CN111382896A - WTA target optimization method of adaptive chaotic parallel clonal selection algorithm - Google Patents
WTA target optimization method of adaptive chaotic parallel clonal selection algorithm Download PDFInfo
- Publication number
- CN111382896A CN111382896A CN201811645323.0A CN201811645323A CN111382896A CN 111382896 A CN111382896 A CN 111382896A CN 201811645323 A CN201811645323 A CN 201811645323A CN 111382896 A CN111382896 A CN 111382896A
- Authority
- CN
- China
- Prior art keywords
- population
- antibody
- sub
- chaotic
- wta
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000000739 chaotic effect Effects 0.000 title claims abstract description 42
- 238000005457 optimization Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 31
- 230000003044 adaptive effect Effects 0.000 title description 7
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 10
- 238000013377 clone selection method Methods 0.000 claims abstract description 10
- 230000007123 defense Effects 0.000 claims abstract description 9
- 230000005764 inhibitory process Effects 0.000 claims abstract description 8
- 230000007246 mechanism Effects 0.000 claims abstract description 5
- 230000008929 regeneration Effects 0.000 claims abstract description 5
- 238000011069 regeneration method Methods 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims description 23
- 239000000427 antigen Substances 0.000 claims description 15
- 102000036639 antigens Human genes 0.000 claims description 15
- 108091007433 antigens Proteins 0.000 claims description 15
- 238000010367 cloning Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 6
- 230000006378 damage Effects 0.000 claims description 5
- 230000006399 behavior Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 101000802640 Homo sapiens Lactosylceramide 4-alpha-galactosyltransferase Proteins 0.000 claims description 3
- 102100035838 Lactosylceramide 4-alpha-galactosyltransferase Human genes 0.000 claims description 3
- 150000001875 compounds Chemical class 0.000 claims description 3
- 230000028993 immune response Effects 0.000 claims description 3
- 230000006978 adaptation Effects 0.000 claims 1
- 238000012163 sequencing technique Methods 0.000 claims 1
- 238000013461 design Methods 0.000 abstract description 3
- 230000035772 mutation Effects 0.000 abstract description 3
- 239000013589 supplement Substances 0.000 abstract description 2
- 239000011159 matrix material Substances 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000005291 chaos (dynamical) Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 210000000987 immune system Anatomy 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention relates to a WTA target optimization method of a self-adaptive chaotic parallel clone selection algorithm, which solves the problem of weapon target distribution of air defense formation; wherein, a population initialization operator and a mutation operator are designed by utilizing chaotic regeneration and chaotic disturbance; performing parallel mechanism design on each sub-population by adopting a parallel population classification method, and keeping population diversity according to affinity; the self-adaptive clone multiplication operator, the antibody inhibition operator and the antibody circulation supplement operator are designed to improve the clone selection algorithm, and the operators can improve the global optimization capability and the local search capability.
Description
Technical Field
The invention belongs to the field of fire distribution, and particularly relates to a WTA target optimization method of a self-adaptive chaotic parallel clonal selection algorithm.
Background
With the development of modern military transformation, the manifestation of sea battle gradually changes from single-soldier operation to formation operation, but formation air defense operation always faces serious air target threat. Therefore, the research on the fire power distribution (WTA) is very important, and the aim is to research the optimal decision relationship between weapons and targets and maximize the expected effect of the overall combat effectiveness. The WTA problem is essentially a nonlinear combinatorial optimization problem, which is typically a non-deterministic polynomial complete problem.
For WTA models with different application backgrounds, scholars at home and abroad propose different algorithms to improve the calculation efficiency and precision:
in the early stage, the traditional mathematical linear or nonlinear methods are mainly adopted to solve the model, but because the number of weapons and targets is large, the traditional methods easily cause the problem of high computational complexity and cannot meet the requirements of accuracy and real-time performance of application; in recent years, with the development of computer technology, some enlightening intelligent algorithms such as differential evolution, tabu search, neural networks, genetic algorithms, particle swarm optimization and the like attract more and more students' attention, and the enlightening intelligent algorithms show good solving capability under different conditions. However, these algorithms have more initial parameters and large calculation amount.
