Method, apparatus and storage medium for monitoring physical fields of a nuclear reactor

Abstract

The application relates to a nuclear reactor physical field monitoring method, device, equipment and storage medium. The method comprises the following steps: based on a response data splicing rule, splicing real-time response data collected by at least two types of nuclear reactor detectors to obtain detector measurement values; wherein the nuclear reactor detectors are arranged in the nuclear reactor core and / or outside the nuclear reactor core; determining reduced basis fitting coefficients according to the detector measurement values; determining a real-time monitoring data set of the nuclear reactor according to a target reduced basis and the reduced basis fitting coefficients; and determining real-time monitoring data of at least two physical fields of the nuclear reactor from the real-time monitoring data set according to a physical field splitting rule corresponding to the response data splicing rule. The method can improve the efficiency and accuracy of nuclear reactor core physical monitoring.

Description

Methods, devices, equipment, and storage media for monitoring the physical fields of nuclear reactors Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, equipment and storage medium for monitoring the physical field of a nuclear reactor. Background Technology

[0002] With the development of artificial intelligence technology in various fields, a technology has emerged in nuclear power plants that uses neural network models to analyze data monitored in the nuclear reactor core, thereby obtaining real-time monitoring data of the nuclear reactor core.

[0003] However, a nuclear reactor core comprises multiple physical fields. Obtaining real-time monitoring data for the reactor core requires integrating data from each physical field. Current technology employs a separate monitoring algorithm for each physical field to obtain corresponding monitoring data, which is then integrated to generate real-time monitoring data for the reactor core. This process is cumbersome and inefficient. Furthermore, inconsistencies may arise during the integration of different types of monitoring data, resulting in lower processing quality and affecting the accuracy of the nuclear reactor physical field monitoring results. These issues urgently need to be addressed. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, equipment, and storage medium for monitoring the physical field of a nuclear reactor that can improve the efficiency and accuracy of physical monitoring of the reactor core, in order to address the aforementioned technical problems.

[0005] Firstly, this application provides a method for monitoring the physical fields of a nuclear reactor. The method includes:

[0006] Based on the response data splicing rules, real-time response data collected by at least two types of nuclear reactor detectors are spliced ​​together to obtain detector measurements; wherein, the nuclear reactor detectors are configured inside and / or outside the nuclear reactor.

[0007] Determine the reduced basis fitting coefficients based on the detector measurements;

[0008] Based on the target reduction basis and the reduction basis fitting coefficient, the real-time monitoring dataset of the nuclear reactor is determined;

[0009] Based on the physical field splitting rules corresponding to the response data splicing rules, determine the real-time monitoring data of at least two physical fields of the nuclear reactor from the real-time monitoring dataset.

[0010] In one embodiment, determining the reduced basis fitting coefficients based on detector measurements includes:

[0011] The reduced basis fitting coefficients are determined based on detector measurements using a nonlinear fitting model.

[0012] In one embodiment, the reduced basis fitting coefficients are determined based on detector measurements using a nonlinear fitting model, including:

[0013] The detector measurements are normalized and then input into the nonlinear fitting model to obtain the reduced basis fitting coefficients.

[0014] In one embodiment, the number of target sub-reduction bases included in the target reduction basis is the same as the number of sub-fit coefficients included in the reduction basis fitting coefficients, and they correspond one-to-one.

[0015] Accordingly, based on the target reduction basis and the reduction basis fitting coefficient, the real-time monitoring dataset of the nuclear reactor is determined, including:

[0016] By fusing the target sub-reduction basis and sub-fit coefficients that have corresponding relationships, at least one set of sub-datasets can be obtained;

[0017] The datasets from each subset are combined to obtain the real-time monitoring dataset for the nuclear reactor.

[0018] In one embodiment, the method further includes:

[0019] Obtain simulation distribution data of at least two physical fields corresponding to nuclear reactors under various operating conditions;

[0020] According to the physical field splicing rules, the simulation distribution data of at least two physical fields corresponding to various operating conditions are spliced ​​to obtain the simulation monitoring dataset of nuclear reactors under various operating conditions; among them, the physical field splicing rules and the physical field splitting rules are a set of inverse rules.

[0021] The simulation monitoring dataset of nuclear reactors under various operating conditions is subjected to order reduction calculation to obtain candidate sub-reduction basis and candidate singular values; the number of candidate sub-reduction basis and candidate singular values ​​is the same and they correspond one-to-one.

[0022] Based on the candidate sub-reduction basis and candidate singular values, the target reduction basis is selected from the candidate sub-reduction basis.

[0023] In one embodiment, selecting a target reduction basis from candidate sub-reduction basis based on candidate sub-reduction basis and candidate singular values ​​includes:

[0024] Sort the candidate singular values ​​according to their size;

[0025] The target number of reduction bases is determined based on the sorted candidate singular values ​​and the preset threshold.

[0026] Based on the number of target reduction bases and the ranking of candidate singular values, target reduction bases are selected from candidate sub-reduction bases.

[0027] In one embodiment, determining the target reduction base number based on the sorted candidate singular values ​​and a preset threshold includes:

[0028] The largest candidate singular value is selected as the current singular value, and the current singular value is added to the singular value set.

[0029] Determine the ratio of the first singular value summation result to the second singular value summation result; wherein, the first singular value summation result is the sum of all candidate singular values ​​located in the singular value set; and the second singular value summation result is the sum of all candidate singular values.

[0030] Determine if the ratio is less than a preset threshold;

[0031] If so, the next candidate singular value sorted after the current singular value is taken as the current singular value, and the operation of adding the current singular value to the singular value set is returned.

[0032] If not, the number of candidate singular values ​​in the singular value set is used as the target reduction basis number.

[0033] Secondly, this application also provides a physical field monitoring device for a nuclear reactor. The device includes:

[0034] The first splicing module, based on response data splicing rules, splices real-time response data collected by at least two types of nuclear reactor detectors to obtain detector measurement values; wherein, the nuclear reactor detectors are configured inside and / or outside the nuclear reactor.

[0035] The coefficient determination module is used to determine the reduced basis fitting coefficients based on the detector measurements.

[0036] The dataset determination module is used to determine the real-time monitoring dataset of the nuclear reactor based on the target reduction basis and the reduction basis fitting coefficient.

