KR102596045B1 - Leakage detection system through sound wave detection in optical cables - Google Patents

Leakage detection system through sound wave detection in optical cables Download PDF

Info

Publication number
KR102596045B1
KR102596045B1 KR1020200158801A KR20200158801A KR102596045B1 KR 102596045 B1 KR102596045 B1 KR 102596045B1 KR 1020200158801 A KR1020200158801 A KR 1020200158801A KR 20200158801 A KR20200158801 A KR 20200158801A KR 102596045 B1 KR102596045 B1 KR 102596045B1
Authority
KR
South Korea
Prior art keywords
water
water leak
unit
optical cable
control server
Prior art date
Application number
KR1020200158801A
Other languages
Korean (ko)
Other versions
KR20220071542A (en
Inventor
박석원
이일우
정구열
Original Assignee
주식회사 아리안
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 주식회사 아리안 filed Critical 주식회사 아리안
Priority to KR1020200158801A priority Critical patent/KR102596045B1/en
Publication of KR20220071542A publication Critical patent/KR20220071542A/en
Application granted granted Critical
Publication of KR102596045B1 publication Critical patent/KR102596045B1/en

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M3/00—Investigating fluid-tightness of structures
    • G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
    • G01M3/04—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point
    • G01M3/24—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using infrasonic, sonic, or ultrasonic vibrations
    • 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
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
    • G01F15/00—Details of, or accessories for, apparatus of groups G01F1/00 - G01F13/00 insofar as such details or appliances are not adapted to particular types of such apparatus
    • G01F15/06—Indicating or recording devices
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
    • G01L1/00—Measuring force or stress, in general
    • G01L1/02—Measuring force or stress, in general by hydraulic or pneumatic means
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A20/00—Water conservation; Efficient water supply; Efficient water use

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Fluid Mechanics (AREA)
  • Examining Or Testing Airtightness (AREA)

Abstract

본 발명은 광케이블 내부에 조사된 광의 산란파의 주파수를 분석하여 광섬유 케이블이 내설된 구간 내의 누수 여부를 판단하고, 누수데이터에 의해 생성된 기계 학습 알고리즘을 통해 상하수도관의 상태 정보를 판단할 수 있는 광케이블 내 음파감지를 통한 누수 탐지 시스템에 관한 것이다. 본 발명은 광케이블 내부에 조사된 광의 산란파의 주파수별 진폭의 평균값 및 최대값을 측정하여 누수 여부를 판단하되, 누수가 발생된 구간의 유량과 수압을 계측하여 실제로 누수가 되었는지 여부를 판단함으로서, 기존 광통신용 광케이블을 이용하여 별도의 센서 장비 없이 누수를 판단할 수 있는 이점이 있다. 또한, 본 발명은 누수데이터에 대한 특징 정보를 통해 기계 학습 알고리즘을 생성하고, 생성된 기계 학습 알고리즘을 통해 상하수도관의 상태 정보를 판단함으로서, 누수 및 상하수도관의 이상 상황을 예측할 수 있는 이점이 있다.The present invention is an optical cable that analyzes the frequency of the scattered waves of light irradiated inside the optical cable to determine whether there is water leakage in the section where the optical fiber cable is installed, and determines the status information of the water supply and sewage pipes through a machine learning algorithm generated by the water leakage data. This is about my water leak detection system using acoustic wave detection. The present invention determines whether there is a water leak by measuring the average value and maximum value of the amplitude at each frequency of the scattered wave of light irradiated inside the optical cable, and determines whether there has actually been a water leak by measuring the flow rate and water pressure in the section where the water leak occurred. There is an advantage in that water leakage can be determined without separate sensor equipment by using an optical cable for optical communication. In addition, the present invention has the advantage of predicting water leaks and abnormal situations in water and sewer pipes by generating a machine learning algorithm through characteristic information about water leak data and determining the status information of water and sewer pipes through the generated machine learning algorithm. .

Description

광케이블 내 음파감지를 통한 누수 탐지 시스템 {Leakage detection system through sound wave detection in optical cables}Leakage detection system through sound wave detection in optical cables}

본 발명은 광케이블 내 음파감지를 감지하여 누수를 탐지하는 시스템에 관한 것으로, 보다 상세하게는 광케이블 내부에 조사된 광의 산란파의 주파수를 분석하여 광섬유 케이블이 내설된 구간 내의 누수 여부를 판단하고, 누수데이터에 의해 생성된 기계 학습 알고리즘을 통해 상하수도관의 상태 정보를 판단할 수 있는 광케이블 내 음파감지를 통한 누수 탐지 시스템에 관한 것이다. The present invention relates to a system for detecting water leaks by detecting sound waves within an optical cable. More specifically, it analyzes the frequency of scattered waves of light irradiated inside the optical cable to determine whether there is water leakage within the section where the optical fiber cable is installed, and provides water leakage data. This is about a water leak detection system through sound wave detection within an optical cable that can determine the status information of water and sewage pipes through a machine learning algorithm created by .

누수란 상하수도 등의 관로에서 물이 새는 현상을 말한다. 누수가 시작되는 지점을 정확하게 탐지하는 것을 누수탐지라고 부르는데, 누수탐지는 크게 가정집, 빌라, 아파트 등의 건물 내부의 내부누수탐지와 건물외부, 공장, 창고 등의 외부누수탐지로 나눌 수 있다.Water leakage refers to the phenomenon of water leaking from pipes such as water supply and sewage. Accurately detecting the point where water leakage begins is called water leak detection. Water leak detection can be broadly divided into internal water leak detection inside buildings such as homes, villas, and apartments, and external water leak detection outside buildings, factories, and warehouses.

기존의 누수 탐지는 일반적으로 사용자가 직접 장비를 들고 이동하면서 누수 발생 탐지를 하는 방식으로 진행하기 때문에 작업 속도도 느리며, 작업자의 경험에 많은 부분을 의존해야 한다. 또한 누수 탐지의 정확도를 높이기 위해서는 물 사용이 적은 심야시간에 탐지를 해야 하기 때문에 작업에 어려움이 따른다. Existing water leak detection is generally carried out by the user carrying the equipment and moving around to detect water leaks, so the work speed is slow and requires a lot of dependence on the operator's experience. In addition, in order to increase the accuracy of water leak detection, detection must be done late at night when water use is low, making the work difficult.

종래의 수도관용 누수감지장치는 수도관의 누수시에 발생되는 수압강하를 검출하는 압력센서나 음향센서를 통해 수도관의 누수를 감지하는 방식이 주로 사용되고 있다. Conventional water leak detection devices for water pipes are mainly used to detect water pipe leaks through a pressure sensor or acoustic sensor that detects a drop in water pressure that occurs when a water pipe leaks.

이에 한국등록특허 제10-1406507호(이하 '선행문헌'이라 칭함)는 도관의 누수시에 발생되는 수압강하를 검출하는 압력센서와 수도관의 누수시에 발생되는 음파를 검출하는 음향센서가 함께 구비됨에 따라 수도관의 누수 여부가 정확하면서도 신속하게 감지될 수 있도록 한 음향/압력 복합센서를 구비한 상수도관용 누수감지장치에 관한 것이다. 선행문헌은 수도관의 누수시에 발생되는 수압강하를 검출하는 압력센서와 수도관의 누수시에 발생되는 음파를 검출하는 음향센서가 함께 구비됨에 따라 수도관의 미미한 누수 여부까지도 정확하면서도 신속하게 감지될 수 있는 장점이 있다.Accordingly, Korean Patent No. 10-1406507 (hereinafter referred to as 'prior document') is equipped with a pressure sensor that detects the water pressure drop that occurs when a water pipe leaks and an acoustic sensor that detects sound waves that occur when a water pipe leaks. As a result, the present invention relates to a water leak detection device for water pipes equipped with a sound/pressure composite sensor that can accurately and quickly detect water leaks in water pipes. Previous literature suggests that even minor water leaks in water pipes can be accurately and quickly detected by providing a pressure sensor that detects the drop in water pressure that occurs when a water pipe leaks and an acoustic sensor that detects sound waves that occur when a water pipe leaks. There is an advantage.

선행문헌은 압력센서와 음향센서를 모두 사용하여 수도관의 누수를 측정하고 있으나, 음향센서나 압력센서 중 어느 하나가 누수로 판단하지 않을 경우, 누수의 진위 여부를 판단하는데 어려움이 발생된다. 단순히 2개의 센서를 구비함에 따라 누수 감지 성능이 뛰어나다고 할수 만은 없다.Prior literature measures water pipe leaks using both pressure sensors and acoustic sensors, but if either the acoustic sensor or the pressure sensor does not determine that there is a water leak, it becomes difficult to determine whether the water leak is genuine. It cannot be said that water leak detection performance is excellent simply because it has two sensors.

이에 한국등록특허 제10-1406507호(발명의 명칭 : 음향/압력 복합센서를 구비한 상수도관용 누수감지장치, 등록일 : 2014.06.03)Accordingly, Korean Patent No. 10-1406507 (Title of invention: Water leak detection device for water pipes with sound/pressure composite sensor, Registration date: 2014.06.03)

본 발명은 위와 같은 문제점을 해결하기 위해 광케이블 내부에 조사된 광의 산란파의 주파수별 진폭의 평균값 및 최대값을 측정하여 누수 여부를 판단하되, 누수가 발생된 구간의 유량과 수압을 계측하여 실제로 누수가 되었는지 여부를 판단하는데 그 목적이 있다. In order to solve the above problem, the present invention determines whether there is a water leak by measuring the average value and maximum value of the amplitude for each frequency of the scattered wave of light irradiated inside the optical cable, and measures the flow rate and water pressure in the section where the water leak occurs to determine whether the water leak actually occurs. The purpose is to determine whether or not it has been done.

또한, 본 발명은 누수데이터에 대한 특징 정보를 통해 기계 학습 알고리즘을 생성하고, 생성된 기계 학습 알고리즘을 통해 상하수도관의 상태 정보를 판단하는데 그 목적이 있다.In addition, the purpose of the present invention is to generate a machine learning algorithm through characteristic information about water leakage data and determine the status information of water and sewage pipes through the generated machine learning algorithm.

본 발명의 광케이블 내부에 광을 조사하고, 외부 이벤트에 의해 발생된 산란파를 수신하여 분포형음파센싱부, 및 기 설정된 알고리즘을 통해 상기 산란파의 주파수를 분석하여 상기 광케이블이 내설된 구간 내의 누수 여부를 판단하는 누수판단부를 포함하는 음향측정부와 상수도의 유량과 수압을 계측하는 센서부와 상기 음향측정부에 의해 누수가 발생된 구간이 식별되면, 상기 센서부를 통해 상기 누수가 발생된 구간의 유량과 수압을 계측하여 실제로 누수가 되었는지 여부를 판단하는 관제서버를 포함함한다. Light is irradiated inside the optical cable of the present invention, and scattered waves generated by external events are received, and the frequency of the scattered waves is analyzed through a distributed sound wave sensing unit and a preset algorithm to determine whether there is water leakage in the section where the optical cable is installed. When a section in which water leakage occurs is identified by an acoustic measuring unit that includes a water leak determination unit and a sensor unit that measures the flow rate and water pressure of the water supply, and the acoustic measuring unit, the flow rate of the section in which the water leak occurred is determined through the sensor unit. It includes a control server that measures water pressure and determines whether there is actually a water leak.

본 발명의 상기 음향측정부는 상기 산란파의 주파수성분을 분석하는 주파수분석부, 설정된 시간에 대한 주파수별 진폭의 평균값 및 최대값을 측정하는 진폭측정부, 및 상기 측정된 진폭의 최대값이 기 설정된 수치보다 높거나, 상기 최대값이 상기 평균값보다 임계치 이상인지 여부를 판단하는 판단부, 및 상기 관제서버에 의해 실제 누수가 된것으로 판단되지 않으면, 상기 기 설정된 알고리즘을 수정하는 알고리즘수정부를 포함한다. The acoustic measurement unit of the present invention includes a frequency analysis unit that analyzes the frequency component of the scattered wave, an amplitude measurement unit that measures the average value and maximum value of the amplitude for each frequency for a set time, and the maximum value of the measured amplitude is a preset value. It includes a determination unit that determines whether or not the maximum value is greater than a threshold value than the average value, and an algorithm modification unit that modifies the preset algorithm if it is not determined by the control server that there is an actual water leak.

