WO2022146341A1 - Procédé de détection et de suivi de véhicules ferroviaires à détection acoustique répartie - Google Patents

Procédé de détection et de suivi de véhicules ferroviaires à détection acoustique répartie Download PDF

Info

Publication number
WO2022146341A1
WO2022146341A1 PCT/TR2021/051390 TR2021051390W WO2022146341A1 WO 2022146341 A1 WO2022146341 A1 WO 2022146341A1 TR 2021051390 W TR2021051390 W TR 2021051390W WO 2022146341 A1 WO2022146341 A1 WO 2022146341A1
Authority
WO
WIPO (PCT)
Prior art keywords
track
observation
trace
alarm
tracks
Prior art date
Application number
PCT/TR2021/051390
Other languages
English (en)
Inventor
Mustafa AKUR
Mehmet Umut DEMİRÇİN
Lütfi Murat GEVREKCİ
Original Assignee
Aselsan Elektroni̇k Sanayi̇ Ve Ti̇caret Anoni̇m Şi̇rketi̇
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Aselsan Elektroni̇k Sanayi̇ Ve Ti̇caret Anoni̇m Şi̇rketi̇ filed Critical Aselsan Elektroni̇k Sanayi̇ Ve Ti̇caret Anoni̇m Şi̇rketi̇
Publication of WO2022146341A1 publication Critical patent/WO2022146341A1/fr

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D5/00—Mechanical means for transferring the output of a sensing member; Means for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for converting; Transducers not specially adapted for a specific variable
    • G01D5/26—Mechanical means for transferring the output of a sensing member; Means for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for converting; Transducers not specially adapted for a specific variable characterised by optical transfer means, i.e. using infrared, visible, or ultraviolet light
    • G01D5/32—Mechanical means for transferring the output of a sensing member; Means for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for converting; Transducers not specially adapted for a specific variable characterised by optical transfer means, i.e. using infrared, visible, or ultraviolet light with attenuation or whole or partial obturation of beams of light
    • G01D5/34—Mechanical means for transferring the output of a sensing member; Means for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for converting; Transducers not specially adapted for a specific variable characterised by optical transfer means, i.e. using infrared, visible, or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells
    • G01D5/353—Mechanical means for transferring the output of a sensing member; Means for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for converting; Transducers not specially adapted for a specific variable characterised by optical transfer means, i.e. using infrared, visible, or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells influencing the transmission properties of an optical fibre
    • G01D5/35338—Mechanical means for transferring the output of a sensing member; Means for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for converting; Transducers not specially adapted for a specific variable characterised by optical transfer means, i.e. using infrared, visible, or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells influencing the transmission properties of an optical fibre using other arrangements than interferometer arrangements
    • G01D5/35354—Sensor working in reflection
    • G01D5/35358—Sensor working in reflection using backscattering to detect the measured quantity
    • G01D5/35361—Sensor working in reflection using backscattering to detect the measured quantity using elastic backscattering to detect the measured quantity, e.g. using Rayleigh backscattering
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B61—RAILWAYS
    • B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
    • B61L1/00—Devices along the route controlled by interaction with the vehicle or train
    • B61L1/16—Devices for counting axles; Devices for counting vehicles
    • B61L1/163—Detection devices
    • B61L1/166—Optical
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
    • G01H9/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
    • G01H9/004—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means using fibre optic sensors

