An Algorithm for Combat Deployment of Air Defense Weapons
By building an optimization model for air defense weapons deployment and using genetic algorithms or particle swarm algorithms, the problem of inefficient deployment of air defense weapons in the existing technology is solved, and the optimal deployment solution is achieved quickly, and the all-round cover capability and deployment of air defense weapons is improved. efficiency.
Patent Information
- Application Number
- CN202111594859.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-23
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2041-12-23
AI Technical Summary
The combat deployment of existing air defense weapons mainly relies on manual experience, is long and difficult to optimize quickly, and cannot effectively consider the battlefield environment and deployment location, resulting in inefficient deployment.
Genetic algorithms or particle swarm algorithms are used to build an optimization model for air defense weapons deployment, and through loss functions and geospatial models, the optimal deployment plan is solved, and an effective air defense weapon deployment display diagram is automatically generated.
It has achieved rapid acquisition of the optimal deployment plan, reduced the probability of manual operation errors, improved the all-round cover capability of air defense weapons, and improved deployment efficiency.
Smart Images

Figure CN114330862B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to an air defense weapon combat deployment algorithm, belonging to regional air defense and anti-missile command and control technology. Background Art
[0002] In modern air defense operations, the purpose of air defense weapon combat deployment is to create a combat situation that is favorable to air defense and unfavorable to air raids under certain combat conditions, so as to form an optimized firepower structure and detection structure in the battle, occupy a certain time and space advantage, and give full play to the advantages of air defense firepower, curb the power of air raid weapons and achieve the purpose of defending our important places. A good deployment situation can enable air defense weapons and equipment with different performances to play a synergistic advantage under systematic confrontation. Therefore, as an important part of pre-war planning, the reasonable deployment of air defense weapons is particularly important. At present, the combat deployment of air defense weapons is generally manually configured based on experience, evaluated and verified through simulation deduction, and optimized through repeated iterative adjustments, which takes a long time overall. Summary of the invention
[0003] In order to solve the above technical problems, the present invention provides an air defense weapon combat deployment algorithm, which can comprehensively consider the battlefield environment, deployment location, cover capability and other constraints of air defense weapons, with the goal of obtaining the optimal deployment plan, and provide an air defense weapon deployment optimization model, with the goal of achieving all-round maximum cover for multiple key locations.
[0004] The present invention is achieved through the following technical solutions.
[0005] The present invention provides an air defense weapon combat deployment algorithm, comprising the following steps:
[0006] ① Construct loss function: According to the coverage range of air defense weapons on the defense key points, construct the coverage loss function of air defense weapons on the defense key points;
[0007] ② Determine the geographic model: Build a geographic spatial model, which distinguishes deployable areas and non-deployable areas based on grids;
[0008] ③ Determine the deployment model: With the goal of minimizing the calculated value of the cover loss function of multiple air defense weapons for defending key areas, and with the geographic space model as a constraint, establish an air defense weapon deployment optimization model;
[0009] ④ Solve the deployment model: Use genetic algorithm or particle swarm algorithm to solve the air defense weapon deployment optimization model and obtain the optimal deployment plan.
[0010] The coverage range of the air defense weapon for the defense of the key point is calculated based on the performance parameters of the air defense weapon, which include the radius r of the bombing circle. tf , the distance between the air defense weapon and the center of the key point rb , Maximum killing radius R max , Maximum route shortcut P max .
[0011] The air defense weapon has a constraint condition on the coverage range of the defense key point, and the constraint condition is calculated using the following formula:
[0012]
[0013] Among them, the air attack azimuth α∈(-π,π] is the angle between the carrier air attack direction and the baseline, the route shortcut P is the shortest distance from the ground air defense weapon to the horizontal plane projection of the carrier route; the cover depth R n Refers to the distance the carrier aircraft passes through the key anti-aircraft fire circle before reaching the bombing circle; For cover range.
[0014] The coverage range of the air defense weapons for the key areas to be defended is in the following forms:
[0015]
[0016]
[0017] in, They are respectively the long-range comprehensive protection value vector, the medium-range comprehensive protection value vector and the short-range comprehensive protection value vector, Loss(YH i,j ) is the loss function of weapon i to be deployed to key point j, and K is the maximum subscript after discretizing the 360° direction of the defended key point.
[0018] The coverage range of the air defense weapons for the key points to be defended shall be in the following form when there are multiple key points to be defended:
[0019]
[0020] Where M is the number of key locations, is the protection loss function of all air defense weapons to the key point m, η m Weight the importance of location m, Loss YH_sum It is the protection loss function of all air defense weapons to all key locations.
