Unmanned equipment system reliability optimization method, equipment, medium and product

Abstract

The invention discloses an unmanned equipment system reliability optimization method and device, a medium and a product, and relates to the field of equipment system reliability, and the method comprises the steps: constructing a heterogeneous network model of an unmanned equipment system; carrying out sensitivity analysis on key parameters of the heterogeneous network model of the unmanned equipment system by utilizing a Sobol sensitivity analysis method; constructing a dynamic reconstruction strategy; the dynamic reconstruction strategy comprises intra-chain reconstruction, inter-chain reconstruction and node self-repairing; and integrating and optimizing a sensitivity analysis result and a dynamic reconstruction strategy, and determining the reliability of the unmanned equipment system by using an optimization result. According to the method, the robustness of the unmanned equipment system when the unmanned equipment system is attacked and the adaptability of the unmanned equipment system in a dynamic change environment can be improved.

Description

Technical Field

[0001] The present application relates to the field of equipment system reliability, and in particular to an unmanned equipment system reliability optimization method, equipment, medium and product. Background Art

[0002] As the situation evolves rapidly, unmanned equipment systems are becoming increasingly important. Unmanned equipment systems consist of a variety of unmanned platforms, such as drones, unmanned vehicles, and unmanned ships, which achieve specific combat missions through a high degree of autonomy and intelligence. When performing tasks, these equipment systems need to face complex and changing environments and diverse threats from the opponent. Therefore, their reliability has become a key factor in ensuring the effectiveness of mission completion.

[0003] However, in the design process of existing unmanned equipment systems, the heterogeneity between nodes and its impact on the reliability of the entire system are often not fully considered. In actual mission execution, the unmanned equipment system includes multiple nodes such as reconnaissance, decision-making, and strike, and the interaction between them has a direct impact on the stability of the system and the reliability of the mission. In addition, as the environment continues to change, the unmanned equipment system needs to have the ability to respond quickly and dynamically reconstruct in order to adapt to emergencies and maintain corresponding effectiveness.

[0004] At present, the research on dynamic reconstruction strategies for unmanned equipment systems is still in its infancy. There is a lack of systematic and quantitative analysis methods, making it difficult to quickly and effectively adjust the mission network structure during the mission to resist enemy attacks or restore combat capabilities.

[0005] In view of the above problems, there is an urgent need to provide a reliability optimization method or system for an unmanned equipment system, so as to improve the robustness of the unmanned equipment system when attacked and its adaptability in a dynamically changing environment. Summary of the invention

[0006] The purpose of this application is to provide a method, device, medium and product for optimizing the reliability of an unmanned equipment system, which can improve the robustness of the unmanned equipment system when attacked and its adaptability in a dynamically changing environment.

[0007] To achieve the above objectives, this application provides the following solutions:

[0008] In a first aspect, the present application provides a method for optimizing the reliability of an unmanned equipment system, the method comprising:

[0009] Constructing a heterogeneous network model of an unmanned equipment system; the heterogeneous network model is used to simulate different types of nodes in an actual task execution network and simulate the connection probability between nodes; the nodes are equipment in the unmanned equipment system;

[0010] The Sobol sensitivity analysis method is used to conduct sensitivity analysis on the key parameters of the heterogeneous network model of the unmanned equipment system; the key parameters include: the number of nodes, the probability of node connection and the number of node edges;

[0011] Construct a dynamic reconstruction strategy; the dynamic reconstruction strategy includes: intra-chain reconstruction, inter-chain reconstruction and node self-repair; the intra-chain reconstruction means that when a node of the unmanned equipment system fails, the failed node is replaced by a node of the same type in the same kill chain; the inter-chain reconstruction means that when a node of the unmanned equipment system fails, the failed node is replaced by a node of the same type in a different kill chain; the node self-repair means that when a node of the unmanned equipment system fails, the kill chain is restored by adding a new identical node or repairing the failed node;

[0012] The sensitivity analysis results are integrated and optimized with the dynamic reconstruction strategy, and the optimization results are used to determine the reliability of the unmanned equipment system.

[0013] Optionally, the construction of a heterogeneous network model of an unmanned equipment system specifically includes:

[0014] Divide the equipment in the unmanned equipment system;

[0015] According to the division results, the corresponding transfer matrix and arrival matrix are determined respectively;

[0016] Determine the number of kill chains in the unmanned equipment system based on the arrival matrix.

[0017] Optionally, the Sobol sensitivity analysis method is used to perform sensitivity analysis on key parameters of the heterogeneous network model of the unmanned equipment system, specifically including:

[0018] Determine the value range and number of values ​​corresponding to the key parameters of each partition result;

[0019] According to the value range and number of the key parameters of each partition result, the Sobol sequence generation function is used to determine the corresponding random value;

[0020] According to the value range and value number corresponding to the key parameters of each partition result and the corresponding random value, the reliability function is used to determine the reliability index of the heterogeneous network model;

[0021] Determine the average number of kill chains corresponding to each reliability indicator;

[0022] According to the average value of the number of kill chains corresponding to each reliability indicator and the change of each reliability indicator, the influence of each reliability indicator on the reliability of the heterogeneous network model is determined, and the corresponding Sobol index is determined. Then, the Sobol index is sorted to obtain the sensitivity analysis results.

[0023] Optionally, the reliability function R(i+1) is:

[0024]

[0025] Among them, A temp is the adjacency matrix, exp(A temp ) ij is the sum of the non-zero elements in the adjacency matrix index, i and j are nodes, and n is the total number of nodes.

[0026] Optionally, in the node self-repair, failed nodes with a high node connection probability are repaired.

[0027] Optionally, the sensitivity analysis results are integrated and optimized with the dynamic reconstruction strategy, and the reliability of the unmanned equipment system is determined using the optimization results, specifically including:

[0028] Determine the proportion of effective kill chains in heterogeneous network models;

[0029] When the attack strategy of randomly deleting nodes is carried out, a dynamic reconstruction strategy is adopted to redetermine the effective kill chain ratio in the heterogeneous network model.

[0030] In a second aspect, the present application provides an unmanned equipment system reliability optimization device, the unmanned equipment system reliability optimization device comprising:

[0031] A heterogeneous network model building module is used to build a heterogeneous network model of an unmanned equipment system; the heterogeneous network model is used to simulate different types of nodes in an actual task execution network and simulate the connection probability between nodes; the node is the equipment in the unmanned equipment system;

[0032] A sensitivity analysis module is used to perform sensitivity analysis on key parameters of the heterogeneous network model of the unmanned equipment system using the Sobol sensitivity analysis method; the key parameters include: the number of nodes, the probability of node connection and the number of node edges;

[0033] A dynamic reconstruction strategy construction module is used to construct a dynamic reconstruction strategy; the dynamic reconstruction strategy includes: intra-chain reconstruction, inter-chain reconstruction and node self-repair; the intra-chain reconstruction means that when a node of the unmanned equipment system fails, the failed node is replaced by a node of the same type in the same kill chain; the inter-chain reconstruction means that when a node of the unmanned equipment system fails, the failed node is replaced by a node of the same type in a different kill chain; the node self-repair means that when a node of the unmanned equipment system fails, the kill chain is restored by adding a new identical node or repairing the failed node;

[0034] The optimization module is used to integrate and optimize the sensitivity analysis results with the dynamic reconstruction strategy, and use the optimization results to determine the reliability of the unmanned equipment system.

[0035] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the unmanned equipment system reliability optimization method.

[0036] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the unmanned equipment system reliability optimization method.

[0037] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the unmanned equipment system reliability optimization method.

[0038] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0039] This application provides a reliability optimization method, equipment, medium and product for unmanned equipment system. By constructing a heterogeneous network model of the unmanned equipment system, simulating the complex relationship between different types of nodes and connections in the unmanned equipment system, and using the SobolSobol sensitivity analysis method, the key parameters that affect the reliability of the system are deeply explored; and a dynamic reconstruction strategy including intra-chain reconstruction, inter-chain reconstruction and node self-repair is constructed to deal with different environments and attacks from the other party; the dynamic reconstruction strategy is integrated and optimized through the sensitivity analysis results to further improve the robustness and adaptability of the unmanned equipment system. This application can improve the robustness of the unmanned equipment system when it is attacked and its adaptability in a dynamically changing environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 A schematic diagram of a process flow of an unmanned equipment system reliability optimization method in one embodiment of the present application;

[0042] Figure 2 is the node degree and frequency histogram;

[0043] Figure 3 It is a schematic diagram of the dynamic reconstruction strategy;

[0044] Figure 4 This is a schematic diagram of the chain reconstruction process;

[0045] Figure 5 This is a schematic diagram of the inter-chain reconstruction process;

[0046] Figure 6 This is a schematic diagram of the node self-repair process;

[0047] Figure 7 A flowchart diagram is used simultaneously for all strategies within a dynamic reconstruction strategy. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0050] In an exemplary embodiment, Figure 1 As shown, a method for optimizing the reliability of an unmanned equipment system is provided, which is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method includes the following S101 to S104. Among them:

[0051] S101, constructing a heterogeneous network model of an unmanned equipment system; the heterogeneous network model is used to simulate different types of nodes in an actual task execution network and simulate the connection probability between nodes; the node is equipment in the unmanned equipment system;

[0052] S101 specifically includes:

[0053] S11, classify the equipment in the unmanned equipment system; the classification results are three categories: reconnaissance equipment S, decision-making equipment D, and influence equipment I, as well as the opponent's target T;

[0054] S12, determining the corresponding transfer matrix and arrival matrix respectively according to the division result;

[0055] The arrival matrix determination process is:

[0056] Determine the adjacent transfer matrix A IJ and the transfer matrix A JK ; Transfer matrix A IJ The arrival node type and transfer matrix A JK The starting node type is the same;

[0057] Through the transfer between adjacent transfer matrices, we can obtain: A II =A IJ ·A JM ·…·A PI ;

[0058] Taking the typical kill chain T→S→D→I→T as an example, we can get the arrival matrix A of T under the kill chain TSDIT: TSDIT for:

[0059] A TSDIT =A TS ·A SD ·A DI ·A IT ;

[0060] S13, determining the number of kill chains in the unmanned equipment system according to the arrival matrix.

[0061] Taking the typical kill chain T→S→D→I→T as an example, the number of kill chains of T under the kill chain TSDIT is:

[0062]

[0063] The number N of the kill chain of the unmanned equipment system is expressed as:

[0064] N=N TTSDIT +N TSSDIT +N TDDID +N TSSDDIT +N TSDSDIT +N TSSDSDIT +N TSDDSDIT ;

[0065] S102, using the Sobol sensitivity analysis method to perform sensitivity analysis on key parameters of the heterogeneous network model of the unmanned equipment system; the key parameters include: the number of nodes, the probability of node connection, and the number of node edges;

[0066] The Sobol sensitivity analysis method was proposed by Russian mathematician Ilya M. Sobol and is an effective tool for comprehensively analyzing the impact of parameters on model output. Its main advantage is that it can decompose the total effect sensitivity into the sum of first-order, second-order and higher-order effects, thereby more comprehensively analyzing the impact of parameters on model output. The Sobol sensitivity analysis method is widely used in modeling and optimization in engineering, science, finance and other fields. It is the most commonly used sensitivity analysis method today and can effectively determine the factors that have the greatest impact on the model or have strong interactions. Therefore, the Sobol sensitivity analysis method can be used to obtain the most influential variables among the various variables of the network reliability of the unmanned equipment system to perform tasks, and provide a strong guarantee for the subsequent reliability optimization strategy.

[0067] S102 specifically includes:

[0068] S21, determine the value range and number of values ​​corresponding to the key parameters of each partition result; among them, the number of S nodes is set to [10, 20], the number of D nodes is set to [1, 10], the number of I nodes is set to [5, 15], and the number of T nodes is set to [5, 15]. The node connection probability fluctuates up and down [-0.1, 0.1] according to the node connection probability in the heterogeneous network model with 40 nodes generated previously. The number of edges connected to the node is based on Figure 2 The distribution histogram of the node degree is set to [10, 20];

[0069] S22, according to the value range and value number corresponding to the key parameter of each partition result, using the Sobol sequence generation function to determine the corresponding random value;

[0070] S23, according to the value range and value number corresponding to the key parameter of each partition result and the corresponding random value, using the reliability function, determine the reliability index of the heterogeneous network model;

[0071] The reliability function R(i+1) is:

[0072]

[0073] Among them, A temp is the adjacency matrix, exp(A temp ) ij is the sum of the non-zero elements in the adjacency matrix index, i and j are nodes, and n is the total number of nodes.

[0074] For each node i, generate a temporary adjacency matrix A temp , the adjacency matrix A temp The original adjacency matrix A is obtained by deleting the i-th node and its related edges; check the adjacency matrix A temp Is the heterogeneous network model still connected? If not, the reliability value remains unchanged from the current node i and the loop is exited. If connected, the reliability value remains unchanged according to the formula Determine reliability indicators.

[0075] S24, sorting the values ​​of each reliability index according to size, and determining an average value of the number of kill chains corresponding to each reliability index;

[0076] S25, determine the influence of each reliability indicator on the reliability of the heterogeneous network model according to the average value of the number of kill chains corresponding to each reliability indicator and the change of each reliability indicator, and determine the corresponding Sobol index, and then sort according to the Sobol index to obtain the sensitivity analysis result.

[0077] The output results of the variables of the number of nodes in the unmanned equipment system mission execution network are shown in Table 1:

[0078] Table 1

[0079] Node Type S D I T Total Impact Sobol Index 0.7818 0.2680 0.3113 0.2060 0.5422

[0080] As shown in Table 1, the sensitivity ranking of different types of node numbers is: N S >N 总 >N I >N D >N T ,Therefore, the number of reconnaissance (S) nodes has the greatest impact on the reliability level of the network for unmanned equipment system to perform tasks.

[0081] The output results of the connection probability of various nodes in the unmanned equipment system mission network are shown in Table 2:

[0082] Table 2

[0083] Connection probability of different types of nodes Sobol Index <![CDATA[P SS ]]> 0.2892 <![CDATA[P SD ]]> 0.3688 <![CDATA[P DS ]]> 0.1155 <![CDATA[P DD ]]> 0.2039 <![CDATA[P DI ]]> 0.3945 <![CDATA[P IT ]]> 0.3742 <![CDATA[P TS ]]> 0.3655 Total Impact 0.2691

[0084] As shown in Table 2, the connection probability sensitivity ranking of different types of nodes is: DI >P IT >P SD >P TS >P SS >P 总 >P DD >P DS Therefore, the connection probability between decision-making (D) nodes and influencing (I) nodes has the second greatest impact on the reliability of the unmanned equipment system's mission execution network.

[0085] The output results of the number of edges connected to various nodes in the unmanned equipment system execution task network are shown in Table 3:

[0086] Table 3

[0087] Number of edges between different types of nodes Sobol Index <![CDATA[N SS ]]> 0.0801 <![CDATA[N SD ]]> 0.0475 <![CDATA[N DS ]]> 0.0228 <![CDATA[N DD ]]> 0.0306 <![CDATA[N DI ]]> 0.0349 <![CDATA[N IT ]]> 0.0185 <![CDATA[N TS ]]> 0.0312 Total Impact 0.0433

[0088] As shown in Table 3, the sensitivity ranking of the number of edges connecting different types of nodes is: SS >N SD >N 总 >N DI >N TS >N DD >N DS >N IT Therefore, the number of edges between the impact class (I) nodes and the target class (T) nodes has the least impact on the reliability of the unmanned equipment system's mission execution network.

[0089] S103, construct a dynamic reconstruction strategy; Figure 3As shown, the dynamic reconstruction strategy includes: intra-chain reconstruction, inter-chain reconstruction and node self-repair; the intra-chain reconstruction means that when a node of the unmanned equipment system fails, the failed node is replaced by a node of the same type in the same kill chain; the inter-chain reconstruction means that when a node of the unmanned equipment system fails, the failed node is replaced by a node of the same type in a different kill chain; the node self-repair means that when a node of the unmanned equipment system fails, the kill chain is restored by adding a new identical node or repairing the failed node;

[0090] Reconstruction strategy 1 (reconstruction within the chain): When the node of the unmanned equipment system fails, the node of the same type in the same kill chain can be replaced. Reconstruction strategy 1 can reduce the performance of the kill chain and continue to maintain the original working state. There are fewer ways to attack the target node, and the reliability is reduced. The specific process of reconstruction strategy 1 is as follows Figure 4 As shown;

[0091] Reconstruction Strategy 2 (Inter-chain Reconstruction): When the node of the unmanned equipment system fails, the nodes of the same type in other kill chains can be replaced. Reconstruction Strategy 2 can reduce the performance of the kill chain and still maintain the original working state. The reliability of the target node is reduced. The priority of Reconstruction Strategy 2 is lower than that of Reconstruction Strategy 1. The specific process of Reconstruction Strategy 2 is as follows: Figure 5 As shown;

[0092] Reconstruction strategy 3 (node ​​self-repair): When a node in the unmanned equipment system fails, the kill chain can be restored by adding a new identical node or repairing the failed node. Reconstruction strategy 3 can restore the original unmanned equipment system mission execution network to its original perfect state, thereby increasing the cost and materials required. The specific process of reconstruction strategy 3 is as follows Figure 6 As shown;

[0093] When testing the reconstruction algorithm, the reliability of the original heterogeneous network model of reconstruction strategy 1 was 0.14286. After adding dynamic reconstruction with reconstruction strategy 1, the reliability of the network model by replacing the same nodes in the same kill chain was increased to 0.62417; after adding dynamic reconstruction with reconstruction strategy 2, the reliability of the heterogeneous network model by replacing the same type of nodes in other kill chains was reduced to 0.1229; after adding dynamic reconstruction with reconstruction strategy 3, the reliability of the heterogeneous network model by adding or repairing new nodes was increased to 0.1920.

[0094] like Figure 7 As shown, when considering the impact of the simultaneous use of three reconstruction strategies on reliability, the three dynamic reconstruction strategies are merged into one, and then each kill chain is reconstructed to obtain a new heterogeneous network model, and the impact on network reliability is calculated.

[0095] The output results show that the reliability of the original network model is 0.14286. After adding three reconstruction strategies, the reliability of the network model is improved to 0.71429.

[0096] The final conclusion is shown in the data in Table 4. When the three dynamic reconstruction strategies are used simultaneously, the optimization effect on the network reliability of the unmanned equipment system to perform tasks is the best. It can be obtained that: three reconstruction strategies > reconstruction strategy 1 > reconstruction strategy 3 > reconstruction strategy 2.

[0097] Table 4

[0098]

[0099] S104, integrating and optimizing the sensitivity analysis results with the dynamic reconstruction strategy, and using the optimization results to determine the reliability of the unmanned equipment system.

[0100] S104 specifically includes:

[0101] Determine the proportion of effective kill chains in heterogeneous network models;

[0102] When the attack strategy of randomly deleting nodes is carried out, a dynamic reconstruction strategy is adopted to redetermine the effective kill chain ratio in the heterogeneous network model.

[0103] In an exemplary embodiment, for reconstruction strategy 1, priority is given to increasing the number of nodes to improve network reliability. At the same time, since the node connection probability has the second greatest impact on network reliability, when selecting replacement nodes, priority is given to increasing the number of nodes to reduce the impact of reconstruction on network links. The specific optimization scheme is as follows:

[0104] Increase the number of nodes: Consider increasing the number of nodes on the basis of the original network, such as increasing the number of nodes by 10% or 20%. When increasing the number of nodes, it is also necessary to consider the connectivity of the network to ensure that the newly added nodes can be fully utilized and improve the reliability of the network;

[0105] Select replacement nodes: When replacing nodes, give priority to nodes with the same node connection probability to reduce the impact of reconstruction on network links. At the same time, it is necessary to ensure that the replaced nodes can maintain the connectivity and stability of the network;

[0106] In an exemplary embodiment, for reconstruction strategy 2, priority is given to increasing the number of nodes to improve network reliability. Since the node connection probability has little impact on network reliability, when selecting replacement nodes, priority is given to increasing the number of nodes. The specific optimization scheme is as follows:

[0107] Increase the number of nodes: Consider increasing the number of nodes on the basis of the original network, such as increasing the number of nodes by 10% or 20%. When increasing the number of nodes, it is also necessary to consider the connectivity of the network to ensure that the newly added nodes can be fully utilized and improve the reliability of the network;

[0108] Select replacement nodes: When replacing nodes, give priority to increasing the number of nodes to reduce the impact of reconstruction on network links. At the same time, it is necessary to ensure that the replaced nodes can maintain the connectivity and stability of the network;

[0109] In an exemplary embodiment, for reconstruction strategy 3, different optimization schemes are used to optimize the addition of new nodes and the repair of failed nodes. The specific optimization schemes are as follows:

[0110] Adding new nodes: When adding new nodes, give priority to adding nodes with the same node connection probability to maintain the stability of the network. At the same time, the connectivity of the network needs to be considered to ensure that the newly added nodes can be fully utilized to improve the reliability of the network;

[0111] Repair of failed nodes: When repairing failed nodes, priority is given to nodes with a higher probability of node connection to minimize the impact on network connectivity. At the same time, it is necessary to ensure that the replaced nodes can maintain network connectivity and stability.

[0112] This application constructs a heterogeneous network model that can more realistically simulate the complex interactions of different types of nodes in the unmanned equipment system; the Sobol sensitivity analysis method is used to identify the key parameters that have the greatest impact on the reliability of the unmanned equipment system, providing a scientific basis for subsequent reconstruction strategies. The dynamic reconstruction strategy enables the unmanned equipment system to quickly restore its combat capability when it suffers an external attack or internal failure, significantly improving the reliability of the system. The reconstruction strategy is optimized based on the Sobol sensitivity analysis, further improving the execution efficiency of the strategy and the adaptability of the system. This application can improve the reliability and effectiveness of the unmanned equipment system in complex environments.

[0113] Based on the same inventive concept, the embodiment of the present application also provides an unmanned equipment system reliability optimization device for implementing the unmanned equipment system reliability optimization method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more unmanned equipment system reliability optimization device embodiments provided below can refer to the limitations of the unmanned equipment system reliability optimization method above, and will not be repeated here.

[0114] In an exemplary embodiment, a device for optimizing the reliability of an unmanned equipment system is provided, comprising:

[0115] A heterogeneous network model building module is used to build a heterogeneous network model of an unmanned equipment system; the heterogeneous network model is used to simulate different types of nodes in an actual task execution network and simulate the connection probability between nodes; the node is the equipment in the unmanned equipment system;

[0116] A sensitivity analysis module is used to perform sensitivity analysis on key parameters of the heterogeneous network model of the unmanned equipment system using the Sobol sensitivity analysis method; the key parameters include: the number of nodes, the probability of node connection and the number of node edges;

[0117] A dynamic reconstruction strategy construction module is used to construct a dynamic reconstruction strategy; the dynamic reconstruction strategy includes: intra-chain reconstruction, inter-chain reconstruction and node self-repair; the intra-chain reconstruction means that when a node of the unmanned equipment system fails, the failed node is replaced by a node of the same type in the same kill chain; the inter-chain reconstruction means that when a node of the unmanned equipment system fails, the failed node is replaced by a node of the same type in a different kill chain; the node self-repair means that when a node of the unmanned equipment system fails, the kill chain is restored by adding a new identical node or repairing the failed node;

[0118] The optimization module is used to integrate and optimize the sensitivity analysis results with the dynamic reconstruction strategy, and use the optimization results to determine the reliability of the unmanned equipment system.

[0119] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a reliability optimization method for an unmanned equipment system is implemented.

[0120] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0121] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0122] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0123] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0124] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0125] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0126] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A reliability optimization method for an unmanned equipment system, characterized in that: The unmanned equipment system reliability optimization method comprises: Constructing a heterogeneous network model of an unmanned equipment system; the heterogeneous network model is used to simulate different types of nodes in an actual task execution network and simulate the connection probability between nodes; the nodes are equipment in the unmanned equipment system; The Sobol sensitivity analysis method is used to conduct sensitivity analysis on the key parameters of the heterogeneous network model of the unmanned equipment system; the key parameters include: the number of nodes, the probability of node connection and the number of node edges; Construct a dynamic reconstruction strategy; the dynamic reconstruction strategy includes: intra-chain reconstruction, inter-chain reconstruction and node self-repair; the intra-chain reconstruction means that when a node of the unmanned equipment system fails, the failed node is replaced by a node of the same type in the same kill chain; the inter-chain reconstruction means that when a node of the unmanned equipment system fails, the failed node is replaced by a node of the same type in a different kill chain; the node self-repair means that when a node of the unmanned equipment system fails, the kill chain is restored by adding a new identical node or repairing the failed node; The sensitivity analysis results are integrated and optimized with the dynamic reconstruction strategy, and the optimization results are used to determine the reliability of the unmanned equipment system.

2. The unmanned equipment system reliability optimization method according to claim 1, characterized in that: The heterogeneous network model for constructing the unmanned equipment system specifically includes: Divide the equipment in the unmanned equipment system; According to the division results, the corresponding transfer matrix and arrival matrix are determined respectively; Determine the number of kill chains in the unmanned equipment system based on the arrival matrix.

3. The unmanned equipment system reliability optimization method according to claim 2, characterized in that: The Sobol sensitivity analysis method is used to perform sensitivity analysis on key parameters of the heterogeneous network model of the unmanned equipment system, specifically including: Determine the value range and number of values ​​corresponding to the key parameters of each partition result; According to the value range and number of the key parameters of each partition result, the Sobol sequence generation function is used to determine the corresponding random value; According to the value range and value number corresponding to the key parameters of each partition result and the corresponding random value, the reliability function is used to determine the reliability index of the heterogeneous network model; Determine the average number of kill chains corresponding to each reliability indicator; According to the average value of the number of kill chains corresponding to each reliability indicator and the change of each reliability indicator, the influence of each reliability indicator on the reliability of the heterogeneous network model is determined, and the corresponding Sobol index is determined. Then, the Sobol index is sorted to obtain the sensitivity analysis results.

4. The unmanned equipment system reliability optimization method according to claim 1, characterized in that: The reliability function R(i+1) is: Among them, A temp is the adjacency matrix, exp(A temp ) ij is the sum of the non-zero elements in the adjacency matrix index, i and j are nodes, and n is the total number of nodes.

5. The unmanned equipment system reliability optimization method according to claim 1, characterized in that: In the node self-repair, failed nodes with a high node connection probability are repaired.

6. The unmanned equipment system reliability optimization method according to claim 1, characterized in that: The sensitivity analysis results are integrated and optimized with the dynamic reconstruction strategy, and the reliability of the unmanned equipment system is determined by using the optimization results, specifically including: Determine the proportion of effective kill chains in heterogeneous network models; When the attack strategy of randomly deleting nodes is carried out, a dynamic reconstruction strategy is adopted to redetermine the effective kill chain ratio in the heterogeneous network model.

7. An unmanned equipment system reliability optimization device, characterized in that: The unmanned equipment system reliability optimization equipment includes: A heterogeneous network model building module is used to build a heterogeneous network model of an unmanned equipment system; the heterogeneous network model is used to simulate different types of nodes in an actual task execution network and simulate the connection probability between nodes; the node is the equipment in the unmanned equipment system; A sensitivity analysis module is used to perform sensitivity analysis on key parameters of the heterogeneous network model of the unmanned equipment system using the Sobol sensitivity analysis method; the key parameters include: the number of nodes, the probability of node connection and the number of node edges; A dynamic reconstruction strategy construction module is used to construct a dynamic reconstruction strategy; the dynamic reconstruction strategy includes: intra-chain reconstruction, inter-chain reconstruction and node self-repair; the intra-chain reconstruction means that when a node of the unmanned equipment system fails, the failed node is replaced by a node of the same type in the same kill chain; the inter-chain reconstruction means that when a node of the unmanned equipment system fails, the failed node is replaced by a node of the same type in a different kill chain; the node self-repair means that when a node of the unmanned equipment system fails, the kill chain is restored by adding a new identical node or repairing the failed node; The optimization module is used to integrate and optimize the sensitivity analysis results with the dynamic reconstruction strategy, and use the optimization results to determine the reliability of the unmanned equipment system.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the unmanned equipment system reliability optimization method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the unmanned equipment system reliability optimization method described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the unmanned equipment system reliability optimization method described in any one of claims 1 to 6 is implemented.

Images