JP7351718B2 - Nuclear plant dose equivalent prediction method, dose equivalent prediction program, and dose equivalent prediction device - Google Patents

Description

Application of Article 30, Paragraph 2 of the Patent Act [1] Date: July 24, 2020 to July 26, 2020 Meeting name and venue: Japan Society of Maintenance Engineers 16th Academic Conference Link Station Hall Aomori (1-4-1 Tsutsumi-cho, Aomori City) [2] Publication date: July 24, 2020 Publication: Japan Society of Maintenance Engineers 16th Academic Conference Abstracts Pages 684-685 General Incorporated Association Japan Conservation Society

The present disclosure relates to a dose equivalent prediction method, a dose equivalent prediction program, and a dose equivalent prediction device for a nuclear power plant.

At a nuclear power plant, workers may enter the interior for inspection purposes after the plant has shut down. At this time, it is necessary to understand the dose equivalent of the components of the nuclear power plant and manage the radiation exposure of workers. The dose equivalent of component equipment increases due to adhesion of radioactive substances contained in cooling water. For example, metal elements (eg, Ni, Co) are eluted from materials used in component equipment due to corrosion or the like, and are sent to the reactor core by cooling water. These metal elements adhere to the reactor core and become radioactive, thereby changing into radioactive substances (for example, Ni becomes Co-58 and Co becomes Co-60). The radioactive materials generated in the reactor core are melted and separated from the reactor core, sent out of the reactor by cooling water, and deposited on the components, increasing the dose equivalent of the components.

In order to reduce the radiation exposure of workers who enter the interior of a nuclear power plant, it is required to reduce the dose equivalent of component equipment after the plant is shut down. In response to such demands, for example, in Patent Document 1, in a nuclear power plant using a boiling water reactor, corrosion of the external components is suppressed by controlling the water quality of the reactor water. It has been proposed to suppress the deposition of radioactive materials and reduce the dose equivalent.

Patent No. 3281213

The dose equivalent of the component equipment after the plant has been shut down is used, as mentioned above, to manage the amount of radiation exposure of workers when they enter the plant. Therefore, in order to formulate a work plan, it is desirable to predict the dose equivalent in advance before the plant is shut down. However, the dose equivalent of component equipment after plant shutdown is thought to be complicatedly related to a large number of parameters related to plant operating conditions, and the details thereof have not been fully elucidated. Patent Document 1 suggests that the quality of reactor water during plant operation has a correlation with the dose equivalent of component equipment after plant shutdown, but this is because some parameters related to plant operating conditions are However, it is difficult to make reliable predictions of dose equivalents based on this.

At least one embodiment of the present disclosure has been made in view of the above-mentioned circumstances, and provides a dose equivalent prediction method for a nuclear power plant, a dose equivalent prediction program, and a dose equivalent prediction program that can accurately predict the dose equivalent of component equipment after the nuclear power plant is shut down. , aims to provide a dose equivalent prediction device.

In order to solve the above problems, a method for predicting dose equivalent of a nuclear power plant according to at least one embodiment of the present disclosure includes:
In a nuclear power plant having a nuclear reactor, a first parameter including at least an in-operation parameter regarding the nuclear power plant during operation and a shutdown operation parameter regarding the nuclear power plant during a shutdown operation period; The method includes the step of obtaining a predicted value of the second parameter from data corresponding to the first parameter using a prediction model that shows a correlation with a second parameter indicating a dose equivalent of equipment constituting the nuclear power plant.

In order to solve the above problems, a nuclear power plant dose equivalent prediction device according to at least one embodiment of the present disclosure,
computer,
In a nuclear power plant having a nuclear reactor, a first parameter including at least an in-operation parameter regarding the nuclear power plant during operation and a shutdown operation parameter regarding the nuclear power plant during a shutdown operation period; Using a prediction model showing a correlation with a second parameter indicating the dose equivalent of equipment constituting a nuclear power plant, the method functions as means for determining a predicted value of the second parameter from data corresponding to the first parameter.

In order to solve the above problems, a nuclear power plant dose equivalent prediction program according to at least one embodiment of the present disclosure,
In a nuclear power plant having a nuclear reactor, a first parameter including at least an in-operation parameter regarding the nuclear power plant during operation and a shutdown operation parameter regarding the nuclear power plant during a shutdown operation period; A predicted value configured to obtain a predicted value of the second parameter from data corresponding to the first parameter using a prediction model that shows a correlation with a second parameter indicating a dose equivalent of equipment constituting a nuclear power plant. Equipped with a calculation section.

According to at least one embodiment of the present disclosure, it is possible to provide a dose equivalent prediction method, a dose equivalent prediction program, and a dose equivalent prediction device for a nuclear power plant that can accurately predict the dose equivalent of component equipment after the nuclear power plant is shut down. .

FIG. 1 is a schematic configuration diagram of a nuclear power plant. 2 is a flowchart showing, step by step, a method for creating a prediction model used in a dose equivalent prediction method according to some embodiments. This is an example of a first parameter candidate list. This is an example of a first parameter candidate list. This is an example of driving history data. FIG. 1 is a configuration diagram of a dose equivalent prediction device according to some embodiments. 1 is a flowchart showing each step of a dose equivalent prediction method according to some embodiments. 7 is an example of a verification result showing a comparison between a predicted value of a dose equivalent obtained by the dose equivalent prediction method of FIG. 6 and an actual value. 7 is a flowchart showing each step of the driving support method implemented by the dose equivalent prediction device of FIG. 6. 7 is a flowchart showing, step by step, learning control of the prediction model M performed by the dose equivalent prediction device of FIG. 6. FIG.

Hereinafter, some embodiments of the present invention will be described with reference to the accompanying drawings. However, the dimensions, materials, shapes, relative arrangements, etc. of the components described as the embodiments or shown in the drawings are not intended to limit the scope of the present invention thereto, and are merely illustrative examples. do not have.

First, a description will be given of a nuclear power plant 1 that is a target of implementation of dose equivalent prediction methods according to some embodiments. FIG. 1 is a schematic configuration diagram of a nuclear power plant 1. As shown in FIG. A nuclear power plant 1 has a nuclear reactor 2 for generating steam using thermal energy generated in a nuclear fission reaction. Although the nuclear reactor 2 is a pressurized water reactor (PWR), in other embodiments the nuclear reactor 2 may be a boiling water reactor (BWR), or Unlike light water reactors, including pressurized water reactors and boiling water reactors, nuclear reactors may be of a type that uses substances other than light water as a moderator or coolant.

