Task planning method for electronic countermeasure equipment based on improved genetic algorithm

Abstract

The invention discloses a task planning method of electronic confrontation equipment based on an improved genetic algorithm. The method comprises the following steps: S1, constructing an electronic confrontation task complex network model based on a'detection-control-disturbance-evaluation-prevention 'capability ring; s2, constructing a task execution time sequence model based on multiple combat chains; s3, constructing a'detection-control-disturbance-evaluation-prevention 'complex network combat effectiveness measurement model based on the task completion degree; and S4, constructing an electronic confrontation equipment task planning algorithm model based on the improved genetic algorithm. On the basis of a genetic algorithm, an expansion factor is added to establish a time and efficiency weight dynamic control algorithm, and time and efficiency simultaneously reach expected values to optimize electronic countermeasure equipment task planning.

Description

Technical Field

[0001] The invention belongs to the field of military operations research and electronic countermeasure technology, and in particular relates to a task planning method for electronic countermeasure equipment based on an improved genetic algorithm. Background Art

[0002] The reasonable matching of combat missions and equipment resources is the main content of the task planning stage of electronic countermeasure equipment. One of the key issues of electronic countermeasure equipment task planning is combat mission scheduling, that is, given a combat mission, allocating time and equipment resources for the combat mission under the condition of satisfying constraints. This process is actually a matching process of combat missions, equipment resources, combat effectiveness and mission time, which is affected and restricted by many factors such as combat mission attributes, equipment resource attributes, combat effectiveness, mission time limit and mission environment.

[0003] At present, there are still the following shortcomings in the task planning of electronic countermeasure equipment: 1. The electronic countermeasure equipment task planning model based on platform organizational form optimization focuses on the capability demand constraints of combat missions on combat resource platforms, but does not consider the time constraints of combat missions and the timing constraints of combat missions; 2. The research on combat mission resource allocation algorithm based on MDLS and GA considers the requirements of resource scheduling time and quantity in detail, but does not take into account the combat effectiveness of equipment in performing tasks; 3. The army's tactical-level combat task allocation and optimization method published in the "Journal of Ordnance" in May 2023 mainly established a multi-objective optimization function based on factors such as synergy, combat loss rate, and the relationship between tasks and organized forces, and did not model it from the perspective of efficiency factors. Summary of the invention

[0004] In order to overcome the deficiencies of the prior art, the present invention aims to provide a task planning method for electronic countermeasure equipment based on an improved genetic algorithm.

[0005] In order to achieve the above-mentioned invention object, the present invention adopts the following technical scheme:

[0006] A task planning method for electronic countermeasure equipment based on an improved genetic algorithm comprises the following steps:

[0007] S1. Construct a complex network model of electronic countermeasure tasks based on the "detection-control-interference-evaluation-defense" capability loop;

[0008] S2. Construct a task execution time series model based on multiple combat chains;

[0009] S3. Construct a complex network combat effectiveness measurement model of "detection-control-interference-evaluation-prevention" based on task completion;

[0010] S4. Construct an electronic countermeasure equipment task planning algorithm model based on an improved genetic algorithm.

[0011] Furthermore, the above step S1 includes the following sub-steps:

[0012] S1.1. Determine the combat mission: The combat mission set is decomposed according to the capability loop of "detection-control-interference-evaluation-defense". The complex network of electronic countermeasure missions containing N tasks is denoted as G = {T, E}, where T is:

[0013]

[0014] Where, T 侦 、T 控 、T 扰 、T 评 、T 防 There is an execution order dependency and constraint relationship between them. Its properties include the task start time Mission duration

[0015] E=E i×i i=1,2,…,(I+J+K+L+M) is the set of edges between T, and the edges are directed edges, indicating T 侦 、T 控 、T 扰 、T 评 、T 防 between Characterization of execution order dependencies and constraints;

[0016] S1.2. Determine the electronic countermeasure equipment resources: Let the set of electronic countermeasure equipment resources containing S items be R = {R s |s=1,2,…,S};

[0017] S1.3, determine the execution time of combat mission and equipment resource matching: the corresponding execution time matrix of mission and resource matching is TRT = (Trt s,i ) S×(I+J+K+L+M) , where Trt s,i Indicates platform resources R s Matching Task T i Execution time;

[0018] S1.4. Determine the task completion degree of the matching between combat mission and equipment resources: The task completion degree of the corresponding execution of the matching between mission and resources is PRT = (Prt s,i ) S×(I+J+K+L+M) , where Trt s,i Indicates platform resources R s In the execution of task T i degree of task completion;

[0019] S1.5. Determine the combat mission and platform resource planning allocation plan: remember the mission-resource allocation plan like It means platform resource R m Assigned to task T i Use, otherwise When a resource of the same type is assigned to multiple tasks at the same time, the resource will be allocated to each task in the logical order of task execution.

[0020] Furthermore, the above step S2 is operated as follows: Assuming that the task of the combat chain is assigned to the electronic countermeasure equipment resources, establish the combat chain time sequence TLink k ={t k1 ,t k2 ,…,t ki}, where t ki ≥t ki-1 , k=1,2,…,n,k is the combat chain number; n is the number of combat chains, i=1,2,…,m,i is the task number, m is the number of tasks in the kth combat chain; TLink k is the kth combat chain time sequence determined according to the electronic countermeasure equipment allocation plan, t ki It is the accumulation of tasks performed by combat chain equipment, that is, t ki =t ki-1 +Trt s，ki ;

[0021] The steps for constructing the task execution sequence model are as follows: first, establish a task execution sequence reconstruction algorithm for two combat chains; then, use the reconstruction algorithm to traverse all combat chains, reconstruct the time sequence of each combat chain, and finally form the task execution sequence of all combat chains.

[0022] Furthermore, in the above step S2.1, the step of constructing the task execution sequence model includes the following sub-steps:

[0023] S2.11. Determine the combat missions and combat mission resource allocation of the two combat chains;

[0024] S2.12. Set the task duplication flag TLinkTFlag between combat chains k ={Tflag k1 , Tflag k2 , ..., Tflag ki} and the task resource conflict flag TLinkRTimeFlag between the combat chain k ={RTimeflag k1 , RTimeflag k2 , ..., RTimeflag ki};

[0025] S2.13. Traversing the TLinkRTimeFlag of two combat chains k and TLinkRTimeFlag l Sequence, compare the number of RTimeflag 0 in the two sequences; assuming that the number of 0 in the lth combat sequence is greater than that in the kth, then take the kth combat sequence as the basis, and compare the resources allocated to the i-th task in the kth combat sequence with the resources allocated to the lth combat sequence one by one. When Tflag ki = 0, and there is a resource conflict, update TLinkRTimeFlag l RTimeflag in lj The value is 0, otherwise it is 1; when Tflag ki =1, RTimeflag lj The value is 0;

[0026] S2.14, according to TLinkRTimeFlag l RTimeflag lj When the value is 1, update the iteration TLink l In and TLink k In Among them, m l is the number of tasks in the first combat sequence; m k is the number of tasks in the kth combat sequence; when traversing the lth combat sequence, TLink l Update completed, and TLink k In Also updated;

[0027] S2.15. After traversing the i value of the kth combat sequence, the task execution time sequence of the two combat sequences is obtained, that is, TLink k and TLink l .

[0028] Furthermore, the above step S3 is operated as follows: Assume that the T of the complex network G of the electronic countermeasure task containing N tasks ki Allocate resources R s The task completion rate is Prt s，ki , then R s Complete T ki The self-information of is I(x) ki =-ln(Prt s,ki ), according to T ki Belong to T 侦 、T 控 、T 扰 、T 评 、T防 One of them, determine I(x) ki Properties f∈(detection, control, interference, evaluation, defense), according to the n combat chains decomposed by the set E of edges between T, the combat effectiveness measurement model of the kth combat chain is

[0029]

[0030] in,

[0031] The combat effectiveness measurement of n combat chains is:

[0032]

[0033] Furthermore, the above step S4 includes the following sub-steps:

[0034] S4.1. Determine the time objective function

[0035] When platform resources are allocated to various tasks according to the task-resource allocation scheme, the task execution time is the final end time of all tasks, that is,

[0036]

[0037] The planning and scheduling of electronic countermeasure equipment combat missions takes the shortest combat time as the goal. The objective function of the mathematical model of electronic countermeasure equipment combat mission planning and scheduling is:

[0038]

[0039] S4.2. Determine the operational effectiveness objective function

[0040] When platform resources are allocated to various tasks according to the task-resource allocation plan, the operational effectiveness of the n operational chains after decomposition is

[0041]

[0042] The planning and scheduling of electronic countermeasure equipment combat missions takes the maximum combat effectiveness as the goal. The objective function of the mathematical model of electronic countermeasure equipment combat mission planning and scheduling is:

[0043]

[0044] S4.3. Establish a mathematical model for task planning based on time and efficiency

[0045] With the goal of minimizing the execution time TRT of electronic countermeasure equipment combat missions and maximizing the combat effectiveness PRT, a mathematical model for planning and scheduling the combat missions of electronic countermeasure equipment is established as follows:

[0046]

[0047] S4.4. Improved genetic algorithm based on threshold and dynamic weight

[0048] (1) Add a threshold to the existing mathematical model, that is, add a time threshold T in time. min ,min(TRT)≥T min , add a performance threshold P to the performance max , max(PRT)≥P max , the planning mathematical model is obtained as

[0049]

[0050] In the formula, represents the time objective function; Represents the combat effectiveness objective function; TLink k represents the combat chain time series; T min Indicates the time threshold; P max represents the efficacy threshold;

[0051] (2) Assign an initial weight to the maximum and minimum objective function results. Based on the electronic countermeasure equipment task planning model, assign weights to min(TRT) and max(PRT), that is, ω T and ω P ;

[0052] (3) The minimum objective function is transformed into the maximum objective function, min(TRT) is transformed into

[0053] (4) Redesign the maximum objective function, maxF = ω T ×maxT+ω P ×maxPRT, and introduce an expansion factor EXPLAND_FACTOR to the maximum objective function. The objective function value of each iteration is expanded to speed up the convergence speed. The objective function value is maxF=EXPLAND_FACTOR×maxF;

[0054] (5) Based on the initial weights, the calculation is performed according to the results of the genetic algorithm. If the target is met, the process ends. If the target is not met, the weights are iteratively updated according to the results of the genetic algorithm, and then genetic calculation is performed again according to the new weights until the planning target is reached. The algorithm for dynamic weight update is as follows:

[0055]

[0056] Among them, ω P(r+1) and ω T(r+1)The r in the equation is the rth genetic operation, and each genetic operation is calculated according to the genetic algebra.

[0057] Due to the adoption of the above-mentioned technical solution, the present invention has the following advantages:

[0058] This task planning method for electronic countermeasure equipment based on improved genetic algorithm is based on the time and combat effectiveness constraints of electronic countermeasure equipment in a complex network combat mission system, and on the basis of the genetic algorithm, an expansion factor is added to establish a dynamic control algorithm for time and effectiveness weights, which effectively solves the problem of achieving expected values ​​of time and effectiveness at the same time and optimizes the task planning of electronic countermeasure equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a structural diagram of an embodiment of a complex network for electronic countermeasure tasks based on a "detection-control-interference-assessment-prevention" capability loop;

[0060] Figure 2 yes Figure 1 The structural diagram of the task combat chain of the complex network decomposition of the electronic countermeasure task;

[0061] Figure 3 is a flow chart of the improved genetic algorithm in the present invention;

[0062] Figure 4 It is the curve diagram of the best objective function value change in the first cycle iteration;

[0063] Figure 5 It is the curve diagram of the optimal objective function value change in the 10th cycle iteration;

[0064] Figure 6 This is the curve diagram of the optimal objective function value change in the 18th cycle iteration;

[0065] Figure 7 It is a dynamic change curve of time weight and efficiency weight;

[0066] Figure 8 It is a curve chart of minimum time ratio and maximum efficiency change. DETAILED DESCRIPTION

[0067] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0068] A task planning method for electronic countermeasure equipment based on an improved genetic algorithm comprises the following steps:

[0069] S1. Construct a complex network model of electronic countermeasure tasks based on the "detection-control-interference-assessment-prevention" capability loop, and the operations are:

[0070] S1.1. Determine the combat mission: Construct the combat mission network structure according to the logical order of reconnaissance, control, interference, evaluation, and protection. The reconnaissance node, control node, interference node, evaluation node, and protection node form a loop, that is, a capability loop. The combat mission set is decomposed according to the capability loop of "reconnaissance-control-interference-evaluation-defense". The complex network of electronic countermeasure missions containing N tasks is denoted as G = {T, E}, where T is:

[0071]

[0072] Where, T 侦 、T 控 、T 扰 、T 评 、T 防 There is an execution order dependency and constraint relationship between them. Its properties include the task start time Mission duration

[0073] E=E i＝i i=1,2,…,(I+J+K+L+M) is the set of edges between T, and the edges are directed edges, indicating T 侦 、T 控 、T 扰 、T 评 、T 防 between Characterization of execution order dependencies and constraints;

[0074] S1.2. Determine the electronic countermeasure equipment resources: Decompose the electronic countermeasure equipment resources according to the type of electronic countermeasure equipment, the unit to which the equipment belongs, and the nature of the task to obtain resources that can match the task; the decomposed resources have the ability to independently undertake electronic countermeasure reconnaissance, control, interference, evaluation, and defense tasks, and can all be occupied at the same time; the set of electronic countermeasure equipment resources containing S items is denoted as R = {R s |s=1,2,…,S};

[0075] S1.3, determine the execution time of combat mission and equipment resource matching: combat missions occupy different electronic countermeasure equipment platform resources, and their execution time is different. The corresponding execution time matrix of task and resource matching is TRT = (Trt s,i ) S×(I+J+K+L+M) , where Trt s,i Indicates platform resources R s Matching Task T i The execution time of Trt s,i =0, it means that the platform resources and tasks cannot be matched;

[0076] S1.4. Determine the task completion degree of matching combat missions and equipment resources: Combat missions occupy different electronic countermeasure equipment platform resources, and the degree to which the equipment platform resources complete combat missions is different. The task completion degree of the corresponding execution of task and resource matching is recorded as PRT = (Prt s,i ) S×(I+J+K+L+M) , where Prt s,i Indicates platform resources R s In the execution of task T i The task completion degree; if Prt s,i =0, it means the platform resource R s Execute Task T i The task completion degree is 0, if Trt s,i =0, then Prt s,i =0;

[0077] S1.5. Determine the combat mission and platform resource planning allocation plan: For a series of electronic countermeasure tasks, through task selection based on dynamic list planning, the task-resource allocation plan can be optimally utilized in terms of time and efficiency. Resources are allocated to each task, and the execution sequence of task resources and the efficiency of resource execution tasks are obtained to solve the optimization problem of electronic countermeasure equipment combat mission scheduling; record the task-resource allocation plan like It means platform resource R m Assigned to task T i Use, otherwise When a resource of the same type is assigned to multiple tasks at the same time, the resource will be assigned to each task in the logical order of task execution, and Trt m,i =0 and Prt m,i = 0 resource R m Cannot be assigned to task T i ;

[0078] S2. After decomposing the tasks to form a task operation chain, the task-resource allocation plan is determined. R-T , forming a task execution sequence; constructing a task execution time sequence model based on multiple combat chains to calculate the task execution sequence model with the best execution time; assuming that the tasks of the combat chain are assigned with electronic countermeasure equipment resources, establishing the combat chain time sequence TLink k ={t k1 ,t k2 ,…,t ki}, where t ki ≥t ki-1 , k=1,2,…,n, k is the combat chain number; n is the number of combat chains, i=1,2,…,m, i is the task number, m is the number of tasks in the kth combat chain; TLink kis the kth combat chain time sequence determined according to the electronic countermeasure equipment allocation plan, t ki It is the accumulation of tasks performed by combat chain equipment, that is, t ki =t ki-1 +Trt s,ki ; Here we assume that T ki Allocate resources R s The time required, the initial value of which only considers a single combat chain, is not affected by conflicts in the resources of other combat chain tasks;

[0079] When there are multiple combat chains, there will be two situations: task duplication and equipment resource allocation conflict. To solve the above two situations, the construction steps of the task execution sequence model are as follows: first, establish a task execution sequence reconstruction algorithm for two combat chains; then, use the reconstruction algorithm to traverse all combat chains, reconstruct each combat chain time series, and finally form the task execution sequence of all combat chains; the task execution sequence model is based on the task execution sequence reconstruction algorithm of two combat chains, and the specific steps are as follows:

[0080] (1) Determine the combat missions and combat mission resource allocation of the two combat chains;

[0081] (2) Set the task duplication flag TLinkTFlag between combat chains k ={Tflag k1 , Tflag k2 , ..., Tflag ki} and the task resource conflict flag TLinkRTimeFlag between the combat chain k ={RTimeflag k1 , RTimeflag k2 , ..., RTimeflag ki};

[0082] When a task from one combat chain appears in another combat chain, Tflag ki =1, otherwise, Tflag ki =0; when a combat chain's Tflag ki = 0, and the resources allocated to the ith task of the combat chain appear in the task resources of another combat chain, then RTimeflag ki =0, indicating that the combat chain ki ,t k(i+1) ...needs to be adjusted, otherwise RTimeflag ki =1, indicating t ki Available, no adjustment required;

[0083] (3) Traverse the TLinkRTimeFlag of the two combat chainsk and TLinkRTimeFlag l Sequence, compare the number of RTimeflag 0 in the two sequences; assuming that the number of 0 in the lth combat sequence is greater than that in the kth, then take the kth combat sequence as the basis, and compare the resources allocated to the i-th task in the kth combat sequence with the resources allocated to the lth combat sequence one by one. When Tflag ki = 0, and there is a resource conflict, update TLinkRTimeFlag l RTimeflag in lj The value is 0, otherwise it is 1; when Tflag ki =1, RTimeflag lj The value is 0;

[0084] (4) According to TLinkRTimeFlag l RTimeflag lj When the value is 1, update the iteration TLink l In and TLink k In Among them, m l is the number of tasks in the first combat sequence; m k is the number of tasks in the kth combat sequence; when traversing the lth combat sequence, TLink l Update completed, and TLink k In Also updated;

[0085] (5) After traversing the i value of the kth combat sequence, the task execution time sequence of the two combat sequences is obtained, that is, TLink k and TLink l ;

[0086] S3. Construct a complex network combat effectiveness measurement model based on task completion of "detection-control-interference-evaluation-prevention"

[0087] Due to the influence of factors such as the internal state of each entity in the complex network G of electronic countermeasure tasks and the complexity of the battlefield environment, the combat effectiveness of electronic countermeasure equipment to complete the task is uncertain. The task completion index is used to represent the uncertainty of combat effectiveness, and a combat effectiveness uncertainty information measurement model is established.

[0088] The operation is: Assume that the T of the complex network G of the electronic countermeasure task contains N tasks ki Allocate resources R s The task completion rate is Prt s，ki , then R s Complete T kiThe self-information of is I(x) ki =-ln(Prt s,ki ), according to T ki Belong to T 侦 、T 控 、T 扰 、T 评 、T 防 One of them, determine I(x) ki Properties f∈(detection, control, interference, evaluation, defense), according to the n combat chains decomposed by the set E of edges between T, the combat effectiveness measurement model of the kth combat chain is

[0089]

[0090] in,

[0091] The combat effectiveness measurement of n combat chains is:

[0092]

[0093] S4. Constructing an electronic countermeasure equipment mission planning algorithm model based on an improved genetic algorithm

[0094] Plan allocation according to combat missions and platform resources D R-T , can calculate the task chain TLink, and obtain the corresponding combat effectiveness I, the electronic countermeasure equipment task planning model is based on the optimal task equipment allocation plan D R-T , in order to achieve the optimal time and efficiency. Therefore, the objective function mainly includes the time objective function and the efficiency objective function; including the following sub-steps:

[0095] S4.1. Determine the time objective function

[0096] When platform resources are allocated to various tasks according to the task-resource allocation scheme, the task execution time is the final end time of all tasks, that is,

[0097]

[0098] The planning and scheduling of electronic countermeasure equipment combat missions takes the shortest combat time as the goal. The shorter the combat mission time, the faster the resources of the electronic countermeasure equipment combat platform can respond, and the more they can adapt to the complex and changeable electromagnetic environment on the battlefield. Therefore, the objective function of the mathematical model of electronic countermeasure equipment combat mission planning and scheduling is:

[0099]

[0100] S4.2. Determine the operational effectiveness objective function

[0101] When platform resources are allocated to various tasks according to the task-resource allocation plan, the operational effectiveness of the n operational chains after decomposition is

[0102]

[0103] The planning and scheduling of electronic countermeasure equipment combat missions takes the maximum combat effectiveness as the goal. The objective function of the mathematical model of electronic countermeasure equipment combat mission planning and scheduling is:

[0104]

[0105] S4.3. Establish a mathematical model for task planning based on time and efficiency

[0106] With the goal of minimizing the execution time TRT of electronic countermeasure equipment combat missions and maximizing the combat effectiveness PRT, the mathematical model of electronic countermeasure equipment combat mission planning and scheduling is established by comprehensively considering the constraints of the task execution time series model in the task-resource allocation process:

[0107]

[0108] S4.4. Improved genetic algorithm based on threshold and dynamic weight

[0109] Since there are two optimization models, the minimum and maximum, in the planning model, the genetic algorithm has large fluctuations when solving. For such maximum and minimum objective functions, improvements are made on the basis of the existing genetic algorithm to achieve a more objective balance between time and efficiency. The specific operations are as follows:

[0110] (1) To make the planning model more purposeful, a threshold is added to the existing mathematical model, that is, a time threshold T is added to the time. min ,min(TRT)≤T min , add a performance threshold P to the performance max , max(PRT)≥P max , the planning mathematical model is obtained as

[0111]

[0112] In the formula, represents the time objective function; Represents the combat effectiveness objective function; TLink k represents the combat chain time series; T min Indicates the time threshold; P max represents the efficacy threshold;

[0113] (2) Assign an initial weight to the maximum and minimum objective function results. Based on the electronic countermeasure equipment task planning model, assign weights to min(TRT) and max(PRT), that is, ω T and ω P ;

[0114] (3) The minimum objective function is transformed into the maximum objective function, min(TRT) is transformed into

[0115] (4) Redesign the maximum objective function, maxF = ω T ×maxT+ω P ×maxPRT, and introduce an expansion factor EXPLAND_FACTOR to the maximum objective function. The objective function value of each iteration is expanded to speed up the convergence speed. The objective function value is maxF=EXPLAND_FACTOR×maxF;

[0116] (5) Based on the initial weights, the calculation is performed according to the results of the genetic algorithm. If the target is met, the process ends. If the target is not met, the weights are iteratively updated according to the results of the genetic algorithm, and then genetic calculation is performed again according to the new weights until the planning target is reached. The algorithm for dynamic weight update is as follows:

[0117]

[0118] Among them, ω P(r+1) and ω T(r+1) The r in the equation is the rth genetic operation. Each genetic operation is calculated according to the genetic algebra (evolutionary algebra). The automatic updating of weights can solve the problem that different dimensions of time and efficiency cannot be uniformly measured.

[0119] Example

[0120] like Figure 1 As shown, the electronic countermeasure equipment task planning method based on the improved genetic algorithm of the present invention performs electronic countermeasure equipment task planning on the electronic countermeasure task complex network, assuming that the electronic countermeasure equipment platform resource set is R = {R 1 ,R 2 ,…,R 12 ,R 13}, the corresponding execution time matrix TRT of task matching with platform resources is:

[0121]

[0122] The task completion matrix of the corresponding execution of task and resource matching is:

[0123]

[0124] Improved genetic algorithm initial parameters: weight ω T =0.1,ω P =0.9, threshold T min =13,P max =0.85; unit binary DNA_SIZE=8, population size POP_SIZE=200, crossover probability CROSSOVER_RATE=0.8, mutation probability MUTATION_RATE=0.005, genetic generations N_GENERATIONS=70, expansion factor EXPLAND_FACTOR=1.0001.

[0125] After calculation by Python code, the following results are obtained:

[0126]

[0127] The allocation scheme is: R 2 Assign to T 1 T 6 T 10 T 11 , R 6 Assign to T 2 T 9 , R 4 Assign to T 3 T 4 , R 5 Assign to T 5 , R 9 Assign to T 7 , R 3 Assign to T 8 ,Under the improved genetic algorithm, its execution time is 8.3, the combat effectiveness is 0.89, the time weight is 0.61, and the effectiveness weight is 0.39.

[0128] In the present invention, the improved genetic algorithm performs a total of 18 genetic algorithm cycles, and the best objective function values ​​of the 1st, 10th, and 18th genetic calculations are as follows: Figure 4 , 5 , 6, the weights of time and efficiency change as follows Figure 7 As shown, the time ratio and efficiency are Figure 8 As shown in the above results, it can be seen that the results of the algorithm model in the present invention have achieved the expected purpose and can effectively solve the problem of electronic countermeasure equipment task planning related to time and efficiency.

[0129] The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention. Without departing from the spirit and scope of the present invention, all equivalent changes and modifications made within the scope of the patent application of the present invention shall fall within the scope of patent protection of the present invention.

Claims

1. A task planning method for electronic countermeasure equipment based on an improved genetic algorithm, characterized in that: It includes the following steps: S1. Construct a complex network model of electronic countermeasure tasks based on the "detection-control-interference-evaluation-defense" capability loop; S2. Construct a task execution time series model based on multiple combat chains; S3. Construct a "detection-control-interference-assessment-prevention" complex network combat effectiveness measurement model based on task completion; S4. Construct an electronic countermeasure equipment task planning algorithm model based on an improved genetic algorithm.

2. The task planning method for electronic countermeasure equipment based on improved genetic algorithm according to claim 1 is characterized in that: The step S1 comprises the following sub-steps: S1.

1. Determine the combat mission: The combat mission set is decomposed according to the capability loop of "detection-control-interference-evaluation-defense". The complex network of electronic countermeasure missions containing N tasks is denoted as G = {T, E}, where T is: Where, T 侦 , T 控 , T 扰 , T 评 , T 防 There is an execution order dependency and constraint relationship between them. Its properties include the task start time Mission duration E=E i×i i=1,2,…,(I+J+K+L+M) is the set of edges between T, and the edges are directed edges, indicating T 侦 , T 控 , T 扰 , T 评 , T 防 between Characterization of execution order dependencies and constraints; S1.

2. Determine the electronic countermeasure equipment resources: Let the set of electronic countermeasure equipment resources containing S items be R = {R s |s=1,2,…,S}; S1.3, determine the execution time of combat mission and equipment resource matching: the corresponding execution time matrix of mission and resource matching is TRT = (Trt s，i ) S×(I+J+K+L+M) , where Trt s，i Indicates platform resources R s Matching Task T i Execution time; S1.

4. Determine the task completion degree of the matching between combat mission and equipment resources: The task completion degree of the corresponding execution of the matching between mission and resources is PRT = (Prt s，i ) S×(I+J+K+L+M) , where Trt s，i Indicates platform resources R s In the execution of task T i degree of task completion; S1.

5. Determine the combat mission and platform resource planning allocation plan: remember the mission-resource allocation plan like It means platform resource R m Assigned to task T i Use, otherwise When a resource of the same type is assigned to multiple tasks at the same time, the resource will be allocated to each task in the logical order of task execution.

3. The task planning method for electronic countermeasure equipment based on improved genetic algorithm according to claim 1 or 2, characterized in that: The operation of step S2 is as follows: assuming that the task of the combat chain allocates electronic countermeasure equipment resources, establish the combat chain time sequence TLink k ={t k1 , t k2 ,…,t ki }, where t ki ≥t ki-1 , k = 1, 2, ..., n, k is the combat chain number; n is the number of combat chains, i = 1, 2, ..., m, i is the task number, m is the number of tasks in the kth combat chain; TLink k is the kth combat chain time sequence determined according to the electronic countermeasure equipment allocation plan, t ki It is the accumulation of tasks performed by combat chain equipment, that is, t ki =t ki-1 +Trt s，ki ; The steps for constructing the task execution sequence model are as follows: first, establish a task execution sequence reconstruction algorithm for two combat chains; then, use the reconstruction algorithm to traverse all combat chains, reconstruct the time sequence of each combat chain, and finally form the task execution sequence of all combat chains.

4. The task planning method for electronic countermeasure equipment based on improved genetic algorithm according to claim 3 is characterized in that: In step S2.1, the step of constructing the task execution sequence model includes the following sub-steps: S2.

11. Determine the combat missions and combat mission resource allocation of the two combat chains; S2.

12. Set the task duplication flag TLinkTFlag between combat chains k ={Tflag k1 , Tflag k2 , ..., Tflag ki } and the task resource conflict flag between the combat chain TLinkRTimeFlag k ={RTimeflag k1 , RTimeflag k2 , ..., RTimeflag ki }; S2.

13. Traversing the TLinkRTimeFlag of two combat chains k and TLinkRTimeFlag l Sequence, compare the number of RTimeflag 0 in the two sequences; assuming that the number of 0 in the lth combat sequence is greater than that in the kth, then take the kth combat sequence as the basis, and compare the resources allocated to the i-th task in the kth combat sequence with the resources allocated to the lth combat sequence one by one. When Tflag ki = 0, and there is a resource conflict, update TLinkRTimeFlag l RTimeflag in lj The value is 0, otherwise it is 1; when Tflag ki =1, RTimeflag lj The value is 0; S2.14, according to TLinkRTimeFlag l RTimeflag lj When the value is 1, update the iteration TLink l t in lj , …, and TLink k t in ki , …, Among them, m l is the number of tasks in the first combat sequence; m k is the number of tasks in the kth combat sequence; when traversing the lth combat sequence, TLink l Update completed, and TLint k t in ki , …, Also updated; S2.

15. After traversing the i value of the kth combat sequence, the task execution time sequence of the two combat sequences is obtained, that is, TLink k and TLink l .

5. The task planning method for electronic countermeasure equipment based on improved genetic algorithm according to claim 2 is characterized in that: The operation of step S3 is: Assume that the T of the complex network G of electronic countermeasure tasks including N tasks ki Allocate resources R s The task completion rate is Prt s，ki , then R s Complete T ki The self-information of is I(x) ki =-ln(Prt s，ki ), according to T ki Belong to T 侦 , T 控 , T 扰 , T 评 , T 防 One of them, determine I(x) ki Properties f∈(detection, control, interference, evaluation, defense), according to the n combat chains decomposed by the set E of edges between T, the combat effectiveness measurement model of the kth combat chain is in, The combat effectiveness measurement of n combat chains is:

6. The task planning method for electronic countermeasure equipment based on improved genetic algorithm according to claim 1, 2, 3 or 5, characterized in that: The step S4 comprises the following sub-steps: S4.

1. Determine the time objective function When platform resources are allocated to various tasks according to the task-resource allocation scheme, the task execution time is the final end time of all tasks, that is, The planning and scheduling of electronic countermeasure equipment combat missions takes the shortest combat time as the goal. The objective function of the mathematical model of electronic countermeasure equipment combat mission planning and scheduling is: S4.

2. Determine the operational effectiveness objective function When platform resources are allocated to various tasks according to the task-resource allocation plan, the operational effectiveness of the n operational chains after decomposition is The planning and scheduling of electronic countermeasure equipment combat missions takes the maximum combat effectiveness as the goal. The objective function of the mathematical model of electronic countermeasure equipment combat mission planning and scheduling is: S4.

3. Establish a mathematical model for task planning based on time and efficiency With the goal of minimizing the execution time TRT of electronic countermeasure equipment combat missions and maximizing the combat effectiveness PRT, a mathematical model for planning and scheduling the combat missions of electronic countermeasure equipment is established as follows: S4.

4. Improved genetic algorithm based on threshold and dynamic weight (1) Add a threshold to the existing mathematical model, that is, add a time threshold T in time. min ,min(TRT)≤T min , add a performance threshold P to the performance max , max(PRT)≥P max , the planning mathematical model is obtained as In the formula, represents the time objective function; Represents the combat effectiveness objective function; TLink k represents the combat chain time series; T min Indicates the time threshold; P max represents the efficacy threshold; (2) Assign an initial weight to the maximum and minimum objective function results. Based on the electronic countermeasure equipment task planning model, assign weights to min(TRT) and max(PRT), that is, ω T and ω P ; (3) The minimum objective function is transformed into the maximum objective function, min(TRT) is transformed into (4) Redesign the maximum objective function, maxF = ω T ×maxT+ω P ×maxPRT, and introduce an expansion factor EXPLAND_FACTOR to the maximum objective function. The objective function value of each iteration is expanded to speed up the convergence speed. The objective function value is maxF=EXPLAND_FACTOR×maxF; (5) Based on the initial weights, the calculation is performed according to the results of the genetic algorithm. If the target is met, the process ends. If the target is not met, the weights are iteratively updated according to the results of the genetic algorithm, and then genetic calculation is performed again according to the new weights until the planning target is reached. The algorithm for dynamic weight update is as follows: Among them, ω P(r+1) and ω T(r+1) The r in the equation is the rth genetic operation, and each genetic operation is calculated according to the genetic algebra.

Images