Task allocation method for multi-aircraft coordinated attack on multiple targets

Abstract

The present application belongs to the technical field of task allocation, and relates to a task allocation method for multiple aircraft to coordinately strike multiple targets, including: obtaining a scenario of multiple aircraft to coordinately strike multiple targets, obtaining the inherent characteristics of the aircraft, the inherent information of the target, and the relative motion information between the aircraft and the target, and calculating the comprehensive performance index of task allocation; establishing a task allocation model according to the comprehensive performance index of task allocation; in the task allocation model, each aircraft has a corresponding strike target, each target is covered, and the coordination time constraint is satisfied; establishing a genetic algorithm with the comprehensive performance index of task allocation as the fitness function; solving the task allocation model with the genetic algorithm, and taking the optimal solution of the genetic algorithm as the task allocation scheme. The present application can realize the coordinated strike of multiple targets by multiple aircraft.

Description

Technical Field

[0001] The present application relates to the technical field of task allocation, and in particular to a task allocation method for multiple aircraft to coordinately attack multiple targets. Background Art

[0002] In the mission scenario of multiple aircrafts coordinating to strike multiple targets, task allocation is required, taking into account the attack advantages of the aircrafts themselves to different targets, the value of the targets themselves, flight time adjustment restrictions and other constraints. When the constraints are met, the overall strike efficiency is maximized. The allocation of targets for coordinated strikes by multiple aircrafts determines the scientificity and rationality of task allocation and is a key link in the coordinated strike mission.

[0003] When multiple aircraft are completing the same task or multiple tasks with logical relationships within the same time or space, it is necessary to consider time, space, and effect, and reasonably allocate tasks to obtain the best strike effect with the maximum cost-effectiveness and minimum risk. Therefore, the task allocation of multi-aircraft coordinated strike against multiple targets can be described as a multi-constraint optimization problem, which is usually also called the weapon-target assignment (WAT) method. Cooperative target allocation is a typical nonlinear polynomial complete problem. The decision space grows exponentially with the increase of the problem scale (i.e., the number of aircraft and the number of targets). The real-time, accuracy, and effectiveness of the solution will directly affect whether the best strike effect can be achieved in the process.

[0004] In the prior art, commonly used solutions include: simulated annealing algorithm, ant colony optimization algorithm, particle swarm optimization algorithm, evolutionary algorithm, etc.

[0005] However, none of the above methods can achieve the effect of multiple aircraft coordinating to strike multiple targets. Summary of the invention

[0006] Based on this, it is necessary to provide a task allocation method for multiple aircraft to coordinately strike multiple targets in response to the above-mentioned technical problems, which can realize the coordinated strike of multiple targets by multiple aircraft under the constraint of the adjustable range of aircraft strike time.

[0007] The task allocation method for multiple aircraft to cooperate in attacking multiple targets includes:

[0008] Acquire the scenario of multiple aircrafts coordinating to attack multiple targets, obtain the inherent characteristics of the aircrafts, the inherent information of the targets, and the relative motion information between the aircrafts and the targets, and obtain the comprehensive performance indicators of task allocation;

[0009] According to the comprehensive performance index of task allocation, a task allocation model is established; in the task allocation model, each aircraft has a corresponding strike target, each target is covered, and the coordination time constraint is satisfied; the coordination time constraint is: the maximum value of the lower boundary of the remaining flight time of all aircraft is less than the minimum value of the upper boundary of the remaining flight time of all aircraft;

[0010] A genetic algorithm is established with the comprehensive performance index of task allocation as the fitness function; the task allocation model is solved by the genetic algorithm, and the optimal solution of the genetic algorithm is used as the task allocation plan.

[0011] In one embodiment, for a cruise aircraft, the strike time is adjusted according to the cruise speed to obtain an adjustment range of the remaining flight time of the cruise aircraft;

[0012] For gliding aircraft, the strike time is adjusted according to the guidance law to obtain the adjustment range of the remaining flight time of the gliding aircraft.

[0013] In one embodiment, a genetic algorithm is established with the comprehensive performance index of task allocation as the fitness function, including:

[0014] Using decimal coding, the gene value represents the target, the gene position represents the aircraft, the chromosome length represents the number of aircraft, and the number of aircraft is not less than the target number, and the chromosome coding structure is obtained;

[0015] According to the chromosome coding structure, all targets are randomly filled into different gene positions, and the vacant gene positions are filled with any target to generate an initial population;

[0016] Taking the comprehensive performance index of task allocation as the fitness function, the fitness value of each individual in the initial population is calculated, and it is determined whether the fitness value meets the preset conditions;

[0017] When the fitness value does not meet the preset conditions, the evolution operation is performed and the initial population is updated to obtain the next population; the fitness value of each individual in the next population is calculated and re-judged until the fitness value meets the preset conditions, then the iteration is stopped and the optimal solution of the genetic algorithm is obtained.

[0018] In one embodiment, after generating the initial population, the method further includes:

[0019] Determine whether the chromosome encoding structure contains all targets and satisfies the coordination time constraint;

[0020] If the judgment is yes, the fitness value is calculated;

[0021] If the judgment is no, the chromosome coding structure is genetically repaired.

[0022] In one embodiment, the gene repair comprises:

[0023] When it is determined that the chromosome encoding structure does not contain all targets: detect missing gene values ​​and repeated gene values, select the missing gene value and randomly insert it into any point where the repeated gene value is located for replacement, until all missing gene values ​​are inserted into the chromosome encoding structure;

[0024] When it is determined that the chromosome coding structure does not satisfy the collaborative time constraint: detect the gene bit corresponding to the maximum value of the lower boundary of the remaining flight time of all aircraft and modify the maximum value of the lower boundary of the remaining flight time of all aircraft to repair the lower boundary; or detect the gene bit corresponding to the minimum value of the upper boundary of the remaining flight time of all aircraft and modify the minimum value of the upper boundary of the remaining flight time of all aircraft to repair the upper boundary.

[0025] In one embodiment, detecting the gene bit corresponding to the maximum value of the lower boundary of the remaining flight time of all aircraft and modifying the maximum value of the lower boundary of the remaining flight time of all aircraft to repair the lower boundary; or detecting the gene bit corresponding to the minimum value of the upper boundary of the remaining flight time of all aircraft and modifying the minimum value of the upper boundary of the remaining flight time of all aircraft to repair the upper boundary, including:

[0026] Detect the gene position corresponding to the lower boundary maximum value of the remaining flight time of all aircraft, and use the gene value set with a smaller lower boundary and less than the upper boundary minimum value as the substitute gene candidate set; randomly select the gene value in the substitute gene candidate set to replace the lower boundary maximum value to repair the lower boundary;

[0027] Detect the gene position corresponding to the upper boundary minimum value of the remaining flight time of all aircraft, and use the gene value set with a larger upper boundary and greater than the lower boundary maximum value as the substitute gene candidate set; randomly select the gene value in the substitute gene candidate set to replace the upper boundary minimum value to repair the upper boundary.

[0028] In one embodiment, if the candidate set of substitute genes for the lower boundary repair is an empty set, the upper boundary repair is performed; if the candidate set of substitute genes for the upper boundary repair is an empty set, the lower boundary repair is performed;

[0029] If the candidate sets of substitute genes for lower boundary repair and the candidate sets of substitute genes for upper boundary repair are both empty sets, any legal individual is used to replace the maximum value of the lower boundary or the minimum value of the upper boundary.

[0030] In one embodiment, a scenario of multiple aircrafts coordinating to attack multiple targets is obtained, inherent characteristics of the aircrafts, inherent information of the targets, and relative motion information between the aircrafts and the targets are obtained, and comprehensive performance indicators of task allocation are calculated, including:

[0031] Acquire a scenario of multiple aircrafts coordinating to attack multiple targets, and obtain inherent characteristics of the aircrafts, wherein the inherent characteristics include: the aircrafts' discrimination of targets, the aircrafts' anti-interference capability of targets, and the aircrafts' reliability; and establish an advantage evaluation model based on the inherent characteristics of the aircrafts according to the aircrafts' discrimination of targets, the aircrafts' anti-interference capability of targets, and the aircrafts' reliability;

[0032] Acquire a scenario in which multiple aircrafts cooperate to attack multiple targets, and obtain inherent information of the targets, wherein the inherent information includes: the volume of the targets and the speed of the targets; and establish an advantage assessment model based on the inherent information of the targets according to the volume of the targets and the speed of the targets;

[0033] Acquire a scenario in which multiple aircraft cooperate to strike multiple targets, and obtain relative motion information between the aircraft and the target, wherein the relative motion information includes: a velocity inclination angle between the aircraft and the target, an azimuth angle between the aircraft and the target, a relative distance between the aircraft and the target, and an overload between the aircraft and the target; establish an advantage assessment model based on the relative motion information between the aircraft and the target according to the velocity inclination angle between the aircraft and the target, the azimuth angle between the aircraft and the target, the relative distance between the aircraft and the target, and the overload between the aircraft and the target;

[0034] Based on the advantage assessment model based on the inherent characteristics of the aircraft, the advantage assessment model based on the inherent information of the target, and the advantage assessment model based on the relative motion information between the aircraft and the target, the advantage index of multi-aircraft coordinated attack on multiple targets is established;

[0035] According to the superiority index of multi-aircraft coordinated attack on multiple targets, the comprehensive performance index of task allocation is obtained.

[0036] In one embodiment, the comprehensive performance index of task allocation is obtained according to the superiority index of multiple aircrafts coordinating to strike multiple targets, including:

[0037] According to the penetration efficiency of the aircraft and the penetration probability of the aircraft striking the target, the comprehensive penetration probability of the aircraft striking the target is obtained;

[0038] According to the superiority index of multi-aircraft coordinated attack on multiple targets and the comprehensive penetration probability of aircraft attacking targets, the comprehensive performance index of task allocation is obtained.

[0039] The above-mentioned task allocation method for coordinated attack of multiple targets by multiple aircrafts, for the task scenario of coordinated attack of multiple targets by multiple aircrafts, takes into account the inherent characteristics of the aircraft, the inherent information of the target and the relative motion information between the aircraft and the target, and constructs a comprehensive performance index of task allocation; taking into account the simultaneous attack of multiple aircrafts and the limitation of the aircraft time adjustment capability, a coordinated time constraint is designed, and a fast task allocation model is constructed under the constraint conditions that all aircrafts have attack targets, all targets have aircrafts responsible for attacking, and multiple aircrafts can be attacked simultaneously under the limited time adjustment of the aircraft; based on the genetic algorithm for solving, a real number coding method is adopted in which all aircrafts have attack targets, and a gene repair method is designed to make the individual coding legal, that is, to simultaneously meet the coordinated constraint conditions and multiple constraints such as all targets are covered, and generate a task allocation plan. This application has been verified by simulation and has effectiveness and superiority. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is an application scenario diagram of a task allocation method for multiple aircrafts to cooperate in attacking multiple targets in one embodiment;

[0041] Figure 2 A schematic diagram of a process flow of a method for allocating tasks of multiple aircrafts coordinating attacks on multiple targets in one embodiment;

[0042] Figure 3 A schematic diagram of the distribution of remaining flight time that satisfies the coordination time constraint condition in one embodiment;

[0043] Figure 4 A schematic diagram of the distribution of the remaining flight time that does not meet the coordination time constraint condition in one embodiment;

[0044] Figure 5 A diagram of a chromosome coding structure in one embodiment;

[0045] Figure 6 A crossover operation diagram in one embodiment;

[0046] Figure 7 is a variation operation diagram in one embodiment;

[0047] Figure 8 A schematic diagram of the first gene repair in one embodiment;

[0048] Fig. 9 is a schematic diagram of the second gene repair in one embodiment;

[0049] Fig.10 A genetic algorithm flow chart in one embodiment;

[0050] Fig.11 This is a diagram showing the result of using aircraft 1-6 to strike target 1-3 in one embodiment;

[0051] Fig.12 This is a diagram showing the result of using aircraft 1-6 to strike target 1-4 in one embodiment;

[0052] Fig.13 This is a diagram showing the result of using aircraft 1-7 to strike target 1-4 in one embodiment;

[0053] Fig.14 This is a diagram showing the result of using aircraft 1-7 to strike target 1-5 in one embodiment;

[0054] Fig.15 This is a diagram showing the result of using aircraft 1-8 to strike target 1-5 in one embodiment;

[0055] Fig.16 This is a diagram showing the result of using aircraft 1-8 to attack target 1-6 in one embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0057] In addition, the descriptions of "first", "second", etc. in this application are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "multiple groups" means at least two groups, such as two groups, three groups, etc., unless otherwise clearly and specifically defined.

[0058] In this application, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, a physical connection, or a wireless communication connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0059] In addition, the technical solutions between the various embodiments of the present application can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0060] The task allocation method for multi-aircraft coordinated attack on multiple targets provided in this application can be applied to Figure 1 In the application scenario diagram shown, the terminal 102 communicates with the server 104 through the network, and the terminal 102 may include but is not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices, and the server 104 may be various portal websites, servers corresponding to the backend of the work system, etc.

[0061] This application provides a task allocation method for multiple aircraft to cooperate in attacking multiple targets, such as Figure 2 The flowchart shown in FIG. 1 shows a method for applying the method to Figure 1 The following is an example of a terminal in the example, including:

[0062] Step 202, acquire a scenario of multiple aircrafts coordinating to attack multiple targets, obtain inherent characteristics of the aircrafts, inherent information of the targets, and relative motion information between the aircrafts and the targets, and calculate comprehensive performance indicators of task allocation.

[0063] Specifically:

[0064] Obtain a scenario where multiple aircrafts cooperate to attack multiple targets, and obtain the inherent characteristics of the aircrafts, including: the aircrafts' ability to discriminate targets, the aircrafts' ability to resist interference with targets, and the aircrafts' reliability; establish an advantage assessment model based on the aircrafts' inherent characteristics according to the aircrafts' ability to discriminate targets, the aircrafts' ability to resist interference with targets, and the aircrafts' reliability;

[0065] Acquire a scenario where multiple aircrafts cooperate to attack multiple targets, and obtain the inherent information of the targets, including the volume and speed of the targets; and establish an advantage assessment model based on the inherent information of the targets according to the volume and speed of the targets;

[0066] Acquire a scenario where multiple aircraft cooperate to attack multiple targets, and obtain relative motion information between the aircraft and the target, the relative motion information including: the speed inclination angle between the aircraft and the target, the azimuth angle between the aircraft and the target, the relative distance between the aircraft and the target, and the overload between the aircraft and the target; establish an advantage assessment model based on the relative motion information between the aircraft and the target according to the speed inclination angle between the aircraft and the target, the azimuth angle between the aircraft and the target, the relative distance between the aircraft and the target, and the overload between the aircraft and the target;

[0067] Based on the advantage assessment model based on the inherent characteristics of the aircraft, the advantage assessment model based on the inherent information of the target, and the advantage assessment model based on the relative motion information between the aircraft and the target, the advantage index of multi-aircraft coordinated attack on multiple targets is established;

[0068] According to the penetration efficiency of the aircraft and the penetration probability of the aircraft striking the target, the comprehensive penetration probability of the aircraft striking the target is obtained;

[0069] According to the superiority index of multi-aircraft coordinated attack on multiple targets and the comprehensive penetration probability of aircraft attacking targets, the comprehensive performance index of task allocation is obtained.

[0070] More specifically:

[0071] Obtain a scenario where multiple aircraft cooperate to attack multiple targets, and obtain the inherent characteristics of the aircraft, which include: the aircraft's ability to discriminate targets (if the aircraft is to attack a designated target among several adjacent targets, the aircraft must have high distance discrimination and angle discrimination. An aircraft with high discrimination can distinguish the designated target from several adjacent targets), the aircraft's ability to resist interference with targets (the aircraft's ability to resist interference refers to the ability of the guidance system to maintain its normal operation when attacked by the other party, electronic countermeasures, anti-missile countermeasures, and internal and external interference), and the aircraft's reliability (reliability refers to the ability of the aircraft to complete the specified function under specified conditions and within a specified time. It is usually expressed by the probability that the aircraft will not fail within the allowed working time. The greater the probability, the smaller the possibility of failure of the aircraft, that is, the higher the reliability of the aircraft). According to the aircraft's ability to discriminate targets, the aircraft's ability to resist interference with targets, and the aircraft's reliability, an advantage evaluation model based on the aircraft's inherent characteristics is established:

[0072] ;

[0073] In the formula, For aircraft The advantages of the inherent characteristics of For aircraft Reliability, For aircraft The discernment, For aircraft Anti-interference ability, is the number of aircraft, and are different weighting coefficients;

[0074] Obtain a scenario where multiple aircraft cooperate to strike multiple targets (different targets in the target group have different strike values ​​and impacts. For important targets, more aircraft should be assigned to strike to enhance the strike effect). Obtain the inherent information of the target, which includes: the volume of the target (the volume of the target represents the target's capacity and impact; targets of different volumes have different performances, and the volume of the target determines the amount of equipment loaded. The larger the volume, the higher the firepower, that is, the higher the impact, the higher the strike value) and the speed of the target (the speed of the target represents the target's power and maneuverability; the speed of the target determines the target's maneuverability. Too fast a speed makes it difficult to hit, but due to the limitation of the power system, too high a speed often indicates that the target is insufficient in quality); according to the volume and speed of the target, establish an advantage evaluation model based on the inherent information of the target:

[0075] ;

[0076] ;

[0077] ;

[0078] In the formula, For target-based The target value of the volume, For the goal The volume of For the goal The number of For target-based The target value of speed, For the goal speed, To comprehensively consider the preset speed of target performance, For the goal The inherent information advantage (the indicator of strike value), and are different weighting coefficients;

[0079] Obtain a scenario where multiple aircraft cooperate to attack multiple targets, and obtain the relative motion information between the aircraft and the target. The relative motion information includes: the attack angle between the aircraft and the target, the relative distance between the aircraft and the target (the distance between the aircraft and the target will inevitably affect the generation of guidance instructions and the realization of the attack target. When the distance is too close, the reaction time of the aircraft is too short, which brings great pressure to the execution of the guidance instructions. On the contrary, when the distance is too far, the detection accuracy of the aircraft is adversely affected, and excessive energy loss will also affect the completion of the attack mission) and the overload of the aircraft and the target (because the maneuverability and control ability of the aircraft is directly reflected in the available overload, and the overload can simultaneously include the relative angle, distance and speed, therefore, the overload is introduced as a variable to characterize the advantage of the aircraft over different targets. The specific method is as follows: Based on the current flight status and target information of the aircraft, the optimal guidance method is used to calculate the required lateral overload command of the aircraft; the larger the overload command, the shorter the waiting time and the more difficult the strike mission. Excessive overload commands will exceed the control capability of the aircraft, resulting in the failure of the strike mission; smaller overload commands mean smaller control capability requirements and a straighter trajectory, but a straight trajectory will reduce penetration performance), among which the strike angle between the aircraft and the target (because the aircraft needs to meet the speed inclination constraint and eliminate the heading error when attacking the target, the attack angle advantage assessment needs to comprehensively consider the speed inclination and speed azimuth) includes: the speed inclination of the aircraft and the target (in the longitudinal channel, when the real-time speed inclination is equal to the terminal constraint, the guidance is easier to achieve, which means that the strike advantage increases with the decrease of the angle difference) and the azimuth of the aircraft and the target (in the lateral channel, the main goal of the aircraft guidance is to eliminate the heading error Therefore, the larger the absolute value of the error, the more difficult the guidance task will be. On the contrary, if =0, the aircraft has the greatest advantage over the target); according to the velocity inclination angle between the aircraft and the target, the azimuth angle between the aircraft and the target, the relative distance between the aircraft and the target, and the overload between the aircraft and the target, an advantage evaluation model based on the relative motion information between the aircraft and the target is established:

[0080] ;

[0081] ;

[0082] ;

[0083] ;

[0084] In the formula, Based on The striking advantage, For aircraft The velocity inclination angle, For aircraft Target The expected angle of fall, Based on The striking advantage, For aircraft The velocity azimuth, For aircraft Relative Target The sight angle, Based on The striking advantage, For aircraft Relative Target The relative distance The distance is determined by comprehensively considering the detection capability and maneuverability. Based on The striking advantage, For aircraft Target The overload instruction, is the overload reference quantity determined based on the control capability, For aircraft Target The advantage of relative motion information, , , , are different weighting coefficients;

[0085] Based on the advantage evaluation model based on the inherent characteristics of the aircraft, the advantage evaluation model based on the inherent information of the target, and the advantage evaluation model based on the relative motion information between the aircraft and the target, the advantage index of multi-aircraft coordinated attack on multiple targets is established:

[0086] ;

[0087] In the formula, For aircraft Target The dominance index, , , are different weighting coefficients and satisfy ;

[0088] According to the penetration efficiency of the aircraft (the penetration efficiency of the aircraft has uncertain factors and is affected by natural factors, namely the wind and weather conditions in the area. When the wind is stronger, the penetration efficiency decreases due to the increased difficulty of the aircraft to control itself; when the weather is worse, the penetration efficiency of the aircraft increases due to the obstruction of the opponent's vision. The penetration efficiency of the aircraft obeys the normal distribution of natural factors) and the penetration probability of the aircraft hitting the target, the comprehensive penetration probability of the aircraft hitting the target is obtained:

[0089] ;

[0090] In the formula, For aircraft Target The comprehensive penetration probability of , For aircraft The penetration efficiency, For aircraft Target The probability of penetration;

[0091] According to the superiority index of multi-aircraft coordinated attack on multiple targets and the comprehensive penetration probability of aircraft attacking targets, the comprehensive performance index of task allocation is obtained:

[0092] ;

[0093] In the formula, Comprehensive performance indicators for task assignment, is the aircraft-to-target allocation matrix The elements corresponding to the target in the distribution matrix The elements corresponding to the target to be hit are established based on the comprehensive penetration probability of the aircraft and the cost of the aircraft. Marked as 1, otherwise Marked as 0.

[0094] In this step, a comprehensive performance index for task allocation is constructed by considering the inherent advantages of the aircraft, the target value, and the relative motion advantages.

[0095] Step 204, establish a task allocation model based on the comprehensive performance indicators of task allocation; in the task allocation model, each aircraft has a corresponding strike target, each target is covered, and the coordination time constraint is satisfied; the coordination time constraint is: the maximum value of the lower boundary of the remaining flight time of all aircraft is less than the minimum value of the upper boundary of the remaining flight time of all aircraft.

[0096] Specifically:

[0097] Each aircraft has a corresponding attack target:

[0098] ;

[0099] In the formula, is the number of aircraft;

[0100] Each target is covered by:

[0101] ;

[0102] In the formula, For the goal the number of

[0103] In a multi-aircraft coordinated strike mission, the simultaneous arrival of multiple aircraft can saturate the opponent's defense system, thereby increasing the probability of aircraft penetration. Therefore, time coordination is a major constraint for multi-aircraft coordination. Due to the different state conditions and adjustment capabilities of each aircraft, the adjustable time range is limited when attacking different targets. If the coordination time constraint is not considered when assigning tasks, the aircraft will not be able to attack the target on time, resulting in the failure of the coordinated mission. The coordination time constraint is that the lower limit of the remaining flight time of all aircraft is less than the upper limit of the remaining flight time of all aircraft:

[0104] ;

[0105] in,

[0106] ;

[0107] ;

[0108] ;

[0109] In the formula, is the lower bound of the remaining flight time of all aircraft, is the upper limit of the remaining flight time of all aircraft, To determine the remaining flight time of the aircraft under the allocation plan.

[0110] Among them, in coordinated attack missions, aircraft can be roughly divided into cruise and gliding types.

[0111] For cruise aircraft, the engine can continuously provide adjustable thrust during flight. According to the cruise speed, the strike time is adjusted to obtain the adjustment range of the remaining flight time of the cruise aircraft:

[0112] ;

[0113] In the formula, For aircraft With the goal The projectile distance, For aircraft Attack Target The remaining flight time, For aircraft Maximum speed, For aircraft Minimum speed;

[0114] Gliding aircraft are usually powered by engines with a predetermined thrust curve. They cannot control their speed and can only change the length of their flight path by changing the curvature of their flight trajectory, thereby controlling their flight time. Assuming that proportional guidance is used, the strike time is adjusted according to the guidance law (proportional guidance law with attack angle constraints), and the adjustment range of the remaining flight time of gliding aircraft is obtained:

[0115] ;

[0116] ;

[0117] ;

[0118] ;

[0119] ;

[0120] ;

[0121] ;

[0122] In the formula, is the acceleration instruction; is the proportional guidance coefficient; is the aircraft speed; is the rate of change of the missile-target sight angle; is a constant parameter; is the leading angle; is the distance between the projectile and the target; is the aircraft speed inclination angle; is the sight angle of the projectile; is the desired angle of attack; The remaining flight time; For aircraft Attack Target The remaining flight time;

[0123] It can be seen that by adjusting the proportional guidance coefficient The flight time can be controlled; when Take the maximum value The minimum remaining flight time ;when Take the minimum value , corresponding to the maximum remaining flight time .

[0124] Then, the coordination time constraint can be obtained according to the adjustment range of the remaining flight time of the cruise aircraft and the adjustment range of the remaining flight time of the gliding aircraft.

[0125] Under the allocated scheme, when the intersection of the remaining flight time of all aircraft is not an empty set, the allocation scheme is considered to meet the collaborative time constraint conditions, such as Figure 3 The diagram of the remaining flight time distribution that satisfies the collaborative time constraint is shown in Figure 1. When the intersection of the remaining flight time of all aircraft is an empty set, it is considered that the allocation scheme does not satisfy the collaborative time constraint, such as Figure 4 Schematic diagram of the remaining flight time distribution that does not meet the coordination time constraint.

[0126] In this step, we take multi-agent aircraft as the research object and coordinate strikes (attacks) on multiple targets as the research background. Aircraft strike The task allocation problem with different value objectives. The designed task allocation model is based on the following reasonable assumptions:

[0127] 1) The number of aircraft in the coordinated strike is greater than or equal to the number of targets;

[0128] 2) Each aircraft can share data through the data link, and the master aircraft can obtain the status data of all slave aircraft;

[0129] 3) Each aircraft can only attack a single target, and each target can be assigned to any aircraft for attack.

[0130] Under the above assumptions, the advantage assessment model is constructed by considering the situation of both sides and the strike capability of the aircraft. The task allocation model is established by considering the target value of the aircraft during the strike, the relative advantage of the aircraft in striking different targets, and the relative information between the aircraft and the target.

[0131] Step 206, using the comprehensive performance index of task allocation as the fitness function, establishing a genetic algorithm; using the genetic algorithm to solve the task allocation model, and using the optimal solution of the genetic algorithm as the task allocation solution.

[0132] Specifically:

[0133] Using decimal coding, the gene value represents the target, the gene position represents the aircraft, the chromosome length represents the number of aircraft, and the number of aircraft is not less than the target number, and the chromosome coding structure is obtained;

[0134] According to the chromosome coding structure, all targets are randomly filled into different gene positions, and the vacant gene positions are filled with any target to generate the initial population;

[0135] Taking the comprehensive performance index of task allocation as the fitness function, the fitness value of each individual in the initial population is calculated, and it is determined whether the fitness value meets the preset conditions;

[0136] When the fitness value does not meet the preset conditions, the evolution operation is performed and the initial population is updated to obtain the next population; the fitness value of each individual in the next population is calculated and re-judged until the fitness value meets the preset conditions, then the iteration is stopped and the optimal solution of the genetic algorithm is obtained;

[0137] The genetic algorithm is used to solve the task allocation model, and the optimal solution of the genetic algorithm is used as the task allocation plan.

[0138] More specifically:

[0139] Genetic Algorithm is an optimization algorithm that simulates the biological evolution process in nature and is widely used to solve various complex optimization problems. It gradually optimizes the quality of the solution by simulating operations such as selection, crossover and mutation in the evolution process, thereby finding the optimal solution or a solution close to the optimal solution. Genetic algorithm has invisible parallelism and high global optimization ability, and can obtain the global optimal solution with a high probability, and has strong adaptive ability. Its operation object is directly oriented to the structural object, and the feasible solution representation method is very extensive.

[0140] Using decimal encoding, with gene value 1~ represents the target, the gene position represents the aircraft, and the chromosome length represents the number of aircraft , the number of aircraft is not less than the target number, and the chromosome coding structure diagram is obtained as follows Figure 5 As shown, the chromosomes are Position and rear - bit composition;

[0141] According to the chromosome coding structure, all targets are randomly filled into different gene positions (previous Position), the vacant gene position (later - The first position of the chromosome is filled with any target as the initial solution, and each initial solution is used as an individual to generate the initial population (that is, when generating the initial population, the chromosome Bit, composed of a group of 1~ It is composed of non-repeating natural numbers, so that the constraint condition that each target has a flying vehicle responsible for attacking is satisfied; after the chromosome - bit, then from 1 to The natural numbers are randomly supplemented in between, so that the constraint condition that each aircraft is assigned a mission objective can be satisfied);

[0142] Taking the comprehensive performance index of task allocation as the fitness function, calculate the fitness value of each individual in the initial population (the fitness value is used as an indicator to measure the pros and cons of the individual solution in the problem, and the higher the fitness value, the better the individual solution), and judge whether the fitness value meets the preset conditions;

[0143] When the fitness value does not meet the preset conditions, an evolution operation is performed; wherein the evolution operation includes: selection operation, crossover operation and mutation operation;

[0144] The selection operation is to select several individuals from the population with a certain probability according to the fitness value of the individual. Its purpose is to select excellent individuals from the current population so that they have the opportunity to reproduce offspring as parents. Individuals with high fitness values ​​are more likely to be selected, thereby increasing their frequency of appearance in the next generation. The commonly used strategy is roulette. The probability of an individual being selected as a parent is:

[0145]

[0146] Crossover operation refers to the crossover operation of the selected parent individuals to generate a certain number of offspring individuals. This operation simulates the gene combination process in biological inheritance and generates new solutions by exchanging the chromosome fragments of individuals. It is the core part of the genetic algorithm and the main operation for generating new individuals. The crossover operator is implemented as follows: two crossover points are randomly generated, and the two parent individuals are first exchanged. P 1 and P The gene segment between the 2 intersections P 1' and P 2', generating two offspring C1 and C2, such as Figure 6 The crossover operation diagram is shown. This crossover operator is not a blind search. It effectively inherits part of the gene segments of the parents, tending to make the population have more excellent genes. After the crossover operation, the chromosome may become an illegal chromosome, which will be repaired in the end;

[0147] Mutation operation refers to the operation of mutation on offspring individuals to introduce new gene variants. This operation simulates the gene mutation phenomenon in biological inheritance. By randomly changing the chromosomes of individuals, the diversity of the search space is increased, thereby maintaining the diversity of the population and determining the local search ability of the genetic algorithm. This application adopts single-point mutation, such as Figure 7 The mutation operation diagram is shown. After the mutation operation, the chromosome may become an illegal chromosome, which will be repaired in the end;

[0148] After the evolutionary operation, the parent and offspring individuals are merged to form a new generation of population to update the initial population and obtain the next population; the fitness value of each individual in the next population is calculated and re-judged until the fitness value meets the preset conditions (such as reaching the maximum number of iterations or finding a solution that meets the requirements), then the iteration is stopped to obtain the optimal solution of the genetic algorithm;

[0149] The optimal genetic algorithm is used to solve the task allocation model, and the optimal solution of the genetic algorithm is used as the task allocation plan.

[0150] Preferably, after generating the initial population and performing the evolution operation, it also includes: performing gene detection on the evolved population to determine whether it is legal, and repairing it if it is illegal (if it cannot contain all targets and meet the coordination time constraint, it becomes an illegal gene).

[0151] Specifically: determine whether the chromosome coding structure contains all targets and satisfies the coordinated time constraint; if it is determined to be yes, calculate the fitness value; if it is determined to be no, perform gene repair on the chromosome coding structure.

[0152] Among them, gene repair includes two parts. The first gene repair is performed to ensure that the constraint condition that each target has an aircraft responsible for attacking is met, and then the second gene repair is performed to ensure that the constraint condition of the coordinated time constraint is met; specifically:

[0153] When it is judged that the chromosome encoding structure does not contain all the targets (that is, the gene value in the chromosome is 1~ Not all of them are present but some are missing): Detect missing gene values ​​and repeated gene values, select missing gene values ​​and randomly insert them into any point where a repeated gene value is located for replacement, until all missing gene values ​​are inserted into the chromosome coding structure to ensure that the chromosome contains a complete 1~ Natural numbers that make the gene legal, such as Figure 8 Schematic diagram of the first gene repair shown;

[0154] When it is determined that the chromosome encoding structure does not meet the coordination time constraint, the lower boundary maximum value of the remaining flight time of all aircraft is detected. and the upper minimum Corresponding gene positions, any gene value can be modified to meet the constraint conditions: detect the lower boundary maximum value of the remaining flight time of all aircraft The corresponding gene position is used to modify the lower boundary maximum value of the remaining flight time of all aircraft to repair the lower boundary (specifically: the gene position corresponding to the lower boundary maximum value of the remaining flight time of all aircraft is detected, and the lower boundary is smaller and less than the upper boundary minimum value (i.e. ) is the candidate set of substitute genes; randomly select the gene value in the candidate set of substitute genes to replace the lower boundary maximum value to repair the lower boundary); or detect the upper boundary minimum value of the remaining flight time of all aircraft The corresponding gene position is used to modify the upper boundary minimum value of the remaining flight time of all aircraft to repair the upper boundary (specifically: the gene position corresponding to the upper boundary minimum value of the remaining flight time of all aircraft is detected, and the upper boundary is larger and greater than the lower boundary maximum value (i.e. ) is the set of gene values ​​of the candidate set of substitute genes; randomly select the gene value in the candidate set of substitute genes and replace the minimum value of the upper boundary to repair the upper boundary), such as Fig. 9 Schematic diagram of the second gene repair shown.

[0155] If the candidate set of substitute genes for the lower boundary repair is an empty set, the upper boundary repair is performed; if the candidate set of substitute genes for the upper boundary repair is an empty set, the lower boundary repair is performed;

[0156] If the candidate sets of substitute genes for lower boundary repair and the candidate sets of substitute genes for upper boundary repair are both empty sets, any legal individual is used to replace the maximum value of the lower boundary or the minimum value of the upper boundary to ensure that the population size remains unchanged.

[0157] After two gene repairs, it is necessary to check again whether the genes are legal. If not, they will be repaired again until all genes are legal.

[0158] In this step, the genetic algorithm flow chart is as follows Fig.10 shown.

[0159] Among them, the decimal encoding method is adopted to solve the problem that "the traditional genetic algorithm uses binary encoding. When the number of aircraft and targets is large, the length of the encoding string increases, the search space becomes larger, and it is easier to generate individuals that do not meet the constraints, resulting in a sharp drop in optimization efficiency."

[0160] In addition, illegal genes are repaired to avoid affecting the population evolution rate due to abandoning individuals with illegal genes, and to accelerate the convergence speed and improve the efficiency of finding the optimal solution.

[0161] The above-mentioned task allocation method for coordinated attack of multiple targets by multiple aircrafts, for the task scenario of coordinated attack of multiple targets by multiple aircrafts, takes into account the inherent characteristics of the aircraft, the inherent information of the target and the relative motion information between the aircraft and the target, and constructs a comprehensive performance index of task allocation; taking into account the simultaneous attack of multiple aircrafts and the limitation of the aircraft time adjustment capability, a coordinated time constraint is designed, and a fast task allocation model is constructed under the constraint conditions that all aircrafts have attack targets, all targets have aircrafts responsible for attacking, and multiple aircrafts can be attacked simultaneously under the limited time adjustment of the aircraft; based on the genetic algorithm for solving, a real number coding method is adopted in which all aircrafts have attack targets, and a gene repair method is designed to make the individual coding legal, that is, to simultaneously meet the coordinated constraint conditions and multiple constraints such as all targets are covered, and generate a task allocation plan. This application has been verified by simulation and has effectiveness and superiority.

[0162] It should be understood that although Figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0163] In a specific embodiment, a simulation experiment is conducted, in which eight aircraft are set to coordinately attack six high-value targets.

[0164] The target parameters are set as shown in Table 1, and the weighting coefficients are set as: , .

[0165] Table 1 Target parameters

[0166]

[0167] The inherent parameters of the aircraft are shown in Table 2, and the weighting coefficients are set as: , .

[0168] Table 2 Intrinsic parameters of aircraft

[0169]

[0170] The simulation experiment is mainly to verify the correctness and effectiveness of the designed method, so the dominance index is directly given here. , Penetration Probability And time adjustment range As shown in Tables 3 to 5.

[0171] Table 3 Dominance index :

[0172]

[0173] Table 4 Penetration probability :

[0174]

[0175] Table 5 Time adjustment range :

[0176]

[0177] The simulation experiment was verified by 6 sets of examples, namely 6-3, 6-4, 7-4, 7-5, 8-5, and 8-6. Taking 6-3 as an example, it means that aircraft 1-6 attacks target 1-3, sets the population size to 40, and the number of iterations to 100. Based on i7-11800H, 2.30 GHz processor and MATLAB R2022a, the simulation experimental results are shown in Table 6 below.

[0178] Table 6 Simulation experiment results:

[0179]

[0180] In Table 6, E-Ga represents the optimal index obtained based on the genetic algorithm; E-Tr represents the optimal index obtained based on the enumeration method; CT-Ga represents the calculation time based on the genetic algorithm; CT-Tr represents the calculation time based on the enumeration method; Num-Sch represents the total number of legal solutions that need to be traversed by the enumeration method; Sch-Ga represents the optimal allocation solution obtained based on the genetic algorithm; Sch-Tr represents the optimal allocation solution obtained based on the enumeration method.

[0181] From the simulation results, it can be seen that the task allocation method designed based on genetic algorithm can obtain the same optimal result as the enumeration method, which shows the correctness and effectiveness of the proposed method; at the same time, it can be seen that when the number of aircraft and the number of targets are small, the computational time of the proposed task allocation method based on genetic algorithm is slightly longer than that of the enumeration method. As the number of aircraft and targets increases, the complexity of the problem increases. At this time, the computational time of the proposed method remains unchanged, while the computational time of the enumeration method increases almost exponentially. Analyzing the reason, the computational amount of the proposed task allocation method based on genetic algorithm is only related to the set population size and the number of iterations, while the enumeration method needs to calculate all the solutions, and its computational time is determined by the total number of allocation solutions Num-Sch. As the complexity of the problem increases, the total number of allocation solutions increases exponentially, so the computational time will also increase exponentially, which is unacceptable in practical applications. Therefore, the task allocation scheme based on genetic algorithm proposed in this paper has significant advantages. Figures 11 to 16 The result diagram of the aircraft hitting the target is shown. From the results, it can be seen that they can effectively converge to the optimal value.

[0182] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in this field.

[0183] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0184] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A task allocation method for multiple aircraft to coordinately attack multiple targets, characterized in that: include: Acquire the scenario of multiple aircrafts coordinating to attack multiple targets, obtain the inherent characteristics of the aircrafts, the inherent information of the targets, and the relative motion information between the aircrafts and the targets, and calculate the comprehensive performance indicators of task allocation; According to the comprehensive performance index of task allocation, a task allocation model is established; in the task allocation model, each aircraft has a corresponding strike target, each target is covered, and the coordination time constraint is satisfied; the coordination time constraint is: the maximum value of the lower boundary of the remaining flight time of all aircraft is less than the minimum value of the upper boundary of the remaining flight time of all aircraft; A genetic algorithm is established with the comprehensive performance index of task allocation as the fitness function; a genetic algorithm is established with the comprehensive performance index of task allocation as the fitness function, including: using a decimal encoding method, using gene values ​​to represent targets, gene positions to represent aircraft, chromosome lengths to represent the number of aircraft, and the number of aircraft is not less than the number of targets, to obtain a chromosome encoding structure; according to the chromosome encoding structure, all targets are randomly filled into different gene positions, and the vacant gene positions are filled with any target to generate an initial population; using the comprehensive performance index of task allocation as the fitness function, calculating the fitness value of each individual in the initial population, and judging whether the fitness value meets a preset condition; When the fitness value does not meet the preset conditions, an evolutionary operation is performed and the initial population is updated to obtain the next population; the fitness value of each individual in the next population is calculated and re-judged until the fitness value meets the preset conditions, then the iteration is stopped and the optimal solution of the genetic algorithm is obtained; the task allocation model is solved using the genetic algorithm, and the optimal solution of the genetic algorithm is used as the task allocation plan.

2. The task allocation method for multiple aircraft coordinated strike against multiple targets according to claim 1 is characterized in that: For cruise aircraft, the strike time is adjusted according to the cruise speed to obtain the adjustment range of the remaining flight time of the cruise aircraft; For gliding aircraft, the strike time is adjusted according to the guidance law to obtain the adjustment range of the remaining flight time of the gliding aircraft.

3. The task allocation method for multiple aircraft coordinated strike against multiple targets according to claim 2 is characterized in that: After generating the initial population, it also includes: Determine whether the chromosome encoding structure contains all targets and satisfies the coordination time constraint; If the judgment is yes, the fitness value is calculated; If the judgment is no, the chromosome coding structure is genetically repaired.

4. The task allocation method for multiple aircraft coordinated strike against multiple targets according to claim 3 is characterized in that: The gene repair comprises: When it is determined that the chromosome encoding structure does not contain all targets: detect missing gene values ​​and repeated gene values, select the missing gene value and randomly insert it into any point where the repeated gene value is located for replacement, until all missing gene values ​​are inserted into the chromosome encoding structure; When it is determined that the chromosome coding structure does not satisfy the collaborative time constraint: detect the gene bit corresponding to the maximum value of the lower boundary of the remaining flight time of all aircraft and modify the maximum value of the lower boundary of the remaining flight time of all aircraft to repair the lower boundary; or detect the gene bit corresponding to the minimum value of the upper boundary of the remaining flight time of all aircraft and modify the minimum value of the upper boundary of the remaining flight time of all aircraft to repair the upper boundary.

5. The task allocation method for multiple aircraft coordinated strike against multiple targets according to claim 4 is characterized in that: Detecting the gene bit corresponding to the maximum value of the lower boundary of the remaining flight time of all aircraft and modifying the maximum value of the lower boundary of the remaining flight time of all aircraft to repair the lower boundary; or detecting the gene bit corresponding to the minimum value of the upper boundary of the remaining flight time of all aircraft and modifying the minimum value of the upper boundary of the remaining flight time of all aircraft to repair the upper boundary, including: Detect the gene position corresponding to the lower boundary maximum value of the remaining flight time of all aircraft, and use the gene value set with a smaller lower boundary and less than the upper boundary minimum value as the substitute gene candidate set; randomly select the gene value in the substitute gene candidate set to replace the lower boundary maximum value to repair the lower boundary; Detect the gene position corresponding to the upper boundary minimum value of the remaining flight time of all aircraft, and use the gene value set with a larger upper boundary and greater than the lower boundary maximum value as the substitute gene candidate set; randomly select the gene value in the substitute gene candidate set to replace the upper boundary minimum value to repair the upper boundary.

6. The task allocation method for multiple aircraft coordinated strike against multiple targets according to claim 5 is characterized in that: If the candidate set of substitute genes for the lower boundary repair is an empty set, the upper boundary repair is performed; if the candidate set of substitute genes for the upper boundary repair is an empty set, the lower boundary repair is performed; If the candidate sets of substitute genes for lower boundary repair and the candidate sets of substitute genes for upper boundary repair are both empty sets, any legal individual is used to replace the maximum value of the lower boundary or the minimum value of the upper boundary.

7. The task allocation method for multiple aircraft coordinated strike against multiple targets according to claim 1 or 2 is characterized in that: Acquire the scenario of multiple aircrafts coordinating to attack multiple targets, obtain the inherent characteristics of the aircrafts, the inherent information of the targets, and the relative motion information between the aircrafts and the targets, and calculate the comprehensive performance indicators of task allocation, including: Acquire a scenario of multiple aircrafts coordinating to attack multiple targets, and obtain inherent characteristics of the aircrafts, wherein the inherent characteristics include: the aircrafts' discrimination of targets, the aircrafts' anti-interference capability of targets, and the aircrafts' reliability; and establish an advantage evaluation model based on the inherent characteristics of the aircrafts according to the aircrafts' discrimination of targets, the aircrafts' anti-interference capability of targets, and the aircrafts' reliability; Acquire a scenario in which multiple aircrafts cooperate to attack multiple targets, and obtain inherent information of the targets, wherein the inherent information includes: the volume of the targets and the speed of the targets; and establish an advantage assessment model based on the inherent information of the targets according to the volume of the targets and the speed of the targets; Acquire a scenario in which multiple aircraft cooperate to strike multiple targets, and obtain relative motion information between the aircraft and the target, wherein the relative motion information includes: a velocity inclination angle between the aircraft and the target, an azimuth angle between the aircraft and the target, a relative distance between the aircraft and the target, and an overload between the aircraft and the target; establish an advantage assessment model based on the relative motion information between the aircraft and the target according to the velocity inclination angle between the aircraft and the target, the azimuth angle between the aircraft and the target, the relative distance between the aircraft and the target, and the overload between the aircraft and the target; Based on the advantage assessment model based on the inherent characteristics of the aircraft, the advantage assessment model based on the inherent information of the target, and the advantage assessment model based on the relative motion information between the aircraft and the target, the advantage index of multi-aircraft coordinated attack on multiple targets is established; According to the superiority index of multi-aircraft coordinated attack on multiple targets, the comprehensive performance index of task allocation is obtained.

8. The task allocation method for multiple aircraft coordinated strikes on multiple targets according to claim 7 is characterized in that: According to the superiority index of multi-aircraft coordinated attack on multiple targets, the comprehensive performance index of task allocation is obtained, including: According to the penetration efficiency of the aircraft and the penetration probability of the aircraft striking the target, the comprehensive penetration probability of the aircraft striking the target is obtained; According to the superiority index of multi-aircraft coordinated attack on multiple targets and the comprehensive penetration probability of aircraft attacking targets, the comprehensive performance index of task allocation is obtained.

Images