KR-20260065191-A - Method for estimating impact location of loose parts in reactor coolant system

KR20260065191AKR 20260065191 AKR20260065191 AKR 20260065191AKR-20260065191-A

Abstract

The present invention relates to a method for training and utilizing a neural network model to estimate the impact location of a metal foreign substance inside a reactor coolant system (RCS). A method for estimating the impact location of a metal fragment according to one embodiment of the present invention comprises the steps of collecting impact signals from a plurality of sensors installed on the outer surface of the reactor coolant system, converting each of the collected impact signals into spectrograms, and training a neural network model by setting each of the converted spectrograms and the impact location on the inner surface of a hemispherical head of the reactor coolant system as a training dataset, wherein the impact location is defined by a three-dimensional Cartesian coordinate system.

Inventors

오현석
최정식
오정민

Assignees

광주과학기술원

Dates

Publication Date: 20260508
Application Date: 20241101

Claims (15)

A step of collecting impact signals from a plurality of sensors installed on the outer surface of the Reactor Coolant System (RCS); A step of converting each of the collected impact signals into a spectrogram; and The method includes the step of training a neural network model by setting each of the above-described converted spectrograms and the impact location on the inner surface of the hemispherical head of the coolant system as a training dataset, The above impact location is defined by a three-dimensional Cartesian coordinate system Method for estimating the location of metal fragment impact.
In paragraph 1, The above plurality of sensors are acceleration sensors. Method for estimating the location of metal fragment impact.
In paragraph 1, At least one of the plurality of sensors is installed on the outer surface of the hemispherical head. Method for estimating the location of metal fragment impact.
In paragraph 1, The above coolant system is a steam generator Method for estimating the location of metal fragment impact.
In paragraph 1, The above-mentioned converting step includes the step of converting each impact signal into a two-dimensional spectrogram on the time-frequency axis, wherein The pixel value of the spectrogram corresponds to the intensity of the impact signal. Method for estimating the location of metal fragment impact.
In paragraph 1, The above-mentioned transforming step includes the step of transforming each impulse signal into a Wigner-Ville distribution and transforming the Wigner-Ville distribution into a two-dimensional spectrogram on the time-frequency axis. Method for estimating the location of metal fragment impact.
In paragraph 1, The above hemispherical head is the upper head or lower head of the above coolant system Method for estimating the location of metal fragment impact.
In paragraph 1, The above training step includes the step of supervising the neural network model by setting each spectrogram as an input to the neural network model and the impact location as an output to the neural network model. Method for estimating the location of metal fragment impact.
In paragraph 1, The above impact location is a position converted from a spherical coordinate system to a three-dimensional Cartesian coordinate system. Method for estimating the location of metal fragment impact.
In Paragraph 9, The position according to the above spherical coordinate system is In this case, the impact position is defined as (x, y, z) according to the following [Equation 1] [Mathematical Formula 1] (Here, r is the radius of the hemispherical head, is the elevation angle, is the azimuth angle Method for estimating the location of metal fragment impact.
In paragraph 1, The above training step includes the step of training the neural network model by further setting fragment mass as a training dataset. Method for estimating the location of metal fragment impact.
In Paragraph 11, The above training step includes the step of supervising the neural network model by setting each spectrogram as an input to the neural network model and setting the impact location and fragment mass as outputs to the neural network model. Method for estimating the location of metal fragment impact.
In paragraph 1, A step of collecting target impact signals from the plurality of sensors; A step of converting each of the collected target impact signals into a target spectrogram; and The method further includes the step of inputting each of the transformed target spectrograms into the learned neural network model to identify the predicted impact location. Method for estimating the location of metal fragment impact.
In Paragraph 13, The step of identifying the predicted impact location includes the step of converting the 3D Cartesian coordinates output from the neural network model into a spherical coordinate system to identify the predicted impact location. Method for estimating the location of metal fragment impact.
In Paragraph 13, The above-mentioned identifying step includes the step of inputting each target spectrogram into the learned neural network model to further identify the expected fragment mass. Method for estimating the location of metal fragment impact.

Description

Method for estimating impact location of loose parts in reactor coolant system The present invention relates to a method for training and utilizing a neural network model to estimate the impact location of metallic foreign matter inside a reactor coolant system (RCS). The Loose Part Monitoring System (LPMS) is a system that prevents system damage by acquiring and analyzing impact signals caused by metallic foreign objects inside the reactor coolant system (RCS) and estimating the presence, location, and mass of the metallic foreign objects, and is operated in most nuclear power plants. Although LPMS currently features some automation in signal analysis, expert judgment is required to determine the presence and location of metallic foreign objects. Furthermore, there is a problem in that field experts face very high levels of fatigue due to relevant regulations requiring the assessment of the impact location and the extent of damage caused by the impact within 72 hours of the impact occurring. In addition, the tremendous noise and vibration generated in the coolant system during the operation of the reactor act as noise in the signal analysis of the LPMS, causing a decrease in the accuracy of the analysis. Accordingly, there is a need for a method that can estimate the location of metallic foreign objects with high accuracy without expert intervention. FIG. 1 is a diagram illustrating a coolant system to which the metal fragment impact location estimation method of the present invention is applied. FIG. 2 is a flowchart illustrating a method for estimating the location of a metal fragment impact according to an embodiment of the present invention. FIG. 3 is a drawing showing a plurality of sensors installed on the outer surface of a steam generator. FIG. 4 is a diagram showing the impact signals collected from each sensor. Figure 5 is a diagram illustrating the process of converting each impact signal into a spectrogram. Figure 6 is a diagram illustrating the learning process of a neural network model. FIG. 7 is a drawing showing the hemispherical head and impact location of the coolant system. FIG. 8 is a diagram showing the impact location illustrated in FIG. 7 according to a spherical coordinate system. FIG. 9 is a diagram showing the impact location predicted by a neural network model in a spherical coordinate system. FIG. 10 is a diagram illustrating the process of determining the impact location based on the output of the neural network model of the present invention. The aforementioned objectives, features, and advantages are described in detail below with reference to the attached drawings, thereby enabling those skilled in the art to easily implement the technical concept of the present invention. In describing the present invention, detailed descriptions of known technologies related to the present invention are omitted if it is determined that such descriptions would unnecessarily obscure the essence of the invention. Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the attached drawings. In the drawings, the same reference numerals are used to indicate the same or similar components. In this specification, terms such as "first," "second," etc. are used to describe various components, but these components are not limited by these terms. These terms are used merely to distinguish one component from another, and unless specifically stated otherwise, the first component may be the second component. Additionally, in this specification, the statement that any configuration is disposed on the "upper (or lower)" or "upper (or lower)" of a component may mean not only that any configuration is disposed in contact with the upper (or lower) surface of said component, but also that another configuration may be interposed between said component and any configuration disposed on (or below) said component. Furthermore, where it is stated in this specification that one component is "connected," "coupled," or "connected" to another component, it should be understood that while the components may be directly connected or connected to each other, another component may be "interposed" between each component, or each component may be "connected," "coupled," or "connected" through another component. Additionally, singular expressions used in this specification include plural expressions unless the context clearly indicates otherwise. In this application, terms such as "composed of" or "comprising" should not be interpreted as necessarily including all of the various components or steps described in the specification, and should be interpreted as meaning that some of the components or steps may not be included, or that additional components or steps may be included. Additionally, in this specification, "A and/or B" means A, B, or A and B unless specifically stated otherwise, and "C to D" means C or more and D or less, unless specifically stated otherwise