Method and device for determining dose response rate setting value of reactor under emergency working condition

Abstract

The invention relates to a method and a device for determining a dose response rate setting value of a reactor under an emergency working condition. The method comprises the following steps: acquiring a target accident scene corresponding to the reactor under the emergency working condition; based on the target accident scene, determining a target reactor core damage state and target burnup of the reactor; inputting the target reactor core damage state and the target burnup into a gating circulation unit model to obtain a target dose response rate setting value; the gating circulation unit model is constructed by constructing a dynamic event tree based on a simulated reactor, determining various simulated accident scenes through the dynamic event tree, obtaining simulated reactor core stockpiling amounts, simulated burnup and simulated dose response rate setting values corresponding to the various simulated accident scenes, and adopting a machine learning algorithm. According to the invention, a plurality of different accident situations are considered, so that the gating circulation unit model can calculate the dose response rate setting values corresponding to different accidents according to different accident situations, thereby adapting to a plurality of different emergency working conditions.

Description

Technical Field

[0001] The invention relates to the technical field of nuclear radiation emergency, and in particular to a method and device for determining a set value of a reactor dose response rate under emergency conditions. Background Art

[0002] After the Fukushima nuclear accident in 2011, core damage assessment became a popular nuclear accident emergency assessment method internationally. The International Atomic Energy Agency (IAEA) proposed in 2014 that nuclear emergency protection actions can be directly guided by the core damage assessment results. Therefore, core damage assessment is one of the necessary nuclear emergency response technical means for nuclear power plants today.

[0003] In the core damage assessment methods in the prior art, the dose response rate setting value of the detector in the reactor containment is used as one of the main judgment methods for core damage assessment. In nuclear emergency conditions, the current core damage degree is obtained by comparing the currently monitored dose response rate with the dose response rate setting value.

[0004] In the actual operation of the reactor, various accident scenarios may occur due to various factors such as different reactor operation history, different accumulation of radioactive materials in the core, and different accident locations, resulting in different dose response rate setting values. However, in the prior art, only the preset core accumulation can be used to determine the dose response rate setting value, which makes it impossible to apply to various emergency conditions.

[0005] The above problems need to be solved urgently. Summary of the invention

[0006] The invention discloses a method and a device for determining a set value of a reactor dose response rate under emergency conditions, aiming to solve the technical problems existing in the prior art.

[0007] The present invention adopts the following technical solutions:

[0008] On the one hand, the present invention provides a method for determining a set value of a reactor dose response rate under emergency conditions, comprising: obtaining a target accident scenario corresponding to the reactor under emergency conditions; based on the target accident scenario, determining a target core damage state and a target burnup of the reactor; inputting the target core damage state and the target burnup into a gated cycle unit model to obtain a target dose response rate set value; wherein the gated cycle unit model is based on constructing a dynamic event tree under the condition of a simulated reactor, determining a plurality of simulated accident scenarios through the dynamic event tree, obtaining simulated core inventory, simulated burnup and simulated dose response rate set values ​​corresponding to the plurality of simulated accident scenarios, and is constructed through a machine learning algorithm.

[0009] Optionally, before inputting the target core damage state and the target burnup into the gated cycle unit model to obtain the target dose response rate setting value, the method also includes: determining a simulated reactor, wherein the simulated reactor is a nuclear transformation device used to indicate a nuclear fission or nuclear fusion reaction; constructing a dynamic event tree to determine a plurality of simulated accident scenarios corresponding to the simulated reactor, wherein the plurality of simulated accident scenarios are used to indicate accidents that may occur after the simulated reactor produces nuclear transformation; obtaining the simulated core inventory, simulated burnup and simulated dose response rate setting values ​​corresponding to the plurality of simulated accident scenarios; and constructing the gated cycle unit model through a machine learning algorithm with the simulated core inventory, the simulated burnup and the plurality of simulated accident scenarios as input and the simulated dose response rate setting value as output.

[0010] Optionally, the construction of a dynamic event tree determines a plurality of simulated accident scenarios corresponding to the simulated reactor, including: determining an initial accident scenario corresponding to the simulated reactor; constructing an initial dynamic event tree with the initial accident scenario as the root node of the dynamic event tree, the accident scenario trends as branches, and a plurality of simulated accident scenarios as branch nodes; obtaining growth probabilities corresponding to the branch nodes in the initial dynamic event tree; and truncating branch nodes corresponding to growth probabilities lower than preset probabilities and branches corresponding to the branch nodes to obtain the dynamic event tree.

[0011] Optionally, obtaining the simulated core inventory, simulated burnup and simulated dose response rate setting values ​​corresponding to the multiple simulated accident scenarios includes: obtaining a first core inventory and a first burnup corresponding to the simulated reactor, wherein the first core inventory is used to indicate the core inventory in all time periods in the simulated reactor, and the first burnup is used to indicate the burnup in all time periods in the simulated reactor; determining a trend of core inventory changing with burnup based on the first core inventory and the first burnup; determining a simulated burnup based on the trend of the core inventory changing with burnup, wherein the simulated burnup is used to indicate the burnup when the trend of the core inventory changing with burnup selected from the first burnup exceeds a preset range; determining a simulated core inventory based on the trend of the core inventory changing with burnup, wherein the simulated core inventory is used to indicate the core inventory when the trend of the core inventory changing with burnup selected from the first core inventory exceeds a preset range.

[0012] Optionally, obtaining the simulated core inventory, simulated burnup and simulated dose response rate setting values ​​corresponding to the multiple simulated accident scenarios includes: determining the degree of trend change based on the trend of the core inventory changing with fuel consumption; determining the simulated burnup corresponding to the trend of the core inventory changing with fuel consumption when the degree of trend change exceeds a preset degree, wherein the simulated burnup is used to indicate the burnup selected from the first fuel consumption when the degree of trend change exceeds a preset degree; determining the simulated core inventory corresponding to the simulated burnup based on the simulated burnup and the trend of the core inventory changing with fuel consumption, wherein the simulated core inventory is used to indicate the core inventory selected from the first core inventory when the degree of trend change exceeds a preset degree.

[0013] Optionally, the gated circulation unit model is constructed by a machine learning algorithm with the simulated core inventory, the simulated fuel consumption, and the multiple simulated accident scenarios as inputs and the simulated dose response rate setting value as output, including: determining an accident scenario object based on the simulated core inventory and the simulated fuel consumption, wherein the accident scenario object is used to indicate an accident scenario screened from multiple simulated accident scenarios and matching the simulated core inventory and the simulated fuel consumption; and constructing the gated circulation unit model by a machine learning algorithm with the simulated core inventory, the simulated fuel consumption, and the accident scenario object as inputs and the simulated dose response rate setting value as output.

[0014] Optionally, the gated circulation unit model is constructed by a machine learning algorithm with the simulated core inventory, the simulated burnup and the accident scenario object as input and the simulated dose response rate setting value as output, including: determining a simulated core damage state based on the simulated core inventory and multiple accident scenario objects, wherein the simulated core damage state includes at least: a core damage state corresponding to a 1% damage to the fuel cladding in a simulated accident scenario, a core damage state corresponding to a 100% damage to the fuel cladding in a simulated accident scenario, a core damage state corresponding to a 1% melt of the fuel in a simulated accident scenario, and a core damage state corresponding to a 1% melt of the fuel in a simulated accident scenario; the gated circulation unit model is constructed by a machine learning algorithm with the simulated core damage state, the simulated burnup and the accident scenario object as input and the simulated dose response rate setting value as output.

[0015] According to another aspect of an embodiment of the present invention, there is also provided a device for determining a set value of a reactor dose response rate under emergency conditions, comprising: an acquisition module for acquiring a target accident scenario corresponding to the reactor under emergency conditions; a determination module for determining a target core damage state and a target fuel consumption of the reactor based on the target accident scenario; a response rate module for inputting the target core damage state and the target fuel consumption into a gated cycle unit model to obtain a target dose response rate set value; wherein the gated cycle unit model constructs a dynamic event tree based on a simulated reactor, determines a plurality of simulated accident scenarios through the dynamic event tree, obtains simulated core inventory, simulated fuel consumption and simulated dose response rate set values ​​corresponding to the plurality of simulated accident scenarios, and is constructed through a machine learning algorithm.

[0016] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is also provided, wherein the non-volatile storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing any one of the methods for determining a set value of a reactor dose response rate under emergency conditions.

[0017] According to another aspect of an embodiment of the present invention, there is also provided a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods for determining a set value of a reactor dose response rate under emergency conditions.

[0018] The technical solution adopted by the present invention can achieve at least one of the following beneficial effects:

[0019] In an embodiment of the present invention, a target accident scenario corresponding to a reactor under emergency conditions is obtained; based on the target accident scenario, a target core damage state and a target fuel consumption of the reactor are determined; the target core damage state and the target fuel consumption are input into a gated cycle unit model to obtain a target dose response rate setting value; wherein the gated cycle unit model constructs a dynamic event tree based on a simulated reactor, determines a plurality of simulated accident scenarios through the dynamic event tree, obtains simulated core inventory, simulated fuel consumption and simulated dose response rate setting values ​​corresponding to the plurality of simulated accident scenarios, and is constructed through a machine learning algorithm, thereby achieving the purpose of constructing a gated cycle unit model based on constructing a dynamic event tree and taking into account a plurality of accident scenarios, thereby achieving the technical effect of taking into account a plurality of different accident scenarios, so that the gated cycle unit model can calculate the dose response rate setting values ​​corresponding to different accidents according to different accident scenarios, thereby adapting to a plurality of different emergency conditions, thereby solving the technical problem that the dose response rate setting value cannot be applied to a plurality of different emergency conditions due to the fact that a plurality of different accident scenarios are not considered in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments, which constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions explain the present invention and do not constitute improper limitations on the present invention. In the drawings:

[0021] Figure 1 is a flow chart of a method for determining a set value of a reactor dose response rate under emergency conditions in Example 1 of the present invention;

[0022] Figure 2 is a flow chart of an optional method for determining a set value of a reactor dose response rate under emergency conditions in Example 2 of the present invention;

[0023] Figure 3 It is a structural schematic diagram of a device for determining a set value of a reactor dose response rate under emergency conditions in Example 3 of the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the specific embodiments of the present invention and the corresponding drawings. In the description of the present invention, it should be noted that the term "or" is usually used in the sense of including "and / or", unless the content clearly indicates otherwise.