본 발명의 상기 관제서버는 실제 누수가 된것으로 판단되면, 상기 누수데이터를 저장하는 데이터저장부, 상기 누수데이터에 대한 특징 정보를 추출하는 특징정보추출부, 상기 추출된 특징정보를 통해 기계 학습 알고리즘을 생성하는 알고리즘생성부, 및 상기 생성된 기계 학습 알고리즘을 통해 상기 광케이블이 내설된 구간 내의 상태 정보를 판단하는 인공지능판단부를 포함한다.If it is determined that there is an actual water leak, the control server of the present invention includes a data storage unit for storing the water leak data, a feature information extraction unit for extracting feature information about the leak data, and a machine learning algorithm using the extracted feature information. It includes an algorithm generation unit that generates, and an artificial intelligence determination unit that determines state information within a section where the optical cable is installed through the generated machine learning algorithm.

본 발명의 상기 특징정보추출부는 상기 누수데이터의 주파수성분을 분석하여 주파수 영역을 식별하는 주파수영역식별부, 및 상기 주파수 영역에 기 설정된 필터를 적용하고, 각 주파수의 대역별 세기를 측정하여 상기 주파수 영역의 고유한 특징을 추출하는 주파수특징추출부를 포함한다.The feature information extraction unit of the present invention includes a frequency domain identification unit that analyzes the frequency component of the water leak data to identify the frequency domain, and a preset filter is applied to the frequency domain, and the intensity of each frequency band is measured to determine the frequency domain. It includes a frequency feature extraction unit that extracts unique features of the region.

본 발명의 상기 관제서버는 상기 구간 내의 누수 및 상기 상태정보가 비정상인 것으로 판단되면, 상기 누수 및 비정상 상태에 대한 이벤트정보를 외부 단말기로 전송한다. If the control server of the present invention determines that water leakage and the status information in the section are abnormal, it transmits event information about the water leak and abnormal status to an external terminal.

본 발명은 광케이블 내부에 조사된 광의 산란파의 주파수별 진폭의 평균값 및 최대값을 측정하여 누수 여부를 판단하되, 누수가 발생된 구간의 유량과 수압을 계측하여 실제로 누수가 되었는지 여부를 판단함으로서, 기존 광통신용 광케이블을 이용하여 별도의 센서 장비 없이 누수를 판단할 수 있는 이점이 있다. The present invention determines whether there is a water leak by measuring the average value and maximum value of the amplitude at each frequency of the scattered wave of light irradiated inside the optical cable, and determines whether there has actually been a water leak by measuring the flow rate and water pressure in the section where the water leak occurred. There is an advantage in that water leakage can be determined without separate sensor equipment by using an optical cable for optical communication.

또한, 본 발명은 누수데이터에 대한 특징 정보를 통해 기계 학습 알고리즘을 생성하고, 생성된 기계 학습 알고리즘을 통해 상하수도관의 상태 정보를 판단함으로서, 누수 및 상하수도관의 이상 상황을 예측 및 모니터링할 수 있는 이점이 있다.In addition, the present invention generates a machine learning algorithm through characteristic information about water leak data, and determines the status information of water and sewer pipes through the generated machine learning algorithm, thereby predicting and monitoring water leaks and abnormal situations in water and sewer pipes. There is an advantage.

도 1은 광케이블 내부에 광을 조사하여 상수관로의 누수를 탐지하는 방식을 설명하기 위한 도면이다.
도 2는 본 발명에 따른 광케이블 내 음파감지를 통한 누수 탐지 시스템의 구성도이다.
도 3은 본 발명에 따른 음향신호를 통한 누수감지 및 기계 학습 알고리즘 생성방법을 설명하기 위한 플로우챠트이다.
도 4는 본 발명에 따른 산란파의 주파수를 분석하여 누수를 판단하는 알고리즘이다.
도 5는 Cepstrum 분석을 나타내는 도면이다.
도 6은 본 발명에 따른 기계 학습 알고리즘을 기반으로 하는 누수 탐지 방법을 설명하기 위한 플로우챠트이다.Figure 1 is a diagram for explaining a method of detecting a water leak in a water pipe by irradiating light inside an optical cable.
Figure 2 is a configuration diagram of a water leak detection system through detection of sound waves in an optical cable according to the present invention.
Figure 3 is a flow chart to explain the method for detecting water leaks and generating a machine learning algorithm through acoustic signals according to the present invention.
Figure 4 is an algorithm for determining water leakage by analyzing the frequency of scattered waves according to the present invention.
Figure 5 is a diagram showing Cepstrum analysis.
Figure 6 is a flow chart to explain a water leak detection method based on a machine learning algorithm according to the present invention.

이하, 본 발명의 바람직한 실시 예에 대하여 첨부된 도면을 참조하여 상세히 설명하기로 한다. 본 발명의 실시 예를 설명함에 있어서 관련된 공지 기술에 대한 구체적인 설명이 본 발명의 요지를 불필요하게 흐릴 수 있다고 판단되는 경우에 그 상세한 설명을 생략하기로 한다. Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the attached drawings. In describing embodiments of the present invention, if it is determined that a detailed description of related known technologies may unnecessarily obscure the gist of the present invention, the detailed description will be omitted.

도 1은 광케이블 내부에 광을 조사하여 상수관로의 누수를 탐지하는 방식을 설명하기 위한 도면이다. 도 1을 참조하면, 본 발명은 분포형음파센싱(DAS : Distributed Acoustic Sensing) 계측 기술을 통해 상수관로 근접 및 교차구간의 발생하는 미세한 누수를 감지할 수 있다. 분포형음파센싱부(100)는 광케이블 (200)내로 광선을 조사한다. 광케이블(200)에 인접한 곳에서 소리 등의 이벤트가 발생되면, 광케이블(200)에 변형이 가해지며, 조사된 광의 산란이 변경된다. 산란파는 이벤트에 따라 서로 다른 성격을 가지며, 분포형음파센싱부(100)는 반사된 산란파를 측정/처리한다.Figure 1 is a diagram for explaining a method of detecting a water leak in a water pipe by irradiating light inside an optical cable. Referring to Figure 1, the present invention can detect minute water leaks that occur in proximity to and intersections of water pipes through Distributed Acoustic Sensing (DAS) measurement technology. The distributed sound wave sensing unit 100 radiates light into the optical cable 200. When an event such as a sound occurs near the optical cable 200, strain is applied to the optical cable 200, and the scattering of the irradiated light is changed. Scattered waves have different characteristics depending on the event, and the distributed sound wave sensing unit 100 measures/processes the reflected scattered waves.

도 2는 본 발명에 따른 광케이블 내 음파감지를 통한 누수 탐지 시스템의 구성도이다. Figure 2 is a configuration diagram of a water leak detection system through sound wave detection in an optical cable according to the present invention.

도 2를 참조하면, 음향측정부(1000)는 상수도관의 누수를 측정하기 위해 복수개(n)로 구성될 수 있으며, 음향측정부(1000)는 측정된 누수감지이벤트와 energy/trace 정보를 관제서버(2000)로 전송한다. 음향측정부(1000)는 분포형음파센싱부(100)와 누수판단부(110)으로 구성될 수 있다. 분포형음파센싱부(100)에 의해 측정된 산란파는 MEC(Mobile Edge Computing)를 기반으로 누수판단부(120)로 전송된다. 누수판단부(120)는 기 설정된 알고리즘을 통해 산란파의 주파수를 분석하여 광케이블(200)이 내설된 구간 내의 누수 여부를 판단한다. 누수를 판단하는 알고리즘은 후술하도록 한다.Referring to FIG. 2, the acoustic measurement unit 1000 may be composed of a plurality (n) to measure water leaks in water pipes, and the acoustic measurement unit 1000 controls the measured water leak detection event and energy/trace information. It is transmitted to the server (2000). The acoustic measurement unit 1000 may be composed of a distributed sound wave sensing unit 100 and a water leak determination unit 110. The scattered waves measured by the distributed sound wave sensing unit 100 are transmitted to the water leak determination unit 120 based on MEC (Mobile Edge Computing). The water leak determination unit 120 analyzes the frequency of the scattered wave using a preset algorithm to determine whether there is water leakage within the section where the optical cable 200 is installed. The algorithm for determining water leakage will be described later.

관제서버(2000)는 센서부(3000)로부터 누수가 발생된 구간의 유량과 수압을 계측정보를 수신하며, 실제로 누수가 발생되었는지 여부를 판단한다.The control server 2000 receives measurement information on the flow rate and water pressure in the section where the water leak occurred from the sensor unit 3000, and determines whether the water leak has actually occurred.

센서부(3000)는 상수도관의 유량과 수압을 계측하기 위한 유량계실(310), 유량계실(310)에서 계측된 유량과 수압의 정보를 수집하기 위한 센서정보수집부(320), 유량과 수압정보를 관제서버(2000)로 전송하기 위한 센서통신부(330)를 포함할 수 있다. The sensor unit 3000 includes a flow meter room 310 for measuring the flow rate and water pressure of a water pipe, a sensor information collection unit 320 for collecting information on the flow rate and water pressure measured in the flow meter room 310, and a flow rate and water pressure. It may include a sensor communication unit 330 for transmitting information to the control server 2000.

관제서버(2000)는 실제 누수가 된것으로 판단되면, 누수데이터를 데이터저장부(210)에 저장한다. 특정정보추출부(220)는 누수데이터에 대한 기계 학습 알고리즘을 생성하기 위한 특징 정보를 추출한다. 특징정보는 Spectrogram, MFCC 등이 활용될 수 있으며, 주파수성분을 분석하여 주파수 영역을 식별하는 주파수영역식별부와 주파수 영역에 기 설정된 필터를 적용하고, 각 주파수의 대역별 세기를 측정하여 주파수 영역의 고유한 특징을 추출하는 주파수특징추출부를 포함할 수 있다.If it is determined that there is an actual water leak, the control server 2000 stores the water leak data in the data storage unit 210. The specific information extraction unit 220 extracts feature information to create a machine learning algorithm for water leak data. Spectrogram, MFCC, etc. can be used as feature information, and a frequency domain identification unit that identifies the frequency domain by analyzing frequency components and a preset filter are applied to the frequency domain, and the intensity of each frequency band is measured to identify the frequency domain. It may include a frequency feature extraction unit that extracts unique features.

알고리즘생성부(230)는 추출된 특징정보를 통해 기계 학습 알고리즘을 생성하며, Train Model외 Gaussian Mixture Model (GMM), Hidden Markov Model(HMM), Naive Bayes (NB), Restricted Boltzmann Machine (RBM), Thompson Sampling과 같은 알고리즘이 적용될 수 있다.The algorithm generator 230 generates a machine learning algorithm through the extracted feature information, and includes Train Model, Gaussian Mixture Model (GMM), Hidden Markov Model (HMM), Naive Bayes (NB), Restricted Boltzmann Machine (RBM), Algorithms such as Thompson Sampling can be applied.

인공지능판단부(240)는 생성된 기계 학습 알고리즘을 통해 광케이블(200)이 내설된 구간 내의 상태를 판단한다. The artificial intelligence judgment unit 240 determines the state within the section where the optical cable 200 is installed through the generated machine learning algorithm.

서버통신부(250)는 누수 및 상수도관의 상태정보에 대한 이벤트정보를 외부 단말기로 전송한다. The server communication unit 250 transmits event information about water leaks and status information of water pipes to an external terminal.

한편, 관제서버(2000)에 의해 실제 누수가 된것으로 판단되지 않으면, 음향측정부(1000)는 기 설정된 알고리즘을 수정한다.Meanwhile, if the control server 2000 does not determine that there is an actual water leak, the acoustic measurement unit 1000 modifies the preset algorithm.

도 3은 본 발명에 따른 음향신호를 통한 누수감지 및 기계 학습 알고리즘 생성방법을 설명하기 위한 플로우챠트이다.Figure 3 is a flow chart to explain the method for detecting water leaks and generating a machine learning algorithm through acoustic signals according to the present invention.

도 3을 참조하면, 음향측정부(1000)는 광케이블(200)에 광신호를 조사하여 실시간으로 누수를 계측한다(S1010). 음향측정부(1000)는 기 설정된 알고리즘을 통해 반사되어 수신된 산란판의 주파수를 분석하여 누수를 감지한다(S1030). Referring to FIG. 3, the acoustic measurement unit 1000 measures water leakage in real time by irradiating an optical signal to the optical cable 200 (S1010). The acoustic measurement unit 1000 detects water leakage by analyzing the frequency of the reflected and received scattering plate through a preset algorithm (S1030).