The artificial immune algorithm is used as an intelligent imitation method of the natural immune system function, and is one of the latest research results of intelligent optimization; the method has the advantages that a good scholars introduces a Clone Selection Algorithm (CSA) into the WTA, so that the complexity and time consumption of calculation can be avoided, but the cross probability and the mutation probability of the clone selection algorithm are quantitative values, the affinity and the concentration of an antibody are not considered, and the adaptability and the robustness of the algorithm are reduced; in order to improve the convergence rate of the algorithm and integrate the advantages of the CSA and the genetic algorithm, an improved CSA algorithm is provided, but the premature phenomenon cannot be overcome.
In order to overcome the above disadvantages, it is desirable to develop a new CSA algorithm to implement high-quality and high-efficiency solution of the WTA problem.
Disclosure of Invention
In order to overcome the defects in the conventional fire distribution scheme, the invention provides a WTA target optimization method of a self-adaptive chaotic parallel clone selection algorithm.
The technical problem to be solved by the invention is realized by the following technical scheme:
a WTA target optimization method of a self-adaptive chaotic parallel clonal selection algorithm comprises the following steps:
step 1: constructing an optimization model of the formation air defense combat WTA, wherein an optimization model f is defined as:
in the formula, pij∈[0,1]Indicating the effectiveness of the weapon, W indicating the number of weapons, i 1,2 … W, T indicating the number of enemy threat objects, j 1,2 … T, λj∈[0,1]Representing the damage probability, x, of an enemy threat objectijIndicating whether the ith weapon was assigned to the jth enemy threat target, if x was assignedij1, otherwise xij=0;
Step 2: defining antibodies, antigens and affinities by comparing an immune response mechanism with a WTA model, wherein the antigens represent an objective function and constraint conditions, and the antibodies represent all potential solutions of fire power distribution, namely all solutions of an optimization model number f; affinity provides a quantitative estimate of antibody, antigen, representing the greatest mathematical expectation of combat effectiveness, and is defined as:
and step 3: initializing relevant parameters including an antibody scale N, a memory population scale M (M < N), and a maximum iteration number K;
and 4, step 4: setting the current iteration number as k, and calculating the antibody X by formula (3)i(k) Fitness to antigen fi(k),i∈N;
And 5: judging a termination condition: if the current iteration number K is equal to K, outputting an optimal result Xopt;
Otherwise, let k be k +1 and pass the fitness fi(k) Calculating memory population Pm(k);
In particular, according to the fitness fi(k) Is ranked to form an antibody population P*(k) And from said antibody population P*(k) M optimal individuals are selected to form a memory populationPm(k);
Step 6: for antibody population P*(k) Performing parallel classification to generate multiple antibody sub-populations including elite sub-population PE(k) Conventional sub-population PG(k) And a rogue sub-population PI(k);
And 7: respectively for elite sub-population PE(k) Conventional sub-population PG(k) Performing clone reproduction calculation to obtain cloned elite populationAnd conventional sub-populations
And 8: respectively aligning the cloned elite populationsAnd conventional sub-populationsPerforming chaotic variation calculation to obtain the varied elite populationAnd conventional sub-populations
And step 9: for variant elite populationAnd conventional sub-populationsPerforming clone selection calculation to obtain an antibody evolution population P of the antibody evolution populationM(k) Specifically, the method comprises the following steps:
respectively aligning the elite sub-populations by the formula (3)And conventional sub-populationsCalculating the fitness of the individual;
if the antibody XiFitness f (X)i) Less than the corresponding new antibody generated after the treatment of step 7 and step 8Is adapted toNamely:
then using the variant antibodyReplacing original antibody Xi(ii) a Otherwise, the original antibody population P is kept*(k) Antibody X of (1)i;
Step 10: calculation of antibody evolution population PM(k) Diversity of DijAnd by diversity DijPerforming antibody inhibition judgment;
step 11: renewing antibody population P (k) ═ Pm(k)+PM(k)+PN(k) I.e. the updated population comprises the memory population Pm(k) Evolved population PM(k) And a new inferior subgroup PN(k);
Step 12: recalculating the fitness f between the antigen and the antibody in the population after the update using equation (3)i(k) And according to the fitness fi(k) The values of (A) are arranged in a descending order, M antibodies with high fitness are selected to update the memory population, and a new memory population P is formedm(k);
Step 13: and returning to the step 5.