[0021] The geospatial model is two-dimensionally unfolded and divided into grids.
[0022] In the geographic space model, both deployable areas and non-deployable areas are marked as grids.
[0023] In step ④, a genetic algorithm is used to calculate and solve the problem in the following steps:
[0024] A. Randomly generate a population, determine the individual fitness, and use the roulette strategy to determine the cumulative probability of the individual;
[0025] B. Generate new individuals according to certain mutation probability and mutation method, and judge whether they are illegal solutions. If yes, mutate or crossover again, otherwise continue;
[0026] C. Determine whether the optimization criteria are met. If so, output the best individual and its optimal solution.
[0027] The beneficial effects of the present invention are that it can comprehensively consider the battlefield environment, deployment position, cover capability and other constraints of air defense weapons, with the goal of obtaining the optimal deployment plan, and provide an air defense weapon deployment optimization model, with the goal of achieving all-round maximum cover for multiple key locations. By solving the optimal solution to the model, an air defense weapon combat deployment plan is obtained, and an effective air defense weapon deployment display diagram is automatically given, which is beneficial for quickly providing commanders with an initial optimized deployment plan for the air defense weapon system and reducing the probability of manual operation errors. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] Figure 1 is a flow chart of the present invention;
[0029] Figure 2 A schematic diagram of a simulation scene environment model in a specific embodiment of the present invention;
[0030] Figure 3 It is a schematic diagram of the weapon configuration scheme 1 of the present invention;
[0031] Figure 4 It is a schematic diagram of the weapon configuration scheme 2 of the present invention;
[0032] Figure 5 It is a schematic diagram of the weapon configuration scheme 3 of the present invention;
[0033] Figure 6 It is a schematic diagram of the weapon configuration scheme 4 of the present invention;
[0034] Figure 7 It is a schematic diagram of the weapon configuration scheme 5 of the present invention;
[0035] Figure 8 It is a schematic diagram of the weapon configuration scheme 6 of the present invention. DETAILED DESCRIPTION
[0036] The technical solution of the present invention is further described below, but the scope of protection claimed is not limited to the description.
[0037] Example 1
[0038] like Figures 1 to 8 An air defense weapon combat deployment algorithm shown includes the following steps:
[0039] ① Construct loss function: According to the coverage range of air defense weapons on the defense key points, construct the coverage loss function of air defense weapons on the defense key points;
[0040] ② Determine the geographic model: Build a geographic spatial model, which distinguishes deployable areas and non-deployable areas based on grids;
[0041] ③ Determine the deployment model: With the goal of minimizing the calculated value of the cover loss function of multiple air defense weapons for defending key areas, and with the geographic space model as a constraint, establish an air defense weapon deployment optimization model;
[0042] ④ Solve the deployment model: Use genetic algorithm or particle swarm algorithm to solve the air defense weapon deployment optimization model and obtain the optimal deployment plan.
[0043] Example 2
[0044] Based on Example 1, the coverage range of the air defense weapon for the defense key point is calculated according to the performance parameters of the air defense weapon, and the performance parameters include the radius r of the bombing circle. tf , the distance between the air defense weapon and the center of the key point r b , Maximum killing radius R max , Maximum route shortcut P max .
[0045] Example 3
[0046] Based on Example 2, the air defense weapon has a constraint condition on the coverage range of the defense key point, and the constraint condition is calculated using the following formula:
[0047]
[0048] Among them, the air attack azimuth α∈(-π,π] is the angle between the carrier air attack direction and the baseline, the route shortcut P is the shortest distance from the ground air defense weapon to the horizontal plane projection of the carrier route; the cover depth R n Refers to the distance the carrier aircraft passes through the key anti-aircraft fire circle before reaching the bombing circle; For cover range.
[0049] Example 4
[0050] Based on Example 1, the coverage range of air defense weapons for defending key areas is in the following form:
[0051]
[0052]
[0053] in, They are respectively the long-range comprehensive protection value vector, the medium-range comprehensive protection value vector and the short-range comprehensive protection value vector, Loss(YH i,j ) is the loss function of weapon i to be deployed to key point j, and K is the maximum subscript after discretizing the 360° direction of the defended key point.
[0054] Example 5
[0055] Based on Example 4, the coverage range of the air defense weapon for the defense key point, when there are multiple defense key points, adopts the following form:
[0056]
[0057] Where M is the number of key locations, is the protection loss function of all air defense weapons to the key point m, η m Weight the importance of location m, Loss YH_sum It is the protection loss function of all air defense weapons to all key locations.
[0058] Example 6
[0059] Based on Example 1, the geographic space model is two-dimensionally unfolded and divided into grids.
[0060] Example 7
[0061] Based on Example 6, in the geographic space model, both the deployable areas and the non-deployable areas are marked as grids.
[0062] Example 8
[0063] Based on Example 1, in step ④, a genetic algorithm is used to calculate and solve the problem in the following steps:
[0064] A. Randomly generate a population, determine the individual fitness, and use the roulette strategy to determine the cumulative probability of the individual;
[0065] B. Generate new individuals according to certain mutation probability and mutation method, and judge whether they are illegal solutions. If yes, mutate or crossover again, otherwise continue;
[0066] C. Determine whether the optimization criteria are met. If so, output the best individual and its optimal solution.
[0067] Example 9
[0068] Based on the above embodiment, the following steps are specifically adopted:
[0069] Step S101, determining and quantifying the coverage range of air defense weapons for key locations, designing a coverage loss function of air defense weapons for a certain key location, and then obtaining a coverage loss function for multiple key locations;
[0070] Step S102, determining the geographical environment model, providing the environment model and its constraint environment;
[0071] Step S103, determining the air defense weapon deployment optimization model, and using a genetic algorithm based on a grid map to solve the air defense weapon deployment model, by setting the number of weapon configurations of each type and the environmental model, automatically generating an optimal deployment display diagram under the current weapon configuration.
[0072] Furthermore, the coverage range of air defense weapons for key areas to be defended was determined, including:
[0073] (1) When R max >r tf , 0≤r b ≤r tf -R max hour,
[0074] (2) When R max >r tf 、r b >r tf -R max When θ p =θ j or θ p =π-θ j hour,
[0075] (3) When R max >r tf , 0≤r b ≤R max -r tf hour,
[0076] (4) When R max >r tf 、r b >R max -r tf 、r b ≤P max hour,
[0077] (5) When R max >r tf 、r b >R max -r tf , hour,
[0078]
[0079] in, rtf is the radius of the bombing circle, r b is the distance between the air defense weapon and the center of the key point, R max is the maximum killing radius, P max The maximum route shortcut.
[0080] Discretize the 360° direction of the key point into 360 degrees, that is, K = 360, and calculate the basic safety vector The calculation method is:
[0081]
[0082]
[0083]
[0084] Among them, c is the corresponding direction of the attack The subscript of T(k) is The distance from the subscript to c ranges from [0, K / 2], and its corresponding value before discretization is θ, which ranges from [0, 180°]. up, low, a, and b are all configurable parameters, up is the upper limit of the basic safety degree, and low is the lower limit of the basic safety degree.
[0085] Furthermore, according to the r in the cover range tf , establish a defense radius for long-range, medium-range and short-range air defense weapons And calculate separately Among them, YH i,j is the cover vector of weapon i for key point j, and based on this, the long-range cover value vector of each key point is calculated Mid-range cover value vector Close range protection value vector The calculation formula is as follows:
[0086]
[0087]
[0088]
[0089] Among them, e1, e2∈[0,1] are parameters that can be set in the algorithm. As the basic safety, It refers to the protection value vector synthesis operation, and the calculation principle is as follows:
[0090]
[0091] Taking the above factors into consideration, the loss function of weapon i to be deployed to location j is designed as follows:
[0092]
[0093] Consider the long-range cover value vector of the key point Mid-range cover value vector Close range protection value vector The protection loss function of location j is:
[0094]
[0095] Furthermore, considering that air defense weapons need to cover multiple key locations in actual scenarios, the multi-key location cover loss function is designed as follows:
[0096]
[0097] Where M is the number of key locations, is the protection loss function of all air defense weapons to the key point m, η m Weight the importance of location m, Loss YH_sum It is the protection loss function of all air defense weapons to all key locations.
[0098] Furthermore, the geographical environment model is determined, and a grid quantification method is adopted to quantify the air defense weapon deployment environment, including: the environment quantification is carried out in a two-dimensional space, and the defense area is divided into n×n discrete areas using a grid composed of horizontal and vertical lines; each grid unit is a basic unit for deployment, that is, key points and air defense weapons are located on a certain grid; there are rivers, ups and downs and other areas that cannot be deployed in the environmental model.
[0099] Furthermore, for deployment situation I, the air defense weapon deployment optimization model is determined, and the target optimization model is established as follows:
[0100] Objective function:
[0101] Constraints: Different air defense weapons cannot be in the same grid unit; air defense weapons cannot be deployed in undeployable areas.
[0102] The grid map-based genetic algorithm is used to solve the air defense weapon deployment optimization model. By setting the number of weapon configurations of each type and the environmental model, the optimal deployment display diagram under the current weapon configuration is automatically generated. The algorithm flow is as follows:
[0103] (1) Encoding the deployment location of air defense weapons using coordinates;
[0104] (2) According to the encoding method, randomly generate the population and determine the individual fitness
[0105] fitness(I)=-Loss YH_sum(I)-min i (-Loss YH_sum (I i ))
[0106] (3) Using the roulette strategy to determine the cumulative probability of an individual
[0107]
[0108] (4) Generate new individuals using the uniform crossover and nearest neighbor mutation methods and determine whether they are illegal solutions. If so, mutate or crossover again; otherwise, continue;
[0109] (5) Evaluate the fitness of all chromosomes in the population and update the optimal chromosome;
[0110] (6) Determine whether the termination criteria are met. If so, output the best individual and the optimal solution.
[0111] Example 10
[0112] Based on Example 9, the specific steps are as follows:
[0113] (1) Determine and quantify the coverage range of air defense weapons for key locations, design the coverage loss function of air defense weapons for a certain key location, and then obtain the coverage loss function of multiple key locations;
[0114] (2) Determine the geographic environment model;
[0115] (3) determining an air defense weapon deployment optimization model based on the multi-key point loss function in step (1);
[0116] (4) Using a genetic algorithm based on a grid map, the air defense weapon deployment optimization model determined in step (3) is solved under the environmental model determined in step (2).
[0117] A 70×70 grid is given as the simulation scene. The starting point of the attack direction in this scene is (70,70), that is, the attack direction of each key point is the direction from this point to the key point. The simulation scene contains two key points, whose positions are (33,32) and (21,37) respectively.
[0118] The common parameter settings of the two algorithms are as follows: degree of discretization of azimuth: 360, that is, the 360° azimuth of the important place is discretized into 360 parts; defense radius: 200km for long-range, 100km for medium-range, and 40km for short-range; up=0.6, low=0.1, a=70, b=10, e1=0.3, e2=0, pxd=0.7; population size: 1500; crossover probability: 0.9; mutation probability: 0.9; maximum number of generations: 200; maximum number of stagnation generations (termination condition): 20, that is, the algorithm is terminated when the objective function stagnates for 20 generations.
[0119] Weapon performance is:
[0120] Type 1 (Long): Maximum route shortcut 130km, maximum firing range 150km, weapon effectiveness 0.8, electromagnetic compatibility distance 1km;
[0121] Type 2 (Medium): Maximum route shortcut 70km, maximum firing range 90km, weapon effectiveness 0.8, electromagnetic compatibility distance 1km;
[0122] Type 3 (near): Maximum route shortcut 40km, maximum firing range 50km, weapon effectiveness 0.8, electromagnetic compatibility distance 1km.
[0123] As a specific embodiment, given the number of weapon configurations specified, it includes:
[0124] Weapon configuration 1: 1 type 1 (long range), 6 type 2 (medium range), 6 type 3 (close range);
[0125] Weapon configuration 2: Type 1 (long range) 2, Type 2 (medium range) 6, Type 3 (close range) 6;
[0126] Weapon configuration 3: Type 1 (long range) 2, Type 2 (medium range) 5, Type 3 (close range) 6;
[0127] Weapon configuration 4: Type 1 (long range) 2, Type 2 (medium range) 7, Type 3 (close range) 6;
[0128] Weapon configuration 5: 2 units of type 1 (long), 6 units of type 2 (medium), 5 units of type 3 (close); Weapon configuration 6: 2 units of type 1 (long), 6 units of type 2 (medium), 7 units of type 3 (close).
Claims
1. An air defense weapon combat deployment algorithm, characterized in that: The steps include: ① Construct loss function: According to the coverage range of air defense weapons on the defense key points, construct the coverage loss function of air defense weapons on the defense key points; ② Determine the geographic model: Build a geographic spatial model, which distinguishes deployable areas and non-deployable areas based on grids; ③ Determine the deployment model: With the goal of minimizing the calculated value of the cover loss function of multiple air defense weapons for defending key areas, and with the geographic space model as a constraint, establish an air defense weapon deployment optimization model; ④ Solve the deployment model: Use genetic algorithm or particle swarm algorithm to solve the air defense weapon deployment optimization model and obtain the optimal deployment plan; The specific steps are as follows: Step S101, determine and quantify the coverage range of air defense weapons for key locations, design a coverage loss function of air defense weapons for a certain key location, and obtain a coverage loss function for multiple key locations; Step S102, determining the geographical environment model, providing the environment model and its constraint environment; Step S103, determining an air defense weapon deployment optimization model, and solving the air defense weapon deployment model using a genetic algorithm based on a grid map, and automatically generating an optimal deployment display diagram under the current weapon configuration by setting the number of weapon configurations of each type and the environmental model; Determine the coverage of air defense weapons for key areas to be defended, including: (1) When R max >r tf , 0≤r b ≤r tf -R max hour, (2) When R max >r tf 、r b >r tf -R max When θ p =θ j or θ p =π-θ j hour, (3) When R max >r tf , 0≤r b ≤R max -r tf hour, (4) When R max >r tf 、r b >R max -r tf 、r b ≤P max hour, (5) When R max >r tf 、r b >R max -r tf , hour, in, r tf is the radius of the bombing circle, r b is the distance between the air defense weapon and the center of the key point, R max is the maximum killing radius, P max It is the biggest route shortcut; Discretize the 360° direction of the key point into 360 degrees, that is, K = 360, and calculate the basic safety vector The calculation method is: Among them, c is the corresponding direction of the attack The subscript of T(k) is The distance from the subscript to c has a value range of [0, K / 2], and its corresponding value before discretization is θ, which has a value range of [0, 180°]; up, low, a, and b are all configurable parameters, up is the upper limit of the basic safety degree, and low is the lower limit of the basic safety degree; According to the r in the cover range tf , establish a defense radius for long-range, medium-range and short-range air defense weapons And calculate separately Among them, YH i,j is the cover vector of weapon i for key point j, and based on this, the long-range cover value vector of each key point is calculated Mid-range cover value vector Close range protection value vector The calculation formula is as follows: Among them, e1, e2∈[0,1] are parameters that can be set in the algorithm. As the basic safety, It refers to the protection value vector synthesis operation, and the calculation principle is as follows: Taking the above factors into consideration, the loss function of weapon i to be deployed on location j is designed as follows: K is the maximum subscript after discretizing the 360° direction of the defended location; Consider the long-range cover value vector of the key point Mid-range cover value vector Close range protection value vector The protection loss function of location j is: Considering that air defense weapons need to cover multiple key locations in actual scenarios, the loss function for covering multiple key locations is designed as follows: Where M is the number of key locations, is the protection loss function of all air defense weapons to the key point m, η m Weight the importance of location m, Loss YH_sum is the protection loss function of all air defense weapons to all key locations; Determine the geographic environment model and adopt the grid quantification method to quantify the air defense weapon deployment environment, including: the environment quantification is carried out in two-dimensional space, and the defense area is divided into n×n discrete areas using grids composed of horizontal and vertical lines; each grid unit is the basic unit of deployment, that is, the key points and air defense weapons are located on a certain grid; there are rivers, ups and downs and other areas that cannot be deployed in the environment model; According to deployment situation I, the air defense weapon deployment optimization model is determined, and the target optimization model is established as follows: Objective function: Constraints: Different air defense weapons cannot be in the same grid unit; air defense weapons cannot be deployed in non-deployable areas; The grid map-based genetic algorithm is used to solve the air defense weapon deployment optimization model. By setting the number of weapon configurations of each type and the environmental model, the optimal deployment display diagram under the current weapon configuration is automatically generated. The algorithm flow is as follows: (1) Encoding the deployment location of air defense weapons using coordinates; (2) According to the encoding method, randomly generate the population and determine the individual fitness: fitness(I)=-Loss YH_sum (I)-min i (-Loss YH_sum (I i )) (3) Use the roulette strategy to determine the cumulative probability of individuals: (4) Generate new individuals using the uniform crossover and nearest neighbor mutation methods and determine whether they are illegal solutions. If so, mutate or crossover again; otherwise, continue; (5) Evaluate the fitness of all chromosomes in the population and update the optimal chromosome; (6) Determine whether the termination criteria are met. If so, output the best individual and optimal solution; The air defense weapon has a constraint condition on the coverage range of the defense key point, and the constraint condition is calculated using the following formula: Among them, the air attack azimuth α∈(-π,π] is the angle between the carrier air attack direction and the baseline, the route shortcut P is the shortest distance from the ground air defense weapon to the horizontal plane projection of the carrier route; the cover depth R n Refers to the distance the carrier aircraft passes through the key anti-aircraft fire circle before reaching the bombing circle; For cover range.
Citation Information
Patent Citations
Offshore combat air defense deployment optimization design method
CN108520312A
End defense weapon system military strength deployment optimization method based on PSO-GA hybrid algorithm
CN110991119A
Particle swarm algorithm-based heterogeneous unmanned aerial vehicle three-dimensional space deployment method and device
CN113395706A
Method and System for Predicting Wildfire Hazard and Spread at Multiple Time Scales
US20210271934A1
