Apparatus and method for tracking reasons for determining abnormal states using a neural network model

Abstract

The present invention relates to a device for tracking abnormal state judgment grounds using a neural network model, and includes an abnormal state type classification unit that classifies abnormal states into multiple faults in an abnormal operation scenario in which multiple scenarios related to abnormal states are stored; an operating variable derivation unit that derives operating variables that affect abnormal state judgment results for each of the multiple classified faults; a power plant operating variable weighting unit that weights variables associated with the abnormal state among the operating variables; and an abnormal state judgment ground generation unit that tracks abnormal state judgment grounds using the abnormal state judgment results generated through the weighted power plant operating variables.

Description

[Technical field]

[0001] The research related to this patent was conducted with the support of the Nuclear Core Technology Development Project (Project name: Development of artificial intelligence-based nuclear power plant start-up and shutdown operation resource technology, Project number: 1415159084) under the supervision of the Ministry of Trade, Industry and Energy.

[0002] The present invention relates to an apparatus and method for tracking reasons for judging a non-normal state, and more particularly to an apparatus and method for judging a non-normal state using a neural network model and tracing the reasons for the judgment. [Background technology]

[0003] Nuclear power plants have various abnormal operating conditions. When an abnormal operating condition occurs, an alarm is generated in the main control room and the related power plant status changes. Such power plant status changes include temperature, pressure, flow rate, etc.

[0004] Operators will determine what abnormal operating condition has occurred based on the plant alarm and take appropriate action in accordance with procedures for abnormal operating conditions.

[0005] However, nuclear power plants are subject to hundreds of types of abnormal operating states, and inexperienced operators have difficulty making accurate judgments regarding abnormal states, which can result in them being unable to take appropriate measures regarding abnormal states.

[0006] Therefore, research is being conducted on a method of using a neural network model to learn operational data of abnormal states and determine and provide abnormal states of a nuclear power plant so that operators can quickly determine abnormal states due to equipment failures or facility abnormalities and take appropriate measures. However, it is difficult for the neural network model to track which changes in the operational data of the power plant are the basis for determining an abnormal state. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] Korean Patent No. 2095653 (Device and method for determining abnormal operating conditions using neural network model, Korea Hydro & Nuclear Power Co., Ltd.) [Patent Document 2] US Patent 10452845 (Generic framework to detect cyber threats in electric power grid, GENERAL ELECTRIC COMPANY) [Patent Document 3] US Published Patent 20190164057 (Mapping and quantification of influence of neural network features for explainable artificial intelligence, INTEL CORP) Summary of the Invention [Problem to be solved by the invention]

[0008] The present invention is intended to solve the problems of the prior art as described above, and has an object to provide a method for estimating operating variables that are the basis for judging an abnormal state of a nuclear power plant using a neural network model, and an apparatus for tracking the basis for judging an abnormal state using a neural network model. [Means for solving the problem]

[0009] In order to achieve the above-mentioned object, the present invention provides an apparatus for tracking non-normal state judgment grounds using a neural network model, the apparatus comprising: a non-normal type classification unit that classifies non-normal states into a plurality of faults in a non-normal operation scenario in which a plurality of scenarios related to non-normal states are stored; an operation variable derivation unit that derives operation variables that affect a non-normal state judgment result for each of the classified plurality of faults; a power plant operation variable weighting unit that weights variables associated with the non-normal state among the operation variables; and a non-normal state judgment ground generation unit that tracks the non-normal state judgment grounds in the non-normal state judgment result generated via the weighted power plant operation variables.

[0010] In addition, the power plant operation variable weighting unit, which weights the variables associated with the abnormal state among the operation variables, is characterized in that it weights the physical variables associated with the abnormal state, classified in consideration of a physical correlation of a system associated with the abnormal state.

[0011] In addition, the abnormality type classifier classifies the abnormal operation scenario to include at least one of a valve leak, a pump failure, a heat exchanger failure, and a coolant leak.

[0012] In addition, the operation variable derivation unit derives operation variables that affect the abnormal state judgment result for each of the classified failures, and includes deriving a flow rate of a system associated with the valve when the failure is classified as a valve leak, deriving a flow rate and pressure of a system associated with the pump when the failure is classified as a pump failure, deriving a temperature of a system associated with the heat exchanger when the failure is classified as a heat exchanger failure, and deriving a radiation level of the leak site when the failure is classified as a coolant leak.

[0013] Additionally, the physical variables associated with the abnormal state are generated by referring to abnormal procedures or actual plant operating history.

