provides an OTDR fault feature judgment method based on a differential evolution neural network, which is different from traditional fault judgment methods and can judge OTDR fault types with high precision, belonging to the field of power communication testing. Background technique [0002] At present, optical time domain reflectometer (OTDR) is widely used in optical fiber communication to judge faults such as fiber breakage. The signal is sampled and quantized to form the original data curve. And through the automatic judgment algorithm, find the fiber fault point from the curve. [0003] Currently widely used fault judgment algorithms include least square method, five-point method, wavelet algorithm and so on. Among them, the least square method and the five-point method are relatively easy to implement, but the accuracy is not high; while using the wavelet algorithm for processing, it is necessary to find a suitable threshold for e...

AI Technical Summary

Problems solved by technology

Among them, the least square method and the five-point method are relatively easy to implement, but the accuracy is not high; while using the wavelet algorithm for processing, it is necessary to find a suitable threshold for each curve to separate low-frequency components, which is not suitable for practical engineering applications. Use the wavelet algorithm to filter the data and other operations

Images