Module division method and system for small reactor and electronic equipment

Abstract

The invention relates to a module division method and system for a small reactor and electronic equipment, and the method comprises the following steps: determining correlation information of system components of an SMR system according to nuclear power design information, and constructing a comprehensive correlation matrix of the system components of the SMR system according to the correlation information of the system components; performing hierarchical module division according to the comprehensive correlation matrix of the system components of the SMR system to obtain a hierarchical clustering result of the system components of the SMR system; determining an objective function and constraint conditions of SMR system module division; and encoding all modules in the hierarchical clustering result of the system components of the SMR system, and optimizing module division of the SMR system to obtain a target module division scheme. According to the invention, the design efficiency, design quality and applicability of module division can be improved, the reasonability of module division can be optimized, the difficulty of system upgrading and maintenance is reduced, and the expandability and flexibility of the system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of nuclear power reactor system design, and more specifically, to a module division method, system and electronic equipment for a small reactor. Background Art

[0002] Nuclear power is a cost-effective power generation technology that can provide clean energy comparable to other renewable energy technologies. Small Modular Reactor (SMR), as a new generation of nuclear energy technology, usually refers to nuclear reactors with an electric power of less than 300Mwe. With its high flexibility, easy deployment and strong adaptability, it has become an important direction for the future development of nuclear energy. Since the design of SMR needs to adapt to limited space, and its design and construction involve multiple complex subsystems and components, the use of efficient and accurate module division design methods is crucial to improving the overall efficiency and reliability of the system.

[0003] The traditional module division method mainly relies on the experience of designers, which is highly subjective and uncertain. At the same time, when dealing with complex systems, it is easy to cause problems such as insufficient module division and high module coupling, which increases the difficulty of system upgrade and maintenance and reduces the scalability and flexibility of the system. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a module division method, system and electronic equipment for a small reactor in view of the problems existing in the prior art.

[0005] The technical solution adopted by the present invention to solve the technical problem is: constructing a module division method for a small reactor, comprising the following steps:

[0006] Determining correlation information of system components of the SMR system according to the nuclear power design information, and constructing a comprehensive correlation matrix of the system components of the SMR system according to the correlation information of the system components;

[0007] Performing hierarchical module division according to a comprehensive correlation matrix of system components of the SMR system to obtain hierarchical clustering results of system components of the SMR system;

[0008] Determine the objective function and constraints of the SMR system module partitioning;

[0009] All modules in the hierarchical clustering results of the system components of the SMR system are encoded, and the module division of the SMR system is optimized to obtain a target module division scheme.

[0010] In the module division method of the small reactor described in the present invention, the system components include: various equipment and components of the reactor and its auxiliary system; the nuclear power design information includes: nuclear power design specifications and design criteria of the SMR system;

[0011] The determining of the correlation information of the system components of the SMR system according to the nuclear power design information includes:

[0012] Based on the nuclear power design specifications and the design criteria of the SMR system, classification and summary are performed to obtain correlation information of the system components; the correlation information of the system components includes: functional correlation between system components, connection correlation between system components and spatial correlation between system components.

[0013] In the module partitioning method of the small reactor of the present invention, constructing a comprehensive correlation matrix of the system components of the SMR system according to the correlation information of the system components includes:

[0014] Acquire the functional correlation of the system components, the connection correlation of the system components and the spatial correlation between the system components;

[0015] Based on the functional correlation of the system components, the connection correlation of the system components and the spatial correlation between the system components, a comprehensive correlation matrix of the system components is obtained.

[0016] In the module division method of the small reactor of the present invention, the functional correlation between the system components includes: a first function-related evaluation index, a second function-related evaluation index, a third function-related evaluation index and a fourth function-related evaluation index;

[0017] The first function-related evaluation index is: the system combination works together to complete the same sub-function, and the system components are indispensable; the correlation value of the first function-related evaluation index is 1;

[0018] The second function-related evaluation index is: strong function auxiliary relationship; the correlation value of the second function-related evaluation index is 0.5 to 0.9;

[0019] The third function-related evaluation index is: weak function auxiliary relationship; the correlation value of the third function-related evaluation index is 0.1 to 0.4;

[0020] The fourth function-related evaluation indicator is: no functional relationship; the correlation value of the fourth function-related evaluation indicator is 0.

[0021] In the module partitioning method of a small reactor of the present invention, the connection correlation between the system components includes: a first connection-related evaluation index and a second connection-related evaluation index;

[0022] The first connection-related evaluation indicator is: direct physical connection; the correlation value of the first connection-related evaluation indicator is 1;

[0023] The second connection-related evaluation indicator is: no direct physical connection; the correlation value of the second connection-related evaluation indicator is: 0.

[0024] In the module division method of a small reactor of the present invention, the spatial correlation between the system components includes: a first spatial correlation evaluation index and a second spatial correlation evaluation index;

[0025] The first spatial correlation evaluation index is: located in the same spatial area; the correlation value of the first spatial correlation evaluation index is 1;

[0026] The second space-related evaluation index is: located in different cabins or space areas; the correlation value of the second space-related evaluation index is 0.

[0027] In the module partitioning method of the small reactor of the present invention, performing hierarchical module partitioning according to the comprehensive correlation matrix of the system components of the SMR system to obtain the hierarchical clustering results of the system components of the SMR system includes:

[0028] According to the comprehensive correlation matrix of the system components, a fuzzy hierarchical clustering method is used to divide the system components of the SMR system into hierarchical modules to obtain hierarchical clustering results of the system components of the SMR system.

[0029] In the module division method of the small reactor of the present invention, the system components of the SMR system are divided into hierarchical modules by using a fuzzy hierarchical clustering method according to the comprehensive correlation matrix of the system components, and the hierarchical clustering results of the system components of the SMR system are obtained, which includes:

[0030] Based on the comprehensive correlation matrix of the system components, calculating a distance matrix between the components;

[0031] The fuzzy hierarchical clustering method is used to perform hierarchical clustering and obtain the hierarchical clustering tree of system components;

[0032] Clustering results at different levels are combined using a non-uniform granularity clustering function to obtain hierarchical clustering results of the system components.

[0033] In the module partitioning method of the small reactor of the present invention, the hierarchical clustering is performed by using a fuzzy hierarchical clustering method to obtain a hierarchical clustering tree of system components, including:

[0034] Treat each system component as a separate initial cluster;

[0035] In each iteration, the two clusters with the smallest distance are merged to generate a new cluster, and the distance between the new cluster and all other clusters is recalculated. This step is executed repeatedly until all system components are merged into one cluster to generate the hierarchical clustering tree.

[0036] In the module division method of a small reactor of the present invention, the objective function and constraint conditions for determining the module division of the SMR system include:

[0037] Based on the comprehensive correlation matrix and the hierarchical clustering results, determining the comprehensive correlation coefficients between system components, the number of modules, and the number of components in the modules;

[0038] Determining the objective function according to the comprehensive correlation coefficient between the system components, the number of the modules and the number of components in the modules;

[0039] The constraint condition is determined based on a constraint function and an objective function.

[0040] In the module division method of the small reactor described in the present invention, the objective function includes: a coupling evaluation function, a cohesion evaluation function, a module quantity function, a module size restriction evaluation function and a module weight restriction evaluation function;

[0041] Determining the objective function according to the comprehensive correlation coefficient between the system components, the number of the modules, and the number of components in the modules includes:

[0042] Determining the coupling evaluation function according to the comprehensive correlation coefficient between the system components and the number of components in the module;

[0043] Determining the cohesion evaluation function according to the comprehensive correlation coefficient between the system components and the number of modules;

[0044] Obtaining the module quantity function according to the module quantity;

[0045] Determining the module size restriction evaluation function according to the physical size of the module;

[0046] The module weight limit evaluation function is determined according to the total weight of the module and a predetermined upper weight limit.

[0047] In the module partitioning method for a small reactor described in the present invention, the constraints include: minimizing the coupling between modules, maximizing the module cohesion, minimizing the number of modules, component coverage constraints, and module size and weight limit constraints.

[0048] In the module partitioning method of a small reactor of the present invention, encoding all modules in the hierarchical clustering results of the system components of the SMR system, optimizing the module partitioning of the SMR system, and obtaining the target module partitioning scheme comprises:

[0049] All modules in the hierarchical clustering results of the system components of the SMR system are encoded, and a fast non-dominated sorting genetic algorithm is used to optimize the system modularization division to obtain the target module division scheme.

[0050] In the module partitioning method of the small reactor of the present invention, all modules in the hierarchical clustering results of the system components of the SMR system are encoded, and the system modular partitioning is optimized by using a fast non-dominated sorting genetic algorithm, and the target module partitioning scheme is obtained, which includes:

[0051] S4.1: Determine the encoding method;

[0052] S4.2: Encode all modules in the hierarchical clustering result according to the encoding method, and establish a component-module construction matrix;

[0053] S4.3: According to the encoding method and the component-module construction matrix, and under the premise of satisfying constraint conditions, randomly generating an initial population;

[0054] S4.4: performing non-dominated sorting on the initial population to generate different non-dominated hierarchies;

[0055] S4.5: Calculate the crowding degree of individuals in each non-dominated level to obtain the crowding degree of individuals in each non-dominated level;

[0056] S4.6: performing selection, crossover and mutation operations according to the non-dominated level and the crowding degree to generate a new generation of offspring individuals;

[0057] S4.7: Merge the parent and offspring individuals to form a mixed population, and recalculate the non-dominated sorting and crowding degree of the mixed population to construct the next generation population;

[0058] S4.8: Determine the target solution of the previous generation;

[0059] S4.9: Repeat steps S4.4 to S4.8 until the iteration termination condition is met, and output the target module partitioning scheme.

[0060] In the module division method of a small reactor described in the present invention, the coding method includes: a module coding method and a scheme coding method;

[0061] The module encoding method includes: each module is represented by a Boolean vector; each bit of the Boolean vector represents whether a certain component exists;

[0062] The scheme encoding method includes: using a Boolean vector to represent the entire module division scheme; each bit of the Boolean vector represents whether a certain module exists or not.

[0063] The module division method of the small reactor of the present invention further includes:

[0064] Conduct feasibility analysis and verification based on the target module division scheme;

[0065] Determine whether the target module partitioning scheme is passed according to the analysis and verification results;

[0066] If yes, then determine the target module partitioning scheme;

[0067] If not, reselect to determine the target module partitioning scheme.

[0068] The present invention also provides a module division system for a small reactor, comprising:

[0069] A comprehensive matrix construction unit, used to determine correlation information of system components of the SMR system according to nuclear power design information, and to construct a comprehensive correlation matrix of system components of the SMR system according to the correlation information of the system components;

[0070] A module division unit, used for performing hierarchical module division according to a comprehensive correlation matrix of system components of the SMR system to obtain hierarchical clustering results of system components of the SMR system;

[0071] A function condition determination unit, used to determine the objective function and constraint conditions of the SMR system module division;

[0072] The target scheme determination unit is used to encode all modules in the hierarchical clustering results of the system components of the SMR system, and optimize the module division of the SMR system to obtain a target module division scheme.

[0073] The module division system of the small reactor of the present invention further includes:

[0074] Target solution verification unit, used to:

[0075] Conduct feasibility analysis and verification based on the target module division scheme;

[0076] Determine whether the target module partitioning scheme is passed according to the analysis and verification results;

[0077] If yes, then determine the target module partitioning scheme;

[0078] If not, reselect to determine the target module partitioning scheme.

[0079] The present invention also provides a storage medium storing a computer program, wherein the computer program is suitable for being loaded by a processor to execute the steps of the module division method of a small reactor as described above.

[0080] The present invention also provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the steps of the module division method of the small reactor as described above by calling the computer program stored in the memory.

[0081] The module division method, system and electronic device for implementing the small reactor of the present invention have the following beneficial effects: including the following steps: determining the correlation information of the system components of the SMR system according to the nuclear power design information, and constructing the comprehensive correlation matrix of the system components of the SMR system according to the correlation information of the system components; performing hierarchical module division according to the comprehensive correlation matrix of the system components of the SMR system to obtain the hierarchical clustering results of the system components of the SMR system; determining the objective function and constraint conditions of the module division of the SMR system; encoding all modules in the hierarchical clustering results of the system components of the SMR system, and optimizing the module division of the SMR system to obtain the target module division scheme. The present invention can improve the design efficiency, design quality and applicability of module division, and optimize the rationality of module division, thereby reducing the difficulty of system upgrade and maintenance, and improving the scalability and flexibility of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0083] Figure 1 It is a schematic flow chart of the module division method of a small reactor provided by the present invention;

[0084] Figure 2 It is a detailed flow chart of the module division method of the small reactor provided by the present invention;

[0085] Figure 3 It is a principle block diagram of the module division system of the small reactor provided by the present invention;

[0086] Figure 4 It is a schematic diagram of the optimal system module division provided by the present invention. DETAILED DESCRIPTION

[0087] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0088] In order to solve the problems existing in the prior art, the present invention provides a module division method for a small reactor, which can achieve efficient and accurate module division of the SMR system, reduce the coupling between modules, increase the cohesion of modules, and enhance the maintainability and scalability of the system.

[0089] refer to Figure 1 , Figure 1 A schematic flow chart of a preferred embodiment of a method for dividing modules of a small reactor provided by the present invention.

[0090] Specifically, Figure 1 As shown, the module division method of the small reactor includes the following steps:

[0091] Step S1: Determine correlation information of system components of the SMR system according to nuclear power design information, and construct a comprehensive correlation matrix of system components of the SMR system according to the correlation information of the system components.

[0092] In an embodiment of the present invention, the SMR system is a small nuclear reactor with an electric power of less than 300MWe. Wherein, the system components include: various types of equipment and components of the reactor and its auxiliary systems. Optionally, in an embodiment of the present invention, the nuclear power design information includes: nuclear power design specifications and design criteria of the SMR system. Wherein, the correlation information of the system components of the SMR system determined according to the nuclear power design information includes: classifying and summarizing based on the nuclear power design specifications and the design criteria of the SMR system to obtain the correlation information of the system components. Optionally, the correlation information of the system components includes: functional correlation between system components, connection correlation between system components and spatial correlation between system components.

[0093] Specifically, the functional dependencies between system components can be expressed using R g It reflects the degree of mutual cooperation or dependence between two components in the process of realizing system functions. System components with high functional relevance usually need to work closely together or interact frequently when performing tasks. Optionally, in an embodiment of the present invention, the functional relevance between system components includes: a first functional relevance evaluation index, a second functional relevance evaluation index, a third functional relevance evaluation index, and a fourth functional relevance evaluation index.

[0094] Among them, the first function-related evaluation indicator is: the system combination works together to complete the same sub-function, and the system components are indispensable; the correlation value of the first function-related evaluation indicator is 1. The second function-related evaluation indicator is: strong functional auxiliary relationship; the correlation value of the second function-related evaluation indicator is 0.5-0.9. The third function-related evaluation indicator is: weak functional auxiliary relationship; the correlation value of the third function-related evaluation indicator is 0.1-0.4. The fourth function-related evaluation indicator is: no functional relationship; the correlation value of the fourth function-related evaluation indicator is 0.

[0095] The connection dependencies between system components are expressed in R l , which reflects the degree of direct association of components in physical structure. Optionally, in an embodiment of the present invention, the connection correlation between the system components includes: a first connection-related evaluation index and a second connection-related evaluation index. Among them, the first connection-related evaluation index is: direct physical connection; the correlation value of the first connection-related evaluation index is 1; the second connection-related evaluation index is: no direct physical connection; the correlation value of the second connection-related evaluation index is: 0.

[0096] Spatial correlations between system components are calculated using R k It reflects the relative distribution of components at the installation position. Optionally, in an embodiment of the present invention, the spatial correlation between system components includes: a first spatial correlation evaluation index and a second spatial correlation evaluation index. Among them, the first spatial correlation evaluation index is: located in the same spatial area; the correlation value of the first spatial correlation evaluation index is 1; the second spatial correlation evaluation index is: located in different cabins or spatial areas; the correlation value of the second spatial correlation evaluation index is 0.

[0097] In an embodiment of the present invention, the comprehensive correlation matrix of the system components of the SMR system is constructed according to the correlation information of the system components, including: obtaining the functional correlation of the system components, the connection correlation of the system components, and the spatial correlation between the system components; and summarizing based on the functional correlation of the system components, the connection correlation of the system components, and the spatial correlation between the system components to obtain the comprehensive correlation matrix of the system components. Specifically, the comprehensive correlation matrix of the system components can be composed of the functional correlation between the system components, the connection correlation between the system components, and the spatial correlation between the system components, and its specific function expression is as follows:

[0098] R(i,j)=μ g R g (i,j)+μ l R l (i,j)+μ k R k (i,j) (1).

[0099] (1) In the formula, R(i,j) is the comprehensive correlation matrix function, u g ,u l ,u k are the weight coefficients of functional correlation, connection correlation and spatial correlation respectively. At the same time, define the SMR system component set C = {C1,C 2, …,C n}.

[0100] Step S2: performing hierarchical module division according to the comprehensive correlation matrix of the system components of the SMR system to obtain hierarchical clustering results of the system components of the SMR system.

[0101] In an embodiment of the present invention, hierarchical module division is performed according to the comprehensive correlation matrix of the system components of the SMR system to obtain the hierarchical clustering results of the system components of the SMR system, which includes: hierarchical module division is performed on the system components of the SMR system according to the comprehensive correlation matrix of the system components using a fuzzy hierarchical clustering method to obtain the hierarchical clustering results of the system components of the SMR system.

[0102] The fuzzy hierarchical method is: that is, according to the comprehensive correlation matrix of the system components, the fuzzy hierarchical clustering method is used to divide the system components of the SMR system into hierarchical modules, and the hierarchical clustering results of the system components of the SMR system are obtained, including: based on the comprehensive correlation matrix of the system components, the distance matrix between the components is calculated; the fuzzy hierarchical clustering method is used to perform hierarchical clustering to obtain the hierarchical clustering tree of the system components; the clustering results of different levels are combined using a non-uniform granularity clustering function to obtain the hierarchical clustering results of the system components. Specifically, the distance matrix between the system components is first calculated, and then the fuzzy hierarchical clustering method is used to perform hierarchical clustering to construct a hierarchical clustering tree of the system components. Finally, the clustering results of different levels are combined using a non-uniform granularity clustering function, and the module set including all modules is counted. By combining the clustering results at different levels, we can better understand the relationship between each component, that is, we can achieve comprehensive coverage (ensuring that all components are reasonably classified into a module without omission), flexible adjustment (some components are closely related and suitable to be put together; some are not so closely related and suitable to be separated. Different levels of clustering help us flexibly adjust the size and content of each module), and more reasonable module division (combining the information of major and minor categories to ensure that each module can meet the overall functional requirements and deal with specific requirements in details).

[0103] Specifically, after classifying all components (i.e., classifying all components into different modules), module statistics need to be performed. Through module statistics, the integrity of module division can be ensured (confirming that all components are included in a certain module without missing any part), module division can be optimized (by statistically analyzing these modules, we can consider which components within a module have a close relationship (high cohesion) and which modules have few dependencies (low coupling). In this way, the module division can be adjusted so that each module collaborates well internally and is highly independent between modules, facilitating maintenance and upgrading), and preparations can be made for further optimization (after statistically analyzing the module set, we will use the genetic algorithm (NSGA-II) to further optimize these module divisions. This algorithm will find the optimal module division scheme according to the goals we set (such as reducing coupling, increasing cohesion, reducing the number of modules, etc.)).

[0104] Among them, the distance matrix D between system components is as follows:

[0105] D = [1 - r ij n×n = [d ij n×n (2).

[0106] (In formula (2), the comprehensive correlation matrix R = [r ij n×n , d ij represents the distance between the set component C i and the component C j . The smaller the distance, the higher the correlation between the two components, and the more likely they are to be grouped into the same category during the clustering process.)

[0107] In the embodiments of the present invention, the average linkage method can be used to calculate the distance between system components or modules. Specifically, see formula (3).

[0108]

[0109] (In formula (3), |M i | and |M j | respectively represent the number of components included in modules M i and M j . Cm (module m): represents the mth module. Cn (module n): represents the nth module. d mn represents the distance between module m and module n. d mn is used to measure the similarity or correlation between two modules. In hierarchical clustering, the smaller the distance, the higher the similarity between the two modules, and the more likely they are to be merged into a larger module.)

[0110] ​​​Formula (3) uses the Average Linkage Method to calculate the distance between modules. The specific steps are as follows:

[0111] 1. Initial stage: Each component is an independent module, and there are multiple single component modules at the beginning.

[0112] 2. Calculate the distance between modules: Use the mean link method to calculate the distance d between any two modules Cm and Cn mn The calculation formula of the mean link method is usually: Where |Cm| and |Cn| are the number of components contained in modules Cm and Cn respectively, and d(i,j) is the distance between components i and j.

[0113] 3. Merge modules: Find the two modules Cm and Cn with the smallest distance dmn, merge them into a new module, update the module set, and recalculate the distance between the new module and other modules.

[0114] 4. Repeat iterations: Continue merging modules until the stopping condition is met (for example, all components are merged into one module, or a predetermined number of modules is reached).

[0115] This method can capture multi-level correlations: by calculating the distance between different modules, the correlations between components at different levels can be effectively captured. This helps to divide modules at different granularities, ensuring that the modules can cover both overall functions and specific needs in details. Optimize module division: by continuously merging modules with the smallest distance, the cohesion of the modules (the closeness of the components within the modules) and the coupling between modules (the degree of dependence between modules) can be gradually optimized, thereby improving the overall performance and maintainability of the system. Provide a basis for subsequent optimization: Count the module sets that contain all modules to ensure that all components are reasonably divided into a module. This provides a comprehensive module division basis for further optimization using genetic algorithms (such as NSGA-II).

[0116] In an embodiment of the present invention, the fuzzy hierarchical clustering method is used to perform hierarchical clustering to obtain a hierarchical clustering tree of system components, including: treating each system component as an independent initial cluster; merging the two clusters with the smallest distance to generate a new cluster in each iteration, recalculating the distance between the new cluster and all other clusters, and repeating this step until all system components are merged into one cluster to generate the hierarchical clustering tree.

[0117] Step S3: Determine the objective function and constraints of the SMR system module division.

[0118] In the embodiments of the present invention, the determination of the objective function and constraints for the SMR system module division includes: based on the comprehensive correlation matrix and the hierarchical clustering result, determining the comprehensive correlation coefficient between system components, the number of modules, and the number of components in the modules; according to the comprehensive correlation coefficient between system components, the number of modules, and the number of components in the modules, determining the objective function; and determining the constraints based on the constraint function and the objective function. Among them, the objective function includes: a coupling degree evaluation function, a cohesion degree evaluation function, a module number function, a module size limit evaluation function, and a module weight limit evaluation function.

[0119] In the embodiments of the present invention, the determination of the objective function according to the comprehensive correlation coefficient between system components, the number of modules, and the number of components in the modules includes: determining the coupling degree evaluation function according to the comprehensive correlation coefficient between system components and the number of components in the modules; determining the cohesion degree evaluation function according to the comprehensive correlation coefficient between system components and the number of modules; obtaining the module number function according to the number of modules; determining the module size limit evaluation function according to the physical size of the module; and determining the module weight limit evaluation function according to the total weight of the module and a predetermined weight upper limit.

[0120] In the embodiments of the present invention, the constraints include: minimizing the coupling degree between modules, maximizing the cohesion degree within modules, minimizing the number of modules, a component coverage constraint, and a module size and weight limit constraint.

[0121] Specifically, in step S3, the objective function for optimizing the system module division mainly considers three aspects: (1) the degree of tight connection between modules, that is, the coupling degree; (2) the degree of tight connection within modules, that is, the cohesion degree; (3) improving the overall construction of the system by optimizing the number of modules, that is, the number of modules. Module size limit: Ensure that the physical size of each module does not exceed the predetermined design specifications and space limitations, specifically including geometric size parameters such as the length, width, and height of the module; Module weight limit: Ensure that the total weight of each module does not exceed the design load-bearing capacity, considering the requirements of transportation, installation, and structural support.

[0122] Among them, the coupling degree evaluation function is represented by F1, and its specific expression is:

[0123]

[0124] (4) In the formula, r kl is the comprehensive correlation coefficient between component C k and C l , |M i | and |M j | respectively represent modules M i and Mj The number of components contained in the .

[0125] The cohesion evaluation function can be expressed by F2, and its expression is:

[0126]

[0127] (5) In the formula, r jk For component C j With C k The comprehensive correlation coefficient of |X| is the number of modules.

[0128] The module quantity function can be expressed by F3, and its expression is:

[0129] minF3(X)=|X| (6).

[0130] (6)In the formula, |X| is the number of modules.

[0131] The module size limitation evaluation function F4 is:

[0132]

[0133] Among them, L i ,W i ,H i Respectively represent modules M i Length, width and height; L max ,W max ,H max The predetermined length, width and height limits are respectively.

[0134] The module weight limit evaluation function F5 is:

[0135]

[0136] Where W i Indicates module M i Total weight; W max The maximum weight limit is set.

[0137] Constraints are constraints established to ensure that all components in the system are divided into modules. Constraints are used to ensure that all system components in the system are divided into corresponding modules. The constraint function can be expressed as:

[0138]

[0139] (9) In the formula, C represents the set of all components in the system. X represents the set of modules. Respectively represent empty sets. That is, in the intersection formula, ∩Mi∈X, This means that no component belongs to more than one module at the same time.

[0140] Formula (9) can ensure the integrity and uniqueness of module division. Specifically: 1. Integrity, Explanation: The union of all modules Mi is equal to the entire component set C, ensuring that every component in the system is assigned to a module without missing any component. 2. Uniqueness: Explanation: The intersection of all modules Mi is an empty set, which means that no component is assigned to multiple modules, ensuring that each component belongs to only one module and avoiding the same component being shared by multiple modules, thereby simplifying the dependencies between modules and reducing the complexity of the system.

[0141] The function constraint can be used to achieve the following: 1. Improve the rationality of module division: ensure that each component has a clear ownership, avoid the increase of coupling between modules due to component dispersion or repeated allocation, and affect the maintainability and scalability of the system. 2. Optimize the optimization process of the genetic algorithm: when using a genetic algorithm (such as NSGA-II) for module division optimization, formula (9) as a constraint condition can guide the algorithm to only consider module division schemes that meet the integrity and uniqueness during the search process, thereby improving the quality and practicality of the optimization results. 3. Enhance the feasibility and reliability of system design: through strict component allocation rules, ensure the feasibility of the module division scheme in practical applications, reduce errors and inconsistencies in the design process, and improve the overall reliability of the system design.

[0142] Step S4: Encode all modules in the hierarchical clustering results of the system components of the SMR system, and optimize the module division of the SMR system to obtain a target module division scheme.

[0143] In an embodiment of the present invention, all modules in the hierarchical clustering results of the system components of the SMR system are encoded, and the module division of the SMR system is optimized to obtain a target module division scheme, including: encoding the modules according to the division results of fuzzy hierarchical clustering of the system components of the SMR system, and using a fast non-dominated sorting genetic algorithm (NSGA-II) to optimize the system modular division to obtain a target module division scheme.

[0144] Furthermore, according to the partition results of fuzzy hierarchical clustering of system components of the SMR system, the modules are encoded, and the fast non-dominated sorting genetic algorithm (NSGA-II) is used to optimize the system modular partitioning, and the target module partitioning scheme is obtained, including:

[0145] S4.1: Determine the encoding method.

[0146] In the embodiment of the present invention, the encoding method includes: module encoding method and scheme encoding method.

[0147] The module encoding method includes: each module is represented by a Boolean vector; each bit of the Boolean vector represents whether a certain component exists or not. With vector m i =(c1,c2,…,c j ,…,c n ) indicates that c j =1 means component C j Exists in module M i In, c j =0 represents component C j Does not exist in module M i This method can accurately indicate whether each component exists in each module, allowing the optimization algorithm to make detailed adjustments and divisions to the internal structure of the module. It is suitable for scenarios with complex systems and fine-grained module division requirements.

[0148] The scheme encoding method includes: the entire module partitioning scheme is represented by a Boolean vector; each bit of the Boolean vector represents whether a certain module exists or not. That is, the module partitioning scheme x = (x1, x2, ..., x i ,…,x m ) T , where x i =1 indicates component module M i Exists in scheme X, x i =0 represents module M i Does not exist in scheme X. This method represents the entire module partitioning scheme with a single Boolean vector, which reduces the complexity of coding and is suitable for scenarios where the number of system components is large and the partitioning scheme needs to be generated quickly.

[0149] It should be noted that in actual applications, the encoding method can be determined according to project requirements, and the present invention does not make specific limitations.

[0150] S4.2: Encode all modules in the hierarchical clustering result according to the encoding method, and establish a component-module construction matrix.

[0151] Specifically, according to the fuzzy hierarchical clustering results of the system components of the SMR system and the determined encoding method, the component-module construction matrix Z is established. Based on this, the constraint function (9) can be equivalent to (10), that is:

[0152]

[0153] S4.3: According to the encoding method and the component-module construction matrix, an initial population is randomly generated under the premise of satisfying constraints.

[0154] Specifically, after equivalent construction matrix according to S4.2, an initial population of a certain size can be randomly generated according to the determined encoding method and under the premise of satisfying the constraint conditions. At the same time, the objective function value F1(X), F2(X), F3(X), F4(X), F5(X) of each individual can also be set, and the appropriate number of iterations can be set.

[0155] S4.4: Perform non-dominated sorting on the initial population to generate different non-dominated levels.

[0156] S4.5: Crowding calculation: The crowding degree of individuals in each non-dominated level is calculated to obtain the crowding degree of individuals in each non-dominated level. By calculating the crowding degree of individuals in each non-dominated level, the diversity of the population can be maintained.

[0157] S4.6: Crossover and mutation: According to the non-dominated level and the crowding degree, the next generation parent individuals are selected, and crossover and mutation operations are performed on them to generate a new generation of child individuals.

[0158] S4.7: Generate a new population: merge the parent and child individuals to form a mixed population, and re-perform non-dominated sorting and crowding calculation on the mixed population to construct the next generation population. The next generation population can be formed by selecting the top several excellent individuals from the obtained individuals.

[0159] S4.8: Determine the target solution of the previous generation.

[0160] In the embodiment of the present invention, the target solution of the previous generation can be obtained by using an elite strategy method. The target solution is the optimal solution of the previous generation. This method can ensure that the quality of the solution set is continuously improved.

[0161] S4.9: Repeat steps S4.4 to S4.8 until the iteration termination condition is met, and output the target module partitioning scheme.

[0162] Furthermore, if Figure 1 As shown, the module division method of the small reactor also includes the following steps:

[0163] Step S5: Perform feasibility analysis and verification based on the target module partitioning scheme; determine whether the target module partitioning scheme is passed based on the analysis and verification results; if so, determine the target module partitioning scheme; if not, reselect to determine the target module partitioning scheme.

[0164] refer to Figure 3The present invention also provides a module division system for a small reactor, and the module division system for a small reactor can be applied to the module division method for a small reactor disclosed in an embodiment of the present invention. Specifically, Figure 3 As shown, the module division system of the small reactor includes:

[0165] A comprehensive matrix construction unit 301 is used to determine the correlation information of the system components of the SMR system according to the nuclear power design information, and to construct a comprehensive correlation matrix of the system components of the SMR system according to the correlation information of the system components;

[0166] A module division unit 302 is used to perform hierarchical module division according to a comprehensive correlation matrix of system components of the SMR system to obtain hierarchical clustering results of system components of the SMR system;

[0167] Function condition determination unit 303, used to determine the objective function and constraint conditions of the SMR system module division;

[0168] The target solution determination unit 304 is used to encode all modules in the hierarchical clustering results of the system components of the SMR system, and optimize the module division of the SMR system to obtain a target module division solution.

[0169] Furthermore, if Figure 3 As shown, the module division system of the small reactor also includes:

[0170] The target scheme verification unit 305 is used to: perform feasibility analysis and verification based on the target module partitioning scheme; determine whether the target module partitioning scheme is passed according to the analysis and verification results; if so, determine the target module partitioning scheme; if not, reselect to determine the target module partitioning scheme. The feasibility analysis and verification of the target module partitioning scheme can refer to the current scheme, and the present invention does not make specific limitations.

[0171] The following describes the invention in conjunction with specific embodiments.

[0172] like Figure 2 As shown:

[0173] Step 1: Construct an SMR system component correlation index system based on nuclear power design specifications and SMR system design criteria.

[0174] In this embodiment, a radioactive waste gas system (full name in English may be this Radioactive Waste Gas System, WGS) of a certain SMR is modularly divided. The system is distributed in four different spatial areas, with sizes of approximately 11.5m×4m, 4m×3m, 4m×3m and 9m×4m respectively. According to the design and function of WGS, the main 27 components (see table, marked with names) are selected to form a component set C = {C1, C2, …, C 27}. Functional correlation R is constructed based on the system functions, physical structure connection relationships and installation locations between components. g , connection correlation R l and spatial correlation R k matrix.

[0175] According to the comprehensive correlation matrix formula (1), the weight coefficient u g 、u l and u k The values ​​were set to 0.3, 0.3 and 0.4 respectively, and the comprehensive correlation matrix R of WGS was calculated, see Table 1.

[0176] Step 2: According to the correlation characteristics of WGS system components, a fuzzy hierarchical clustering algorithm is used to perform cluster analysis on WGS system components.

[0177] According to the comprehensive correlation matrix in the first step, the distance matrix D is calculated using formula (2).

[0178] According to the distance matrix D, cluster analysis is performed using formula (3), and the number of clusters is plotted, as shown in Figure 4 Then the clustering results of each level are combined to obtain a module set containing all modules, with a total of 42 modules.

[0179] Step 3: According to the WGS design criteria of the nuclear power design specification, the system module division optimization objective function is determined as formula (4)-(8), and the constraint function is formula (9).

[0180] Step 4: According to the WGS modular partitioning results, NSGA-II is used to optimize the system modular partitioning and solve the optimal modular partitioning solution.

[0181] S4.1. Develop coding methods, including module coding and scheme coding.

[0182] S4.2. Encode the WGS module set according to the encoding method in S4.1 and establish a construction matrix Z 42×27 , see Table (1), and combined with the constraint condition (Formula 9), further establish the matching constraint condition, see Formula (10).

[0183] S4.3. Based on the encoding method and under the premise of satisfying the constraints, the initial population is generated, the population size is set to 30, and the number of iterations is set to 100. At the same time, the objective function values ​​F1(X), F2(X), F3(X), F4(X), and F5(X) of each individual are calculated.

[0184] S4.4, Non-dominated sorting: Perform fast non-dominated sorting on the population to generate different non-dominated levels.

[0185] S4.5. Calculate the crowding degree: Calculate the crowding degree of individuals in each non-dominated level to maintain the diversity of the population.

[0186] S4.6, Crossover and mutation: Based on non-dominated sorting and crowding, select the next generation of parent individuals and perform crossover and mutation operations on them to generate a new generation of child individuals. The crossover probability is set to 0.8. The mutation probability is 0.2.

[0187] S4.7. Generate a new population: merge the parent and offspring individuals to form a mixed population, recalculate the non-dominated sorting and crowding degree of the mixed population, and select the top several excellent individuals to form the next generation population.

[0188] S4.8. Adopt an elite strategy to retain the optimal solution of the previous generation to ensure that the quality of the solution set continues to improve.

[0189] S4.9, repeat steps S4.4 to S4.8 until the iteration termination condition is met. The iteration results are shown in Table 1. The final stable calculation result is:

[0190] F1(X * )=0.021,F2(X * )=26.130,F3(X * )=3,F4(X * )=1,F5(X * )

[0191] =1.

[0192] The module code is: 000000 000000 000000 100000 000011 000000 000111 10. The optimal module division scheme is shown in Table 1 below.

[0193] Table 1 Target module division scheme (optimal module division scheme)

[0194]

[0195]

[0196] Step 5: Based on the optimal module division scheme obtained in the fourth step, the efficiency, rationality and scientificity of the optimal module division scheme are finally verified and determined through 3D modeling and comprehensive analysis of the system operation, physical structure connection and installation location of each component. Figure 4 shown.

[0197] The following effects can be achieved by adopting the present invention:

[0198] 1. Comprehensiveness and systematic improvement: By constructing a comprehensive correlation matrix, the functional correlation, connection correlation and spatial correlation between SMR system components are comprehensively considered, and the degree of correlation between components is fully quantified. This systematic analysis method ensures comprehensive coverage in the module division process and avoids module omissions or duplications caused by incomplete analysis in traditional methods.

[0199] 2. High cohesion and low coupling in module division: The fuzzy hierarchical clustering method is used for hierarchical module division, and the NSGA-II algorithm is combined to optimize the coupling between modules and the cohesion within the modules, thus achieving high cohesion and low coupling in module division. High cohesion enhances the collaborative working ability of the internal components of the module, and low coupling reduces the dependency between modules, thus improving the overall performance and maintainability of the system.

[0200] 3. Efficient implementation of multi-objective optimization: By introducing the NSGA-II algorithm, the inter-module coupling, module cohesion, module quantity, and module size and weight restrictions can be optimized simultaneously under the same optimization framework to obtain a set of globally optimal module partitioning schemes. Fast non-dominated sorting and congestion calculation effectively maintain the diversity of the population and improve the comprehensiveness and applicability of the optimization results.

[0201] 4. Enhanced maintainability and scalability of the system: The optimized module division scheme significantly improves the maintainability and scalability of the system by reducing the coupling between modules and improving the cohesion of modules. In the subsequent maintenance, upgrade and expansion of the system, the modules can be modified and optimized independently more conveniently, reducing the impact on the overall system.

[0202] 5. Improved automation and intelligence: Combining fuzzy hierarchical clustering and genetic algorithms, the module division process is automated, reducing the reliance on the subjective experience of designers. Automated module division improves the objectivity and consistency of the design, shortens the design cycle, and effectively improves the design efficiency.

[0203] The module partitioning method of the small reactor of the present invention has unique technical advantages, and other replacement schemes have certain limitations in technical implementation and cannot achieve the effect of the present invention. Among them, the technical limitations of common replacement methods are specifically as follows: the traditional empirical partitioning method is difficult to ensure the optimality and rationality of the module partitioning, which may lead to problems such as system performance degradation, maintenance difficulties, and cost increase. The module partitioning method of a single optimization algorithm is difficult to handle multi-objective optimization problems when dealing with the module partitioning of complex systems: such algorithms are usually optimized for a single objective or a limited number of objectives, and it is difficult to take into account multiple conflicting optimization objectives such as inter-module coupling, module cohesion, and the number of modules in the same framework; it is easy to fall into a local optimal solution: due to the limited search space and strong dependence on the initial solution, a single algorithm is easy to fall into a local optimal solution and cannot effectively obtain the global optimal module partitioning scheme. Rule-based or heuristic design methods have limitations: the formulation of rules usually relies on experience and existing assumptions, and it is difficult to cover all situations in complex systems, and it is impossible to flexibly respond to changing situations in actual layouts; lack of dynamic adjustment capabilities: such methods lack adaptive mechanisms, and cannot be dynamically adjusted according to actual conditions and changes in optimization goals, making it difficult to achieve global optimal module division for complex systems; unable to integrate multiple objectives and multiple constraints: rule-based methods usually focus on a certain optimization goal, and it is difficult to consider multiple optimization goals and complex constraints at the same time during the design process, resulting in insufficient comprehensiveness and optimization of the module division scheme.

[0204] Obviously, the present invention does not have the above limitations. The present invention establishes a comprehensive correlation matrix to accurately reflect the functions, connections and spatial relationships between components, ensure the rationality of module division, and fully consider the multiple correlations between components; using NSGA-II, it can simultaneously optimize the coupling degree between modules, module cohesion and the number of modules under the same optimization framework, obtain the global optimal module division scheme, and effectively deal with the problem of multi-objective optimization; through the chromosome adjustment mechanism and constraint processing method, it is ensured that the generated scheme meets the various constraints in practical applications, has high feasibility and practicality, and can flexibly deal with complex constraints. Therefore, the present invention has unique technical advantages and innovations in solving the problem of SMR modular division, can meet the needs of practical engineering applications, and other replacement schemes are difficult to achieve the same effect.

[0205] Specifically, the specific coordination operation process between the units in the module division system of the small reactor here can refer to the module division method of the small reactor mentioned above, which will not be repeated here.

[0206] In addition, an electronic device of the present invention includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program to implement a module division method of a small reactor as described in any of the above items. Specifically, according to an embodiment of the present invention, the process described with reference to the flowchart above can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed by an electronic device and executed to perform the above functions defined in the method of the embodiment of the present invention. The electronic device in the present invention can be a terminal such as a notebook, a desktop, a tablet computer, a smart phone, or a server.

[0207] In addition, a storage medium of the present invention stores a computer program thereon, and when the computer program is executed by a processor, the module division method of a small reactor of any one of the above items is implemented. Specifically, it should be noted that the storage medium of the present invention can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it. In the present invention, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0208] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0209] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0210] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0211] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0212] The above embodiments are only for illustrating the technical concept and features of the present invention, and their purpose is to enable people familiar with the technology to understand the content of the present invention and implement it accordingly, and they cannot limit the scope of protection of the present invention. All equivalent changes and modifications made to the scope of the claims of the present invention should fall within the scope of the claims of the present invention.

Claims

1. A method for dividing modules of a small reactor, characterized in that: The following steps are involved: Determining correlation information of system components of the SMR system according to the nuclear power design information, and constructing a comprehensive correlation matrix of the system components of the SMR system according to the correlation information of the system components; Performing hierarchical module division according to a comprehensive correlation matrix of system components of the SMR system to obtain hierarchical clustering results of system components of the SMR system; Determine the objective function and constraints of the SMR system module partitioning; All modules in the hierarchical clustering results of the system components of the SMR system are encoded, and the module division of the SMR system is optimized to obtain a target module division scheme.

2. The module division method of a small reactor according to claim 1, characterized in that: The system components include: various equipment and components of the reactor and its auxiliary systems; the nuclear power design information includes: nuclear power design specifications and design criteria of the SMR system; The determining of the correlation information of the system components of the SMR system according to the nuclear power design information includes: Based on the nuclear power design specifications and the design criteria of the SMR system, classification and summary are performed to obtain correlation information of the system components; the correlation information of the system components includes: functional correlation between system components, connection correlation between system components and spatial correlation between system components.

3. The module division method of a small reactor according to claim 2, characterized in that: The step of constructing a comprehensive correlation matrix of system components of the SMR system according to the correlation information of the system components includes: Acquire the functional correlation of the system components, the connection correlation of the system components and the spatial correlation between the system components; Based on the functional correlation of the system components, the connection correlation of the system components and the spatial correlation between the system components, a comprehensive correlation matrix of the system components is obtained.

4. The module division method of a small reactor according to claim 2, characterized in that: The functional correlations between the system components include: a first functional correlation evaluation index, a second functional correlation evaluation index, a third functional correlation evaluation index, and a fourth functional correlation evaluation index; The first function-related evaluation index is: the system combination works together to complete the same sub-function, and the system components are indispensable; the correlation value of the first function-related evaluation index is 1; The second function-related evaluation index is: strong function auxiliary relationship; the correlation value of the second function-related evaluation index is 0.5 to 0.9; The third function-related evaluation index is: weak function auxiliary relationship; the correlation value of the third function-related evaluation index is 0.1 to 0.4; The fourth function-related evaluation indicator is: no functional relationship; the correlation value of the fourth function-related evaluation indicator is 0.

5. The module division method of a small reactor according to claim 2, characterized in that: The connection correlation between the system components includes: a first connection-related evaluation index and a second connection-related evaluation index; The first connection-related evaluation indicator is: direct physical connection; the correlation value of the first connection-related evaluation indicator is 1; The second connection-related evaluation indicator is: no direct physical connection; the correlation value of the second connection-related evaluation indicator is:

0.

6. The module division method of a small reactor according to claim 2, characterized in that: The spatial correlation between the system components includes: a first spatial correlation evaluation index and a second spatial correlation evaluation index; The first spatial correlation evaluation index is: located in the same spatial area; the correlation value of the first spatial correlation evaluation index is 1; The second space-related evaluation index is: located in different cabins or space areas; the correlation value of the second space-related evaluation index is 0.

7. The module division method of a small reactor according to claim 1, characterized in that: The step of performing hierarchical module division according to the comprehensive correlation matrix of the system components of the SMR system to obtain the hierarchical clustering results of the system components of the SMR system includes: According to the comprehensive correlation matrix of the system components, a fuzzy hierarchical clustering method is used to divide the system components of the SMR system into hierarchical modules to obtain hierarchical clustering results of the system components of the SMR system.

8. The method for dividing modules of a small reactor according to claim 7, characterized in that: The step of dividing the system components of the SMR system into hierarchical modules by using a fuzzy hierarchical clustering method according to the comprehensive correlation matrix of the system components to obtain the hierarchical clustering results of the system components of the SMR system includes: Based on the comprehensive correlation matrix of the system components, calculating a distance matrix between the components; The fuzzy hierarchical clustering method is used to perform hierarchical clustering and obtain the hierarchical clustering tree of system components; Clustering results at different levels are combined using a non-uniform granularity clustering function to obtain hierarchical clustering results of the system components.

9. The module division method of a small reactor according to claim 8, characterized in that: The method of performing hierarchical clustering by using a fuzzy hierarchical clustering method to obtain a hierarchical clustering tree of system components includes: Treat each system component as a separate initial cluster; In each iteration, the two clusters with the smallest distance are merged to generate a new cluster, and the distance between the new cluster and all other clusters is recalculated. This step is executed repeatedly until all system components are merged into one cluster to generate the hierarchical clustering tree.

10. The module division method of a small reactor according to claim 1, characterized in that: The objective function and constraint conditions for determining the module division of the SMR system include: Based on the comprehensive correlation matrix and the hierarchical clustering results, determining the comprehensive correlation coefficients between system components, the number of modules, and the number of components in the modules; Determining the objective function according to the comprehensive correlation coefficient between the system components, the number of the modules and the number of components in the modules; The constraint condition is determined based on a constraint function and an objective function.

11. The module division method of a small reactor according to claim 10, characterized in that: The objective functions include: coupling evaluation function, cohesion evaluation function, module quantity function, module size limit evaluation function and module weight limit evaluation function; Determining the objective function according to the comprehensive correlation coefficient between the system components, the number of the modules, and the number of components in the modules includes: Determining the coupling evaluation function according to the comprehensive correlation coefficient between the system components and the number of components in the module; Determining the cohesion evaluation function according to the comprehensive correlation coefficient between the system components and the number of modules; Obtaining the module quantity function according to the module quantity; Determining the module size restriction evaluation function according to the physical size of the module; The module weight limit evaluation function is determined according to the total weight of the module and a predetermined upper weight limit.

12. The method for dividing modules of a small reactor according to claim 10, characterized in that: The constraints include: minimizing the coupling between modules, maximizing the module cohesion, minimizing the number of modules, component coverage constraints, and module size and weight limit constraints.

13. The module division method of a small reactor according to claim 1, characterized in that: The step of encoding all modules in the hierarchical clustering results of the system components of the SMR system and optimizing the module division of the SMR system to obtain a target module division scheme includes: All modules in the hierarchical clustering results of the system components of the SMR system are encoded, and a fast non-dominated sorting genetic algorithm is used to optimize the system modularization division to obtain the target module division scheme.

14. The method for dividing modules of a small reactor according to claim 13, characterized in that: The step of encoding all modules in the hierarchical clustering results of the system components of the SMR system and optimizing the system modularization partitioning by using a fast non-dominated sorting genetic algorithm to obtain the target module partitioning scheme includes: S4.1: Determine the encoding method; S4.2: Encode all modules in the hierarchical clustering result according to the encoding method, and establish a component-module construction matrix; S4.3: According to the encoding method and the component-module construction matrix, and under the premise of satisfying constraint conditions, randomly generating an initial population; S4.4: performing non-dominated sorting on the initial population to generate different non-dominated hierarchies; S4.5: Calculate the crowding degree of individuals in each non-dominated level to obtain the crowding degree of individuals in each non-dominated level; S4.6: performing selection, crossover and mutation operations according to the non-dominated level and the crowding degree to generate a new generation of offspring individuals; S4.7: Merge the parent and offspring individuals to form a mixed population, and recalculate the non-dominated sorting and crowding degree of the mixed population to construct the next generation population; S4.8: Determine the target solution of the previous generation; S4.9: Repeat steps S4.4 to S4.8 until the iteration termination condition is met, and output the target module partitioning scheme.

15. The module division method of a small reactor according to claim 14, characterized in that: The encoding methods include: module encoding method and scheme encoding method; The module encoding method includes: each module is represented by a Boolean vector; each bit of the Boolean vector represents whether a certain component exists; The scheme encoding method includes: using a Boolean vector to represent the entire module division scheme; each bit of the Boolean vector represents whether a certain module exists or not.

16. The method for dividing modules of a small reactor according to any one of claims 1 to 15, characterized in that: Also includes: Conduct feasibility analysis and verification based on the target module division scheme; Determine whether the target module partitioning scheme is passed according to the analysis and verification results; If yes, then determine the target module partitioning scheme; If not, reselect to determine the target module partitioning scheme.

17. A module division system for a small reactor, characterized in that: include: A comprehensive matrix construction unit, used to determine correlation information of system components of the SMR system according to nuclear power design information, and to construct a comprehensive correlation matrix of system components of the SMR system according to the correlation information of the system components; A module division unit, used for performing hierarchical module division according to a comprehensive correlation matrix of system components of the SMR system to obtain hierarchical clustering results of system components of the SMR system; A function condition determination unit, used to determine the objective function and constraint conditions of the SMR system module division; The target scheme determination unit is used to encode all modules in the hierarchical clustering results of the system components of the SMR system, and optimize the module division of the SMR system to obtain a target module division scheme.

18. The module division system of the small reactor according to claim 17, characterized in that: Also includes: Target solution verification unit, used to: Conduct feasibility analysis and verification based on the target module division scheme; Determine whether the target module partitioning scheme is passed according to the analysis and verification results; If yes, then determine the target module partitioning scheme; If not, reselect to determine the target module partitioning scheme.

19. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the steps of the module division method of a small reactor as claimed in any one of claims 1 to 16 by calling the computer program stored in the memory.

Images