Further, in the step 3, an initialization antibody P (0) is calculated by using a Logistic mapping chaotic function;
the method comprises the following specific steps: defining y as a chaotic variable, y0∈ (0,1), and y0Not equal to 0.5, H is the maximum iteration number of chaos, mu is the control parameter of the chaos behavior, and the Logistic mapping is as follows:
wherein H is the current chaos iteration number, H is N,represents the k-th generation of chaotic variables,representing a k +1 th generation chaotic variable; the following steps are generated through the process:
further, the specific content of the parallel classification of the antibody populations in step 6 is as follows:
antibody population P is divided in the ratio E, G, I*(k) Is divided into elite population PE(k) Conventional sub-population PG(k) And a rogue sub-population PI(k) Three groups, wherein E + G + I is 1, PE(k)+PG(k)+PI(k)=P*(k)=P(k)。
Further, in the step 7, the elite population P is treatedE(k) Conventional sub-population PG(k) The calculation method for carrying out clone propagation comprises the following steps:
Hk=Hk.a/Hk.max(7)
γk=round[N×(γ0+ω(1-Hk))](8)
wherein N represents the size of the antibody population, aibDenotes the b variable, a, of the ith antibodyjbDenotes the b variable, H, of the j antibodyijIndicates the affinity between antibody i and antibody j, HaRepresents the average affinity, H, of the antibody populationkDenotes the diversity of the antibody population of the k generation, Hk.maxRepresents the maximum affinity of the antibody population of the k generation; gamma ray0Denotes cloning base number, ω denotes cloning factor, γkRepresents the clone scale and round represents the rounding symbol.
Further, the cloned elite population is subjected to the step 8And conventional sub-populationsThe specific contents of the chaotic variation calculation are as follows:
r=βe(-αT)(10)
in the formula (I), the compound is shown in the specification,new variables generated by the b-th variable of the antibody i are shown, r is a disturbance coefficient, yi is a chaotic variable, and β and α are shown as adjusting variables.
Further, the specific content of step 10 is:
calculation of antibody XiWith antibody XjAnd in said euclidean distanceDiversity of the population DijI.e. by
σ is a threshold for determining whether or not antibody inhibition is performed, and is generally σ ∈ [ 0-1 ];
if D isijIf the sum is more than sigma, updating the inferior sub-population PI (k), and specifically, chaotic regeneration of the inferior sub-population PI (k) through a formula (4) to form a new inferior sub-population P with equal scaleN(k) (ii) a Otherwise, the inferior sub-population P is not performedI(k) And (4) updating.
The invention has the beneficial effects that:
the invention constructs a formation air defense combat WTA optimization model, comprehensively utilizes a chaos theory, a parallel population classification model and a clonal selection algorithm, designs various operators, and also provides a target optimization method of a self-adaptive chaos parallel clonal selection algorithm to improve the global optimization capability and the local search capability.
The present invention will be described in further detail with reference to the accompanying drawings and examples.
Drawings
FIG. 1 is a schematic diagram of a target optimization method of an adaptive chaotic parallel clonal selection algorithm.
FIG. 2 is a diagram illustrating a process of fitness change of an adaptive chaotic parallel clonal selection algorithm.
Detailed Description
To further explain the technical means and effects of the present invention adopted to achieve the intended purpose, the following detailed description of the embodiments, structural features and effects of the present invention will be made with reference to the accompanying drawings and examples.
Example 1:
referring to fig. 1, the embodiment provides a WTA target optimization method of a self-adaptive chaotic parallel clonal selection algorithm, including the following steps:
step 1: constructing an optimization model f of the formation air defense combat WTA, wherein the WTA aims at maximizing the combat effectiveness of weaponry on the target quantity, and the optimization model f is defined as:
in the formula, formula (2) represents a constraint condition; p is a radical ofij∈[0,1]Indicating the effectiveness of the weapon, W indicating the number of weapons, i 1,2 … W, T indicating the number of enemy threat objects, j 1,2 … T, λj∈[0,1]Represents the damage probability of the enemy threat object, [ x ]ij]W×TAs a decision matrix, xijIndicating whether the ith weapon was assigned to the jth enemy threat target, if x was assignedij1, otherwise xij=0;
Step 2: defining antibodies, antigens and affinities by comparing an immune response mechanism with a WTA model, wherein the antigens represent an objective function and constraint conditions, and the antibodies represent all potential solutions of fire power distribution, namely all solutions of an optimization model number f; the affinity provides a quantitative estimate of the antibody, antigen, and represents the maximum mathematical expectation of combat effectivenessThat is, the affinity is defined as:
