Method for automatically generating plant condition monitoring model of nuclear power plant using independent component analysis

Abstract

A method for automatically generating a plant condition monitoring model of a nuclear power plant using independent component analysis comprises the steps of: aggregating a plurality of first monitoring signals and a first novel signal, and a plurality of second monitoring signals and a second novel signal; performing independent component analysis on each of the plurality of first monitoring signals, the first novel signal, the plurality of second monitoring signals, and the second novel signal; reconstructing a first signal monitoring model and a second signal monitoring model on the basis of the independent component analysis; and reconstructing a third signal monitoring model and the second signal monitoring model on the basis of the independent component analysis.

Description

A method for automatically generating a nuclear power plant condition monitoring model using independent component analysis.

[0001] This paper relates to a method for automatically generating a nuclear power plant status monitoring model using independent component analysis.

[0002] In general, the plant condition monitoring model is a model that monitors the condition of a nuclear power plant by using signals received from sensors installed in the facilities included in the nuclear power plant.

[0003] Plant condition monitoring models are generated using signals received from various sensors.

[0004] The conventional method of creating a plant condition monitoring model involves combining signals received from the sensors of the nuclear power plant based on the know-how and experience of engineers based on the physical classification system of the nuclear power plant and optimizing the model through repeated experiments, which increases the model creation time and cost.

[0005] In addition, the conventional method of generating a plant condition monitoring model has a problem in that when a new signal is received from the nuclear power plant to the plant condition monitoring model due to changes in the nuclear power plant equipment or sensors, it is difficult to manually analyze and optimize the correlation between the existing monitoring signals received in the plant condition monitoring model and the new signal to generate a plant condition monitoring model, which lowers the prediction accuracy of the entire plant condition monitoring model.

[0006] One embodiment provides a method for automatically generating a nuclear power plant condition monitoring model using independent component analysis, which automatically generates a plant condition monitoring model with improved prediction accuracy while reducing model generation time and generation cost, even when a new signal is received from a nuclear power plant.

[0007] One aspect provides a method for automatically generating a plant condition monitoring model, the method comprising the steps of collecting a plurality of first monitoring signals and a first new signal received in a first equipment model of a plant condition monitoring model of a nuclear power plant and a plurality of second monitoring signals and a second new signal received in a second equipment model of the plant condition monitoring model, performing an independent component analysis on each of the plurality of first monitoring signals, the first new signal, the plurality of second monitoring signals, and the second new signal, reconstructing first principal component signals having a high correlation among the plurality of first monitoring signals and the first new signals into a first signal monitoring model based on the independent component analysis and reconstructing first separate signals having a low correlation into a second signal monitoring model, and reconstructing second principal component signals having a high correlation among the plurality of second monitoring signals and the second new signals into a third signal monitoring model based on the independent component analysis and reconstructing second separate signals having a low correlation into the second signal monitoring model.

[0008] The step of performing the above independent component analysis can be performed by applying independent component analysis based on dimension reduction.

[0009] The above first signal monitoring model can perform signal restoration prediction based on the above first facility model.

[0010] The third signal monitoring model can perform signal restoration prediction based on the second facility model.

[0011] The above second signal monitoring model can perform approximate nearest neighbor search prediction based on the physical classification system of the nuclear power plant.

[0012] According to one embodiment, a method for automatically generating a nuclear power plant condition monitoring model using independent component analysis is provided, which automatically generates a plant condition monitoring model with improved prediction accuracy while reducing model generation time and generation cost, even when a new signal is received from a nuclear power plant.

[0013] Figure 1 is a flowchart illustrating a method for automatically generating a plant status monitoring model according to one embodiment.

[0014] FIG. 2 is a diagram for explaining a method for automatically generating a plant status monitoring model according to one embodiment.

[0015] FIG. 3 is a graph showing an example of independent component analysis used in a method for automatically generating a plant condition monitoring model according to one embodiment.

[0016] Fig. 4 is a flowchart showing an example of a method for automatically generating a plant status monitoring model according to one embodiment.

[0017] Hereinafter, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. The present invention may be implemented in various different forms and is not limited to the embodiments described herein.

[0018] Additionally, throughout the specification, whenever a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise specifically stated.

[0019] Hereinafter, a method for automatically generating a plant status monitoring model according to one embodiment will be described with reference to FIGS. 1 to 4.

[0020] A method for automatically generating a plant condition monitoring model according to one embodiment may include a method for automatically generating a nuclear power plant condition monitoring model using independent component analysis.

[0021] A method for automatically generating a plant condition monitoring model according to one embodiment can automatically generate a plant condition monitoring model for monitoring the condition of a nuclear power plant, but is not limited thereto.

[0022] A method for automatically generating a plant condition monitoring model according to one embodiment may be performed by artificial intelligence driven by a computing device, but is not limited thereto.

[0023] Fig. 1 is a flowchart illustrating a method for automatically generating a plant condition monitoring model according to one embodiment. Fig. 2 is a diagram for explaining a method for automatically generating a plant condition monitoring model according to one embodiment.

[0024] Referring to FIGS. 1 and 2, first, a plurality of first monitoring signals (MS1) and a first new signal (NS1) received by a first equipment model (100) of a plant status monitoring model (1000) of a nuclear power plant and a plurality of second monitoring signals (MS2) and a second new signal (NS2) received by a second equipment model (200) of the plant status monitoring model (1000) are collected (S100).

[0025] For example, a plurality of first monitoring signals (MS1) and a first new signal (NS1) are received by a first equipment model (100) of a plant condition monitoring model (1000) of a nuclear power plant. The plurality of first monitoring signals (MS1) may include existing monitoring signals received by the first equipment model (100). The first new signal (NS1) may include new signals received by the first equipment model (100). A plurality of second monitoring signals (MS2) and a second new signal (NS2) are received by a second equipment model (200) of a plant condition monitoring model (1000) of a nuclear power plant. The plurality of second monitoring signals (MS2) may include existing monitoring signals received by the second equipment model (200). The second new signal (NS2) may include new signals received by the second equipment model (200). A plurality of first supervisory signals (MS1), a first new signal (NS1), a plurality of second supervisory signals (MS2), and a second new signal (NS2) are collected.

[0026] Next, independent component analysis (ICA) is performed on each of the plurality of first surveillance signals (MS1), the first new signal (NS1), the plurality of second surveillance signals (MS2), and the second new signal (NS2) (S200).

[0027] For example, independent component analysis (ICA) is performed on each of the plurality of first surveillance signals (MS1), the first new signal (NS1), the plurality of second surveillance signals (MS2), and the second new signal (NS2). The ICA may include various known ICAs. For example, various known ICAs may be performed by artificial intelligence driven by a computing device.

[0028] For example, the step of performing independent component analysis of each of a plurality of first surveillance signals (MS1), a first new signal (NS1), a plurality of second surveillance signals (MS2), and a second new signal (NS2) can be performed by applying independent component analysis based on dimension reduction.

[0029] FIG. 3 is a graph showing an example of independent component analysis used in a method for automatically generating a plant condition monitoring model according to one embodiment.

[0030] Referring to Figure 3, for example, AI can automatically classify signal components by applying dimensionality reduction-based independent component analysis (ICA). AI can perform sophisticated predictions by grouping only strongly correlated signals and restoring the signal. ICA based on dimensionality reduction can produce superior prediction results compared to existing statistical techniques. AI can also automatically separate weakly correlated signals and perform separate predictions. ICA based on dimensionality reduction is more efficient and objective than the conventional manual separation method by engineers.

[0031] Next, based on independent component analysis, the first principal component signals (CS1) with high correlation among the plurality of first surveillance signals (MS1) and the first new signal (NS1) are reconstructed into the first signal surveillance model (300), and the first separation signals (SS1) with low correlation are reconstructed into the second signal surveillance model (400) (S300).

[0032] For example, based on independent component analysis, first principal component signals (CS1) with high correlation among a plurality of first surveillance signals (MS1) and first new signals (NS1) are reconstructed into a first signal surveillance model (300). Based on independent component analysis, first separated signals (SS1) with low correlation among a plurality of first surveillance signals (MS1) and first new signals (NS1) are reconstructed into a second signal surveillance model (400).

[0033] The first signal monitoring model (300) can perform signal restoration prediction based on the first facility model (100). The second signal monitoring model (400) can perform Approximate Nearest Neighbor Search (ANNS) prediction based on the physical classification system of the nuclear power plant. The Approximate Nearest Neighbor Search can include various known Approximate Nearest Neighbor Searches. For example, various known Approximate Nearest Neighbor Search predictions can be performed by artificial intelligence driven by a computing device.

