KR20220026915A - Apparatus for sensing leakage using image and sound and method thereof - Google Patents

Abstract

In accordance with one embodiment of the present invention, provided are an apparatus and method for detecting a leakage by using an image and a sound, capable of more accurately determining whether a leakage is true by primarily detecting an image variation area in which an image variation occurs based on an image signal and a sound signal, and secondarily detecting the generation of a sound signal due to a leakage in the image variation area. In accordance with one embodiment of the present invention, the apparatus for detecting a leakage by using an image and a sound includes: an image part acquiring an image signal about a leakage monitoring target; a sound part acquiring a sound signal about the leakage monitoring target; and a control part primarily analyzing an image variation area in which an image variation occurs over time by using the image signal and the sound signal acquired from the image part and the sound part, and then, secondarily analyzing the generation of a sound signal due to a leakage in the image variation area.

Description

Leak detection device and method using image and sound

The present invention relates to an apparatus and method for detecting a leak using an image and sound.

In domestic nuclear power plants, a leak monitoring system is installed and operated to detect leaks in the nuclear reactor system (safety system consisting of pressure vessels and pipes) at an early stage. In such a leak monitoring system, an acoustic emission (AE) sensor for detecting an acoustic wave generated when a nuclear reactor system leaks is distributed and installed on the system surface. In the leak monitoring system, when the AE sensor detects the seismic wave generated from the leaking part of the system surface, it analyzes the signal measured by the AE sensors to estimate the location of the leak. At this time, since the elastic wave propagated along the surface of the system structure due to the leakage has damping characteristics, it is not easy to accurately determine the authenticity of the leakage when the distance from the leakage location to the AE sensor is long. In addition, when leakage occurs in the system (area) where the AE sensor is not installed, there is a disadvantage in that it is not easy to monitor the leakage.

As a related prior art, Japanese Patent No. 3,295,682 discloses "a signal processing method of a pipe leakage location specification method".

Japanese Patent 3,295,682

According to an embodiment of the present invention, an image change region in which an image change occurs is primarily detected based on an image signal and an audio signal, and acoustic signal generation due to leakage is detected secondarily in the image change region to more accurately determine the authenticity of a leak. An object of the present invention is to provide an apparatus and method for detecting a leak using an image and sound.

In addition to the above problems, the embodiment according to the present invention may be used to achieve other problems not specifically mentioned.

A leak detection apparatus using an image and sound according to an embodiment of the present invention includes an image unit for acquiring an image signal for a leak monitoring object, a sound unit for acquiring a sound signal for a leak monitoring object, and an image unit and a sound unit from the and a control unit that primarily analyzes an image change region in which image change occurs over time using the acquired image signal and sound signal, and secondarily analyzes the sound signal generation due to leakage in the image change region.

)을 산출하는 단계, 누설 후보영역(

)을 산출하는 단계, 그리고 시간에 따라 변화하는 영상변화 영역에서 누설에 의한 음향이 발생하는지를 판별하고, 누설에 의한 음향 발생이면 누설발생을 경보하는 단계를 포함한다.On the other hand, the leak detection method using an image and sound according to an embodiment of the present invention includes the steps of acquiring an image signal and a sound signal of a leak monitoring object, and each of the image change region changing over time using the acquired image signal area representative (

), the leakage candidate area (

), and determining whether sound is generated due to leakage in an image change region that changes with time, and alerting the occurrence of leakage if sound is generated due to leakage.

One embodiment of the present invention is to improve the leakage monitoring function for pressure vessels and pipes by further determining whether an acoustic signal due to leakage occurs in the image change region where the image change occurs by using both the image signal and the sound signal. can have an effect.

1 is a view showing a leak detection apparatus using an image and sound according to an embodiment of the present invention.
2 is a flowchart illustrating a leak detection method using an image and sound according to an embodiment of the present invention.
3 is a flowchart illustrating a leak detection state using an image and sound according to an embodiment of the present invention.

With reference to the accompanying drawings, the embodiments of the present invention will be described in detail so that those of ordinary skill in the art to which the present invention pertains can easily implement them. The present invention may be embodied in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and the same reference numerals are used for the same or similar components throughout the specification. In addition, in the case of a well-known known technology, a detailed description thereof will be omitted.

Throughout the specification, when a part "includes" a certain element, it means that other elements may be further included, rather than excluding other elements, unless otherwise stated.

Hereinafter, an apparatus and method for detecting a leak using an image and sound will be described in detail with reference to the drawings.

1 is a diagram illustrating a leak detection apparatus using images and sounds according to an embodiment of the present invention, and FIG. 2 is a flowchart illustrating a leak detection method using images and sounds according to an embodiment of the present invention. And FIG. 3 is a flowchart showing a leak detection state using an image and sound according to an embodiment of the present invention. Referring to FIG. 1 , a leak detection device using an image and sound includes an image unit 100 , a sound unit 110 , a control unit 120 , a display unit 130 , and an alarm unit 140 , and includes an image signal and a sound signal. Based on , the image change region where the image change occurs is primarily detected, and the acoustic signal generation due to leakage is detected secondarily in the image change region, so that it is possible to easily determine the leakage of the leak monitoring object. Here, the leak monitoring object may include a high-temperature/low-temperature pressure vessel and a pipe.

The imaging unit 100 may include an image detection unit that acquires an image signal for a leak monitoring object. The image unit 100 may include a cam or CCTV for image acquisition.

The sound unit 110 may include a sound detection unit that acquires a sound signal for a leak monitoring object. The sound unit 110 may include three or more microphones. A plurality of acoustic units 110 may be installed at a distance from each other in an area where the leak monitoring object is located.

The control unit 120 first analyzes the image change region where the image change occurs over time using the image signal and the sound signal acquired from the image unit 100 and the sound unit 110, and The acoustic signal generation can be analyzed secondarily. The image signal and the sound signal respectively acquired through the image unit 100 and the sound unit 110 may be simultaneously acquired. The control unit 120 may include a microprocessor that performs overall control operations related to the detection and processing of the leak location of the leak monitoring object. The controller 120 may be connected to a general computer to share related information. The control unit 120 may include a separate memory unit. The memory unit may store information processed by the control unit 120 and related data for detecting and controlling a leak location of a leak monitoring object.

Meanwhile, the controller 120 may detect a leak component of the leak monitoring object to generate a leak position indication signal. The display unit 130 may display the leak location of the leak monitoring object based on the leak location indication signal. In addition, the control unit 120 may generate a leak location warning signal by detecting a leak component of the leak monitoring object. The alarm unit 140 may alert the leak location of the leak monitoring object based on the leak location alert signal.

As described above, it is possible to determine the authenticity of a leak of a leak monitoring object based on an image and a sound signal by using the leak detection apparatus using an image and sound according to an embodiment of the present invention. In other words, by using an acoustic signal in addition to the image signal to additionally determine whether an acoustic signal is generated due to leakage in the image change area where the image change has occurred, it has a function of monitoring leakage of pressure vessels and pipes and determining the authenticity compared to the existing method. can be improved

A detection method using a leak detection device using an image and sound according to an embodiment of the present invention will be described with reference to FIGS. 1 to 3 .

)와 음향신호(

)를 동시에 취득할 수 있다. 이때 t는 시간을 나타낸다.First, an audio signal and an image signal are obtained for a leak monitoring object using the image unit 100 and the sound unit 110 (S210). Here, by using the image unit 100 and the sound unit 110, an image signal (

) and sound signals (

) can be obtained simultaneously. In this case, t represents time.

)을 산출한다(S220). 고온/저온 압력 용기 및 배관에서 누설이 발생하는 경우, 온도차에 의하여 누설부위에서 증기나 가스형태의 누설이 발생할 수 있다. 이러한 누설이 발생하는 영역의 영상은 시간(t)에 따라 변화하므로, 수학식 1 내지 수학식 3을 이용하여 측정된 영상신호 (

)중 시간에 따라 변화하는 영상변화 영역을 확인할 수 있다.Using the acquired image signal, each region representative value (

) is calculated (S220). When leakage occurs in high/low temperature pressure vessels and piping, steam or gas leakage may occur in the leakage area due to the temperature difference. Since the image of the region where such leakage occurs changes with time (t), the image signal (

), you can check the image change area that changes with time.

))을 산출한다(S220).First, as in Equation 1, a representative value (

)) is calculated (S220).

[Equation 1]

: 2차원 합성곱,

; 2차원 합성곱에 적용되는 2차원 함수, 가우시안 함수 등 사용 가능,

와

: 촬영한 영상의 m번째 영역(m=1~M)의 좌표)(here,

: two-dimensional convolution,

; 2D function applied to 2D convolution, Gaussian function, etc. can be used,

Wow

: Coordinates of the mth area (m=1~M) of the captured image)

)을 산출하는 단계(S230)에서 각 영역의 대표값(

)에 대해 시간변화에 대한 각 영역의 대표값(

)의 변화값(

)을 수학식 3을 이용하여 산출하고 산출된 변화값이 수학식 4와 같이 설정값을 초과하는 경우 누설 후보영역(

)으로 판별할 수 있다.leakage candidate area (

) in the step (S230) of calculating the representative value (

), the representative value of each domain with respect to time change (

) change value (

) is calculated using Equation 3, and when the calculated change value exceeds the set value as in Equation 4, the leakage candidate area (

) can be identified.

[Equation 2]

[Equation 3]

[Equation 4]

, l=1~L)에 대응하는 영상 위치에 해당하는 사물을 인식하는 방법으로는 사물인식에 사용되는 컨볼루션 신경망(CNN ; Convolutional Neural Network)기법 등을 적용하여, 누설후보영역에 해당하는 사물이 안전계통과 같이 누설경보발생 대상물 인지를 판별하는 방법을 사용할 수 있다. 또한 안전계통과 같이 누설경보발생 대상물이 다른 구조물과 다른 색으로 구분되어 있는 경우에는 누설후보영역에 대응하는 영상 위치에 해당하는 사물이 누설경보발생 대상물에 해당하는 색상인지를 판별하는 방법을 사용할 수 있다.After the step of calculating the candidate leakage area, it may further include a leak alarm occurrence object confirmation step (S240) of recognizing an object corresponding to an image area that changes with time and determining whether the object is a safety system (leakage alarm occurrence object) can Here, the leakage candidate area (

, l = 1~L), by applying the convolutional neural network (CNN) technique used for object recognition, Like this safety system, it is possible to use a method to determine whether a leak alarm is generated. In addition, if the leak warning object is colored differently from other structures, such as in the safety system, a method of determining whether the object corresponding to the image location corresponding to the leak candidate area is the color corresponding to the leak warning object can be used. there is.

)를 이용하여 상호상관함수(

)를 산출하는 단계, 산출된 상호상관함수에 대한 시간지연-주파수 분석을 수행하여, 산출된 상호상관함수의 시간지연-주파수분석 결과(

)를 산출하는 단계, 그리고 산출된 시간지연-주파수분석 결과(

)에서 시간에 따라 변화가 큰 누설 후보영역(

)에 해당하는 시간지연(

와

)에 수직선형태로 표출되는 누설신호가 존재하는 경우 누설에 의한 음향 발생으로 판별하는 단계를 포함할 수 있다. 즉, 시간에 따라 변화가 큰 누설 후보영역(

, l=1~L)에서 누설에 의한 음향이 발생하는지를 판별하는 방법으로는 음향신호(

)에 대한 시간지연-주파수분석(Time delay-Frequency Analysis) 결과(

)에서 시간에 따라 변화가 큰 누설 후보영역(

)에 해당하는 시간지연(

와

)에 수직선형태로 표출되는 누설특징이 존재하는 경우 누설에 의한 음향 발생으로 판별할 수 있다. 이때

는 마이크로폰에서 측정된 음향신호(

,

)를 이용하여 산출된 상호상관함수(

)에 대한 시간지연-주파수분석 결과이다. 이때 3개의 마이크로폰을 한글자음"ㄴ"자 형태로 배치한 경우,

와

이며, C는 음속을 나타내고, d는 마이크로폰 사이의 거리를 나타낸다.Next, the control unit determines whether a sound due to leakage is generated in an image area having a large change over time, and generates an alarm when it is determined to be a leakage (S250). Here, the sound generation determination due to leakage is the sound signal (

) using the cross-correlation function (

), a time delay-frequency analysis of the calculated cross-correlation function is performed, and a time delay-frequency analysis result of the calculated cross-correlation function (

), and the calculated time delay-frequency analysis result (

) in the leakage candidate area (

) corresponding to the time delay (

Wow

), if there is a leakage signal expressed in the form of a vertical line, it may include the step of determining that the sound is generated by the leakage. That is, the leakage candidate area (

, l=1~L), the method for determining whether sound is caused by leakage is

) time delay-frequency analysis result (

) in the leakage candidate area (

) corresponding to the time delay (

Wow

), if there is a leakage characteristic expressed in the form of a vertical line, it can be determined as a sound generation due to leakage. At this time

is the sound signal measured by the microphone (

,

) calculated using the cross-correlation function (

) is the result of time delay-frequency analysis. At this time, if the three microphones are arranged in the shape of the Korean consonant "b",

Wow

, where C represents the speed of sound, and d represents the distance between the microphones.

)는 수학식 5를 이용하여 산출할 수 있다.cross-correlation function (

) can be calculated using Equation 5.

[Equation 5]

: 기대값,

: 시간지연)(here,

: expected value,

: time delay)

To determine leak authenticity, the user can use a method to visually check whether there is a component corresponding to the leak signal in the time delay-frequency conversion result. By using it, a method of determining through deep learning for time delay-frequency analysis images can be used.

As described above, the leak detection method using video and sound according to an embodiment of the present invention uses video signal and sound signal information together to detect leakage, compared to the technology for monitoring leakage occurrence of a leak monitoring object using only video signals. It is possible to determine precisely whether or not Accordingly, it is possible to improve the reliability of determining whether a leak has occurred or not with respect to a leak monitoring object.

In the leak monitoring method using the video signal, when a leak occurs in a high-temperature or low-temperature pressure vessel or pipe, the leaked high-temperature steam or low-temperature gas causes the image near the leakage point among the video signals to change (difference). It is possible to determine whether there is a leak by analyzing the video signal that is used for video). Using video signals, it is possible to monitor leaks from a distance in a non-contact manner. However, the leak monitoring method using an image signal has a disadvantage that structure vibration occurs, movement of other objects, or movement of a worker can be identified as leakage. That is, in the case of monitoring the leakage of the pressure vessel and pipe by detecting only the change (difference) of the video signal between the case of no leakage and the case of leakage, whether it is an image change due to leakage of the pressure vessel and pipe, vibration of the structure, or It cannot be determined whether the image is changed due to the movement of another object. Therefore, a more accurate leakage monitoring technology is required.

The leak detection apparatus and method using an image and sound according to an embodiment of the present invention uses an acoustic signal in addition to the image signal to additionally determine whether an acoustic signal due to leakage occurs in the image region where the image change has occurred. Compared to this, it is possible to improve the leakage monitoring and authenticity detection function for pressure vessels and pipes.

Although preferred embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements by those skilled in the art using the basic concept of the present invention as defined in the following claims are also provided. is within the scope of the

100 ; image unit 110 ; sound department
120 ; control unit 130 ; display
140 ; alert department

Claims (10)

An imaging unit that acquires an image signal for a leak monitoring object;
an acoustic unit for acquiring an acoustic signal for the leak monitoring object; and
A control unit that primarily analyzes an image change region where an image change occurs over time using the image signal and sound signal acquired from the image unit and the sound unit, and secondarily analyzes the sound signal generation due to leakage in the image change region
A leak detection device using an image and sound comprising a. In claim 1,
The control unit detects a leak component of the leak monitoring object to generate a leak position display signal, and based on the leak position display signal, the control unit further comprises a display unit for displaying the leak position of the leak monitoring object Leak using image and sound detection device. In claim 1,
The control unit detects a leak component of the leak monitoring object to generate a leak position warning signal, and based on the leak position alarm signal, the control unit further includes an alarm unit for alerting the leak position of the leak monitoring object Leak using image and sound detection device. acquiring the video signal and the sound signal of the leak monitoring object;
Using the acquired image signal, each region representative value (

) to calculate
leakage candidate area (

) to calculate, and
Determining whether sound is generated due to leakage in the image change area that changes with time, and alerting the occurrence of leakage if sound is generated due to leakage
A leak detection method using an image and sound comprising a. In claim 4,
The representative values of each area (

) is the following Equation 1:
[Equation 1]

(here,

: two-dimensional convolution,

; 2D function applied to 2D convolution, Gaussian function, etc. can be used,

Wow

: Coordinates of the mth area (m=1~M) of the captured image)
A leak detection method using the image and sound calculated using In claim 4,
The leakage candidate area (

) in the step of calculating the representative value (

), the representative value of each domain with respect to time change (

) change value (

), and if the calculated change value exceeds the set value, the leakage candidate area (

) leakage detection method using image and sound In claim 6,
the change value (

) is the following Equation 3:
[Equation 3]

A leak detection method using the image and sound calculated using In claim 4,
Determination of sound generation by the leakage
the sound signal (

) using the cross-correlation function (

) to calculate
Time delay-frequency analysis is performed on the calculated cross-correlation function, and the time delay-frequency analysis result of the calculated cross-correlation function (

) to calculate, and
Calculated time delay-frequency analysis result (

) in the leakage candidate area (

) corresponding to the time delay (

Wow

), when there is a leakage signal expressed in a vertical line form, determining that sound is generated due to leakage. In claim 8,
The cross-correlation function (

) is the following Equation 5:
[Equation 5]

(here,

: expected value,

: time delay)
A leak detection method using the image and sound calculated using In claim 4,
Leak detection method using image and sound further comprising the step of determining whether the object corresponding to the change area is a safety system after the step of calculating the candidate leakage area.

Images