according to the formula (3), the affinity, namely the optimization model in the step 1, is also equivalent to the fitness hereinafter, namely the affinity, the fitness and the mathematical expression of the optimization model are the same;
and step 3: initializing relevant parameters including an antibody scale N, a memory population scale M (M < N), and a maximum iteration number K; wherein:
in the step 3, calculating an initialized antibody P (0) by adopting a Logistic mapping chaotic function;
P(0)=[XB 1(0),XB 2(0)...XB N(0)]whereinB is a variable dimension;
the method comprises the following specific steps: defining y as a chaotic variable, y0∈ (0,1), and y0Not equal to 0.5, H is the maximum iteration number of chaos, mu is the control parameter of the chaos behavior, and the Logistic mapping is as follows:
wherein H is the current chaos iteration number, H is N,represents the k-th generation of chaotic variables,representing a k +1 th generation chaotic variable; the following steps are generated through the process:
and 4, step 4: setting the current iteration number as k, and calculating the antibody X by formula (3)i(k) Fitness to antigen fi(k),i∈N;
And 5: judging a termination condition: if the current iteration number K is equal to K, outputting an optimal result Xopt;
Otherwise, let k be k +1 and pass the fitness fi(k) Calculating memory population Pm(k);
In particular, according to the fitness fi(k) Is ranked to form an antibody population P*(k) And from said antibody population P*(k) M optimal individuals are selected to form a memory population Pm(k);
Step 6: for antibody population P*(k) Performing parallel classification to generate multiple antibody sub-populations including elite sub-population PE(k) Conventional, conventionalSub-population PG(k) And a rogue sub-population PI(k);
The concrete content of parallel classification of the antibody population in the step 6 is as follows:
antibody population P is divided in the ratio E, G, I*(k) Is divided into elite population PE(k) Conventional sub-population PG(k) And a rogue sub-population PI(k) Three groups, wherein E + G + I is 1, PE(k)+PG(k)+PI(k)=P*(k)=P(k)。
And 7: respectively for elite sub-population PE(k) Conventional sub-population PG(k) Performing clone reproduction calculation to obtain cloned elite populationAnd conventional sub-populationsWherein:
the Elite seed population P in the step 7E(k) Conventional sub-population PG(k) The calculation method for carrying out clone propagation comprises the following steps:
Hk=Hk.a/Hk.max(7)
γk=round[N×(γ0+ω(1-Hk))](8)
wherein N represents the size of the antibody population, aibDenotes the b variable, a, of the ith antibodyjbDenotes the b variable, H, of the j antibodyijIndicates the affinity between antibody i and antibody j, HaRepresents the average affinity, H, of the antibody populationkDenotes the diversity of the antibody population of the k generation, Hk.maxRepresents the maximum affinity of the antibody population of the k generation; gamma ray0Representing clonesThe base number, ω, represents the cloning factor, γkRepresents the clone scale and round represents the rounding symbol.
And 8: respectively aligning the cloned elite populationsAnd conventional sub-populationsPerforming chaotic variation calculation to obtain the varied elite populationAnd conventional sub-populations
The cloned elite population is subjected to the step 8And conventional sub-populationsThe specific contents of the chaotic variation calculation are as follows:
r=βe(-αT)(10)
in the formula (I), the compound is shown in the specification,new variable representing the generation of the b-th variable of antibody i, r represents perturbation coefficient, yiRepresenting chaotic variables and β and α representing adjustment variables.
And step 9: for variant elite populationAnd conventional sub-populationsPerforming clone selection calculation to obtain an antibody evolution population P of the antibody evolution populationM(k) Specifically, the method comprises the following steps:
respectively aligning the elite sub-populations by the formula (3)And conventional sub-populationsCalculating the fitness of the individual;
if the antibody XiFitness f (X)i) Less than the corresponding new antibody generated after the treatment of step 7 and step 8Is adapted toNamely, it is
Then using the variant antibodyReplacing original antibody Xi(ii) a Otherwise, the original antibody population P is kept*(k) Antibody X of (1)i;
Step 10: calculation of antibody evolution population PM(k) Diversity of DijAnd by diversity DijPerforming antibody inhibition judgment;
the specific content of the step 10 is as follows:
calculation of antibody XiWith antibody XjAnd representing the diversity D of the population by said Euclidean distanceijI.e. by
σ is a threshold for determining whether or not antibody inhibition is performed, and is generally σ ∈ [ 0-1 ];
if D isijIf > σ, then proceed with the inferior sub-population PI(k) Update of, in particular, a rogue sub-population PI(k) Forming a new inferior sub-population P with equal scale through chaotic regeneration in a formula (4)N(k) (ii) a Otherwise, the inferior sub-population P is not performedI(k) And (4) updating.
