Radioactive waste disposal system and radioactive waste disposal method

Abstract

To adjust kneading viscosity of slurry to an appropriate range when solidifying radioactive waste using a geopolymer.SOLUTION: A radioactive waste disposal system 1 includes: acquiring influence information regarding kneading viscosity when radioactive waste being a solidification processed target is kneaded with a geopolymer material for solidifying the radioactive waste; acquiring influence information regarding kneading viscosity when the geopolymer material is kneaded with the radioactive waste; inputting the influence information of the radioactive waste and the influence information of the geopolymer material as input data D5 into a mixing prediction model M3 subjected to machine learning; and determining, based on output data D6 outputted from the mixing prediction model M3, mixing amounts of the radioactive waste and the geopolymer material to be supplied into a kneading vessel 22 for kneading the radioactive waste and the geopolymer material.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] FIELD OF THE DISCLOSURE Embodiments of the present invention relate to radioactive waste processing. [Background technology]

[0002] One of the problems in storing high-dose radioactive waste is that water in the storage container is radiolyzed and hydrogen is generated. Therefore, it is required to remove water, which is a source of hydrogen generation, from the storage container as much as possible. Geopolymers are considered to be amorphous inorganic polymers composed of elements such as silicon (Si) and aluminum (Al). They are also the same inorganic material as cement, but unlike cement, they do not have hydrates. This geopolymer is attracting attention as a material for solidifying radioactive waste because it does not contain water in its basic structure and the material is less altered compared to cement even when dried and dehydrated. However, the slurry obtained by kneading a base material containing elements such as Si or Al with raw materials such as an alkaline material has the characteristic of being prone to viscosity increase. This slurry can cause an unexpected decrease in fluidity, which can cause, for example, adhesion to equipment piping or poor waste solidification, which can have a negative impact on the waste treatment process. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6926017 Summary of the Invention [Problem to be solved by the invention]

[0004] Known viscosity control techniques for geopolymer slurries include adjusting the geopolymer mix and adding additives. However, the ion concentration and water content of waste vary depending on the operating conditions of the waste source and are not constant. For this reason, conventional viscosity control techniques that do not take into account the properties of the waste may not be sufficient.

[0005] The embodiment of the present invention has been made in consideration of these circumstances, and aims to adjust the kneading viscosity of the slurry to an appropriate range when solidifying radioactive waste using a geopolymer. [Means for solving the problem]

[0006] The radioactive waste treatment system according to an embodiment of the present invention includes one or more computers configured to: acquire impact information related to the kneading viscosity when the radioactive waste to be solidified is kneaded with a geopolymer material for solidifying the radioactive waste; acquire impact information related to the kneading viscosity when the geopolymer material is kneaded with the radioactive waste; input the impact information of the radioactive waste and the impact information of the geopolymer material as input data into a machine-learned blending prediction model; and determine the blending amounts of the radioactive waste and the geopolymer material to be put into a kneading vessel for kneading the radioactive waste and the geopolymer material based on the output data output from the blending prediction model. Effect of the Invention

[0007] According to an embodiment of the present invention, the kneading viscosity of the slurry can be adjusted to an appropriate range when solidifying radioactive waste using a geopolymer. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a configuration diagram showing a radioactive waste treatment system. [Diagram 2] 1 is a flow chart showing radioactive waste treatment. [Diagram 3] FIG. 2 is an explanatory diagram showing the flow of input and output data of the waste prediction model. [Figure 4] FIG. 4 is an explanatory diagram showing the flow of input and output data of a material prediction model. [Diagram 5] An explanatory diagram showing the input / output data and judgment flow of the blend prediction model. [Figure 6] 11 is a flowchart showing a kneading state determination process. [Figure 7] FIG. 13 is an explanatory diagram showing the input / output data and judgment flow of the addition prediction model. [Figure 8] 1 is a graph showing the relationship between the concentration ratio of silicon to aluminum and the kneading viscosity. [Figure 9] Graph showing the relationship between the amount of blast furnace slag added and kneaded viscosity. [Figure 10] 1 is a graph showing the relationship between the amount of fly ash added and kneading viscosity. [Figure 11] 1 is a graph showing the relationship between the amount of boric acid added and kneading viscosity. [Figure 12] 1 is a graph showing the relationship between solid content concentration and kneading viscosity. [Figure 13] 4 is a graph showing the relationship between the current value of the kneading device and the kneading viscosity. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, embodiments of a radioactive waste treatment system and a radioactive waste treatment method will be described in detail with reference to the drawings.

[0010] Reference numeral 1 in Fig. 1 denotes a radioactive waste treatment system according to this embodiment. A radioactive waste treatment method is carried out using this radioactive waste treatment system 1. The radioactive waste treatment system 1 kneads radioactive waste with a geopolymer material to form a solidified body suitable for burial disposal. Here, the radioactive waste treatment system 1 determines the mixing ratio when kneading the radioactive waste and the geopolymer material by a trained model in which parameters have been machine-learned in advance.

[0011] The geopolymer material is a mixture containing a base material and an alkaline material. The base material includes at least one of metakaolin, blast furnace slag, incineration ash, fly ash, zeolite, and mordenite. The alkaline material includes at least one of lithium hydroxide, sodium hydroxide, potassium hydroxide, rubidium hydroxide, cesium hydroxide, lithium silicate, sodium silicate, potassium silicate, rubidium silicate, cesium silicate, orthosilicate, and metasilicate.