[0014] In addition, the abnormal state determination basis is the driving variable capable of distinguishing different abnormal states, and is used to verify the abnormal state determination logic used in the abnormal state determination system.

[0015] The abnormal condition determination basis is used to verify symptoms described in abnormal condition procedures, and the abnormal condition procedures describe the operating variables that change when the abnormal condition occurs.

[0016] Furthermore, the method for generating a basis for judging a non-normal state using a neural network model includes a step of proceeding with learning by utilizing power plant operation data and a neural network model, and generating a non-normal state judgment result in a final stage of the neural network model, and a step of performing an influence analysis on the non-normal state judgment result in a fully connected layer before generating the non-normal state judgment result, and extracting variable values ​​that influence the non-normal state judgment result.

[0017] In addition, the step of extracting variable values ​​that affect the non-normal state judgment result includes the steps of applying a visualization algorithm to virtually generate visualized input change data, using the virtual input change data as input, analyzing the influence of the input change data on changes in the non-normal state judgment result by calculation of the neural network model, and extracting the input change data that contributes most significantly to deriving changes in the non-normal state judgment result. Effect of the Invention

[0018] The abnormality determination basis tracking device and method using a neural network model according to an embodiment of the present invention can determine the exact type of abnormality in a short time when various abnormalities occur and provide the determined type to operators, thereby enabling a quick and accurate response to abnormalities in a nuclear power plant and improving the safety of the nuclear power plant. [Brief description of the drawings]

[0019] [Figure 1] FIG. 1 is a diagram illustrating an outline of a non-normal state determination device to which an existing neural network model is applied. [Diagram 2] 1 is a diagram illustrating an operation process of a device for tracking a reason for determining a non-normal state to which a neural network model according to an embodiment of the present invention is applied; [Diagram 3] 13 is a diagram illustrating an operation process of extracting an operating variable that influences a change in a non-normal state determination result by applying a neural network model according to an embodiment of the present invention. FIG. [Figure 4] 4 is a diagram illustrating an operation process for generating a reason for judging a non-normal state according to an embodiment of the present invention. [Diagram 5] 1 is a schematic block diagram of a non-normal state determination basis tracking device according to an embodiment of the present invention; [Figure 6] 13 is a diagram showing the use of a basis for determining an abnormal state derived by applying a neural network model according to an embodiment of the present invention. FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0020] Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings. However, some components that are not related to the gist of the invention may be omitted or simplified, but the omitted components are not necessarily necessary for the present invention, and can be combined and used by those having ordinary skill in the art to which the present invention pertains.

[0021] FIG. 1 is a diagram illustrating a schematic diagram of a non-normal state determination device to which an existing neural network model is applied.

[0022] As shown in FIG. 1, a non-normal driving state determination device 100 applying a neural network model may include a non-normal driving state data generation unit 110, a non-normal driving state data learning unit 130, a non-normal driving state determination unit 150, and a non-normal driving state monitoring unit 170.

[0023] The non-normal operating condition data generating unit 110 is configured to virtually generate non-normal operating condition data based on information relating to a non-normal operating condition, and may include a scenario database 111 and a simulator 112.

[0024] The scenario database 111 is configured to have a plurality of scenarios related to abnormal operating states. Such scenarios include a scenario based on operating variables related to temperature changes in nuclear power plant equipment, a scenario based on operating variables related to turbine bearing vibration, etc., and various scenarios related to abnormal operating states are stored in the scenario database 111. Here, the operating variables are operating elements for the operating state of the nuclear power plant equipment, etc., and about 1,000 to 2,000 operating variables can be included for each equipment. Such operating variables can include pressure, temperature, flow rate, etc.

[0025] The simulator 112 is configured to simulate an abnormal operating state with respect to a scenario selected from among scenarios related to abnormal operating states stored in the scenario database 111. This allows data for the abnormal operating state to be virtually generated.

[0026] The non-normal driving state data learning unit 130 is configured to visualize and learn a non-normal driving state by applying a visualization algorithm based on the non-normal driving state data generated by the non-normal driving state data generating unit 110. Such a non-normal driving state data learning unit 130 may include a first visualization arrangement unit 131 and a second visualization arrangement unit 132.

[0027] The first visualization arrangement unit 131 is configured to arrange the operation variables of the devices and the like installed in the nuclear power plant based on their physical positions. That is, the operation variables can be arranged in the same arrangement as the structure of the actual nuclear power plant.

[0028] The second visualization arrangement unit 132 is configured to arrange physically identical operating variables first, for example, temperature-related operating variables are arranged in the same area so that when a temperature change occurs, the characteristics of each event are displayed.

[0029] The abnormal operation state determination unit 150 is configured to learn an abnormal operation state based on the abnormal operation state data learning unit 130 applying a visualization algorithm to represent the operation variables, and to determine whether an abnormal operation state has occurred based on the operation variables of the equipment, etc., acquired from the process monitoring and alarm system of the nuclear power plant. The abnormal operation state determination unit 150 may include a neural network model 151 and a signal matching unit 152.

[0030] The neural network model 151 is configured to learn the non-normal driving condition data visualized by the first visualization arrangement unit 131 and the second visualization arrangement unit 132 based on a visualization algorithm.

[0031] The signal matching unit 152 is configured to transmit information about the monitoring signal, including information about the abnormal operating state, in correspondence with the equipment, etc.

[0032] The abnormal operation state monitoring unit 170 is configured to monitor whether the operation state of each device installed in the nuclear power plant is within a normal range. The abnormal operation state monitoring unit 170 can periodically obtain a monitoring signal including information on the operation variables of each device and transmit the signal to the abnormal operation state determination unit 150.

[0033] FIG. 2 is a diagram illustrating an operation process of the device for tracking abnormal state determination basis to which a neural network model is applied according to an embodiment of the present invention.

[0034] As shown in Fig. 2, the non-normal state judgment basis tracking device 200 uses the power plant operation data 210 and the neural network model 230 to proceed with learning and generate the non-normal state judgment result 250. The neural network model 230 is calculated through a multi-layered neural network (deep learning) in order to effectively learn each non-normal state. The non-normal state judgment result 250 is generated in the final stage of the neural network model 230, but in the present invention, an influence analysis 270 on the non-normal state judgment result 250 is performed in a fully connected layer before the non-normal state judgment result 250 is generated, and variable values ​​that influence the non-normal state judgment result 250 are extracted.

[0035] FIG. 3 is a diagram illustrating an operation process of extracting an operating variable that influences a change in a non-normal state determination result by applying a neural network model according to an embodiment of the present invention.

[0036] 3, in the present invention, a visualization algorithm is first applied to virtually generate visualized input change data 310. Using the virtual input change data 310 as an input, the effect of the input change data 310 of each item on the result change 350 is analyzed by calculation of the neural network model 330, and the input change data 310 that contributes most to deriving the result change 350 is extracted.

[0037] Therefore, through the visualization algorithm, when an incident such as a pipe break occurs, the operating variables of the location where the incident actually occurred are collected and arranged, which makes it easier to extract the relevant characteristics during pre-processing convolution and pooling of the neural network model 330.

[0038] FIG. 4 is a diagram illustrating an operation process for generating a reason for judging a non-normal state according to an embodiment of the present invention.

[0039] FIG. 5 illustrates a basis for determining a non-normal state according to an embodiment of the present invention. Tracking Device of FIG. 1 is a schematic block diagram.

[0040] As shown in Figures 4 and 5, the abnormal state judgment basis tracking device 500 may include an abnormal operation scenario 510, an abnormal type classification unit 520, an operation variable derivation unit 530, a power plant operation variable weighting unit 540, and an abnormal state judgment basis generation unit 550.

[0041] The abnormal operation scenario 500 is configured to have a plurality of scenarios related to abnormal operation states. Such scenarios include a scenario based on an operating variable related to a temperature change of nuclear power plant equipment, etc., and a scenario based on an operating variable related to turbine bearing vibration. The abnormal type classification unit 520 classifies the abnormal operation scenario 500 into a valve leak, a pump failure, a heat exchanger failure, a coolant leak, etc., and the operating variable derivation unit 530 derives an operating variable that affects the abnormality judgment result for the classified failure. In one embodiment, when a valve leak is classified, the flow rate of the system related to the valve is derived; when a pump failure is classified, the flow rate and pressure of the system related to the pump are derived; when a heat exchanger failure is classified, the temperature of the system related to the heat exchanger is derived; and when a coolant leak is classified, the radiation level of the leak site is derived. The range of inputs that affect the abnormal state result includes many uncertainties, and in order to extract the basis of the abnormal state judgment result, it is important to derive a change in the input that is physically related to the abnormal state.

[0042] Therefore, the extracted operational variables that are the basis for determining the abnormal state are used as the basis for the neural network judgment, taking into account the physical correlation of the related systems.The abnormal state is physically classified based on the information about the abnormal state, and the physical variables associated with each corresponding abnormal state are weighted.

[0043] In one embodiment, the abnormal condition is classified as a valve leak, and the flow rate of the system that is thermal-hydraulic related to the system is weighted highly to explain the reason for the abnormal condition. The selection of the operating variables that are physically related to the abnormal condition is made by referring to the abnormal procedure or the actual plant operating history.

[0044] The power plant operation variable weighting unit 540 weights physical variables related to abnormal states among the fault-specific operation variables, and finally, the abnormal state determination basis generating unit 550 enables more accurate basis tracing through the results reflecting the weights.

[0045] FIG. 6 is a diagram illustrating the use of a basis for determining a non-normal state derived by applying a neural network model according to an embodiment of the present invention.

[0046] As shown in Fig. 6, the abnormal state determination basis 620 derived from the abnormal operation simulation data 610, which is simulated for a scenario selected from the abnormal operation scenarios 600 having a plurality of scenarios related to abnormal states, is a power plant operation variable that can be distinguished from other abnormal states when the abnormal state occurs. This can be used to verify 630 the abnormal state determination logic being used in the abnormal state determination system. In other words, it can be confirmed whether or not the abnormal state determination logic has been developed by using the operation variables that are changed for the abnormal state.

[0047] In addition, the abnormal procedure describes the operational variables that change when the abnormal condition occurs. The abnormal condition judgment basis 620 can be used to verify symptoms related to the abnormal procedure via abnormal procedure judgment logic verification 640, and can be used to verify and revise the procedure so that the operator can more effectively judge the abnormal condition. [Explanation of symbols]

[0048] 100 Abnormal operating state determination device 200, 500 Abnormal state determination basis tracking device 210 Power Plant Operation Data 230 Neural Networks 510, 600 Abnormal operation scenarios 520 Abnormal type classification section 530 Driving variable derivation part 540 Power Plant Operation Variable Weighting Section 550 Non-normal state judgment basis generation unit

Claims

1. An abnormality type classification unit that classifies an abnormality into a plurality of faults based on an abnormal operation scenario in which a plurality of scenarios relating to an abnormality virtually generated by a simulator are stored (wherein the plurality of scenarios include operating variables for operating states of power plant equipment, and the operating variables include 1,000 to 2,000 for each of the power plant equipment); an operating variable derivation unit that derives an operating variable that affects a non-normal state determination result for each of the classified plurality of faults; a power plant operation variable weighting unit that weights variables associated with the abnormal state among the derived operation variables; and an abnormal state determination reason generating unit that tracks abnormal state determination reasons in the abnormal state determination result generated through the weighted power plant operation variables, The abnormal state determination result is generated at a final stage of the neural network model by learning using the power plant operation data and the neural network model, An influence analysis is performed on the abnormal state judgment result in a fully connected layer before the last stage that generates the abnormal state judgment result, and a variable value that influences the abnormal state judgment result is extracted; The driving variable derivation unit applies a visualization algorithm to virtually generate visualized input change data, and uses the virtually generated visualized input change data as an input to analyze the influence of the virtually generated visualized input change data on a result change through calculation of the neural network model, and extracts input change data that most significantly contributes to deriving the result change; The abnormal state judgment basis is an operating variable that can be distinguished from different abnormal states, and is used to verify the abnormal state judgment logic and to verify the symptoms described in the abnormal state procedure. A device for tracking the basis for determining abnormal conditions using a neural network model.

2. A power plant operation variable weighting unit that weights variables associated with the abnormal state among the operation variables, 2. The abnormal state determination basis tracking device using a neural network model according to claim 1, wherein the weight is assigned to a physical variable related to the abnormal state, the physical variable being classified in consideration of a physical correlation of a system related to the abnormal state.

3. 2. The abnormality type classification unit classifies the abnormal operation scenario to include at least one of a valve leak, a pump failure, a heat exchanger failure, and a coolant leak.

4. 2. The abnormal state determination basis tracking device using a neural network model according to claim 1, wherein the operating variable derivation unit derives operating variables that affect the abnormal state determination result for each of the classified failures, and derives a flow rate of a system associated with the valve when the failure is classified as a valve leak, a flow rate and a pressure of a system associated with the valve when the failure is classified as a pump failure, a temperature of a system associated with the heat exchanger when the failure is classified as a heat exchanger failure, and a radiation level of a leak site when the failure is classified as a coolant leak.

5. 2. The device for tracking reasons for determining an abnormal state using a neural network model according to claim 1, wherein the physical variables associated with the abnormal state are generated by referring to an abnormal procedure or an actual operation history of a power plant.

Images