Step 11: renewing antibody population P (k) ═ Pm(k)+PM(k)+PN(k) I.e. the updated population comprises the memory population Pm(k) Evolved population PM(k) And a new inferior subgroup PN(k);
In this example, antibody population P*(k) The antibodies within P (k) are ranked by fitness, i.e. the size of scale P x (k) is equal to the size of P (k).
Step 12: recalculating the fitness f between the antigen and the antibody in the population after the update using equation (3)i(k) And according to the fitness fi(k) The values of (A) are arranged in a descending order, M antibodies with high fitness are selected to update the memory population, and a new memory population P is formedm(k);
Step 13: and returning to the step 5.
Example 2:
to verify the feasibility and effectiveness of the optimization model and method proposed in example 1, a typical simulation model was designed as follows: the formation air defense system consists of 6 weapon systems, which are positively opposite to 10 intrusions of enemy targets, namely W is 6, T is 10, the weapon damage probability pij(i 1,2 … 6, j 1,2 … 10) and a targeted threat system rj(j ═ 1,2 … 10) is shown in tables 1 and 2.
TABLE 1 weapon Unit destruction probability
TABLE 2 target threat coefficients
|
1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 |
Coefficient of threat | 0.09 | 0.12 | 0.14 | 0.06 | 0.05 | 0.10 | 0.08 | 0.09 | 0.15 | 0.12 |
The parameters of the adaptive chaotic parallel clonal selection algorithm are set as follows: the maximum iteration number K is 500, the population size N is 100, the memory population size M is 0.15N, and the cloning cardinality gamma is00.3, the population classification ratio E: G: I: 0.2:0.4:0.2, the cloning factor ω: 0.25, the cloning scale γkAnd setting a chaotic behavior control parameter mu to be 4, setting the maximum iteration number H of the chaos to be 60, and setting an adjusting variable β to be 0.5 and an adjusting variable α to be 0.6.
As can be seen from fig. 2, the WTA target optimization based on the adaptive chaotic parallel clonal selection algorithm finally converges to 0.9821 in the 40 th generation, and meanwhile, the global optimization and the local optimization are considered, so that the stability is high. The optimal output results are shown in Table 3, WTA decision matrix XoptSee equation (13).
TABLE 3 assignment results
Weapon | Enemy target | |
1 | 1,3,4,10 | |
2 | 1,1,2,3,5 | |
3 | 4,6,6,7 | |
4 | 7,8,10 | |
5 | 7,8,10 | |
6 | 7,8,10 |
From equation (13), the weapon distribution scheme can be seen, such as the first column of the matrix indicates that the weapon unit needs to attack targets # 1, 3, 4, 10; meanwhile, as the number of weapon units is smaller than that of enemy targets, the occurrence of one weapon unit can attack a plurality of local targets. Finally, the combat efficiency of the air defense weapon system in this scenario is 0.9821.
The invention provides a target optimization method of a self-adaptive chaotic parallel clone selection algorithm, which solves the problem of anti-air formation Weapon Target Allocation (WTA). The algorithm combines the advantages of the chaos theory and the parallel population classification, and realizes population initialization and population updating. Wherein, a population initialization operator and a mutation operator are designed by utilizing chaotic regeneration and chaotic disturbance; performing parallel mechanism design on each sub-population by adopting a parallel population classification method, and keeping population diversity according to affinity; and (3) designing an adaptive clone multiplication operator, an antibody inhibition operator and an antibody circulation supplement operator to improve the CSA, wherein the operators can improve the global optimization capability and the local search capability. Finally, the self-adaptive chaotic parallel clone selection algorithm is verified through simulation to have better optimization performance in the aspects of search precision and convergence flexibility, and an efficient method is provided for solving the WTA in formation air defense combat.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (6)
1. A WTA target optimization method of a self-adaptive chaotic parallel clonal selection algorithm is characterized by comprising the following steps of:
step 1: constructing an optimization model of the formation air defense combat WTA, wherein an optimization model f is defined as:
in the formula, pij∈[0,1]Indicating the effectiveness of the weapon, W indicating the number of weapons, i 1,2 … W, T indicating the number of enemy threat objects, j 1,2 … T, λj∈[0,1]Representing the damage probability, x, of an enemy threat objectijIndicating whether the ith weapon was assigned to the jth enemy threat target, if x was assignedij1, otherwise xij=0;
