Unmanned equipment system task reliability model construction method based on reconfigurable killing network

Abstract

The invention discloses an unmanned equipment system task reliability model construction method based on a reconfigurable killing net, and relates to the technical field of unmanned combat equipment control, and the method comprises the steps: obtaining battlefield environment data and unmanned equipment state data in real time through multiple types of sensors; constructing a demand analysis layer based on battlefield environment data and unmanned equipment state data, and analyzing task demands; based on the reconfigurable killing network, a task distribution layer is constructed, and dynamic task distribution is carried out; according to task requirements and dynamic task allocation, a task planning layer is constructed, and task planning is formulated in stages; based on the demand analysis layer, the task distribution layer and the task planning layer, a task reliability model is constructed, and the task reliability of different stages is evaluated; and optimizing the task reliability model based on real-time feedback and dynamic adjustment. According to the invention, by constructing the task reliability model, the flexibility, fault tolerance and task success rate of the unmanned equipment system are improved.

Description

Technical Field

[0001] The present invention relates to the field of unmanned combat equipment control technology, and in particular to a method for constructing a mission reliability model of an unmanned equipment system based on a reconfigurable kill network. Background Art

[0002] With the rapid evolution of modern warfare, the role of unmanned equipment on the battlefield is increasing day by day. Unmanned equipment is not only used for traditional reconnaissance and strike missions, but is increasingly used in complex mission scenarios such as coordinated operations and logistics support. These equipment can effectively reduce casualties and improve the efficiency of mission completion through autonomous decision-making and collaboration in a dynamic and complex battlefield environment. With the development of sensor technology, artificial intelligence and communication technology, the intelligence level of modern unmanned equipment has been significantly improved, and it can perceive the environment and its own status in real time and exchange information with other equipment. However, although the current unmanned equipment system has achieved remarkable results in mission execution, there are still many limitations in task allocation and planning. In particular, when dealing with dynamic changes in complex battlefield environments, existing technologies are difficult to provide sufficient flexibility and reliability.

[0003] Most of the existing unmanned equipment task allocation technologies rely on pre-set rules and task plans, and lack the ability to dynamically respond to changes in the real-time battlefield environment and the status of unmanned equipment. When the battlefield situation changes drastically or the equipment status becomes abnormal, the fixed task allocation plan is often difficult to adjust quickly, resulting in unreasonable task allocation, waste of resources or task failure. In addition, the existing technology usually lacks an effective redundancy mechanism when unmanned equipment cooperates in combat. Once some equipment fails, is damaged or communication is interrupted during the execution of the mission, the lack of a flexible task takeover mechanism can easily lead to task interruption or reduced execution efficiency. Especially in high-risk tasks, the continuity and reliability of the task are crucial. The existing technology has failed to fully consider equipment redundancy and task takeover methods, resulting in low stability and success rate of task execution. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method for constructing a mission reliability model of an unmanned equipment system based on a reconfigurable kill network to solve the problems of insufficient flexibility in task allocation and redundant mechanisms in the prior art.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides a method for constructing a task reliability model of an unmanned equipment system based on a reconfigurable kill net, which includes: acquiring battlefield environment data and unmanned equipment status data in real time through multiple types of sensors; constructing a demand analysis layer based on the battlefield environment data and the unmanned equipment status data to analyze task requirements; constructing a task allocation layer based on the reconfigurable kill net to perform dynamic task allocation; constructing a task planning layer according to task requirements and dynamic task allocation, and formulating task plans in stages; constructing a task reliability model based on the demand analysis layer, the task allocation layer and the task planning layer to evaluate the task reliability at different stages; and optimizing the task reliability model based on real-time feedback and dynamic adjustment.

[0008] As a preferred solution of the method for constructing a mission reliability model of an unmanned equipment system based on a reconfigurable kill net according to the present invention, wherein: the battlefield environment data and unmanned equipment status data are obtained in real time through multiple types of sensors, and the specific steps are as follows:

[0009] Obtain battlefield terrain height data through radar;

[0010] Acquire high-resolution image data of battlefield terrain through optical sensors;

[0011] Monitor enemy positions and troop movement data through infrared and sonar sensors;

[0012] Use meteorological sensors to obtain battlefield weather data in real time;

[0013] Utilize the monitoring equipment on the unmanned equipment to obtain the endurance, load status, location and motion trajectory of the unmanned equipment in real time.

[0014] As a preferred solution of the method for constructing a mission reliability model of an unmanned equipment system based on a reconfigurable kill net according to the present invention, wherein: the requirement analysis layer is constructed based on battlefield environment data and unmanned equipment status data to analyze the mission requirements, and the specific steps are as follows:

[0015] Perform geometric correction and orthographic projection on high-resolution image data, and use image processing algorithms to align the corrected high-resolution image with terrain height data;

[0016] By integrating high-resolution image data with terrain height data through image registration, a three-dimensional battlefield model containing both terrain height and surface texture information is generated, and battlefield environmental factors are analyzed based on the three-dimensional battlefield model;

[0017] Through multi-source data fusion, the unmanned equipment status data is integrated with the battlefield environment data in the three-dimensional battlefield model, and the decision support algorithm is used to calculate the task demand index, which is expressed as:

[0018]

[0019] Wherein, T is the mission requirement index, θ is the battlefield slope, V is the battlefield visibility, W is the wind speed in the battlefield, P is the current precipitation in the battlefield, E represents the enemy's threat coefficient, F represents the enemy's firepower coverage, L is the load of the unmanned equipment, B is the remaining power of the unmanned equipment, S is the model strength of the unmanned equipment, and σ is the Sigmoid function;

[0020] Based on resource consumption and historical task success rate, a low demand threshold T is defined respectively. l and high demand threshold T h ;

[0021] When T≤T l When , the current task is considered to be a low-demand task, the current task consumes less resources, and the task success rate is high;

[0022] When T l <T≤T h When , the current task is considered to be a medium-demand task, the current task resource consumption is moderate, and the task success rate is moderate;

[0023] When T>T h When , the current task is considered to be a high-demand task, which requires a large amount of resources and stronger equipment support, and the task success rate is low;

[0024] The battlefield environmental factors include identifying battlefield terrain information, enemy deployment and weather conditions.

[0025] As a preferred solution of the method for constructing a task reliability model of an unmanned equipment system based on a reconfigurable kill net according to the present invention, wherein: based on the reconfigurable kill net, a task allocation layer is constructed to perform dynamic task allocation, and the specific steps are as follows:

[0026] Based on the mission requirements and the status of unmanned equipment, an unmanned equipment collaboration network is constructed with each unmanned equipment as a node and the collaboration relationship between each equipment as an edge.

[0027] Initial unmanned equipment collaborative network configuration based on mission type and unmanned equipment capabilities;

[0028] Identify task priorities by sorting them from high to low urgency;

[0029] Set task allocation rules based on the functions, task priorities and status of the unmanned equipment;

[0030] Convert task requirements into executable subtasks and assign tasks according to task assignment rules;

[0031] When executing a task, a redundant allocation mechanism is introduced to allocate multiple unmanned equipment to perform the same task in advance, and the abnormal status of the unmanned equipment is detected based on the health monitoring mechanism;

[0032] If an unmanned device fails due to an abnormal state, the kill network reconstruction is automatically triggered, and the unmanned device closest to the failed device and with similar functions takes over the unfinished task. At the same time, the collaborative relationship between the unmanned devices is adjusted to rebuild the unmanned device collaborative network.

[0033] The abnormal status of the unmanned equipment includes failure, damage and communication interruption.

[0034] As a preferred solution of the method for constructing a task reliability model of an unmanned equipment system based on a reconfigurable kill network according to the present invention, wherein: according to task requirements and dynamic task allocation, a task planning layer is constructed, and task planning is formulated in stages. The specific steps are as follows:

[0035] According to the task timeline and demand index T, the task is divided into the initial stage, execution stage and closing stage;

[0036] In the initial stage, the mission planning is based on low-demand intelligence collection tasks. Unmanned equipment with reconnaissance functions is dynamically allocated according to mission requirements to perform reconnaissance missions and collect high-resolution images and enemy situation data. The task allocation of reconnaissance equipment is adjusted in real time according to the real-time status of the equipment.

[0037] In the execution phase, mission planning is based on high-demand offensive missions, dynamically allocating resources according to the urgency and importance of the mission, assigning strike missions to missile-equipped drones, and dynamically adjusting mission allocation through redundancy mechanisms;

[0038] In the closing phase, mission planning is based on medium-demand alert missions, and the allocation of remaining resources is dynamically adjusted according to current mission requirements, with priority given to the use of low-power equipment to perform alert missions.

[0039] As a preferred solution of the method for constructing a mission reliability model of an unmanned equipment system based on a reconfigurable kill network according to the present invention, the mission reliability model is constructed based on the demand analysis layer, the task allocation layer and the task planning layer to evaluate the mission reliability at different stages. The specific steps are as follows:

[0040] Combining the three independent functional layers of demand analysis layer, task allocation layer and task planning layer, a task reliability model framework is constructed;

[0041] Embed Monte Carlo simulation and Markov chain model into each independent functional layer in the mission reliability model framework;

[0042] At different stages of task execution, the feedback information obtained from the demand analysis layer, task allocation layer, and task planning layer is integrated. By simulating the Monte Carlo simulation and Markov chain model, a task reliability model is finally constructed to predict the task reliability scores at different stages. The expression is:

[0043]

[0044] Among them, R i (t) is the task reliability score of the i-th stage, T i (t) is the task demand index of stage i, D i (t) is the task allocation efficiency of the i-th stage, S i (t) is the task success rate of stage i, P i (t) is the task planning efficiency of the i-th stage, F i (t) is the equipment failure rate in stage i, E i (t) is the environmental impact factor of the i-th stage, L i (t) is the task load of the i-th stage, t is the time variable, and i is the index variable of the task stage;

[0045] The reliability of tasks is evaluated based on the reliability scores of tasks at different stages. The higher the reliability score of a task, the higher the reliability of the task; the lower the reliability score of a task, the lower the reliability of the task.

[0046] As a preferred solution of the method for constructing a mission reliability model of an unmanned equipment system based on a reconfigurable kill net according to the present invention, the specific steps are as follows:

[0047] Based on the three-dimensional battlefield model, Monte Carlo simulation is used to simulate the task execution process of the unmanned equipment system in different battlefield environments to verify the task success rate. The expression is:

[0048]

[0049] Among them, S i (t) is the task success rate of the i-th stage, k represents the simulation index, is the task demand index of the i-th stage in the k-th simulation, is the task allocation efficiency of the i-th stage in the k-th simulation, The efficiency of task planning for the i-th stage in the k-th simulation, is the environmental impact factor of the i-th stage in the k-th simulation, is the task load pressure of the i-th stage in the k-th simulation, N represents the total number of simulations, and f() represents the task success rate prediction function;

[0050] The Markov chain model is used to simulate the state changes of each unmanned equipment during the mission execution, and the impact of the state change on the mission success rate is analyzed. The probability of equipment failure during the mission execution is evaluated by solving the steady-state distribution of the Markov chain. The expression is:

[0051]

[0052] Among them, F i (t) represents the equipment failure rate in the i-th stage, π j (t) represents the probability that the unmanned equipment is in state j, λ j represents the stability rate of the unmanned equipment in state j, M represents the total number of unmanned equipment states, and t represents the time variable.

[0053] As a preferred solution of the method for constructing a mission reliability model of an unmanned equipment system based on a reconfigurable kill net according to the present invention, the mission reliability model is optimized based on real-time feedback and dynamic adjustment, and the specific steps are as follows:

[0054] Feedback information is delivered to the demand analysis layer, task allocation layer and task planning layer in real time, and the task demand index T is updated in real time. i (t) and mission planning, optimizing the accuracy of mission planning;

[0055] Through real-time collection of battlefield environment data and unmanned equipment status data by multiple types of sensors, the mission requirement index can be dynamically adjusted to improve the accuracy of mission requirement analysis;

[0056] According to the optimized task demand index and the real-time changes in the status of unmanned equipment, the task allocation rules of the allocation layer are dynamically adjusted to optimize the efficiency of task allocation and improve the reliability and efficiency of task execution;

[0057] Based on the optimized task requirements and optimized task allocation efficiency, the task planning is dynamically adjusted to optimize the task execution sequence and phase division in real time to maximize planning efficiency.

[0058] In a second aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: the computer program, when executed by the processor, implements any step of the method for constructing a mission reliability model of an unmanned equipment system based on a reconfigurable kill net as described in the first aspect of the present invention.

[0059] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: the computer program, when executed by a processor, implements any step of the method for constructing a mission reliability model of an unmanned equipment system based on a reconfigurable kill net as described in the first aspect of the present invention.

[0060] The beneficial effects of the present invention are: through the demand analysis layer, the dynamic task allocation layer based on the reconfigurable kill net and the phased task planning layer, the task execution efficiency and reliability of the unmanned equipment system are improved. The demand analysis layer uses multi-source sensor fusion technology to provide accurate battlefield environment and equipment status data; the dynamic task allocation layer is based on the reconfigurable kill net to achieve flexible task allocation and redundancy mechanism to ensure that tasks are not interrupted when equipment fails; the phased task planning layer dynamically adjusts the task execution order according to task requirements and resource conditions. These three layers work together to improve the flexibility, fault tolerance and task success rate of the unmanned equipment system. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0062] Figure 1 Flow chart of the method for constructing a mission reliability model for an unmanned equipment system based on a reconfigurable kill network in Example 1.

[0063] Figure 2 This is a flowchart for constructing a demand analysis layer based on battlefield environment data and unmanned equipment status data in Example 1 to analyze task requirements. DETAILED DESCRIPTION

[0064] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0065] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0066] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0067] Example 1, reference Figure 1 and Figure 2, which is the first embodiment of the present invention, and provides a method for constructing a mission reliability model of an unmanned equipment system based on a reconfigurable kill network, comprising the following steps:

[0068] S1: Obtain battlefield environment data and unmanned equipment status data in real time through multiple types of sensors.

[0069] S1.1: Obtain battlefield terrain height data through radar.

[0070] Furthermore, it provides critical terrain undulation information for mission planning, helping unmanned equipment navigate and deploy in complex terrain.

[0071] S1.2: Obtain high-resolution image data of battlefield terrain through optical sensors.

[0072] Furthermore, in order to provide accurate surface texture and battlefield visual information, it supports comprehensive analysis of battlefield situation.

[0073] S1.3: Monitor enemy position and troop movement data through infrared sensors and sonar sensors.

[0074] Furthermore, the enemy's movements can be grasped in real time, providing accurate intelligence support for mission decisions and strikes.

[0075] S1.4: Use meteorological sensors to obtain battlefield meteorological data in real time.

[0076] Furthermore, meteorological data includes temperature, humidity, wind speed, wind direction, precipitation, air pressure and visibility, etc., in order to help evaluate the impact of weather on mission execution and ensure the normal operation of unmanned equipment under different meteorological conditions.

[0077] S1.5: Use the monitoring equipment on the unmanned equipment to obtain the endurance, load status, location and movement trajectory of the unmanned equipment in real time.

[0078] Furthermore, ensure that the equipment status during mission execution can be controlled and adjusted in a timely manner.

[0079] S2: Based on battlefield environment data and unmanned equipment status data, build a demand analysis layer to analyze mission requirements.

[0080] S2.1: Perform geometric correction and orthographic projection on the high-resolution image data, and use image processing algorithms to align the corrected high-resolution image with the terrain height data.

[0081] For example, geometric correction is used to eliminate image distortion caused by sensor angle, terrain undulations, etc., to ensure that the position of objects in the image is consistent with the actual geographic coordinates; then, orthographic projection is used to convert the image into an image from a vertical overhead perspective to eliminate perspective distortion; then, the image registration algorithm is used to accurately match the corrected high-resolution image with the terrain height data to generate a three-dimensional battlefield model that integrates terrain height and surface texture, which facilitates more accurate analysis of the battlefield environment.

[0082] S2.1: The high-resolution image data is fused with the terrain height data through image registration to generate a three-dimensional battlefield model that includes both terrain height and surface texture information, and the battlefield environmental factors are analyzed based on the three-dimensional battlefield model.

[0083] For example, by accurately aligning high-resolution images with terrain height data through image registration, the generated three-dimensional battlefield model not only contains the height information of the terrain, but also retains the texture details of the surface, such as the distribution of roads, buildings and vegetation. Based on this model, key factors in the battlefield can be analyzed, such as the impact of terrain slope on the travel path of unmanned equipment, the location of potential obstacles, and possible hiding areas of the enemy, thereby providing a more accurate environmental assessment for mission planning.

[0084] S2.3: Through multi-source data fusion, the unmanned equipment status data is integrated with the battlefield environment data in the three-dimensional battlefield model, and the decision support algorithm is used to calculate the task demand index, which is expressed as:

[0085]

[0086] Among them, T is the mission demand index, θ is the battlefield slope, V is the battlefield visibility, W is the wind speed in the battlefield, P is the current precipitation in the battlefield, E represents the enemy's threat coefficient, F represents the enemy's firepower coverage, L is the load of the unmanned equipment, B is the remaining power of the unmanned equipment, S is the model strength of the unmanned equipment, and σ is the Sigmoid function.

[0087] It should be noted that this expression forms a dynamic and adaptive mission requirement index (T) by coupling multi-dimensional battlefield factors with the status of unmanned equipment, while introducing state parameters such as the load, remaining power, and model strength of the unmanned equipment. In particular, by introducing the Sigmoid function, the smoothing of complex nonlinear relationships is achieved, so that the mission requirement index can flexibly respond to changes in different battlefield conditions, equipment status, and enemy threats. This calculation method based on multi-source data fusion not only improves the accuracy of mission requirement assessment, but also has a high degree of environmental adaptability and can adjust mission planning in real time.

[0088] S2.4: Based on resource consumption and historical task success rate, define a low demand threshold T l and high demand threshold T h .

[0089] It should be noted that resource consumption reflects the complexity of the task and the pressure on the equipment, while the historical task success rate uses the execution experience of similar tasks in the past to help predict the success probability of the current task. Combining these two factors can more accurately define the task requirement threshold, optimize resource allocation and improve the task success rate.

[0090] S2.4.1: When T ≤ T l , it is considered that the current task is a low-demand task, the current task consumes less resources, and the task success rate is high.

[0091] For example, when the mission is simple intelligence gathering or low-intensity patrol, T ≤ T l , which means that fewer resources are required and the task conditions are relatively loose, so unmanned equipment can easily complete the task with a higher success rate.

[0092] S2.4.2: When T l <T≤T h When T is , the current task is considered to be a medium-demand task, the current task resource consumption is moderate, and the task success rate is moderate; for example, when the task is to monitor the enemy's movements or perform local fire suppression, T l <T≤T h , which requires moderate resource support, and the task complexity is high but still within a controllable range, so the task success rate is medium.

[0093] S2.4.3: When T>T h , it is considered that the current task is a high-demand task, which requires a large amount of resources and stronger equipment support, and the task success rate is low.

[0094] For example, when the mission is to attack deep into enemy lines or to strike key targets, T>T h , requires a lot of resources and high-performance equipment support, the mission is risky and complex, so the mission success rate is low.

[0095] Battlefield environmental factors include identifying battlefield terrain information, enemy deployment, and weather conditions.

[0096] It should also be noted that through multi-source data fusion, the status data of unmanned equipment is fully integrated with the battlefield environment (including terrain, enemy deployment, meteorological conditions, etc.) to generate a dynamic mission requirement index T, and by introducing nonlinear processing technologies such as Sigmoid function, the unmanned equipment system can flexibly adapt to different battlefield conditions and real-time data changes. In addition, different mission requirement thresholds (low, medium, and high) are defined based on resource consumption and historical mission success rates to make mission planning more accurate. This step improves the success rate and overall effectiveness of mission execution, especially in complex battlefield environments, showing higher adaptability and reliability.

[0097] S3: Based on the reconfigurable kill net, a task allocation layer is constructed to perform dynamic task allocation.

[0098] S3.1: Based on the mission requirements and the status of unmanned equipment, an unmanned equipment collaboration network is constructed with each unmanned equipment as a node and the collaboration relationship between each equipment as an edge.

[0099] It should be noted that the collaborative relationship refers to the mutual cooperation and coordination of unmanned equipment during the execution of tasks through task division, data sharing, path coordination, redundant support and resource scheduling, ensuring that each equipment can complete the task together according to its function and status. This collaboration is achieved through real-time communication and dynamic adjustment, which improves the efficiency and reliability of task execution, especially ensuring that the task is not interrupted in complex battlefield environments.

[0100] S3.2: Initial unmanned equipment collaborative network configuration based on mission type and unmanned equipment capabilities.

[0101] Furthermore, configuring a collaborative network based on the type of mission and the function of the unmanned equipment can ensure that the equipment performs at its best in its area of ​​expertise, rationally divide labor, and optimize resource utilization, thereby improving the efficiency and success rate of mission execution.

[0102] S3.3: Identify task priorities by sorting them from most urgent to least urgent.

[0103] For example, when sorting tasks by urgency, direct threats such as destroying enemy fire points are prioritized, followed by support tasks such as intelligence gathering, and low-risk tasks such as routine patrols are ranked last. This sorting ensures that the most urgent tasks that have the greatest impact on mission success are executed first.

[0104] S3.4: Set task allocation rules based on the functions, task priorities and status of the unmanned equipment.

[0105] For example, based on mission priorities and the functions of unmanned equipment, strike missions are assigned to armed drones, while reconnaissance missions are assigned to reconnaissance drones equipped with sensors. At the same time, combined with the status of the unmanned equipment, equipment with sufficient power and in good condition is given priority to perform tasks, thereby ensuring efficient execution of tasks and rational allocation of resources.

[0106] S3.5: Convert task requirements into executable subtasks and assign tasks according to task assignment rules.

[0107] The specific process is as follows: First, the mission requirements are decomposed into multiple executable subtasks according to their functions and objectives, such as reconnaissance, strike, communication relay, intelligence analysis, etc. Then, according to the set task allocation rules, combined with the task priority, the function of the unmanned equipment and the equipment status, the most suitable unmanned equipment is selected for each subtask. For example, the reconnaissance subtask is assigned to a drone equipped with a high-resolution sensor, the strike subtask is assigned to a drone carrying weapons, and the communication relay task is assigned to a drone with strong communication capabilities. The remaining resources of the unmanned equipment (such as power and load capacity) must also be considered during allocation to ensure that the equipment is in good condition and can complete the task. Through this process, the mission requirements are reasonably converted into specific operations to ensure that each subtask is supported by the most appropriate equipment, thereby improving the efficiency and success rate of mission execution.

[0108] S3.6: When executing a task, introduce a redundant allocation mechanism to allocate multiple unmanned equipment to perform the same task in advance, and detect abnormal status of the unmanned equipment based on the health monitoring mechanism.

[0109] Specifically, the redundant allocation mechanism refers to reserving spare resources or equipment in task allocation to cope with possible failures or malfunctions of the main equipment. This mechanism improves the reliability and fault tolerance of task execution by increasing the allocation of spare resources.

[0110] S3.7: If an unmanned equipment fails due to an abnormal condition, the kill network reconstruction is automatically triggered, and the unfinished task is taken over by the unmanned equipment closest to the failed equipment and with similar functions. At the same time, the collaborative relationship between the unmanned equipment is adjusted and the unmanned equipment collaborative network is rebuilt.

[0111] It should be noted that when an unmanned device fails due to an abnormal state, the task takeover mechanism is automatically triggered, and the nearest device with similar functions is given priority to take over the unfinished task. At the same time, the collaborative network will readjust and update the collaborative relationship between unmanned devices to ensure the smooth continuation of the task. Through this automatic reconstruction and dynamic allocation mechanism, it is possible to effectively respond to equipment failure, maintain task continuity, and improve the stability and reliability of the overall task.

[0112] Abnormal conditions of unmanned equipment include failure, damage and communication interruption.

[0113] S4: Based on task requirements and dynamic task allocation, build a task planning layer and formulate task plans in stages.

[0114] S4.1: According to the task timeline and demand index T, divide the task into the initial stage, execution stage and closing stage.

[0115] For example, in the initial stage (at the beginning of the mission), the mission requirement T is low, and the equipment performs reconnaissance and preparation work; in the execution stage (mid-mission), as time goes on, the requirement T increases, and the equipment performs core tasks; in the closing stage (late stage of the mission), the mission is nearing completion, the requirement T decreases, and the equipment performs tasks such as evacuation or result confirmation.

[0116] S4.2: In the initial stage, mission planning is based on low-demand intelligence collection tasks. Unmanned equipment with reconnaissance capabilities is dynamically allocated according to mission requirements to perform reconnaissance missions and collect high-resolution images and enemy situation data. The task allocation of reconnaissance equipment is adjusted in real time based on the real-time status of the equipment.

[0117] For example, the unmanned equipment system assigns a drone with reconnaissance capabilities to perform a low-demand intelligence collection mission. When the drone begins to collect high-resolution images and enemy situation data, its battery, location, and payload status are monitored in real time. If the drone is low on battery or encounters an obstacle, the mission is immediately adjusted to allow a nearby drone in better condition to take over the reconnaissance mission, ensuring that the mission continues and efficient intelligence is obtained.

[0118] S4.3: During the execution phase, mission planning is based on high-demand offensive missions, resources are dynamically allocated according to the urgency and importance of the mission, strike missions are assigned to missile-equipped drones, and task allocation is dynamically adjusted through redundancy mechanisms.

[0119] Furthermore, when dynamically adjusting task allocation, drones in poor condition are replaced in real time based on the drone’s battery level, remaining weapons, and battlefield changes, and drones in good condition are assigned to take over the task to ensure the smooth progress of the mission.

[0120] S4.4: In the closing phase, mission planning is based on medium-demand alert missions, and the allocation of remaining resources is dynamically adjusted according to current mission requirements, with priority given to the use of low-power equipment to perform alert missions.

[0121] It should be noted that low-power equipment is given priority in performing alert tasks because alert tasks usually consume fewer resources and can extend the effective use time of low-power equipment, while retaining high-power equipment to perform tasks with higher requirements.

[0122] S5: Based on the demand analysis layer, task allocation layer and task planning layer, a task reliability model is constructed to evaluate the task reliability at different stages.

[0123] S5.1: Construct a task reliability model framework by combining the three independent functional layers of demand analysis layer, task allocation layer and task planning layer.

[0124] It should be noted that the task reliability model framework combines the independent functions of the demand analysis layer, task allocation layer, and task planning layer. First, the demand analysis layer evaluates the battlefield environment, enemy situation, and unmanned equipment status through multi-source data fusion to generate a task demand index. Next, the task allocation layer dynamically allocates resources based on the urgency of the task and the function and status of the unmanned equipment to ensure that the most suitable equipment performs the task. At the same time, the task planning layer dynamically adjusts the task execution path and strategy based on real-time battlefield changes and equipment status feedback. Through the collaborative work of the three layers, this framework realizes a closed-loop feedback mechanism for task demand assessment, resource allocation, and planning adjustment, ensuring the high reliability and flexibility of tasks in complex and dynamic environments.

[0125] S5.1: Embed Monte Carlo simulation and Markov chain models into each independent functional layer in the mission reliability model framework.

[0126] Furthermore, by embedding Monte Carlo simulation and Markov chain models, the uncertainty in the mission and the dynamic changes in equipment status can be evaluated more accurately, thereby optimizing decisions at all levels and improving the reliability and robustness of the mission.

[0127] S5.2: In different stages of task execution, the feedback information obtained from the demand analysis layer, task allocation layer, and task planning layer is integrated, and a task reliability model is finally constructed by simulating the Monte Carlo simulation and Markov chain model to predict the task reliability scores at different stages. The expression is:

[0128]

[0129] Among them, R i (t) is the task reliability score of the i-th stage, T i (t) is the task demand index of stage i, D i (t) is the task allocation efficiency of the i-th stage, S i (t) is the task success rate of stage i, P i (t) is the task planning efficiency of the i-th stage, F i (t) is the equipment failure rate in stage i, E i (t) is the environmental impact factor of the i-th stage, L i (t) is the task load of the i-th stage, t is the time variable, and i is the index variable of the task stage.

[0130] It should be noted that the expression of task allocation efficiency is:

[0131]

[0132] Among them, D i (t) represents the task allocation efficiency of the i-th stage, r a (t) is the resource allocated to the current task, r e (t) is the resource required for the current task, U h (t) is the number of unmanned equipment in normal operation, U t (t) is the total number of allocated unmanned equipment, N o (t) is the number of unmanned equipment nodes operating normally at the current stage, N t (t) is the total number of unmanned equipment nodes currently participating in the task, and t is the time variable.

[0133] In the unmanned equipment system, a node refers to an unmanned equipment or device unit with independent functions that can communicate and collaborate with other nodes in the network to perform tasks and share information.

[0134] The expression of task planning efficiency is:

[0135]

[0136] Among them, P i (t) is the task planning efficiency of stage i, r u (t) is the amount of resources used by the current task, r o (t) The optimal amount of resources for the current task, Δt i is the task execution time of the current stage.

[0137] The expression of task load pressure is:

[0138]

[0139] Among them, L i (t) is the task load of the i-th stage, R u (t) is the actual resource that can be used by the unmanned equipment to perform tasks, R a (t) is the amount of resources required for the unmanned equipment to perform the task, t r is the resource response time.

[0140] The environmental impact factor is the comprehensive impact of the battlefield environment on mission execution, and its expression is:

[0141]

[0142] Among them, E i(t) is the environmental influencing factor of the i-th stage, θ is the battlefield slope, V is the battlefield visibility, W is the wind speed in the battlefield, P is the current precipitation in the battlefield, E represents the enemy's threat coefficient, F represents the enemy's firepower coverage, and t is the time variable.

[0143] S5.3: Evaluate task reliability based on the reliability scores of tasks at different stages. The higher the reliability score of a task, the higher the reliability of the task; the lower the reliability score of a task, the lower the reliability of the task.

[0144] By simulating the Monte Carlo simulation and the Markov chain model, the specific steps are as follows:

[0145] Based on the three-dimensional battlefield model, Monte Carlo simulation is used to simulate the task execution process of the unmanned equipment system in different battlefield environments to verify the task success rate. The expression is:

[0146]

[0147] Among them, S i (t) is the task success rate of the i-th stage, k represents the simulation index, is the task demand index of the i-th stage in the k-th simulation, is the task allocation efficiency of the i-th stage in the k-th simulation, The efficiency of task planning for the i-th stage in the k-th simulation, is the environmental impact factor of the i-th stage in the k-th simulation, is the task load pressure of the i-th stage in the k-th simulation, N represents the total number of simulations, and f() represents the task success rate prediction function.

[0148] S5.4: Use the Markov chain model to simulate the state changes of each unmanned equipment during the mission execution, and analyze the impact of state changes on the mission success rate. By solving the steady-state distribution of the Markov chain, the probability of equipment failure during the mission execution is evaluated. The expression is:

[0149]

[0150] Among them, F i (t) represents the equipment failure rate in stage i, π j (t) represents the probability that the unmanned equipment is in state j, λ j represents the stability rate of the unmanned equipment in state j, M represents the total number of unmanned equipment states, and t represents the time variable.

[0151] S6: Optimize the mission reliability model based on real-time feedback and dynamic adjustment.

[0152] S6.1: Feedback information is transmitted to the demand analysis layer, task allocation layer and task planning layer in real time, and the task demand index T is updated in real time i (t) and task planning, optimizing the accuracy of task planning.

[0153] S6.1.1: Use multiple types of sensors to collect battlefield environment data and unmanned equipment status data in real time, dynamically adjust the mission requirement index, and improve the accuracy of mission requirement analysis.

[0154] Furthermore, the data fusion algorithm is used to comprehensively process multi-source data, identify potential threats and mission opportunities, and dynamically update the mission requirement index T i (t), and optimize resource allocation and task planning through feedback mechanisms. At the same time, combined with Monte Carlo simulation and Markov chain models, the uncertainty and equipment status changes in future task execution are predicted, thereby further improving the accuracy and adaptability of task demand analysis and ensuring the efficiency and reliability of task execution in complex environments.

[0155] S6.1.2: Based on the optimized task demand index and the real-time changes in the status of unmanned equipment, dynamically adjust the task allocation rules of the allocation layer to optimize the task allocation efficiency and improve the reliability and efficiency of task execution.

[0156] Furthermore, according to the optimized task demand index and the real-time status of the unmanned equipment, the task allocation rules are dynamically adjusted to give priority to the equipment with the best status to perform high-priority tasks. At the same time, combined with the changes in task requirements and equipment performance, resource scheduling is optimized in real time to ensure the maximum efficiency of task allocation, thereby improving the reliability and efficiency of task execution and avoiding resource waste or equipment overload.

[0157] S6.1.3: Based on the optimized task requirements and optimized task allocation efficiency, dynamically adjust the task planning to optimize the task execution sequence and phase division in real time to maximize planning efficiency.

[0158] Furthermore, by real-time monitoring of mission requirements and unmanned equipment status, dynamically optimizing the mission execution order and phase division, prioritizing key tasks, flexibly adjusting the mission phase length, ensuring efficient use of resources, and continuously optimizing mission planning through a feedback mechanism, maximum efficiency and mission success rate can be achieved.

[0159] This embodiment also provides a computer device, which is suitable for the method of constructing a mission reliability model of an unmanned equipment system based on a reconfigurable kill net, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the method of constructing a mission reliability model of an unmanned equipment system based on a reconfigurable kill net as proposed in the above embodiment.

[0160] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0161] The present embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for constructing a task reliability model of an unmanned equipment system based on a reconfigurable kill net as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a disk or an optical disk.

[0162] In summary, the present invention improves the task execution efficiency and reliability of the unmanned equipment system through: a demand analysis layer, a dynamic task allocation layer based on a reconfigurable kill net, and a phased task planning layer. The demand analysis layer uses multi-source sensor fusion technology to provide accurate battlefield environment and equipment status data; the dynamic task allocation layer is based on a reconfigurable kill net to achieve flexible task allocation and redundancy mechanisms to ensure that tasks are not interrupted when equipment fails; the phased task planning layer dynamically adjusts the task execution order according to task requirements and resource conditions. These three layers work together to improve the flexibility, fault tolerance, and task success rate of the unmanned equipment system.

[0163] Example 2, referring to Table 1, is the second example of the present invention. To further verify the technical solution of the present invention, experimental simulation data of a method for constructing a mission reliability model of an unmanned equipment system based on a reconfigurable kill network are provided.

[0164] In order to verify the advantages of the present invention in terms of mission reliability, a set of experiments was designed to evaluate the reliability of tasks in different mission scenarios. The core purpose of the experiment is to test the reliability improvement effect of the present invention on tasks in complex battlefield environments through data collection, mission requirement analysis and task allocation mechanism.

[0165] The experimental scenario simulates three typical battlefield environments: low-demand, medium-demand, and high-demand missions. Multiple types of sensors (radar, optical sensors, infrared and sonar sensors, meteorological sensors, etc.) are used to obtain battlefield environment data, including terrain height, surface texture, enemy movements, weather conditions, etc., and the monitoring equipment on the unmanned equipment is used to obtain the equipment status (such as endurance, load status, location, and movement trajectory) in real time.

[0166] First, the experiment uses multiple types of sensors to collect battlefield environment data and unmanned equipment status data in real time, generates a three-dimensional battlefield model and calculates the task requirement index T to determine the complexity of the task and its demand for resources.

[0167] Secondly, based on the real-time status and task requirements of the unmanned equipment, the task allocation rules are dynamically adjusted to ensure that tasks are allocated first to equipment in good condition and with sufficient resources, thereby improving the rationality and efficiency of task allocation.

[0168] Next, during the mission execution, the mission progress and equipment status are monitored in real time, key data such as mission success rate, resource consumption, equipment failure rate, etc. are recorded, and the execution effect of the mission is comprehensively evaluated.

[0169] Finally, by comparing the experimental results, the task reliability scoring formula R i (t), which verifies the significant advantages of the present invention in mission reliability, especially in high-demand mission scenarios, showing higher mission success rate and lower equipment failure rate.

[0170] The details are shown in Table 1 below:

[0171] Table 1 Task reliability evaluation experimental data table

[0172]

[0173]

[0174] Through the analysis of the data in the above table, it can be clearly seen that the present invention is significantly better than the prior art in terms of task reliability in various task scenarios. For example, in terms of task allocation efficiency, the allocation efficiency of the present invention is higher than that of the prior art in all demand scenarios, especially in low-demand and high-demand tasks, the present invention reaches 0.90 and 0.65 respectively, while the prior art is only 0.70 and 0.40. Secondly, in terms of task success rate, the success rates of the present invention in low-, medium- and high-demand tasks are 0.95, 0.85 and 0.78 respectively, which are significantly higher than the 0.88, 0.75 and 0.60 of the prior art. Next, the data on equipment failure rate show that the equipment failure rate of the present invention is always lower than that of the prior art, especially in high-demand tasks, the failure rate of the present invention is 10%, while the prior art is as high as 20%, which further improves the stability and reliability of the task. Finally, through the task reliability score R i (t) It can be seen that the scores of the present invention in all scenarios are much higher than those of the prior art, especially in high-demand tasks, where the score of the present invention is 0.60, while that of the prior art is only 0.30, demonstrating the significant advantages of the present invention in complex task environments.

[0175] In summary, the experimental data clearly show that the present invention has significant advantages over the prior art in terms of mission reliability. Through dynamic task allocation, redundancy mechanism and real-time task adjustment, the present invention effectively improves the efficiency and success rate of task allocation, reduces the equipment failure rate, and thus significantly improves the reliability of the overall task. Especially in high-demand mission scenarios, the adaptability and stability shown by the present invention make it have higher practical value in complex battlefield environments.

[0176] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for constructing a mission reliability model for an unmanned equipment system based on a reconfigurable kill net, characterized in that: include, Obtain battlefield environment data and unmanned equipment status data in real time through multiple types of sensors; Based on battlefield environment data and unmanned equipment status data, build a demand analysis layer to analyze mission requirements; Based on the reconfigurable kill network, a task allocation layer is constructed to perform dynamic task allocation; According to task requirements and dynamic task allocation, build a task planning layer and formulate task plans in stages; Based on the demand analysis layer, task allocation layer and task planning layer, a task reliability model is constructed to evaluate the task reliability at different stages; The mission reliability model is optimized based on real-time feedback and dynamic adjustment.

2. The method for constructing a mission reliability model for an unmanned equipment system based on a reconfigurable kill net according to claim 1, characterized in that: The specific steps of obtaining battlefield environment data and unmanned equipment status data in real time through multiple types of sensors are as follows: Obtain battlefield terrain height data through radar; Acquire high-resolution image data of battlefield terrain through optical sensors; Monitor enemy positions and troop movement data through infrared and sonar sensors; Use meteorological sensors to obtain battlefield weather data in real time; Utilize the monitoring equipment on the unmanned equipment to obtain the unmanned equipment’s endurance, load status, location and motion trajectory in real time.

3. The method for constructing a mission reliability model for an unmanned equipment system based on a reconfigurable kill net as claimed in claim 2, characterized in that: The requirements analysis layer is constructed based on battlefield environment data and unmanned equipment status data to analyze task requirements. The specific steps are as follows: Perform geometric correction and orthographic projection on high-resolution image data, and use image processing algorithms to align the corrected high-resolution image with terrain height data; By integrating high-resolution image data with terrain height data through image registration, a three-dimensional battlefield model containing both terrain height and surface texture information is generated, and battlefield environmental factors are analyzed based on the three-dimensional battlefield model; Through multi-source data fusion, the unmanned equipment status data is integrated with the battlefield environment data in the three-dimensional battlefield model, and the decision support algorithm is used to calculate the task demand index, which is expressed as: Wherein, T is the mission requirement index, θ is the battlefield slope, V is the battlefield visibility, W is the wind speed in the battlefield, P is the current precipitation in the battlefield, E represents the enemy's threat coefficient, F represents the enemy's firepower coverage, L is the load of the unmanned equipment, B is the remaining power of the unmanned equipment, S is the model strength of the unmanned equipment, and σ is the Sigmoid function; Based on resource consumption and historical task success rate, a low demand threshold T is defined respectively. l and high demand threshold T h ; When T≤T l When , the current task is considered to be a low-demand task, the current task consumes less resources, and the task success rate is high; When T l <T≤T h When , the current task is considered to be a medium-demand task, the current task resource consumption is moderate, and the task success rate is moderate; When T>T h When , the current task is considered to be a high-demand task, which requires a large amount of resources and stronger equipment support, and the task success rate is low; The battlefield environmental factors include identifying battlefield terrain information, enemy deployment and weather conditions.

4. The method for constructing a mission reliability model for an unmanned equipment system based on a reconfigurable kill net as claimed in claim 3, characterized in that: The task allocation layer is constructed based on the reconfigurable kill network to perform dynamic task allocation. The specific steps are as follows: Based on the mission requirements and the status of unmanned equipment, an unmanned equipment collaboration network is constructed with each unmanned equipment as a node and the collaboration relationship between each equipment as an edge. Initial unmanned equipment collaborative network configuration based on mission type and unmanned equipment capabilities; Identify task priorities by sorting them from high to low urgency; Set task allocation rules based on the functions, task priorities and status of the unmanned equipment; Convert task requirements into executable subtasks and assign tasks according to task assignment rules; When executing a task, a redundant allocation mechanism is introduced to allocate multiple unmanned equipment to perform the same task in advance, and the abnormal status of the unmanned equipment is detected based on the health monitoring mechanism; If an unmanned device fails due to an abnormal state, the kill network reconstruction is automatically triggered, and the unmanned device closest to the failed device and with similar functions takes over the unfinished task. At the same time, the collaborative relationship between the unmanned devices is adjusted to rebuild the unmanned device collaborative network. The abnormal status of the unmanned equipment includes failure, damage and communication interruption.

5. The method for constructing a mission reliability model for an unmanned equipment system based on a reconfigurable kill net as claimed in claim 4, characterized in that: According to the task requirements and dynamic task allocation, the task planning layer is constructed and the task planning is formulated in stages. The specific steps are as follows: According to the task timeline and demand index T, the task is divided into the initial stage, execution stage and closing stage; In the initial stage, the mission planning is based on low-demand intelligence collection tasks. Unmanned equipment with reconnaissance functions is dynamically allocated according to mission requirements to perform reconnaissance missions and collect high-resolution images and enemy situation data. The task allocation of reconnaissance equipment is adjusted in real time according to the real-time status of the equipment. In the execution phase, mission planning is based on high-demand offensive missions, dynamically allocating resources according to the urgency and importance of the mission, assigning strike missions to missile-equipped drones, and dynamically adjusting mission allocation through redundancy mechanisms; In the closing phase, mission planning is based on medium-demand alert missions, and the allocation of remaining resources is dynamically adjusted according to current mission requirements, with priority given to the use of low-power equipment to perform alert missions.

6. The method for constructing a mission reliability model for an unmanned equipment system based on a reconfigurable kill net as claimed in claim 5, characterized in that: Based on the demand analysis layer, task allocation layer and task planning layer, a task reliability model is constructed to evaluate the task reliability at different stages. The specific steps are as follows: Combining the three independent functional layers of demand analysis layer, task allocation layer and task planning layer, a task reliability model framework is constructed; Embed Monte Carlo simulation and Markov chain model into each independent functional layer in the mission reliability model framework; At different stages of task execution, the feedback information obtained from the demand analysis layer, task allocation layer, and task planning layer is integrated. By simulating the Monte Carlo simulation and Markov chain model, a task reliability model is finally constructed to predict the task reliability scores at different stages. The expression is: Among them, R i (t) is the task reliability score of the i-th stage, T i (t) is the task demand index of stage i, D i (t) is the task allocation efficiency of the i-th stage, S i (t) is the task success rate of stage i, P i (t) is the task planning efficiency of the i-th stage, F i (t) is the equipment failure rate in stage i, E i (t) is the environmental impact factor of the i-th stage, L i (t) is the task load of the i-th stage, t is the time variable, and i is the index variable of the task stage; The reliability of tasks is evaluated based on the reliability scores of tasks at different stages. The higher the reliability score of a task, the higher the reliability of the task; the lower the reliability score of a task, the lower the reliability of the task.

7. The method for constructing a mission reliability model for an unmanned equipment system based on a reconfigurable kill net according to claim 6, characterized in that: By simulating the Monte Carlo simulation and the Markov chain model, the specific steps are as follows: Based on the three-dimensional battlefield model, Monte Carlo simulation is used to simulate the task execution process of the unmanned equipment system in different battlefield environments to verify the task success rate. The expression is: Among them, S i (t) is the task success rate of the i-th stage, k represents the simulation index, is the task demand index of the i-th stage in the k-th simulation, is the task allocation efficiency of the i-th stage in the k-th simulation, P i (k) The efficiency of task planning for the i-th stage in the k-th simulation, is the environmental impact factor of the i-th stage in the k-th simulation, is the task load pressure of the i-th stage in the k-th simulation, N represents the total number of simulations, and f() represents the task success rate prediction function; The Markov chain model is used to simulate the state changes of each unmanned equipment during the mission execution, and the impact of the state change on the mission success rate is analyzed. The probability of equipment failure during the mission execution is evaluated by solving the steady-state distribution of the Markov chain. The expression is: Among them, F i (t) represents the equipment failure rate in stage i, π j (t) represents the probability that the unmanned equipment is in state j, λ j represents the stability rate of the unmanned equipment in state j, M represents the total number of unmanned equipment states, and t represents the time variable.

8. The method for constructing a mission reliability model for an unmanned equipment system based on a reconfigurable kill net according to claim 7, characterized in that: The task reliability model is optimized based on real-time feedback and dynamic adjustment. The specific steps are as follows: Feedback information is delivered to the demand analysis layer, task allocation layer and task planning layer in real time, and the task demand index T is updated in real time. i (t) and mission planning, optimizing the accuracy of mission planning; Through real-time collection of battlefield environment data and unmanned equipment status data by multiple types of sensors, the mission requirement index can be dynamically adjusted to improve the accuracy of mission requirement analysis; According to the optimized task demand index and the real-time changes in the status of unmanned equipment, the task allocation rules of the allocation layer are dynamically adjusted to optimize the efficiency of task allocation and improve the reliability and efficiency of task execution; Based on the optimized task requirements and optimized task allocation efficiency, the task planning is dynamically adjusted to optimize the task execution sequence and phase division in real time to maximize planning efficiency.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for constructing a mission reliability model of an unmanned equipment system based on a reconfigurable kill network as described in any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for constructing a mission reliability model of an unmanned equipment system based on a reconfigurable kill network as described in any one of claims 1 to 8 are implemented.

Images