The nuclear reactor 2 includes a primary cooling loop 4 through which primary cooling water flows, a reactor vessel 6 (pressure vessel) provided in the primary cooling loop 4, a pressurizer 8, a steam generator 10, and a primary cooling water pump 12. ,including. The primary cooling water pump 12 is configured to circulate primary cooling water in the primary cooling loop 4 . Further, the pressurizer 8 is configured to pressurize the primary cooling water in the primary cooling loop 4 so that the primary cooling water does not boil. The reactor vessel 6 , pressurizer 8 , steam generator 10 , and primary cooling water pump 12 that constitute the nuclear reactor 2 in this manner are housed in the reactor containment vessel 13 .

The reactor vessel 6 accommodates fuel rods 14 containing pelletized nuclear fuel (for example, uranium fuel, MOX fuel, etc.), and the thermal energy generated by the nuclear fission reaction of this fuel provides primary cooling within the reactor vessel 6. water is heated. The reactor vessel 6 is provided with control rods 16 for absorbing and adjusting the number of neutrons generated in the reactor core containing nuclear fuel in order to control the reactor output. The primary cooling water heated within the reactor vessel 6 is sent to the steam generator 10, and through heat exchange, the secondary cooling water flowing through the secondary cooling loop 18 is heated to generate steam.

The steam generated by the steam generator 10 rotates a steam turbine (not shown) located outside the reactor vessel 6 via the secondary cooling loop 18 . Thereby, the work of the steam turbine is output as electrical energy and supplied to a predetermined power system.

The primary cooling loop 4 is also provided with a purification line 26 that includes a demineralization tower 20, a volume control tank 22, and a filling pump 24. The purification line 26 is provided from between the steam generator 10 and the primary cooling water pump 12 to between the primary cooling water pump 12 and the reactor vessel 6, bypassing the primary cooling loop 4. The desalination tower 20 removes inorganic salts from the cooling water taken in from the primary cooling loop 4. The volume control tank 22 adjusts the amount of cooling water circulating through the primary cooling loop 4 by storing a portion of the cooling water taken into the purification line 26 from the primary cooling loop 4 . Fill pump 24 regulates the flow rate of cooling water through purge line 26 .

In the nuclear power plant 1 having the above configuration, components exposed to the primary cooling water passing through the reactor 2 (for example, the reactor vessel 6, the pressurizer 8, the steam generator 10, and the primary cooling water pump that constitute the primary cooling loop 4) 12. An oxide film containing radioactive substances may adhere to the surfaces of the members constituting the demineralization tower 20, volume control tank 22, filling pump 24, piping connecting these, etc. that constitute the purification line 26. be. Materials used in the components include metal components such as nickel, cobalt, iron, and chromium. These metal components are eluted due to corrosion, etc., are sent to the reactor core together with cooling water, and are attached to the reactor core and activated, turning into radioactive substances (for example, Ni becomes Co-58, Co becomes Co-60). radioactive). The radioactive materials generated in the reactor core are melted and separated from the reactor core, transported out of the reactor by cooling water, and deposited as an oxide film on the surfaces of component equipment. In this way, as the amount of radioactive substances adhering to the component equipment increases, the dose equivalent of the component equipment increases.

The dose equivalent prediction method according to some embodiments is applied in the nuclear power plant 1 having the above-described configuration to predict the dose equivalent of the component equipment through which the primary cooling water flows after the plant is shut down. In the dose equivalent prediction method according to some embodiments, by using a prediction model M that shows a correlation between a first parameter regarding the nuclear power plant 1 and a second parameter indicating the dose equivalent after the operation of the nuclear power plant 1 is stopped, Predict dose equivalents.

First, with reference to FIG. 2, a method for creating a prediction model M used in a dose equivalent prediction method according to some embodiments will be described. FIG. 2 is a flowchart showing, step by step, a method for creating a prediction model M used in a dose equivalent prediction method according to some embodiments.

First, first parameters X1, X2, etc., which are input parameters of the prediction model M, are acquired from the parameters related to the nuclear power plant 1 (step S100). The first parameters X1, X2, . . . obtained in step S100 can include any parameters that may have a correlation with the second parameter Y. In particular, it includes parameters that may affect the aforementioned mechanism of increase in dose equivalent in the prediction target equipment (e.g. corrosion of component equipment, dissolution/exfoliation of radioactive materials, or adhesion of radioactive materials to the prediction target equipment). It would be good if you could.
Note that the first parameters X1, X2, . . . may be acquired selectively from a group of parameters prepared in advance in step S100. Such selective acquisition may be performed, for example, by assigning a priority to each parameter included in the parameter group according to the degree of contribution to the second parameter Y, and performing the acquisition based on the priority. good.

Here, FIGS. 3A and 3B are examples of a first parameter candidate list L showing candidates that can be obtained as the first parameters X1, X2, . . . . In the first parameter candidate list L, the first parameter candidates are listed in the right column, and are categorized into major, middle, and minor categories from several viewpoints to make it easier to understand the characteristics of each first parameter candidate. Shown separately.

The major category "Equipment parameters" is a parameter related to each component of the nuclear power plant 1, and includes the middle categories "Material parameters used" and "Maintenance history parameters."
The intermediate classification "material parameters used" includes "materials used for component equipment" as a first parameter candidate. This is because the "materials used for component equipment" may have a considerable effect on corrosion of the component equipment, dissolution/exfoliation of radioactive materials, or adhesion of radioactive materials to the predicted equipment.
The middle category "maintenance history parameters" includes "contents and timing of past maintenance work implementation" as a first parameter candidate. During maintenance work, the amount of oxide film formed on the surface of each component of the nuclear power plant 1 changes, resulting in corrosion of the components, dissolution/peeling of radioactive materials, or adhesion of radioactive materials to the predicted equipment. This is because there is a possibility that it may have a considerable influence.

The major category "operating parameters" is a parameter related to the operation of the nuclear power plant 1 (for example, during steady operation excluding start-up operation and stop operation), and includes the middle categories "water quality parameters" and "operation parameters."

The middle category "water quality parameters" is a parameter related to the quality of cooling water during operation, and includes the minor categories "component concentration,""pH," and "impurity concentration."
The subcategory "component concentration" is the concentration of each component contained in the cooling water, and the first parameter candidates are "concentration at the beginning of the cycle,""concentration at the middle of the cycle,""concentration at the end of the cycle," and "during the cycle.""averageconcentration" and "concentration fluctuation range during the cycle". Target components of these first parameter candidates include, for example, boron, lithium, dissolved hydrogen, zinc, etc., which are typical components of cooling water.
The subcategory "pH" is the pH of the cooling water, and the first parameter candidates are "pH at the beginning of the cycle,""pH at the middle of the cycle,""pH at the end of the cycle,""cycle average pH," and "during the cycle." pH fluctuation range” is included.
The subcategory "Impurity concentration" is the concentration of impurities contained in cooling water, and the first parameter candidates are "Impurity concentration at the beginning of the cycle,""Impurity concentration at the middle of the cycle,""Impurity concentration at the end of the cycle," and "Impurity concentration at the end of the cycle." This includes the average impurity concentration during the cycle and the range of impurity concentration fluctuation during the cycle. The target impurities of these first parameter candidates include, for example, Cl, SO ₄ , O ₂ and the like, which are typical impurities of cooling water.