[0034] Next, based on independent component analysis, the second principal component signals (CS2) with high correlation among the plurality of second surveillance signals (MS2) and the second new signal (NS2) are reconstructed into a third signal surveillance model (500), and the second separation signals (SS2) with low correlation are reconstructed into a second signal surveillance model (400) (S400).

[0035] For example, based on independent component analysis, the second principal component signals (CS2) with high correlation among the plurality of second surveillance signals (MS2) and the second new signal (NS2) are reconstructed into a third signal surveillance model (500). Based on independent component analysis, the second separated signals (SS2) with low correlation among the plurality of second surveillance signals (MS2) and the second new signal (NS2) are reconstructed into the above-described second signal surveillance model (400).

[0036] The third signal monitoring model (500) can perform signal restoration prediction based on the second facility model (200). The second signal monitoring model (400) can perform approximate neighbor search prediction based on the physical classification system of the nuclear power plant. The approximate neighbor search can perform various known approximate neighbor searches, and various known approximate neighbor search predictions can be performed by artificial intelligence driven by a computing device.

[0037] Fig. 4 is a flowchart showing an example of a method for automatically generating a plant status monitoring model according to one embodiment.

[0038] Referring to FIG. 4, as an example of a method for automatically generating a plant condition monitoring model according to one embodiment, an artificial intelligence driven by a computing device may automatically generate a signal model by using an independent component analysis method of a dimensionality reduction method when configuring a condition monitoring signal model according to the construction of a new plant and the addition of new monitoring signals for existing facilities, and perform restoration prediction by automatically configuring separate signals with low correlation into a signal model based on adjacent facilities and performing prediction through an approximate nearest neighbor search. The artificial intelligence may perform signal restoration prediction by grouping together principal components with high correlation, thereby improving prediction accuracy, and at the same time, for signals with low correlation, the artificial intelligence may group together adjacent signals into a signal model based on the physical classification system of the nuclear power plant, and perform prediction by finding the most similar value in past data through an approximate nearest neighbor search method.

[0039] In the case of conventional statistical analysis prediction, there is a problem that the prediction accuracy of the entire model is reduced when the correlation between signals is weakened, but the method for automatically generating a plant condition monitoring model according to one embodiment can solve the conventional problem and secure objectivity because it separates based on the correlation of pure data rather than the experience of an engineer.

[0040] In addition, the method for automatically generating a plant condition monitoring model according to one embodiment can operate the system more efficiently through automation.

[0041] For example, a method for automatically generating a nuclear power plant condition monitoring model using independent component analysis is provided, which automatically generates a plant condition monitoring model with improved prediction accuracy while reducing model generation time and generation cost, even when a new signal is received from a nuclear power plant.

[0042] Although the 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 made by those skilled in the art using the basic concept of the present invention defined in the following claims also fall within the scope of the present invention.

[0043] [Explanation of symbols]

[0044] Plant status monitoring model (1000), first equipment model (100), second equipment model (200), first signal monitoring model (300), second signal monitoring model (400), third signal monitoring model (500)

Claims

1. A step of collecting a plurality of first monitoring signals and a first new signal received by a first equipment model of a plant status monitoring model of a nuclear power plant and a plurality of second monitoring signals and a second new signal received by a second equipment model of the plant status monitoring model; A step of performing independent component analysis on each of the plurality of first surveillance signals, the first new signal, the plurality of second surveillance signals, and the second new signal; A step of reconstructing first principal component signals with high correlation among the plurality of first surveillance signals and the first new signal based on the independent component analysis into a first signal surveillance model and reconstructing first separated signals with low correlation into a second signal surveillance model; and A step of reconstructing second principal component signals with high correlation among the plurality of second surveillance signals and the second new signal based on the independent component analysis into a third signal surveillance model and reconstructing second separate signals with low correlation into the second signal surveillance model. A method for automatically generating a plant condition monitoring model including:

2. In paragraph 1, A method for automatically generating a plant condition monitoring model, wherein the step of performing the above independent component analysis is performed by applying independent component analysis based on dimension reduction.

3. In paragraph 1, The above first signal monitoring model is a method for automatically generating a plant status monitoring model that performs signal restoration prediction based on the above first equipment model.

4. In paragraph 1, The third signal monitoring model is a method for automatically generating a plant status monitoring model that performs signal restoration prediction based on the second equipment model.

5. In paragraph 1, The second signal monitoring model is a method for automatically generating a plant condition monitoring model that performs approximate nearest neighbor search prediction based on the physical classification system of the nuclear power plant.

Images