[0037] The monitoring data determination module is used to determine the real-time monitoring data of at least two physical fields of the nuclear reactor from the real-time monitoring dataset according to the physical field splitting rules corresponding to the response data splicing rules.

[0038] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0039] Based on the response data splicing rules, real-time response data collected by at least two types of nuclear reactor detectors are spliced ​​together to obtain detector measurements; wherein, the nuclear reactor detectors are configured inside and / or outside the nuclear reactor.

[0040] Determine the reduced basis fitting coefficients based on the detector measurements;

[0041] Based on the target reduction basis and the reduction basis fitting coefficient, the real-time monitoring dataset of the nuclear reactor is determined;

[0042] Based on the physical field splitting rules corresponding to the response data splicing rules, determine the real-time monitoring data of at least two physical fields of the nuclear reactor from the real-time monitoring dataset.

[0043] Fourthly, this application also provides a computer-readable storage medium. This computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0044] Based on the response data splicing rules, real-time response data collected by at least two types of nuclear reactor detectors are spliced ​​together to obtain detector measurements; wherein, the nuclear reactor detectors are configured inside and / or outside the nuclear reactor.

[0045] Determine the reduced basis fitting coefficients based on the detector measurements;

[0046] Based on the target reduction basis and the reduction basis fitting coefficient, the real-time monitoring dataset of the nuclear reactor is determined;

[0047] Based on the physical field splitting rules corresponding to the response data splicing rules, determine the real-time monitoring data of at least two physical fields of the nuclear reactor from the real-time monitoring dataset.

[0048] Fifthly, this application also provides a computer program product. This computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0049] Based on the response data splicing rules, real-time response data collected by at least two types of nuclear reactor detectors are spliced ​​together to obtain detector measurements; wherein, the nuclear reactor detectors are configured inside and / or outside the nuclear reactor.

[0050] Determine the reduced basis fitting coefficients based on the detector measurements;

[0051] Based on the target reduction basis and the reduction basis fitting coefficient, the real-time monitoring dataset of the nuclear reactor is determined;

[0052] Based on the physical field splitting rules corresponding to the response data splicing rules, determine the real-time monitoring data of at least two physical fields of the nuclear reactor from the real-time monitoring dataset.

[0053] The aforementioned physical field monitoring methods, devices, equipment, and storage media for nuclear reactors monitor the nuclear reactor using at least two types of nuclear reactor detectors, obtaining multiple types of real-time response data that reflect the reactor's operational status from multiple dimensions. The real-time response data is then stitched together according to response data stitching rules to obtain detector measurements describing the overall state of the nuclear reactor. Using these detector measurements to replace the various types of response data improves the uniformity of the response data and facilitates subsequent processing. Furthermore, the reduction basis fitting coefficients are determined based on the detector measurements, and combined with a pre-defined target reduction basis, a real-time monitoring dataset for the nuclear reactor is established. Because the real-time monitoring dataset integrates monitoring results from multiple types of detectors, it provides a more consistent reflection of the nuclear reactor's real-time operational status. Furthermore, by stitching together the response data corresponding to each physical field of the nuclear reactor, and processing only the detector measurements obtained after stitching, rather than processing the monitoring data of each physical field separately, the efficiency of acquiring real-time monitoring datasets can be improved, thereby increasing the efficiency of acquiring real-time monitoring data for at least two physical fields of the nuclear reactor. Moreover, in determining the real-time monitoring dataset, the fitting coefficient of the reduction basis corresponding to the target reduction basis is considered while utilizing the target reduction basis, which can improve the accuracy of the real-time monitoring dataset to a certain extent, thereby improving the accuracy of real-time monitoring data for at least two physical fields of the nuclear reactor. In other words, the entire process can improve the efficiency and accuracy of nuclear reactor core physical monitoring. Attached Figure Description

[0054] Figure 1 is an application environment diagram of a physical field monitoring method for a nuclear reactor provided in this embodiment;

[0055] Figure 2 is a flowchart illustrating the first method for monitoring the physical field of a nuclear reactor provided in this embodiment;

[0056] Figure 3 is a schematic diagram of a process for determining a target reduction basis provided in this embodiment;

[0057] Figure 4 is a schematic diagram of a process for determining the target number of reduction bases provided in this embodiment;

[0058] Figure 5 is a flowchart illustrating the second method for monitoring the physical field of a nuclear reactor provided in this embodiment;

[0059] Figure 6 is a structural block diagram of the physical field monitoring device for the first type of nuclear reactor provided in this embodiment;

[0060] Figure 7 is a structural block diagram of the physical field monitoring device for the second type of nuclear reactor provided in this embodiment;

[0061] Figure 8 is a structural block diagram of the physical field monitoring device for the third type of nuclear reactor provided in this embodiment;

[0062] Figure 9 is a structural block diagram of the physical field monitoring device for the fourth type of nuclear reactor provided in this embodiment;

[0063] Figure 10 is an internal structure diagram of a computer device provided in this embodiment. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0065] Before introducing the nuclear reactor physical field monitoring method provided in the embodiments of this application, it should be noted that the multi-physics fields within the nuclear reactor core can include the temperature field of the fuel or coolant, the coolant flow field, the neutron flux distribution field, and the power distribution field within the fuel. Real-time monitoring of the multi-physics fields within the nuclear reactor core is crucial for ensuring the safe and efficient operation of the nuclear reactor and is also one of the key aspects of nuclear safety supervision. For example, temperature control of the nuclear reactor is essential for ensuring its safe and efficient operation. Typically, reactor temperature control mainly refers to the control of the primary loop average temperature, while the temperatures of the fuel assemblies and the interior of the core cannot be directly measured. Currently, the range of their variation can only be estimated through a series of related parameters, and incorrect estimations may lead to over-power operation of the reactor, resulting in core meltdown or even catastrophic accidents such as nuclear leakage. Therefore, accurate measurement or estimation of the temperatures of the fuel assemblies and the interior of the core is crucial for assessing the safety and stability of reactor operation. For example, monitoring the core power distribution is crucial for the critical safety and thermal safety of a nuclear reactor. However, the power of the core fuel assemblies themselves is not measurable and can only be obtained indirectly by measuring parameters such as neutron response. Furthermore, due to limitations in the accuracy of measuring instruments and harsh measurement environments, it is currently difficult to obtain accurate and stable full-field measurement results, and under certain conditions, direct measurement is even impossible.