In this specification, "cycle" refers to the steady operation period (period excluding the start-up operation period and the stop operation period) from the time when the nuclear power plant 1 is stopped until the time when the nuclear power plant 1 is next stopped. means. For example, when the nuclear power plant 1 is shut down for regular inspections, the term "cycle" is synonymous with the regular operation period at the regular inspection intervals. Moreover, the "stopping operation period" means a period during which the stopping operation is performed after the steady operation period in order to stop the nuclear power plant 1 that is in the steady operation period. In the stop operation period, for example, a plant disconnection operation is performed to disconnect the generator that generates power during the steady operation period.

The medium category "operation parameters" is a parameter related to the operation of the nuclear power plant 1 during operation, and includes the small categories "Long/Short operation items", "ON/OFF operation items", and "UP/DOWN operation items". include. The subcategory "Long/Short operation items" includes, as first parameter candidates, "number of operation days for one cycle," "number of high pH maintenance operation days at the end of the cycle," and "number of elapsed cycles after the start of zinc injection." The subcategory "ON/OFF operation items" includes "number of plant output changes (number of load fluctuations)" as a first parameter candidate. The subcategory "UP/DOWN operating parameters" has the following first parameter candidates: "primary cooling water temperature," "temperature difference at the entrance and exit of the reactor vessel," "linear power density of fuel," and "average purification flow rate during the cycle." ” and “purification flow rate fluctuation range during the cycle.”

Next, as shown in FIG. 3B, the major category "shutdown operation parameters" includes shutdown actions performed to shut down the nuclear power plant 1 (for example, disconnection of generators after steady operation, and performed until the shutdown is completed). (operation) parameters, including the middle classifications ``water quality parameters'' and ``operation parameters.''

The middle category "water quality parameters" is a parameter related to the quality of cooling water during the stop operation period, and includes the small categories "component concentration", "pH", and "impurity concentration".
The subcategory "component concentration" is the concentration of each component contained in the cooling water during stop operation. ). Target components of these first parameter candidates include, for example, boron, lithium, dissolved hydrogen, zinc, etc., which are typical components of cooling water.
The subcategory "pH" is the pH of the cooling water during shutdown operation, and the first parameter candidates are "pH at the beginning of shutdown operation (during cool-down)" and "pH at the end of shutdown operation (during oxidation operation)". include.
The subcategory "Impurity concentration" is the concentration of impurities contained in the cooling water during stop operation. ) including the impurity concentration. The target impurities of these first parameter candidates include, for example, Cl, SO ₄ , O ₂ and the like, which are typical impurities of cooling water.

The medium category "operation parameters" are parameters related to the operation of the nuclear power plant 1 during the shutdown operation period, and the small categories "Long/Short operation items", "ON/OFF operation items", and "UP/DOWN operation items" "including. The subcategory "Long/Short operation items" has the first parameter candidates as "plant disassembly (shutdown) - drop time to purification operation temperature" and "elapsed time from plant disassembly (shutdown) to water removal)" including. The subcategory "ON/OFF operation items" includes "the number of operating primary cooling water pumps 12 in the final stage of shutdown (oxidation operation)" as a first parameter candidate. The subcategory "UP/DOWN operation parameters" has the following first parameter candidates: "purification flow rate at the beginning of the stop operation (during cool-down)", "purification flow rate at the end of the stop operation (during oxidation operation)", and "purification flow rate at the end of the stop operation (during oxidation operation)". Includes the temperature at the end of operation (oxidation operation).

The major classification "post-shutdown parameters" is a parameter related to the operation of the nuclear power plant 1 after the shutdown (after the end of the shutdown operation period), and includes the minor classifications "shutdown period" and "storage data." The subcategory "stop period" includes "plant stop period" as a first parameter. The subcategory "Storage data" has the following parameters as the first parameters: "Temperature of primary cooling water during storage," "Boron concentration of primary cooling water during storage," "Cl concentration of primary cooling water during storage," and "Storage data." ``SO4 concentration of the primary cooling water inside'', ``purification frequency during storage'', and ``purification flow rate during storage''.

Returning to FIG. 2, in step S100, an arbitrary number of first parameters X1, X2, . . . are acquired from such a large number of first parameter candidates. The first parameters X1, X2, . . . are acquired so as to include at least an in-operation parameter regarding the nuclear power plant 1 in operation and a shutdown operation parameter regarding the nuclear power plant 1 in a shutdown operation. Explaining based on the first parameter candidate list L shown in FIGS. 3A and 3B, at least one of the parameters falling under the major classification "operating parameters" is acquired as an operating parameter regarding the nuclear power plant 1 in operation. . Furthermore, at least one of the parameters corresponding to the major classification "shutdown operation parameters" is acquired as the shutdown operation parameter regarding the nuclear power plant in shutdown operation.

During the shutdown operation period of the nuclear power plant 1, the state of the nuclear power plant 1 changes dramatically compared to when the nuclear power plant 1 is in operation, and this has an impact on the dose equivalent of the equipment that makes up the nuclear power plant 1 after the plant is shut down. affect Therefore, by acquiring the first parameters X1, X2, . . . so that the stopping operation parameters are included, it is possible to create a prediction model M that is capable of predicting dose equivalents with higher reliability than in the past.

Moreover, the first parameters X1, X2, . . . may be acquired so as to include parameters related to the operation of the nuclear power plant 1 during the shutdown operation period. Explaining based on the first parameter candidate list L shown in FIGS. 3A and 3B, at least one of the parameters corresponding to the major classification "stopping operation parameters" and the medium classification "operation data" is acquired. Thereby, it is possible to create a prediction model M that takes into consideration the influence on the dose equivalent due to the operational behavior of the nuclear power plant 1 during the shutdown operation period.

Further, the first parameters X1, X2, . . . may be acquired so as to include parameters related to the quality of cooling water during the stop operation period. Explaining based on the first parameter candidate list L shown in FIGS. 3A and 3B, at least one of the parameters corresponding to the major category "stopping operation parameters" and the medium category "water quality data" is acquired. This makes it possible to create a prediction model M that takes into consideration the influence on the dose equivalent due to changes in the quality of the cooling water during the stop operation period.