[0012] The radioactive waste treatment system 1 includes an alkaline solution tank 2, an alkaline material tank 3, a first base material powder tank 4, a second base material powder tank 5, a waste tank 6, an additive tank 7, a first mixing tank 8, and a second mixing tank 9.

[0013] The radioactive waste treatment system 1 also includes an alkaline solution metering tank 10 , an alkaline material metering tank 11 , a first base material powder metering tank 12 , a second base material powder metering tank 13 , a waste metering tank 14 , and an additive metering tank 15 .

[0014] Furthermore, the radioactive waste treatment system 1 includes a base powder information acquisition device 16, a waste information acquisition device 17, a kneading device 18, a status acquisition device 19, a base material mixing computer 20, and a mix design computer 21.

[0015] The radioactive waste treatment system 1 may include components other than those shown in FIG. 1, and some of the components shown in FIG. 1 may be omitted.

[0016] The alkaline solution tank 2 is a tank for storing the alkaline solution to be fed into the kneading device 18. The alkaline solution contains water necessary for solidifying the geopolymer material. The alkaline solution may also contain an aqueous solution of an alkaline material.

[0017] The alkaline material storage tank 3 is a tank for storing the alkaline material to be fed into the kneading device 18. The alkaline material includes at least one of an alkaline hydroxide and an alkaline silicate. The alkaline hydroxide includes at least one of lithium hydroxide, sodium hydroxide, potassium hydroxide, rubidium hydroxide, and cesium hydroxide. The alkaline silicate includes at least one of lithium silicate, sodium silicate, potassium silicate, rubidium silicate, and cesium silicate. The silicate includes at least one of an orthosilicate and a metasilicate. In addition to these materials, an aluminate may be added as an alkaline material.

[0018] The first base powder storage tank 4 is a tank for storing the first base powder of the geopolymer material to be fed into the kneading device 18. The first base powder is, for example, silica powder. The second base powder storage tank 5 is a tank for storing the second base powder of the geopolymer material to be fed into the kneading device 18.

[0019] The second base powder is a geopolymer base material, and is, for example, a material containing at least one of silicon and aluminum as an element. The second base powder is, for example, alumina silica. This second base powder contains at least one of metakaolin, blast furnace slag, incineration ash, fly ash, zeolite, and mordenite. The alumina silica may also be a mixture of a material of aluminum element alone and a material of silicon element alone.

[0020] The measured values ​​of these substances that are the base material of the geopolymer are managed by the base material mixing computer 20. These measured values ​​are linked to information on the base material mixture, such as the Si concentration, Al concentration, Ca concentration, boric acid concentration, amount of fly ash added, and moisture content.

[0021] The waste storage tank 6 is a tank for storing the radioactive waste to be fed into the kneading device 18. Information on the radioactive waste, such as the solids concentration, Si concentration, Al concentration, Ca concentration, boric acid concentration, and water content, is managed by a mix design computer 21.

[0022] The additive storage tank 7 is a tank for storing the additive to be fed into the kneading device 18. The additive contains at least boric acid. The additive may contain an additional geopolymer material.

[0023] The first mixing tank 8 is a tank in which materials fed from the alkaline solution tank 2, the alkaline material tank 3, and the first base powder tank 4 are mixed. The second mixing tank 9 is a tank in which materials fed from the first mixing tank 8, the second base powder tank 5, the waste tank 6, and the additive tank 7 are mixed. This mixed material is fed from the second mixing tank 9 to the kneading device 18. For example, the basic blending of the geopolymer material is performed in the first mixing tank 8, and the subsequent adjustment of the blending amount is performed in the second mixing tank 9. In this way, it becomes easier to adjust the blending of the geopolymer material.

[0024] The kneading device 18 kneads the radioactive waste, the geopolymer material, and other materials fed from the respective tanks. The kneading device 18 includes a kneading vessel 22, a stirring motor 23, a stirring shaft 24, and a stirring blade 25.

[0025] A mixture of radioactive waste and geopolymer material is fed into the kneading vessel 22. These feed materials are then kneaded in the kneading vessel 22. The stirring motor 23 is connected to a stirring shaft 24, and a stirring blade 25 is fixed to the lower end of the stirring shaft 24. When the stirring motor 23 is driven, the stirring blade 25 rotates via the stirring shaft 24. The rotation of the stirring blade 25 kneads the radioactive waste and geopolymer material.

[0026] The kneading device 18 has a function of kneading while feeding the input materials into the kneading container 22. In other words, the input materials are continued to be fed into the kneading container 22 while kneading is continued. For example, when the input materials are fed into the kneading container 22 in two batches, one at the front stage and one at the rear stage, the blending amount of the input materials in the front stage and the blending amount of the input materials in the rear stage may be different. When the blending amount of the input materials in the front stage is not appropriate, the blending amount of the input materials in the rear stage can be adjusted to an appropriate total blending amount.

[0027] The state acquisition device 19 acquires kneading state information indicating the state of the mixture, such as the radioactive waste and the geopolymer material, being kneaded in the kneading container 22. The kneading state information includes at least one of the current value or torque value of the stirring motor 23 provided in the kneading device 18, the image of the inside of the kneading container 22, the temperature in the kneading container 22, and the kneading viscosity measured by a viscometer attached to the kneading container 22. In this way, the viscosity of the radioactive waste and the geopolymer material being kneaded in the kneading container 22 can be acquired from the current value or torque value of the stirring motor 23, the image of the inside of the kneading container 22, or the kneading viscosity measured by a viscometer. In addition, the temperature of the radioactive waste and the geopolymer material being kneaded in the kneading container 22 can be acquired from the temperature in the kneading container 22.