도 4는 본 발명에 따른 산란파의 주파수를 분석하여 누수를 판단하는 알고리즘이다. 도 4를 참조하면. 음향측정부(1000)는 분포형음파센싱(DAS : Distributed Acoustic Sensing) 계측 기술을 통해 산란파의 DAS 데이터(1600 samples/sec)를 수집한다(S410). 음향측정부(1000)의 주파수영역식별부는 퓨리에변환(FFT)를 통해 시간 영역(time domain)으로 표현된 산란파를 주파수 영역(Frequency domain)으로 변환한다(S420). 퓨리에변환(FFT)에 의해 산란파가 Spectrum으로 표현되면, 가로축의 단위는 주파수가 되고, 세로축의 단위는 데시벨(dB)이 된다. 따라서 산란파의 Spectrum을 통해 각 주파수대의 강도를 dB단위로 확인할 수 있다.Figure 4 is an algorithm for determining water leakage by analyzing the frequency of scattered waves according to the present invention. Referring to Figure 4. The acoustic measurement unit 1000 collects DAS data (1600 samples/sec) of scattered waves through distributed acoustic sensing (DAS) measurement technology (S410). The frequency domain identification unit of the acoustic measurement unit 1000 converts the scattered wave expressed in the time domain into the frequency domain through Fourier transform (FFT) (S420). When scattered waves are expressed as a spectrum by Fourier Transform (FFT), the unit on the horizontal axis is frequency, and the unit on the vertical axis is decibel (dB). Therefore, the intensity of each frequency band can be confirmed in dB through the spectrum of the scattered wave.

진폭측정부는 산란파의 Spectrum을 통해 1분(60s)간 주파수별 진폭의 평균값을 계산한다(S430). 이는 진폭값이 일정하게 유지 되지 않는 주파수를 상쇄하기 위함이다. The amplitude measurement unit calculates the average value of the amplitude for each frequency for 1 minute (60s) through the spectrum of the scattered wave (S430). This is to offset frequencies whose amplitude values do not remain constant.

판단부는 측정된 진폭의 최대값이 기 설정된 수치(100Hz)보다 높거나, 최대값이 평균값보다 임계치 이상인지 여부를 판단((max / avg) > 임계치)한다.The determination unit determines whether the maximum value of the measured amplitude is higher than a preset value (100 Hz) or whether the maximum value is greater than the average value or a threshold value ((max / avg) > threshold).

임계치의 경우, 통상적으로 최한시(매일 하루중 01~04시로, 물사용량이 가장 적은 시간대)의 한달 정도의 평균 데이터를 기준으로 선정한다. 수집되는 데이터를 학습 및 통계화하여 해당 시간대의 데이터를 축척하며, 축척된 데이터가 기준 데이터 대비 일정 수준 이상을 넘어서는지 여부와, 기간 등을 고려하여 임계치를 설정한다. 일 예로, 기준 데이터 대비 20%이상, 48시간과 같이 임계치를 설정할 수 있을 것이며, 이는 관리자에 의해 변경 설계 가능한 사항이다. In the case of the threshold, it is usually selected based on the average data of about a month at the lowest hour (01 to 04 o'clock every day, the time when water use is lowest). The collected data is learned and statisticized to accumulate the data in the relevant time period, and the threshold is set by considering whether the accumulated data exceeds a certain level compared to the standard data and the period. As an example, a threshold may be set such as 20% or more of the standard data and 48 hours, and this can be changed and designed by the administrator.

Spectrum은 중요한 정보를 모두 담고 있지만, 그 값의 범위가 일정하지 않은 문제가 있음에 따라 spectrum 신호 전체를 균일하게 시각화하기 위한 Cepstrum 분석을 실시한다. Spectrum contains all important information, but there is a problem with the range of values being inconsistent, so Cepstrum analysis is performed to uniformly visualize the entire spectrum signal.

도 5는 Cepstrum 분석을 나타내는 도면이다. 도 5와 같이, Spectrum 신호의 로그값에 역퓨리에 변환(IFF)을 하면 Cepstrum이 된다. 로그함수는 두 개의 곱으로 형성된 함수를 합으로 분리하여 낼 수 있음에 따라, 주파수 영역으로 변환된 신호의 크기와 위상을 분리할 수 있다.Figure 5 is a diagram showing Cepstrum analysis. As shown in Figure 5, when inverse Fourier transform (IFF) is performed on the logarithmic value of the spectrum signal, it becomes Cepstrum. Since the logarithmic function can be produced by dividing a function formed by the product of two by the sum, the magnitude and phase of the signal converted to the frequency domain can be separated.

다시 도 3을 살펴보면, 음향측정부(1000)는 누수가 감지되면, 관제서버(2000)로 누수감지이벤트를 전송한다(S1030). 관제서버(2000)는 누수감지이벤트가 수신되면, 센서부(3000)로 유량/수압 계측 정보를 요청한다(S1050). 센서부(3000)는 실시간으로 유량/수입을 계측하되(S1020), 관제서버(2000)로부터 전송된 요청신호에 따라 실시간 유량/수압 계측정보를 관제서버(2000)로 전송한다(S1060).Looking at Figure 3 again, when a water leak is detected, the acoustic measurement unit 1000 transmits a water leak detection event to the control server 2000 (S1030). When a water leak detection event is received, the control server 2000 requests flow rate/water pressure measurement information from the sensor unit 3000 (S1050). The sensor unit 3000 measures flow/water pressure in real time (S1020) and transmits real-time flow/water pressure measurement information to the control server 2000 according to a request signal transmitted from the control server 2000 (S1060).

관제서버(2000)는 수신된 유량/수압 계측정보를 통해 실제로 누수가 되었는지 여부를 판단한다(S1070). 관제서버(2000)에 의해 실제로 누수가 되지 않은것으로 판단되면, 음향측정부(1000)는 누수를 판단하는 알고리즘을 수정한다(S1080). The control server 2000 determines whether there is actually a water leak through the received flow rate/water pressure measurement information (S1070). If it is determined by the control server 2000 that there is no actual water leak, the acoustic measurement unit 1000 modifies the algorithm for determining water leakage (S1080).

반면, 관제서버(2000)는 실제 누수가 된것으로 판단되면, 누수데이터를 데이터저장부(210)에 저장한다(S1090). 관제서버(2000)는 누수데이터에 대한 기계 학습 알고리즘을 생성하기 위한 특징 정보를 추출한다(S1100). 관제버(2000)는 추출된 특징정보를 통해 기계 학습 알고리즘을 생성한다(S1120).On the other hand, if the control server 2000 determines that there is an actual water leak, it stores the water leak data in the data storage unit 210 (S1090). The control server (2000) extracts feature information to create a machine learning algorithm for water leak data (S1100). The control server 2000 generates a machine learning algorithm using the extracted feature information (S1120).

이하 도 6을 통해 본 발명에 따른 기계 학습 알고리즘을 기반으로 하는 누수 탐지 방법을 설명한다. 도 6을 살펴보면, 음향측정부(1000)는 광케이블(200)에 광신호를 조사하여 실시간으로 누수를 계측한다(S2010). 음향측정부(1000)는 산란판의 주파수를 분석하여 누수를 감지한다(2020). 음향측정부(1000)는 누수가 감지되면, 1차 누수감지정보를 관제서버(2000)로 전송한다(S2020). 관제서버(2000)는 1차적으로 누수 의심을 예측(S2030)하며, 센서부(3000)로 유량/수압 계측 정보를 수신받는다(S2040). 관제서버(2000)는 수신된 유량/수압 계측정보를 통해 실제로 누수가 된것으로 판단하면, 기계 학습 알고리즘을 통해 1차적으로 상수도관의 상태를 예측한다(S2050). 관제서버(2000)는 1차 누수 의심 및 비정상 상태 및 누수 계측 정보를 시각화한다(S2060). Hereinafter, a water leak detection method based on a machine learning algorithm according to the present invention will be described with reference to FIG. 6. Referring to Figure 6, the acoustic measurement unit 1000 measures water leakage in real time by irradiating an optical signal to the optical cable 200 (S2010). The acoustic measurement unit 1000 detects water leakage by analyzing the frequency of the scattering plate (2020). When a water leak is detected, the acoustic measurement unit 1000 transmits primary water leak detection information to the control server 2000 (S2020). The control server 2000 initially predicts a suspected water leak (S2030) and receives flow/water pressure measurement information from the sensor unit 3000 (S2040). If the control server 2000 determines that there is an actual water leak through the received flow rate/water pressure measurement information, it primarily predicts the state of the water pipe through a machine learning algorithm (S2050). The control server (2000) visualizes the first suspected water leak, abnormal status, and water leak measurement information (S2060).

음향측정부(1000)는 1차 누수 의심을 예측한 이후, 소정 시간이 지나면, 일 예시로 익일 동일한 시간대(일반적으로 물 사용이 적은 심야시간)에 2차적으로 누수를 계측한다. 음향측정부(1000)는 2차적으로 누수 감지가 예측되면, 2차 누수감지정보를 관제서버(2000)로 전송한다(S2070). 관제서버(2000)는 2차적으로 누수 의심을 예측(S2080)하며, 센서부(3000)로 유량/수압 계측 정보를 재수신한다(S2090). 관제서버(2000)는 수신된 유량/수압 계측정보를 통해 실제로 누수가 된것으로 재판단하면, 기계 학습 알고리즘을 통해 2차적으로 상수도관의 상태를 예측한다(S2100). 관제서버(2000)는 2차 누수 의심 및 비정상 상태 및 누수 계측 정보를 시각화한다(S2110). After predicting the suspicion of a primary water leak, the acoustic measurement unit 1000 measures the water leak a second time, for example, at the same time the next day (generally late at night when water use is low) after a predetermined time has elapsed. When secondary water leak detection is predicted, the acoustic measurement unit 1000 transmits secondary water leak detection information to the control server 2000 (S2070). The control server (2000) secondarily predicts a suspected water leak (S2080) and re-receives flow/water pressure measurement information from the sensor unit (3000) (S2090). If the control server (2000) determines that there is an actual water leak based on the received flow/water pressure measurement information, it secondarily predicts the state of the water pipe through a machine learning algorithm (S2100). The control server (2000) visualizes secondary water leak suspicion, abnormal conditions, and water leak measurement information (S2110).

관제서버(2000)는 누수 의심 및 비정상 상태에 대한 이벤트 정보를 외부단말기(4000)로 전송한다(S2120). 여기서 외부단말기(4000)는 누수가 발생되는 현장을 탐사하는 관리자의 단말기를 의미하며, 외부단말기(4000)는 수신된 이벤트 정보를 통해 누수가 발생된 상수도관의 정보를 확인한다(S2130). 관리자는 누수가 발생된 상수도관의 현장을 방문하여 누수에 대한 조치를 취한다(S2140). 누수 조치가 완료되며, 외부단말기(4000)는 누수 조치 알림을 관제서버(2000)로 전송한다(S2150).The control server 2000 transmits event information about suspected water leaks and abnormal conditions to the external terminal 4000 (S2120). Here, the external terminal 4000 refers to the terminal of the manager who explores the site where the water leak occurs, and the external terminal 4000 checks information on the water pipe where the water leak occurred through the received event information (S2130). The manager visits the site of the water pipe where the leak occurred and takes action against the water leak (S2140). The water leak action is completed, and the external terminal (4000) transmits a water leak action notification to the control server (2000) (S2150).

관제서버(2000)는 수신된 누수 조치 알림에 따라 누수된 상수도관이 정비된 것으로 판단하고, 누수 이벤트를 종료한다(S2160).The control server 2000 determines that the leaking water pipe has been repaired according to the received water leak action notification and ends the water leak event (S2160).

본 발명을 활용한 누수 감시시스템은 IWA(International Water Association)에서 추천된 지표인 누수평가지표(ILI : Infrastructure Leakage Index) 4단계 등급 중 B등급 이상의 평가를 받기 위해 누수 감지정확도를 10개 이상 자체 누수탐지 검증하였으며, 상수도사업본부와 함께 추가 10개 이상의 누수 탐지를 통해 80%이상의 누수 감지정확도를 확보한 만큼 우수한 누수 감시능력을 가지고 있다.The water leak monitoring system using the present invention has a leak detection accuracy of 10 or more to receive a rating of B or higher out of the 4 levels of the Infrastructure Leakage Index (ILI), which is an indicator recommended by the International Water Association (IWA). The detection has been verified, and it has excellent water leak monitoring capabilities as it has secured more than 80% water leak detection accuracy by detecting more than 10 additional water leaks in cooperation with the Waterworks Business Headquarters.

누수평가지표(ILI)는 연간 실질손실량 (CARL : Current Annual volume of Real Losses)과 허용손실량 (UARL : Unvoidable Annual Real Losses)의 비율로 아래와 같이 계산된다. Leakage Assessment Index (ILI) is calculated as the ratio of Current Annual Volume of Real Losses (CARL) and Unvoidable Annual Real Losses (UARL) as follows.

CARL(ML/year)은 상수도관로에서 실제로 발생하는 누수량을 나타내며, UARL(ML/year)은 관로에서 발생하는 이론적 최소 누수량을 나타낸다.CARL (ML/year) represents the amount of water leakage that actually occurs in a water supply pipe, and UARL (ML/year) represents the theoretical minimum amount of water leakage that occurs in a water pipe.

누수평가지표(ILI)는 다른 상수도관로와 비교할 수 있도록 개발된 지표이므로 WBI(World Bank Institute)에서는 Banding system을 만들어 ILI를 기준으로 4단계로 등급을 나누고 관로를 평가하고 있다. The Leakage Assessment Index (ILI) is an indicator developed to allow comparison with other water supply pipes, so the World Bank Institute (WBI) created a banding system to grade pipes into four levels based on ILI.

본 발명은 2019년10월부터 2020년12월까지 과학기술정보통신부와 한국정보화진흥원이 지원하고, 대구광역시 상수도사업본부가 주관(참여기업 : 주식회사 아리안)하여 국가인프라 지능정보화 사업에 의해 추진되는 “DAS 및 IoT 기반 스마트 상수도 통합관리체계 구축” 과제에 의한 성과물이다.This invention is supported by the Ministry of Science and ICT and the National Information Society Agency from October 2019 to December 2020, and hosted by the Daegu Metropolitan City Waterworks Business Headquarters (participating company: Ariane Co., Ltd.) and promoted by the national infrastructure intelligent informatization project. This is the outcome of the project “Establishing a smart water supply integrated management system based on DAS and IoT.”

1000 : 음향측정부 2000 : 관제서버
3000 : 센서부 4000 : 외부단말기1000: Sound measurement unit 2000: Control server
3000: Sensor unit 4000: External terminal

Claims (6)

광케이블 내부에 광을 조사하고, 외부 이벤트에 의해 발생된 산란파를 수신하는 분포형음파센싱부 및 기 설정된 알고리즘을 통해 상기 산란파의 주파수를 분석하여 상기 광케이블이 내설된 구간 내의 누수 여부를 판단하는 누수판단부를 포함하는 음향측정부; 상수도관의 유량과 수압을 실시간으로 계측하는 센서부; 및 상기 음향측정부에 의해 누수가 발생된 구간이 식별되면, 상기 센서부를 통해 상기 누수가 발생된 구간의 유량과 수압을 계측하여 실제로 누수가 되었는지 여부를 판단하고, 누수데이터로부터 추출된 특징정보를 통해 기계 학습 알고리즘을 생성하는 알고리즘생성부를 구비하는 관제서버;를 포함하되,
상기 음향측정부는 상기 산란파의 주파수성분을 분석하는 주파수분석부;
상기 설정된 시간에 대한 주파수별 진폭의 평균값 및 최대값을 측정하는 진폭측정부; 및
상기 측정된 진폭의 최대값이 기 설정된 수치보다 높거나, 상기 최대값이 상기 평균값보다 임계치 이상인지 여부를 판단하는 판단부;와
상기 관제서버에 의해 실제 누수가 된것으로 판단되지 않으면, 상기 알고리즘생성부에서 생성한 상기 알고리즘을 수정하는 알고리즘수정부;를 포함하고,
상기 음향측정부의 실시간 누수 계측을 통하여 누수가 감지되면 1차 누수감지정보를 상기 관제서버로 전송하며, 상기 관제서버는 상기 기계 학습 알고리즘을 이용하여 상기 상수도관의 상태를 예측하며 누수 계측 정보를 시각화하며,
상기 음향측정부는 상기 1차 누수감지정보를 상기 관제서버로 전송한 다음, 물 사용이 적은 최한시에 2차 누수여부를 다시 계측하되,
상기 임계치는 상기 2차 누수여부를 일정기간 계측하여 축적한 평균데이터를 기준으로 산정하는 것을 특징으로 하는 광케이블 내 음파감지를 통한 누수 탐지 시스템.
A distributed sound wave sensing unit that irradiates light inside the optical cable and receives scattered waves generated by external events, and analyzes the frequency of the scattered waves through a preset algorithm to determine whether there is water leakage in the section where the optical cable is installed. An acoustic measurement unit including a unit; A sensor unit that measures the flow rate and water pressure of the water pipe in real time; And when the section where water leakage occurred is identified by the acoustic measurement unit, the flow rate and water pressure of the section where water leakage occurred are measured through the sensor unit to determine whether there was actually a water leak, and the characteristic information extracted from the water leakage data is measured. Includes a control server having an algorithm generator that generates a machine learning algorithm through,
The acoustic measurement unit includes a frequency analysis unit that analyzes frequency components of the scattered wave;
An amplitude measuring unit that measures the average and maximum values of amplitude for each frequency for the set time; and
A determination unit that determines whether the maximum value of the measured amplitude is higher than a preset value or whether the maximum value is greater than a threshold value than the average value; and
If it is not determined by the control server that there is an actual water leak, an algorithm modification unit that modifies the algorithm generated by the algorithm generation unit,
When a water leak is detected through real-time water leak measurement of the acoustic measurement unit, primary water leak detection information is transmitted to the control server, and the control server uses the machine learning algorithm to predict the state of the water pipe and visualize the water leak measurement information. And
The acoustic measurement unit transmits the primary water leak detection information to the control server and then measures the secondary water leak again at the shortest time when water use is low.
A water leak detection system through sound wave detection in an optical cable, wherein the threshold is calculated based on average data accumulated by measuring the secondary water leak over a certain period of time.
 삭제delete 삭제delete 제1항에 있어서,
상기 관제서버는 실제 누수가 된것으로 판단되면, 상기 누수데이터를 저장하는 데이터저장부;
상기 누수데이터에 대한 특징 정보를 추출하는 특징정보추출부; 및
상기 생성된 기계 학습 알고리즘을 통해 상기 광케이블이 내설된 구간 내의 상태 정보를 판단하는 인공지능판단부;를 포함하는 것을 특징으로 하는 광케이블 내 음파감지를 통한 누수 탐지 시스템
According to paragraph 1,
If it is determined that there is an actual water leak, the control server includes a data storage unit that stores the water leak data;
a feature information extraction unit that extracts feature information about the water leak data; and
An artificial intelligence judgment unit that determines status information within the section where the optical cable is installed through the generated machine learning algorithm; a water leak detection system through sound wave detection in the optical cable, comprising:
 제4항에 있어서,
상기 특징정보추출부는 상기 누수데이터의 주파수성분을 분석하여 주파수 영역을 식별하는 주파수영역식별부; 및
상기 주파수 영역에 기 설정된 필터를 적용하고, 각 주파수의 대역별 세기를 측정하여 상기 주파수 영역의 고유한 특징을 추출하는 주파수특징추출부;를 포함하는 것을 특징으로 하는 광케이블 내 음파감지를 통한 누수 탐지 시스템
According to paragraph 4,
The feature information extraction unit includes a frequency domain identification unit that identifies a frequency domain by analyzing frequency components of the water leakage data; and
Water leak detection through sound wave detection in the optical cable, comprising: a frequency feature extraction unit that applies a preset filter to the frequency domain and measures the intensity of each frequency band to extract unique features of the frequency domain; system
 제4항에 있어서,
상기 관제서버는 상기 구간 내의 누수 및 상기 상태정보가 비정상인 것으로 판단되면, 상기 누수 및 비정상 상태에 대한 이벤트정보를 외부 단말기로 전송하는 것을 특징으로 하는 광케이블 내 음파감지를 통한 누수 탐지 시스템


According to paragraph 4,
When the control server determines that water leakage and the status information in the section are abnormal, the control server transmits event information about the water leak and abnormal status to an external terminal. A water leak detection system through sound wave detection in an optical cable.
KR1020200158801A 2020-11-24 2020-11-24 Leakage detection system through sound wave detection in optical cables KR102596045B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020200158801A KR102596045B1 (en) 2020-11-24 2020-11-24 Leakage detection system through sound wave detection in optical cables

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020200158801A KR102596045B1 (en) 2020-11-24 2020-11-24 Leakage detection system through sound wave detection in optical cables

Publications (2)

Publication Number Publication Date
KR20220071542A KR20220071542A (en) 2022-05-31
KR102596045B1 true KR102596045B1 (en) 2023-10-31

Family

ID=81780700

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020200158801A KR102596045B1 (en) 2020-11-24 2020-11-24 Leakage detection system through sound wave detection in optical cables

Country Status (1)

Country Link
KR (1) KR102596045B1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114963030A (en) * 2022-06-21 2022-08-30 杭州水务数智科技股份有限公司 Water supply pipeline monitoring method

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190331513A1 (en) * 2016-06-16 2019-10-31 Hifi Engineering Inc. Method of estimating flowrate in a pipeline

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101406507B1 (en) 2014-03-17 2014-06-11 아이에스테크놀로지 주식회사 Acoustic/pressure complex sensing apparatus for detecting leakage of water pipe

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190331513A1 (en) * 2016-06-16 2019-10-31 Hifi Engineering Inc. Method of estimating flowrate in a pipeline

Also Published As

Publication number Publication date
KR20220071542A (en) 2022-05-31

Similar Documents

Publication Publication Date Title
Sevillano et al. DYNAMAP–Development of low cost sensors networks for real time noise mapping
Tejedor et al. Toward prevention of pipeline integrity threats using a smart fiber-optic surveillance system
CN106442720B (en) A kind of acoustic shock type track bridge health monitoring device, system and method
Guo et al. Leakage detection in water distribution systems based on time–frequency convolutional neural network
Can et al. Capturing urban traffic noise dynamics through relevant descriptors
Abou Rjeily et al. Flood forecasting within urban drainage systems using NARX neural network
CN102606891B (en) Water leakage detector, water leakage detecting system and water leakage detecting method
CN109654384A (en) Pipeline leakage testing device and detection method based on PSO-VMD algorithm
KR20190018293A (en) Diagnosis method for Detecting Leak of Water Supply Pipe using Deep Learning by Acoustic Signature
US20140311245A1 (en) Pipe inspection system and related methods
CN102235575A (en) Data processing method and system for checking pipeline leakage
US10386261B2 (en) High repetition rate thermometry system and method
KR102596045B1 (en) Leakage detection system through sound wave detection in optical cables
Gong et al. Detection of emerging through-wall cracks for pipe break early warning in water distribution systems using permanent acoustic monitoring and acoustic wave analysis
WO2021254632A1 (en) Event model training using in situ data
Lopez-Ballester et al. Enabling real-time computation of psycho-acoustic parameters in acoustic sensors using convolutional neural networks
CN111520615A (en) Pipe network leakage identification and positioning method based on line spectrum pair and cubic interpolation search
CN110332466A (en) Water supply line leak detection method based on distribution type fiber-optic sonic transducer
CN112098939B (en) Method and device for identifying and evaluating noise pollution source
El-Zahab et al. Development of a clustering-based model for enhancing acoustic leak detection
CN1808087A (en) Digital and intelligent method for positioning and detecting water leakage of underground pipeline and instrument therefor
CN109933933B (en) Noise treatment method and equipment
CN116186642B (en) Distributed optical fiber sensing event early warning method based on multidimensional feature fusion
CN115479219B (en) Intelligent pipeline state monitoring method, monitoring device and intelligent pipeline system
Wu et al. Novel signal denoising approach for acoustic leak detection

Legal Events

Date Code Title Description
E902 Notification of reason for refusal
AMND Amendment
E601 Decision to refuse application
AMND Amendment
X701 Decision to grant (after re-examination)
GRNT Written decision to grant