Further, the first parameters X1, X2, . . . may be acquired so as to include equipment parameters related to at least one of the materials and maintenance history of equipment constituting the nuclear power plant 1. Explaining based on the first parameter candidate list L shown in FIGS. 3A and 3B, at least one of each parameter corresponding to the major classification "device parameters" is acquired. Thereby, it is possible to create a prediction model M that takes into consideration the influence on the dose equivalent due to the material or maintenance history of the component equipment.

Further, the first parameters X1, X2, . . . may be acquired so as to include parameters related to operations during operation of the nuclear power plant 1. Explaining based on the first parameter candidate list L shown in FIGS. 3A and 3B, at least one of the parameters corresponding to the major category "driving parameters" and the medium category "operating parameters" is acquired. Thereby, a prediction model M can be created that takes into consideration the influence on the dose equivalent due to operations during operation of the nuclear power plant 1.

Further, the first parameters X1, X2, . . . may be acquired so as to include parameters related to the post-shutdown state of the nuclear power plant 1. Explaining based on the first parameter candidate list L shown in FIGS. 3A and 3B, at least one of the parameters corresponding to the major classification "post-stop parameters" is acquired. Thereby, a prediction model M can be created that takes into account the influence of the post-shutdown state of the nuclear power plant 1 on the dose equivalent.

Further, the first parameters X1, X2, . . . may be acquired so as to include the lithium concentration of the cooling water before the shutdown operation period of the nuclear power plant 1. Explaining based on the first parameter candidate list L shown in FIGS. 3A and 3B, for lithium among the components of cooling water, the "concentration at the end of the cycle" belongs to the major category "operating parameters" and the middle category "water quality parameters" is retrieved to include. This parameter is a factor that has a large influence on the dose equivalent of the equipment that constitutes the nuclear power plant 1 after the plant is shut down, and by including it in the input of the prediction model M, it is a prediction that can effectively improve the prediction accuracy of the dose equivalent. Model M can be created.

Further, the first parameters X1, X2, . . . may be acquired so as to include parameters related to the flow rate of cooling water during the period of shutdown operation of the nuclear power plant 1. The explanation will be based on the first parameter candidate list L shown in FIGS. 3A and 3B. number of vehicles in operation). This parameter corresponds to the number of operating primary cooling water pumps 12 for pumping cooling water, and is a factor that has a large influence on the dose equivalent of the equipment that constitutes the nuclear power plant 1 after the plant is shut down. Therefore, by including this parameter in the input of the prediction model M, it is possible to create a prediction model M that can effectively improve the prediction accuracy of the dose equivalent.
Although omitted in FIG. 3B, parameters related to the flow rate of cooling water during the shutdown period of the nuclear power plant 1 include the output of the primary cooling water pump 12 for pumping cooling water, etc. It may also include parameters related to the operating state of the vehicle.

Returning to FIG. 2, next, a second parameter Y indicating the dose equivalent after the equipment constituting the nuclear power plant 1 is stopped is acquired (step S101). The second parameter Y is a parameter related to the dose equivalent after the equipment to be predicted is stopped; for example, it may be the absolute value of the dose equivalent, or it may be the rate of change in dose that is the rate of change from the previous prediction result. Good too.

Subsequently, operation history data regarding the nuclear power plant 1 is acquired (step S102). The operation history data includes information regarding the operation history of the nuclear power plant 1, such as the operation history of the equipment that makes up the nuclear power plant 1, the water quality management history of the primary cooling water, and the dose of each component at the time of shutdown. The first parameters X1, X2, . . . and the second parameter Y include information such as equivalent values (actual measured values and past predicted values).

Note that such operation history data may be provided by a user of the nuclear power plant 1 or may be automatically acquired from the nuclear power plant 1. Further, the driving history data may be obtained online via a communication network, or may be obtained offline without using a communication network.

Next, the first parameters X1, X2, . . . and the second parameter Y are calculated from the driving history data acquired in step S102 (step S103). Here, FIG. 4 is an example of driving history data. In FIG. 4, as an example of operation history data, temporal changes in concentration of components A and B contained in the primary cooling water are shown over a steady operation period T1 (time t1 to t2) and a stop operation period T2 (after time t2). It is shown. For example, if the "concentration at the initial stage of the stop operation (during cool-down)" is acquired for components A and B as the first parameter X1 from the first parameter candidate list L, then the stop operation Initial concentrations CA and CB for period T2 are determined.

In this way, even if the driving history data does not directly include the first parameters X1, X2, . . . and the second parameter Y, the driving history data is analyzed in step S103. Accordingly, the first parameters X1, X2, . . . and the second parameter Y are calculated.

Next, multivariate analysis is performed on the first parameters X1, X2, . . . acquired in step S100 and the second parameter Y acquired in step S101 (step S104). In the multivariate analysis, the correlation between the first parameters X1, X2, . . . and the second parameter Y is expressed by the following general formula.
Y=a1X1+a2X2+... (1)
Here, a1, a2, . . . are arbitrary coefficients. In step S104, coefficients a1, a2,... are obtained by applying the first parameters X1, X2,... and the second parameter Y calculated in step S103 to equation (1). Accordingly, a prediction model M is calculated (step S105).
Note that in the multivariate analysis in step S104, for example, PLS analysis (partial least squares method) can be applied, but the present invention is not limited to this, and other known methods may be applied as appropriate.

Next, a method for predicting dose equivalent using the prediction model M created as described above will be explained. Here, an example will be described in which a dose equivalent prediction method is implemented using a dose equivalent prediction apparatus according to some embodiments. FIG. 5 is a block diagram of a dose equivalent prediction device according to some embodiments, and FIG. 6 is a flowchart showing each step of a dose equivalent prediction method according to some embodiments.

The dose equivalent prediction device 100 includes a main server 104 and a data server 105, which are connected to each other via a communication network 102. The communication network 102 is a network that can transmit and receive various data between the components of the dose equivalent prediction device 100, and can be wired or wireless.

The main server 104 is a server that performs main information processing in the dose equivalent prediction device 100, and installs a program for executing a dose equivalent prediction method on hardware including an electronic calculation device such as a computer. Consisted of. The main server 104 includes a predictive model acquisition unit 106, a driving history data acquisition unit 108, a parameter calculation unit 110, a predicted value calculation unit 112, an output unit 114, a contribution value calculation unit 120, a control parameter calculation unit 122, and a driving support information creation unit. 124, a learning data evaluation section 126, and a predictive model learning section 128. The functional blocks constituting the main server 104 may be integrated with each other or may be further subdivided.

The data server 105 is a server that includes a database that stores various data necessary for arithmetic processing in the main server 104. The data server 105 is configured to be able to store and read various information by accessing it from the main server 104 via the communication network 102 . The data server 105 includes a plurality of databases corresponding to the types of information, specifically, an operation history database 116 that stores operation history data of the nuclear power plant 1, and a prediction model M created as described above. and a predictive model database 118 that stores.

