Unmanned aerial vehicle combat performance evaluation method and evaluation system, memory and electronic equipment

Abstract

The invention provides an unmanned aerial vehicle combat performance evaluation method and evaluation system, a memory and electronic equipment, and belongs to the technical field of unmanned aerial vehicles, and the method comprises the steps: constructing a Bayesian network; improving the Bayesian network to form a weighted Bayesian algorithm; determining an attack benefit value of the unmanned aerial vehicle to the target at the current moment by using an Euclidean distance measurement algorithm or a weighted Bayesian algorithm; constructing a weighted dynamic Bayesian algorithm based on a weighted Bayesian algorithm, and determining a strike benefit value between the unmanned aerial vehicle and the matched target according to the strike benefit value of the unmanned aerial vehicle to the target at the current moment and the weighted dynamic Bayesian algorithm; determining strike benefit values between all the unmanned aerial vehicles and the matched targets to form a strike benefit data set; and determining a combat performance evaluation value of the unmanned aerial vehicle based on the strike benefit data set and the matching rate, thereby evaluating the combat performance. According to the method, the relevance among multiple evaluation indexes of the unmanned aerial vehicle system is improved, and the combat ability of the unmanned aerial vehicle system can be reflected more accurately.

Description

Technical Field

[0001] The present invention belongs to the technical field of unmanned aerial vehicles, and relates to unmanned aerial vehicle combat performance evaluation technology, specifically to an unmanned aerial vehicle combat performance evaluation method, evaluation system, memory and electronic equipment. Background Art

[0002] Drones have become crucial in executing precision strikes and attack decisions. An efficient and accurate strike assessment and decision support system plays a vital role in improving the overall combat capability of drones, reducing potential risks, rationally allocating resources, and coping with various complex environments.

[0003] When drones conduct strike drills in actual combat exercises, it is necessary to evaluate the effect of comprehensive algorithms on strike targets. The essence of this is to evaluate the technical performance of drones when performing specific tasks. The evaluation process is not only a test of a single technology, but also a comprehensive performance test of multiple algorithms such as target identification, continuous tracking, and rapid decision-making. In the context of actual combat exercises, the use of comprehensive algorithm evaluation can more comprehensively reflect the actual combat capability of the drone system. The core purpose of evaluating comprehensive algorithms is to test the performance of drones at the technical level, aiming to continuously optimize the combat performance of drones. Through data collection and analysis in actual combat exercises, we can more accurately understand the performance of drones in various complex environments and the effects of various algorithms in drone systems in actual applications. This will not only help to discover problems with drone systems, but also provide valuable data support for subsequent improvements and enhancements of drones.

[0004] At present, when evaluating the comprehensive algorithm of the UAV system, multiple evaluation indicators are independent of each other. For example, the perception ability of the UAV is only evaluated based on the positioning accuracy of multiple sensors such as GPS, inertial measurement unit (IMU), camera, lidar, etc., without considering the correlation between other indicators and perception ability. However, in actual combat exercises, multiple evaluation indicators of UAVs are interrelated and will affect each other. For example, the perception ability of the UAV will affect the tracking ability of the UAV. Therefore, the data provided by the existing evaluation algorithm is inaccurate and cannot provide strong data support for the overall performance improvement of the UAV. Summary of the invention

[0005] As described in the above background technology, the existing evaluation algorithms have multiple evaluation indicators that are independent of each other during evaluation, and there is a technical problem that it is unable to provide strong data support for improving the overall performance of the UAV. To address this technical problem, the present invention proposes a UAV combat performance evaluation method, evaluation system, memory and electronic device.

[0006] The present invention constructs a Bayesian network based on multiple evaluation indicators, and uses a grey correlation algorithm to improve the Bayesian network, weakening the independence assumptions of multiple evaluation indicators so that multiple evaluation indicators are correlated with each other, fully considering the correlation between multiple evaluation indicators and the volatility of multiple evaluation indicator data, and then determining the strike benefit value of the drone to the target, and finally determining the strike benefit value between each drone and its corresponding target to form a strike benefit data set, and then combining the strike benefit data set and the matching rate to determine the combat performance evaluation value of the drone, thereby evaluating the combat performance of the drone. The correlation between multiple evaluation indicators of the drone system is improved, and strong data support can be provided for the overall performance improvement of the drone, thereby more accurately reflecting the combat capability of the drone system.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solutions: The method for evaluating the combat performance of a UAV of the present invention comprises the following steps: Determine multiple evaluation indicators of UAV combat performance, and construct a Bayesian network based on the correlation between multiple evaluation indicators; The Bayesian network is improved by using the grey correlation algorithm to form a weighted Bayesian algorithm; The Euclidean distance measurement algorithm or the weighted Bayesian algorithm is used to determine the strike benefit value of the UAV against the target at the current moment; a weighted dynamic Bayesian algorithm is constructed based on the weighted Bayesian algorithm, and the strike benefit value between the UAV and its matching target is determined according to the strike benefit value of the UAV against the target at the current moment and the weighted dynamic Bayesian algorithm; Repeat the above steps until the strike benefit values ​​between all drones and their matching targets are determined to form a strike benefit data set; Determine the match rate between the drone and the target; The combat performance evaluation value of the UAV is determined based on the strike effectiveness data set and the matching rate, and the combat performance of the UAV is evaluated according to the combat performance evaluation value of the UAV.

[0008] It is further defined that the improvement of the Bayesian network by using the grey correlation algorithm to form a weighted Bayesian algorithm specifically includes: The grey correlation algorithm is used to assign different weights to each node of the Bayesian network. The weights of each child node relative to the root node in the Bayesian network are determined by combining the different weights of each node, thus forming a weighted Bayesian algorithm.

[0009] It is further defined that the use of the Euclidean distance measurement algorithm or the weighted Bayesian algorithm to determine the strike effectiveness value of the UAV against the target at the current moment specifically includes: using the Euclidean distance measurement algorithm to compare and judge the similarity of evaluation indicators at different moments, and determining the strike effectiveness value of the UAV against the target at the current moment based on the similarity judgment results of the evaluation indicators at different moments or the weighted Bayesian algorithm.

[0010] It is further defined that the use of the Euclidean distance measurement algorithm to compare and determine the similarity of the evaluation indicators at different times, and determining the strike benefit value of the drone on the target at the current moment according to the similarity judgment results of the evaluation indicators at different times or the weighted Bayesian algorithm specifically includes: The Euclidean distance measurement algorithm is used to determine the similarity of the evaluation indicators corresponding to two adjacent moments. If the similarity is less than the similarity threshold, the strike benefit value of the previous moment is used as the strike benefit value of the UAV to the target at the current moment; if the similarity exceeds the similarity threshold, the strike benefit value of the UAV to the target at the current moment is determined according to the weighted Bayesian algorithm.

[0011] It is further defined that constructing a weighted dynamic Bayesian algorithm based on the weighted Bayesian algorithm specifically includes: adding time series data to the weighted Bayesian algorithm to construct a weighted dynamic Bayesian algorithm.

[0012] It is further defined that the determining the matching rate between the drone and the target specifically includes: Determine the threat level of the target, match the drone with the target based on the threat level of the target and the strike effectiveness value between the drone and its matching target, and determine the matching rate.

[0013] It is further defined that the evaluation indicators include strike effectiveness, perception capability, tracking capability, maneuverability and real-time performance; among which, the perception capability includes false alarm rate, missed detection rate and positioning accuracy, and the maneuverability includes relative speed, relative altitude and heading angle.

[0014] The UAV combat performance evaluation system of the present invention is applied to the above-mentioned UAV combat performance evaluation method, comprising: A Bayesian network building module is used to determine multiple evaluation indicators of the combat performance of the UAV and to build a Bayesian network based on the correlation between the multiple evaluation indicators; Improvement module: used to improve the Bayesian network using the grey correlation algorithm to form a weighted Bayesian algorithm; The strike benefit value determination module is used to determine the strike benefit value of the UAV to the target at the current moment by using the Euclidean distance measurement algorithm or the weighted Bayesian algorithm; it is used to construct a weighted dynamic Bayesian algorithm based on the weighted Bayesian algorithm, and determine the strike benefit value between the UAV and its matching target according to the strike benefit value of the UAV to the target at the current moment and the weighted dynamic Bayesian algorithm; Strike effectiveness data set determination module: used to repeat the improvement module and the strike effectiveness value determination module until the strike effectiveness values ​​between all drones and their matching targets are determined to form a strike effectiveness data set; Matching module: used to determine the matching rate between the drone and the target; And a combat performance evaluation module: used to determine the combat performance evaluation value of the UAV based on the strike effectiveness data set and the matching rate, and evaluate the combat performance of the UAV according to the combat performance evaluation value of the UAV.

[0015] The memory of the present invention stores a program file, and the program file is executed to implement the program instructions formed by the above-mentioned UAV combat performance evaluation method.

[0016] The electronic device of the present invention comprises a processor and a memory coupled to each other, wherein: The memory is used to store program instructions formed by the above-mentioned UAV combat performance evaluation method; The processor is used to execute program instructions stored in the memory.

[0017] Compared with the prior art, the present invention has the following beneficial effects: 1. The combat performance evaluation method of the UAV of the present invention is to construct a Bayesian network based on multiple evaluation indicators, and at the same time improve the Bayesian network using a gray correlation algorithm, weaken the independence assumption of multiple evaluation indicators, so that multiple evaluation indicators are correlated with each other, and fully consider the correlation between multiple evaluation indicators and the volatility of multiple evaluation indicator data, and then determine the strike benefit value of the UAV to the target, and finally determine the strike benefit value between each UAV and its corresponding target to form a strike benefit data set, and then combine the strike benefit data set and the matching rate to determine the combat performance evaluation value of the UAV, so as to evaluate the combat performance of the UAV. The correlation between multiple evaluation indicators of the UAV system is improved, and strong data support can be provided for the overall performance improvement of the UAV, so as to more accurately reflect the combat capability of the UAV system.

[0018] 2. In the present invention, the grey correlation algorithm is first used to assign different weights to each node of the Bayesian network, thereby differentially assigning different weights to the evaluation indicators of each node in the Bayesian network; then, the weights of each child node in the Bayesian network relative to the root node are determined in combination with the different weights of each node, thereby achieving an objective allocation of weights of multiple evaluation indicators, effectively enhancing the interdependence between each node, weakening the independence assumption in the existing comprehensive algorithm, and thus improving the evaluation performance.

[0019] 3. In the present invention, the Euclidean distance metric algorithm is used to compare and judge the similarity of multiple evaluation indicators corresponding to each moment, thereby reducing the computational complexity and improving the real-time performance of the dynamic Bayesian algorithm. In addition, in a limited computing resource environment, it can also effectively save computing resource consumption.

[0020] 4. By using the UAV combat performance evaluation method of the present invention to evaluate the comprehensive performance of UAVs in actual combat exercises, a large amount of combat performance data about UAVs can be accumulated. The combat performance data can not only provide a basis for the current performance optimization of UAVs, but also provide strong support for the research and development and improvement of future UAV technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 Schematic diagram of the combat performance evaluation method of a UAV of the present invention; Figure 2 A schematic diagram of a UAV combat performance evaluation system according to the present invention; Figure 3 is a schematic diagram of a Bayesian network; Figure 4 This is a comparison chart of the evaluation results formed by the UAV combat performance evaluation method of the present invention and the existing comprehensive algorithm. DETAILED DESCRIPTION

[0022] The technical solution of the present invention is further explained below in conjunction with the accompanying drawings and embodiments, but the present invention is not limited to the implementation modes described below.

[0023] See also Figure 1 The present invention provides a method for evaluating the combat performance of a UAV, comprising the following steps: S1: Determine multiple evaluation indicators of UAV combat performance and construct a Bayesian network based on the correlation between multiple evaluation indicators; See also Figure 3 , the evaluation indicators in the present invention include strike effectiveness, perception ability, tracking ability, maneuverability and real-time performance. Perception ability is a key indicator to measure whether the UAV can effectively identify and locate the target, including false alarm rate, missed detection rate and positioning accuracy. The false alarm rate is the proportion of non-targets misjudged as targets. The missed detection rate is the proportion of real targets that cannot be detected. Positioning accuracy is the accuracy of the target position obtained by the relationship between the target image and the coordinates. The tracking ability is determined by the number of times the target is lost during the tracking process. If the UAV frequently loses the target, the probability of its successful strike will be significantly reduced. Maneuverability is an important indicator to measure the flexibility and sensitivity of the UAV during movement, including relative speed, relative altitude and heading angle. Real-time performance is an indicator to measure the reaction speed of the UAV. A highly sensitive reaction speed can ensure the reaction time of the UAV from receiving the control signal to the actual action, affecting the strike effect of the UAV.

[0024] According to the correlation between the evaluation indicators (causal relationship and logical dependency), a Bayesian network is constructed, and the node variables of the Bayesian network are determined. The Bayesian network takes a total of 11 node variables, among which the false alarm rate, missed detection rate, positioning accuracy, relative speed, relative altitude and heading angle are observable node variables, and the strike benefit, perception capability, tracking capability, maneuverability and real-time performance are implicit node variables, as shown in Table 1.

[0025] Table 1: Node variable table S2: Use the grey correlation algorithm to improve the Bayesian network and form a weighted Bayesian algorithm; Step S2 is specifically as follows: using the grey correlation algorithm to assign different weights to each node of the Bayesian network, and determining the weight of each child node relative to the root node in the Bayesian network according to the different weights of each node, thereby forming a weighted Bayesian algorithm to determine the relative importance of the evaluation index to the strike effectiveness.

[0026] Specifically, the weights of the sub-nodes (false alarm rate, missed detection rate and positioning accuracy) relative to the root node (perception capability) are calculated respectively; the weights of the sub-nodes (relative speed, relative altitude and heading angle) relative to the root node (maneuverability) are calculated respectively; the weights of the sub-nodes (perception capability, tracking capability, maneuverability and real-time performance) relative to the root node (strike effectiveness) are calculated respectively.

[0027] Reference sequence: Select the maximum and minimum values ​​of the child nodes as the reference sequence. Assuming there are n evaluation indicators, two reference sequences can be obtained, namely the maximum reference sequence and the minimum reference sequence. , the minimum reference sequence , i is the serial number of the evaluation index, is the number of evaluation indicators, is the maximum reference value of the i-th evaluation index, is the minimum reference value of the i-th evaluation indicator.

[0028] Evaluation sequence: It is composed of the actual values ​​of evaluation indicators at different times. , where j is the time value.

[0029] In order to eliminate the influence of the dimensions and magnitudes of different evaluation indicators and make them comparable, the evaluation sequence is standardized using the range method. The standardized sequence is , is the dimensionless value of the i-th evaluation index at the j-th moment, and its calculation formula is: In the formula, is the actual value of the i-th evaluation indicator at the j-th moment, is the minimum value at the jth moment in the evaluation sequence; is the maximum value at the jth moment in the evaluation sequence.

[0030] The grey correlation algorithm is used to balance the correlation between the evaluation sequence and the reference sequence, and the maximum correlation coefficient of the i-th evaluation index at the j-th moment is used. and the minimum correlation coefficient of the i-th evaluation index at the j-th moment express: In the formula, ρ is the resolution coefficient, which is 0.5; is the minimum difference between the two levels; is the maximum difference between the two levels.

[0031] Grey relational depth coefficient for: The average correlation degree of each evaluation indicator on all evaluation objects and the standard deviation of the correlation for: Where m is the number of evaluation sequences; other parameters are defined as above.

[0032] According to the coefficient of variation method, the weight of each evaluation indicator is equal to its coefficient of variation divided by the sum of the coefficients of variation of all evaluation indicators, and then normalized to obtain the weight of the evaluation indicator. , the calculation formula is as follows: In the formula, is the coefficient of variation of the i-th evaluation indicator; is the weight of the i-th evaluation indicator; other parameters are defined as above.

[0033] The present invention uses the grey correlation algorithm and the coefficient of variation method to determine the weights of the evaluation indicators, comprehensively considers the correlation between multiple evaluation indicators and the volatility of data, and makes the weight distribution of multiple evaluation indicators more objective.

[0034] S3: Use the Euclidean distance measurement algorithm or the weighted Bayesian algorithm to determine the strike benefit value of the drone to the target at the current moment; construct a weighted dynamic Bayesian algorithm based on the weighted Bayesian algorithm, and determine the strike benefit value between the drone and its matching target according to the strike benefit value of the drone to the target at the current moment and the weighted dynamic Bayesian algorithm.

[0035] Step S3 is specifically as follows: using the Euclidean distance measurement algorithm to compare and judge the similarity of the evaluation indicators at different moments, and determining the strike benefit value of the drone against the target at the current moment according to the similarity judgment results of the evaluation indicators at different moments or the weighted Bayesian algorithm. Specifically, the Euclidean distance measurement algorithm is used to judge the similarity of the evaluation indicators corresponding to two adjacent moments. If the similarity is less than the similarity threshold, the strike benefit value at the previous moment is used as the strike benefit value of the drone against the target at the current moment; if the similarity exceeds the similarity threshold, the strike benefit value of the drone against the target at the current moment is determined according to the weighted Bayesian algorithm.

[0036] The evaluation sequence of the evaluation index at time (j-1) is set to , the evaluation sequence of the evaluation index at time j is , the weight vector of the evaluation index , n is the number of evaluation indicators, calculated by the Euclidean distance metric algorithm and The similarity between .

[0037] A similarity threshold δ is set. If the similarity of the evaluation indicators corresponding to two adjacent moments is less than the similarity threshold, the strike benefit value of the previous moment is used as the strike benefit value of the UAV to the target at the current moment; if the similarity of the evaluation indicators corresponding to two adjacent moments exceeds the similarity threshold, the strike benefit value of the UAV to the target at the current moment is determined according to the weighted Bayesian algorithm.

[0038] The weighted Bayesian algorithm weakens the independence assumption of the evaluation indicators by weighting, and can more accurately evaluate the effectiveness of drone strikes at each moment.

[0039] (1) A Bayesian network is a directed acyclic graph that represents the probabilistic dependency between variables. The conditional independence assumption implied in the Bayesian network assumes that the sub-nodes in the conditional node background network are independent of each other. However, in practical applications, given the common correlation between multiple evaluation indicators, the independence assumption needs to be adjusted. In order to improve the overall evaluation performance, different weights are assigned to each node variable to enhance the connection between nodes, thereby weakening the existing independence assumption and achieving a more accurate and comprehensive strike effectiveness evaluation. Among them, the weighted Bayesian algorithm is: In the formula, is the value state of the kth root node; the number of k root nodes; For the The value status of the child nodes, is the number of child nodes; the root node prior probability distribution , the conditional probability distribution of child nodes and the weight of the i-th evaluation indicator Deriving the Posterior Probability ; is the root node The collection of child nodes.

[0040] (2) Based on the weighted Bayesian algorithm, the weighted Bayesian algorithm is combined with time series data to form a dynamic Bayesian network. In the weighted dynamic Bayesian algorithm, the state transition probability between two moments is set, that is, the prior probability of the strike benefit is dynamically updated at each moment. is the state transition probability matrix; is the posterior probability of hitting the benefit node at the current moment and the prior probability of hitting the benefit at the next moment It can be expressed as: In the formula, the posterior probability of attacking the benefit node at the current moment is Equal to the posterior probability of the current strike effect .

[0041] S4: Determine the matching rate between the drone and the target; Step S4 is specifically as follows: determining the threat level of the target, matching the drone with the target according to the threat level of the target and the strike effectiveness value between the drone and the target it matches, and determining the matching rate. Specifically, one drone corresponds to one target and one strike effectiveness value; that is, the correspondence between multiple drones and multiple targets is: each drone corresponds to the strike effectiveness value of one target.

[0042] S5: Determine the combat performance evaluation value of the UAV based on the strike effectiveness data set and the matching rate, and evaluate the combat performance of the UAV according to the combat performance evaluation value of the UAV.

[0043] Among them, the calculation formula for determining the combat performance evaluation value of the drone based on the strike effectiveness data set and the matching rate is: Where E is the combat performance evaluation value of the UAV; (P1, P2, ..., P d ) is the strike effectiveness dataset; d is the number of drones; is the weight factor of the strike effect, with a value range of 0.40 to 0.65; is the weight factor of the matching rate, ranging from 0.35 to 0.60; M is the matching rate, which is the ratio of the predicted number of matches to the actual number of matches.

[0044] The combat performance evaluation method of the UAV of the present invention is compared with the existing comprehensive algorithm. Under the given prior probability, state transition probability and the observed variable values ​​at different times, the weighted dynamic Bayesian algorithm is substituted to calculate the probability that the strike benefit level belongs to each state at different times. The specific results are shown in Table 3. The weights of the evaluation indicators are determined by the grey correlation algorithm as (0.153, 0.136, 0.121, 0.148, 0.161, 0.124, 0.057, 0.1).

[0045] By comparing Table 2 and Table 3, it can be seen that at T1, the parameters of multiple evaluation indicators of the drone's perception and tracking capabilities are at a low level. Although real-time performance has certain advantages, the strike benefit level is still judged to be low. At T3, the relative speed of the drone has increased, and the parameters of perception and tracking capabilities have also reached a medium level. However, real-time performance has decreased, and the strike benefit level is judged to be medium. At T4, the parameters of the drone's perception and tracking capabilities are at a high level, and real-time performance is also at a medium level, so the strike benefit level is judged to be high.

[0046] Table 2: Observation node variable data at different times Table 3: Probability of strike effectiveness level at different times See also Figure 4 , the strike benefit probabilities obtained at time T1 and time T2 are similar. Since the observed variable values ​​at time T2 and time T1 show similarity after similarity measurement calculation, the strike benefit level probabilities of the UAV combat performance evaluation method of the present invention are the same at the two times.

[0047] See also Figure 2 , the present invention also provides a UAV combat performance evaluation system, which is applied to the above-mentioned UAV combat performance evaluation method, including a Bayesian network construction module, an improvement module, a strike benefit value determination module, a strike benefit data set determination module, a matching module and a combat performance evaluation module; A Bayesian network building module is used to determine multiple evaluation indicators of the combat performance of the UAV and to build a Bayesian network based on the correlation between the multiple evaluation indicators; Improvement module: used to improve the Bayesian network using the grey correlation algorithm to form a weighted Bayesian algorithm; The strike benefit value determination module is used to determine the strike benefit value of the UAV to the target at the current moment by using the Euclidean distance measurement algorithm or the weighted Bayesian algorithm; it is used to construct a weighted dynamic Bayesian algorithm based on the weighted Bayesian algorithm, and determine the strike benefit value between the UAV and its matching target according to the strike benefit value of the UAV to the target at the current moment and the weighted dynamic Bayesian algorithm; Strike effectiveness data set determination module: used to repeat the improvement module and the strike effectiveness value determination module until the strike effectiveness values ​​between all drones and their matching targets are determined to form a strike effectiveness data set; Matching module: used to determine the matching rate between the drone and the target; And a combat performance evaluation module: used to determine the combat performance evaluation value of the UAV based on the strike effectiveness data set and the matching rate, and evaluate the combat performance of the UAV according to the combat performance evaluation value of the UAV.

[0048] The UAV combat performance evaluation system of the present invention corresponds to the above-mentioned UAV combat performance evaluation method, wherein the specific contents of the Bayesian network construction module, improvement module, strike effectiveness value determination module, strike effectiveness data set determination module, matching module and combat performance evaluation module refer to the description of the above-mentioned UAV combat performance evaluation method part, and the present invention will not be repeated here.

[0049] The present invention also provides a memory on which a program file is stored. The program file is executed to implement program instructions formed by the above-mentioned UAV combat performance evaluation method.

[0050] The memory in the present invention may specifically include random access memory (RAM), internal memory, read-only memory (ROM), programmable ROM, erasable programmable ROM, register, hard disk, removable disk or CD-ROM. It should be noted that those skilled in the art may specifically select the form and type of storage medium according to actual use requirements, and the present invention does not make further specific limitations.

[0051] The present invention also provides an electronic device, including a processor and a memory coupled to each other, wherein the memory is used to store program instructions formed by the above-mentioned UAV combat performance evaluation method; and the processor is used to execute the program instructions stored in the memory.

[0052] The electronic device in the present invention includes any electronic device that can execute program instructions, such as a computer, a mobile terminal, a remote control device or a wearable device.

[0053] The above content is only used to illustrate the technical solution of the present invention, rather than to limit the present invention. Although the present invention has been described in detail with reference to the foregoing, a person skilled in the art should understand that the technical solution described above can still be modified, or part or all of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not make the essence of the corresponding technical solution deviate from the scope of the technical solution of the present invention.

Claims

1. A method for evaluating the combat performance of an unmanned aerial vehicle, characterized in that: The following steps are involved: Determine multiple evaluation indicators of UAV combat performance, and construct a Bayesian network based on the correlation between multiple evaluation indicators; The Bayesian network is improved by using the grey correlation algorithm to form a weighted Bayesian algorithm; The Euclidean distance measurement algorithm or the weighted Bayesian algorithm is used to determine the strike benefit value of the UAV against the target at the current moment; a weighted dynamic Bayesian algorithm is constructed based on the weighted Bayesian algorithm, and the strike benefit value between the UAV and its matching target is determined according to the strike benefit value of the UAV against the target at the current moment and the weighted dynamic Bayesian algorithm; Repeat the above steps until the strike benefit values ​​between all drones and their matching targets are determined to form a strike benefit data set; Determine the match rate between the drone and the target; The combat performance evaluation value of the UAV is determined based on the strike effectiveness data set and the matching rate, and the combat performance of the UAV is evaluated according to the combat performance evaluation value of the UAV.

2. The method for evaluating the combat performance of an unmanned aerial vehicle according to claim 1, characterized in that: The method of improving the Bayesian network by using the grey correlation algorithm to form a weighted Bayesian algorithm specifically includes: The grey correlation algorithm is used to assign different weights to each node of the Bayesian network. The weights of each child node relative to the root node in the Bayesian network are determined by combining the different weights of each node, thus forming a weighted Bayesian algorithm.

3. The method for evaluating the combat performance of an unmanned aerial vehicle according to claim 1 or 2, characterized in that: The method of using the Euclidean distance measurement algorithm or the weighted Bayesian algorithm to determine the strike benefit value of the drone on the target at the current moment specifically includes: The Euclidean distance measurement algorithm is used to compare and judge the similarity of the evaluation indicators at different times, and the strike benefit value of the UAV on the target at the current moment is determined based on the similarity judgment results of the evaluation indicators at different times or the weighted Bayesian algorithm.

4. The method for evaluating the combat performance of a UAV according to claim 3, characterized in that: The method of using the Euclidean distance measurement algorithm to compare and judge the similarity of evaluation indicators at different times, and determining the strike benefit value of the drone against the target at the current moment according to the similarity judgment results of the evaluation indicators at different times or the weighted Bayesian algorithm specifically includes: The Euclidean distance measurement algorithm is used to determine the similarity of the evaluation indicators corresponding to two adjacent moments. If the similarity is less than the similarity threshold, the strike benefit value of the previous moment is used as the strike benefit value of the UAV to the target at the current moment; if the similarity exceeds the similarity threshold, the strike benefit value of the UAV to the target at the current moment is determined according to the weighted Bayesian algorithm.

5. The method for evaluating the combat performance of a UAV according to claim 1, characterized in that: The weighted dynamic Bayesian algorithm based on the weighted Bayesian algorithm specifically includes: Time series data is added to the weighted Bayesian algorithm to construct a weighted dynamic Bayesian algorithm.

6. The method for evaluating the combat performance of a UAV according to claim 1, characterized in that: Determining the matching rate between the drone and the target specifically includes: Determine the threat level of the target, match the drone with the target based on the threat level of the target and the strike effectiveness value between the drone and its matching target, and determine the matching rate.

7. The method for evaluating the combat performance of a UAV according to claim 1, characterized in that: The evaluation indicators include strike effectiveness, perception capability, tracking capability, maneuverability and real-time performance; among them, the perception capability includes false alarm rate, missed detection rate and positioning accuracy, and the maneuverability includes relative speed, relative altitude and heading angle.

8. A UAV combat performance evaluation system, applied to the UAV combat performance evaluation method according to claim 1, characterized in that: include: A Bayesian network building module is used to determine multiple evaluation indicators of the combat performance of the UAV and to build a Bayesian network based on the correlation between the multiple evaluation indicators; Improvement module: used to improve the Bayesian network using the grey correlation algorithm to form a weighted Bayesian algorithm; The strike benefit value determination module is used to determine the strike benefit value of the UAV to the target at the current moment by using the Euclidean distance measurement algorithm or the weighted Bayesian algorithm; it is used to construct a weighted dynamic Bayesian algorithm based on the weighted Bayesian algorithm, and determine the strike benefit value between the UAV and its matching target according to the strike benefit value of the UAV to the target at the current moment and the weighted dynamic Bayesian algorithm; Strike effectiveness data set determination module: used to repeat the improvement module and the strike effectiveness value determination module until the strike effectiveness values ​​between all drones and their matching targets are determined to form a strike effectiveness data set; Matching module: used to determine the matching rate between the drone and the target; And a combat performance evaluation module: used to determine the combat performance evaluation value of the UAV based on the strike effectiveness data set and the matching rate, and evaluate the combat performance of the UAV according to the combat performance evaluation value of the UAV.

9. A memory, characterized in that A program file is stored, and the program file is executed to implement program instructions formed by the method for evaluating the combat performance of a UAV as described in any one of claims 1 to 7.

10. An electronic device, characterized in that The invention comprises a processor and a memory coupled to each other, wherein: The memory is used to store program instructions formed by the method for evaluating the combat performance of a UAV according to any one of claims 1 to 7; The processor is used to execute program instructions stored in the memory.

Images