CN101551642A - Improved particle swarm algorithm for automatic optimization of control law parameters of unmanned aircraft - Google Patents
Improved particle swarm algorithm for automatic optimization of control law parameters of unmanned aircraft Download PDFInfo
- Publication number
- CN101551642A CN101551642A CNA2009100293105A CN200910029310A CN101551642A CN 101551642 A CN101551642 A CN 101551642A CN A2009100293105 A CNA2009100293105 A CN A2009100293105A CN 200910029310 A CN200910029310 A CN 200910029310A CN 101551642 A CN101551642 A CN 101551642A
- Authority
- CN
- China
- Prior art keywords
- particle
- algorithm
- particle swarm
- swarm algorithm
- max
- 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.)
- Pending
Links
- 239000002245 particle Substances 0.000 title claims abstract description 66
- 238000005457 optimization Methods 0.000 title claims abstract description 15
- 238000009396 hybridization Methods 0.000 claims description 13
- 238000000034 method Methods 0.000 claims description 9
- 230000006872 improvement Effects 0.000 claims description 7
- 238000013461 design Methods 0.000 abstract description 4
- 238000005096 rolling process Methods 0.000 abstract 2
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007429 general method Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001915 proofreading effect Effects 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to an improved particle swarm algorithm for automatic optimization of control law parameters of an unmanned aircraft. The particle swarm algorithm is based on an iterative optimized algorithm; control parameters are initialized to be a group of random solutions; and optimal values are found by iteration; the improved particle swarm algorithm is characterized by comprising the following steps of: in the particle swarm algorithm, introducing a crossover operator, selecting a plurality of particles in which the optimal position value of single particle is positioned in the middle to carry out random two-two crossover; generating offspring particles with the same number; replacing parent particles with offspring particles; selecting crossover time according to convergent algebra of the standard particle swarm algorithm, namely, 17 to 20 generations for pitching and yawing channel and 7 to 10 generations for rolling channel; and selecting algebra of disturbing start as follows: starting from twelfth generation for the pitching and yawing channel and starting from fourth generation for the rolling channel. The improved particle swarm algorithm expands the range of understanding the space, has total searching capacity; the obtained parameters can meet given performance indexes; and the algorithm can save design time and has application value of engineering.
Description
Technical field:
The present invention relates to a kind of improvement population (PSO) algorithm that is used for unmanned aerial vehicle control law parameter automatic optimization, belong to the unmanned aerial vehicle flight control technology.
Background technology:
The general method for designing of unmanned aerial vehicle control law is to get the exemplary operation point of some in whole flight envelope, on each working point, carry out linearization of microvariations then, at the linearization mathematical model, can use method for designing in time domain or the frequency domain to obtain to satisfy the controlled variable of performance requirement, adopt the method for gain-adjusted to obtain full envelope curve Flight Control Law at last.Therefore when having determined after the control structure of unmanned aerial vehicle that the controlled variable that design has superperformance just becomes a main task.
The performance index of unmanned aerial vehicle control system have: time domain index (rise time t
r, time to peak t
p, stable state time t
s, overshoot σ
p, steady-state error e
SsDeng), frequency-domain index (magnitude margin G
m, phase margin P
m, cutoff frequency ω
c, bandwidth etc.), when above-mentioned performance index can not all satisfy, also need to trade off, to satisfy most important several index, therefore no matter adopting time domain still is classical design methods in the frequency domain, hand-designed control law parameter all is careful a, time-consuming job, and is subjected to the influence of subjective factors such as deviser's experience.For Unmanned combat aircraft of new generation, because the characteristics of fighting in its big angle of attack, big overload, big spatial domain, aerodynamic parameter changes violent, full envelope curve linearization working point may be up to hundreds of (more when carrying out the working point checking), controlled variable manually be designed to one very numerous and diverse, even not acceptable sometimes task.In the case, adopt optimized Algorithm to carry out controlled variable and be designed to the effective way that addresses this problem automatically, wherein population (PSO-Particle Swarm Optimization) algorithm is owing to the excellent performance in pid control parameter optimization comes into one's own day by day, (GA) compares with conventional genetic algorithm, particle swarm optimization algorithm is simple in structure, travelling speed is fast, be particularly suitable for the controlled variable application of design automatically, yet the standard particle colony optimization algorithm is absorbed in local optimum easily when unmanned aerial vehicle hyperchannel control law parameter optimization, success ratio is not high.
