CN105005820B - Target assignment optimizing method based on particle swarm algorithm of population explosion - Google Patents
Target assignment optimizing method based on particle swarm algorithm of population explosion Download PDFInfo
- Publication number
- CN105005820B CN105005820B CN201510155893.1A CN201510155893A CN105005820B CN 105005820 B CN105005820 B CN 105005820B CN 201510155893 A CN201510155893 A CN 201510155893A CN 105005820 B CN105005820 B CN 105005820B
- Authority
- CN
- China
- Prior art keywords
- particle
- population
- optimal solution
- iteration
- border
- 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.)
- Active
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a target assignment optimizing method based on a particle swarm algorithm of population explosion, and belongs to the field of intelligent algorithm optimization. In the optimizing method, according to aggregation situation of population in a process of optimization searching, a "population explosion operator" is introduced; divergent treatment of particles is performed under a restricted condition based on partial principles of chaos searching and self-adapting; and parameter adjustment is performed at the same time. The population is prevented against prematurely falling into local optimization, and the problem of target assignment of a battle between intelligent tanks in a virtual battlefield is solved. The method comprises: step 1, performing real number coding of an own side and an opposite side, and generating excellent initial population by utilizing chaos searching; step 2, adjusting initial parameters of the algorithm; step 3, performing iterative optimization searching by adopting the particle swarm algorithm based on the "population explosion operator"; and step 4, ending iteration when the iteration number reaches a set number, and obtaining an optimal scheme. Compared to a method based on an original algorithm, the method increases the total optimization searching ability of particles, and satisfies the requirement of high timeliness.
Description
Technical field
The invention belongs to intelligent algorithm optimize field, more particularly, to a kind of based on population explode particle cluster algorithm target divide
Join optimization method.
Background technology
Target Assignment in virtual battlefield environment is that (Computer Generated Forces, computer generates soldier to CGF
Power) real behavior simulation an importance, Target Assignment is a joint act of many CGF operation entities, it simulate
Accuracy directly affect other operation behaviors of CGF and the verity of CGF simulation.
The Research Significance of " Target Assignment " is not only the credibility that can lift simulated effect in CGF analogue system, gives
People is with good " feeling of immersion ".Meanwhile, the research of " Target Assignment " can also play huge effect in actual operation, can be
Combatant provides quick, efficiently strike scheme.
In virtual battlefield environment, the Target Assignment of CGF is a highly important problem in modern war.However, its solution is empty
Between with weapon sum and target sum increase and exponentially increase so as to become the " NP of a multiparameter, multiple constraint
Complete problem ".So can only be solved with complete enumerative technique that its optimal solution is obtained.Obviously it is unrealistic in the case of larger
It is therefore necessary to be solved by certain intelligent algorithm.For solving this problem, it has been proposed that many algorithms, for example, nerve net
Network method, genetic algorithm, particle cluster algorithm etc..These algorithms respectively have quality, but also mostly have certain limitation, example
Be difficult in as relatively slow in convergence rate, practical operation etc..
Particle cluster algorithm (PSO algorithm) is equal to nineteen ninety-five proposition by Kennedy earliest, and this algorithm is subject to flock of birds foraging behavior
Inspire, and be used for solving optimization problem.Compared with genetic algorithm, PSO algorithm not only has the global optimizing ability of genetic algorithm,
Also there is stronger local optimal searching ability.Because PSO algorithm concept is simple, realize easily, fast convergence rate, be suitable for extensive
The advantages of model, PSO was widely used in multiple fields.But PSO algorithm is often restrained too fast, when solution is empty at the initial stage of search
Between in when there is multiple extreme points (i.e. in the region near this point, the allocative decision representated by this point is best), plant
Group is easily converged in Near The Extreme Point, and the therefore later stage population in optimizing is easily trapped into locally optimal solution, leads to be difficult to obtain
Excellent solution.
Content of the invention
For solving the above problems, the present invention provides a kind of Target Assignment optimization side of the particle cluster algorithm that explodes based on population
Method, it specifically includes following steps：
Step 1, by one's own side and other side all using real coding, other side is designated as 1,2 ... q ... N, one's own side is designated as 1,2 ... k ...
M, then the solution space in searching process is (x1,x2…xi…xM), represent allocative decision, and randomly generate original allocation side
Case, wherein, xiSpan be integer between 1～N, xi=q represents that q-th other side distributes to i-th one's own side, and N is other side
Sum, M is one's own side's sum；
Step 11, randomly generates first primaryParticle position is each
The component value of dimension belongs to interval (0,1)；
Step 12, with first primary X1Based on, according toGenerate
Other primaries X2～XD；Wherein, D is population scale,Represent the i-th dimension component of n-th particle position；
Step 13, by all primary X of generationnBy round (Xn× (N-1)+1) round, obtain original allocation side
Case, wherein n=1,2 ... D；
Step 2, using formulaCalculate initial population X1～XDIn
The fitness value of each particle, and set the fitness value of each particle as the current individual optimal solution pbest of each particle；From
The minimum globally optimal solution gbest as initial population is selected in the individual optimal solution pbest of each particle；
Wherein, tqFor the threat angle value of q-th other side, pkqFor the hit rate to other side q for the one's own side k, ykqValue be 0 or 1, if
Attack other side q for 1 one's own side k, otherwise one's own side k does not attack other side q；
Step 3, carries out optimizing search using iterative process：
Step 31, if current particle population meets three below condition, execution step 32 simultaneously；Otherwise, directly execute
35；
1) iterate to from the m time and between current iteration, keep the sustained iterationses of globally optimal solution gbest (t-m)
More than the first given threshold；
2) set t as current iteration number of times, t is less than the second given threshold；
3) population blast operator is not shielded, and initial population blast operator is defaulted as not shielded；
Step 32, judges the degree of convergence of particle：
Pass through c_boundary=((MaxDT-t)/MaxDT+0.05) × dis_BANG according to current iterationses t to count
Calculate a convergence border c_boundary, and calculate each particle to the Euclidean distance DIS of globally optimal solution gbest, if DIS<Receive
Hold back border c_boundary, then particle converges on globally optimal solution gbest；
After having judged the degree of convergence of all particles, if the particle in convergence border c_boundary reaches holding during set amount
Row step 33, otherwise direct execution step 35；
Wherein,MaxDT is maximum iteration time, and dis_BANG is constant, represents
Big convergence border；
Step 33, execution step 34 after execution population blast operator, execution population blast operator includes：
Step 331, calculates brisance BANG using BANG=((MaxDT-t)/MaxDT+0.02) × (N/3)+1, its
In, MaxDT is maximum iteration time, and t is current iteration number of times；,
Step 332, according toCalculate the blast direction matrix f of i-th particlei, then
Result of calculation is expressed as：Rand represents and takes between 0～1 uniformly
One random number of distribution,Represent i-th particle jth dimension will by " gravitation ",Represent i-th particle
Jth dimension will by " repulsion ", described " repulsion " though particle away from globally optimal solution direction power；" gravitation " is even if particle connects
The power in nearly globally optimal solution direction；
Step 333, uses vi+fi× BANG updates particle rapidity vi, use Xi+viUpdate particle position Xi；
Step 34, uses (w+w_1) × vi+c1×rand×(pbest-Xi)+(c2+c_2)×rand×(gbest-Xi) more
New particle speed vi, then execution step 36, wherein w_1 and c_2 are the adjusting parameter introducing, and terminate in iteration each time
After be updated, w_1 w_1+ (- 0.3/40) real-time update, c_2 c_2+ (1/40) real-time update；
Wherein, w is the weighted value of speed more new formula Central Plains speed, c1、c2It is respectively local optimum in speed more new formula
Solution and the weighted value of globally optimal solution；
Step 35, if be unsatisfactory for condition 3)：
Then according to (w+w_1) × vi+c1×rand×(pbest-Xi)+(c2+c_2)×rand×(gbest-Xi) update grain
Sub- speed vi, then execution step 36；
If meeting condition 3)：
Then according to w × vi+c1×rand×(pbest-Xi)+c2×rand×(gbest-Xi) update particle rapidity vi, so
Execution step 36 afterwards；
Step 36, whether detection particle rapidity crosses the border：Particle rapidity viArbitrarily one-dimensional value outside [- N/4, N/4],
Then cross the border, otherwise do not cross the border；If crossing the border, the velocity amplitude of this dimension takes boundary value, and speed of not crossing the border is constant；Execution step 37；
Step 37, according to Xi+viUpdate particle position Xi, execution step 38；
Step 38, whether detection particle position crosses the border：The arbitrarily one-dimensional value of particle outside for [1, N], is then crossed the border, no
Then, do not cross the border；If crossing the border, the value of this dimension takes boundary value a range of random value nearby, and position of not crossing the border is constant；
Step 39, updates globally optimal solution and individual optimal solution
If the fitness of the particle new position of t iteration generation is less than the adaptation of the individual optimal solution pbest of this particle
Degree, then the individual optimal solution updating this particle is particle new position, otherwise constant；If the individual optimal solution of particle new position is suitable
Response is less than the fitness of globally optimal solution, then replace globally optimal solution with the individual optimal solution of this particle, otherwise constant；Simultaneously
Execution step 40 and step 41；
Step 40, if executing population blast operator during current iteration, will generate shadow population：Shadow population
Initial position is the personal best particle of particle position that t-1 iteration is finished or each particle；If current iteration mistake
It was not carried out population blast operator, then direct execution step 4 in journey；
Carry out crossover operation successively in impact algebraically t+1 to the t+U that population explodes operator, until the t+U time iteration is tied
Bundle, obtains the globally optimal solution of shadow population；
U is population blast shield amount, and that is, t+1 to t+U acquiescence population blast operator is to be shielded, and is subject to population blast to calculate
Son impact, execution step 42；
Step 41, in t+1 to t+U iteration, the direct execution step of virtual population 34,36,37,38 and 39, until t+U
Secondary iteration terminates, and obtains the globally optimal solution of virtual population, execution step 42；
Step 42, shadow population is merged with virtual population：If the fitness of the globally optimal solution of shadow population is less than real
The fitness value of the globally optimal solution of border population, the globally optimal solution of shadow population is assigned to the global optimum of virtual population
Solution, an optional particle, the globally optimal solution of shadow population is assigned to the individual optimal solution of this particle, then executes step simultaneously
Rapid 4；
Step 4, judges whether the maximum iteration time of population reaches set point number, if reaching, iteration terminates, and repeatedly
For the final globally optimal solution obtaining virtual population after terminating, and this final globally optimal solution is converted to allocative decision；Otherwise
Return execution step 3.
Beneficial effect：
Compared to former algorithm, after optimization, algorithm passes through to introduce population blast operator, prevents population to be absorbed in locally optimal solution, because
This strengthens the global optimizing ability of algorithm；By introducing shadow population, strengthen the optimizing energy near current global extremum
Power.Therefore, by this optimized algorithm, the probability finding optimal solution can be greatly increased.Due to enhancing global optimizing ability, obtain
The probability of inferior solution (the substantially poor solution of fitness) is greatly reduced.
Realize simple, the time cost (time increasing on former algorithm time basis) optimizing operation is relatively low.We
Several parameters are only introduced, amount of calculation is few, the time complexity of execution population blast operator is held with basic particle group algorithm in method
The time complexity of row generation optimizing operation is identical；Every generation of shadow population updates the also time with execution generation optimizing operation
Complexity is identical.Due to the restriction effect of operator that population is exploded, will not frequently execute population blast operator, can meet high real
The requirement of when property.
Brief description
Fig. 1 a is 6 × 5 scale result figures of the present invention；
Fig. 1 b is 10 × 10 scale result figures of the present invention；
Fig. 1 c is 15 × 20 scale result figures of the present invention.
Specific embodiment
The Target Assignment optimization method of the particle cluster algorithm that exploded based on population of the present invention, it includes：
Step 1, by one's own side and other side all using real coding, other side is designated as 1,2 ... q ... N, one's own side is designated as 1,2 ... k ...
M, then the solution space in searching process is (x1,x2…xi…xM), represent allocative decision, and randomly generate original allocation side
Case, wherein, xiSpan be integer between 1～N, xi=q represents that q-th other side distributes to i-th one's own side, and N is other side
Sum, M is one's own side's sum；
Step 11, randomly generates first primaryParticle position is each
The component value of dimension belongs to interval (0,1)；
Step 12, with first primary X1Based on, according toGenerate it
He is primary X2～XD；Wherein, D is population scale,Represent the i-th dimension component of n-th particle position；
Step 13, by all primary X of generationnBy round (Xn× (N-1)+1) round, obtain original allocation side
Case, wherein n=1,2 ... D；
Step 2, using formulaCalculate initial population X1～XD
In each particle fitness value, and set the fitness value of each particle as the current individual optimal solution pbest of each particle；
The minimum globally optimal solution gbest as initial population is selected from the individual optimal solution pbest of each particle；
Wherein, tqFor the threat angle value of q-th other side, pkqFor the hit rate to other side q for the one's own side k, ykqValue be 0 or 1, if
Attack other side q for 1 one's own side k, otherwise one's own side k does not attack other side q；
Step 3, carries out optimizing search using iterative process：
Step 31, if current particle population meets three below condition, execution step 32 simultaneously；Otherwise, directly execute
35；
1) iterate to from the m time and between current iteration, keep the sustained iterationses of globally optimal solution gbest (t-m)
More than the first given threshold；
2) set t as current iteration number of times, t is less than the second given threshold；
3) population blast operator is not shielded, and initial population blast operator is defaulted as not shielded；
Step 32, judges the degree of convergence of particle：
Pass through c_boundary=((MaxDT-t)/MaxDT+0.05) × dis_BANG according to current iterationses t to count
Calculate a convergence border c_boundary, and calculate each particle to the Euclidean distance DIS of globally optimal solution gbest, if DIS<Receive
Hold back border c_boundary, then particle converges on globally optimal solution gbest；
After having judged the degree of convergence of all particles, if the particle in convergence border c_boundary reaches holding during set amount
Row step 33, otherwise direct execution step 35；
Wherein,MaxDT is maximum iteration time, and dis_BANG is constant, represents
Maximum convergence border；
Step 33, execution step 34 after execution population blast operator, execution population blast operator includes：
Step 331, calculates brisance BANG using BANG=((MaxDT-t)/MaxDT+0.02) × (N/3)+1, its
In, MaxDT is maximum iteration time, and t is current iteration number of times；,
Step 332, according toCalculate the blast direction matrix f of i-th particlei, then
Result of calculation is expressed as：Rand represents and takes between 0～1 uniformly
One random number of distribution,Represent i-th particle jth dimension will by " gravitation ",Represent i-th particle
Jth dimension will by " repulsion ", described " repulsion " though particle away from globally optimal solution direction power；" gravitation " is even if particle connects
The power in nearly globally optimal solution direction；
Step 333, uses vi+fi× BANG updates particle rapidity vi, use Xi+viUpdate particle position Xi；
Step 34, uses (w+w_1) × vi+c1×rand×(pbest-Xi)+(c2+c_2)×rand×(gbest-Xi) more
New particle speed vi, then execution step 36, wherein w_1 and c_2 are the adjusting parameter introducing, and terminate in iteration each time
After be updated, w_1 w_1+ (- 0.3/40) real-time update, c_2 c_2+ (1/40) real-time update；
Wherein, w is the weighted value of speed more new formula Central Plains speed, c1、c2It is respectively local optimum in speed more new formula
Solution and the weighted value of globally optimal solution；
Step 35, if be unsatisfactory for condition 3)：
Then according to (w+w_1) × vi+c1×rand×(pbest-Xi)+(c2+c_2)×rand×(gbest-Xi) update grain
Sub- speed vi, then execution step 36；
If meeting condition 3)：
Then according to w × vi+c1×rand×(pbest-Xi)+c2×rand×(gbest-Xi) update particle rapidity vi, so
Execution step 36 afterwards；
Step 36, whether detection particle rapidity crosses the border：Particle rapidity viArbitrarily one-dimensional value outside [- N/4, N/4],
Then cross the border, otherwise do not cross the border；If crossing the border, the velocity amplitude of this dimension takes boundary value, and speed of not crossing the border is constant；Execution step 37；
Step 37, according to Xi+viUpdate particle position Xi, execution step 38；
Step 38, whether detection particle position crosses the border：The arbitrarily one-dimensional value of particle outside for [1, N], is then crossed the border, no
Then, do not cross the border；If crossing the border, the value of this dimension takes boundary value a range of random value nearby, and position of not crossing the border is constant；
Step 39, updates globally optimal solution and individual optimal solution
If the fitness of the particle new position of t iteration generation is less than the adaptation of the individual optimal solution pbest of this particle
Degree, then the individual optimal solution updating this particle is particle new position, otherwise constant；If the individual optimal solution of particle new position is suitable
Response is less than the fitness of globally optimal solution, then replace globally optimal solution with the individual optimal solution of this particle, otherwise constant；Simultaneously
Execution step 40 and step 41；
Step 40, if executing population blast operator during current iteration, will generate shadow population：Shadow population
Initial position is the personal best particle of particle position that t-1 iteration is finished or each particle；If current iteration mistake
It was not carried out population blast operator, then direct execution step 4 in journey；
Carry out crossover operation successively in impact algebraically t+1 to the t+U that population explodes operator, until the t+U time iteration is tied
Bundle, obtains the globally optimal solution of shadow population；
U is population blast shield amount, and that is, t+1 to t+U acquiescence population blast operator is to be shielded, and is subject to population blast to calculate
Son impact, execution step 42；
Step 41, in t+1 to t+U iteration, the direct execution step of virtual population 34,36,37,38 and 39, until t+U
Secondary iteration terminates, and obtains the globally optimal solution of virtual population, execution step 42；
Step 42, shadow population is merged with virtual population：If the fitness of the globally optimal solution of shadow population is less than real
The fitness value of the globally optimal solution of border population, the globally optimal solution of shadow population is assigned to the global optimum of virtual population
Solution, an optional particle, the globally optimal solution of shadow population is assigned to the individual optimal solution of this particle, then executes step simultaneously
Rapid 4；
Step 4, judges whether the maximum iteration time of population reaches set point number, if reaching, iteration terminates, and repeatedly
For the final globally optimal solution obtaining virtual population after terminating, and this final globally optimal solution is converted to allocative decision；Otherwise
Return execution step 3.
For further illustrating above-mentioned algorithm, improvement particle cluster algorithm (M-PSO) and standard particle group that the present invention is used
Algorithm (PSO) is emulated on target assignment problem.Consideration 6 × 5 respectively, 10 × 10 and 15 × 20 3 kinds of scales, i.e. 6 friends
5 enemies in side, 10 friend side 10 enemies, three kinds of scales of 15 friend side 20 enemies.
C in 6 × 5 scales1=c2=2, w=0.7289, population scale is 50, and evolutionary generation is 1000；On 10 × 10 rule
C in mould1=c2=2, w=0.7289, population scale is 50, and evolutionary generation is 1000；C in 15 × 20 scales1=c2=2, w
=0.7289, population scale is 50, and evolutionary generation is 1000.Carry out 30 experiments respectively, randomly select two kinds of calculations of certain experiment
, as shown in Fig. 1 a to Fig. 1 c, in 30 experiments, average effect result is as follows for the Contrast on effect of method：
Can be seen that from this result has preferable lifting algorithm relative standard particle cluster algorithm performance after improvement, especially
It is when scale is less, the performance boost of this optimized algorithm is notable.According to force search result, under 6 × 5 scales, 0.29295 is
Optimal value；Under 10 × 10 scales, 0.76350 is optimal value.Although being difficult to find optimal value again when larger, but
Optimized algorithm remains to the larger optimizing ability lifting former algorithm.This optimized algorithm can make optimal time increase on a small quantity, but is consumed
Time still meets scene requirement.Therefore, this algorithm can obtain more preferable effect compared to original algorithm, has well
Practical value.
Certainly, the present invention also can have other various embodiments, in the case of without departing substantially from present invention spirit and its essence, ripe
Know those skilled in the art and work as and various corresponding changes and deformation can be made according to the present invention, but these corresponding changes and change
Shape all should belong to the protection domain of appended claims of the invention.
Claims (1)
1. a kind of Target Assignment optimization method based on population blast particle cluster algorithm is it is characterised in that include：
Step 1, by one's own side and other side all using real coding, other side is designated as 1,2 ... q ... N, one's own side is designated as 1,2 ... k ... M, then
Solution space in searching process is (x1, x2…xi…xM), represent allocative decision, and randomly generate original allocation scheme, its
In, xiSpan be integer between 1～N, xi=q represents that q-th other side distributes to i-th one's own side, and N is other side's sum,
M is one's own side's sum；
Step 11, randomly generates first primaryThe each dimension of particle position
Component value belongs to interval (0,1)；
Step 12, with first primary X1Based on, according toGenerate at the beginning of other
Beginning particle X2～XD；Wherein, D is population scale,Represent the i-th dimension component of n-th particle position；
Step 13, by all primary X of generationnBy round (Xn× (N-1)+1) round, obtain original allocation scheme,
Wherein n=1,2 ... D；
Step 2, using formulaCalculate initial population X1～XDIn each
The fitness value of particle, and set the fitness value of each particle as the current individual optimal solution pbest of each particle；From each
The minimum globally optimal solution gbest as initial population is selected in the individual optimal solution pbest of particle；
Wherein, tqFor the threat angle value of q-th other side, pkqFor the hit rate to other side q for the one's own side k, ykqValue be 0 or 1, if 1
Then one's own side k attacks other side q, and otherwise one's own side k does not attack other side q；
Step 3, carries out optimizing search using iterative process：
Step 31, if current particle population meets three below condition, execution step 32 simultaneously；Otherwise, 35 are directly executed；
1) iterating to from the m time keeps the sustained iterationses of globally optimal solution gbest (t-m) to be more than between current iteration
First given threshold；
2) set t as current iteration number of times, t is less than the second given threshold；
3) population blast operator is not shielded, and initial population blast operator is defaulted as not shielded；
Step 32, judges the degree of convergence of all particles：
Calculate one according to current iterationses t by c_boundary=((MaxDT-t)/MaxDT+0.05) × dis_BANG
Individual convergence border c_boundary, and calculate each particle to the Euclidean distance DIS of globally optimal solution gbest, if DIS ＜ convergence side
Boundary c_boundary, then particle converge on globally optimal solution gbest；
After having judged the degree of convergence of all particles, if the particle in convergence border c_boundary reaches executes step during set amount
Rapid 33, otherwise direct execution step 35；
Wherein,MaxDT is maximum iteration time, and dis_BANG is constant, represents maximum receipts
Hold back border；
Step 33, execution step 34 after execution population blast operator, execution population blast operator includes：
Step 331, calculates brisance BANG using BANG=((MaxDT-t)/MaxDT+0.02) × (N/3)+1, wherein,
MaxDT is maximum iteration time, and t is current iteration number of times；,
Step 332, according toCalculate the blast direction matrix f of i-th particlei, then calculate
Result is expressed as：Rand represents to take and is uniformly distributed between 0～1
A random number,Represent i-th particle jth dimension will by " gravitation ",Represent the of i-th particle
J dimension will by " repulsion ", described " repulsion " though particle away from globally optimal solution direction power；" gravitation " is even if particle is close to complete
The power in office optimal solution direction；
Step 333, uses vi+fi× BANG updates particle rapidity vi, use Xi+viUpdate particle position Xi；
Step 34, uses (w+w_1) × vi+c1×rand×(pbest-Xi)+(c2+c_2)×rand×(gbest-Xi) update grain
Sub- speed vi, then execution step 36, wherein w_1 and c_2 are the adjusting parameter introducing, and terminate laggard in iteration each time
Row updates, w_1 w_1+ (- 0.3/40) real-time update, c_2 c_2+ (1/40) real-time update；
Wherein, w is the weighted value of speed more new formula Central Plains speed, c1、c2Be respectively speed more new formula in locally optimal solution and
The weighted value of globally optimal solution；
Step 35, if be unsatisfactory for condition 3)：
Then according to (w+w_1) × vi+ci×rand×(pbest-Xi)+(c2+c_2)×rand×(gbest-Xi) more new particle speed
Degree vi, then execution step 36；
If meeting condition 3)：
Then according to w × vi+c1×rand×(pbest-Xi)+c2×rand×(gbest-Xi) update particle rapidity vi, then hold
Row step 36；
Step 36, whether detection particle rapidity crosses the border：Particle rapidity viArbitrarily one-dimensional value outside [- N/4, N/4], is then got over
Boundary, does not otherwise cross the border；If crossing the border, the velocity amplitude of this dimension takes boundary value, and speed of not crossing the border is constant；Execution step 37；
Step 37, according to Xi+viUpdate particle position Xi, execution step 38；
Step 38, whether detection particle position crosses the border：The arbitrarily one-dimensional value of particle outside for [1, N], is then crossed the border, otherwise,
Do not cross the border；If crossing the border, the value of this dimension takes boundary value a range of random value nearby, and position of not crossing the border is constant；
Step 39, updates globally optimal solution and individual optimal solution
If the fitness of the particle new position of t iteration generation is less than the fitness of the individual optimal solution pbest of this particle,
The individual optimal solution then updating this particle is particle new position, otherwise constant；If the adaptation of the individual optimal solution of particle new position
Degree less than the fitness of globally optimal solution, then replaces globally optimal solution with the individual optimal solution of this particle, otherwise constant；Hold simultaneously
Row step 40 and step 41；
Step 40, if executing population blast operator during current iteration, will generate shadow population：Shadow population initial
Position is the personal best particle of particle position that t-1 iteration is finished or each particle；If during current iteration
It was not carried out population blast operator, then direct execution step 4；
Carry out crossover operation successively in impact algebraically t+1 to the t+U that population explodes operator, until the t+U time iteration terminates, obtain
Obtain the globally optimal solution of shadow population；
U is population blast shield amount, and that is, t+1 to t+U acquiescence population blast operator is to be shielded, and is subject to population blast operator shadow
Ring, execution step 42；
Step 41, in t+1 to t+U iteration, the direct execution step of virtual population 34,36,37,38 and 39, until the t+U time changes
In generation, terminates, and obtains the globally optimal solution of virtual population, execution step 42；
Step 42, shadow population is merged with virtual population：If the fitness of the globally optimal solution of shadow population is less than actual kind
The fitness value of the globally optimal solution of group, the globally optimal solution of shadow population is assigned to the globally optimal solution of virtual population, with
Mono- particle of Shi Renxuan, the globally optimal solution of shadow population is assigned to the individual optimal solution of this particle, then execution step 4；
Step 4, judges whether the maximum iteration time of population reaches set point number, if reaching, iteration terminates, and iteration knot
Obtain the final globally optimal solution of virtual population after bundle, and this final globally optimal solution is converted to allocative decision；Otherwise return
Execution step 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510155893.1A CN105005820B (en) | 2015-04-03 | 2015-04-03 | Target assignment optimizing method based on particle swarm algorithm of population explosion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510155893.1A CN105005820B (en) | 2015-04-03 | 2015-04-03 | Target assignment optimizing method based on particle swarm algorithm of population explosion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105005820A CN105005820A (en) | 2015-10-28 |
| CN105005820B true CN105005820B (en) | 2017-02-22 |
Family
ID=54378483
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510155893.1A Active CN105005820B (en) | 2015-04-03 | 2015-04-03 | Target assignment optimizing method based on particle swarm algorithm of population explosion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105005820B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105470947B (en) * | 2015-11-23 | 2017-12-22 | 杭州电子科技大学 | A kind of micro-capacitance sensor dispatching method based on quantum-behaved particle swarm optimization |
| CN107273581B (en) * | 2017-05-23 | 2020-03-06 | 浙江大学 | Self-adaptive electric field automatic analysis system |
| CN109739959B (en) * | 2018-11-30 | 2021-02-26 | 东软集团股份有限公司 | Method and device used in topic association calculation |
| CN109872009A (en) * | 2019-03-14 | 2019-06-11 | 西安电子科技大学 | A kind of interference increment method method for improving particle swarm algorithm |
| CN111709525B (en) * | 2019-07-18 | 2023-06-02 | 中国人民解放军火箭军工程大学 | Weapon-target distribution solving method based on improved genetic algorithm |
| CN111709547B (en) * | 2019-08-02 | 2024-04-23 | 中国人民解放军火箭军工程大学 | Weapon-target distribution solving method based on multi-target particle swarm algorithm |
| CN112307622B (en) * | 2020-10-30 | 2024-05-17 | 中国兵器科学研究院 | Autonomous planning system and planning method for generating force by computer |
| CN112907057B (en) * | 2021-02-06 | 2022-11-11 | 北京理工大学 | Production scheduling optimization method and system based on improved MOPSO algorithm |
| CN113435722B (en) * | 2021-06-17 | 2024-01-23 | 上海海事大学 | Multi-device mixed scheduling method for U-shaped automatic wharf and electronic device |
| CN114040336B (en) * | 2021-11-05 | 2023-11-17 | 北京理工大学 | Beacon deployment method based on reduction judgment positioning method and particle swarm optimization algorithm |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101908097B (en) * | 2010-07-13 | 2012-03-21 | 北京航空航天大学 | Particle swarm optimization method for air combat decision |
| CN104200264B (en) * | 2014-09-25 | 2017-10-31 | 国家电网公司 | A kind of two benches particle swarm optimization algorithm including independent global search |
-
2015
- 2015-04-03 CN CN201510155893.1A patent/CN105005820B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN105005820A (en) | 2015-10-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105005820B (en) | Target assignment optimizing method based on particle swarm algorithm of population explosion | |
| Xin et al. | An efficient rule-based constructive heuristic to solve dynamic weapon-target assignment problem | |
| CN112507622B (en) | Anti-unmanned aerial vehicle task allocation method based on reinforcement learning | |
| 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 | |
| CN114594794B (en) | Multi-machine collaborative task planning method considering subsystem execution capacity | |
| CN110515845B (en) | Combined test case optimization generation method based on improved IPO strategy | |
| CN110991683B (en) | Method for optimizing and solving weapon-target distribution based on particle swarm optimization | |
| CN116702633B (en) | Heterogeneous warhead task reliability planning method based on multi-objective dynamic optimization | |
| CN111797966B (en) | Multi-machine collaborative global target distribution method based on improved flock algorithm | |
| Cheng et al. | Weapon-target assignment of ballistic missiles based on Q-learning and genetic algorithm | |
| Sun et al. | A novel and more efficient search strategy of quantum-behaved particle swarm optimization | |
| CN116090356B (en) | Heterogeneous warhead multi-objective task planning method based on task reliability constraint | |
| CN115328189B (en) | Multi-unmanned plane cooperative game decision-making method and system | |
| Wu et al. | Dynamic multitarget assignment based on deep reinforcement learning | |
| Zhou et al. | Multiobjective weapon-target assignment problem by two-stage evolutionary multiobjective particle swarm optimization | |
| CN110782062A (en) | Many-to-many packet interception target distribution method and system for air defense system | |
| CN111382896B (en) | WTA target optimization method of self-adaptive chaotic parallel clone selection algorithm | |
| Zhao et al. | Binary particle swarm optimization with multiple evolutionary strategies | |
| Ruining et al. | Improved genetic algorithm for weapon target assignment problem | |
| CN116596287B (en) | Task driving decision-making method and system | |
| Xu et al. | Multi-objective optimization based on chaotic particle swarm optimization | |
| CN117556718B (en) | Thermal power distribution method based on neural network and multi-strategy combined gray wolf optimization algorithm | |
| Chen et al. | Research on multiple kill vehicles firepower distribution strategy based on adjust genetic algorithm | |
| Wang et al. | An improved artificial immune algorithm for solving weapon-target assignment problem |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |