An air target recognition method and system based on fuzzy reasoning

Abstract

The embodiment of the application provides a kind of method and system for identifying air target based on fuzzy inference, it is related to target identification technical field.The method for identifying air target based on fuzzy inference includes: obtaining the multiple flight data corresponding to target aircraft at multiple times;According to the fuzzy processing of multiple flight data by preset flight parameter, generate multiple input variable fuzzy data;According to the multiple input variable fuzzy data obtained by preset intuitionistic fuzzy inference model and multiple output variable fuzzy data;The comprehensive identification result is obtained by fusing multiple output variable fuzzy data.The method for identifying air target based on fuzzy inference can realize the technical effect of the accuracy of air target identification.

Description

Technical Field

[0001] This application relates to the field of target recognition technology, and more specifically, to an aerial target recognition method, system, electronic device, and computer-readable storage medium based on fuzzy reasoning. Background Technology

[0002] Currently, aerial target friend-or-foe identification (AFF) is one of the means of military confrontation between opposing sides in modern air warfare. It plays a vital role in reducing the probability of friendly fire and collateral damage, improving combat response speed, and strengthening coordination among various combat units. With the rapid development of military technology and the application of various advanced weapons and equipment, in the face of complex and massive amounts of air situation information, accurate and efficient identification of aerial targets' friend-or-foe attributes is of great significance for grasping the air battlefield situation and seizing the initiative. In existing technologies, aerial target friend-or-foe identification is relatively rarely integrated with battlefield airspace control activities, and its tactical value is not closely aligned with actual combat, resulting in relatively limited accuracy. Summary of the Invention

[0003] The purpose of this application is to provide an aerial target recognition method, system, electronic device, and computer-readable storage medium based on fuzzy reasoning, which can achieve the technical effect of accurate aerial target recognition.

[0004] This application provides an aerial target recognition method based on fuzzy reasoning, including:

[0005] Acquire multiple flight data points for the target aircraft at multiple times;

[0006] The multiple flight data are fuzzified according to preset flight parameters to generate multiple input variable fuzzy data.

[0007] Based on a preset intuitionistic fuzzy reasoning model and the fuzzy data of the multiple input variables, multiple fuzzy data of output variables are obtained;

[0008] The fuzzy data of the multiple output variables are fused to obtain a comprehensive recognition result.

[0009] In the above implementation process, based on preset flight parameters, it closely follows battlefield airspace control activities. According to the airspace control procedures (preset flight parameters) executed by the air target (target aircraft), fuzzy data is assigned to its output variables, broadening the identification range of air target identity information and realizing dynamic updates of air target identity information, thus minimizing the probability of accidental strikes and friendly fire. Algorithmically, fuzzy inference tools are used to establish corresponding inference rules, reasonably describing the correspondence between the behavioral characteristics of air targets and their friend-or-foe attributes. Multiple output variable fuzzy data are fused to process the internal uncertainties, resulting in a more scientific and reasonable identification result. Therefore, this method can achieve the technical effect of accurate air target identification.

[0010] Furthermore, the flight data includes altitude data, speed data, and heading data. The step of fuzzifying the multiple flight data according to preset flight parameters to generate multiple input variable fuzzy data includes:

[0011] Input variables are generated based on the absolute value of the difference between the preset flight parameters and the flight data;

[0012] The multiple input variable fuzzy data are generated based on the preset membership function and the input variables.

[0013] In the above implementation process,

[0014] Furthermore, the output variables in the fuzzy data of the output variables include "own people," "acquaintances," "strangers," and "enemies." Before the step of obtaining multiple fuzzy data of output variables based on a preset intuitionistic fuzzy reasoning model and the multiple input variable fuzzy data, the method further includes:

[0015] Extract the inference rules between the input variables and the output variables according to a preset rule base;

[0016] The preset intuitive fuzzy reasoning model is generated based on the reasoning rule formula between the input variables and the output variables.

[0017] In the above implementation process,

[0018] Furthermore, in the step of generating the preset intuitionistic fuzzy inference model based on the inference rule formula between the input variable and the output variable, the inference rule formula between the input variable and the output variable under a single rule is as follows:

[0019]

[0020] Where n = 1, 2, ..., N, and N is the number of reasoning rules; μ n(·) represents the membership function of each intuitive fuzzy subset corresponding to the input variable and the output variable under the nth rule; H represents altitude, V represents speed, C represents heading, FR represents friendly people, AC represents familiar people, ST represents strangers, and FO represents enemies.

[0021] In the above implementation process,

[0022] Furthermore, the step of fusing the fuzzy data of the multiple output variables to obtain a comprehensive recognition result includes:

[0023] The comprehensive recognition result is obtained by fusing the fuzzy data of the multiple output variables according to the DS evidence theory. The Mass function of the DS evidence theory is as follows:

[0024]

[0025] Among them, w l (0 < w l <1) indicates the reliability of the input data; L represents the total number of Mass functions constructed, U p Let Θ represent the intuitive fuzzy subset corresponding to the output variable, Θ be the identification framework of the DS evidence theory, and m represent the assignment of the Mass function.

[0026] In the above implementation process,

[0027] Furthermore, the step of fusing the fuzzy data of the multiple output variables according to the DS evidence theory to obtain the comprehensive recognition result includes:

[0028] The assigned value of the Mass function is modified to obtain the modified Mass function;

[0029] The modified Mass function is fused according to the DS combination rule to obtain the comprehensive recognition result.

[0030] In the above implementation process,

[0031] Secondly, embodiments of this application provide an aerial target recognition system based on fuzzy reasoning, comprising:

[0032] The acquisition module is used to acquire multiple flight data points of the target aircraft at multiple times.

[0033] The input variable module is used to fuzzify the multiple flight data according to preset flight parameters to generate multiple input variable fuzzy data.

[0034] The output variable module is used to obtain multiple output variable fuzzy data based on a preset intuitionistic fuzzy reasoning model and the multiple input variable fuzzy data;

[0035] The comprehensive recognition module is used to fuse the fuzzy data of the multiple output variables to obtain a comprehensive recognition result.

[0036] Furthermore, the flight data includes altitude data, speed data, and heading data, and the input variable module includes:

[0037] An input variable unit is used to generate input variables based on the absolute value of the difference between the preset flight parameters and the flight data.

[0038] The membership function unit is used to generate fuzzy data of the multiple input variables based on the preset membership function and the input variables.

[0039] Furthermore, the output variables in the fuzzy data include "own people," "acquaintances," "strangers," and "enemies," and the system also includes:

[0040] The extraction module is used to extract the inference rules between the input variables and the output variables according to a preset rule base;

[0041] The fuzzy reasoning module is used to generate the preset intuitive fuzzy reasoning model based on the reasoning rule formula between the input variables and the output variables.

[0042] Furthermore, the comprehensive recognition module is specifically used to fuse the fuzzy data of the multiple output variables according to the DS evidence theory to obtain the comprehensive recognition result. The Mass function of the DS evidence theory is as follows:

[0043]

[0044] Among them, w l (0 < w l <1) indicates the reliability of the input data; L represents the total number of Mass functions constructed, U p Let Θ represent the intuitive fuzzy subset corresponding to the output variable, Θ be the identification framework of the DS evidence theory, and m represent the assignment of the Mass function.

[0045] Furthermore, the integrated identification module includes:

[0046] A correction unit is used to correct the assignment of the Mass function to obtain a corrected Mass function;

[0047] The fusion unit is used to fuse the modified Mass function according to the DS combination rule to obtain the comprehensive recognition result.

[0048] Thirdly, an electronic device provided in this application includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method as described in any of the first aspects.

[0049] Fourthly, embodiments of this application provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method described in any of the first aspects.

[0050] Fifthly, embodiments of this application provide a computer program product that, when run on a computer, causes the computer to perform the method described in any of the first aspects.

[0051] Other features and advantages disclosed in this application will be set forth in the following description, or some features and advantages may be inferred from the description or determined without doubt, or may be learned by practicing the above-described technology disclosed in this application.

[0052] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0053] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 A flowchart illustrating an aerial target recognition method based on fuzzy reasoning, provided for an embodiment of this application;

[0055] Figure 2 This is a schematic diagram of the spatial location of the airspace cooperation measures provided in the embodiments of this application;

[0056] Figure 3 A flowchart illustrating another aerial target recognition method based on fuzzy reasoning provided in this application embodiment;

[0057] Figure 4 A structural block diagram of an aerial target recognition system based on fuzzy reasoning provided in an embodiment of this application;

[0058] Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0059] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0060] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0061] This application provides an aerial target identification method, system, electronic device, and computer-readable storage medium based on fuzzy reasoning, which can be applied to the identification of friendly and enemy targets in the aerial target identification process. In this fuzzy reasoning-based aerial target identification method, based on preset flight parameters, it closely follows battlefield airspace control activities. According to the aerial target's (target aircraft's) execution of airspace control procedures (preset flight parameters), it assigns fuzzy data to its output variables, broadening the identification range of aerial target identity information and realizing dynamic updates of aerial target identity information, thus minimizing the probability of accidental strikes and friendly fire. The algorithm uses fuzzy reasoning tools to establish corresponding reasoning rules, reasonably describing the correspondence between the aerial target's behavioral characteristics and friendly / enemy attributes. It also fuses multiple output variable fuzzy data to process internal uncertainties, obtaining a more scientific and reasonable identification result. Therefore, this method can achieve the technical effect of accurate aerial target identification.

[0062] For example, in modern air warfare, the main combat forces, in addition to air force units, also include air-to-air firepower, high-trajectory ground-based indirect fire, and various new unmanned combat systems. The emergence of various airspace users has led to increasingly strained battlefield airspace resources. To ensure the efficient implementation of air operations, it is essential to fully integrate airspace resources and exercise military control over the airspace. This means imposing minimal constraints on airspace users during combat operations within a unified framework of battlefield airspace control, thereby improving airspace efficiency, reducing the risk of friendly fire and collateral damage, and enhancing air combat effectiveness. Therefore, every aspect of air operations must strictly adhere to airspace control procedures to efficiently achieve the intended operational objectives.

[0063] Please see Figure 1 , Figure 1 The flowchart illustrates an aerial target recognition method based on fuzzy reasoning, which includes the following steps:

[0064] S100: Acquire multiple flight data points for the target aircraft at multiple times.

[0065] For example, in aerial target identification, flight data (flight parameters) mainly refers to flight parameters such as altitude, speed, and heading of the target aircraft during flight.

[0066] S200: Based on preset flight parameters, multiple flight data are fuzzified to generate multiple input variable fuzzy data.

[0067] For example, to reflect the degree of conformity between the actual flight parameters of an aerial target and the standard flight parameters, the absolute value of the difference between the actual data and the standard data of each flight parameter can be used as the input variable, i.e., the input variables are altitude H, speed V, and heading C. Based on the classification of friend / foe attribute labels, the output variables are determined as follows: friend FR, familiar friend AC, stranger ST, and enemy FO.

[0068] S300: Obtain multiple output variable fuzzy data based on a preset intuitionistic fuzzy reasoning model and multiple input variable fuzzy data.

[0069] For example, fuzzy reasoning is a type of indeterminate reasoning that extends mathematical logic, which is based on general set theory, by using fuzzy set theory as a descriptive tool. By pre-setting the correspondence between input and output fuzzy variable data in an intuitionistic fuzzy reasoning model, the corresponding output fuzzy variable data can be obtained from the input fuzzy variable data.

[0070] S400: Fusion of fuzzy data from multiple output variables to obtain a comprehensive recognition result.

[0071] For example, airborne target identification is a dynamic process. By fusing fuzzy data of multiple output variables, the identification results at various detection times can be integrated, thereby improving the effectiveness and accuracy of airborne target identification. Optionally, DS evidence theory can be used to fuse fuzzy data of multiple output variables to obtain a comprehensive identification result.

[0072] For example, DS evidence theory belongs to the field of artificial intelligence and was first applied to expert systems. It has the ability to process uncertain information. As an uncertain reasoning method, the main characteristics of evidence theory are: it satisfies weaker conditions than Bayesian probability theory; and it has the ability to directly express "uncertainty" and "not knowing".

[0073] In some implementations, this fuzzy reasoning-based aerial target identification method, based on preset flight parameters, closely revolves around battlefield airspace control activities. It assigns fuzzy data to the output variables based on the aerial target's (target aircraft's) execution of airspace control procedures (preset flight parameters), broadening the scope of aerial target identification information and enabling dynamic updates of aerial target identification information, thus minimizing the probability of accidental strikes or friendly fire. Algorithmically, it uses fuzzy reasoning tools to establish corresponding reasoning rules, reasonably describing the correspondence between the aerial target's behavioral characteristics and friend-or-foe attributes. Furthermore, it fuses multiple output variable fuzzy data to process internal uncertainties, obtaining a more scientific and reasonable identification result. Therefore, this method can achieve the technical effect of accurate aerial target identification.

[0074] Please see Figure 2 , Figure 2 This is a schematic diagram of the spatial location of the airspace cooperation measures provided in the embodiments of this application.

[0075] For example, aerial target friend or foe identification accompanies the entire operational process of air combat. For ease of understanding, the following will combine... Figure 2 This document explains the process of identifying friend or foe when aerial targets return to their destination within the framework of battlefield airspace control.

[0076] For example, commonly used procedural control measures mainly include airspace coordination measures such as "IFF (Identification Friend or Foe) on / off line," "minimum risk route," "low-altitude crossing corridor," and "air corridor." When an aircraft returns after completing a combat mission, to protect the safety of friendly aircraft and reduce flight conflicts with high-altitude forward-deployed combat aircraft, the aircraft usually does not return directly to friendly airports. Instead, it enters the minimum risk route according to instructions. Before entering the minimum risk route, the aircraft will activate its IFF at the on / off line for preliminary IFF identification. To avoid interference and IFF failure, while the aircraft is flying in the minimum risk route, friendly forces will continue to identify its identity information based on its flight parameters, assign different levels of attribute tags based on the identification results, and take corresponding countermeasures based on the identification results. If it can be clearly identified that the aircraft is friendly, it can be directed to return via the low-altitude crossing corridor into the air corridor.

[0077] For example, the criteria and standards for identifying friend or foe of aerial targets are not static, but constantly changing according to operational needs. At the same time, the language of some of its identification attributes also has a certain degree of ambiguity. Therefore, it is necessary to use uncertainty reasoning tools to model the method.

[0078] Please see Figure 3 , Figure 3 This is a flowchart illustrating another aerial target recognition method based on fuzzy reasoning provided in an embodiment of this application.

[0079] For example, the flight data includes altitude data, speed data, and heading data. S200: The step of fuzzifying multiple flight data according to preset flight parameters to generate multiple input variable fuzzy data includes:

[0080] S210: Generate input variables based on the absolute value of the difference between preset flight parameters and flight data;

[0081] S220: Generate fuzzy data of multiple input variables based on the preset membership function and input variables.

[0082] For example, a Gaussian membership function can be used as the membership function to describe the input and output variables, that is:

[0083] μ A (x) = exp(-(xc)) 2 / 2σ 2 (1);

[0084] γ A (x)=1-π A (x)-exp(-(xc) 2 / 2σ 2 (2);

[0085] Where, π A (x) represents the degree of hesitation, c and σ represent the center and width of the Gaussian membership function, respectively, x represents the input variable, and μ A (x) and γ A (x) represents the membership degree and non-membership degree of element x in the intuitive fuzzy set A, respectively.

[0086] Optionally, for the target aircraft's permissible deviation from the standard track range, the ranges of the input variables H, V, and C are selected as [0m, 100m], [0km / h, 50km / h], and [0°, 10°], respectively. It should be noted that the permissible deviation from the standard track range for the target aircraft is only a capability and not a limitation, and the ranges of the input variables H, V, and C can be set according to actual needs.

[0087] For example, to reduce computational load, the three input variables H, V, and C are normalized to the interval [0,1] and categorized into five classes based on the degree to which the actual flight parameters deviate from the standard: small, relatively small, medium, relatively large, and large. Their corresponding intuitionistic fuzzy subsets are as follows: Where T k (k = 1, 2, 3) represent the input variables H, V, and C, respectively.

[0088] For example, for the output variables FR, AC, ST, and FO, the four output variables FR, AC, ST, and FO are uniformly normalized to the interval [0,1], and their corresponding output results are divided into 5 levels based on their reliability: low, lower-low, medium, higher-high, and high. The corresponding intuitionistic fuzzy subsets are as follows: U p (p = 1, 2, 3, 4) represent the output variables FR, AC, ST, and FO, respectively.

[0089] For example, the output variables in the fuzzy data of output variables include "own people," "acquaintances," "strangers," and "enemies." S300: Before the step of obtaining multiple fuzzy data of output variables based on a preset intuitionistic fuzzy inference model and multiple input variable fuzzy data, the method further includes:

[0090] S301: Extract the inference rules between input and output variables based on the preset rule base;

[0091] S302: Generate a preset intuitionistic fuzzy reasoning model based on the reasoning rule formula between input and output variables.

[0092] For example, in order to enable the reasonable operation of intuitionistic fuzzy reasoning, it is necessary to extract the implication relationship (reasoning rules) between input variables and output variables from the established preset rule base.

[0093] For example, the number of membership functions corresponding to input variables H, V, and C are N respectively. H =N V =N C =5, the number of membership functions corresponding to the output variables FR, AC, ST, and FO are N respectively. FR =N AC =N ST =N FO =5. Therefore, the number of intuitive fuzzy reasoning rules for identifying friend or foe of aerial targets is N = N H ×N V ×N C =125. Therefore, its multi-dimensional reasoning rules are as follows:

[0094] IF h is H i AND v is V i AND c is C i THEN fr is FR j AND ac is AC j AND stis ST j AND fo is FO j .

[0095] Where i = j = 1, 2, 3, 4, 5; H, V, and C are all input variables; FR, AC, ST, and FO are all output variables.

[0096] Intuitive fuzzy reasoning rules for aerial target identification need to be established based on the experience of experts in relevant fields. Some of the rules are shown in Table 1:

[0097] Table 1 Rules for Inferring Foe and Foe in Aerial Targets

[0098]

[0099] For example, in step S301: generating a preset intuitionistic fuzzy inference model based on the inference rule formula between input variables and output variables, the inference rule formula between input variables and output variables under a single rule is as follows:

[0100]

[0101] Where n = 1, 2, ..., N, and N is the number of reasoning rules; μ n (·) represents the membership function of each intuitive fuzzy subset corresponding to the input and output variables under the nth rule; H represents altitude, V represents speed, C represents heading, FR represents friendly forces, AC represents familiar people, ST represents strangers, and FO represents enemies.

[0102] For example, the "∨-∧" composition rule is used for inference operations, and the comprehensive fuzzy implication relations under all inference rules are as follows:

[0103]

[0104] Let the input variables at a certain moment be H′, V′, and C′. According to the inference rules, the corresponding fuzzy output can be obtained as follows:

[0105]

[0106] To achieve a smoother fuzzy inference output, the centroid method is selected as the defuzzification algorithm, and the fuzzy output obtained by equation (5) is defuzzified to obtain the output values ​​corresponding to the output variables FR, AC, ST, and FO.

[0107] For example, S400: The step of fusing fuzzy data of multiple output variables to obtain a comprehensive recognition result includes:

[0108] S410: Based on the DS evidence theory, fuzzy data of multiple output variables are fused to obtain a comprehensive recognition result. The Mass function of the DS evidence theory is as follows:

[0109]

[0110] Among them, w l (0 < w l <1) indicates the reliability of the input data; L represents the total number of Mass functions constructed, U p Θ represents the intuitive fuzzy subset corresponding to the output variable, Θ is the identification framework of the DS evidence theory, and m represents the assignment of the Mass function.

[0111] For example, the DS evidence theory is used to fuse the obtained intuitionistic fuzzy reasoning results (fuzzy data of multiple input variables) to obtain a comprehensive identification result; among them, the output variables FR, AC, ST, and FO are the results required for air target friend or foe identification, serving as the identification framework Θ of the DS evidence theory. For example, the fuzzy output of equation (5) and the output value after defuzzification can be regarded as components of the basic probability assignments of each Mass function, that is, the output values ​​corresponding to FR, AC, ST, and FO reflect the distribution of the basic probability assignments corresponding to these four pieces of evidence. Therefore, by normalizing them, the assignments of each Mass function can be obtained.

[0112] For example, S410: The step of fusing fuzzy data of multiple output variables according to the DS evidence theory to obtain a comprehensive recognition result includes:

[0113] The assignment to the Mass function is modified to obtain the modified Mass function;

[0114] The modified Mass function is fused according to the DS combination rule to obtain a comprehensive recognition result.

[0115] For example, in order to minimize the impact of uncertain information during the fusion process, the basic probability assignment of the Mass function needs to be modified to improve the effectiveness of aerial target recognition.

[0116] For example, since the conflict coefficient k is not a perfect description of conflict information, the conflict information of the evidence is described by combining the conflict coefficient k and the Jousselme distance, and the evidence discounting method is used to correct each Mass function.

[0117] First, calculate the Jousselme distance for each Mass function, using the following formula:

[0118]

[0119] Where l,s=1,2,…,L;m l m s This is the vector form of the corresponding Mass function; This is a similarity matrix. Then, the conflict coefficient k is combined with the result of the Jousselme distance to obtain the combined conflict metric coefficient cf, and thus the weights α of each Mass function are obtained as follows:

[0120]

[0121] Then, by using the evidence discounting method to correct each Mass function, we can obtain the corrected Mass function, as follows:

[0122]

[0123] Among them, the discount factor α max =max(α) l ).

[0124] For example, the modified Mass function described above can be fused using the DS combination rule, as follows:

[0125]

[0126] The final result obtained by fusing through equation (10) is as follows:

[0127] m = [m(U 1 ),m(U 2 ),m(U 3 ),m(U 4 ),m(Θ)];

[0128] Then the mass function m with the largest basic probability assignment value m max (U p The attribute label corresponding to the target is the final identification result of the aerial target.

[0129] In some implementation scenarios, it is known that five groups of targets are flying towards our lowest-risk flight path. Due to enemy electronic jamming, the IFF (Identification Friend or Foe) responses of all five groups of targets are "chaotic." Therefore, airspace coordination measures are needed for identification. The standard flight altitude is set at 900m, speed at 500km / h, and heading at 30°. To verify the rationality of this aerial target IFF method, we assume that target 1 is friendly and its aircraft is in good condition; target 2 is also friendly, but its aircraft has suffered minor damage during the mission and its flight attitude has a slight deviation; target 3 is friendly, but its aircraft has suffered severe damage during combat and its flight attitude is difficult to control; target 4 is enemy, attempting to infiltrate our airspace to strike important targets; and target 5 is enemy, lacking knowledge of our flight parameters, attempting to force its way in and strike. The actual flight parameters of the five groups of targets are shown in Table 2.

[0130] Table 2 Actual Flight Parameters of Aerial Targets

[0131]

[0132] Based on the data in Table 2, the values ​​of the input variables H, V, and C corresponding to each time step from target 1 to 5 can be obtained. Then, these values ​​are converted into normalized inputs and subjected to intuitionistic fuzzy inference to obtain the inference results for each time step from target 1 to 5, as shown in Table 3.

[0133] Table 3 Results of Intuitive Fuzzy Reasoning for Identifying Foe and Foe of Aerial Targets

[0134]

[0135] Let w l =0.9. Based on the data in Table 3, the basic probability assignments for each detection cycle of target 1-5 can be obtained by equation (6). The basic probability assignments are corrected and fused by equations (7)-(10) to obtain the final friend-or-foe identification results, as shown in Table 4.

[0136] Table 4 Basic Probability Assignments for Identification of Airborne Targets (Friend or Foe)

[0137]

[0138] To avoid incorrect classifications due to excessively low numerical values ​​in the identified results, a discrimination threshold c = 0.05 is introduced as a criterion for judging the reasonableness of the fused recognition results. This means selecting the two recognition results m with the highest assigned basic probabilities from the fused recognition results. max1 and m max2 If |m max1 -m max2 |≥c, then the identification is considered valid, and m max1 The result for this is the final identification result; if |m max1 -m max2 If | < c, then the identification is considered invalid and the identification of the target needs to be continued.

[0139] As shown in Table 4, targets 1 and 2 were ultimately identified as friendly, target 4 as a stranger, and target 5 as an enemy. This is largely consistent with the experimental scenario and meets the expected experimental objectives. Target 3 was identified as a familiar person, but the specific data shows that the algorithm assigned a base probability of 0.307 for being a familiar person and a base probability of 0.301 for being a stranger. The absolute value of the difference is 0.006, which is less than the discrimination threshold. Therefore, this identification result is invalid and further identification is required. The actual flight data of target 3 after three detection cycles is shown in Table 5.

[0140] Table 5 Actual Flight Parameters of Target 3

[0141]

[0142] The corresponding fuzzy inference results are shown in Table 6:

[0143] Table 6. Results of Intuitive Fuzzy Reasoning for Actual Flight Parameters of Target 3

[0144]

[0145] Similarly, the basic probability values ​​for target 3 in cycles 4-6 are obtained and fused with the basic probability values ​​for the first 3 cycles to obtain the final recognition result. See Table 7:

[0146] Table 7. Basic probability assignment and fusion results for Target 3.

[0147]

[0148]

[0149] Based on the data obtained from Table 7, the two identification results with the highest basic probability assignment values ​​for target 3, "one of us" and "acquaintances", were selected. The absolute value of the difference between their basic probability assignment values ​​was calculated to be 0.219, which is greater than the discrimination threshold. Therefore, the identification result is valid.

[0150] In summary, as can be seen from Tables 2 and 4:

[0151] 1) Target 1 is an ally, because it had mastered the relevant requirements for entering the minimum risk flight route before carrying out the mission, and its flight parameters at the three moments were constantly close to the prescribed standards. Therefore, the final identification result is an ally, which is consistent with the preset experimental scenario.

[0152] 2) Target 2 is an ally. Although it suffered some damage during the mission, causing slight fluctuations in flight parameters at three points, it mastered the relevant flight requirements and continuously controlled the aircraft to fly according to the prescribed standards. Therefore, the final identification result is also an ally, which is consistent with the preset scenario.

[0153] 3) Target 3 is an acquaintance with a "friendly" tendency. Due to the severe damage to the aircraft during the flight mission, it was difficult to maintain its flight attitude in the first three moments, resulting in the identification result of an acquaintance. However, the identification result did not meet the discrimination requirements. Subsequently, we continued to detect it for 3 cycles and fused the identification results of 6 cycles for judgment. As shown in Table 7, the final identification result of the target is "acquaintance". Although there is a certain difference from the expected experimental scenario, it avoids misjudgment in such cases and thus meets the expected experimental purpose.

[0154] 4) Target 4 is a stranger with "hostile" tendencies. This target attempted to disguise itself and infiltrate our airspace by stealing the flight parameters of targets 1, 2 and 3. Because it did not master the flight method to enter the least risk route, although its flight attitude was relatively stable at the three moments, it did not meet our specified flight standards. Therefore, it was finally identified as a stranger. Although it deviated from the preset scenario to some extent, the expected identification purpose was achieved in general.

[0155] 5) Target 5 is the enemy. Since it does not know our flight parameters and intends to quickly break through our defenses and strike us, the final identification result is "enemy", which is consistent with the expected scenario and meets the expected experimental purpose.

[0156] Based on the final identification results, the commander can make corresponding decisions, such as: instructing Target 1 to enter the low-to-high-level passageway for a return flight; instructing Target 2 to return and prepare for aircraft maintenance and support; instructing Target 3 to land at the nearest alternate landing site, prepare for emergency repair and support, and dispatch search and rescue aircraft to accompany it to ensure Target 3's flight safety. Closely monitor Target 4, instruct it to circle and wait, and dispatch friendly aircraft to verify and intercept Target 4. If the target does not comply with instructions or is verified as an enemy, it can be shot down; for Target 5, immediate measures should be taken to shoot it down.

[0157] For example, aerial target identification (AMI), as an important component of air combat operations, is closely integrated with battlefield airspace control activities. The aerial target identification method proposed in this application closely revolves around airspace control activities, proposing an AMI process and discrimination criteria within this framework, which closely aligns with actual combat. Furthermore, mathematical tools such as intuitionistic fuzzy reasoning and evidence theory are used to model and verify the method, demonstrating its rationality and reliability.

[0158] Please see Figure 4 , Figure 4 This is a structural block diagram of an aerial target recognition system based on fuzzy reasoning provided in an embodiment of this application. The fuzzy reasoning-based aerial target recognition system includes:

[0159] The acquisition module 100 is used to acquire multiple flight data of the target aircraft at multiple times;

[0160] The input variable module 200 is used to perform fuzzification processing on multiple flight data according to preset flight parameters to generate multiple input variable fuzzy data.

[0161] The output variable module 300 is used to obtain multiple output variable fuzzy data based on a preset intuitionistic fuzzy inference model and multiple input variable fuzzy data.

[0162] The comprehensive recognition module 400 is used to fuse fuzzy data of multiple output variables to obtain a comprehensive recognition result.

[0163] For example, the flight data includes altitude data, speed data, and heading data, and the input variable module 200 includes:

[0164] The input variable unit is used to generate input variables based on the absolute value of the difference between preset flight parameters and flight data.

[0165] The membership function unit is used to generate fuzzy data of multiple input variables based on a preset membership function and input variables.

[0166] For example, the output variables in the fuzzy data include "own people," "acquaintances," "strangers," and "enemies." The system also includes:

[0167] The extraction module is used to extract the inference rules between input and output variables based on a preset rule base.

[0168] The fuzzy reasoning module is used to generate a preset intuitive fuzzy reasoning model based on the reasoning rule formula between input and output variables.

[0169] For example, the comprehensive recognition module 400 is specifically used to fuse fuzzy data of multiple output variables according to the DS evidence theory to obtain a comprehensive recognition result. The Mass function of the DS evidence theory is as follows:

[0170]

[0171] Among them, w l (0 < w l <1) indicates the reliability of the input data; L represents the total number of Mass functions constructed, U p Θ represents the intuitive fuzzy subset corresponding to the output variable, Θ is the identification framework of the DS evidence theory, and m represents the assignment of the Mass function.

[0172] For example, the integrated identification module 400 includes:

[0173] The correction unit is used to correct the assignment of the Mass function to obtain the corrected Mass function;

[0174] The fusion unit is used to fuse the modified Mass function according to the DS combination rule to obtain the comprehensive recognition result.

[0175] This application also provides an electronic device, please refer to [link to application]. Figure 5 , Figure 5This is a structural block diagram of an electronic device provided in an embodiment of this application. The electronic device may include a processor 510, a communication interface 520, a memory 530, and at least one communication bus 540. The communication bus 540 is used to enable direct communication between these components. In this embodiment, the communication interface 520 of the electronic device is used for signaling or data communication with other node devices. The processor 510 may be an integrated circuit chip with signal processing capabilities.

[0176] The processor 510 described above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor, or the processor 510 can be any conventional processor.

[0177] The memory 530 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc. The memory 530 stores computer-readable instructions. When these computer-readable instructions are executed by the processor 510, the electronic device can perform the aforementioned operations. Figures 1 to 3 The various steps involved in the method implementation examples.

[0178] Alternatively, the electronic device may also include a storage controller and an input / output unit.

[0179] The memory 530, storage controller, processor 510, peripheral interface, and input / output unit are electrically connected directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses 540. The processor 510 is used to execute executable modules stored in the memory 530, such as software function modules or computer programs included in electronic devices.

[0180] The input / output unit is used to provide users with the ability to create tasks and to set optional start periods or preset execution times for those tasks, thereby enabling user-server interaction. The input / output unit may be, but is not limited to, a mouse and keyboard.

[0181] Understandable. Figure 5 The structure shown is for illustrative purposes only; the electronic device may also include components that are more advanced than those shown. Figure 5 The more or fewer components shown, or having the same Figure 5 The different configurations shown. Figure 5 The components shown can be implemented using hardware, software, or a combination thereof.

[0182] This application also provides a storage medium storing instructions. When the instructions are run on a computer, the computer program is executed by a processor to implement the method described in the method embodiment. To avoid repetition, the method will not be described again here.

[0183] This application also provides a computer program product that, when run on a computer, causes the computer to perform the method described in the method embodiment.

[0184] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0185] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0186] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0187] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application. It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0188] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0189] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for aerial target recognition based on fuzzy reasoning, characterized in that, include: Acquire multiple flight data points for the target aircraft at multiple times; The multiple flight data are fuzzified according to preset flight parameters to generate multiple input variable fuzzy data. Based on a preset intuitionistic fuzzy reasoning model and the fuzzy data of the multiple input variables, multiple fuzzy data of output variables are obtained; The fuzzy data of the multiple output variables are fused to obtain a comprehensive recognition result; The output variables in the fuzzy data of the output variables include "own people," "acquaintances," "strangers," and "enemies." Before the step of obtaining multiple fuzzy data of output variables based on a preset intuitionistic fuzzy reasoning model and the multiple input variable fuzzy data, the method further includes: Extract the inference rules between the input variables and the output variables according to a preset rule base; The preset intuitive fuzzy reasoning model is generated based on the inference rule formula between the input variables and the output variables; In the step of generating the preset intuitionistic fuzzy inference model based on the inference rule formula between the input variable and the output variable, the inference rule formula between the input variable and the output variable under a single rule is as follows: ； in , The number of reasoning rules; Indicates the first Under these rules, the membership functions of each intuitive fuzzy subset corresponding to the input variable and the output variable are: H represents altitude, V represents speed, C represents heading, FR represents friendly forces, AC represents familiar people, ST represents strangers, and FO represents enemies.

2. The aerial target recognition method based on fuzzy reasoning according to claim 1, characterized in that, The flight data includes altitude data, speed data, and heading data. The step of fuzzifying the multiple flight data according to preset flight parameters to generate multiple input variable fuzzy data includes: Input variables are generated based on the absolute value of the difference between the preset flight parameters and the flight data; The multiple input variable fuzzy data are generated based on the preset membership function and the input variables.

3. The aerial target recognition method based on fuzzy reasoning according to claim 1, characterized in that, The step of fusing the fuzzy data of the multiple output variables to obtain a comprehensive recognition result includes: The comprehensive recognition result is obtained by fusing the fuzzy data of the multiple output variables according to the DS evidence theory. The Mass function of the DS evidence theory is as follows: ； in, Indicates the reliability of the input data; This represents the total number of Mass functions constructed. U p This represents the intuitive fuzzy subset corresponding to the output variable. This forms the identification framework for the DS evidence theory. m This indicates the assignment of the Mass function.

4. The aerial target recognition method based on fuzzy reasoning according to claim 3, characterized in that, The step of fusing the fuzzy data of the multiple output variables according to the DS evidence theory to obtain the comprehensive recognition result includes: The assigned value of the Mass function is modified to obtain the modified Mass function; The modified Mass function is fused according to the DS combination rule to obtain the comprehensive recognition result.

5. An aerial target recognition system based on fuzzy reasoning, characterized in that, include: The acquisition module is used to acquire multiple flight data points of the target aircraft at multiple times. The input variable module is used to fuzzify the multiple flight data according to preset flight parameters to generate multiple input variable fuzzy data. The output variable module is used to obtain multiple output variable fuzzy data based on a preset intuitionistic fuzzy reasoning model and the multiple input variable fuzzy data; The comprehensive recognition module is used to fuse the fuzzy data of the multiple output variables to obtain a comprehensive recognition result; The output variables in the fuzzy data include "own people," "acquaintances," "strangers," and "enemies." The system also includes: The extraction module is used to extract the inference rules between the input variables and the output variables according to a preset rule base; The fuzzy inference module is used to generate the preset intuitive fuzzy inference model based on the inference rule formula between the input variables and the output variables. The comprehensive recognition module is specifically used to fuse the fuzzy data of the multiple output variables according to the DS evidence theory to obtain the comprehensive recognition result. The Mass function of the DS evidence theory is as follows: ； in, Indicates the reliability of the input data; This represents the total number of Mass functions constructed. U p This represents the intuitive fuzzy subset corresponding to the output variable. This forms the identification framework for the DS evidence theory. m This indicates the assignment of the Mass function.

6. The aerial target recognition system based on fuzzy reasoning according to claim 5, characterized in that, The flight data includes altitude data, speed data, and heading data, and the input variable module includes: An input variable unit is used to generate input variables based on the absolute value of the difference between the preset flight parameters and the flight data. The membership function unit is used to generate fuzzy data of the multiple input variables based on the preset membership function and the input variables.

7. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the fuzzy reasoning-based aerial target recognition method as described in any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the fuzzy inference-based aerial target recognition method as described in any one of claims 1 to 4.

Images