[0066] Currently, monitoring of the reactor core temperature is mainly achieved by measuring the coolant outlet temperature using thermocouples. However, this method has the following problems: (1) The measured temperature is the outlet coolant temperature, which does not directly reflect the internal temperature of the reactor core. (2) The measurement only targets the temperature at some discrete points, and cannot obtain the three-dimensional temperature distribution inside the reactor core. (3) The working conditions are harsh, leading to the reliance on imports for some temperature measuring devices, resulting in high costs. Furthermore, different types of nuclear reactor detectors are deployed inside or outside the reactor core to measure neutron flux or power distribution. Typical nuclear reactor detectors include self-powered neutron detectors (SPDs) inside the reactor core, external neutron detectors (EXCOREs) outside the reactor pressure vessel (RPV), and thermocouples (T / C) located at the coolant inlet and outlet of the fuel assemblies. SPDs placed in the fuel assemblies are directly used to monitor neutron reactions generated within the fuel assemblies, while EXCOREs are affected by the diffusion of neutrons from the outer core assemblies to the sensitive section of the external core detector. The outlet T / C readings of the coolant temperature at the fuel assembly outlet, as well as the uniform inlet temperature of the coolant, can indirectly monitor changes in the average power distribution of each assembly. Signals generated by these core detectors (such as SPD, EXCORE, and T / C) are commonly used in reactor core monitoring systems (CMS) to monitor multiphysics changes within the operating reactor core in real time. While these detectors are strategically placed, they only cover a portion of the core or reflect only a part of the multiphysics quantities to be monitored. Therefore, it is necessary to acquire indirect measurement information for the entire reactor location.

[0067] The nuclear reactor physical field monitoring method provided in this application embodiment can be applied to the application environment shown in Figure 1. In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram is shown in Figure 1. The computer device includes a processor, memory, and network interface connected via a system bus. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device stores relevant data for monitoring the physical field of the nuclear reactor. The network interface of the computer device is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a nuclear reactor physical field monitoring method.

[0068] In one embodiment, as shown in Figure 2, a method for monitoring the physical field of a nuclear reactor is provided. Taking the application of this method to the computer in Figure 1 as an example, the method includes the following steps:

[0069] S201, based on the response data splicing rules, splices the real-time response data collected by at least two types of nuclear reactor detectors to obtain the detector measurement values.

[0070] Nuclear reactor detectors are located inside and / or outside the nuclear reactor. They are a crucial component of the control rod drive mechanism, used to monitor the actual position and timing of the control rods in the reactor and to provide control and protection interlock signals. Response data can be the output values ​​of various detectors used to monitor the reactor's operating status. Response data can be of many types, each corresponding one-to-one with the type of nuclear reactor detector. For example, the types of response data can include at least: in-core neutron detector response SPD(i), out-of-core detector response EXCORE(j), in-core and out-of-core thermocouple responses T / C(k), in-core and out-of-core pressure sensor responses Press(m), and in-core and out-of-core flowmeter responses Flowmeter(n); where i, j, k, m, and n represent the number of each type of nuclear reactor detector. It is understood that the type and number of nuclear reactor detectors correspond one-to-one with the response data. In other words, if the nuclear reactor detectors include 10 thermocouple detectors at the outlets and 10 in-core self-powered neutron detectors, then the real-time response data includes the thermocouple responses T / C(k) inside and outside the core and the in-core neutron detector responses SPD(i), where both k and i are 10. The splicing rules can be pre-determined rules used to fuse the output values ​​of each detector; these rules can be determined based on historical experience. The detector measurements are obtained by fusing the output values ​​of each detector using the response data splicing rules, and these measurements directly reflect the monitoring status of the nuclear reactor.

[0071] Optionally, real-time response data can be obtained by placing various types of nuclear reactor detectors at corresponding locations within the nuclear reactor. For example, the nuclear reactor detectors can be configured inside the reactor core and connected to a nuclear reactor monitoring system. During reactor combustion, the detectors monitor the combustion status in real time and send the monitoring data to the nuclear reactor monitoring system, where the real-time response data can be read. Alternatively, the nuclear reactor detectors can be configured outside the reactor core and connected to the nuclear reactor monitoring system. During reactor combustion, the detectors monitor the reactor core in real time and send the monitoring data to the nuclear reactor monitoring system, where the real-time response data can be read. In this embodiment, the nuclear reactor detectors can also be configured both inside and outside the reactor core; this is not limited.

[0072] Optionally, the detector measurement values ​​can be obtained by combining the real-time response data collected by each nuclear reactor detector with the response data splicing rules to obtain the splicing results, and then using the splicing results as the detector measurement values.

[0073] For example, taking a nuclear reactor detector comprising i in-core neutron detectors (SPDs), j external detectors (EXCOREs), and k thermocouples (T / Cs) inside and outside the reactor core, the response data can include the in-core neutron detector response SPD(i), the external detector response EXCORE(j), and the thermocouple responses T / C(k). Then, the real-time response data collected by various nuclear reactor detectors can be spliced ​​using the response data splicing rules shown in formula (1), and the detector measurement values ​​can be determined based on the splicing results.

[0074]

[0075] In the formula, MD(t) represents the detector measurement value; SPD(i) represents the response of the in-core neutron detector; EXCORE(j) represents the response of the external detector; and T / C(k) represents the response of each thermocouple inside and outside the core.

[0076] S202, Determine the reduced basis fitting coefficients based on the detector measurements.

[0077] Among them, the reduction basis fitting coefficient can be a coefficient used to characterize the importance of each reduction basis, which can be understood as the weight of each reduction basis.

[0078] Optionally, the reduced basis fitting coefficients can also be determined by pre-determining a reduced basis fitting coefficient determination strategy. This strategy includes strategies for determining reduced basis fitting coefficients corresponding to various detector measurements. Based on the detector measurements, the corresponding reduced basis fitting coefficients can be determined using this strategy. Alternatively, the reduced basis fitting coefficients can be determined using a nonlinear fitting model based on the detector measurements. The nonlinear fitting model can be a pre-trained model used to process the detector measurements. In this embodiment, the detector measurements can be input into the pre-trained nonlinear fitting model, which processes the input measurements and outputs the corresponding reduced basis fitting coefficients.

[0079] It should be noted that the nonlinear fitting model construction methods used in determining the reduced basis fitting coefficients can include various typical machine learning methods, such as deep neural networks, radial basis function neural networks, random forests, stochastic gradient regression, or ridge regression algorithms. Using neural network models to determine the reduced basis fitting coefficients can make the determination faster and more accurate.

[0080] Furthermore, since the physical magnitudes of the responses of different detectors vary greatly, all detector readings can be normalized, i.e., the detector measurement data values ​​can be scaled to the interval [0, 1]. Therefore, in the process of determining the reduced basis fitting coefficients, the detector measurements can also be normalized, and the normalized detector measurements can be input into the nonlinear fitting model to obtain the reduced basis fitting coefficients. Optionally, there are many ways to normalize the detector measurements, and no limitation is made on this. One possible approach is to pre-train a normalization model, input the detector measurements into the normalization model, process the detector measurements, and input the normalized detector measurements. Another possible approach is to pre-determine a normalization formula, such as formula (2), and obtain the normalized detector measurements based on the detector measurements and the normalization formula.

[0081] MD t '=(MD t -max(MD t )) / (max(MD t )-min(MD t (2)

[0082] In the formula, MD t 'Represents the detector measurement after normalization; MD t This represents the detector's measured value; max(MD) t () represents the largest value among the detector measurements; min(MD) t ) represents the smallest value among the detector measurements.

[0083] In this embodiment, the detector measurements are normalized during the process of determining the reduced basis fitting coefficients, which can improve the processing efficiency of the nonlinear fitting model.

[0084] S203, based on the target reduction basis and the reduction basis fitting coefficient, determines the real-time monitoring dataset of the nuclear reactor.

[0085] The target reduction basis can be the parameters obtained by reducing the dimensionality of the nuclear reactor's physical field. The real-time monitoring dataset can be data used to characterize all monitoring results of the nuclear reactor, or it can be a fusion of monitoring results from multiple detectors.

[0086] Optionally, the real-time monitoring dataset for a nuclear reactor can be determined by: pre-training a dataset determination model, inputting the target reduction basis and the reduction basis fitting coefficients into the model, and having the model process the input target reduction basis and reduction basis fitting coefficients to output the corresponding real-time monitoring dataset for the nuclear reactor; or pre-determining a dataset determination formula, substituting the target reduction basis and the reduction basis fitting coefficients into the formula to calculate the real-time monitoring dataset for the nuclear reactor.

[0087] It should be noted that the number of target sub-reduction bases contained in the target reduction basis is the same as the number of sub-fitting coefficients contained in the reduction basis fitting coefficients, and they correspond one-to-one; that is, the reduction basis sub-fitting coefficients correspond one-to-one with the target sub-reduction bases. Accordingly, based on the target reduction basis and the reduction basis fitting coefficients, the real-time monitoring dataset of the nuclear reactor is determined, including: fusing the corresponding target sub-reduction bases and sub-fitting coefficients to obtain at least one set of subsets; and combining the subsets to obtain the real-time monitoring dataset of the nuclear reactor. Optionally, fusing the corresponding target sub-reduction bases and sub-fitting coefficients can be done by multiplying the corresponding target sub-reduction bases and sub-fitting coefficients to determine the product, and using the product of the target sub-reduction bases and sub-fitting coefficients as the subset. Multiplying each corresponding target sub-reduction base and sub-fitting coefficient yields multiple products, thus obtaining multiple subsets. The real-time monitoring dataset of the nuclear reactor can be obtained by combining the various subset datasets. Optionally, the subset datasets can be combined by adding them together, that is, by adding the subset datasets together to obtain the sum of the subset datasets, which serves as the real-time monitoring dataset of the nuclear reactor. For example, the dataset determination formula can be shown in the following formula (3):

[0088]

[0089] In the formula, Multiphysis(s) represents the real-time monitoring dataset of the nuclear reactor; Indicates the first subfit coefficient; This represents the first sub-reduction basis corresponding to the first sub-fit coefficient; correspondingly, Represents the fitting coefficient of the m-th sub-unit; This represents the m-th sub-reduction basis corresponding to the m-th sub-fit coefficient.

[0090] S204. Based on the physical field splitting rules corresponding to the response data splicing rules, determine the real-time monitoring data of at least two physical fields of the nuclear reactor from the real-time monitoring dataset.

[0091] The physical field splitting rules can be pre-defined rules for splitting the fused physical field. It's important to note that since the response data corresponds to the detector type (one type of detector corresponds to one type of response data) and the detector type corresponds to the nuclear reactor physical field (one type of detector monitors one type of physical field data in the nuclear reactor), the physical fields are spliced ​​simultaneously with the response data. In other words, each response data splicing rule has a corresponding physical field splicing rule, and the various physical fields of the nuclear reactor can generate a fused physical field based on these splicing rules. Correspondingly, the reverse process of the physical field splicing rules is the physical sound splitting rule.

[0092] Optionally, in this embodiment, the real-time monitoring dataset can be processed according to the physical field splitting rules to split the real-time monitoring dataset into real-time monitoring data of at least two physical fields of the nuclear reactor. Alternatively, the real-time monitoring dataset and the physical field splitting rules can be input into a pre-trained splitting model, and the model can process the real-time monitoring dataset according to the physical field splitting rules to output real-time monitoring data of at least two physical fields of the nuclear reactor.

[0093] In the aforementioned method for monitoring the physical field of a nuclear reactor, the reactor is monitored using at least two types of nuclear reactor detectors, resulting in various types of real-time response data. This data reflects the reactor's operational status from multiple dimensions. The real-time response data is then stitched together according to response data stitching rules to obtain detector measurements describing the overall state of the reactor. Using these detector measurements to replace the different types of response data improves the uniformity of the response data and facilitates subsequent processing. Furthermore, a reduction basis fitting coefficient is determined based on the detector measurements, and combined with a pre-defined target reduction basis, a real-time monitoring dataset for the nuclear reactor is established. Because the real-time monitoring dataset integrates monitoring results from multiple types of detectors, it provides a more consistent reflection of the reactor's real-time operational status. Furthermore, by stitching together the response data corresponding to each physical field of the nuclear reactor, and processing only the detector measurements obtained after stitching, rather than processing the monitoring data of each physical field separately, the efficiency of acquiring real-time monitoring datasets can be improved, thereby increasing the efficiency of acquiring real-time monitoring data for at least two physical fields of the nuclear reactor. Moreover, in determining the real-time monitoring dataset, the fitting coefficient of the reduction basis corresponding to the target reduction basis is considered while utilizing the target reduction basis, which can improve the accuracy of the real-time monitoring dataset to a certain extent, thereby improving the accuracy of real-time monitoring data for at least two physical fields of the nuclear reactor. In other words, the entire process can improve the efficiency and accuracy of nuclear reactor core physical monitoring.

[0094] It should be noted that the target reduction basis used in step S203 above can be predetermined, as shown in Figure 3. The process of determining the target reduction basis can be described in detail, and may include the following steps:

[0095] S301, acquire simulation distribution data of at least two physical fields corresponding to nuclear reactors under various operating conditions.

[0096] In this context, physical fields can be parameters used to characterize and evaluate the operation of a nuclear reactor across multiple dimensions. It is understood that during operation, a nuclear reactor can have at least two physical fields describing its operational state. Simulation distribution data can be data used to describe the operation of the nuclear reactor.

[0097] Optionally, the simulation distribution data can be obtained by adjusting the operating parameters of the nuclear reactor to allow the reactor to traverse all operating conditions. For each operating condition, multiphysics simulation software within the reactor core is used to perform calculations to obtain the corresponding physical field data for each condition. Based on the physical field data of the nuclear reactor under each operating condition, the simulation distribution data is determined. It is understood that the physical field data corresponding to the nuclear reactor under each operating condition can also include at least the in-core neutron detector response SPD(i), the external detector response EXCORE(j), the responses T / C(k) of various thermocouples inside and outside the reactor core, the responses Press(m) of pressure sensors inside and outside the reactor core, and the responses Flowmeter(n) of flowmeters inside and outside the reactor core. The difference is that the simulation distribution data can be calculated using simulation software, rather than being monitored in real time by detectors.

[0098] It should be noted that the operating parameters of a nuclear reactor can include at least the power level, reactivity control measures (such as control rod position or soluble boron concentration), inlet and outlet temperatures, power operating history, or control rod operating history (controlling xenon oscillation). Simulation software can include physical-thermal-mechanical coupling software (e.g., SARAX nuclear design software or COMSOL), multiphysics analysis software, or CFD fluid simulation software. Multiphysics fields can include temperature field T(r1), flow field F(r2), pressure field P(r3), neutron field N(r4), and power distribution field Pow(r5).

[0099] S302. According to the physical field splicing rules, the simulation distribution data of at least two physical fields corresponding to various operating conditions are spliced ​​to obtain the simulation monitoring dataset of nuclear reactors under various operating conditions.

[0100] Among them, the physical field splicing rule and the physical field splitting rule are a set of inverse rules. Optionally, the simulation monitoring dataset of the nuclear reactor under various operating conditions can be obtained by first processing the simulation distribution data of each physical field of the nuclear reactor under each operating condition in combination with the physical field splicing rule to obtain the simulation monitoring dataset of the nuclear reactor under that operating condition. Thus, the simulation monitoring dataset of the nuclear reactor under various operating conditions can be obtained. For example, if the nuclear reactor includes three physical fields: temperature field T(r1), flow field F(r2), and pressure field P(r3), the simulation distribution data of each physical field of the nuclear reactor under one operating condition can be spliced ​​according to the physical field splicing rule shown in the following formula (4) to obtain the simulation monitoring dataset of the nuclear reactor under that operating condition.

[0101]

[0102] In the formula, Multiphysis(s') represents the simulation monitoring dataset corresponding to a nuclear reactor under a certain operating condition; T(r1) represents the temperature field monitoring data; F(r2) represents the flow field monitoring data; P(r3) represents the pressure field monitoring data; and r represents the dimension identifier.

[0103] For the physical field simulation distribution data under various operating conditions, the data is spliced ​​according to the splicing method shown in the above formula (4) to obtain the simulation monitoring dataset of nuclear reactor under various operating conditions. For example, if the number of operating conditions is a, the simulation monitoring dataset of nuclear reactor under various operating conditions Multiphysis(s', a) can be obtained. It should be noted that, under normal circumstances, a needs to be at least 100.

[0104] S303 performs order reduction calculations on simulation monitoring datasets of nuclear reactors under various operating conditions to obtain candidate sub-reduction basis and candidate singular values.

[0105] In this system, the number of candidate sub-reduction bases and candidate singular values ​​are the same, and they correspond one-to-one. A candidate sub-reduction base can be any reduction base, and correspondingly, a candidate singular value can be any singular value corresponding to any reduction base.

[0106] In this embodiment, a model reduction method can be used to reduce the order of the simulation monitoring dataset of the nuclear reactor. For example, intrinsic orthogonal decomposition (POD) or singular value decomposition (SVD) can be used to reduce the order of Multiphysis(s', a). Candidate sub-reduction bases are then obtained. and the corresponding candidate singular values

[0107] S304. Based on the candidate sub-reduction basis and the candidate singular value, select the target reduction basis from the candidate sub-reduction basis.

[0108] Optionally, in this embodiment, the method for selecting the target reduction basis can be to input candidate sub-reduction basis and candidate singular values ​​into a pre-determined target reduction basis selection model, which processes the input candidate sub-reduction basis and candidate singular values ​​and outputs the target reduction basis. Another possible approach is to sort the candidate singular values ​​according to their size; determine the number of target reduction basis units based on the sorted candidate singular values ​​and a preset threshold; and select the target reduction basis from the candidate sub-reduction basis units based on the number of target reduction basis units and the sorting result of the candidate singular values. The preset threshold can be a pre-set threshold used to determine the number of reduction basis units. In this embodiment, the method for sorting the candidate singular values ​​can be to sort them in descending order, and the number of target reduction basis units can be determined based on the sorted candidate singular values ​​and the preset threshold, combined with a pre-determined target reduction basis unit number determination strategy. Alternatively, the number of target reduction bases can be determined by combining the sorted candidate singular values ​​and the preset threshold with the predetermined number of target reduction bases. For example, the number of target reduction bases can be determined by the following formula (5). Specifically, the smallest m value that satisfies the following formula (5) is obtained, and the m value is taken as the number of target reduction bases.

[0109]

[0110] In the formula, Let i represent candidate singular values, where i ranges from 1 to n. Represents all candidate singular values; The value of x represents the target singular value, which ranges from 1 to m; m is the number of target reduction bases; and e is the preset threshold.

[0111] After determining the number of target reduction bases (taking m as an example), based on the number of target reduction bases and the ranking of candidate singular values, the top m candidate singular values ​​are taken as target singular values, and the candidate sub-reduction bases corresponding to the target singular values ​​are taken as target reduction bases. This implementation reduces the number of reduction bases by selecting target reduction bases from candidate sub-reduction bases, which facilitates the subsequent determination of the real-time monitoring dataset for the nuclear reactor.

[0112] In the above embodiments, the simulated distribution data includes at least two physical field data corresponding to the nuclear reactor under various operating conditions. This allows the simulated distribution data to comprehensively reflect the operating status of the nuclear reactor. Furthermore, using simulated monitoring data instead of real monitoring data can reduce the waste of nuclear power resources. Performing order reduction calculations on the simulated monitoring dataset to determine the target reduction basis can reduce the physical field dimension, providing a guarantee for determining the real-time monitoring dataset of the nuclear reactor in subsequent practical applications.

[0113] Furthermore, to make the process of determining the number of target reduction bases more comprehensive, in one embodiment, as shown in FIG4, the method of selecting target reduction bases from candidate sub-reduction bases based on candidate sub-reduction bases and candidate singular values ​​in S304 is described in detail, which may include the following steps:

[0114] S401, take the largest candidate singular value as the current singular value, and add the current singular value to the singular value set.

[0115] The singular value set can be a set used to store the current singular values.

[0116] Specifically, in this embodiment, for the sorted candidate singular values, the candidate singular value that is first in the sort and the largest is taken as the current singular value and added to the singular value set.

[0117] S402, determine the ratio of the first singular value summation result to the second singular value summation result.

[0118] The first singular value summation result is the sum of all candidate singular values ​​located in the singular value set; the second singular value summation result is the sum of all candidate singular values.

[0119] Specifically, in this embodiment, the singular values ​​in the singular value set are summed, and the summation result is used as the first singular value summation result. All candidate singular values ​​are summed, and the summation result is used as the second singular value summation result. The ratio of the first singular value summation result to the second singular value summation result is determined.

[0120] S403, determine whether the ratio is less than the preset threshold. If yes, execute S404; otherwise, execute S405.

[0121] Specifically, in this embodiment, the ratio of the sum of the first singular values ​​to the sum of the second singular values ​​is compared with a preset threshold to obtain a comparison result. It is then determined whether the ratio is less than the preset threshold. If so, S404 is executed; otherwise, S405 is executed.

[0122] S404: Select the next candidate singular value sorted after the current singular value as the current singular value, and return to perform the operation of adding the current singular value to the singular value set.

[0123] Specifically, if the ratio is less than a preset threshold, then based on the candidate singular value sorting result, the next candidate singular value after the current singular value is taken as the next current singular value, and the operation of S401 is returned.

[0124] S405, the number of candidate singular values ​​in the singular value set is used as the target reduction basis number.

[0125] Specifically, if the ratio is greater than a preset threshold, the number of candidate singular values ​​in the singular value set is determined, and the number of candidate singular values ​​in the singular value set is used as the number of target reduction bases.

[0126] In the above embodiments, by setting a set of singular values, the process of determining the target singular value is made more comprehensive and richer.

[0127] To facilitate understanding by those skilled in the art, the physical field monitoring method for the above-mentioned nuclear reactor is described in detail, as shown in Figure 5. This method may include:

[0128] S501, acquire simulation distribution data of at least two physical fields corresponding to nuclear reactors under various operating conditions.

[0129] S502, according to the physical field splicing rules, splices the simulation distribution data of at least two physical fields corresponding to various operating conditions to obtain the simulation monitoring dataset of nuclear reactors under various operating conditions.

[0130] Among them, the physical field splicing rule and the physical field splitting rule are a set of inverse rules.

[0131] S503 performs order reduction calculations on simulation monitoring datasets of nuclear reactors under various operating conditions to obtain candidate sub-reduction basis and candidate singular values.

[0132] Among them, the number of candidate sub-reduction bases and candidate singular values ​​are the same and correspond one-to-one.

[0133] S504. Sort the candidate singular values ​​according to their size.

[0134] S505: Take the largest candidate singular value as the current singular value and add the current singular value to the singular value set.

[0135] S506, determine the ratio of the first singular value summation result to the second singular value summation result.

[0136] The first singular value summation result is the sum of all candidate singular values ​​located in the singular value set; the second singular value summation result is the sum of all candidate singular values.

[0137] S507, determine whether the ratio is less than the preset threshold. If yes, execute S508; otherwise, execute S509.

[0138] S508, select the next candidate singular value after the current singular value as the current singular value, and return to execute S505.

[0139] S509 uses the number of candidate singular values ​​in the singular value set as the target reduction basis number.

[0140] S510: Based on the number of target reduction bases and the sorting results of candidate singular values, select the target reduction base from the candidate sub-reduction bases.

[0141] S511, acquire real-time response data collected by at least two types of nuclear reactor detectors.

[0142] The nuclear reactor detector is located inside and / or outside the nuclear reactor.

[0143] S512, based on response data splicing rules, splices real-time response data collected from at least two types of nuclear reactor detectors to obtain detector measurement values.

[0144] S513, normalize the detector measurements and input the normalized detector measurements into the nonlinear fitting model to obtain the reduced basis fitting coefficients.

[0145] S514, fuse the target reduction basis and the target sub-reduction basis and sub-fitting coefficients that have corresponding relationships in the target reduction basis and the reduction basis fitting coefficients to obtain at least one set of sub-data sets.

[0146] The number of target sub-reduction bases contained in the target reduction basis is the same as the number of sub-fit coefficients contained in the reduction basis fitting coefficients, and they correspond one-to-one.

[0147] S515 combines the various subset datasets to obtain the real-time monitoring dataset for the nuclear reactor.

[0148] S516, Based on the physical field splitting rules corresponding to the response data splicing rules, determine the real-time monitoring data of at least two physical fields of the nuclear reactor from the real-time monitoring dataset.

[0149] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0150] Based on the same inventive concept, this application also provides a physical field monitoring device for a nuclear reactor to implement the physical field monitoring method for a nuclear reactor as described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the physical field monitoring device for a nuclear reactor provided below can be found in the limitations of the physical field monitoring method for a nuclear reactor described above, and will not be repeated here.

[0151] In one embodiment, as shown in FIG6, a physical field monitoring device 1 for a nuclear reactor is provided, comprising: a first splicing module 10, a coefficient determination module 11, a dataset determination module 12, and a monitoring data determination module 13, wherein:

[0152] The first splicing module 10 splices real-time response data collected from at least two types of nuclear reactor detectors based on response data splicing rules to obtain detector measurement values.

[0153] The nuclear reactor detector is located inside and / or outside the nuclear reactor.

[0154] The coefficient determination module 11 is used to determine the reduced basis fitting coefficients based on the detector measurements.

[0155] The dataset determination module 12 is used to determine the real-time monitoring dataset of the nuclear reactor based on the target reduction basis and the reduction basis fitting coefficient.

[0156] The monitoring data determination module 13 is used to determine the real-time monitoring data of at least two physical fields of the nuclear reactor from the real-time monitoring dataset according to the physical field splitting rules corresponding to the response data splicing rules.

[0157] In one embodiment, the coefficient determination module 11 is specifically used to determine the reduced basis fitting coefficients based on detector measurements using a nonlinear fitting model.

[0158] In one embodiment, the coefficient determination module 11 is further configured to normalize the detector measurement values ​​and input the normalized detector measurement values ​​into the nonlinear fitting model to obtain the reduced basis fitting coefficients.

[0159] In one embodiment, the number of target sub-reduction bases included in the target reduction basis is the same as the number of sub-fit coefficients included in the reduction basis fitting coefficients, and they correspond one-to-one; accordingly, as shown in FIG7, the dataset determination module 12 includes a fusion unit 120 and a combination unit 121. Wherein:

[0160] The fusion unit 120 is used to fuse the target sub-reduction basis and sub-fit coefficients that have corresponding relationships to obtain at least one set of sub-datasets.

[0161] Combination unit 121 is used to combine the various subset datasets to obtain the real-time monitoring dataset of the nuclear reactor.

[0162] In one embodiment, as shown in FIG8, the physical field monitoring device 1 for the nuclear reactor shown in FIG6 further includes: an acquisition module 14, a second splicing module 15, a reduction module 16, and a screening module 17. Wherein:

[0163] The acquisition module 14 is used to acquire simulation distribution data of at least two physical fields corresponding to the nuclear reactor under various operating conditions.

[0164] The second splicing module 15 is used to splice the simulation distribution data of at least two physical fields corresponding to various operating conditions according to the physical field splicing rules, so as to obtain the simulation monitoring dataset of the nuclear reactor under various operating conditions.

[0165] Among them, the physical field splicing rule and the physical field splitting rule are a set of inverse rules.

[0166] The order reduction module 16 is used to perform order reduction calculations on the simulation monitoring dataset of nuclear reactors under various operating conditions to obtain candidate sub-reduction basis and candidate singular values.

[0167] Among them, the number of candidate sub-reduction bases and candidate singular values ​​are the same and correspond one-to-one.

[0168] The filtering module 17 is used to filter the target reduction basis from the candidate sub-reduction basis based on the candidate sub-reduction basis and the candidate singular value.

[0169] In one embodiment, as shown in FIG9, the filtering module 17 includes a sorting unit 170, a determining unit 171, and a filtering unit 172. Wherein:

[0170] The sorting unit 170 is used to sort the candidate singular values ​​according to their size.

[0171] The determining unit 171 is used to determine the target reduction base number based on the sorted candidate singular values ​​and a preset threshold.

[0172] The filtering unit 172 is used to filter the target reduction basis from the candidate sub-reduction basis according to the sorting result of the number of target reduction basis and the candidate singular values.

[0173] In one embodiment, the determining unit 171 includes a first determining subunit, a second determining subunit, a judging subunit, a re-execution subunit, and a third determining subunit. Wherein:

[0174] The first determining sub-unit is used to select the largest candidate singular value as the current singular value and add the current singular value to the singular value set.

[0175] The second determining subunit is used to determine the ratio of the first singular value summation result to the second singular value summation result. The first singular value summation result is the sum of all candidate singular values ​​located in the singular value set; the second singular value summation result is the sum of all candidate singular values.

[0176] The judgment sub-unit is used to determine whether the ratio is less than a preset threshold.

[0177] The sub-unit is re-executed to take the next candidate singular value sorted after the current singular value as the current singular value, and returns to the operation of adding the current singular value to the singular value set performed by the first determined sub-unit.

[0178] The third determining subunit is used to take the number of candidate singular values ​​in the singular value set as the target reduction basis number.

[0179] The modules in the aforementioned physical field monitoring device for nuclear reactors can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0180] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram is shown in Figure 10. The computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for monitoring the physical field of a nuclear reactor. The display unit of the computer device is used to form a visually visible image and may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0181] Those skilled in the art will understand that the structure shown in Figure 10 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or may combine certain components, or may have different component arrangements.

[0182] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0183] Based on the response data splicing rules, real-time response data collected by at least two types of nuclear reactor detectors are spliced ​​together to obtain detector measurements; wherein, the nuclear reactor detectors are configured inside and / or outside the nuclear reactor.

[0184] Determine the reduced basis fitting coefficients based on the detector measurements;

[0185] Based on the target reduction basis and the reduction basis fitting coefficient, the real-time monitoring dataset of the nuclear reactor is determined;

[0186] Based on the physical field splitting rules corresponding to the response data splicing rules, determine the real-time monitoring data of at least two physical fields of the nuclear reactor from the real-time monitoring dataset.

[0187] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0188] Based on the response data splicing rules, real-time response data collected by at least two types of nuclear reactor detectors are spliced ​​together to obtain detector measurements; wherein, the nuclear reactor detectors are configured inside and / or outside the nuclear reactor.

[0189] Determine the reduced basis fitting coefficients based on the detector measurements;

[0190] Based on the target reduction basis and the reduction basis fitting coefficient, the real-time monitoring dataset of the nuclear reactor is determined;

[0191] Based on the physical field splitting rules corresponding to the response data splicing rules, determine the real-time monitoring data of at least two physical fields of the nuclear reactor from the real-time monitoring dataset.

[0192] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0193] Based on the response data splicing rules, real-time response data collected by at least two types of nuclear reactor detectors are spliced ​​together to obtain detector measurements; wherein, the nuclear reactor detectors are configured inside and / or outside the nuclear reactor.

[0194] Determine the reduced basis fitting coefficients based on the detector measurements;

[0195] Based on the target reduction basis and the reduction basis fitting coefficient, the real-time monitoring dataset of the nuclear reactor is determined;

[0196] Based on the physical field splitting rules corresponding to the response data splicing rules, determine the real-time monitoring data of at least two physical fields of the nuclear reactor from the real-time monitoring dataset.

[0197] It should be noted that the user information (including but not limited to information collected by the detector and simulation information) and data (including but not limited to response data and real-time monitoring data) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0198] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0199] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0200] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for monitoring the physical field of a nuclear reactor, characterized in that, The method includes: stitching real-time response data collected by at least two types of nuclear reactor detectors based on response data stitching rules to obtain detector measurement values; wherein the nuclear reactor detectors are configured inside and / or outside the nuclear reactor; determining reduction basis fitting coefficients based on the detector measurement values; determining the real-time monitoring dataset of the nuclear reactor based on the target reduction basis and the reduction basis fitting coefficients; wherein the number of target sub-reduction basis included in the target reduction basis is the same as the number of sub-fitting coefficients included in the reduction basis fitting coefficients and they correspond one-to-one; correspondingly, determining the real-time monitoring dataset of the nuclear reactor based on the target reduction basis and the reduction basis fitting coefficients includes: multiplying the corresponding target sub-reduction basis and sub-fitting coefficients to obtain at least one set of subset datasets; adding the subset datasets to obtain the real-time monitoring dataset of the nuclear reactor; wherein... The method for determining the target reduction basis includes: acquiring simulation distribution data of at least two physical fields corresponding to the nuclear reactor under various operating conditions; splicing the simulation distribution data of at least two physical fields corresponding to various operating conditions according to the physical field splicing rules to obtain simulation monitoring datasets of the nuclear reactor under various operating conditions; wherein the physical field splicing rules and the physical field splitting rules are a set of inverse rules; performing order reduction calculations on the simulation monitoring datasets of the nuclear reactor under various operating conditions to obtain candidate sub-reduction basis and candidate singular values; wherein the number of candidate sub-reduction basis and candidate singular values ​​is the same and they correspond one-to-one; selecting the target reduction basis from the candidate sub-reduction basis according to the candidate sub-reduction basis and candidate singular values; and determining the real-time monitoring data of at least two physical fields of the nuclear reactor from the real-time monitoring dataset according to the physical field splitting rules corresponding to the response data splicing rules.

2. The method according to claim 1, characterized in that, The step of determining the reduced basis fitting coefficient based on the detector measurements includes: determining the reduced basis fitting coefficient based on the detector measurements using a nonlinear fitting model.

3. The method according to claim 2, characterized in that, The step of determining the reduced basis fitting coefficients based on the detector measurements using a nonlinear fitting model includes: normalizing the detector measurements and inputting the normalized detector measurements into the nonlinear fitting model to obtain the reduced basis fitting coefficients.

4. The method according to claim 1, characterized in that, The step of selecting a target reduction basis from the candidate sub-reduction basis based on the candidate sub-reduction basis and the candidate singular value includes: sorting the candidate singular values ​​according to their size; determining the number of target reduction basis based on the sorted candidate singular values ​​and a preset threshold; and selecting a target reduction basis from the candidate sub-reduction basis based on the number of target reduction basis and the sorting result of the candidate singular values.

5. The method according to claim 4, characterized in that, Based on the sorted candidate singular values ​​and a preset threshold, the target number of reduction bases is determined, including: taking the largest candidate singular value as the current singular value and adding the current singular value to the singular value set; determining the ratio of a first singular value summation result to a second singular value summation result; wherein, the first singular value summation result is the sum of all candidate singular values ​​located in the singular value set; the second singular value summation result is the sum of all candidate singular values; determining whether the ratio is less than a preset threshold; if so, taking the next candidate singular value sorted after the current singular value as the current singular value, and returning to execute the operation of adding the current singular value to the singular value set; if not, taking the number of candidate singular values ​​in the singular value set as the target number of reduction bases.

6. The method according to any one of claims 1-5, characterized in that, The at least two physical fields include a temperature field, a flow field, and a pressure field.

7. A physical field monitoring device for a nuclear reactor, characterized in that, The device includes: a first splicing module, which splices real-time response data collected by at least two types of nuclear reactor detectors based on response data splicing rules to obtain detector measurement values; wherein the nuclear reactor detectors are configured inside and / or outside the nuclear reactor; a coefficient determination module, used to determine reduction basis fitting coefficients based on the detector measurement values; and a dataset determination module, used to determine the real-time monitoring dataset of the nuclear reactor based on the target reduction basis and the reduction basis fitting coefficients; wherein the number of target sub-reduction basis included in the target reduction basis is the same as the number of sub-fitting coefficients included in the reduction basis fitting coefficients and they correspond one-to-one; correspondingly, determining the real-time monitoring dataset of the nuclear reactor based on the target reduction basis and the reduction basis fitting coefficients includes: multiplying the corresponding target sub-reduction basis and sub-fitting coefficients to obtain at least one set of subset datasets; and adding the subset datasets to obtain the real-time monitoring dataset of the nuclear reactor. The dataset includes a target reduction basis determined by: acquiring simulation distribution data of at least two physical fields corresponding to the nuclear reactor under various operating conditions; splicing the simulation distribution data of at least two physical fields corresponding to various operating conditions according to physical field splicing rules to obtain simulation monitoring datasets of the nuclear reactor under various operating conditions; wherein the physical field splicing rules and the physical field splitting rules are a set of inverse rules; performing order reduction calculations on the simulation monitoring datasets of the nuclear reactor under various operating conditions to obtain candidate sub-reduction basis and candidate singular values; wherein the number of candidate sub-reduction basis and candidate singular values ​​is the same and they correspond one-to-one; selecting a target reduction basis from the candidate sub-reduction basis according to the candidate sub-reduction basis and candidate singular values; and a monitoring data determination module, used to determine the real-time monitoring data of at least two physical fields of the nuclear reactor from the real-time monitoring dataset according to the physical field splitting rules corresponding to the response data splicing rules.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images