Rail Fracture Detection Using DAS Signal Variation Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing rail fracture detection methods using vibration sensors are unreliable due to the need for sensors at every train passage point and interference from external vibrations, while distributed acoustic sensing (DAS) can fail to distinguish rail fractures from similar vibrations, especially during construction changes.

Innovation Solution

A rail fracture decision system utilizing DAS that sets up multiple measuring positions with a reference point and calculates vibration signal variations at specific frequency ranges to accurately detect rail fractures, minimizing external interference and requiring less frequent database updates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If vibration sensors are installed at every train passage point, then rail fracture detection coverage is improved, but device complexity and cost increase

Engineering Contradiction:
Improverail fracture detection coverageVSAvoidsensor installation complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent divides the rail into multiple sections with reference points and measuring positions, using a single sensor to sequentially monitor different segments as the train passes, replacing the need for continuous sensor coverage along the entire rail

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an optical cable as an intermediary element that runs alongside the rail, using DAS technology to detect vibrations at multiple positions without requiring physical sensors at each location, thus reducing installation complexity while maintaining detection coverage

Inventive Principle:
Principle #24Intermediary (Mediator)

2Device complexity

If DAS is used for rail fracture detection, then device complexity is reduced, but measurement precision decreases due to inability to distinguish rail fractures from similar vibrations

Engineering Contradiction:
Improvedetection system complexityVSAvoidfracture detection accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent segments the vibration signal analysis into multiple measuring positions along the rail, comparing signal characteristics at each position to distinguish rail fractures from other vibrations, thereby improving measurement precision while maintaining the simplicity of DAS technology

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements a decision-making process that analyzes vibration signals from multiple measuring positions and uses comparison logic to determine whether a rail fracture has occurred, providing feedback-based discrimination to enhance detection accuracy without increasing device complexity

Inventive Principle:
Principle #23Feedback

3Measurement precision

If vibration sensors are used, then measurement precision is maintained, but reliability decreases due to interference from external vibrations

Engineering Contradiction:
Improvevibration signal accuracyVSAvoiddetection reliability
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent extracts and compares vibration signal characteristics from multiple measuring positions, isolating the specific signal pattern indicative of rail fractures from external vibration interference by analyzing relative differences between positions

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent adds a spatial dimension to the analysis by measuring vibrations at multiple positions along the rail rather than at a single point, enabling differentiation between rail fractures and external vibrations through comparative analysis across the spatial dimension

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The system effectively decides rail fractures by using relative signal variations among multiple measuring positions, reducing false positives and negatives, and maintaining accuracy even with environmental vibrations, thus enhancing the reliability and efficiency of rail condition monitoring.

Implementation Method 1

DAS signals which are obtained by injecting light pulses into an optical fiber close to the railway tracks and measuring the Rayleigh backscatter

Methodology Applied
Scientific EffectRayleigh backscatter: Rayleigh Scattering

Implementation Method 2

The signal measuring part comprises vibration sensors configured to measure vibration signals at each of the measuring positions

Methodology Applied
Scientific EffectVibration: Vibration

Data Source

PatentEP3910301B1Rail fracture decision system and method for deciding rail fracture using the same
Publication Date: 2023.10.11 KOREA RAILROAD RESEARCH INSTITUTE
  • EP3910301B1 patent drawingFigure 1
  • EP3910301B1 patent drawingFigure 2
  • EP3910301B1 patent drawingFigure 3

AI summary

In a rail fracture decision system (10) and a method for deciding rail fracture using the rail fracture decision system (10). The rail fracture decision system (10) includes a measuring position setup part (100), a signal measuring part (200), a data processing part (300) and a decision part (400). The measuring position setup part (100) is configured to determine a plurality of measuring positions having a reference point, and the measuring positions are different from each other. The signal measuring part (200) is configured to measure vibration signals at each of the measuring positions, when a train passes through the measuring positions having the reference point. The data processing part (300) is configured to calculate a maximum value at a predetermined frequency range on the measured vibration signals. The decision part (400) is configured to calculate variation of the vibration signals at the measuring positions, based on the calculated maximum values, and to decide whether a rail is fractured at the reference point.