The dose equivalent prediction device 100 having such a configuration is configured to be able to implement the dose equivalent prediction method shown in FIG. 6 . First, the prediction model acquisition unit 106 acquires a prediction model M that shows the correlation between the first parameters X1, X2, . . . and the second parameter Y (step S200). The predictive model M is created in advance using the above-described creation method and stored in the predictive model database 118, and is obtained by reading this through the communication network 102.

Subsequently, the driving history data acquisition unit 108 acquires driving history data (step S201). The operation history database 116 stores operation history data provided by users of the nuclear power plant 1, and the operation history data acquisition unit 108 acquires the operation history by accessing the operation history database 116 via the communication network 102. Get data.

Subsequently, the parameter calculation unit 110 calculates first parameters X1, X2, etc. used in the prediction model M acquired in step S200 from the driving history data acquired in step S202 (step S202). . The calculation of the first parameters X1, X2, . . . in step S202 is performed in the same manner as step S103 described above with reference to FIG.

Subsequently, the predicted value calculation unit 112 inputs the first parameters X1, A second parameter Y indicating the dose equivalent after the operation of the constituent equipment is stopped is calculated (step S204). Specifically, the second parameter Y is calculated by inputting the first parameters X1, X2, . . . to equation (1) in which the coefficients a1, a2, .

The second parameter Y calculated in this way is output by the output unit 114 (step S205).

Here, FIG. 7 is an example of a verification result showing a comparison between the predicted value of the dose equivalent obtained by the dose equivalent prediction method of FIG. 6 and the actual value. As shown in FIG. 7, a high correlation was confirmed between the predicted value and the measured value of the dose equivalent, and the correlation coefficient was "0.880". This verified that the predicted value of dose equivalent obtained by this method has high reliability.

Further, the dose equivalent prediction device 100 may support the operation of the nuclear power plant 1 using the prediction model M. FIG. 8 is a flowchart showing, step by step, the operation support method performed by the dose equivalent prediction device 100 of FIG. 6.

In the dose equivalent prediction apparatus 100, first, the prediction model M is acquired by the prediction model acquisition unit 106 (step S300), similarly to step S200. Subsequently, the contribution value calculation unit 120 analyzes the prediction model M acquired in step S300 to calculate the contribution to the second parameter Y for each of the first parameters X1, X2, ... included in the prediction model M. The respective degrees are calculated (step S301). For example, in the prediction model M expressed by equation (1), the importance of each first parameter is calculated using a statistical t value, P value, or the like. By calculating the contribution of each of the first parameters X1, X2, ... in this way, it is possible to quantitatively evaluate which first parameter has an influence on the second parameter Y and to what extent. .

Next, the control parameter calculation unit 122 calculates effective control parameters for reducing the dose equivalent of the equipment from the first parameters X1, X2, etc. based on the degree of contribution calculated in step S301 (step S302). For example, by preferentially calculating the first parameters X1, X2, etc. that have a large contribution to the second parameter Y, it becomes possible to provide operational support to effectively reduce the dose equivalent after the plant is shut down. .

Note that the control parameter calculated in step S302 may be singular or plural. Typically, in the prediction model M, a large number of first parameters and second parameters have a complex correlation, so in order to reduce the second parameter, a combination of a plurality of first parameters is calculated as a control parameter. Ru.

Subsequently, the driving support information creation unit 124 creates driving support information including the control parameters calculated in step S302 (step S303). Such driving support information is created, for example, by including the target value of the control parameter in step S303 so as to serve as a guideline when the user to whom the driving support information is provided adjusts the control parameter.

The driving support information created in this way is output from the output unit 114 (step S304). As a result, the user of the nuclear power plant 1 can effectively reduce the dose equivalent of the predicted equipment after the plant is shut down by controlling the first parameter acquired as the control parameter based on the operation support information. becomes.

Further, the dose equivalent prediction device 100 may perform learning control of the prediction model M as necessary. FIG. 9 is a flowchart showing the learning control of the prediction model M performed by the dose equivalent prediction apparatus 100 of FIG. 6 for each step.

In the dose equivalent prediction apparatus 100, first, the prediction model acquisition unit 106 acquires the prediction model M, similarly to step S200 (step S400). Subsequently, similarly to step S201, driving history data is acquired by the driving history data acquisition unit 108 (step S401).

Subsequently, the learning data evaluation unit 126 determines whether the driving history data acquired in step S401 is within the range of the learning data (driving history data acquired in step S102) used to construct the prediction model M acquired in step S400. It is determined whether or not it deviates from the above (step S402).

If the driving history data does not deviate from the learning data range (step S402: NO), the predictive model learning unit 128 does not relearn the predictive model M, and the current predictive model M is maintained (step S404).

On the other hand, if the driving history data deviates from the range of the learning data (step S402: YES), it is determined whether the amount of deviation of the driving history data from the learning data is within a specified range (step S403). If the deviation amount is within the specified range (step S403: YES), the driving history data acquired in step S401 is presumed to have relatively high reliability, so the predictive model learning unit 128 uses the driving history data. The prediction model M is re-trained using the prediction model M (step S405). Thereby, the accuracy of the prediction model M can be improved by learning based on new learning data that includes driving history data in a wider range than the existing learning data.

On the other hand, if the deviation amount is not within the specified range (step S403: NO), it is assumed that the reliability of the driving history data acquired in step S401 is relatively low. The current prediction model M is maintained without relearning (step S404).

As explained above, according to some embodiments, there is provided a dose equivalent prediction method, a dose equivalent prediction program, and a dose equivalent prediction program for the nuclear power plant 1 that can accurately predict the dose equivalent of the component equipment after the nuclear power plant 1 is shut down. A prediction device can be provided.

In addition, the components in the embodiments described above can be replaced with well-known components as appropriate without departing from the spirit of the present disclosure, and the embodiments described above may be combined as appropriate.

The contents described in each of the above embodiments can be understood as follows, for example.

(1) The dose equivalent prediction method for a nuclear power plant according to an embodiment of the present disclosure includes:
In a nuclear power plant (for example, the nuclear power plant 1 of the above embodiment) having a nuclear reactor (for example, the reactor vessel 6 of the above embodiment), operating parameters related to the nuclear power plant (for example, in FIG. and a shutdown operation parameter regarding the nuclear power plant during the shutdown operation period (for example, a first parameter candidate belonging to the major classification "shutdown operation parameter" in FIG. 3B of the above embodiment). Using a prediction model (for example, prediction model M of the above embodiment) that shows a correlation between the first parameter and a second parameter indicating the dose equivalent of the equipment constituting the nuclear power plant after the nuclear power plant has stopped operating, The method includes a step of calculating a predicted value of the second parameter using data corresponding to the first parameter (for example, steps S203 to S204 in the above embodiment).

According to the method (1) above, in addition to operating parameters, a prediction model that includes as input shutdown operation parameters related to the nuclear power plant during the shutdown operation period is used to predict the dose equivalent of the equipment after the shutdown operation. . During the shutdown operation period of a nuclear power plant, the state of the nuclear power plant changes dramatically compared to when the nuclear power plant is in operation, which affects the dose equivalent of the equipment after the shutdown. Therefore, by using a prediction model that includes stopping operation parameters, it becomes possible to predict dose equivalents with higher reliability than in the past.

(2) In the method for predicting the dose equivalent of a nuclear power plant according to one aspect, in the method of (1) above,
The shutdown operation parameters are parameters related to the operation of the nuclear power plant during the shutdown operation period (for example, the first parameter candidates belonging to the major classification "shutdown operation parameters" and the medium classification "operation parameters" in FIG. 3B of the above embodiment). include.

According to the method (2) above, dose equivalent prediction is performed using a prediction model that includes as input parameters regarding the operation of the nuclear power plant during the shutdown operation period. This makes it possible to predict dose equivalents that take into account the influence on dose equivalents due to the operating behavior of a nuclear power plant during a shutdown period, and provides superior reliability compared to the conventional method.

(3) In the method for predicting dose equivalent of a nuclear power plant according to one aspect, in the method of (1) or (2) above,
The shutdown operation parameters are parameters related to the water quality of cooling water (for example, primary cooling water in the above embodiment) passing through the reactor during the shutdown operation period (for example, in FIG. 3B of the above embodiment, the main classification is "shutdown operation parameters" and (first parameter candidate belonging to the intermediate classification "water quality parameter").

According to the method (3) above, dose equivalent prediction is performed using a prediction model that includes as input parameters regarding the quality of cooling water during the stop operation period. This makes it possible to predict the dose equivalent by taking into consideration the effect on the dose equivalent due to changes in the quality of the cooling water during the period of stop operation, and provides superior reliability compared to the conventional method.

(4) In the method for predicting the dose equivalent of a nuclear power plant according to one aspect, in any one of the methods (1) to (3) above,
The first parameters include equipment parameters related to at least one of materials and maintenance history of equipment constituting the nuclear power plant (for example, first parameter candidates belonging to the major category "equipment parameters" in FIG. 3A of the above embodiment).

According to the method (4) above, dose equivalent prediction is performed using a prediction model that includes as input parameters related to the materials or maintenance history of the components of the nuclear power plant. This makes it possible to predict the dose equivalent in consideration of the influence of the material or maintenance history of the component equipment on the dose equivalent, and provides superior reliability compared to the conventional method.

(5) In the method for predicting the dose equivalent of a nuclear power plant according to one aspect, in any one of the methods (1) to (4) above,
The operating parameters include parameters related to operations during the operation of the nuclear power plant (for example, first parameter candidates belonging to the major category "operating parameters" and the intermediate category "operating parameters" in FIG. 3A of the above embodiment).

According to the method (5) above, dose equivalent prediction is performed using a prediction model that includes as input parameters related to operations during operation of a nuclear power plant. This makes it possible to predict dose equivalents that take into account the influence of operations during nuclear plant operation on dose equivalents, and provides superior reliability compared to conventional techniques.

(6) In the radiation prediction method for a nuclear power plant according to one aspect, in any one of the methods (1) to (5) above,
The in-operation parameters include parameters related to the quality of cooling water (for example, primary cooling water in the above embodiment) passing through the nuclear reactor during operation.

According to the method (6) above, dose equivalent prediction is performed using a prediction model that includes as input parameters regarding the quality of cooling water during operation of a nuclear power plant. This makes it possible to predict dose equivalents that take into account the influence of the quality of cooling water during operation of nuclear power plants on dose equivalents, and provides superior reliability compared to conventional methods.

(7) In the method for predicting the dose equivalent of a nuclear power plant according to one aspect, in any one of the methods (1) to (6) above,
The first parameter includes a parameter related to the post-shutdown state of the nuclear power plant (for example, a first parameter candidate belonging to the broad category "post-shutdown parameter" in FIG. 3B of the above embodiment).

According to the method (7) above, dose equivalent prediction is performed using a prediction model that includes as input parameters regarding the post-shutdown state of the nuclear power plant. This makes it possible to predict dose equivalents that take into account the influence of the nuclear plant's post-shutdown state on dose equivalents, resulting in superior reliability compared to conventional methods.

(8) In the method for predicting the dose equivalent of a nuclear power plant according to one aspect, in any one of the methods (1) to (7) above,
The in-operation parameter is the lithium concentration of the cooling water before the outage period of the nuclear power plant (for example, in FIG. 3A of the above embodiment, the Contains the parameter candidate "concentration at the end of the cycle").

According to the method (8) above, dose equivalent prediction is performed using a prediction model that includes as input the lithium concentration of the cooling water before the shutdown period of the nuclear power plant (at the end of the cycle). Such parameters are factors that have a large influence on the dose equivalent of the equipment after shutdown, and by including them in the input of the prediction model, the accuracy of predicting the dose equivalent can be effectively improved.

(9) In the method for predicting the dose equivalent of a nuclear power plant according to one aspect, in any one of the methods (1) to (8) above,
The shutdown operation parameters include the lithium concentration of the cooling water passing through the nuclear reactor at the beginning of the shutdown operation period of the nuclear power plant (for example, in FIG. 3B of the above embodiment, the major classification "shutdown operation parameters" and the medium classification "water quality parameters") includes the first parameter candidate “concentration at the initial stage of the stop operation (during cool-down)”) belonging to the first parameter candidate.

According to the method (9) above, dose equivalent prediction is performed using a prediction model that includes as input the lithium concentration of the cooling water at the beginning of the shutdown operation period (during cool-down) of the nuclear power plant. Such parameters are factors that have a large influence on the dose equivalent of the equipment after shutdown, and by including them in the input of the prediction model, the accuracy of predicting the dose equivalent can be effectively improved.

(10) In the method for predicting the dose equivalent of a nuclear power plant according to one aspect, in any one of the methods (1) to (9) above,
The shutdown operation parameters are parameters related to the flow rate of cooling water passing through the nuclear reactor during the shutdown operation period of the nuclear power plant (for example, in FIG. 3B of the above embodiment, the major classification "shutdown operation parameters" and the medium classification "operation parameters") The first parameter candidate belonging to "the number of operating primary cooling water pumps at the end of the stop operation (during oxidation operation)") is included.

According to the method (10) above, dose equivalent prediction is performed using a prediction model that includes as input a parameter regarding the flow rate of cooling water during a period of shutdown operation of a nuclear power plant. Such parameters are factors that have a large influence on the dose equivalent of the equipment after shutdown, and by including them in the input of the prediction model, the accuracy of predicting the dose equivalent can be effectively improved.

(11) In the method for predicting dose equivalent of a nuclear power plant according to one aspect, in the method of (10) above,
The parameter is the number of operating units or output of a pump device (for example, the primary cooling water pump 12 of the above embodiment) for pumping the cooling water.

According to the method (11) above, dose equivalent prediction is performed using a prediction model that includes as input the number of operating pump devices or the output of pump devices for pumping the cooling water as a parameter regarding the flow rate of the cooling water. Such parameters are factors that have a large influence on the dose equivalent of the equipment after shutdown, and by including them in the input of the prediction model, the accuracy of predicting the dose equivalent can be effectively improved.

(12) In the method for predicting dose equivalent for a nuclear power plant according to one aspect, in any one of the methods (1) to (11) above,
a step of acquiring operation history data of the nuclear power plant (for example, steps S102 and S201 of the above embodiment);
a step of calculating the stopping operation parameter from the driving history data (for example, steps S103 and S202 in the above embodiment);
It further includes:

According to the method (12) above, the shutdown operation parameters used in the prediction model can be calculated from the operation history data of the nuclear power plant.

(13) In the method for predicting the dose equivalent of a nuclear power plant according to one aspect, in any one of the methods (1) to (12) above,
a step of acquiring operation history data of the nuclear power plant (for example, step S102 of the above embodiment);
creating the prediction model by performing multivariate analysis on the first parameter and the second parameter calculated from the driving history data (for example, step S104 in the above embodiment);
It further includes:

According to the method (13) above, the above-mentioned predictive model can be created by performing multivariate analysis on a data set including the first parameter and the second parameter. By predicting the dose equivalent using the prediction model created in this way, superior reliability can be obtained compared to the conventional method.

(14) In the method for predicting dose equivalent of a nuclear power plant according to one aspect, in any one of the methods (1) to (13) above,
Calculating the degree of contribution of each of the first parameters to the second parameter (for example, step S301 in the above embodiment);
determining a control parameter effective for reducing the dose equivalent of the device based on the degree of contribution from the first parameter (for example, step S302 in the above embodiment);
It further includes:

According to the method (14) above, calculating the contribution of each parameter included in the first parameter to the second parameter is effective for reducing the dose equivalent of the equipment from each parameter included in the first parameter. It is possible to obtain control parameters. By employing the control parameters determined in this way, the dose equivalent of the equipment can be effectively reduced.

(15) In the method for predicting the dose equivalent of a nuclear power plant according to one aspect, in any one of the methods (1) to (14) above,
a step of acquiring operation history data of the nuclear power plant (for example, step S401 of the above embodiment);
When the first parameter included in the driving history data deviates from the range of learning data used to construct the prediction model, the amount of deviation of the first parameter included in the driving history data from the learning data is If it is within a specified range, relearning the predictive model using the driving history data (for example, steps S402, S403, and S405 in the above embodiment);
Equipped with

According to the method (15) above, when a dataset that deviates from the range of the training data used to construct the predictive model is obtained, on the condition that the amount of deviation of the dataset is within the specified range, The predictive model will be retrained. By relearning the prediction model using the data set, a prediction model with improved reliability can be obtained. By using a prediction model obtained by repeating learning in accordance with the acquisition of data sets in this way, it becomes possible to predict dose equivalents with higher reliability.

(16) In the method for predicting dose equivalent of a nuclear power plant according to one aspect, in any one of the methods (1) to (15) above,
The nuclear power plant is a pressurized water reactor,
The equipment is a component of the primary cooling system of the pressurized water reactor.

According to the method (16) above, it is possible to accurately predict the dose equivalent in the components of the primary cooling system of a nuclear power plant having a pressurized water reactor.

(17) A dose equivalent prediction program for a nuclear power plant according to an embodiment of the present disclosure includes:
computer,
In a nuclear power plant (for example, the nuclear power plant 1 of the above embodiment) having a nuclear reactor (for example, the reactor vessel 6 of the above embodiment), operating parameters regarding the nuclear power plant in operation (for example, the major classification in FIG. 3A of the above embodiment) (a first parameter candidate belonging to "in-operation parameters"), and a shutdown operation parameter regarding the nuclear power plant during the shutdown operation period (for example, a first parameter candidate belonging to the major classification "shutdown operation parameter" in FIG. 3B of the above embodiment) using a prediction model (for example, prediction model M of the above embodiment) that shows a correlation between a first parameter that includes at least Then, it functions as a means (for example, the predicted value calculation unit 112 of the above embodiment) for calculating the predicted value of the second parameter using the data corresponding to the first parameter.

According to the program (17) above, in addition to the operating parameters, a prediction model that includes as input the shutdown operation parameters related to the nuclear power plant during the shutdown operation period is used to predict the dose equivalent of the equipment after the shutdown operation. . During the shutdown operation period of a nuclear power plant, the state of the nuclear power plant changes dramatically compared to when the nuclear power plant is in operation, which affects the dose equivalent of the equipment after the shutdown. Therefore, by using a prediction model that includes stopping motion parameters, it becomes possible to predict radiation with higher reliability than in the past.

(18) The dose equivalent prediction device for a nuclear power plant according to an embodiment of the present disclosure includes:
In a nuclear power plant (for example, the nuclear power plant 1 of the above embodiment) having a nuclear reactor (for example, the reactor vessel 6 of the above embodiment), operating parameters regarding the nuclear power plant in operation (for example, the major classification in FIG. 3A of the above embodiment) (a first parameter candidate belonging to "in-operation parameters"), and a shutdown operation parameter regarding the nuclear power plant during the shutdown operation period (for example, a first parameter candidate belonging to the major classification "shutdown operation parameter" in FIG. 3B of the above embodiment) using a prediction model (for example, prediction model M of the above embodiment) that shows a correlation between a first parameter that includes at least The apparatus includes a predicted value calculation section (for example, the predicted value calculation section 112 of the above embodiment) configured to calculate a predicted value of the second parameter using data corresponding to the first parameter.

According to the apparatus in (18) above, in addition to the operating parameters, the dose equivalent of the equipment after the shutdown is performed using a prediction model that includes as input the shutdown operation parameters related to the nuclear power plant during the shutdown operation period. . During the shutdown operation period of a nuclear power plant, the state of the nuclear power plant changes dramatically compared to when the nuclear power plant is in operation, which affects the dose equivalent of the equipment after the shutdown. Therefore, by using a prediction model that includes stopping motion parameters, it becomes possible to predict radiation with higher reliability than in the past.

1 Nuclear power plant 2 Reactor 4 Primary cooling loop 6 Reactor vessel 8 Pressurizer 10 Steam generator 12 Primary cooling water pump 13 Reactor containment vessel 14 Fuel rods 16 Control rods 18 Secondary cooling loop 20 Desalination tower 22 Volume control tank 24 Filling pump 26 Purification line 100 Dose equivalent prediction device 102 Communication network 104 Main server 105 Data server 106 Prediction model acquisition section 108 Operation history data acquisition section 110 Parameter calculation section 112 Predicted value calculation section 114 Output section 116 Operation history database 118 Prediction model Database 120 Contribution value calculation section 122 Control parameter calculation section 124 Driving support information creation section 126 Learning data evaluation section 128 Prediction model learning section L First parameter candidate list M Prediction model

Claims (19)

In a nuclear power plant having a nuclear reactor, a first parameter including at least an in-operation parameter regarding the nuclear power plant during operation and a shutdown operation parameter regarding the nuclear power plant during a shutdown operation period; using a prediction model showing a correlation with a second parameter indicating a dose equivalent of equipment constituting a nuclear power plant, and obtaining a predicted value of the second parameter from data corresponding to the first parameter ;
A method for predicting a dose equivalent of a nuclear power plant, wherein the first parameter includes an equipment parameter regarding at least one of materials used or maintenance history regarding equipment constituting the nuclear power plant. The nuclear power plant dose equivalent prediction method according to claim 1, wherein the shutdown operation parameters include parameters related to the operation of the nuclear power plant during the shutdown operation period. 3. The method for predicting dose equivalents of a nuclear power plant according to claim 1, wherein the shutdown operation parameters include parameters related to the quality of cooling water passing through the reactor during the shutdown operation period. The nuclear power plant dose equivalent prediction method according to any one of claims 1 to 3 , wherein the in-operation parameters include parameters related to operations during operation of the nuclear power plant. The method for predicting dose equivalents of a nuclear power plant according to any one of claims 1 to 4 , wherein the in-operation parameters include parameters related to the quality of cooling water passing through the nuclear reactor during operation. The method for predicting dose equivalent of a nuclear power plant according to any one of claims 1 to 5 , wherein the first parameter includes a post-shutdown parameter regarding the state of the nuclear power plant after it is shut down. The method for predicting dose equivalent of a nuclear power plant according to any one of claims 1 to 6 , wherein the in-operation parameter includes a lithium concentration of cooling water passing through the nuclear reactor before the shutdown operation period of the nuclear power plant. . The method for predicting dose equivalent of a nuclear power plant according to any one of claims 1 to 7 , wherein the shutdown operation parameter includes a lithium concentration of cooling water passing through the nuclear reactor at the beginning of the shutdown operation period of the nuclear power plant. . The nuclear power plant dose equivalent prediction method according to any one of claims 1 to 8 , wherein the shutdown operation parameters include parameters regarding the flow rate of cooling water passing through the nuclear reactor during the shutdown operation period of the nuclear power plant. . 10. The method for predicting dose equivalent of a nuclear power plant according to claim 9 , wherein the parameter regarding the flow rate of the cooling water is the number of operating pump devices or the output of pump devices for pumping the cooling water. acquiring operation history data of the nuclear power plant;
calculating the first parameter from the driving history data;
The method for predicting dose equivalent of a nuclear power plant according to any one of claims 1 to 10 , further comprising: acquiring the operation history data of the nuclear power plant;
creating the prediction model by performing multivariate analysis on the first parameter and the second parameter calculated from the driving history data;
The method for predicting dose equivalent of a nuclear power plant according to claim 11 , further comprising: calculating the contribution of each of the first parameters to the second parameter;
determining a control parameter effective for reducing the dose equivalent of the device based on the degree of contribution from the first parameter;
The dose equivalent prediction method for a nuclear power plant according to any one of claims 1 to 12 , further comprising: acquiring operation history data of the nuclear power plant;
When the first parameter included in the driving history data deviates from the range of learning data used to construct the prediction model, the amount of deviation of the first parameter included in the driving history data from the learning data is If it is within a specified range, relearning the prediction model using the driving history data;
The dose equivalent prediction method for a nuclear power plant according to any one of claims 1 to 13 , comprising: The nuclear power plant is a pressurized water reactor,
The method for predicting dose equivalents in a nuclear power plant according to any one of claims 1 to 14, wherein the equipment is a component of a primary cooling system of the pressurized water reactor. In a nuclear power plant having a nuclear reactor, a first parameter including at least an in-operation parameter regarding the nuclear power plant during operation and a shutdown operation parameter regarding the nuclear power plant during a shutdown operation period; using a prediction model showing a correlation with a second parameter indicating a dose equivalent of equipment constituting a nuclear power plant, and obtaining a predicted value of the second parameter from data corresponding to the first parameter;
A method for predicting a dose equivalent of a nuclear power plant, wherein the first parameter includes a post-shutdown parameter regarding a state of the nuclear power plant after it is shut down. In a nuclear power plant having a nuclear reactor, a first parameter including at least an in-operation parameter regarding the nuclear power plant during operation and a shutdown operation parameter regarding the nuclear power plant during a shutdown operation period; using a prediction model showing a correlation with a second parameter indicating a dose equivalent of equipment constituting a nuclear power plant, and obtaining a predicted value of the second parameter from data corresponding to the first parameter;
A method for predicting dose equivalents in a nuclear power plant, wherein the shutdown operation parameter includes a lithium concentration in cooling water passing through the nuclear reactor at the beginning of the shutdown operation period of the nuclear power plant. computer,
In a nuclear power plant having a nuclear reactor, a first parameter including at least an in-operation parameter regarding the nuclear power plant during operation and a shutdown operation parameter regarding the nuclear power plant during a shutdown operation period; Functioning as means for determining the predicted value of the second parameter from data corresponding to the first parameter using a prediction model that shows a correlation with a second parameter indicating the dose equivalent of equipment constituting the nuclear power plant ,
The first parameter is a dose equivalent prediction program for a nuclear power plant, wherein the first parameter includes an equipment parameter regarding at least one of materials used or maintenance history regarding equipment constituting the nuclear power plant. In a nuclear power plant having a nuclear reactor, a first parameter including at least an in-operation parameter regarding the nuclear power plant during operation and a shutdown operation parameter regarding the nuclear power plant during a shutdown operation period; A predicted value configured to obtain a predicted value of the second parameter from data corresponding to the first parameter using a prediction model that shows a correlation with a second parameter indicating a dose equivalent of equipment constituting a nuclear power plant. Equipped with a calculation section ,
A dose equivalent prediction device for a nuclear power plant, wherein the first parameter includes an equipment parameter regarding at least one of materials used or maintenance history regarding equipment constituting the nuclear power plant.

Images