Step 2: defining antibodies, antigens and affinities by comparing an immune response mechanism with a WTA model, wherein the antigens represent an objective function and constraint conditions, and the antibodies represent all potential solutions of fire power distribution, namely all solutions of an optimization model number f; affinity provides a quantitative estimate of antibody, antigen, representing the greatest mathematical expectation of combat effectiveness, and is defined as:
and step 3: initializing relevant parameters including an antibody scale N, a memory population scale M (M < N), and a maximum iteration number K;
and 4, step 4: setting the current iteration number as k, and calculating the antibody X by formula (3)i(k) Fitness to antigen fi(k),i∈N;
And 5: judging a termination condition: if the current iteration number K is equal to K, outputting an optimal result Xopt;
Otherwise, let k be k +1 and pass the fitness fi(k) Calculating memory population Pm(k);
In particular, according to the fitness fi(k) Sequencing the values of (A) to form antibody speciesGroup P*(k) And from said antibody population P*(k) M optimal individuals are selected to form a memory population Pm(k);
Step 6: for antibody population P*(k) Performing parallel classification to generate multiple antibody sub-populations including elite sub-population PE(k) Conventional sub-population PG(k) And a rogue sub-population PI(k);
And 7: respectively for elite sub-population PE(k) Conventional sub-population PG(k) Performing clone reproduction calculation to obtain cloned elite populationAnd conventional sub-populations
And 8: respectively aligning the cloned elite populationsAnd conventional sub-populationsPerforming chaotic variation calculation to obtain the varied elite populationAnd conventional sub-populations
And step 9: for variant elite populationAnd conventional sub-populationsPerforming clone selection calculation to obtain antibody of antibody evolution populationEvolved population PM(k) Specifically, the method comprises the following steps:
respectively aligning the elite sub-populations by the formula (3)And conventional sub-populationsCalculating the fitness of the individual;
if the antibody XiFitness f (X)i) Less than the corresponding new antibody generated after the treatment of step 7 and step 8Is adapted toNamely:
then using the variant antibodyReplacing original antibody Xi(ii) a Otherwise, the original antibody population P is kept*(k) Antibody X of (1)i;
Step 10: calculation of antibody evolution population PM(k) Diversity of DijAnd by diversity DijPerforming antibody inhibition judgment;
step 11: renewing antibody population P (k) ═ Pm(k)+PM(k)+PN(k) I.e. the updated population comprises the memory population Pm(k) Evolved population PM(k) And a new inferior subgroup PN(k);
Step 12: recalculating the fitness f between the antigen and the antibody in the population after the update using equation (3)i(k) And according to the fitness fi(k) The values of (A) are sorted in descending order, M adaptations are selectedThe high-degree antibody updates the memory population to form a new memory population Pm(k);
Step 13: and returning to the step 5.
2. The WTA target optimization method according to claim 1, wherein in step 3, an initialization antibody P (0) is calculated using Logistic mapping chaotic function;
the method comprises the following specific steps: defining y as a chaotic variable, y0∈ (0,1), and y0Not equal to 0.5, H is the maximum iteration number of chaos, mu is the control parameter of the chaos behavior, and the Logistic mapping is as follows:
wherein H is the current chaos iteration number, H is N,represents the k-th generation of chaotic variables,representing a k +1 th generation chaotic variable; the following steps are generated through the process:
3. the WTA target optimization method according to claim 2, wherein the antibody population in step 6 is classified in parallel according to the following specific contents:
dividing the antibody population P x (k) into an elite population P according to the ratio E: G: IE(k) Conventional sub-population PG(k) And a rogue sub-population PI(k) Three groups, wherein E + G + I is 1, PE(k)+PG(k)+PI(k)=P*(k)=P(k)。
4. The WTA target optimization method of claim 3, wherein the elite sub-population P is subjected to the step 7E(k) Conventional sub-population PG(k) The calculation method for carrying out clone propagation comprises the following steps:
Hk=Hk.a/Hk.max(7)
γk=round[N×(γ0+ω(1-Hk))](8)
wherein N represents the size of the antibody population, aibDenotes the b variable, a, of the ith antibodyjbDenotes the b variable, H, of the j antibodyijIndicates the affinity between antibody i and antibody j, HaRepresents the average affinity, H, of the antibody populationkDenotes the diversity of the antibody population of the k generation, Hk.maxRepresents the maximum affinity of the antibody population of the k generation; gamma ray0Denotes cloning base number, ω denotes cloning factor, γkRepresents the clone scale and round represents the rounding symbol.