[0025] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or a magnetic connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. In addition, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance. In the description of the present invention, the meaning of "multiple" is at least two, such as two, three or more, etc., unless otherwise clearly and specifically limited.

[0026] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] First, to facilitate understanding of the embodiments of the present invention, some terms or nouns involved in the present invention are explained below:

[0028] Emergency conditions refer to special operating states that equipment or systems must take in an emergency to ensure personnel safety and prevent further damage to equipment. This condition usually occurs in industries such as radiation, chemical, electric power, and mining. When faced with emergencies or abnormal situations, emergency measures must be taken quickly to ensure production safety.

[0029] Dose rate response refers to the characteristic of a quantity that characterizes the radiation effect of an ionizing radiation dosimeter changing with the dose rate. It is an important indicator of a dosimeter, used to describe the response performance of a dosimeter at different dose rates.

[0030] A reactor is a device that realizes a self-sustaining chain fission reaction or nuclear fusion reaction in a controllable manner. The reactor consists of a core, a coolant system, a moderator system, a control and protection system, a shielding system, and a radiation monitoring system.

[0031] The core inventory is a key parameter in the design of nuclear power plants. It refers to the accumulation of various radionuclides in the reactor core. These nuclides mainly come from the fission process of nuclear fuel and the activation products produced by the interaction between neutrons and reactor structural materials.

[0032] In order to solve the problems existing in the prior art, the embodiments of the present application provide a method and device for determining a set value of a reactor dose response rate under emergency conditions.

[0033] Example 1

[0034] This embodiment provides a method for determining a set value of a reactor dose response rate under emergency conditions, such as Figure 1 As shown, Figure 1 is a flow chart of a method for determining a set value of a reactor dose response rate under emergency conditions in embodiment 1 of the present invention, the method comprising:

[0035] Step S102, obtaining a target accident scenario corresponding to the reactor under emergency conditions;

[0036] Optionally, the target accident scenario of the reactor under the current emergency condition is obtained, and based on the above target accident scenario, the dose response rate setting value required for the target accident scenario is determined, and then the dose response rate is compared with the dose response rate setting value under the current accident scenario, so as to objectively obtain the current core damage degree and effectively determine the emergency protection actions required under the current emergency condition.

[0037] Step S104, determining a target core damage state and a target burnup of the reactor based on the target accident scenario;

[0038] Optionally, to obtain a dose response rate setting value, it is necessary to obtain a target core damage state and a target burnup under a current target accident scenario, and use them as inputs in sequence to obtain a dose response rate setting value.

[0039] Step S106, input the target core damage state and the target fuel consumption into the gated cycle unit model to obtain the target dose response rate setting value; wherein the gated cycle unit model is based on constructing a dynamic event tree under the condition of simulating a reactor, and determines a plurality of simulated accident scenarios through the dynamic event tree, obtains the simulated core inventory, simulated fuel consumption and simulated dose response rate setting values ​​corresponding to the plurality of simulated accident scenarios, and is constructed through a machine learning algorithm.

[0040] Optionally, the gated cyclic unit model is constructed based on a variety of accident scenarios traversed by a dynamic event tree, and can adapt to a variety of emergency conditions to obtain the target dose response rate setting value. Based on the corresponding target dose response rate setting value obtained under the emergency condition, the measures that should be taken under the emergency condition can be determined, thereby effectively protecting the safety of personnel under the current emergency condition.

[0041] In some preferred embodiments, before the target core damage state and target burnup are input into the gated cycle unit model to obtain the target dose response rate setting value, the method also includes: determining a simulated reactor, wherein the simulated reactor is used to indicate a nuclear transformation device that reacts by nuclear fission or nuclear fusion; constructing a dynamic event tree to determine a plurality of simulated accident scenarios corresponding to the simulated reactor, wherein the plurality of simulated accident scenarios are used to indicate accidents that may occur after the simulated reactor produces nuclear transformation; obtaining the simulated core inventory, simulated burnup and simulated dose response rate setting values ​​corresponding to the plurality of simulated accident scenarios; and constructing a gated cycle unit model through a machine learning algorithm with the simulated core inventory, simulated burnup and a plurality of simulated accident scenarios as input and the simulated dose response rate setting value as output.

[0042] Alternatively, a dynamic event tree is a tool used to describe and analyze potential accident sequences and their probabilities in complex systems. In simulated reactors, building a dynamic event tree can help determine multiple simulated accident scenarios.

[0043] The specific steps of constructing a dynamic event tree are as follows: first, determine the initial event, where the initial event may be a fault or abnormal state in the reactor, such as coolant leakage or control system failure.

[0044] Secondly, analyze the event development path. Starting from the initial event, analyze the possible accident development paths. These paths may involve multiple physical phenomena and interactions inside the reactor. On each path, possible system responses and operator intervention measures need to be considered.

[0045] Third, to calculate the probability of an event, for each event on the path, its probability of occurrence needs to be calculated, which relies on an in-depth understanding of the reactor system and operators as well as analysis of historical data.

[0046] Finally, a complete event tree is constructed, integrating all possible accident development paths and event probabilities to form a complete event tree.

[0047] Optionally, multiple simulated accident scenarios can be determined based on the constructed dynamic event tree. These scenarios may include: reactor core melt accident, which is caused by the loss of coolant or control system failure, resulting in the overheating and melting of the reactor core. Radioactive material leakage accident, which is caused by the rupture of the reactor vessel or the failure of the safety system, resulting in the leakage of radioactive materials into the environment. Fire and explosion accidents, which are caused by electrical failures and fuel leakage.

[0048] In some preferred embodiments, a dynamic event tree is constructed to determine a plurality of simulated accident scenarios corresponding to a simulated reactor, including: determining an initial accident scenario corresponding to the simulated reactor; constructing an initial dynamic event tree with the initial accident scenario as the root node of the dynamic event tree, the accident scenario trends as branches, and a plurality of simulated accident scenarios as branch nodes; obtaining growth probabilities corresponding to branch nodes in the initial dynamic event tree; and truncating branch nodes corresponding to growth probabilities lower than preset probabilities and branches corresponding to the branch nodes to obtain a dynamic event tree.

[0049] Optionally, the initial accident scenario is used as the root node, wherein the initial accident scenario is the occurrence of a safety hazard, the accident scenario trend is used as the branch, wherein the accident scenario trend is the cause of the possible safety hazard, and the simulated accident scenario is used as the branch node, wherein the simulated accident scenario is the damage to a certain component or the change of the reactor based on the cause of the current safety hazard. For example, the simulated accident scenario is the loss of coolant or the failure of the control system, and the accident scenario trend is the overheating and melting of the reactor core, and finally reaches the root node and a safety hazard occurs.

[0050] Optionally, based on the growth probability corresponding to the branch node in the initial dynamic event tree, the growth probability is the probability that the cause of the safety hazard may occur. If the probability of the cause (possibility) of the safety hazard is lower than the preset probability, the branch is truncated to reduce the branches of the dynamic event tree, thereby reducing the computing power required for the calculation of the dynamic event tree and effectively improving the speed of calculation and generation of the dynamic event tree.

[0051] In some preferred embodiments, simulated core inventory, simulated burnup and simulated dose response rate setting values ​​corresponding to a plurality of simulated accident scenarios are obtained, including: obtaining a first core inventory and a first burnup corresponding to the simulated reactor, wherein the first core inventory is used to indicate the core inventory in all time periods in the simulated reactor, and the first burnup is used to indicate the burnup in all time periods in the simulated reactor; determining the trend of core inventory changing with burnup based on the first core inventory and the first burnup; determining the simulated burnup based on the trend of core inventory changing with burnup, wherein the simulated burnup is used to indicate the burnup when the trend of core inventory changing with burnup selected from the first burnup exceeds a preset range; determining the simulated core inventory based on the trend of core inventory changing with burnup, wherein the simulated core inventory is used to indicate the core inventory when the trend of core inventory changing with burnup selected from the first burnup exceeds a preset range.

[0052] Optionally, each simulated accident scenario is a process that changes with time and has a certain time trend. For the reactor reaction process, there are multiple first core inventories and multiple first fuel consumptions. As time gradually changes, the first core inventories and first fuel consumptions corresponding to the simulated accident scenarios are obtained, and a trend graph of the core inventory changing with fuel consumption is constructed. Points in the trend graph where the changing trend exceeds a preset range are found. Based on the points that exceed the preset range, the trend of changes in the simulated core inventory and simulated fuel consumption that gradually form the simulated accident scenario can be determined, that is, when the simulated core inventory and simulated fuel consumption exceed the preset range, the reactor may gradually develop into the corresponding simulated accident scenario.

[0053] Optionally, based on the determined representative simulated core inventory and simulated fuel consumption, the trend of the current simulated accident scenario can be effectively determined, so that when the target core inventory and target fuel consumption under the emergency conditions are obtained, the trend of safety hazards under the current emergency conditions can be inferred, so that response measures can be made in advance to effectively protect the safety of surrounding personnel.

[0054] In some preferred embodiments, simulated core inventory, simulated burnup and simulated dose response rate setting values ​​corresponding to a variety of simulated accident scenarios are obtained, including: determining the degree of trend change based on the trend of core inventory changing with burnup; determining the simulated burnup corresponding to the trend of core inventory changing with burnup when the degree of trend change exceeds a preset degree, wherein the simulated burnup is used to indicate the burnup selected from the first burnup when the degree of trend change exceeds a preset degree; determining the simulated core inventory corresponding to the simulated burnup based on the simulated burnup and the trend of core inventory changing with burnup, wherein the simulated core inventory is used to indicate the core inventory when the degree of trend change selected from the first core inventory exceeds a preset degree.

[0055] Optionally, a trend chart is constructed based on the trend of the core inventory changing with the fuel consumption. Based on the degree of trend change in the trend chart, that is, the trend of an upward change or a downward change, when the degree of trend change exceeds a preset degree, that is, the upward change or the downward change is too fast, the display in the trend chart is a large slope, which means that the fuel consumption increases or decreases in a short time. If the fuel consumption increases in a short time, it may indicate that some reactions in the reactor are abnormal, which requires excessive attention.

[0056] Optionally, the corresponding simulated fuel consumption for excessive increase or decrease in fuel consumption in a short period of time is determined based on the trend chart, and based on the trend chart, the simulated core inventory can be found according to the determined simulated fuel consumption, and the above selected contents are saved, thereby obtaining the changing trends of the simulated fuel consumption and simulated core inventory corresponding to the possible accident scenario.

[0057] In some preferred embodiments, a gated circulation unit model is constructed by using a machine learning algorithm, with simulated core inventory, simulated fuel consumption, and multiple simulated accident scenarios as inputs and a simulated dose response rate setting value as output, including: determining an accident scenario object based on the simulated core inventory and the simulated fuel consumption, wherein the accident scenario object is used to indicate an accident scenario that matches the simulated core inventory and the simulated fuel consumption screened from multiple simulated accident scenarios; and constructing a gated circulation unit model by using a machine learning algorithm, with simulated core inventory, simulated fuel consumption, and accident scenario objects as inputs and a simulated dose response rate setting value as output.

[0058] Optionally, based on the simulated core inventory and simulated fuel consumption obtained above when exceeding the preset range, it is equivalent to obtaining the accident characteristics corresponding to the simulated accident scenario, that is, according to the target core inventory and target fuel consumption obtained under the emergency condition, the accident scenario object of the accident scenario development can be determined. Based on the above method, the accident characteristics (simulated core inventory and simulated fuel consumption) corresponding to a variety of simulated accident scenarios are obtained, and a variety of accident scenario objects can be obtained. The various accident scenario objects are placed together to form different accident scenarios that may occur under actual emergency conditions. The gated cycle unit model constructed based on the above method accommodates a variety of accident scenario objects, so that the target accident scenario and target fuel consumption under the current emergency condition can be used to determine the direction of the subsequent accident scenario. At the same time, based on the gated cycle unit model, the dose response rate setting value can be obtained, so as to determine in advance the measures that should be taken under the emergency condition, thereby effectively protecting the safety of personnel under the current emergency condition.

[0059] In some preferred embodiments, a gated circulation unit model is constructed by using a machine learning algorithm, with simulated core inventory, simulated fuel consumption and accident scenario objects as inputs and a simulated dose response rate setting value as output, including: determining a simulated core damage state based on the simulated core inventory and a variety of accident scenario objects, wherein the simulated core damage state at least includes: a core damage state corresponding to a 1% damage to the fuel cladding in a simulated accident scenario, a core damage state corresponding to a 100% damage to the fuel cladding in a simulated accident scenario, a core damage state corresponding to a 1% melt of the fuel in a simulated accident scenario, and a core damage state corresponding to a 1% melt of the fuel in a simulated accident scenario; a gated circulation unit model is constructed by using a machine learning algorithm, with simulated core damage state, simulated fuel consumption and accident scenario objects as inputs and a simulated dose response rate setting value as output.

[0060] Optionally, constructing a gated circulation unit model requires not only simulation of the core inventory and fuel consumption, but also determination of the simulated core damage state. The simulated core damage state can intuitively show the safety hazards of the reactor, thereby determining the measures to be taken under the emergency condition based on the simulated core damage state.

[0061] Optionally, the simulated core damage state includes at least: the core damage state corresponding to the case where the fuel cladding is damaged by 1% in the simulated accident scenario, the core damage state corresponding to the case where the fuel cladding is damaged by 100% in the simulated accident scenario, the core damage state corresponding to the case where the fuel melts by 1% in the simulated accident scenario, and the core damage state corresponding to the case where the fuel melts by 1% in the simulated accident scenario. Specifically, the above corresponding simulated core damage states are representative and can characterize the degree of core damage under the current emergency condition. The gated circulation unit model is constructed based on the representative simulated core damage states, which can effectively determine the measures that should be taken under the emergency condition, thereby effectively protecting the safety of personnel under the current emergency condition.

[0062] Through the above steps S102 to S106, the purpose of constructing a gated cyclic unit model based on building a dynamic event tree and taking into account a variety of accident scenarios is achieved, thereby realizing the consideration of a variety of different accident scenarios, so that the gated cyclic unit model can calculate the dose response rate setting values ​​corresponding to different accidents according to different accident scenarios, thereby adapting to a variety of different emergency conditions. The technical effect solves the technical problem that the dose response rate setting value cannot be applied to a variety of different emergency conditions due to the fact that factors of a variety of different accident scenarios are not considered in the prior art.

[0063] Example 2

[0064] Based on the above embodiments and optional embodiments, the present invention also proposes an optional implementation mode: Figure 2is a flow chart of an optional method for determining a reactor dose response rate setting value under emergency conditions in Example 2 of the present invention, such as Figure 2 As shown, the method includes:

[0065] Step S1, using a dynamic event tree (DET) to determine possible accident scenarios for a variety of different simulated reactors;

[0066] Step S2, by adjusting the truncation probability of DET (truncating the branch nodes corresponding to the growth probability lower than the preset probability and the branches corresponding to the branch nodes) to adjust the total number of branches, while ensuring that most simulated accident scenarios are covered, the total number of branches is reduced as much as possible to reduce the training pressure.

[0067] Step S3, with respect to the trends of core inventory changes with fuel consumption during the entire life cycle corresponding to a plurality of different simulated reactors, select a number of representative fuel consumptions (wherein the representative fuel consumption refers to the fuel consumption corresponding to the point where the trend change degree exceeds a preset degree), combine the core inventory corresponding to each selected fuel consumption with the simulated accident scenario in the dynamic event tree, and determine the accident scenario object.

[0068] Step S4, after determining the accident scenario object, use the severe accident analysis program and the dose calculation program to calculate the accident scenario objects corresponding to multiple simulated accidents respectively, and each accident scenario object needs to calculate the change process of the dose response rate setting value of the detector in the cladding corresponding to different core damage states required for core damage evaluation, such as fuel cladding damage of 1%, fuel cladding damage of 100%, fuel melting of 1%, fuel melting of 100%, etc. (the specific setting value needs to be adjusted according to the core damage state defined by the specific core damage evaluation method).

[0069] Step S5, taking the accident scenario object, accident location, fuel consumption, and core damage status as input, and taking the dose response rate setting value of the detector in the cladding obtained by the severe accident analysis program and the dose calculation program as output, as the training set and test set required for the gated cyclic unit model training.

[0070] Step S6, constructing a gated recurrent unit model through machine learning based on the training set and test set required for gated recurrent unit model training.

[0071] Step S7, before performing core damage assessment under emergency conditions, the trained gated cycle unit model can be used to obtain in real time the current reactor state and the set value of the detector dose response rate in the containment corresponding to the subsequent time, and then perform core damage assessment and predict the core damage state in the future.

[0072] Through the above steps S1 to S7, the dose response rate setting values ​​of the radioactive source items corresponding to several different core radioactive material accumulations, accident scenarios (accident location, accident type), and different core damage states to the detector positions in the containment are calculated in advance, and the above dose response rates are used to train the gated cyclic unit model. Before performing core damage assessment under emergency conditions, the trained gated cyclic unit model is used to obtain in real time the dose response rate setting values ​​of the detectors in the containment corresponding to the current reactor state.

[0073] Example 3

[0074] In this embodiment, a device for determining the set value of the reactor dose response rate under emergency conditions is also provided, and the device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the terms "module" and "device" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0075] According to an embodiment of the present invention, there is also provided an embodiment of a device for implementing the above method for determining a set value of a reactor dose response rate under an emergency condition. Figure 3 is a schematic diagram of the structure of a device for determining a set value of a reactor dose response rate under emergency conditions in Example 3 of the present invention, such as Figure 3 As shown, the above-mentioned device for determining the set value of the reactor dose response rate under emergency conditions includes: a measurement acquisition module 301, a determination module 302 and a response rate module 303, wherein:

[0076] An acquisition module 301 is used to acquire a target accident scenario corresponding to the reactor under emergency conditions;

[0077] The determination module 302 is connected to the acquisition module 301 and is used to determine the target core damage state and target burnup of the reactor based on the target accident scenario;

[0078] The response rate module 303 is connected to the determination module 302 and is used to input the target core damage state and the target burnup into the gated cycle unit model to obtain a target dose response rate setting value;

[0079] Among them, the gated cycle unit model constructs a dynamic event tree based on the simulated reactor situation, determines multiple simulated accident scenarios through the dynamic event tree, obtains the simulated core inventory, simulated fuel consumption and simulated dose response rate setting values ​​corresponding to multiple simulated accident scenarios, and is constructed through a machine learning algorithm.

[0080] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0081] It should be noted that the acquisition module 301, the determination module 302 and the response rate module 303 correspond to steps S102 to S106 in the embodiment, and the examples and application scenarios implemented by the modules and the corresponding steps are the same, but are not limited to the contents disclosed in the embodiment. It should be noted that the modules as part of the device can be run in a computer terminal.

[0082] It should be noted that the optional or preferred implementation of this embodiment can refer to the relevant description in the embodiment, which will not be repeated here.

[0083] The above-mentioned device for determining the set value of the reactor dose response rate under an emergency condition may also include a processor and a memory. The above-mentioned acquisition module 301, determination module 302 and response rate module 303 are all stored in the memory as program modules, and the processor executes the above-mentioned program modules stored in the memory to realize the corresponding functions.

[0084] The processor includes a kernel, which retrieves the corresponding program module from the memory. The kernel may be one or more. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. The memory includes at least one memory chip.

[0085] According to an embodiment of the present application, an embodiment of a non-volatile storage medium is also provided. Optionally, in this embodiment, the non-volatile storage medium includes a stored program, wherein when the program is run, the device where the non-volatile storage medium is located is controlled to execute any of the above methods for determining a set value of a reactor dose response rate under an emergency condition.

[0086] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group, and the non-volatile storage medium includes a stored program.

[0087] Optionally, when the program is running, the device where the non-volatile storage medium is located is controlled to perform the following functions: obtain a target accident scenario corresponding to the reactor under emergency conditions; based on the target accident scenario, determine the target core damage state and target fuel consumption of the reactor; input the target core damage state and target fuel consumption into the gated cycle unit model to obtain a target dose response rate setting value; wherein the gated cycle unit model is based on constructing a dynamic event tree under the condition of simulating a reactor, determining a variety of simulated accident scenarios through the dynamic event tree, obtaining simulated core accumulation, simulated fuel consumption and simulated dose response rate setting values ​​corresponding to a variety of simulated accident scenarios, and is constructed through a machine learning algorithm.

[0088] According to an embodiment of the present application, an embodiment of a processor is also provided. Optionally, in this embodiment, the processor is used to run a program, wherein when the program is run, any of the above methods for determining a set value of a reactor dose response rate under an emergency condition is executed.

[0089] According to an embodiment of the present application, an embodiment of a computer program product is also provided. Optionally, in this embodiment, the computer program product includes a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned methods for determining a set value of a reactor dose response rate under emergency conditions.

[0090] Optionally, the above-mentioned computer program product, when executed on a data processing device, is suitable for executing an initialization program having the following method steps: obtaining a target accident scenario corresponding to the reactor under emergency conditions; based on the target accident scenario, determining the target core damage state and target fuel consumption of the reactor; inputting the target core damage state and target fuel consumption into a gated cycle unit model to obtain a target dose response rate setting value; wherein the gated cycle unit model is based on constructing a dynamic event tree under the condition of a simulated reactor, determining a variety of simulated accident scenarios through the dynamic event tree, obtaining simulated core inventory, simulated fuel consumption and simulated dose response rate setting values ​​corresponding to a variety of simulated accident scenarios, and is constructed through a machine learning algorithm.

[0091] An embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: obtaining a target accident scenario corresponding to a reactor under emergency conditions; determining a target core damage state and a target fuel consumption of the reactor based on the target accident scenario; inputting the target core damage state and the target fuel consumption into a gated cycle unit model to obtain a target dose response rate setting value; wherein the gated cycle unit model is constructed based on a dynamic event tree constructed under the condition of a simulated reactor, and a plurality of simulated accident scenarios are determined through the dynamic event tree, and a simulated core inventory, simulated fuel consumption, and simulated dose response rate setting values ​​corresponding to the plurality of simulated accident scenarios are obtained, and the gated cycle unit model is constructed through a machine learning algorithm.

[0092] The above sequence of the embodiments of the present invention is for description only and does not represent the superiority or inferiority of the embodiments.

[0093] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0094] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the above modules can be a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, modules or indirect coupling or communication connection of modules, which can be electrical or other forms.

[0095] The modules described above as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0096] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of software functional modules.

[0097] If the above-mentioned integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a non-volatile storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present invention. The aforementioned non-volatile storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0098] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for determining a set value of a reactor dose response rate under emergency conditions, characterized in that: include: Obtain the target accident scenario corresponding to the reactor under emergency conditions; Based on the target accident scenario, determining a target core damage state and a target burnup of the reactor; Inputting the target core damage state and the target burnup into a gated cycle unit model to obtain a target dose response rate setting value; Among them, the gated cycle unit model constructs a dynamic event tree based on a simulated reactor, determines multiple simulated accident scenarios through the dynamic event tree, obtains the simulated core inventory, simulated fuel consumption and simulated dose response rate setting values ​​corresponding to the multiple simulated accident scenarios, and is constructed through a machine learning algorithm.

2. The method according to claim 1, characterized in that Before inputting the target core damage state and the target burnup into the gated cycle unit model to obtain the target dose response rate setting value, the method further includes: Determining a simulated reactor, wherein the simulated reactor is used to indicate a nuclear transformation device for performing a nuclear fission or nuclear fusion reaction; Constructing a dynamic event tree to determine a plurality of simulated accident scenarios corresponding to the simulated reactor, wherein the plurality of simulated accident scenarios are used to indicate possible accidents that may occur after the simulated reactor undergoes nuclear change; Obtaining simulated core stockpiles, simulated burnup, and simulated dose response rate setting values ​​corresponding to the multiple simulated accident scenarios; The gated circulation unit model is constructed by using a machine learning algorithm, with the simulated core inventory, the simulated burnup, and the multiple simulated accident scenarios as inputs and the simulated dose response rate setting value as output.

3. The method according to claim 2, characterized in that The dynamic event tree is constructed to determine a plurality of simulated accident scenarios corresponding to the simulated reactor, including: Determine the initial accident scenario corresponding to the simulated reactor; The initial accident scenario is used as the root node of the dynamic event tree, the accident scenario trends are used as branches, and the multiple simulated accident scenarios are used as branch nodes to construct an initial dynamic event tree; Obtaining the growth probability corresponding to the branch node in the initial dynamic event tree; The branch nodes corresponding to the growth probabilities lower than the preset probabilities and the branches corresponding to the branch nodes are cut off to obtain the dynamic event tree.

4. The method according to claim 2, characterized in that: The obtaining of the simulated core stockpiles, simulated burnup and simulated dose response rate setting values ​​corresponding to the multiple simulated accident scenarios includes: Obtaining a first core inventory and a first burnup corresponding to the simulated reactor, wherein the first core inventory is used to indicate the core inventory in all time periods of the simulated reactor, and the first burnup is used to indicate the burnup in all time periods of the simulated reactor; Based on the first core inventory and the first burnup, determining a trend of a core inventory changing with burnup; Determine a simulated burnup based on the trend of the core inventory changing with the burnup, wherein the simulated burnup is used to indicate the burnup when the trend of the core inventory changing with the burnup selected from the first burnup exceeds a preset range; Based on the trend of the core inventory changing with fuel consumption, a simulated core inventory is determined, wherein the simulated core inventory is used to indicate the core inventory screened out from the first core inventory when the trend of the core inventory changing with fuel consumption exceeds a preset range.

5. The method according to claim 4, characterized in that The obtaining of the simulated core stockpiles, simulated burnup and simulated dose response rate setting values ​​corresponding to the multiple simulated accident scenarios includes: Determining a degree of trend change based on a trend of the core inventory changing with fuel consumption; In the case where the degree of change of the trend exceeds a preset degree, determining a simulated burnup corresponding to the trend of the core inventory changing with the burnup, wherein the simulated burnup is used to indicate the burnup selected from the first burnup when the degree of change of the trend exceeds a preset degree; Based on the simulated fuel consumption and the trend of the core inventory changing with the fuel consumption, the simulated core inventory corresponding to the simulated fuel consumption is determined, wherein the simulated core inventory is used to indicate the core inventory selected from the first core inventory when the degree of change of the trend exceeds a preset degree.

6. The method according to claim 2, characterized in that The gated cycle unit model is constructed by taking the simulated core inventory, the simulated burnup, and the multiple simulated accident scenarios as inputs and the simulated dose response rate setting value as output through a machine learning algorithm, including: Determining an accident scenario object based on the simulated core stockpiles and the simulated burnup, wherein the accident scenario object is used to indicate an accident scenario that is screened from a plurality of simulated accident scenarios and matches the simulated core stockpiles and the simulated burnup; The gated cycle unit model is constructed by using a machine learning algorithm, with the simulated core inventory, the simulated burnup and the accident scenario object as inputs and the simulated dose response rate setting value as output.

7. The method according to claim 6, characterized in that Taking the simulated core inventory, the simulated burnup and the accident scenario object as inputs and the simulated dose response rate setting value as output, the gated cycle unit model is constructed through a machine learning algorithm, including: Based on the simulated core inventory and multiple accident scenario objects, a simulated core damage state is determined, wherein the simulated core damage state includes at least: a core damage state corresponding to a case where the fuel cladding is damaged by 1% in a simulated accident scenario, a core damage state corresponding to a case where the fuel cladding is damaged by 100% in a simulated accident scenario, a core damage state corresponding to a case where the fuel is melted by 1% in a simulated accident scenario, and a core damage state corresponding to a case where the fuel is melted by 1% in a simulated accident scenario; The gated cyclic unit model is constructed by using the simulated core damage state, the simulated burnup and the accident scenario object as inputs and the simulated dose response rate setting value as output through a machine learning algorithm.

8. A device for determining a set value of a reactor dose response rate under emergency conditions, characterized in that: include: An acquisition module, used to acquire a target accident scenario corresponding to the reactor under emergency conditions; A determination module, configured to determine a target core damage state and a target burnup of the reactor based on the target accident scenario; A response rate module, used for inputting the target core damage state and the target burnup into a gated cycle unit model to obtain a target dose response rate setting value; Among them, the gated cycle unit model constructs a dynamic event tree based on a simulated reactor, determines multiple simulated accident scenarios through the dynamic event tree, obtains the simulated core inventory, simulated fuel consumption and simulated dose response rate setting values ​​corresponding to the multiple simulated accident scenarios, and is constructed through a machine learning algorithm.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executed by a method for determining a set value of a reactor dose response rate under emergency conditions as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of a method for determining a set value of a reactor dose response rate under emergency conditions as described in any one of claims 1 to 7 are implemented.

Images