Optical Line Fault Segment Estimation Using Multi-Point Signal Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating the location of abnormalities in optical transmission lines require expensive equipment or signal processing circuits, and machine learning-based methods suffer from decreased accuracy with increasing labels.
Innovation Solution
An abnormal section estimation method that divides the optical transmission line into sections at monitoring points, using optical signal monitors to extract signal data on a complex plane, which is input to trained models for accurate abnormality estimation without extensive calculation load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If dedicated equipment such as OTDR is used to estimate abnormality position, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent uses signal data from standard optical receivers (which are already deployed for communication) to create virtual measurements of abnormality positions. Instead of using dedicated OTDR equipment, the system copies and processes existing communication signals to extract diagnostic information, thereby achieving abnormality detection without additional specialized hardware.
Solution Approach 2:
The patent replaces the mechanical/optical measurement system (OTDR with physical light pulses) with a digital signal processing system. By substituting the physical measurement approach with digital processing of communication signals, the system eliminates the need for dedicated measuring equipment while maintaining diagnostic capability.
2Quantity of substance
If machine learning models estimate multiple section abnormalities simultaneously, then measurement completeness is improved, but manufacturing precision deteriorates
Solution Approach 1:
The patent divides the optical transmission line into multiple distinct sections with clear boundaries defined by monitoring points. Each section is independently analyzed by the machine learning model, allowing simultaneous estimation of multiple abnormalities while maintaining accuracy for each individual section through segmented processing.
Solution Approach 2:
The patent introduces spatial segmentation by dividing the transmission line into multiple sections along the distance dimension. This dimensional approach allows the system to estimate abnormalities at different positions simultaneously by processing signal data from multiple monitoring points, effectively adding a spatial dimension to the analysis.
3Quantity of substance
If more monitoring points are added to increase estimation coverage, then measurement completeness is improved, but device complexity increases
Solution Approach 1:
The patent makes the monitoring points serve dual functions: they are used both for normal communication signal routing and for abnormality detection. The same infrastructure components (optical fibers, receivers) perform both communication and diagnostic functions, eliminating the need for separate dedicated monitoring equipment at each point.
Solution Approach 2:
The system uses its own communication signals to perform self-diagnosis. The optical signals already transmitted for communication purposes are simultaneously used as probe signals for detecting abnormalities, allowing the system to monitor itself without external intervention or additional equipment.
Data Source
AI summary
Provided is an abnormal section estimation method in a system in which an optical transmitter and an optical receiver are connected by an optical transmission line, the optical transmission line being divided into a plurality of sections at one or more monitoring points from the optical transmitter to the optical receiver, the abnormal section estimation method including: extracting, based on an optical signal transmitted from the optical transmitter, signal data on a complex plane of the optical signal expressed by phase and amplitude at the one or more monitoring points; acquiring an abnormality estimation result of at least one of the plurality of sections by inputting the signal data extracted at the one or more monitoring points to trained models trained to receive the signal data as input and output the abnormality estimation result; and estimating a section where an abnormality has occurred based on the acquired abnormality estimation result.