KR20200075081A - Device for diagnosing core using cherenkov radiation image and method thereof - Google Patents

Abstract

The present invention relates to a device for diagnosing a core using a Cherenkov radiation image and a method thereof. The device for diagnosing a core comprises: a collection unit collecting an image of photographing a nuclear reactor from a camera mounted in a region near the nuclear reactor in real-time; a digital signal conversion unit converting the brightness and color difference of Cherenkov radiation included in the photographed image into a digital signal; and a core diagnosis unit diagnosing whether or not a core output of the nuclear reactor and an internal state of the core are normal in accordance with the digital signal.

Description

DEVICE FOR DIAGNOSING CORE USING CHERENKOV RADIATION IMAGE AND METHOD THEREOF}

Provided is a core diagnosis apparatus and method using a Cherenkov radiation image.

Reactor protection systems such as Hanaro are applied with design requirements such as multiplicity, diversity, and independence to maximize reliability. The control system also has design requirements such as multiplicity and independence applied to the implementation of some important functions to maximize the reliability of output control. Accordingly, various reactor output measurement devices enable safe protection of the reactor and output control.

The output of the Hanaro reactor is currently confirmed by heat output, neutron output, and gamma output. In the case of heat output, the response speed is very slow, and in the case of neutron output and gamma output, the response speed is very fast. In the case of a neutron output or gamma output measuring instrument, the measuring instrument itself can detect an instantaneous output change, but in the process of processing a measurement signal or output signal, a very short change may not be recorded. This is useful if there is a measuring device with a medium response speed.

In addition, it is necessary to secure a system capable of measuring abnormalities such as flow pipes and nuclear fuel inside the core, or a system capable of detecting changes in nuclear fuel after use.

On the other hand, in recent years, machine learning through neural networks has been applied to various fields as an advantage of improving the diversity and accuracy of pattern recognition through big data. Reactor-related fields are also being studied for monitoring cores using the neural network. As a related prior document, Korean Patent Registration No. 1,651,893 discloses a method for synthesizing an axial output distribution of a reactor core using a neural network circuit and a core monitoring system to which the method is applied.

Korean Registered Patent 1,651,893

One embodiment of the present invention is to diagnose a normal state or an abnormal state of a nuclear reactor core using a Cherenkov radiation.

One embodiment of the present invention is to more accurately diagnose the normal or abnormal state of the reactor core through deep learning.

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

The core diagnosis apparatus according to an embodiment of the present invention is a collection unit that collects in real time a captured image of a nuclear reactor from a camera mounted in a region near the nuclear reactor, and the brightness and color difference of the Cherenkov radiation included in the captured image as a digital signal. It includes a digital signal conversion unit for converting, and a core diagnosis unit for diagnosing whether the core output and the internal state of the nuclear reactor are normal according to the digital signal.

The diagnostic method of the core diagnostic apparatus according to an embodiment of the present invention includes the steps of photographing the radiation of the Cherenkov radiation emitted from the nuclear reactor through an interlocked camera, converting the radiation of the Cherenkov radiation in the captured image to an RGB histogram, RGB Converting the histogram into a digital signal, analyzing the core output of the nuclear reactor according to the digital signal and whether the internal state of the core is normal, and diagnosing the core based on the output of the analyzed reactor and whether the core is normal. Includes.

According to one embodiment of the present invention, by observing the reactor using the Cherenkov radiation observed according to the reactor output, it is also possible to observe the instantaneous output change due to the afterimage effect of light.

According to one embodiment of the present invention, by monitoring the reactor output through an image using a general digital camera, it is possible to monitor safe reactor operation at a low cost and secure maintenance convenience according to analysis of the core change.

According to an embodiment of the present invention, it is possible to quickly and accurately detect an abnormal state through deep learning of a nuclear fuel rod, a flow tube, a nuclear reactor component, and a nuclear fuel after use, as well as a core of the nuclear reactor as well as a nuclear reactor in which a Cherenkov radiation phenomenon is observed.

1 is an exemplary view showing a core diagnostic system according to an embodiment of the present invention.
2 is a block diagram showing a core diagnostic apparatus according to an embodiment of the present invention.
3 is a flowchart illustrating a diagnostic method of a core diagnostic apparatus according to an embodiment of the present invention.
4 is an exemplary view showing an RGB histogram according to an embodiment of the present invention.

The embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art to which the present invention pertains may easily practice. The present invention can be implemented in many different forms and is not limited to the embodiments described herein. In the drawings, parts not related to the description are omitted in order to clearly describe the present invention, and the same reference numerals are used for the same or similar elements throughout the specification. In the case of well-known technology, detailed description thereof will be omitted.

Throughout the specification, when a part “includes” a certain component, this means that other components may be further included rather than excluding other components unless specifically stated to the contrary.

1 is an exemplary view showing a core diagnostic system according to an embodiment of the present invention.

As shown in FIG. 1, the reactor 100 is a structure generated when nuclear fission is performed through a plurality of nuclear fuel rod bundles, and is composed of a moderator, a control rod, a coolant, and various other structures that control the nuclear reactor.

The reactor 100 represents an upper open reactor such as a Hanaro reactor.

On the other hand, when the reactor is a closed type, a camera must be installed inside the reactor generated from the reactor. In this case, it is difficult to shoot through a general digital camera due to the high temperature effect of the reactor, and a camera composed of special equipment is required.

Next, the core diagnosis apparatus 200 analyzes an image photographed in real time through the interlocked camera 300 to determine whether the core is in a normal or abnormal state.

The core diagnosis apparatus 200 collects an image of the Cherenkov radiation observed when the reactor 100 is started.

Here, the Cherenkov radiation is light generated when a charged particle passes through an optically transparent medium, and the particle speed is greater than the light velocity in the medium. The Cherenkov radiant light has a blue color, and the color difference and brightness of the Cherenkov radiant light are different depending on the output of the nuclear reactor.

Accordingly, the core diagnosis apparatus 200 may measure the output of the nuclear reactor according to the image of the Cherenkov radiation, and may diagnose one or more of the core state, the flow tube inside the core, or the state of nuclear fuel after use.

Accordingly, the core diagnosis apparatus 200 may continuously monitor one or more of the inside of the reactor core, the flow tube state of the reactor, the state of parts of the reactor, or spent nuclear fuel.

Next, the camera 300 represents a general 10 million pixel or more digital camera, and is installed in an area near the nuclear reactor. More specifically, the camera 300 may be installed above the upper open reactor or may be installed in a space in which a Cherenkov radiation is likely to occur in addition to an area near the reactor.

In addition, the camera 300 has a unique ID, and may store a real-time image or an image captured in a preset time unit in a separate database (not shown).

In addition, the camera 300 may be set and stored together with the unique ID and the location, function, pixel, setting conditions, and shooting conditions of the camera 300.

Although the camera 300 is illustrated as one in FIG. 1, a plurality of cameras may be installed to photograph the same nuclear reactor.

Meanwhile, the core diagnosis apparatus 200 may be a server, a terminal, or a combination of them.

The terminal is a device having a computational processing capability by providing a memory and a processor, respectively. For example, there are personal computers, handheld computers, personal digital assistants (PDAs), cell phones, smart devices, tablets, and the like.

The server is a processor in which a plurality of modules are stored, and a processor that is connected to the memory and reacts to a plurality of modules and processes service information provided to a terminal or action information for controlling service information, communication Means, and a user interface (UI) display means.

Memory is a device that stores information, such as high-speed random access memory (magnetic disk storage devices, flash memory devices, other non-volatile solid-state memory devices) It may include various types of memory, such as volatile memory.

The communication means transmits and receives service information or action information to the terminal in real time.

The UI display means outputs service information or action information of the system in real time. The UI display means may be an independent device that directly or indirectly outputs or displays the UI, or may be a part of the device.

Hereinafter, a core diagnosis apparatus for diagnosing whether the core state is normal by analyzing a captured image using FIG. 2 will be described.

2 is a block diagram showing a core diagnostic apparatus according to an embodiment of the present invention.

As shown in FIG. 2, the core diagnostic apparatus 200 includes a collection unit 210, a digital signal conversion unit 220, and a core diagnosis unit 230. The learning unit 240 may be further included.

First, the collection unit 210 collects the captured image in real time through communication with the camera 300 mounted in the region near the nuclear reactor. When a plurality of cameras are installed in the reactor, the collection unit 210 may collect images from each camera.

