Device for prediction of reactor water quality of nuclear reactor

1. A device for prediction of reactor water quality of a nuclear reactor in a nuclear power plant, the device comprising:

one or more processors;

a display device; and

one or more storage devices, wherein

the one or more storage devices store a reactor water quality prediction model which is learned using learning data and with which future reactor water quality is predicted,

an explanatory variable of the reactor water quality prediction model includes a value in a predetermined period unit that is generated from data acquired in an operating nuclear power plant;

the one or more processors are configured to:

generate the value in a predetermined period unit from data acquired in a target nuclear power plant by calculating, as at least a part of the explanatory variable, a daily metal impurity accumulation amount in the nuclear reactor in the target nuclear power plant based on:

a fuel change history held on a cycle-by-cycle basis; and

a daily supplied water quality measured value;

acquire a first predicted value of the reactor water quality in the target nuclear power plant based on:

the reactor water quality prediction model; and

the value in a predetermined period unit;

receive information of a plurality of countermeasures for improving the reactor water quality; and

upon receiving the information of the plurality of countermeasures:

acquire other predicted values of the reactor water quality in the target nuclear power plant based on the countermeasures by inputting assumed values for the countermeasures, respectively and

simultaneously display, on the display device:

the first predicted value which is not based on a countermeasures; and

the other predicted values which are based on the countermeasures, respectively,

to enable comparison to determine an appropriate countermeasure from the plurality of countermeasures.

2. The device according to claim 1 , wherein

the data acquired in the target nuclear power plant includes values in different period units, and

the one or more processors are configured to generate the value in a predetermined period unit from each of the values in different period units.

3. The device according to claim 1 , wherein

the explanatory variable of the reactor water quality prediction model includes a fixed value of a component constituting the nuclear power plant.

4. The device according to claim 1 , wherein

the value in a predetermined period unit is a value within an operation cycle of the target nuclear power plant, and

the one or more processors are configured to acquire a predicted value of the reactor water quality in the target nuclear power plant in the future within the operation cycle from the reactor water quality prediction model.

5. The device according to claim 1 , wherein

the learning data includes previous data of a nuclear power plant different from the target nuclear power plant.

6. The device according to claim 1 , wherein

the one or more processors are configured to execute learning of the reactor water quality prediction model with the data acquired in the target nuclear power plant serving as learning data.

7. The device according to claim 1 , wherein

the explanatory variable of the reactor water quality prediction model includes a water supply system measured value and a reactor water system measured value older than the water supply system measured value.

8. The device according to claim 1 , wherein

the reactor water quality prediction model predicts a future value of a variable included in the explanatory variable of the reactor water quality prediction model,

the explanatory variable includes a changing value in the target nuclear power plant, and

the one or more processors are configured to acquire a future second predicted value from a first predicted value of the reactor water quality prediction model based on the reactor water quality prediction model, the first prediction value, and an assumed value of the changing value.

9. The device according to claim 1 , wherein

the one or more processors are configured to output the predicted value of the reactor water quality in the target nuclear power plant to an output device.

10. A method for prediction of reactor water quality of a nuclear reactor in a nuclear power plant by a device, wherein

the device comprises one or more processors,

the device stores a reactor water quality prediction model which is learned using learning data and with which future reactor water quality is predicted, and

an explanatory variable of the reactor water quality prediction model includes a value in a predetermined period unit that is generated from data acquired in an operating nuclear power plant,

the method comprising the steps of:

generating, by the device, the value in a predetermined period unit from data acquired in a target nuclear power plant by calculating, as at least a part of the explanatory variable, a daily metal impurity accumulation amount in the nuclear reactor in the target nuclear power plant based on:

a fuel change history held on a cycle-by-cycle basis; and

a daily supplied water quality measured value;

acquiring, by the device, a first predicted value of the reactor water quality in the target nuclear power plant based on:

the reactor water quality prediction model; and

the value in a predetermined period unit;

receiving, by the device, information of a plurality of countermeasures for improving the reactor water quality; and

upon receiving the information of the plurality of countermeasures:

acquiring other predicted values of the reactor water quality in the target nuclear power plant based on the countermeasures by inputting assumed values for the countermeasures, respectively; and

simultaneously displaying on a display device:

the first predicted value which is not based on a countermeasure; and

the other predicted values which are based on the countermeasures, respectively,

to enable comparison to determine an appropriate countermeasure from the plurality of countermeasures.