5. The WTA target optimization method of claim 4, wherein the cloned elite sub-population in step 8 is subjected toAnd conventional sub-populationsDevice for calculating chaos variationThe body content is as follows:
r=βe(-αT)(10)
6. The WTA target optimization method according to claim 5, wherein the specific content of step 10 is:
calculation of antibody XiWith antibody XjAnd representing the diversity D of the population by said Euclidean distanceijI.e. by
σ is a threshold for determining whether or not antibody inhibition is performed, and is generally σ ∈ [ 0-1 ];
if D isijIf the sum is more than sigma, updating the inferior sub-population PI (k), and specifically, chaotic regeneration of the inferior sub-population PI (k) through a formula (4) to form a new inferior sub-population P with equal scaleN(k) (ii) a Otherwise, the inferior sub-population P is not performedI(k) And (4) updating.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811645323.0A CN111382896B (en) | 2018-12-29 | 2018-12-29 | WTA target optimization method of self-adaptive chaotic parallel clone selection algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811645323.0A CN111382896B (en) | 2018-12-29 | 2018-12-29 | WTA target optimization method of self-adaptive chaotic parallel clone selection algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111382896A true CN111382896A (en) | 2020-07-07 |
CN111382896B CN111382896B (en) | 2023-10-31 |
Family
ID=71222418
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811645323.0A Active CN111382896B (en) | 2018-12-29 | 2018-12-29 | WTA target optimization method of self-adaptive chaotic parallel clone selection algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111382896B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113919425A (en) * | 2021-10-11 | 2022-01-11 | 中国兵器装备集团自动化研究所有限公司 | Aerial target autonomous allocation method and system |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103116806A (en) * | 2013-03-13 | 2013-05-22 | 兰州理工大学 | Molten aluminum ladle loading optimization method based on chaos clonal operator |
CN103425840A (en) * | 2013-08-14 | 2013-12-04 | 西北工业大学 | Cooperative air combat firepower distribution method based on improved multi-target leapfrog algorithm |
CN103646285A (en) * | 2013-11-25 | 2014-03-19 | 大连海联自动控制有限公司 | Chaos-clonal evolution method |
CN103679270A (en) * | 2013-11-21 | 2014-03-26 | 大连海联自动控制有限公司 | Heuristic adaptive immune clonal method |
US20150094850A1 (en) * | 2013-09-27 | 2015-04-02 | Brain Corporation | Apparatus and methods for training of robotic control arbitration |
CN105122727A (en) * | 2013-01-11 | 2015-12-02 | Db网络公司 | Systems and methods for detecting and mitigating threats to a structured data storage system |
CN105704025A (en) * | 2014-12-12 | 2016-06-22 | 华北电力大学 | Route optimization method based on chaos searching and artificial immune algorithm |
CN106599537A (en) * | 2016-11-17 | 2017-04-26 | 西北工业大学 | Mass weapon target assignment method based on multiple-target clonal evolutionary algorithm |
CN107832885A (en) * | 2017-11-02 | 2018-03-23 | 南京航空航天大学 | A kind of fleet Algorithm of Firepower Allocation based on adaptive-migration strategy BBO algorithms |
-
2018
- 2018-12-29 CN CN201811645323.0A patent/CN111382896B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105122727A (en) * | 2013-01-11 | 2015-12-02 | Db网络公司 | Systems and methods for detecting and mitigating threats to a structured data storage system |
CN103116806A (en) * | 2013-03-13 | 2013-05-22 | 兰州理工大学 | Molten aluminum ladle loading optimization method based on chaos clonal operator |
CN103425840A (en) * | 2013-08-14 | 2013-12-04 | 西北工业大学 | Cooperative air combat firepower distribution method based on improved multi-target leapfrog algorithm |
US20150094850A1 (en) * | 2013-09-27 | 2015-04-02 | Brain Corporation | Apparatus and methods for training of robotic control arbitration |
CN103679270A (en) * | 2013-11-21 | 2014-03-26 | 大连海联自动控制有限公司 | Heuristic adaptive immune clonal method |
CN103646285A (en) * | 2013-11-25 | 2014-03-19 | 大连海联自动控制有限公司 | Chaos-clonal evolution method |