Definitions

  • the present invention is a method for detecting and tracking road-railway vehicles with distributed acoustic sensing using two stages as generation observation points with various pre-processing techniques, and JPDA-modified algorithm which fed with observations generated in first stage.
  • the offered DAS network comprises a plurality of interrogator units interrogating sensing fibres deployed along paths of interest to provide DAS sensors.
  • Targets are tracked at each of a plurality of tracker nodes of the DAS network, where each tracker node receives measurement signals from one or more DAS sensors and applies a tracking algorithm to track any targets in a respective tracker zone.
  • Each tracker node maintains, for each target, a tracking dataset of target properties for tracking that target.
  • the method involves identifying when a first target in a first tracker zone of a first tracker node is approaching a second tracker zone of a second tracker node and supplying from the first tracker node to the second tracker node a target descriptor for the first target.
  • the second tracker node uses the target descriptor to track any entry of the first target into the second tracker zone.
  • the application numbered EP3531078A1 relates to an evaluation unit for the evaluation of digital signals, a tracking system for tracking rail vehicles and a method for evaluating a digital signal.
  • the evaluation unit for the evaluation of digital signals comprises a connection to a digital data output of a distributed sensor for position sensing, and a comparator unit which is configured to receive a digital data signal provided by the distributed sensor, to compare the digital data signal with at least one predefined pattern and to provide a digital output signal.
  • the digital data signal (DS) comprises position information, and the digital output signal depends on the predefined pattern and on the digital data signal.
  • the application numbered CN1 10608760A presents a method for improving signal to noise ratio of disturbance detection of phase-sensitive optical time domain reflection sensing system.
  • the present invention is a method for detecting and tracking road-railway vehicles with distributed acoustic sensing using two stages as generation observation points with various pre-processing techniques, and JPDA-modified algorithm which fed with observations generated in first stage. Not only tracking multiple targets and preventing false alarms from the region of non-moving noise sources are possible with the presented method, but also target tracking could be continued in case of missing observations up to 10%.
  • Figure 1 shows a sample of visualized DAS data according to SNR values.
  • Figure 2 shows block diagram of detection and tracking algorithms.
  • Figure 3 shows block diagram of generation observation points.
  • Figure 4 shows block diagram of JPDA-modified algorithm which fed with observations generated in first stage shown in Figure 3.
  • Figure 5 shows the visualization of the performance of the overall algorithm for a record.
  • DAS Distributed Acoustic Sensing
  • FIG. 1 A sample of visualized DAS data according to SNR (Signal to Noise Ratio) values is given in Figure 1 .
  • SNR Signal to Noise Ratio
  • vehicle detection and tracking algorithms consists of two main stages. First one is generation observation points with various pre-processing techniques, and the second stage is fed to the modified-JPDA algorithm with the observations produced in the first stage.
  • a morphological expansion window of size N (may vary by site, sensor sensitivity, application) is applied.
  • N size morphological wear window is applied (combining with the previous step effectively applies morphological closure).
  • Observations produced first are most likely correlated to existing traces. Situations such as taking a single observation for multiple tracks (to model intersecting targets), taking no observations for any track (to model missing observations) are used when calculating the most probable matches. (To improve performance, a gating algorithm can be applied, that is, observations close to N1 of the track location can be used for each trace during association).
  • the state vectors of the tracks are updated and track scores are calculated. According to the calculated score, the tracks are either continued to be followed, a new vehicle alarm is given (alarm is generated for the track, the track becomes mature) or the track is removed from the tracking. o In mature (alarm-generated) traces, if the track score is lower than the threshold value set for unfollowing, the following control procedure is applied before unfollowing:
  • the allowable consecutive missing observation time is calculated by the formula C + R * (time elapsed since the start of the permit): where C is the constant specifying the time required for a trace to generate an alarm. R is a value between 0 and 1 .
  • the current trace density is calculated by taking the ratio of the total number of timesteps containing at least one observation associated with the current track to N.
  • the distance between the current position of the track and the starting position of the track must be greater than the L threshold (the track must be moving).
  • Figure 5 the visualization of the performance of the overall algorithm for a record is given.
  • the image in Figure 5 was obtained by mounting three images.
  • First image represents the binarized version of the SNR image seen in Figure 1 .
  • Middle image shows the result of observation generation part.
  • the white pixels in the middle image represent the points given as observations to the modified-JPDA algorithm.
  • In the rightmost image shows the result of tracks produced by the modified-JPDA algorithm (Algorithm is run from top to bottom on the data in the image). Pixels below the cross indicate mature (alarm generated) tracks, and white dots above the cross indicate immature (not yet alarm generated) tracks.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Mechanical Engineering (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
  • Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)

Abstract

La présente invention concerne un procédé de détection et de suivi de véhicules ferroviaires à détection acoustique distribuée à l'aide de deux étapes telles que la génération de points d'observation à l'aide de diverses techniques de prétraitement, et l'alimentation d'un algorithme modifié par JPDA avec des observations générées dans la première étape. Non seulement le suivi de multiples cibles et la prévention de fausses alarmes provenant de la région de sources de bruit non mobiles sont possibles grâce au procédé présenté, mais le suivi de la cible peut également être poursuivi en cas d'observations manquées jusqu'à 10 %.
PCT/TR2021/051390 2020-12-29 2021-12-10 Procédé de détection et de suivi de véhicules ferroviaires à détection acoustique répartie WO2022146341A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
TR2020/22238A TR202022238A1 (tr) 2020-12-29 2020-12-29 Karayolu ve demi̇ryolu taşitlari i̇çi̇n dağitik akusti̇k algilamali tespi̇t ve taki̇p yöntemi̇
TR2020/22238 2020-12-29

Publications (1)

Publication Number Publication Date
WO2022146341A1 true WO2022146341A1 (fr) 2022-07-07

Family

ID=80595166

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/TR2021/051390 WO2022146341A1 (fr) 2020-12-29 2021-12-10 Procédé de détection et de suivi de véhicules ferroviaires à détection acoustique répartie

Country Status (2)

Country Link
TR (1) TR202022238A1 (fr)
WO (1) WO2022146341A1 (fr)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3531078A1 (fr) * 2018-02-21 2019-08-28 Frauscher Sensortechnik GmbH Unité d'évaluation, système de poursuite et procédé pour évaluer un signal numérique

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3531078A1 (fr) * 2018-02-21 2019-08-28 Frauscher Sensortechnik GmbH Unité d'évaluation, système de poursuite et procédé pour évaluer un signal numérique

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
AKUR MUSTAFA ET AL: "Vehicle Tracking in Land Roads and Railways Using DAS Systems", 2020 28TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), IEEE, 5 October 2020 (2020-10-05), pages 1 - 4, XP033873435, DOI: 10.1109/SIU49456.2020.9302133 *
DEMARCO KEVIN J ET AL: "Tracking multiple fragmented objects with 2D imaging sonar", OCEANS 2016 MTS/IEEE MONTEREY, IEEE, 19 September 2016 (2016-09-19), pages 1 - 10, XP033014424, DOI: 10.1109/OCEANS.2016.7761260 *
WIESMEYR CHRISTOPH ET AL: "Real-Time Train Tracking from Distributed Acoustic Sensing Data", APPLIED SCIENCES, vol. 10, no. 2, 8 January 2020 (2020-01-08), pages 448, XP055781144, DOI: 10.3390/app10020448 *

Also Published As

Publication number Publication date
TR202022238A1 (tr) 2022-07-21

Similar Documents

Publication Publication Date Title
US10401199B2 (en) Tracking using distributed fibre optic sensing
CN108603785B (zh) 用于监视铁路网络的分布式光纤感测
US10377397B2 (en) Detection of anomalies in rail wheelsets
US11867541B2 (en) Distributed fibre optic sensing
CA2862362C (fr) Detection de la separation d'un train
AU2016344513A1 (en) Monitoring traffic flow
Papp et al. A real-time algorithm for train position monitoring using optical time-domain reflectometry
US11124211B2 (en) Methods and devices for locating a railway vehicle
US12116030B2 (en) Methods and systems for monitoring a transportation path with acoustic or vibration sensing
Timofeev et al. Multimodal heterogeneous monitoring of super-extended objects: modern view
JP2024516568A (ja) 光ファイバセンシングを用いたマッピング
WO2022146341A1 (fr) Procédé de détection et de suivi de véhicules ferroviaires à détection acoustique répartie
US20230339524A1 (en) Method for monitoring a railway track and monitoring system for monitoring a railway track
KR102676335B1 (ko) 철도의 선로 및 차량 모니터링 시스템
WO2023228299A1 (fr) Dispositif de détection de véhicule en déplacement, procédé de détection de véhicule en déplacement et support lisible par ordinateur non transitoire
KR102264039B1 (ko) 차량 탑재형 열차 지진 경보 시스템 및 방법
Litzenberger et al. Real-Time Train Wheel Defect Detection with Fiber Optic Acoustic Sensing
Corera Orzanco et al. Long-range traffic monitoring based on pulse-compression distributed acoustic sensing and advanced vehicle tracking and classification algorithm

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21863085

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21863085

Country of ref document: EP

Kind code of ref document: A1