ISM model weight distribution parameter selection method, system, device and medium

Abstract

The invention provides an ISM model weight distribution parameter selection method, system and device and a medium, and belongs to the field of system safety analysis, and the method comprises the steps: obtaining a function pointing relation and a hierarchical division result of a plurality of subsystems of a to-be-analyzed engineering system; determining the hierarchy weight of each subsystem according to the hierarchy division results of the plurality of subsystems; a structural importance function of the structural importance and the in-degree coefficient of each subsystem is generated based on the hierarchical weight and the pointing relation of each subsystem, and the out-degree coefficient in the structural importance function is converted into a relational expression of the in-degree coefficient in advance through a constraint relation of the out-degree coefficient and the in-degree coefficient; solving a structural importance function based on the structural importance of different layers of subsystems to obtain a value range of an in-degree coefficient; and determining an in-degree coefficient and an out-degree coefficient according to the value range of the in-degree coefficient. According to the method, subjective experience judgment of a parameter selection problem is converted into objective mathematical calculation, and the accuracy and reliability of system safety analysis are improved.

Description

Technical Field

[0001] This invention belongs to the field of system security analysis, specifically involving the method, system, equipment, and medium for selecting weight allocation parameters in the ISM model. Background Technology

[0002] System safety analysis is a systematic engineering approach designed to identify, assess, and control potential risks in complex systems to ensure their reliability, stability, and security during operation. Its core is to develop effective preventative measures by analyzing the interrelationships of internal system components, fault propagation paths, and critical weaknesses. As modern engineering systems become increasingly complex, they often consist of numerous subsystems with intricate dependencies and interactions. For example, a failure in one subsystem can trigger a chain reaction through network effects, ultimately leading to the collapse of the entire system. Therefore, system safety analysis can quantify risk prioritization from a global perspective, avoid local optimization, provide a scientific basis for resource allocation and decision-making, and prevent catastrophic accidents.

[0003] To address the security analysis needs of complex systems, existing technologies utilize Interpretative Structural Models (ISMs) to analyze the interrelationships and hierarchical divisions of subsystems. For example, they calculate the structural importance of each subsystem to measure its influence weight in the fault propagation path, thereby simplifying complex system structures into clear hierarchical networks. However, the calculation of structural importance depends on the values ​​of weighting parameters such as out-degree coefficients (O) and in-degree coefficients (I). Existing weighting parameter values ​​rely on researchers' subjective experience. When the system's connections and hierarchical nesting are complex, these subjectively determined empirical values ​​often fail to meet the "in-degree influence is less than out-degree influence" propagation logic after global calculation and superposition. This leads to discrepancies between the structural importance ranking calculated by the ISM model and the actual risk propagation path, reducing the accuracy of system security analysis. Summary of the Invention

[0004] To address the problem of insufficient accuracy in security analysis due to the subjective setting of weight allocation parameters in existing ISM models used for analyzing system security, this invention provides a method, system, device, and medium for selecting weight allocation parameters in ISM models.

[0005] To achieve the above objectives, the present invention provides the following technical solution: Methods for selecting weight allocation parameters in ISM models include: Obtain the functional orientation relationships and hierarchical division results of multiple subsystems of the engineering system to be analyzed; determine the hierarchical weight of each subsystem based on the hierarchical division results of multiple subsystems; Based on the hierarchical weights and pointing relationships of each subsystem, a structural importance function is generated for each subsystem, including the structural importance and in-degree coefficients. The weight allocation parameters include the out-degree coefficients and in-degree coefficients. The out-degree coefficients in the structural importance function are pre-converted into the in-degree coefficients through the constraint relationship between the out-degree coefficients and in-degree coefficients. The structural importance function is solved based on the structural importance of different subsystems to obtain the range of values ​​for the in-degree coefficient; the in-degree coefficient and out-degree coefficient are determined based on the range of values ​​for the in-degree coefficient; and the System Security Analysis (ISM) model of the engineering system to be analyzed is constructed using the in-degree coefficient and out-degree coefficient.

[0006] Optionally, the ISM model weight allocation parameter selection method provided by the present invention further includes: For a subsystem, the hierarchical weights of multiple subsystems that functionally point to the subsystem and the hierarchical weights of multiple subsystems that functionally point to the subsystem are determined by the functional pointing relationship. The mean weights of the subsystems that function to the subsystem and the subsystems that the subsystem points to are calculated respectively to obtain the mean weights of the subsystems that function to the subsystem and the mean weights of the subsystems that the subsystem points to. Based on the constraint relationship between the out-degree coefficient and the in-degree coefficient, a structural importance function is constructed, which uses the mean weight pointing to the subsystem, the hierarchical weight of the subsystem, and the mean weight of the multiple subsystems pointed to by the subsystem. The function has the in-degree coefficient of the subsystem as the independent variable and the structural importance of the subsystem as the dependent variable.

[0007] Optionally, in the ISM model weight allocation parameter selection method provided by the present invention, the constraint relationship between the out-degree coefficient and the in-degree coefficient is that the sum of the out-degree coefficient and the in-degree coefficient is a fixed value, and the out-degree coefficient is greater than the in-degree coefficient.

[0008] Optionally, the ISM model weight allocation parameter selection method provided by the present invention further includes: When a subsystem does not have multiple subsystems that functionally point to it, the compensation weights of the multiple subsystems that the subsystem points to are multiplied by the compensation coefficient to obtain the compensation weights of the multiple subsystems that the subsystem points to; and a structural importance function is constructed based on the compensation weights of the multiple subsystems that the subsystem points to and the hierarchical weights of the subsystem. When a subsystem does not have multiple subsystems that it points to, the compensation weights of the multiple subsystems that functionally point to the subsystem are obtained by multiplying the average weights of the multiple subsystems that functionally point to the subsystem with the compensation coefficient; and the structural importance function is constructed based on the multiple subsystems that functionally point to the subsystem and the hierarchical weights of the subsystem.

[0009] Optionally, the ISM model weight allocation parameter selection method provided by the present invention further includes: The structural importance functions of multiple subsystems at the same level are intersected. When the structural importance functions of multiple subsystems at the same level do not intersect within the preset range of independent variables, the multiple subsystems at the same level are ranked by importance based on the structural importance corresponding to any independent variable.

[0010] Optionally, the ISM model weight allocation parameter selection method provided by the present invention further includes: When the structural importance functions of multiple subsystems at the same level intersect within a preset range of independent variables, the multiple subsystems with intersections are considered as candidate subsystems at that level. Based on the constraints of the structural importance of subsystems at different levels, the in-degree coefficients are solved according to the structural importance functions of the candidate subsystems at that level, the candidate subsystems above that level, and the candidate subsystems below that level. The constraint of the structural importance of subsystems at different levels is that the structural importance of the candidate subsystems above that level is greater than that of the candidate subsystems at that level, and the structural importance of the candidate subsystems at that level is greater than that of the candidate subsystems at the level below that level.

[0011] Optionally, the ISM model weight allocation parameter selection method provided by the present invention further includes: Within the range of values ​​for the in-degree coefficient, the values ​​of the in-degree coefficient are used as variables to calculate the between-group sum of squares, the sum of squares of errors, and the total sum of squares using the analysis of variance model. The in-degree coefficient is determined based on the between-group sum of squares, the sum of squares of errors, and the total sum of squares. The out-degree coefficient is determined from the in-degree coefficient based on the constraint relationship between the out-degree coefficient and the in-degree coefficient.

[0012] This invention also provides an ISM model weight allocation parameter selection system, including: The hierarchy weight determination module is used to obtain the functional orientation relationship and hierarchy division results of multiple subsystems of the engineering system to be analyzed; and to determine the hierarchy weight of each subsystem based on the hierarchy division results of multiple subsystems. The structural importance function construction module is used to generate the structural importance function of each subsystem and the in-degree coefficient based on the hierarchical weight and pointing relationship of each subsystem. The out-degree coefficient in the structural importance function is pre-converted into the in-degree coefficient relationship through the constraint relationship between the out-degree coefficient and the in-degree coefficient. The weight allocation parameter determination module is used to solve the structural importance function based on the structural importance of different subsystem layers, and obtain the value range of the in-degree coefficient; determine the in-degree coefficient and out-degree coefficient according to the value range of the in-degree coefficient; and construct the system security analysis (ISM) model of the engineering system to be analyzed from the in-degree coefficient and out-degree coefficient.

[0013] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement any of the steps in the ISM model weight allocation parameter selection method.

[0014] The present invention also provides a computer-readable storage medium storing a computer program that, when loaded by a processor, can execute any step of the ISM model weight allocation parameter selection method.

[0015] The method for selecting weight allocation parameters for the ISM model provided by this invention has the following beneficial effects: The ISM model weight allocation parameter selection method provided by this invention determines the hierarchical weight of each subsystem based on the hierarchical division results. Then, it constructs a structural importance function by combining the hierarchical weights and functional orientation relationships. The weight allocation parameters in this function are ultimately uniformly expressed as an in-degree coefficient relationship through preset constraints. Then, by solving the relationship between the structural importance of subsystems at different levels, the range of values ​​for the in-degree coefficient is derived, and the out-degree coefficient is determined based on the in-degree coefficient. In this invention, because the functional orientation relationships between subsystems, the hierarchical division results, and the hierarchical weights are used as objective inputs to generate a function of the structural importance of each subsystem with respect to the in-degree coefficient, the parameter selection problem is transformed from subjective experience-based judgment into objective mathematical calculation. This effectively eliminates the problems of arbitrary parameter values ​​and incomparable analysis results caused by differences in researchers' personal experience in the ISM model for system security analysis, thereby improving the accuracy and reliability of the ISM model in system security analysis. Attached Figure Description

[0016] To more clearly illustrate the embodiments and design schemes of the present invention, the accompanying drawings required for this embodiment will be briefly described below. The drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A schematic diagram of the ISM model weight allocation parameter selection method provided in this embodiment of the invention; Figure 2 This is an example of the connection relationship of an airborne hydrogen system provided in an embodiment of the present invention. Detailed Implementation

[0018] To enable those skilled in the art to better understand and implement the technical solutions of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and should not be construed as limiting the scope of protection of the present invention.

[0019] The existing ISM model lacks a unified and scientific basis for determining the out-degree and in-degree coefficients, relying heavily on the subjective experience of researchers. This not only leads to the risk of non-compliance of transmission logic in complex systems, but also causes incomparable analysis results due to differences in values ​​taken by different researchers, reducing the reliability of the ISM model in engineering practice.

[0020] In summary, existing technologies, lacking a mathematical model and constraint system for parameter selection tailored to the hierarchical characteristics of ISM, cannot fundamentally address the subjectivity and uncertainty of parameter values. Therefore, a standardized parameter selection scheme for out-degree and in-degree coefficients is urgently needed to support the widespread application of ISM models. The ISM model weight allocation parameter selection method provided in this invention defines and determines the basic constraints of O and I, derives the functional relationship between structural importance and parameters using lemmas, proposes the concept of double-chain structural importance for calculation, establishes the parameter value range by combining inter-level importance constraints, and finally verifies parameter significance using optional two-way ANOVA. This invention provides a standardized parameter selection scheme for calculating the structural importance of ISM, avoiding analytical biases caused by subjective values ​​and improving the accuracy and reliability of system security analysis.

[0021] Example 1 This application provides a method for selecting weight allocation parameters in the ISM model, specifically as follows: Figure 1 As shown, it includes the following steps: Step 11: Obtain the functional orientation relationship and hierarchical division results of multiple subsystems of the engineering system to be analyzed; determine the hierarchical weight of each subsystem based on the hierarchical division results of multiple subsystems.

[0022] Specifically, the system hierarchy importance and the connectivity between subsystems are first determined through ISM hierarchical structure analysis. Node importance is determined solely by the node's own hierarchy, the hierarchical distribution of its neighboring nodes, and its out-degree and in-degree values; there is no direct mutual influence between nodes at the same hierarchy. When any node and all its neighboring nodes belong to the same network hierarchy, the importance of each node is a monotonically increasing function of its degree value.

[0023] Step 12: Generate a structural importance function for each subsystem based on its hierarchical weights and pointing relationships, including the structural importance and in-degree coefficients. The weight allocation parameters include out-degree and in-degree coefficients. The out-degree coefficients in the structural importance function are pre-converted into an in-degree coefficient relationship using constraints between out-degree and in-degree coefficients. For example, the constraint relationship between out-degree and in-degree coefficients is that the sum of the out-degree and in-degree coefficients is a fixed value, and the out-degree coefficient is greater than the in-degree coefficient.

[0024] The structural importance function can be constructed through the following steps: Step 121: For a subsystem, determine the hierarchical weights of multiple subsystems that functionally point to the subsystem, and the hierarchical weights of multiple subsystems that the subsystem functionally points to, based on the functional pointing relationship.

[0025] Step 122: Calculate the mean weights of the multiple subsystems that functionally point to the subsystem and the multiple subsystems that the subsystem points to, respectively, to obtain the mean weights of the multiple subsystems that functionally point to the subsystem and the mean weights of the multiple subsystems that the subsystem points to.

[0026] Step 123: Based on the constraint relationship between the out-degree coefficient and the in-degree coefficient, construct a structural importance function with the in-degree coefficient of the subsystem as the independent variable and the structural importance of the subsystem as the dependent variable, using the mean weight pointing to the subsystem in terms of function, the hierarchical weight of the subsystem, and the mean weight of the multiple subsystems pointed to by the subsystem.

[0027] When the subsystem does not point to any other subsystem or there are no other subsystems pointing to the subsystem, the structural importance function can be constructed using the following steps: Step 124: When a subsystem does not have multiple subsystems that functionally point to it, the compensation weights of the multiple subsystems pointed to by the subsystem are obtained by multiplying the average weights of the multiple subsystems pointed to by the subsystem by the compensation coefficient; and the structural importance function is constructed based on the compensation weights of the multiple subsystems pointed to by the subsystem and the hierarchical weights of the subsystem.

[0028] Step 125: When a subsystem does not have multiple subsystems that it points to, the compensation weights of the multiple subsystems that functionally point to the subsystem are multiplied by the compensation coefficient to obtain the compensation weights of the multiple subsystems that functionally point to the subsystem; and the structural importance function is constructed based on the multiple subsystems that functionally point to the subsystem and the hierarchical weights of the subsystem.

[0029] Specifically, this invention considers that the influence of degree nodes on the nodes to be evaluated within a single subsystem is less than that of out-degree nodes. Therefore, the in-degree coefficient is set to be less than the out-degree coefficient, i.e., I < 0. Furthermore, in order to ensure that the structural importance is a dimensionless pure numerical value and that the sum of the structural importance of all subsystems within the system is constant, thus maintaining analytical consistency, the sum of the out-degree coefficient and the in-degree coefficient needs to be set to a fixed value, for example, 0 + I = 1.

[0030] Based on this, the structural importance calculation formula of the ISM model, combined with the constraint O=1-I, transforms the structural importance expression into a linear function of the importance of the double-chain structure, as shown in formula (1): (1) The importance of the double-chain structure is the result of processing the mean of the importance of the subsystem structure, as shown in formula (2): (2) in, For the structural importance of subsystem i or function i, Let be the mean of the structural importance of subsystem i. Let i be the hierarchical weight of subsystem i or function i. Let function j be the hierarchy weight of the level where function i resides. Let i be the hierarchy weight of the level at which function k resides. This represents the number of levels at which function i is located, as pointed to by function j. This represents the number of levels at which function k, which is pointed to by function i, resides.

[0031] When the in-degree or out-degree term of subsystem i is 0, for example, if subsystem i does not have a function j pointing to the subsystem corresponding to function i, or if function i does not have a function k pointing to the subsystem corresponding to function k, then this term is set to 0, and the other term is multiplied by 2, thereby maintaining the doubly chained structure of the doubly chained importance function.

[0032] Step 13: Perform an intersection judgment on the structural importance functions of multiple subsystems at the same level. When the structural importance functions of multiple subsystems at the same level do not have an intersection point within the preset independent variable interval, sort the multiple subsystems at the same level by importance based on the structural importance corresponding to any independent variable.

[0033] Step 14: Solve the structural importance function based on the structural importance of different subsystem layers to obtain the range of values ​​for the in-degree coefficient; determine the in-degree coefficient and out-degree coefficient of the engineering system to be analyzed based on the range of values ​​for the in-degree coefficient; construct the System Security Analysis (ISM) model of the engineering system to be analyzed based on the in-degree coefficient and out-degree coefficient.

[0034] The structural importance function can be solved using the following steps: Step 141: When the structural importance functions of multiple subsystems at the same level intersect within the preset independent variable interval, the multiple subsystems with intersection points are regarded as candidate subsystems of that level.

[0035] Step 142: Based on the constraints of the structural importance of subsystems at different levels, solve for the in-degree coefficients according to the structural importance functions of the candidate subsystems at this level, the candidate subsystems above this level, and the candidate subsystems below this level. The constraint of the structural importance of subsystems at different levels is that the structural importance of the candidate subsystems above this level is greater than the structural importance of the candidate subsystems at this level, and the structural importance of the candidate subsystems at this level is greater than the structural importance of the candidate subsystems at the level below this level.

[0036] Specifically, since the structural importance of a subsystem can only represent the probability weight of a functional failure chain passing through that subsystem when the system is functionally damaged (for example, a single subsystem may be pointed to by multiple other systems or point to multiple other systems), the structural importance of a higher-level subsystem does not have an absolute causal relationship with the structural importance of a lower-level subsystem.

[0037] Considering that the number of subsystems in a complete ISM system is usually large, pairwise comparisons would result in a huge amount of computation. However, the magnitude of rational numbers is transitive. If we ensure that the subsystem with the least importance of the double-chain structure in the upper layer is still greater than the subsystem with the most importance of the double-chain structure in the lower layer, we can maintain the importance order between layers.

[0038] This invention is based on the constraint that the importance of the double-chain structure in the upper subsystem is much greater than that in the lower subsystem. By establishing an inequality constraint between the subsystem with the least importance of the double-chain structure in the upper subsystem and the subsystem with the most importance of the double-chain structure in the lower subsystem, the range of values ​​of I is obtained by solving the constraint. The range of values ​​is further refined by combining the derivation conclusion that I < 0.5.

[0039] For example, we first compare subsystems at the same level. Suppose that in an ISM system with a level number and the functional relationship between the subsystems, there are two subsystems c and d at the same level. The importance of the doubly chain structure of subsystems c and d is shown in Equation (3) and Equation (4), respectively:

[0040] (3) (4) After that, and When comparing the functions represented by the two functions, if the two functions do not intersect within the interval [0,1], that is... Always greater than ,or Always less than At this point, the order of importance between the two can be directly determined, and when the two functions intersect within the interval [0,1], there must exist... and When two subsystems have opposite signs, they are considered as candidate subsystems for subsequent determination of hierarchical relationships. For example, the system order within a hierarchy is identified through classification and discussion, providing a basis for subsequent ordering between hierarchical levels. For instance, when there is an intersection point within a hierarchy in the interval from zero to one, the interval is divided into smaller blocks based on the intersection points of the functions within the interval. Since these smaller blocks are all linear or constant functions, the intersection points can cause changes in the hierarchical order. Therefore, the systems within the hierarchy are ordered, and the corresponding intervals of the top-level and bottom-level systems are considered to achieve comparison between different levels.

[0041] Specifically, in the process of determining the upper and lower levels, let subsystems a and b belong to different levels in the same ISM system, with a located at the upper level and b located at the lower level. In this case, the importance of the double-chain structure of subsystems a and b is shown in formula (5) and formula (6) respectively: (5) (6) Since the structural importance of the upper-level subsystem needs to be greater than that of the lower-level subsystem, as shown in formula (7), formulas (5) and (6) are then combined to obtain the relationship shown in formula (8): (7) (8) After rearranging and simplifying formula (8), when When the value is greater than 0, the in-degree coefficient I is deducted. The relationship of the in-degree coefficient I is shown in formula (9): (9) Similarly, when When the in-degree coefficient I is less than 0, the relationship is shown in formula (10): (10) In summary, by establishing the hierarchical structure and subsystem relationships described above, constraints on the value of I can be established, thereby determining its reasonable range. Furthermore, based on the constraints of the in-degree and out-degree coefficients, an ISM model for the system security analysis of the engineering system to be analyzed can be constructed, thus completing the security analysis of the engineering system.

[0042] The in-degree and out-degree coefficients can be confirmed and verified through the following steps: Step 143: Within the range of values ​​for the in-degree coefficient, using the values ​​of the in-degree coefficient as variables, calculate the between-group sum of squares, the error sum of squares, and the total sum of squares using the analysis of variance model.

[0043] Step 144: Determine the in-degree coefficient based on the between-group sum of squares, the error sum of squares, and the total sum of squares.

[0044] Step 145: Determine the out-degree coefficient from the in-degree coefficient based on the constraint relationship between the out-degree coefficient and the in-degree coefficient.

[0045] Specifically, once the range of values ​​for I is obtained, any value within that range can be used as the in-degree / out-degree coefficient in the quantitative safety analysis of ISM. For ease of calculation, it is recommended to use the median of this range or round it appropriately. Furthermore, a two-way ANOVA can be used to further examine the significance of the parameter values ​​on the results. For example, using different values ​​of I as variables, an ANOVA model can be constructed, calculating the between-group sum of squares (SA), the sum of squares of errors (Se), and the total sum of squares (ST), and then calculating the F-value. The significance level can be determined based on the system size. To verify whether the parameter values ​​have a significant impact on the ranking of structural importance.

[0046] Example 2 Based on Example 1, taking an airborne hydrogen system in an engineering system as an example, the in-degree and out-degree coefficients are determined using the ISM model weight allocation parameter selection method provided by this invention. A corresponding system safety analysis ISM model is then constructed, and a safety analysis of the airborne hydrogen system is performed, thereby verifying the feasibility of the ISM model weight allocation parameter selection method provided by this invention in the direction of system safety analysis. The airborne hydrogen system includes F1: electronic / electrical system, F2: hydrogen storage system, F3: booster pump pressurization system, F4: hydrogen supply pipeline system, F5: hydrogen internal combustion engine combustion system, F6: pilot control system, F7: cooling system, F8: storage capacity sensing system, F9: flow rate sensing system, and F10: temperature sensing system.

[0047] First, according to the airborne hydrogen system, such as Figure 2 The connections between each subsystem are hierarchically divided as shown in Table 1: Table 1. ISM Hierarchy Classification of Airborne Hydrogen Systems Then, combined with the structural quantitative analysis formula The importance or hierarchy weight of each level is determined, as shown in Table 2: Table 2 Importance of the ISM Functional Hierarchy Subsequently, based on the hierarchical weights of each subsystem's corresponding level, a functional representation model of the bi-chain structure was constructed, as shown in Table 3: Table 3 Modeling Table of Functional Expressions for Double-Chain Structures Where X is the in-degree coefficient of the independent variable, and Y is the structural importance of the dependent variable subsystem. First, multiple subsystems within the same level are compared. Since the third-level system has multiple subsystems, the importance ranking of the doubly chained structure of the third-level system ({F1,F3,F4,F6,F9,F10}) within the domain [0,1] is always {F4} < {F1} < {F10} < {F6} < {F3} < {F9}. The overall doubly chained structure function of the system must conform to the hierarchical structure requirements, specifically satisfying the predefined constraint relationship: {F5} < {F7} < {F1,F3,F4,F6,F9,F10} < {F8} < {F2}. Based on the above constraints, when F2 > F8 always holds, i.e., -0.0799X + 0.0799 > 0.0639X + 0.0319, it can be deduced that X < 0.333. According to the constraint that the importance of the double-chain structure in the fourth-layer system must be greater than the importance of the maximum double-chain structure in the third-layer system, i.e., when {F9} < {F8}, X > 0.1248, the range of X is limited to [0.1248, 0.333]. Within this range, the minimum importance of the double-chain structure in the third-layer system is always greater than that in the second-layer system, and the minimum importance of the double-chain structure in the second-layer system is always greater than that in the first-layer system, satisfying all level constraints. At this time, the range of the in-degree coefficient is [0.1248, 0.333], and the range of the out-degree coefficient is [0.667, 0.8752]. In this case, the average value of the in-degree coefficient is selected, for example, 0.23, as the in-degree coefficient, and 0.77 is selected as the out-degree coefficient.

[0048] Next, a two-way ANOVA was performed on the aforementioned in-degree coefficients and out-degree coefficients. First, five candidate values ​​for the in-degree coefficients (0.13, 0.18, 0.23, 0.28, and 0.33) within the range of in-degree coefficient values ​​were selected as analysis variables. For each in-degree coefficient, the structural importance of the corresponding subsystem element was calculated, and the elements were ranked according to their structural importance. At this point, the in-degree coefficients and the subsystem were designated as the two factors in the two-way ANOVA. Considering that there is no interaction between the subsystem and the in-degree coefficient, and no need for second-order checks, the Bonfurone correction method was used to control the Type I error rate in the multiple comparisons. The analysis is shown in Table 4.

[0049] Table 4. Two-way ANOVA table of ISM input and output coefficients. Among them, R2 =0.984. As shown in Table 4, when the source of difference is the system, F=238.647, *p<0.05, **p<0.01, which is significant, indicating that the main effect exists and the system will have a difference relationship with the ranking. The specific difference can be further analyzed through one-way ANOVA. When the source of difference is the value of I, F=0, p is 1, which is greater than 0.05, and it is not significant, indicating that the value of I will not have a difference relationship with the ranking.

[0050] Example 3 This application also provides an ISM model weight assignment parameter selection system, including: The hierarchy weight determination module is used to obtain the functional orientation relationship and hierarchy division results of multiple subsystems of the engineering system to be analyzed; and to determine the hierarchy weight of each subsystem based on the hierarchy division results of multiple subsystems. The structural importance function construction module is used to generate the structural importance function of each subsystem and the in-degree coefficient based on the hierarchical weight and pointing relationship of each subsystem. The out-degree coefficient in the structural importance function is pre-converted into the in-degree coefficient relationship through the constraint relationship between the out-degree coefficient and the in-degree coefficient. The weight allocation parameter determination module is used to solve the structural importance function based on the structural importance of different subsystems, and obtain the range of values ​​for the in-degree coefficient; determine the in-degree coefficient and out-degree coefficient of the engineering system to be analyzed based on the range of values ​​for the in-degree coefficient; and construct the system security analysis (ISM) model of the engineering system to be analyzed from the in-degree coefficient and out-degree coefficient.

[0051] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the steps in the embodiment of the ISM model weight allocation parameter selection method. Specific implementation methods can be found in the method embodiments, and will not be repeated here.

[0052] Furthermore, the present invention also provides a non-transitory computer-readable storage medium containing instructions on which a computer program is stored. For example, a memory containing instructions that can be executed by a processor of a computer device to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc. When the computer program is executed by the processor, it can implement the steps in the embodiment of the ISM model weight allocation parameter selection method. Specific implementation methods can be found in the method embodiments, which will not be repeated here.

[0053] Those skilled in the art will understand that embodiments of the present invention can provide methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0054] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0055] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0056] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0057] It should be noted that the specific embodiments described above enable those skilled in the art to more fully understand the present invention, but do not limit the present invention in any way. Therefore, although the present invention has been described in detail in this specification and embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the present invention; and all technical solutions and improvements that do not depart from the spirit and scope of the present invention are covered within the protection scope of the present invention patent. No reference numerals in the claims should be construed as limiting the scope of the claims. Any simple variations or equivalent substitutions of technical solutions that can be readily obtained by those skilled in the art within the scope of the technology disclosed in the present invention are within the protection scope of the present invention.

Claims

1. A method for selecting weight allocation parameters in an ISM model, characterized in that, include: Obtain the functional orientation relationships and hierarchical division results of multiple subsystems of the engineering system to be analyzed; The hierarchical weight of each subsystem is determined by the hierarchical division results of the multiple subsystems; Based on the hierarchical weights and pointing relationships of each subsystem, a structural importance function is generated for each subsystem, including the structural importance and in-degree coefficients. The weight allocation parameters include the out-degree coefficients and the in-degree coefficients. The out-degree coefficients in the structural importance function are pre-converted into an in-degree coefficient relationship through the constraint relationship between the out-degree coefficients and the in-degree coefficients. The structural importance function is solved based on the structural importance of different subsystems to obtain the range of values ​​for the in-degree coefficient; the in-degree coefficient and out-degree coefficient are determined based on the range of values ​​for the in-degree coefficient; and the System Security Analysis (ISM) model of the engineering system to be analyzed is constructed using the in-degree coefficient and out-degree coefficient.

2. The method for selecting weight allocation parameters in the ISM model according to claim 1, characterized in that, The structural importance function, which generates the structural importance and in-degree coefficient of each subsystem based on the hierarchical weights and functional orientation relationships of each subsystem, includes: For a subsystem, the hierarchical weights of multiple subsystems that functionally point to the subsystem and the hierarchical weights of multiple subsystems that functionally point to the subsystem are determined by the functional pointing relationship. The mean weights of the subsystems that function to the subsystem and the subsystems that the subsystem points to are calculated respectively to obtain the mean weights of the subsystems that function to the subsystem and the mean weights of the subsystems that the subsystem points to. Based on the constraint relationship between the out-degree coefficient and the in-degree coefficient, a structural importance function is constructed using the mean weight pointing to the subsystem, the hierarchical weight of the subsystem, and the mean weight of the multiple subsystems to which the subsystem points. The function has the in-degree coefficient of the subsystem as the independent variable and the structural importance of the subsystem as the dependent variable.

3. The method for selecting weight allocation parameters in the ISM model according to claim 2, characterized in that, The constraint relationship between the out-degree coefficient and the in-degree coefficient is that the sum of the out-degree coefficient and the in-degree coefficient is a fixed value, and the out-degree coefficient is greater than the in-degree coefficient.

4. The method for selecting weight allocation parameters in the ISM model according to claim 2, characterized in that, The structural importance function of the subsystem, which is constructed from the mean weights pointing to the subsystem, the hierarchical weights of the subsystem, and the mean weights of the multiple subsystems to which the subsystem points, includes: When the subsystem does not have multiple subsystems that functionally point to it, the compensation weight of the multiple subsystems that the subsystem points to is obtained by multiplying the average weight of the multiple subsystems that the subsystem points to by the compensation coefficient; the structural importance function is constructed based on the compensation weight of the multiple subsystems that the subsystem points to and the hierarchical weight of the subsystem. When the subsystem does not have multiple subsystems that the subsystem points to, the compensation weight of the multiple subsystems that functionally point to the subsystem is obtained by multiplying the average weight of the multiple subsystems that functionally point to the subsystem by the compensation coefficient; the structural importance function is constructed based on the multiple subsystems that functionally point to the subsystem and the hierarchical weight of the subsystem.

5. The method for selecting weight allocation parameters in the ISM model according to claim 1, characterized in that, Before solving the structural importance function based on the structural importance of different subsystem layers, the following steps are also included: The structural importance functions of multiple subsystems at the same level are intersected. When the structural importance functions of multiple subsystems at the same level do not intersect within a preset range of independent variables, the multiple subsystems at the same level are ranked by importance based on the structural importance corresponding to any independent variable.

6. The method for selecting weight allocation parameters in the ISM model according to claim 5, characterized in that, Solving the structural importance function based on the structural importance of different subsystem layers includes: When the structural importance functions of multiple subsystems at the same level intersect within a preset range of independent variables, the multiple subsystems with intersecting points are considered as candidate subsystems at that level. Based on the constraint of the structural importance of subsystems at different levels, the in-degree coefficients are solved according to the structural importance functions corresponding to the candidate subsystems at that level, the candidate subsystems above that level, and the candidate subsystems below that level. The constraint of the structural importance of subsystems at different levels is that the structural importance of the candidate subsystems above that level is greater than the structural importance of the candidate subsystems at that level, and the structural importance of the candidate subsystems at that level is greater than the structural importance of the candidate subsystems at the level below that level.

7. The method for selecting weight allocation parameters in the ISM model according to claim 1, characterized in that, Determining the in-degree coefficient and the out-degree coefficient based on the range of values ​​for the in-degree coefficient includes: Within the range of the in-degree coefficient, the values ​​of the in-degree coefficient are used as variables to calculate the between-group sum of squares, the error sum of squares, and the total sum of squares using an analysis of variance model. The in-degree coefficient is determined based on the inter-group sum of squares, the sum of squares of errors, and the total sum of squares. The out-degree coefficient is determined by the in-degree coefficient based on the constraint relationship between the out-degree coefficient and the in-degree coefficient.

8. An ISM model weight allocation parameter selection system, characterized in that, include: The hierarchy weight determination module is used to obtain the functional orientation relationship and hierarchy division results of multiple subsystems of the engineering system to be analyzed; The hierarchical weight of each subsystem is determined by the hierarchical division results of the multiple subsystems; The structural importance function construction module is used to generate a structural importance function for each subsystem based on the hierarchical weights and pointing relationships of each subsystem, wherein the out-degree coefficients in the structural importance function are pre-converted into a relational expression for the in-degree coefficients through the constraint relationship between the out-degree coefficients and the in-degree coefficients; The weight allocation parameter determination module is used to solve the structural importance function based on the structural importance of different subsystem layers to obtain the value range of the in-degree coefficient; determine the in-degree coefficient and the out-degree coefficient according to the value range of the in-degree coefficient; and construct the System Security Analysis (ISM) model of the engineering system to be analyzed from the in-degree coefficient and the out-degree coefficient.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the ISM model weight allocation parameter selection method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is loaded by the processor, it is able to execute the steps of the ISM model weight allocation parameter selection method according to any one of claims 1 to 7.

Images