CN105704025A (en) * | 2014-12-12 | 2016-06-22 | 华北电力大学 | Route optimization method based on chaos searching and artificial immune algorithm |
CN106599537A (en) * | 2016-11-17 | 2017-04-26 | 西北工业大学 | Mass weapon target assignment method based on multiple-target clonal evolutionary algorithm |
CN107832885A (en) * | 2017-11-02 | 2018-03-23 | 南京航空航天大学 | A kind of fleet Algorithm of Firepower Allocation based on adaptive-migration strategy BBO algorithms |
Non-Patent Citations (5)
Title |
---|
FANG LIU: "Self-adaptive chaos quantum clonal evolutionary programming", 《IEEE》 * |
余有明;刘玉树;刘昆;陈云飞;: "混沌伪并行遗传算法及其在火力分配优化中的应用", 北京理工大学学报, no. 12 * |
冯超;姚鹏;景小宁;李晓阳;: "基于改进量子免疫克隆多目标优化算法的火力分配问题", 计算机工程与科学, no. 12 * |
梁洪涛: "adaptive chaotic clonalA Narrow Sheet Beam Electron Gun Designed by Approximate Pierce Method for the Millimeter Wave TWT", 《IEEE》 * |
赵敏;李言俊;: "一种基于克隆选择原理的空战目标分配算法", 火力与指挥控制, no. 11 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113919425A (en) * | 2021-10-11 | 2022-01-11 | 中国兵器装备集团自动化研究所有限公司 | Aerial target autonomous allocation method and system |
CN113919425B (en) * | 2021-10-11 | 2023-12-26 | 中国兵器装备集团自动化研究所有限公司 | Autonomous aerial target allocation method and system |
Also Published As
Publication number | Publication date |
---|---|
CN111382896B (en) | 2023-10-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Chang et al. | Solving the dynamic weapon target assignment problem by an improved artificial bee colony algorithm with heuristic factor initialization | |
CN107832885B (en) | Ship formation fire power distribution method based on self-adaptive migration strategy BBO algorithm | |
CN113741508B (en) | Unmanned aerial vehicle task allocation method based on improved wolf pack algorithm | |
CN105005820A (en) | Target assignment optimizing method based on particle swarm algorithm of population explosion | |
CN104950673A (en) | Method for distributing targets cooperatively attacked by unmanned aerial vehicle group | |
CN111709511A (en) | Harris eagle optimization algorithm based on random unscented Sigma point variation | |
CN108416421A (en) | The dynamic Algorithm of Firepower Allocation of bat algorithm is improved based on DDE | |
CN114565239A (en) | Comprehensive low-carbon energy scheduling method and system for industrial park | |
CN113836803A (en) | Improved wolf colony algorithm-based unmanned aerial vehicle cluster resource scheduling method | |
CN106022601B (en) | Multi-target resource allocation method | |
CN114330715A (en) | Intelligent ammunition co-evolution task allocation method | |
Wang et al. | Unmanned ground weapon target assignment based on deep Q-learning network with an improved multi-objective artificial bee colony algorithm | |
CN116681223A (en) | Multi-stage combat resource collaborative allocation method based on enhanced MOEA/D | |
Lu et al. | An improved genetic algorithm for target assignment, optimization of naval fleet air defense | |
CN111382896A (en) | WTA target optimization method of adaptive chaotic parallel clonal selection algorithm | |
CN111797966B (en) | Multi-machine collaborative global target distribution method based on improved flock algorithm | |
CN107169561B (en) | Power consumption-oriented hybrid particle swarm pulse neural network mapping method | |
Martinez-Soto et al. | Fuzzy logic controllers optimization using genetic algorithms and particle swarm optimization | |
CN109325598A (en) | A kind of combination Chaos Genetic Algorithm of resourceoriented distribution | |
CN108764448A (en) | A kind of method that optimization for ant algorism solves first kind assembly line balancing problem | |
CN114493106B (en) | Space crowdsourcing task allocation method based on geographical division | |
CN115730743A (en) | Battlefield combat trend prediction method based on deep neural network | |
Zhou et al. | Multiobjective weapon-target assignment problem by two-stage evolutionary multiobjective particle swarm optimization | |
CN111080035A (en) | Global path planning method based on improved quantum particle swarm optimization algorithm | |
Ruining et al. | Improved genetic algorithm for weapon target assignment problem |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |