Unmanned system cluster task importance analysis method based on task reliability

Abstract

The invention provides an unmanned system cluster task importance analysis method based on task reliability. The method comprises the following steps: constructing a task scene through unmanned system cluster constituent elements; based on the task scene, performing task reliability calculation according to the unmanned system cluster constituent elements to obtain an unmanned system cluster task reliability model; performing importance calculation on the unmanned system cluster task reliability model through an equipment state and a cluster killing chain to obtain an unmanned system cluster task importance analysis model; and performing maintenance optimization sorting according to the unmanned system cluster task reliability model and the unmanned system cluster task importance analysis model to obtain an unmanned system cluster optimization strategy. According to the method, reliability and importance analysis is carried out on the unmanned system cluster, and key task node identification and maintenance priority ranking are realized, so that the task execution flexibility, robustness and cost effectiveness of the unmanned system are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of unmanned swarm maintenance and optimization technology, and in particular to a method for analyzing the importance of unmanned system swarm tasks based on task reliability. Background Technology

[0002] In recent years, unmanned system swarm technology has developed rapidly, demonstrating enormous potential in military reconnaissance, coordinated strikes, electronic warfare, and civilian applications such as disaster relief and logistics transportation. Its core advantage lies in achieving a swarm intelligence emergent effect of "1+1>2" through distributed collaborative control. While the emergent nature of unmanned system swarms can play a crucial role, identifying key equipment and optimizing the recovery sequence of faulty equipment under limited resources is particularly important to ensure and improve the overall lethality of the swarm and guarantee the timely recovery of critical systems, thereby enhancing the overall capability of the unmanned system swarm.

[0003] However, as the cluster size increases and task complexity grows, system reliability faces severe challenges. The failure of a single node can lead to a cascading effect, causing a precipitous drop in the overall cluster performance. In dynamic adversarial environments, traditional uniform redundancy strategies waste resources and fail to ensure the continuous operation of critical functions. Furthermore, the lack of quantitative assessment of task-level reliability makes it difficult to accurately identify key subsystems that have a decisive impact on the overall cluster's lethality. Therefore, designing a task importance analysis method for unmanned system clusters based on task reliability is essential. Summary of the Invention

[0004] The purpose of this invention is to provide a method for analyzing the importance of unmanned system clusters based on task reliability. By performing reliability and importance analysis on unmanned system clusters, the method can identify key task nodes and prioritize their maintenance, thereby improving the flexibility, robustness, and cost-effectiveness of unmanned system task execution.

[0005] To achieve the above objectives, the present invention provides the following solution: A method for analyzing the importance of unmanned system cluster tasks based on task reliability includes the following steps: The mission scenario is constructed by the constituent elements of an unmanned system cluster; the constituent elements of an unmanned system cluster include: a cluster of equipment, a set of equipment fault parameters, a set of equipment attributes, and a set of target information. Based on the mission scenario, the mission reliability is calculated according to the constituent elements of the unmanned system cluster, and a mission reliability model of the unmanned system cluster is obtained. The importance of the unmanned system cluster mission reliability model is calculated by considering equipment status and cluster kill chain, thus obtaining the unmanned system cluster mission importance analysis model. Based on the unmanned system cluster task reliability model and the unmanned system cluster task importance analysis model, maintenance optimization is prioritized to obtain the unmanned system cluster optimization strategy.

[0006] Optionally, the task scenario can be constructed using the constituent elements of an unmanned system cluster, including: Construct clustered equipment sets based on different equipment types; Construct a set of equipment failure parameters based on the failure rates of different equipment types; Construct equipment attribute sets based on the attributes of different equipment types; Construct a target information set; The task scenario is constructed based on the cluster equipment set, equipment fault parameter set, equipment attribute set, and target information set.

[0007] Optionally, based on the mission scenario, mission reliability is calculated according to the constituent elements of the unmanned system cluster to obtain an unmanned system cluster mission reliability model, including: The number of effective kill chains is calculated based on the set of equipment attributes. The total number of kill chains is calculated based on the number of effective kill chains; The number of missions completed is calculated based on the number of effective kill chains. The task completion rate is calculated based on the number of tasks completed. A reliability model for unmanned system cluster tasks is constructed based on the number of effective kill chains, the total number of kill chains, the number of completed tasks, and the task completion rate.

[0008] Optionally, the importance of the unmanned system swarm mission reliability model is calculated based on equipment status and swarm kill chain to obtain an unmanned system swarm mission importance analysis model, including: The cluster kill chain effect of the equipment in its normal state is calculated based on the set of equipment attributes. The cluster kill chain effect of equipment failure status is calculated based on the set of equipment attributes. Preset the initial kill chain count; An analysis model for the importance of unmanned system cluster missions is constructed based on the initial number of kill chains and the impact of cluster kill chains under normal and faulty equipment conditions.

[0009] Optionally, maintenance optimization is prioritized based on the unmanned system cluster task reliability model and the unmanned system cluster task importance analysis model to obtain unmanned system cluster optimization strategies, including: An initial cluster network is generated based on the set of equipment attributes; Determine the failed nodes in the initial cluster network based on the set of equipment failure parameters; The task importance of the failed node is calculated based on the task importance analysis model of the unmanned system cluster. The importance of tasks is ranked, and an optimization strategy for unmanned system clusters is generated based on the ranking results.

[0010] According to specific embodiments of the present invention, the following technical effects are disclosed: The present invention provides a method for analyzing the importance of unmanned system cluster tasks based on task reliability. This method includes: constructing a task scenario using the constituent elements of the unmanned system cluster; the constituent elements of the unmanned system cluster include: a set of cluster equipment, a set of equipment fault parameters, a set of equipment attributes, and a set of target information; based on the task scenario, calculating task reliability according to the constituent elements of the unmanned system cluster to obtain a task reliability model for the unmanned system cluster; calculating the importance of the task reliability model of the unmanned system cluster using equipment status and cluster kill chains to obtain a task importance analysis model for the unmanned system cluster; and performing maintenance optimization ranking based on the task reliability model and the task importance analysis model of the unmanned system cluster to obtain an optimization strategy for the unmanned system cluster. This method, by performing reliability and importance analysis on the unmanned system cluster, achieves the identification of key task nodes and the ranking of maintenance priorities, thereby significantly improving the flexibility, robustness, and cost-effectiveness of unmanned system task execution. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, 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.

[0012] Figure 1 This is a flowchart of the unmanned system cluster task importance analysis method of the present invention; Figure 2 This is a cross-sectional view of an unmanned system cluster task according to an embodiment of the present invention; Figure 3 This is a graph showing the time-varying trend of the OODA ring of the unmanned system cluster according to an embodiment of the present invention. Figure 4 This is a graph showing the time-varying reliability of the unmanned system cluster task according to an embodiment of the present invention. Figure 5 This is a sequence diagram of the recovery order of an unmanned system cluster based on importance, according to an embodiment of the present invention. Detailed Implementation

[0013] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0014] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0015] like Figure 1 As shown, this invention provides a method for analyzing the importance of unmanned system cluster tasks based on task reliability, comprising the following steps: Step 100: Construct the mission scenario using the constituent elements of an unmanned system cluster; the constituent elements of an unmanned system cluster include: a set of cluster equipment, a set of equipment fault parameters, a set of equipment attributes, and a set of target information; specific steps include: To configure the cluster equipment composition, a cluster equipment set is constructed based on different equipment types, and the expression is: ;in, Indicates a collection of clustered equipment. Indicates the first A reconnaissance device, Indicates the first A decision-making tool, Indicates the first A strike weapon.

[0016] Set the fault parameters for all equipment, and construct a set of equipment fault parameters based on the fault rates of different equipment types. The expression is: ;in, This represents the set of equipment fault parameters. Indicates the first The failure rate of individual reconnaissance equipment, Indicates the first The failure rate of decision-making equipment. Indicates the first The failure rate of individual strike equipment.

[0017] Set the attributes of all equipment, and construct a set of equipment attributes based on the attributes of different equipment types. The expression is: ; ; in, Represents the set of equipment attributes. Indicates the first The attributes of a reconnaissance device, Indicates the first The attributes of a decision-making device. Indicates the first The attributes of each combat equipment.

[0018] Set the target information to construct a target information set, the expression is: ;in, Represents the target information set. Indicates the first Information about each target. Finally, the cluster equipment set, equipment fault parameter set, equipment attribute set, and target information set are integrated to obtain the mission scenario.

[0019] Step 200: Based on the task scenario, perform task reliability calculations according to the constituent elements of the unmanned system cluster to obtain the unmanned system cluster task reliability model; specific steps include: The number of effective kill chains for a mission by an unmanned system cluster is calculated based on the set of equipment attributes, expressed as follows: ;in, Indicates in At any time, targeting The number of kill chains, Indicates the node to be attacked For the target To strike, This represents the set of neighboring nodes that the decision node attacks. This represents the set of decision-making neighbor nodes of the scout node. Indicates target discovery The set of reconnaissance nodes Indicates the node to be attacked For the target When striking The value is 1.

[0020] The total number of kill chains in the unmanned system cluster is calculated based on the number of effective kill chains, expressed as: ;in, Indicates in The total number of kill chains in the kill network formed by the entire unmanned swarm at that moment.

[0021] The number of tasks completed by the unmanned system cluster is calculated based on the number of effective kill chains, expressed as follows: ;in, Indicates in The number of tasks completed at any given time. This indicates the timeline from investigation to decision-making to strike. less than the threshold time hour The value is 1. Indicates duration of strike Attack time exceeding the threshold hour The value is 1. Indicates the number of kill chains Number greater than the threshold hour The value is 1.

[0022] The task completion rate of the unmanned system cluster is calculated based on the number of tasks completed, and the expression is: ;in, Indicates in Current task completion rate This indicates the total number of times the task was executed.

[0023] Finally, by integrating the number of effective kill chains, the total number of kill chains, the number of completed tasks, and the task completion rate, a reliability model for unmanned system cluster tasks is obtained. The expression of this model is: ; ; in, Indicates unmanned system clusters in Real-time task reliability Indicates the first During the next task execution Successfully execute tasks at all times. This indicates the total number of times the task was executed. Indicates the first During the next task execution When the number of successfully executed tasks is greater than 1 .

[0024] Step 300: Calculate the importance of the unmanned system swarm mission reliability model based on equipment status and swarm kill chain to obtain the unmanned system swarm mission importance analysis model; specific steps include: The impact of equipment on the cluster kill chain under normal conditions is calculated based on the set of equipment attributes, and the expression is: , ; The impact of equipment failure on the cluster kill chain is calculated based on the set of equipment attributes, and the expression is: , ; The initial kill chain count is preset, expressed as: ; Finally, by integrating the initial kill chain count with the cluster kill chain impact under both normal and faulty equipment conditions, a task importance analysis model for unmanned system clusters is obtained. The expression for this model is: ; in, Indicates equipment exist Reliability observations at time 10:00 Indicates equipment exist At any given time, the task is performed under normal conditions. Task reliability, Indicates equipment exist For tasks under fault conditions at all times Task reliability, Indicates equipment exist The current time represents the number of kill chains in the cluster under normal conditions. Indicates the initial number of kill chains in the cluster. Indicates equipment exist The equipment here represents the number of kill chains in a faulty cluster. It represents various types of equipment.

[0025] Step 400: Based on the unmanned system cluster task reliability model and the unmanned system cluster task importance analysis model, perform maintenance optimization ranking to obtain the unmanned system cluster optimization strategy. The specific steps are as follows: First, generate an initial cluster network based on equipment node attributes; then, determine whether some nodes have failed based on the equipment failure rate; next, calculate the task importance of failed nodes and rank them by importance; finally, under available maintenance resources, perform maintenance on nodes with high task importance and generate optimization strategies. In some embodiments, the implementation process is as follows: This invention also provides a specific embodiment, the mission scenario of which is a reconnaissance, early warning, and strike scenario of a maritime unmanned system swarm against low, small, and slow-moving aerial targets. The maritime unmanned system swarm consists of a total of 35 pieces of equipment, including 10 small UAVs, 10 large UAVs, 5 small unmanned surface vessels (USVs), 3 large USVs, and 2 command centers. The components of these unmanned systems mainly include early warning and detection equipment, communication equipment, navigation equipment, mission payload equipment, and intelligent control equipment. The operational element parameter settings of the unmanned system swarm are shown in Table 1. Table 1. Parameter Settings for Unmanned System Cluster Combat Elements Based on the composition and mission requirements of unmanned system cluster equipment, the following results are obtained: Figure 2The task profile shown. Then, as... Figure 3 The trend of OODA loop number over time is obtained based on changes in equipment status and connection relationships. Then, as shown... Figure 4 The number of kill chains formed against the target is calculated, and the trend of unmanned system cluster mission reliability over time is obtained by comparing the number of effective kill chains with the target threshold number.

[0026] Depend on Figure 5 It is evident that in the initial stage, equipment failures cause numerous effective kill chains to fail, resulting in a significant decrease in the number of enemy targets the cluster can engage. Random failures have the least impact on mission reliability. In contrast, deliberate attacks have a greater impact on mission reliability. When random failures and deliberate attacks occur simultaneously, the cluster's mission reliability drops rapidly. For example, when time equals 100, mission reliability almost drops to zero. Specifically, when time exceeds 60, the rate of decrease in mission reliability slows down. This slowing down can be explained by the fact that at the beginning of the mission, the cluster contains a large number of nodes, each equipped with various devices such as detection, decision-making, and attack equipment, resulting in strong mission completion capabilities. However, when some nodes fail, mission effectiveness drops significantly. In the later stages, due to the substantial reduction in the number of nodes—for example, only four devices remain to cooperate in attacking a single target, with the remaining devices no longer cooperating—failures of additional nodes have little impact on mission completion capabilities. At this point, the rate of decrease in mission reliability slows down.

[0027] In summary, mission reliability rapidly declines under the combined effects of random failures and deliberate attacks (without optimization strategies), and the rate of decline slows down after the number of nodes decreases to a certain level. This is because as the number of nodes decreases, the failure of the remaining nodes has a smaller impact on the overall mission completion capability. Therefore, it is necessary to prioritize equipment repair based on its importance to optimize mission reliability.

[0028] The construction process of the unmanned system swarm mission importance analysis model in this embodiment is as follows: Taking a typical unmanned system swarm as an example, the equipment importance during the mission process is analyzed. The number of reconnaissance nodes, decision-making nodes, attack nodes, and target nodes are 94, 5, 195, and 60, respectively. The simulation time is set to 100 seconds, and the number of simulations is 1000. The equipment importance at a certain moment is shown in Table 2. Table 2 Ranking of Importance of Unmanned System Cluster Equipment As shown in Table 2, at this point in time, the decision-making equipment is more important than other equipment. For equipment that fails at this point, maintenance should be carried out sequentially from top to bottom based on equipment importance. The maintenance order is as follows: .

[0029] The unmanned system cluster optimization strategy generation process in this embodiment is as follows: Under the condition of limited maintenance resources, the recovery effect of the unmanned system cluster based on the maintenance priority strategy of importance is experimentally analyzed, and the equipment maintenance recovery order at each time point is shown in Table 3. Table 3 Equipment Maintenance Sequence Based on Importance The maintenance priority based on importance affects the recovery results of unmanned system clusters, as follows: Figure 5 As shown in the figure, the horizontal axis represents time, and the vertical axis represents task reliability. Experiments compared the recovery effects under scenarios of unreconstructed random failure and deliberate attack. The results show that the system task reliability is significantly improved after adopting an importance-based recovery optimization strategy. Specifically, as time progresses, this strategy can quickly identify critical nodes and prioritize their repair, enabling the system reliability to recover to a high level in a shorter time. In contrast, traditional methods suffer from low recovery efficiency due to uneven resource allocation. This result verifies the effectiveness of importance assessment in optimizing maintenance resource allocation and provides theoretical support for enhancing the reliability of unmanned system clusters.

[0030] The beneficial effects of this invention are as follows: 1) By constructing a kill chain-based mission reliability model and mission importance analysis model, the impact of each equipment node on the overall mission completion capability can be quantitatively evaluated, thereby accurately identifying the key equipment that has the greatest impact on the cluster mission efficiency. 2) Under the condition of limited maintenance resources, faulty equipment is prioritized based on the importance of the task, and the equipment with the greatest impact on the reliability of the task is repaired first, which avoids waste of resources and significantly improves maintenance efficiency and system recovery speed. 3) By dynamically assessing the impact of equipment status changes on mission completion and combining this with time constraints (such as OODA loop time, strike duration, etc.), the cluster's mission reliability and continuous combat capability in complex environments have been effectively improved. 4) It can quickly reconstruct the kill chain in the event of equipment failure or mission time change, thereby maintaining the overall combat effectiveness of the cluster, and is especially suitable for combat scenarios with strong confrontation and changeable environment.

[0031] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0032] Specific examples have been used to illustrate the principles and implementation methods of this invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this invention. Furthermore, those skilled in the art will recognize that, based on the ideas of this invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this invention.

Claims

1.A method for analyzing importance of a task of a cluster of unmanned systems based on reliability of the task, characterized in that, The method comprises the following steps: A task scene is constructed by using unmanned system cluster elements, which include a cluster equipment set, an equipment failure parameter set, an equipment attribute set, and a target information set; Based on the task scene, task reliability is calculated according to the unmanned system cluster elements, and an unmanned system cluster task reliability model is obtained; Importance of the unmanned system cluster task reliability model is calculated by using equipment states and cluster kill chains, and an unmanned system cluster task importance analysis model is obtained; Maintenance optimization sorting is performed according to the unmanned system cluster task reliability model and the unmanned system cluster task importance analysis model, and an unmanned system cluster optimization strategy is obtained. 2.The method of claim 1, wherein, The task scene is constructed by using unmanned system cluster elements, which include: The cluster equipment set is constructed according to different equipment types; The equipment failure parameter set is constructed according to failure rates of different equipment types; The equipment attribute set is constructed according to attributes of different equipment types; The target information set is constructed; The task scene is constructed according to the cluster equipment set, the equipment failure parameter set, the equipment attribute set, and the target information set. 3.The method of claim 1, wherein, Based on the task scene, task reliability is calculated according to the unmanned system cluster elements, and an unmanned system cluster task reliability model is obtained, which includes: The number of effective kill chains is calculated according to the equipment attribute set; The total number of kill chains is calculated according to the number of effective kill chains; The number of task completions is calculated according to the number of effective kill chains; The task completion degree is calculated according to the number of task completions; The unmanned system cluster task reliability model is constructed according to the number of effective kill chains, the total number of kill chains, the number of task completions, and the task completion degree. 4.The method of claim 1, wherein, Importance of the unmanned system cluster task reliability model is calculated by using equipment states and cluster kill chains, and an unmanned system cluster task importance analysis model is obtained, which includes: The cluster kill chain influence of equipment normal state is calculated according to the equipment attribute set; The cluster kill chain influence of equipment failure state is calculated according to the equipment attribute set; The initial number of kill chains is preset; The unmanned system cluster task importance analysis model is constructed according to the initial number of kill chains and the cluster kill chain influences under equipment normal state and equipment failure state. 5.The method of claim 1, wherein, Maintenance optimization sorting is performed according to the unmanned system cluster task reliability model and the unmanned system cluster task importance analysis model, and an unmanned system cluster optimization strategy is obtained, which includes: An initial cluster network is generated according to the equipment attribute set; Invalid nodes in the initial cluster network are determined according to the equipment failure parameter set; Task importance of the invalid nodes is calculated according to the unmanned system cluster task importance analysis model; The task importance is sorted according to importance, and the unmanned system cluster optimization strategy is generated according to the sorting result.

Images