Crack early warning analysis method and device for nuclear power plant coolant loss accident
By building a core operation model and using historical data to train a fault warning model, identifying the size of the crack in the coolant loss accident in a nuclear power plant, the problems of LOCA accident warning and crack identification are solved, and the safe and stable operation and automation intelligence of the nuclear power plant are achieved change.
Patent Information
- Application Number
- CN202411020052.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-29
- Publication Date
- 2024-11-22
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In nuclear power plants, main circuit coolant loss accident (LOCA) will lead to reactor cooling failure, overheating and potential nuclear leakage. It is difficult for the existing technology to effectively warn and identify the size of the breakout, affecting accident handling and safe and stable operation.
By constructing a core operation model, using historical operation data to train a fault warning model, calculate the Euclidean distance and buck rate, combine the voltage regulator liquid level drop rate, sort to determine the breaking size, and adopt an adaptive integrated neural network optimization model. Realize early identification of coolant loss accidents and intelligent monitoring of breaking size.
Quickly identify the size of the breakout, reduce the difficulty of operator tasks, improve the automation and intelligence level of nuclear reactors, ensure the safe and stable operation of nuclear power plants, and provide an unattended technical foundation.
Smart Images

Figure CN119008059A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of nuclear power plant safety monitoring, and in particular to a breach warning analysis method and device for a coolant loss accident in a nuclear power plant. Background Art
[0002] Under normal operating conditions of a nuclear power plant, operators need to monitor the overall status of the nuclear reactor to ensure that the nuclear reactor is in normal operating conditions. Once an abnormal state of the nuclear reactor is found, the status of the nuclear reactor must be quickly diagnosed and analyzed to determine the cause and source of the abnormality / fault / accident. The fault must be eliminated or the nuclear reactor must be brought into and maintained in a safe state through manual intervention in a timely manner. In a nuclear power plant safety accident, the loss of primary coolant is a serious safety accident, which greatly affects the safety of the nuclear reactor.
[0003] Loss of coolant accident (LOCA) refers to a breach in the reactor's main circuit, where the coolant replenishment capacity is insufficient to compensate for the loss from the breach, causing the core to gradually lose cooling and an accident. It may lead to failure of reactor cooling, overheating of the nuclear reactor, melting of nuclear fuel, or even nuclear leakage. It may also cause system pressure to rise, trigger explosions or damage to other equipment, exacerbate the accident, and may even trigger a chain reaction, affecting other parts of the equipment and expanding the scope and impact of the accident. Therefore, effective measures need to be taken to prevent and deal with such accidents to ensure the safe and stable operation of nuclear power plants. On the one hand, it is necessary to achieve early warning and diagnosis of LOCA accidents to promptly remind operators to intervene, and on the other hand, it is necessary to identify the size of the breach of LOCA accidents in a timely manner so that appropriate intervention measures can be taken for LOCA accidents to reduce the scope of the accident. Summary of the invention
[0004] In order to overcome the above-mentioned deficiencies of the prior art, the present application provides a breach warning analysis method and device for a coolant loss accident in a nuclear power plant, which specifically adopts the following technical solutions:
[0005] A breach warning analysis method for a loss of coolant accident in a nuclear power plant comprises the following steps:
[0006] Determine the relevant parameters and modeling parameters when a nuclear power plant coolant loss accident occurs, and build a core operation model;
[0007] The historical normal operation data of variable operating conditions in different operation periods are collected as training sets and test sets respectively, and the core operation model is trained using the training set to obtain a fault warning model;
[0008] Use the test set to verify the fault warning model. If the verification passes, proceed to the next step; if the verification fails, reselect the training set and train to obtain a new fault warning model;
[0009] Calculate the Euclidean distance between the output data of the fault warning model and the actual data based on the historical normal operation data;
[0010] Determine the difference between the Euclidean distance and the preset threshold value during the corresponding operation period. If the Euclidean distance is less than the preset threshold value, it is determined that a coolant loss accident has occurred, and proceed to the next step. If the Euclidean distance is greater than or equal to the preset threshold value, it is determined that no coolant loss accident has occurred.
[0011] When a coolant loss accident occurs, calculate the main circuit pressure drop rate and the regulator liquid level drop rate;
[0012] The main circuit pressure reduction rate and the stabilizer liquid level reduction rate are sorted to determine the breach size, wherein the breach size includes micro breach, small breach, medium breach and large breach;
[0013] Optional: The historical operating data includes at least containment radioactivity, containment pressure, pressurizer liquid level, main loop pressure and main steam pressure.
[0014] Optional: When the fault warning model is verified using the test set, the containment pressure, pressurizer liquid level and main steam pressure are used for verification.
[0015] Optionally: the step of calculating the Euclidean distance between the output data of the fault warning model and the actual data is:
[0016]
[0017] Where d is the Euclidean distance between the output data of the fault warning model and the actual data; is the actual data corresponding to the running period i; is the output data of the fault warning model during the operation period i; n is the total operation period.
[0018] Optionally: The calculation steps of the main circuit pressure reduction rate are:
[0019]
[0020] Where P s The main circuit pressure reduction rate; P is the main circuit pressure measurement value.
[0021] Optional: The calculation steps of the pressurizer liquid level drop rate are:
[0022]
[0023] where hv is the rate of drop of the pressurizer liquid level; h is the measured value of the pressurizer liquid level.
[0024] Optionally, the step of determining the breach size by sorting the main circuit pressure reduction rate and the regulator liquid level drop rate comprises:
[0025] Set the first pressure reduction rate threshold, the second pressure reduction rate threshold and the third pressure reduction rate threshold of the main circuit pressure reduction rate; set the first liquid level threshold, the second liquid level threshold and the third liquid level threshold of the stabilizer liquid level drop rate;
[0026] Obtain the main circuit pressure reduction rate and the regulator liquid level drop rate in different operating periods respectively;
[0027] When the main circuit pressure reduction rate is less than the first pressure reduction rate threshold, and the regulator liquid level drop rate is less than the first liquid level threshold, the breach size is judged to be a large breach;
[0028] When the main circuit pressure reduction rate is between the first pressure reduction rate threshold and the second pressure reduction rate threshold, and the pressurizer liquid level drop rate is between the first liquid level threshold and the second liquid level threshold, the breach size is judged to be a medium breach;
[0029] When the main circuit pressure reduction rate is between the second pressure reduction rate threshold and the third pressure reduction rate threshold, and the pressurizer liquid level drop rate is between the second liquid level threshold and the third liquid level threshold, the breach size is judged to be a small breach;
[0030] When the main circuit pressure reduction rate is between the second pressure reduction rate threshold and the third pressure reduction rate threshold, and the pressurizer liquid level drop rate is between the second liquid level threshold and the third liquid level threshold, the breach size is judged to be a small breach;
[0031] When the main circuit pressure reduction rate is greater than the third pressure reduction rate threshold, and the regulator liquid level drop rate is greater than the third liquid level threshold, the breach size is determined to be a micro breach.
[0032] Optional: When a coolant loss accident is determined to have occurred based on the Euclidean distance, the containment radioactivity data is used for auxiliary judgment. When the containment radioactivity data shows an upward trend and is greater than the safety radiation threshold, a coolant loss accident is confirmed to have occurred.
[0033] Optional: When the core operation model is trained using the training set, an adaptive integrated neural network is used to optimize the core operation model.
[0034] In addition, the present application also discloses a breach warning analysis device for a coolant loss accident in a nuclear power plant, which comprises:
[0035] Model building module, used to determine the relevant parameters and modeling parameters when a nuclear power plant coolant loss accident occurs, and to build a core operation model;
[0036] A model training module is used to collect historical operating data of variable conditions in different operating periods as training sets and test sets, and use the training sets to train the core operation model to obtain a fault warning model;
[0037] The model verification module is used to verify the fault warning model using the test set. If the verification passes, the next step is performed; if the verification fails, the training set is reselected and a new fault warning model is obtained by training with the model training module;
[0038] A first calculation module, used for calculating the Euclidean distance between the output data of the fault warning model and the actual data based on the historical operation data;
[0039] The accident judgment module is used to judge the size of the Euclidean distance and the preset threshold value in the corresponding operation period. If the Euclidean distance is less than the preset threshold value, it is determined that a coolant loss accident has occurred and the next step is performed; if the Euclidean distance is greater than or equal to the preset threshold value, it is determined that no coolant loss accident has occurred;
[0040] The second calculation module is used to calculate the main circuit pressure reduction rate and the stabilizer liquid level drop rate when a coolant loss accident occurs.
[0041] The breach determination module is used to sort the main circuit pressure reduction rate and the stabilizer liquid level drop rate to determine the breach size, and the breach size includes micro breach, small breach, medium breach and large breach.
[0042] Beneficial Effects
[0043] The technical solution of this application has the following beneficial effects:
[0044] The breach warning analysis method of the present application can quickly identify the size of the breach by using the historical operating data of variable operating conditions to train and analyze the main circuit depressurization rate and the stabilizer liquid level drop rate of the reactor, and then can intelligently monitor and identify the size of the breach in the early stage of an accident, greatly reducing the difficulty of the operating tasks of nuclear power plant operators, improving the automation and intelligence level of nuclear reactors, effectively ensuring the safe and stable operation of nuclear power plants, and providing a technical foundation for low-staff / unmanned operation. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] Figure 1 It is a flow chart of the breach warning analysis method in the embodiment of the present application.
[0046] Figure 2 Schematic diagram of the structure of the breach warning analysis device in the embodiment of the present application.
[0047] Figure 3 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION
[0048] The present application is further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and cannot be used to limit the scope of protection of the present application. It should be noted that the following detailed descriptions are all exemplary and are intended to provide further explanation of the present application.
[0049] At present, the nuclear power plant system mainly uses the coolant in the main circuit to take away the heat generated by the fission of nuclear fuel, and uses the steam generator as a heat exchange site to transfer the heat carried by the main circuit to the secondary circuit, turning the water in the secondary circuit into steam, which is then passed into the turbine to drive its rotation and thus generate electricity.
[0050] The reactor coolant system is the core part of the main loop system (also called the primary loop system). The reactor coolant system has two important functions: one is to transfer the heat energy generated in the reactor from the main loop to the secondary loop, completing the conversion of the nuclear energy of the nuclear fuel to the internal energy of the secondary loop working fluid; the second is to serve as a second barrier to prevent the leakage of radioactive substances. Once the reactor coolant system operates abnormally, the impact will not only affect other components of the main loop system, but also the operation of the secondary loop system.
[0051] Reactor coolant loss is an accident in which the reactor loses coolant due to a rupture or leakage in the coolant system, also known as a loss of coolant accident. When a breach occurs in the coolant system, coolant leakage will occur. The coolant leakage rate varies depending on the size of the breach. For example, when the breach is small, the coolant leaks slowly. At this time, the heat energy leaked through the breach will gradually increase the temperature and pressure in the containment. At this time, the main circuit pressure is controlled by adjusting the opening of the steam generator pressure relief valve to balance the injection flow and the breach leakage. When the breach is large, the coolant will spray out quickly, and the pressure inside the containment will rise rapidly in a short period of time. At this time, boron-containing water needs to be quickly injected, and the temperature and pressure should be reduced in time according to the opportunity, and the radioactive concentration in the containment should be suppressed.
[0052] Therefore, when a reactor coolant loss accident occurs, it is necessary to promptly issue an early warning of the accident and quickly confirm the size of the breach so that operators can take correct measures in time according to the size of the breach to ensure that the reactor cools down quickly and reduce the risk of a melt when an accident occurs.
[0053] like Figure 1 As shown, the embodiment of the present application specifically discloses a breach warning analysis method for a coolant loss accident in a nuclear power plant, which comprises the following steps:
[0054] Step 1: Determine the relevant parameters and modeling parameters when a nuclear power plant coolant loss accident occurs, and build a core operation model;
[0055] Step 2: Collect historical operating data of variable operating conditions in different operating periods as training sets and test sets respectively, and use the training set to train the core operation model to obtain a fault warning model; the historical operating data in the embodiment of the present application at least includes containment radioactivity, containment pressure, pressurizer liquid level, main circuit pressure and main steam pressure. When using the training set to train the core operation model, an adaptive integrated neural network is used to optimize the core operation model.
[0056] Step three: Use the test set to verify the fault warning model. If the verification passes, proceed to the next step; if the verification fails, reselect the training set and train to obtain a new fault warning model. It should be noted that when the fault warning model is verified using the test set in this embodiment, it is preferred to use the containment pressure, the pressurizer liquid level and the main steam pressure for verification.
[0057] Step 4: Calculate the Euclidean distance between the output data of the fault warning model and the actual data based on the historical normal operation data; specifically, the step of calculating the Euclidean distance between the output data of the fault warning model and the actual data in the present application is:
[0058]
[0059] Where d is the Euclidean distance between the output data of the fault warning model and the actual data; is the actual data corresponding to the running period i; is the output data of the fault warning model during the operation period i; n is the total operation period.
[0060] Step 5. Determine the Euclidean distance and the preset threshold value in the corresponding operating period. If the Euclidean distance is less than the preset threshold, it is determined that a coolant loss accident has occurred, and proceed to the next step; if the Euclidean distance is greater than or equal to the preset threshold, it is determined that no coolant loss accident has occurred; further, when a coolant loss accident is determined to have occurred based on the Euclidean distance, the containment radioactivity data can also be used for auxiliary judgment. When the coolant loss accident is determined to have occurred by the Euclidean distance, it can be further determined whether the containment radioactivity data shows an upward trend or whether the containment radioactivity data is greater than the safety radiation threshold. When the containment radioactivity data shows an upward trend or the containment radioactivity data is greater than the safety radiation threshold, it can be confirmed that a coolant loss accident has occurred; but when the containment radioactivity data does not show an upward trend or the containment radioactivity data is not greater than the safety radiation threshold, it is determined that a warning abnormality has occurred, and it can be determined manually or by other means.
[0061] Step 6: When the coolant loss accident is confirmed, the main circuit pressure reduction rate and the regulator liquid level drop rate are calculated in real time;
[0062] The calculation process of the main circuit pressure reduction rate is as follows:
[0063]
[0064] Where P s P is the pressure reduction rate of the main circuit; P is the pressure measurement value of the main circuit; t is the pressure reduction time of the main circuit.
[0065] Furthermore, the calculation process of the pressurizer liquid level drop rate is:
[0066]
[0067] where h v is the rate of drop of the pressurizer liquid level; h is the measured value of the pressurizer liquid level; t is the time duration of the pressurizer liquid level drop.
[0068] Step seven: sort the main circuit pressure reduction rate and the stabilizer liquid level drop rate to determine the breach size, which includes micro breach, small breach, medium breach and large breach.
[0069] Specifically, in the present application, the step of determining the breach size by sorting the main circuit pressure reduction rate and the regulator liquid level drop rate includes:
[0070] The first pressure reduction rate threshold, the second pressure reduction rate threshold and the third pressure reduction rate threshold of the main circuit pressure reduction rate are set; the first liquid level threshold, the second liquid level threshold and the third liquid level threshold of the pressurizer liquid level drop rate are set; it should be noted that the acquisition of the above thresholds in the embodiment of the present application can calculate the main circuit pressure reduction rate and the pressurizer liquid level drop rate under different working conditions according to the historical operation data, and use the main circuit pressure reduction rate and the pressurizer liquid level drop rate as the horizontal coordinate and the vertical coordinate respectively, and construct the liquid level drop rate and the main circuit pressure reduction rate change diagram corresponding to different breach sizes. As shown in the figure, the main circuit pressure reduction rate is used as the vertical coordinate, the unit is MPa / min, which indicates the value of the main circuit pressure drop per minute; the pressurizer liquid level drop rate is used as the horizontal coordinate, the unit is m / min, which indicates the pressurizer liquid level drop value per minute. By analyzing the upper and lower limits of the main circuit pressure reduction rate corresponding to the same breach size and the upper and lower limits of the pressurizer liquid level drop rate, the corresponding thresholds for distinguishing different breach sizes can be obtained.
[0071] Then, the main circuit pressure reduction rate and the regulator liquid level reduction rate under different operating periods are obtained respectively;
[0072] When the main circuit pressure reduction rate is less than the first pressure reduction rate threshold, and the regulator liquid level drop rate is less than the first liquid level threshold, the breach size is judged to be a large breach;
[0073] When the main circuit pressure reduction rate is between the first pressure reduction rate threshold and the second pressure reduction rate threshold, and the pressurizer liquid level drop rate is between the first liquid level threshold and the second liquid level threshold, the breach size is judged to be a medium breach;
[0074] When the main circuit pressure reduction rate is between the second pressure reduction rate threshold and the third pressure reduction rate threshold, and the pressurizer liquid level drop rate is between the second liquid level threshold and the third liquid level threshold, the breach size is judged to be a small breach;
[0075] When the main circuit pressure reduction rate is between the second pressure reduction rate threshold and the third pressure reduction rate threshold, and the pressurizer liquid level drop rate is between the second liquid level threshold and the third liquid level threshold, the breach size is judged to be a small breach;
[0076] When the main circuit pressure reduction rate is greater than the third pressure reduction rate threshold, and the regulator liquid level drop rate is greater than the third liquid level threshold, the breach size is determined to be a micro breach.
[0077] In addition, Figure 2 As shown, the present application also discloses a breach warning analysis device for a coolant loss accident in a nuclear power plant, which comprises:
[0078] Model building module, used to determine the relevant parameters and modeling parameters when a nuclear power plant coolant loss accident occurs, and to build a core operation model;
[0079] A model training module is used to collect historical operating data of variable conditions in different operating periods as training sets and test sets, and use the training sets to train the core operation model to obtain a fault warning model;
[0080] The model verification module is used to verify the fault warning model using the test set. If the verification passes, the next step is performed; if the verification fails, the training set is reselected and a new fault warning model is obtained by training with the model training module;
[0081] A first calculation module, used for calculating the Euclidean distance between the output data of the fault warning model and the actual data based on the historical operation data;
[0082] The accident judgment module is used to judge the size of the Euclidean distance and the preset threshold value in the corresponding operation period. If the Euclidean distance is less than the preset threshold value, it is determined that a coolant loss accident has occurred and the next step is performed; if the Euclidean distance is greater than or equal to the preset threshold value, it is determined that no coolant loss accident has occurred;
[0083] The second calculation module is used to calculate the main circuit pressure reduction rate and the regulator liquid level reduction rate when a coolant loss accident occurs;
[0084] The breach determination module is used to sort the main circuit pressure reduction rate and the stabilizer liquid level drop rate to determine the breach size, and the breach size includes micro breach, small breach, medium breach and large breach.
[0085] The device provided in the embodiment of the present application can implement each process of the breach warning analysis method, and to avoid repetition, it will not be described here.
[0086] like Figure 3 As shown, the embodiment of the present application also provides an electronic device, including a processor and a memory, a program or instruction stored in the memory and executable on the processor, and when the program or instruction is executed by the processor, the following is achieved: Figure 1 The various processes of the method embodiment shown in the figure can achieve the same technical effect. To avoid repetition, they will not be described again here.
[0087] The embodiment of the present application also provides a readable storage medium on which a program or instruction is stored. When the program or instruction is executed by a processor, the above Figure 1 The various processes of the method embodiments described above can achieve the same technical effect, and will not be described again here to avoid repetition.
[0088] The present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the above Figure 1 The various processes of the method embodiments described above can achieve the same technical effect, and will not be described again here to avoid repetition.
[0089] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned sequence numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.
[0090] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.
[0091] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another device, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.
[0092] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0093] In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be a separate unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0094] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, etc., various media that can store program codes.
[0095] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can essentially or in other words, the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a device (which can be a terminal or a platform, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.
[0096] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.
Claims
1. A breach warning analysis method for a coolant loss accident in a nuclear power plant, characterized in that: The steps include: Determine the relevant parameters and modeling parameters when a nuclear power plant coolant loss accident occurs, and build a core operation model; The historical operating data of variable conditions in different operating periods are collected as training sets and test sets respectively, and the core operation model is trained using the training set to obtain a fault warning model; Use the test set to verify the fault warning model. If the verification passes, proceed to the next step; If the verification fails, reselect the training set and train to obtain a new fault warning model; Calculate the Euclidean distance between the output data of the fault warning model and the actual data based on the historical operation data; Determine the difference between the Euclidean distance and the preset threshold value during the corresponding operation period. If the Euclidean distance is less than the preset threshold value, it is determined that a coolant loss accident has occurred, and proceed to the next step. If the Euclidean distance is greater than or equal to the preset threshold value, it is determined that no coolant loss accident has occurred. When a coolant loss accident occurs, calculate the main circuit pressure drop rate and the regulator liquid level drop rate; The main circuit pressure reduction rate and the stabilizer liquid level drop rate are sorted to determine the breach size, which includes micro breach, small breach, medium breach and large breach.
2. The breach warning analysis method according to claim 1, characterized in that: The historical operation data at least includes containment radioactivity, containment pressure, pressurizer liquid level, main loop pressure and main steam pressure.
3. The breach warning analysis method according to claim 1, characterized in that: When the fault warning model is verified using the test set, the containment pressure, pressurizer liquid level and main steam pressure are used for verification.
4. The breach warning analysis method according to claim 1, characterized in that: The step of calculating the Euclidean distance between the output data of the fault warning model and the actual data is: Where d is the Euclidean distance between the output data of the fault warning model and the actual data; is the actual data corresponding to the running period i; is the output data of the fault warning model during the operation period i; n is the total operation period.
5. The breach warning analysis method according to claim 4, characterized in that: The calculation steps of the main circuit pressure reduction rate are: Where P s The main circuit pressure reduction rate; P is the main circuit pressure measurement value.
6. The breach warning analysis method according to claim 4, characterized in that: The calculation steps of the pressurizer liquid level drop rate are: where h v is the rate of drop of the pressurizer liquid level; h is the measured value of the pressurizer liquid level.
7. The breach warning analysis method according to claim 1, characterized in that: The step of sorting the main circuit pressure reduction rate and the stabilizer liquid level drop rate to determine the breach size comprises: Set the first pressure reduction rate threshold, the second pressure reduction rate threshold and the third pressure reduction rate threshold of the main circuit pressure reduction rate; set the first liquid level threshold, the second liquid level threshold and the third liquid level threshold of the stabilizer liquid level drop rate; Obtain the main circuit pressure reduction rate and the regulator liquid level drop rate in different operating periods respectively; When the main circuit pressure reduction rate is less than the first pressure reduction rate threshold, and the regulator liquid level drop rate is less than the first liquid level threshold, the breach size is judged to be a large breach; When the main circuit pressure reduction rate is between the first pressure reduction rate threshold and the second pressure reduction rate threshold, and the pressurizer liquid level drop rate is between the first liquid level threshold and the second liquid level threshold, the breach size is judged to be a medium breach; When the main circuit pressure reduction rate is between the second pressure reduction rate threshold and the third pressure reduction rate threshold, and the pressurizer liquid level drop rate is between the second liquid level threshold and the third liquid level threshold, the breach size is judged to be a small breach; When the main circuit pressure reduction rate is between the second pressure reduction rate threshold and the third pressure reduction rate threshold, and the pressurizer liquid level drop rate is between the second liquid level threshold and the third liquid level threshold, the breach size is judged to be a small breach; When the main circuit pressure reduction rate is greater than the third pressure reduction rate threshold, and the regulator liquid level drop rate is greater than the third liquid level threshold, the breach size is determined to be a micro breach.
8. The breach warning analysis method according to claim 5, characterized in that: When a coolant loss accident is determined to have occurred based on the Euclidean distance, the containment radioactivity data is used for auxiliary judgment. When the containment radioactivity data shows an upward trend and is greater than the safety radiation threshold, a coolant loss accident is confirmed to have occurred.
9. The breach warning analysis method according to claim 1, characterized in that: When the core operation model is trained using the training set, an adaptive integrated neural network is used to optimize the core operation model.
10. A breach warning analysis device for a coolant loss accident in a nuclear power plant, characterized in that: include: Model building module, used to determine the relevant parameters and modeling parameters when a nuclear power plant coolant loss accident occurs, and to build a core operation model; A model training module is used to collect historical operating data of variable conditions in different operating periods as training sets and test sets, and use the training sets to train the core operation model to obtain a fault warning model; The model verification module is used to verify the fault warning model using the test set. If the verification passes, the next step is performed. If the verification fails, the training set is reselected and the model training module is used to train a new fault warning model; A first calculation module, used for calculating the Euclidean distance between the output data of the fault warning model and the actual data based on the historical operation data; The accident judgment module is used to judge the size of the Euclidean distance and the preset threshold value in the corresponding operation period. If the Euclidean distance is less than the preset threshold value, it is determined that a coolant loss accident has occurred and the next step is performed; if the Euclidean distance is greater than or equal to the preset threshold value, it is determined that no coolant loss accident has occurred; The second calculation module is used to calculate the main circuit pressure reduction rate and the regulator liquid level reduction rate when a coolant loss accident occurs; The breach determination module is used to sort the main circuit pressure reduction rate and the stabilizer liquid level drop rate to determine the breach size, and the breach size includes micro breach, small breach, medium breach and large breach.
Citation Information
Patent Citations
Cooling method, device and system for loss-of-coolant accident of first loop of nuclear power station
CN105469840A
Pressurized water reactor large break loss of coolant accident starting emergency working condition prediction method
CN110970142A
Nuclear power station equipment comprehensive state evaluation method and device based on feature vector space
CN115249126A
Nuclear power plant accident intelligent identification and decision-making method and system
CN115564247A
Pressurized water reactor nuclear power plant water loss accident diagnosis method and system based on LSTM
CN116759126A