[0028] The state acquisition device 19 has sensors such as an ammeter, a torque meter, a camera, a thermometer, and a viscometer. The kneading state information acquired by the state acquisition device 19 is sent to the blending design computer 21. When an image of the inside of the kneading container 22 is acquired, the user may check the image once, and the confirmation result may be input to the blending design computer 21. The confirmation result includes the result of the user's judgment of the quality of the kneading state when the user visually checks the image.

[0029] 13 is a graph showing the relationship between the current value of the stirring motor 23 of the kneading device 18 and the viscosity of the kneaded material. The current value and the torque value of the stirring motor 23 of the kneading device 18 are correlated with the viscosity of the kneaded material. Therefore, the viscosity of the kneaded material can be estimated from the current value of the stirring motor 23 of the kneading device 18.

[0030] Figure 12 is a graph showing the relationship between the particle shape of geopolymer material and the viscosity of the mixture. For example, when the solid content in the geopolymer material increases, the apparent viscosity increases. Furthermore, based on the relationship between the particle shape and the viscosity of the mixture, it can be said that these physical properties are correlated with viscosity. The relationship between the particle shape and the viscosity of the mixture is expressed by the following relationship.

[0031]

number

[0032]

number

[0033] Here, η m and η c is the apparent viscosity of the geopolymer material. s m , φ g m is the actual volume ratio of fine aggregate and coarse aggregate. β s and β g is a shape coefficient that depends on the particle shape and particle size of the fine and coarse aggregates. The coefficients a and b are called solidification coefficients, and indicate that the geopolymer slurry becomes a solid (suspended solid) that does not flow due to compaction or adhesion to the aggregate surface.

[0034] 8 is a graph showing the relationship between the concentration ratio of silicon to aluminum in a slurry and the kneading viscosity. It can be seen that the apparent viscosity increases as the Si / Al ratio in the slurry increases.

[0035] Figure 9 is a graph showing the relationship between the amount of blast furnace slag added and the viscosity of the mixture. It shows the change in viscosity over time when part of the base material metakaolin is replaced with blast furnace slag, the main component of which is calcium. It can be seen that as the replacement rate with blast furnace slag increases, the viscosity of the slurry also increases, because a gel consisting of dissolved calcium and either silicon or aluminum, or both, is generated.

[0036] Figure 10 is a graph showing the relationship between the amount of fly ash added and kneaded viscosity. It shows the change in kneaded viscosity over time when part of the base material metakaolin is replaced with fly ash, which is said to have good fluidity. It can be seen that the kneaded viscosity is suppressed by increasing the amount of fly ash added.

[0037] 11 is a graph showing the relationship between the amount of boric acid added and the kneading viscosity. It can be seen that the kneading viscosity is suppressed by increasing the amount of boric acid added.

[0038] In conventional technology, the properties of radioactive waste cannot be controlled to a constant level, and the operating conditions and mixing amount cannot be significantly changed depending on the mixing state because of the impact on the downstream treatment process. Therefore, the radioactive waste treatment system 1 aims to suppress the occurrence of poor mixing by using machine learning to adjust the optimal mixing amount within the design specifications according to the components of the radioactive waste, the components of the geopolymer material, and the mixing state.

[0039] 1, the alkaline solution metering tank 10 measures the amount of alkaline solution that is guided from the alkaline solution metering tank 10 to the first mixing tank 8. The alkaline solution metering tank 10 also adjusts the flow rate of the alkaline solution that flows toward the first mixing tank 8. Note that the adjustment of the flow rate in this embodiment includes switching between a flow state and a non-flow state.

[0040] The alkaline material metering tank 11 measures the amount of alkaline material introduced from the alkaline material metering tank 11 to the first mixing tank 8. The alkaline material metering tank 11 also adjusts the flow rate of the alkaline material flowing toward the first mixing tank 8.

[0041] The first base powder metering tank 12 measures the first base powder that is introduced from the first base powder metering tank 12 to the first mixing tank 8. The first base powder metering tank 12 also adjusts the flow rate of the first base powder that flows toward the first mixing tank 8.

[0042] The second base powder metering tank 13 measures the second base powder that is guided from the second base powder metering tank 13 to the second mixing tank 9. The second base powder metering tank 13 also adjusts the flow rate of the second base powder that flows toward the second mixing tank 9.

[0043] The base material mixing computer 20 controls the alkaline solution metering tank 10, the alkaline material metering tank 11, the first base material powder metering tank 12, and the second base material powder metering tank 13. Various data acquired in the alkaline solution metering tank 10, the alkaline material metering tank 11, the first base material powder metering tank 12, and the second base material powder metering tank 13 are sent to the base material mixing computer 20.

[0044] The waste metering tank 14 measures the amount of radioactive waste that is guided from the waste storage tank 6 to the second mixing tank 9. The waste metering tank 14 also adjusts the flow rate of the radioactive waste that flows toward the second mixing tank 9.

[0045] The additive metering tank 15 measures the additive introduced from the additive storage tank 7 to the second mixing tank 9. The additive metering tank 15 also adjusts the flow rate of the additive flowing toward the second mixing tank 9.

[0046] The blend design computer 21 controls the waste material metering tank 14 and the additive material metering tank 15. Various data acquired by the waste material metering tank 14 and the additive material metering tank 15 are sent to the blend design computer 21.

[0047] In this embodiment, an in-drum mixing system is illustrated. Note that this embodiment is not limited to the in-drum mixing system, and an out-drum mixing system may also be applied.

[0048] The base powder information acquisition device 16 acquires various data of the second base powder stored in the second base powder measuring tank 13 in order to acquire information on the effects of the geopolymer material. This various data includes component information related to the components of the geopolymer material. The various data acquired by the base powder information acquisition device 16 is sent to the base material mixing computer 20.

[0049] The base material mixing computer 20 adjusts the composition of the mixture of geopolymer materials mixed in the first mixing tank 8 and the second mixing tank 9. Various data acquired by the base material mixing computer 20 is sent to the composition design computer 21. In addition, the base material mixing computer 20 adjusts the composition of the mixture of geopolymer materials based on the various data sent from the composition design computer 21.

[0050] The waste information acquisition device 17 acquires various data on the radioactive waste stored in the waste measuring tank 14 in order to acquire information on the effects of the radioactive waste. This various data includes component information related to the components of the radioactive waste. The various data acquired by the waste information acquisition device 17 is sent to the mix design computer 21.

[0051] The mix design computer 21 comprehensively controls the radioactive waste treatment system 1. The radioactive waste treatment method of this embodiment is realized by executing various programs on the mix design computer 21. The mix design computer 21 includes at least a processing circuit and a memory unit.

[0052] The processing circuit is, for example, a circuit equipped with a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or a dedicated or general-purpose processor. This processor realizes various functions by executing various programs stored in a storage unit. The processing circuit may also be configured with hardware such as an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit). Various functions can also be realized by such hardware. The processing circuit can also realize various functions by combining software processing by a processor and a program with hardware processing.

[0053] The storage unit stores various information required for performing radioactive waste treatment. For example, the storage unit stores a predetermined program executed by the processing circuit. The storage unit also stores a trained model.

[0054] The trained model includes an input layer, an intermediate layer, and an output layer. Input data is input to the input layer. The intermediate layer has its parameters trained in advance by machine learning using training data. The output layer outputs output data indicating the results of processing in the intermediate layer in response to input data input to the input layer.

[0055] The trained model is machine-trained using training data in which at least one of the input data or data simulating the input data is input, and at least one of the output data or data simulating the input data is output.

[0056] The machine learning of this embodiment includes at least one of a neural network, XGBoost (a method for enhancing decision trees and random forests), a k-nearest neighbor method, a support vector machine, a random forest, a decision tree, and a linear regression. In the following description, a neural network is exemplified.

[0057] The mix design computer 21 includes artificial intelligence (AI). The mix design computer 21 may also include a deep learning unit that extracts a specific pattern from multiple patterns based on deep learning.

[0058] A mathematical algorithm such as a deep learning algorithm or regression analysis can be used for the analysis using the mix design computer 21. In addition, the form of machine learning includes forms such as clustering and deep learning.

[0059] For example, a neural network is provided with an intermediate layer having multiple layers. Each intermediate layer is composed of multiple units. In addition, by having the multi-layered neural network learn in advance using learning data (teacher data), it is possible to automatically extract feature quantities in patterns of changes in the state of the system. Note that the number of intermediate layers, the number of units, the learning rate, the number of learning times, and the activation function of the multi-layered neural network can be set on the user interface.

[0060] In addition, deep reinforcement learning may be used in the neural network, in which a reward function is set for each information item to be learned, and the information item with the highest value is extracted based on the reward function.

[0061] The trained models of this embodiment include a waste prediction model M1 (FIG. 3), a material prediction model M2 (FIG. 4), a blend prediction model M3 (FIG. 5), and an addition prediction model M4 (FIG. 7). Although these trained models are generated individually, they may be generated together as a single trained model.

[0062] In this embodiment, the mix design computer 21 automatically controls various devices, but other modes are also possible. For example, the mix design computer 21 may control various devices by accepting input operations from the user. In other words, the mix design computer 21 may be a remote control unit for controlling various devices by manual operations by the user.

[0063] Next, the radioactive waste treatment executed by the mix design computer 21 will be explained using the flowchart in Figure 2. This flowchart simplifies the main process flow to facilitate understanding. The above-mentioned drawings will be used as references as appropriate.

[0064] Note that the arrows in FIG. 2 are one example showing the flow of processes, and there may be other process flows than those shown by the arrows. Furthermore, the order of each process is not necessarily fixed, and the order of some processes may be interchanged. Furthermore, some processes may be executed in parallel with other processes. Furthermore, the following processes are at least some of the processes included in the radioactive waste treatment, and other processes may be included in the radioactive waste treatment.

[0065] First, in step S1, the mix design computer 21 acquires impact information on the radioactive waste to be solidified. This impact information on the radioactive waste is information related to the kneading viscosity when the radioactive waste is kneaded with the geopolymer material, and includes a predicted value (estimated value).

[0066] In the next step S2, the mix design computer 21 acquires impact information of the geopolymer material for solidifying the radioactive waste. This impact information of the geopolymer material is information related to the kneading viscosity when the geopolymer material is kneaded with the radioactive waste, and includes a predicted value (estimated value) thereof.

[0067] In the next step S3, the mix design computer 21 determines the mix amounts of radioactive waste and geopolymer material to be put into the kneading container 22 for kneading the radioactive waste and geopolymer material.

[0068] In the next step S4, the mix design computer 21 puts the radioactive waste and the geopolymer material into the kneading vessel 22. The kneading device 18 kneads the materials put into the kneading vessel 22. Here, the kneading device 18 kneads the radioactive waste and the geopolymer material introduced from the second mixing tank 9 in the kneading vessel 22.

[0069] In the next step S5, the state acquisition device 19 acquires kneading state information of the material being kneaded in the kneading container 22. The mix design computer 21 acquires the kneading state information from the state acquisition device 19.

[0070] In the next step S6, the mix design computer 21 judges whether the kneaded state of the kneaded material is within the range of the predetermined design specifications. If the kneaded state is within the range of the design specifications (YES in step S6), the current state is maintained and continues until the predetermined kneading time has elapsed. On the other hand, if the kneaded state is not within the range of the design specifications (NO in step S6), the process proceeds to step S7.

[0071] In the next step S7, the mix design computer 21 determines the amount of additives to be added to the kneading vessel 22.

[0072] In the next step S8, the mix design computer 21 puts the additives into the kneading container 22 and continues kneading.

[0073] In the next step S9, the state acquisition device 19 acquires kneading state information of the material being kneaded in the kneading container 22. The mix design computer 21 acquires the kneading state information from the state acquisition device 19.

[0074] In the next step S10, the mix design computer 21 judges whether the kneaded state of the kneaded material is within the range of the predetermined design specifications. If the kneaded state is within the range of the design specifications (YES in step S10), the current state is maintained and continues until the predetermined kneading time has elapsed. On the other hand, if the kneaded state is not within the range of the design specifications (NO in step S10), the process proceeds to step S11.

[0075] In the next step S11, the mix design computer 21 judges whether or not the error is solvable. Here, a solvable error means that the kneading state that is judged to be outside the range of the design specifications can be corrected to within the range of the design specifications by further adding at least one of the additive and the geopolymer material. Here, if the error is solvable (YES in step S11), return to step S7. On the other hand, if the error is not solvable (NO in step S11), proceed to step S12.

[0076] In step S12, the mix design computer 21 outputs an error notification and ends the process. By outputting an error notification, it is possible to inform the user that there is a risk of poor kneading.

[0077] FIG. 3 shows an example of the process in which the mix design computer 21 acquires information on the effects of radioactive waste in step S1 (FIG. 2) described above.

[0078] The mix design computer 21 inputs the component information of radioactive waste as input data D1 to the machine-learned waste prediction model M1. The mix design computer 21 then predicts the impact information of radioactive waste based on the output data D2 output from this waste prediction model M1. In this way, it is possible to predict (estimate) the impact information of radioactive waste from the component information of radioactive waste.

[0079] The component information of the radioactive waste as the input data D1 includes at least one of the solid concentration, silicon concentration, aluminum concentration, calcium concentration, boric acid concentration, and water content of the radioactive waste. Note that data other than these may be included in the input data D1. The input data D1 is acquired by the waste information acquisition device 17 and sent to the mix design computer 21. The input data D1 may also be input to the mix design computer 21 by a user.

[0080] The impact information of radioactive waste as output data D2 includes the kneading viscosity when radioactive waste is kneaded with geopolymer material. This output data D2 is a predicted viscosity by the waste prediction model M1, which has machine-learned the relationship with the kneading viscosity when kneaded with the basic composition in the past using the parameters of the input data D1. Note that data other than these may be included in the output data D2.

[0081] FIG. 4 shows an example of a process in which the mix design computer 21 acquires the effect information of the geopolymer material in step S2 (FIG. 2) described above.

[0082] The mix design computer 21 inputs the component information of the geopolymer material as input data D3 to the machine-learned material prediction model M2. The mix design computer 21 then predicts the impact information of the geopolymer material based on the output data D4 output from the material prediction model M2. In this way, the impact information of the geopolymer material can be predicted (estimated) from the component information of the geopolymer material.

[0083] The component information of the geopolymer material as input data D3 includes at least one of silicon concentration, aluminum concentration, calcium concentration, boric acid concentration, fly ash addition amount, and moisture content.

[0084] This input data D3 is information on geopolymer materials related to the kneading viscosity of geopolymer in the basic mix. For example, the input data D3 is the concentration of metakaolin (Si, Al), the concentration of blast furnace slag (Si, Al, Ca), the additive concentration (boric acid concentration), the concentration of fly ash (Si, Al, Ca), and the concentration of silica fume (Si). The input data D3 is also the concentration of alkaline materials (alkaline hydroxides such as sodium hydroxide and potassium hydroxide) and the concentration of incineration ash (Si, Al, Ca). The input data D3 is also the concentration of alkaline silicates or solutions such as water glass, potassium silicate solution, and metasilicate, and the amount of added water.

[0085] In addition, data other than these may be included in the input data D3. The input data D3 is input by the user to the blending design computer 21. In addition, the input data D3 may be acquired by the base powder information acquisition device 16 and sent to the blending design computer 21 via the base material mixing computer 20.

[0086] The impact information of the geopolymer material as the output data D4 includes the kneading viscosity when the geopolymer material is kneaded with radioactive waste. This output data D4 is a predicted viscosity by the material prediction model M2 in which the relationship with the kneading viscosity when kneaded with the basic composition using the parameters of the input data D3 in the past is machine-learned. Note that data other than these may be included in the output data D4.

[0087] FIG. 5 shows an example of the process in which the mix design computer 21 determines the mix amounts of radioactive waste and geopolymer material in step S3 (FIG. 2) described above.

[0088] The mix design computer 21 inputs the impact information of radioactive waste, the impact information of geopolymer material, and the design specification information as input data D5 to the machine-learned mix prediction model M3. Then, the mix design computer 21 determines the mix amount of radioactive waste and geopolymer material based on the output data D6 output from this mix prediction model M3.

[0089] The input data D5 includes at least information on the impact of radioactive waste and information on the impact of geopolymer materials. The input data D5 also includes design specification information. This design specification information is a design specification that has been approved in advance by a government agency. Therefore, it is assumed that the upper and lower limits of the mixture adjustment are within the range of the measurement tolerance. Furthermore, data other than these may be included in the input data D5.

[0090] The output data D6 includes at least the mixing amounts of radioactive waste and geopolymer material. The output data D6 may also include the kneading viscosity estimated when kneading with the output mixing amounts. Furthermore, data other than these may also be included in the output data D6.

[0091] In step S13, which is performed after the output data D6 is output, the mix design computer 21 determines whether the kneading viscosity estimated from the mix amount based on the output data D6 output from the mix prediction model M3 is within the range of the predetermined design specifications. The mix design computer 21 may also determine whether the mix amount is within the range of the design specifications and can be kneaded. If the kneading viscosity is not within the range of the design specifications (NO in step S13), the process proceeds to step S14. On the other hand, if the kneading viscosity is within the range of the design specifications (YES in step S13), the process proceeds to step S15.

[0092] In step S14, the mix design computer 21 outputs an error notification. In this way, the user can be informed that there is a risk of poor mixing. Then, the mix design computer 21 again inputs the input data D5 to the mix prediction model M3, outputs the output data D6, and redoes the process.

[0093] In step S15, the mix design computer 21 determines the mixing amount based on the output data D6. The mix design computer 21 sends the determined mixing amount to the base material mixing computer 20. The base material mixing computer 20 controls the alkaline solution metering tank 10, the alkaline material metering tank 11, the first base material powder metering tank 12, and the second base material powder metering tank 13 based on the determined mixing amount. Furthermore, the mix design computer 21 controls the waste metering tank 14 based on the determined mixing amount. In this way, the mixing amount of radioactive waste and geopolymer material can be adjusted.

[0094] The mix design computer 21 measures the amount of radioactive waste and geopolymer material to be introduced into the mixing vessel 22 based on the measurement by the waste measuring tank 14. Furthermore, the mix design computer 21 adjusts the amount of radioactive waste and geopolymer material to be introduced into the mixing vessel 22 based on the mixing state information acquired by the state acquisition device 19. In this way, when the mixing amount based on the mix prediction model M3 is not appropriate, the mixing amount can be appropriately adjusted.

[0095] In addition, the compounding design computer 21 may cause the compounding prediction model M3 to learn using this adjusted compounding amount as learning data. By doing so, for the compounding amount of the next batch, an optimal compounding is presented in advance by machine learning based on the content of the previous process, so that the processing time can be shortened. In addition, the frequency of occurrence of kneading defects can be reduced by accumulating learning data.

[0096] FIG. 6 shows a specific example of the process executed by the compounding design computer 21 during the kneading of radioactive waste and geopolimer material from step S4 to step S12 (FIG. 2) described above.

[0097] First, in step S21, the compounding design computer 21 acquires kneading state information from the state acquisition device 19. This kneading state information includes at least one of the viscosity or temperature of the radioactive waste and geopolimer material being kneaded in the kneading container 22.

[0098] In the next step S22, the compounding design computer 21 determines whether the kneading state is within the range of the design specifications. For example, the compounding design computer 21 determines whether the viscosity and temperature of the radioactive waste and geopolimer material being kneaded in the kneading container 22 are within the range of predetermined design specifications. Here, when the kneading state is within the range of the design specifications (YES in step S22), the current state is maintained and continued until the elapse of the predetermined kneading time is completed. On the other hand, when the kneading state is not within the range of the design specifications (NO in step S22), the process proceeds to step S23.

[0099] In step S23, the compounding design computer 21 controls the additive metering tank 15 to add an additive to the kneading container 22.

[0100] In the next step S24, the compounding design computer 21 acquires additional kneading state information from the state acquisition device 19.

[0101] In the next step S25, the mix design computer 21 judges whether the kneading state is within the range of the design specifications. If the kneading state is within the range of the design specifications (YES in step S25), the current state is maintained and continues until the predetermined kneading time has elapsed. On the other hand, if the kneading state is not within the range of the design specifications (NO in step S25), the process proceeds to step S26.

[0102] In step S26, the mix design computer 21 outputs an error notification and ends the process. By outputting an error notification, it is possible to inform the user that there is a risk of poor kneading.

[0103] FIG. 7 shows an example of the process in which the mix design computer 21 determines the amount of additive to be added in step S7 (FIG. 2) described above.

[0104] The mix design computer 21 inputs the impact information of radioactive waste, the impact information of geopolymer material, the design specification information, the mix amount, and the kneading state information as input data D7 into the machine-learned additive prediction model M4. Then, the mix design computer 21 determines the additive amount based on the output data D8 output from this additive prediction model M4.

[0105] The input data D7 includes at least the impact information of the radioactive waste and the impact information of the geopolymer material. The input data D7 also includes design specification information. The input data D7 also includes at least one of the viscosity or temperature of the radioactive waste and the geopolymer material being kneaded in the kneading vessel 22 as kneading state information. Furthermore, data other than these may be included in the input data D7.

[0106] The output data D8 includes at least the amount of additive added. The output data D8 may also include a kneading viscosity estimated when the additive is added in the output amount and kneaded. Furthermore, data other than these may also be included in the output data D8.

[0107] In step S31, which is performed after the output data D8 is output, the mix design computer 21 judges whether the kneading viscosity estimated from the mix amount and the addition amount based on the output data D8 output from the addition prediction model M4 is within the range of the predetermined design specifications. If the kneading viscosity is not within the range of the design specifications (NO in step S31), the input data D7 is input again to the addition prediction model M4, the output data D8 is output, and the process is repeated. Here, the mix design computer 21 may output an error notification. On the other hand, if the kneading viscosity is within the range of the design specifications (YES in step S31), the process proceeds to step S32.

[0108] In step S32, the blending design computer 21 determines the amount of additives to be added based on the output data D8. The blending design computer 21 controls the additive measuring tank 15 based on the determined amount of additives to be added. In this way, the kneading state can be adjusted by the additives.

[0109] In addition, the blending design computer 21 measures the additives to be introduced into the kneading vessel 22 based on the measurement by the additive measuring tank 15. Furthermore, the blending design computer 21 adjusts the amount of additives to be introduced into the kneading vessel 22 based on the kneading state information acquired by the state acquisition device 19. In this way, when the addition amount output from the addition prediction model M4 is not appropriate, the addition amount can be appropriately adjusted.

[0110] In addition, the blending design computer 21 may train the addition prediction model M4 using the adjusted addition amount as learning data. In this way, the next amount of additive to be added is presented in advance as an optimal blend by machine learning based on the contents of the previous processing, thereby shortening the processing time.

[0111] The radioactive waste treatment system 1 adjusts the mix using machine learning according to the properties of the radioactive waste and the state when mixed. In this way, the mix viscosity of the geopolymer slurry can be adjusted to an appropriate range. In addition, since past operating data is reflected as learning data for machine learning, the mix amount for the next process can be presented in a pre-optimized state.

[0112] In addition, although the properties of radioactive waste cannot be controlled to a constant level, they are likely to affect the kneading viscosity of the geopolymer slurry. Therefore, the radioactive waste treatment system 1 uses machine learning to adjust the mixing amount to an optimal amount within the design specifications. In this way, the kneading viscosity of the geopolymer slurry can be suppressed and the fluidity required for kneading can be maintained.

[0113] The radioactive waste treatment system 1 described above includes a control device, a storage device, an output device, an input device, and a communication interface. Here, the control device includes a highly integrated processor such as a central processing unit (CPU), a graphics processing unit (GPU), a field programmable gate array (FPGA), or a dedicated chip. The storage device includes a read only memory (ROM), a random access memory (RAM), a hard disk drive (HDD), a solid state drive (SSD), etc. The output device includes a display panel, a head mounted display, a projector, a printer, etc. The input device includes a mouse, a keyboard, a touch panel, etc. This radioactive waste treatment system 1 can be realized by a hardware configuration using a normal computer.

[0114] The program or trained model executed in the radioactive waste treatment system 1 is provided by being pre-installed in a ROM or the like. Additionally or alternatively, the program or trained model is provided by being stored in a computer-readable non-transitory storage medium as a file in an installable or executable format. The storage medium includes a CD-ROM, a CD-R, a memory card, a DVD, a flexible disk (FD), and the like.

[0115] The program or trained model executed in the radioactive waste treatment system 1 may be stored in a computer connected to a network such as the Internet and downloaded via the network to be provided. That is, the program or trained model may be provided from a cloud computing resource. A server on the cloud may execute the program or trained model, and only the processing results may be provided via the cloud. The radioactive waste treatment system 1 may also be configured by combining separate modules that independently perform the functions of the components, which are mutually connected via a network or a dedicated line.

[0116] Each component of the radioactive waste treatment system 1 does not necessarily have to be provided in one mix design computer 21. For example, one radioactive waste treatment system 1 may be realized by a plurality of computers connected to each other via a network. For example, the waste prediction model M1, the material prediction model M2, the mix prediction model M3, and the addition prediction model M4 may each be installed in an individual computer.

[0117] In the above example, the mix design computer 21 constituting the radioactive waste treatment system 1 performs various processes (including various processes such as judgment and setting), but other forms are also possible. For example, a user may perform some of the various processes described above, and the computer may receive input of the processing results and use them for its own processing.

[0118] According to the embodiment described above, the mixing amount is determined based on the output data D6 output from the mixing prediction model M3, so that the mixing viscosity of the slurry can be adjusted to an appropriate range when solidifying radioactive waste using geopolymer.

[0119] Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, modifications, and combinations can be made without departing from the spirit of the invention. These embodiments or modifications thereof are within the scope of the invention and its equivalents as described in the claims, as well as within the scope and spirit of the invention. [Explanation of symbols]

[0120] Reference Signs List 1...radioactive waste treatment system, 2...alkaline solution storage tank, 3...alkaline material storage tank, 4...first base material powder storage tank, 5...second base material powder storage tank, 6...waste storage tank, 7...additive storage tank, 8...first mixing tank, 9...second mixing tank, 10...alkaline solution metering tank, 11...alkaline material metering tank, 12...first base material powder metering tank, 13...second base material powder metering tank, 14...waste metering tank, 15...additive metering tank, 16...base material powder information acquisition device , 17...waste information acquisition device, 18...kneading device, 19...status acquisition device, 20...base material mixing computer, 21...mixture design computer, 22...kneading container, 23...mixing motor, 24...mixing shaft, 25...mixing blade, D1, D3, D5, D7...input data, D2, D4, D6, D8...output data, M1...waste prediction model, M2...material prediction model, M3...mixture prediction model, M4...addition prediction model.

Claims

1. Obtaining influence information related to the kneading viscosity when the radioactive waste to be solidified is kneaded with a geopolymer material for solidifying the radioactive waste; Obtaining influence information regarding the kneading viscosity when the geopolymer material is kneaded with the radioactive waste; The impact information of the radioactive waste and the impact information of the geopolymer material are input as input data into a machine-learned mixture prediction model; Based on the output data output from the blend prediction model, a blend amount of the radioactive waste and the geopolymer material to be input into a kneading vessel for kneading the radioactive waste and the geopolymer material is determined; one or more computers configured to Radioactive waste treatment system.

2. The computer includes: Inputting component information relating to the components of the radioactive waste as input data into a machine-learned waste prediction model; Predicting information on the impact of the radioactive waste based on output data output from the waste prediction model. It is configured as follows: The radioactive waste treatment system according to claim 1 .

3. The component information of the radioactive waste includes at least one of a solid concentration, a silicon concentration, an aluminum concentration, a calcium concentration, a boric acid concentration, and a water content. The radioactive waste treatment system according to claim 2.

4. The computer includes: Component information relating to the components of the geopolymer material is input as input data into a machine-learned material prediction model; Predicting impact information of the geopolymer material based on output data output from the material prediction model. It is configured as follows: The radioactive waste treatment system according to any one of claims 1 to 3.

5. The component information of the geopolymer material includes at least one of silicon concentration, aluminum concentration, calcium concentration, boric acid concentration, fly ash addition amount, and moisture content; The radioactive waste treatment system according to claim 4.

6. The computer includes: Determine whether or not the kneading viscosity estimated from the blending amounts based on the output data output from the blending prediction model is within a predetermined design specification range; outputting an error notification when the kneading viscosity estimated based on the blending amounts is not within the range of the design specifications; It is configured as follows: The radioactive waste treatment system according to any one of claims 1 to 3.

7. The computer includes: Acquire mixing status information indicating the state of the radioactive waste and the geopolymer material being mixed in the mixing vessel; Weighing the radioactive waste and the geopolymer material introduced into the mixing vessel; Adjusting the amount of the radioactive waste and the geopolymer material to be introduced into the mixing vessel based on the mixing state information; It is configured as follows: The radioactive waste treatment system according to any one of claims 1 to 3.

8. The kneading state information includes at least one of a current value or a torque value of a stirring motor provided in the kneading vessel, an image of the inside of the kneading vessel, a temperature in the kneading vessel, and a viscosity measured by a viscometer attached to the kneading vessel. The radioactive waste treatment system according to claim 7.

9. The kneading state information includes at least one of the viscosity or temperature of the radioactive waste and the geopolymer material being kneaded in the kneading vessel; The computer includes: determining whether the viscosity and the temperature are within predetermined design specifications; outputting an error notification if at least one of the viscosity or the temperature is not within the design specification range; It is configured as follows: The radioactive waste treatment system according to claim 7.

10. The computer includes: The impact information of the geopolymer material, the impact information of the radioactive waste, the blending amount, and the kneading state information are input as input data into a machine-learned additive prediction model, determining an amount of the additive to be added to the kneading vessel based on output data output from the addition prediction model; It is configured as follows: The radioactive waste treatment system according to claim 7.

11. The computer includes: Metering the additives introduced into the kneading vessel; adjusting the amount of the additive to be introduced into the kneading vessel based on the kneading state information; It is configured as follows: The radioactive waste treatment system according to claim 10.

12. The computer includes: determining whether the addition amount of the additive based on the output data output from the addition prediction model is within a range of a predetermined design specification; outputting an error notification if the amount of addition is not within the range of the design specification; It is configured as follows: The radioactive waste treatment system according to claim 10.

13. A waste information acquisition device for acquiring information on the effect of the radioactive waste; A waste measuring tank for measuring the amount of the radioactive waste introduced into the kneading vessel; A base powder measuring tank for measuring the amount of the geopolymer material introduced into the kneading vessel; An additive measuring tank for measuring the additives to be introduced into the kneading vessel; A kneading device that kneads the radioactive waste, the geopolymer material, and the additive introduced from the waste measuring tank, the base powder measuring tank, and the additive measuring tank in the kneading container; A state acquisition device for acquiring the kneading state information; Equipped with The radioactive waste treatment system according to claim 10.

14. The geopolymer material comprises: A base material containing at least one of metakaolin, blast furnace slag, incineration ash, fly ash, zeolite, and mordenite; an alkaline material containing at least one of lithium hydroxide, sodium hydroxide, potassium hydroxide, rubidium hydroxide, cesium hydroxide, lithium silicate, sodium silicate, potassium silicate, rubidium silicate, cesium silicate, orthosilicate, and metasilicate; A mixture comprising: The radioactive waste treatment system according to any one of claims 1 to 3.

15. Obtaining influence information related to the kneading viscosity when the radioactive waste to be solidified is kneaded with a geopolymer material for solidifying the radioactive waste; Obtaining influence information regarding the kneading viscosity when the geopolymer material is kneaded with the radioactive waste; The impact information of the radioactive waste and the impact information of the geopolymer material are input as input data into a machine-learned mixture prediction model; Based on the output data output from the blend prediction model, a blend amount of the radioactive waste and the geopolymer material to be input into a kneading vessel for kneading the radioactive waste and the geopolymer material is determined; The processing is performed by one or more computers; Radioactive waste disposal methods.

Images