Next, the digital signal converter 220 converts the brightness and color difference of the Cherenkov radiation included in the captured image into a digital signal. The digital signal converter 220 may convert the captured image into an RGB histogram, and then convert the RGB histogram into a digital signal.

Next, the core diagnosis unit 230 diagnoses whether the core output and the internal state of the nuclear reactor are normal based on a digital signal.

At this time, the core diagnosis unit 230 may diagnose an abnormal state of the core by comparing the image with a normal state, and diagnose the state of the spent nuclear fuel.

For example, the core diagnosis unit 230 stores the image of the Cherenkov radiation light of the normal core or the digital signal based on the corresponding image, and stores the digital signal light as the big data in the image of the Cherenkov radiation light of the abnormal state or the corresponding image. In addition, it is possible to estimate and diagnose the state of the core by searching for an image having the highest similarity to the digital signal converted in real time.

In addition, the core diagnosis unit 230 may diagnose whether a core output and a core internal state of a nuclear reactor are normal according to a digital signal from an image photographed in real time through a learned neural network.

In addition, the learning unit 240 trains a neural network for estimating whether the internal signal of the reactor core is normal and the reactor output for the digital signal value of the Cherenkov radiation based on the previously stored learning data. The learning unit 240 performs deep learning through a deep neural network.

Here, the learning data includes a digital signal of the Cherenkov radiant light according to the output change and the core change from zero output to maximum output when the reactor is started. Accordingly, the learning unit 240 may learn and analyze in a settable output unit according to the state of Cherenkov.

In addition, the learning unit 240 may continuously train the neural network by using data according to the diagnosis result of the core diagnosis unit 230 as learning data.

Hereinafter, a method of diagnosing a core through a Cherenkov radiation of a nuclear reactor photographed with a digital camera will be described in detail with reference to FIGS. 3 and 4. At this time, a method of diagnosing the core using deep learning, which is one of methods for diagnosing the core, will be described.

3 is a flowchart illustrating a diagnostic method of a core diagnostic apparatus according to an embodiment of the present invention, and FIG. 4 is an exemplary view showing an RGB histogram according to an embodiment of the present invention.

As shown in FIG. 3, the core diagnostic apparatus 200 photographs the Cherenkov radiation emitted from the nuclear reactor through an interlocked camera 300 (S310).

The core diagnosis apparatus 200 may control the camera 300 installed in the region near the nuclear reactor to transmit a captured image by performing shooting in real time or at a set time. Then, the camera 300 may transmit an image of the nuclear reactor to the core diagnosis apparatus 200 and separately store it in a database.

Next, the core diagnosis apparatus 200 converts the radiation of Cherenkov from the captured image into an RGB histogram (S320).

The core diagnosis apparatus 200 may convert the captured image into an RGB histogram based on the amount of data according to the brightness level of the light.

4 shows an RGB histogram converted according to the reactor output value. The graphs in FIG. 4 show a function showing the number of pixels having the density level for each level of the density for the image, or a ratio for all the pixel numbers.

Accordingly, in the graphs of FIG. 4, the horizontal axis represents brightness, and the vertical axis represents data amount, that is, the amount of data having a corresponding brightness value. Therefore, as the value of the horizontal axis increases, the degree of brightness increases, and as the value of the vertical axis increases, the amount of data increases.

The graphs shown in FIG. 4 are graphs showing an RGB histogram showing the process up to the point at which the reactor starts up to the maximum output and ends the output of the reactor.

For example, FIG. 4(a) is a graph obtained by converting an image captured in a 0MW situation into a histogram before the reactor is started, and it can be seen that the values without the brightest value are the most. 4(b) is a situation in which the output of the reactor is 15MW, and many values with a large brightness value are displayed, and (c) is a situation in which the output of the reactor is 30MW, and the brightness level is close to 100%. You can see that it is dense.

FIG. 4(d) shows that the output of the reactor is 25 MW, and many values having a brightness level close to 100% were detected, but a number of values having a relatively low brightness level compared to FIG. 4(c) were also converted. Able to know. Next, FIG. 4(e) is a graph in which the degree of brightness has been uniformly converted to the time when the reactor is finished, and (f) is a graph that converts the situation after a certain time from the time when the reactor is started to a histogram. to be.

As described above, it can be seen that the characteristics of the histogram appear differently for each time point due to the radiation of the Cherenkov radiation emitted at the time when the reactor starts to output the maximum power and ends the output of the reactor. In particular, looking at (e) and (f) of FIG. 4, even after the use of the reactor is completed, the value of the degree of brightness can be checked due to the afterimage effect of light, so that the state of the reactor after the use is completed can be seen.

Next, the core diagnosis apparatus 200 converts the RGB histogram into a digital signal (S330).

The core diagnosis apparatus 200 may monitor the digital signal according to the Cherenkov radiation in real time.

Then, the core diagnosis apparatus 200 uses the training data to train the neural network (S340).

The neural network is an estimation of the reactor output for the digital signal value of the Cherenkov radiation, and whether the internal state of the core is normal, and represents deep learning formed by a deep neural network.

Here, the learning data represents a digital signal of the Cherenkov radiant light according to the output change and the core change according to the entire output of the nuclear reactor or the partial output of the nuclear fuel channel. The core diagnosis apparatus 200 may use the measured value of the reactor core for the total output value of the nuclear reactor, and the partial output value of the nuclear fuel channel may use the estimated value calculated through the core calculation program.

In addition, the learning data may include a digital signal of the Cherenkov radiation according to conditions such as a reactor core, a reactor flow tube, a reactor component, and a normal or abnormal state of nuclear fuel after use.

For example, the learning data may include a digital signal of the Cherenkov radiation measured under abnormal conditions, such as a situation in which a part of the nuclear fuel rod bundle is broken, a cooling passage is not normally operated, or a part of the passage is blocked.

In addition, after learning the neural network, the core diagnosis apparatus 200 may re-learn the neural network when the result of the learned neural network has a reliability lower than a threshold.

The core diagnosis apparatus 200 applies a digital signal acquired in real time to a pre-trained neural network and analyzes whether the reactor core output and the core internal state are normal (S350 ).

The core diagnosis apparatus 200 may analyze an abnormal state by comparing the normal state image and data and the real-time image and data through the learned neural network.

Here, the data represents data analyzed and compared through an image, and may further include reactor control data, reactor record data, inspection data, drive data of a device interlocked with the reactor, and the like. The core diagnosis apparatus 200 may analyze an abnormal state of a nuclear reactor core, and may analyze an abnormal state of a flow tube of a nuclear reactor, a nuclear reactor component, and spent nuclear fuel.

Next, the core diagnosis apparatus 200 diagnoses the core based on the analyzed output of the reactor and whether the core is normal (S360).

In addition, the core diagnosis apparatus 200 may diagnose whether the core state is a normal state or an abnormal state based on data analyzed through a neural network, and may also detect an abnormal state of a flow tube, a nuclear reactor component, and a nuclear fuel after use. Can be diagnosed. As described above, the core diagnosis apparatus 200 may check the core state of the nuclear reactor in real time through a digital signal according to the Cherenkov radiation, and an abnormal state type, an area estimated to be an abnormal state, and an abnormal state through a pre-trained neural network. The degree of condition can be diagnosed.

At this time, the core diagnosis apparatus 200 may be set to analyze the abnormal state of the core through the automatically trained neural network only when the monitored digital signal is outside the normal range or the effective range. These settings can be easily changed and designed by the user later.

In addition, when the abnormality condition is abnormal, the core diagnosis apparatus 200 may generate and provide a notification message, and transmit the notification message to an interworking administrator terminal.

Here, the notification message may include a type of an abnormal state, a device diagnosed as an abnormal state, a location of the corresponding device, and a detected time.

On the other hand, the core diagnosis apparatus 200 may analyze and diagnose that the state of the reactor core is normal or abnormal, and store the result in the database by linking the result of the reactor, the RGB histogram of the corresponding image, and a digital signal. In addition, the core diagnostic apparatus 200 may improve the reliability of the neural network by learning the neural network using the stored analysis and diagnostic data. The program for executing the method according to one embodiment of the present invention may be recorded on a computer-readable recording medium.

Computer-readable media may include program instructions, data files, data structures, or the like alone or in combination. The media may be specially designed and constructed, or may be known and usable by those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs, DVDs, magnetic-optical media such as floppy disks, and ROM, RAM, flash memory, etc. Hardware devices specifically configured to store and execute the same program instructions are included. Here, the medium may be a transmission medium such as an optical or metal line, a waveguide, or the like including a carrier wave that transmits a signal designating a program command, data structure, or the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, etc., as well as machine language codes produced by a compiler.

Although the 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 of those skilled in the art using the basic concepts of the present invention defined in the following claims are also provided. It belongs to the scope of rights.

100: reactor 200: core diagnostic device
210: collection unit 220: digital signal conversion unit
230: core diagnosis unit 240: learning unit
300: digital camera

Claims (14)

A collection unit that collects, in real time, the captured image of the nuclear reactor from a camera mounted in the vicinity of the nuclear reactor,
A digital signal conversion unit for converting the brightness and color difference of the Cherenkov radiation included in the captured image into a digital signal, and
A core diagnosis unit for diagnosing whether the core output of the nuclear reactor and the internal state of the nuclear reactor are normal according to the digital signal.
In claim 1,
The digital signal conversion unit,
A core diagnostic apparatus that converts the brightness and color difference of the Cherenkov radiation into RGB histograms and converts them into digital signals using the converted RGB histograms.
In claim 1,
The core diagnosis unit,
Monitor the digital signal according to the Cherenkov radiation to check the core state of the reactor in real time,
A core diagnosis apparatus for diagnosing the type of an abnormal state of the core, an area estimated to be an abnormal state, and the degree of the abnormal state.
In claim 1,
The core diagnosis unit,
A core diagnosis apparatus for diagnosing an abnormal condition of the core by comparing the normal state of the radiation signal of the Cherenkov with the radiation image of the Cherenkov taken in real time when the reactor is started.
In claim 1,
The collection unit,
Collecting a nuclear light image of Cherenkov in real time that has been used in the nuclear reactor,
The core diagnosis unit,
A core diagnostic apparatus for estimating the nuclear fuel state by comparing the Cherenkov radiant light image of normal nuclear fuel with the photographed Cherenkov radiant light image, and diagnosing an abnormal condition of the spent nuclear fuel.
In claim 1,
Based on the pre-stored learning data, further comprising a learning unit for learning a neural network for estimating the normality of the state inside the core and the reactor output for the digital signal value of the Cherenkov radiation,
The core diagnosis unit is a core diagnosis apparatus for diagnosing whether the core output and the internal state of the core are normal according to the digital signal through a previously learned neural network.
In claim 6,
The learning data,
A core diagnosis apparatus including a digital signal of a Cherenkov radiant light according to an output change and a core change from zero output to maximum output when the reactor is started.
In claim 6,
The learning data,
The reactor output value includes a total output value, which is a measured value of the reactor core, and a partial output value of a nuclear fuel channel, which is an estimated value calculated through a core calculation program.
In claim 6,
The learning unit,
A core diagnosis apparatus for continuously learning the neural network by using data according to the diagnosis result of the core diagnosis unit as learning data.
In claim 1,
The camera,
With a digital camera, a core diagnosis apparatus installed on the upper portion of the reactor and photographing the reactor.
Photographing the radiation of the Cherenkov radiation emitted from the nuclear reactor through a linked camera,
Converting the Cherenkov radiation from the captured image into an RGB histogram,
Converting the RGB histogram to a digital signal,
Analyzing whether the reactor core output and the core internal state are normal according to the digital signal, and
Diagnosing the core based on the analyzed output of the reactor and whether the core is normal,
Diagnostic method of the core diagnostic apparatus comprising a.
In claim 11,
Analyzing whether the reactor core output and the inner core state is normal,
A method of analyzing a core analysis device that compares and analyzes a steady state Cherenkov radiation image and a real-time Cherenkov radiation image with respect to the reactor core.
In claim 11,
Further comprising the step of learning the neural network by using the digital signal of the Cherenkov radiation according to the output change and the core change according to the total output of the nuclear reactor or the partial output of the nuclear fuel channel,
The analyzing step,
An analysis method of a core analysis apparatus that analyzes whether the core output and the core internal state of the nuclear reactor are normal by applying the digital signal to a previously learned neural network.
In claim 13,
The step of learning the neural network,
When the diagnosis of the nuclear reactor core is completed, an analysis method of the core analysis apparatus that stores related data in a database and uses the neural network as data for learning.

Images