Summary of the invention:
The present invention proposes improving one's methods of a kind of PSO algorithm, be used for unmanned aerial vehicle control law parameter automatic optimization.
Technical scheme of the present invention, a kind of improvement particle cluster algorithm that is used for unmanned aerial vehicle control law parameter automatic optimization, described particle cluster algorithm, it is the PSO algorithm, be a kind of optimized Algorithm based on iteration, controlled variable is initialized as one group of RANDOM SOLUTION, seeks optimal value by iteration, the algorithm mathematics model is: being located in the n dimension search volume has m particle, particle x
i(i=1,2 ..., locus m) is p
i=(x
I1, x
I2..., x
In), m, n are natural number, with particle x
iBring objective function into and calculate fitness, weigh x according to the size of fitness
iQuality, the optimal location that single particle lived through is designated as p
Id, the optimal location note that whole population lives through is made p
Xd, particle upgrades the speed v of oneself according to following formula
IdWith position x
Id:
v
id(t+1)=w×v
id(t)+c
1×rand()×(p
id(t)-x
id(t)+c
2×rand()×(p
nd(t)-x
id(t))
x
id(t+1)=x
id(t)+v
id(t+1)
T is the current time in the formula, and w is a weighting coefficient, c
1With c
2Be the study factor, x
Id(t) be t particle position constantly;
It is characterized in that particle number m is taken as 10~30, weighting coefficient utilizes the adjustment of following formula self-adaptation:
w=w
max-(w
max-w
min)×g/g
max
W in the formula
MaxBe the weighting coefficient maximal value, get 0.7~0.9, w
MinBe the weighting coefficient minimum value, get 0.1~0.3, g gets 1~50, g for convergence algebraically
MaxFor maximum convergence algebraically, get 50, study factor c
1With c
2For non-negative constant, all be taken as 2;
Introduce a hybridization operator, its method is to select the optimal location p that single particle lived through
IdSeveral particles of mediating of value carry out at random hybridization in twos, produce the filial generation particle of similar number, replace the parent particle with the filial generation grain, establish x
iAnd x
jBe 2 parent particles, the computing formula of then carrying out crossover operation is
x
i(t+1)=s·x
i(t)+(1-s)·x
j(t)
x
j(t+1)=s·x
j(t)+(1-s)·x
i(t)
S is the random number between [0,1] in the formula;
The choose opportunities of hybridization, establishing criteria PSO convergence of algorithm algebraically, i.e. in pitching and 17~20 generations of jaw channel,, in 7~10 generations of roll channel, the algebraically that disturbance begins is elected as: pitching and jaw channel are since the 12nd generation, and roll channel is since the 4th generation.
Description of drawings:
Fig. 1 is an algorithm flow chart of the present invention
Specific embodiments
The PSO algorithm is a kind of optimized Algorithm based on iteration, and system initialization is one group of RANDOM SOLUTION, seeks optimal value by iteration, and algorithm mathematics is described below:
Be located in the n dimension search volume and m particle arranged, particle x
i(i=1,2 ..., locus m) is p
i=(x
I1, x
I2..., x
In), with x
iBring objective function into and just can calculate its fitness, weigh x according to the size of fitness
iQuality.The optimal location that single particle lived through is designated as p
Id, the optimal location note that whole population lives through is made p
Xd, particle upgrades speed and the position of oneself according to following formula:
v
id(t+1)=w×v
id(t)+c
1×rand()×(P
id(t)-x
id(t)+c
2×rand()×(p
nd(t)-x
id(t))
x
id(t+1)=x
id(t)+v
id(t+1)
The PSO algorithm application in finding the solution the unmanned aerial vehicle (UAV) control parameter, is needed to consider the parameter setting of algorithm, comprising: population size m, maximum update speed v
Max, weighting coefficient w, study factor c
1And c
2, maximum algebraically g
Max
(1) population size
Foundation is the experience of emulation repeatedly, and population size m is taken as 20 can obtain enough good result, and maximal rate generally is set at the scope width of particle, and it is fixed to get according to the scope of hand-designed controlled variable here.
(2) weighting coefficient
Weighting coefficient w makes particle keep motional inertia.Utilize the following formula self-adaptation to adjust the value of w:
w=w
max-(w
max-w
min)×g/g
max
W wherein
MaxBe taken as 0.9, w
MinBe taken as 0.2, when finding the solution the unmanned aerial vehicle (UAV) control parameter, convergence algebraically is usually between 7~50, so g
MaxCan be taken as 50.
(3) the study factor
Study factor c
1And c
2Be non-negative constant, value is 2 usually.
Result of study shows, to the single channel model, standard P SO optimized Algorithm shows good performance, once be optimized to power>99%, yet for the manual multi-channel model of proofreading to difficulty of transferring, the performance of canonical algorithm is unsatisfactory, and one-time success rate has only about 45%, its reason is exactly so-called " convergence precocious ", and algorithm is too early as a rule has been absorbed in local optimum.From the unmanned plane self character, reason is that multi-channel model has comprised interchannel coupling, reach control stabilization and have the good response characteristic, and very harsh to the requirement of controlled variable, the parameter that satisfies the performance index requirement is confined in the very little scope.
Because standard P SO optimized Algorithm is easy to be absorbed in local optimum to the Control Parameter Optimization of unmanned aerial vehicle multi-channel model, therefore must enlarge the hunting zone of particle, just in the algorithm operational process, need particle is carried out the diversity of certain disturbance with the expansion particle, consider that simultaneously canonical algorithm is in speed of convergence in early stage advantage faster, this disturbance needn't be carried out at the very start, in order to avoid convergence of algorithm speed is brought considerable influence.The convergence algebraically of establishing criteria PSO, it is pitching and 17 ~ 20 generations of jaw channel, 7 ~ 10 generations of roll channel, the algebraically that disturbance begins can be elected as: pitching and jaw channel are since the 12nd generation, roll channel is since the 4th generation, a large amount of tests show that such selection is to guarantee algorithm convergence and better trading off between the execution time.
Adopted " hybridization " method in the evolution this applicant, promptly passed through in algorithm, to introduce a hybridization operator, made population obtain the diversity that new " gene " keeps population, thereby the scope of expansion solution space is absorbed in the possibility of local optimum with minimizing.Here we always select p
IdSeveral particles of mediating of value carry out at random hybridization in twos, the reason that this bar is done is: if high p
IdParticle be about to gather local optimum, then hybridization will weaken the trend that the medium particle in position also enters this state, on the contrary if high p
IdThe trend of particle is global optimum's point, and doing so can not influence it yet and finally reach global optimum, and its cost is that convergence time may prolong.
The result of hybridization computing is the filial generation particle that has produced similar number, replaces the parent particle with the filial generation particle, can keep the quantity of whole population constant.If x
iAnd x
jBe 2 parent particles, then as follows to its computing formula of carrying out crossover operation:
x
i(t+1)=s·x
i(t)+(1-s)·x
j(t)
x
j(t+1)=s·x
j(t)+(1-s)·x
i(t)
Wherein s is the random number between [0,1], and s is taken as 0.2 here.
After hybridization, having produced new particle at random in the individual hypercube that forms, guaranteed the diversity of particle by parent, make progeny inherit the advantage of parents' particles simultaneously.
Good effect of the present invention
For the single channel model, standard P SO optimization method is got and is decided after the reasonable parameter enough good performance has been arranged, satisfies the performance index requirement fully.Improve the raising slightly of back performance and can ignore from engineering viewpoint, and the prolongation to some extent on the contrary of the convergence time of two passages, the performance on roll channel is particularly evident.
To multi-channel model, the overshoot of canonical algorithm surpasses 20% in most cases, change initial value and algorithm parameter and also do not have improvement, algorithm after the improvement one section " deadtime " can occur at first in hybridization, but because the diversity of its particle is better than canonical algorithm, the performance index function minimum value that obtains at last meets the requirement of controlling performance much smaller than canonical algorithm.One-time success rate to multi-channel model optimization behind the employing improvement algorithm can reach 80%.
Fig. 1 is an algorithm flow chart of the present invention.
Claims (1)
1. improvement particle cluster algorithm that is used for unmanned aerial vehicle control law parameter automatic optimization, described particle cluster algorithm, it is the PSO algorithm, it is a kind of optimized Algorithm based on iteration, controlled variable is initialized as one group of RANDOM SOLUTION, seek optimal value by iteration, the algorithm mathematics model is: being located in the n dimension search volume has m particle, particle x
i(i=1,2 ..., locus m) is p
i=(x
I1, x
I2..., x
In), m, n are natural number, with particle x
iBring objective function into and calculate fitness, weigh x according to the size of fitness
iQuality, the optimal location that single particle lived through is designated as p
Id, the optimal location note that whole population lives through is made p
Xd, particle upgrades the speed v of oneself according to following formula
IdWith position x
Id:
v
id(t+1)=w×v
id(t)+c
1×rand()×(p
id(t)-x
id(t)+c
2×rand()×(p
nd(t)-x
id(t))
x
id(t+1)=x
id(t)+v
id(t+1)
T is the current time in the formula, and w is a weighting coefficient, c
1With c
2Be the study factor, x
Id(t) be t particle position constantly;
It is characterized in that particle number m is taken as 10~30, weighting coefficient utilizes the adjustment of following formula self-adaptation:
w=w
max-(w
max-w
min)×g/g
max
W in the formula
MaxBe the weighting coefficient maximal value, get 0.7~0.9, w
MinBe the weighting coefficient minimum value, get 0.1~0.3, g is a convergence algebraically, between 1~50, and g
MaxFor maximum convergence algebraically, get 50, study factor c
1With c
2For non-negative constant, all be taken as 2;
Introduce a hybridization operator, its method is to select the optimal location p that single particle lived through
IdSeveral particles of mediating of value carry out at random hybridization in twos, produce the filial generation particle of similar number, replace the parent particle with the filial generation particle, establish x
iAnd x
jBe 2 parent particles, the computing formula of then carrying out crossover operation is:
x
i(t+1)=s·x
i(t)+(1-s)·x
j(t)
x
j(t+1)=s·x
j(t)+(1-s)·x
i(t)
S is the random number between [0,1] in the formula;
The choose opportunities of hybridization, establishing criteria PSO convergence of algorithm algebraically, i.e. in pitching and 17~20 generations of jaw channel,, in 7~10 generations of roll channel, the algebraically that disturbance begins is elected as: pitching and jaw channel are since the 12nd generation, and roll channel is since the 4th generation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2009100293105A CN101551642A (en) | 2009-04-08 | 2009-04-08 | Improved particle swarm algorithm for automatic optimization of control law parameters of unmanned aircraft |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2009100293105A CN101551642A (en) | 2009-04-08 | 2009-04-08 | Improved particle swarm algorithm for automatic optimization of control law parameters of unmanned aircraft |
Publications (1)
Publication Number | Publication Date |
---|---|
CN101551642A true CN101551642A (en) | 2009-10-07 |
Family
ID=41155917
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNA2009100293105A Pending CN101551642A (en) | 2009-04-08 | 2009-04-08 | Improved particle swarm algorithm for automatic optimization of control law parameters of unmanned aircraft |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101551642A (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102023640A (en) * | 2010-11-23 | 2011-04-20 | 北京航空航天大学 | Selection method of nominal design point in flight envelope |
CN103823367A (en) * | 2014-02-28 | 2014-05-28 | 西安费斯达自动化工程有限公司 | Design method of longitudinal flight model cluster flutter suppression combination frequency robust controller |
CN103853050A (en) * | 2014-03-19 | 2014-06-11 | 湖北蔚蓝国际航空学校有限公司 | PID optimization control method of four-rotor aircraft |
CN103645636B (en) * | 2013-11-25 | 2016-01-06 | 南京航空航天大学 | A kind of PID controller parameter optimization method |
CN105322784A (en) * | 2014-07-11 | 2016-02-10 | 英飞凌科技奥地利有限公司 | Method and apparatus for controller optimization of switching voltage regulator |
CN105955029A (en) * | 2016-06-06 | 2016-09-21 | 南京航空航天大学 | PID control parameter optimization method with robustness guarantee |
CN108171315A (en) * | 2017-12-27 | 2018-06-15 | 南京邮电大学 | Multiple no-manned plane method for allocating tasks based on SMC particle cluster algorithms |
CN108885466A (en) * | 2017-11-22 | 2018-11-23 | 深圳市大疆创新科技有限公司 | A kind of control parameter configuration method and unmanned plane |
CN111123923A (en) * | 2019-12-17 | 2020-05-08 | 青岛科技大学 | Unmanned ship local path dynamic optimization method |
CN111580550A (en) * | 2020-04-29 | 2020-08-25 | 杭州电子科技大学 | Unmanned aerial vehicle human-simulated intelligent control method |
CN112035922A (en) * | 2020-08-25 | 2020-12-04 | 中船文化科技(北京)有限公司 | Intelligent shelter layout planning system and method, electronic equipment and storage medium |
CN113325699A (en) * | 2021-05-25 | 2021-08-31 | 上海机电工程研究所 | Parameter adjusting method and system suitable for composite stability control system |
CN113375512A (en) * | 2021-06-07 | 2021-09-10 | 河北迥然科技有限公司 | Air-fried ammunition compound spacing method and device and terminal equipment |
CN113859586A (en) * | 2021-09-17 | 2021-12-31 | 北京空间机电研究所 | On-orbit automatic adjustment method for control parameters of servo control system of space remote sensor |
CN115167144A (en) * | 2022-08-04 | 2022-10-11 | 北京航空航天大学 | Airplane actuating system based on particle swarm algorithm |
-
2009
- 2009-04-08 CN CNA2009100293105A patent/CN101551642A/en active Pending
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102023640A (en) * | 2010-11-23 | 2011-04-20 | 北京航空航天大学 | Selection method of nominal design point in flight envelope |
CN102023640B (en) * | 2010-11-23 | 2012-07-04 | 北京航空航天大学 | Selection method of nominal design point in flight envelope |
CN103645636B (en) * | 2013-11-25 | 2016-01-06 | 南京航空航天大学 | A kind of PID controller parameter optimization method |
CN103823367A (en) * | 2014-02-28 | 2014-05-28 | 西安费斯达自动化工程有限公司 | Design method of longitudinal flight model cluster flutter suppression combination frequency robust controller |
CN103823367B (en) * | 2014-02-28 | 2016-04-06 | 西安费斯达自动化工程有限公司 | Longitudinal Flight model cluster Flutter Suppression combination frequency robust Controller Design method |
CN103853050A (en) * | 2014-03-19 | 2014-06-11 | 湖北蔚蓝国际航空学校有限公司 | PID optimization control method of four-rotor aircraft |
CN105322784A (en) * | 2014-07-11 | 2016-02-10 | 英飞凌科技奥地利有限公司 | Method and apparatus for controller optimization of switching voltage regulator |
CN105322784B (en) * | 2014-07-11 | 2018-06-22 | 英飞凌科技奥地利有限公司 | For the method and apparatus of the controller optimization of regulator |
CN105955029A (en) * | 2016-06-06 | 2016-09-21 | 南京航空航天大学 | PID control parameter optimization method with robustness guarantee |
CN105955029B (en) * | 2016-06-06 | 2019-03-29 | 南京航空航天大学 | A kind of pid control parameter optimization method for protecting robustness |
CN108885466A (en) * | 2017-11-22 | 2018-11-23 | 深圳市大疆创新科技有限公司 | A kind of control parameter configuration method and unmanned plane |
CN108171315A (en) * | 2017-12-27 | 2018-06-15 | 南京邮电大学 | Multiple no-manned plane method for allocating tasks based on SMC particle cluster algorithms |
CN108171315B (en) * | 2017-12-27 | 2021-11-19 | 南京邮电大学 | Multi-unmanned aerial vehicle task allocation method based on SMC particle swarm algorithm |
CN111123923A (en) * | 2019-12-17 | 2020-05-08 | 青岛科技大学 | Unmanned ship local path dynamic optimization method |
CN111123923B (en) * | 2019-12-17 | 2022-09-06 | 青岛科技大学 | Unmanned ship local path dynamic optimization method |
CN111580550A (en) * | 2020-04-29 | 2020-08-25 | 杭州电子科技大学 | Unmanned aerial vehicle human-simulated intelligent control method |
CN112035922A (en) * | 2020-08-25 | 2020-12-04 | 中船文化科技(北京)有限公司 | Intelligent shelter layout planning system and method, electronic equipment and storage medium |
CN113325699A (en) * | 2021-05-25 | 2021-08-31 | 上海机电工程研究所 | Parameter adjusting method and system suitable for composite stability control system |
CN113375512A (en) * | 2021-06-07 | 2021-09-10 | 河北迥然科技有限公司 | Air-fried ammunition compound spacing method and device and terminal equipment |
CN113859586A (en) * | 2021-09-17 | 2021-12-31 | 北京空间机电研究所 | On-orbit automatic adjustment method for control parameters of servo control system of space remote sensor |
CN113859586B (en) * | 2021-09-17 | 2023-02-28 | 北京空间机电研究所 | On-orbit automatic adjustment method for control parameters of servo control system of space remote sensor |
CN115167144A (en) * | 2022-08-04 | 2022-10-11 | 北京航空航天大学 | Airplane actuating system based on particle swarm algorithm |
CN115167144B (en) * | 2022-08-04 | 2024-04-30 | 北京航空航天大学 | Aircraft actuating system based on particle swarm optimization |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101551642A (en) | Improved particle swarm algorithm for automatic optimization of control law parameters of unmanned aircraft | |
CN110308649A (en) | A kind of pid parameter optimization method based on PSO-SOA blending algorithm | |
Rahimian et al. | Optimal PID controller design for AVR system using particle swarm optimization algorithm | |
CN107272403A (en) | A kind of PID controller parameter setting algorithm based on improvement particle cluster algorithm | |
CN106598849B (en) | A kind of combined test case generation method based on AP-PSO algorithm | |
CN105425612B (en) | A kind of method for optimizing of Adaptive System of Water-Turbine Engine control parameter | |
CN109947124A (en) | Improve particle swarm algorithm Optimization of Fuzzy PID unmanned helicopter attitude control method | |
US10747184B2 (en) | Controlling a target system | |
CN108181802A (en) | A kind of controllable PID controller parameter optimization setting method of performance | |
CN110288074A (en) | A kind of improvement longicorn palpus searching algorithm based on the mechanism of encirclement | |
WO2013008345A1 (en) | Optimum solution searching method and optimum solution searching device | |
CN104102133A (en) | Improved artificial bee colony algorithm based quadrotor proportional integral derivative (PID) parameter optimization method | |
Cheng et al. | Interior ballistic charge design based on a modified particle swarm optimizer | |
CN108985438A (en) | A kind of cuckoo searching algorithm based on neighborhood topology | |
CN111143983A (en) | Low sidelobe comprehensive optimization method of sparse antenna array based on improved water circulation algorithm | |
CN110516318A (en) | Airfoil Design method based on radial basis function neural network agent model | |
Qingwen et al. | Cooperative jamming resource allocation of UAV swarm based on multi-objective DPSO | |
Siqueira et al. | Recursive linear models optimized by bioinspired metaheuristics to streamflow time series prediction | |
CN102393645A (en) | Control method of high-speed electro-hydraulic proportional governing system | |
CN114519292A (en) | Air-to-air missile over-shoulder launching guidance law design method based on deep reinforcement learning | |
CN103809434B (en) | The multistage PID controller design method of the compound root locus of Longitudinal Flight model cluster | |
KR102406851B1 (en) | Coordinated optimization method for maximizing the power of wind farm using scalable wake digraph and apparatus performing the same | |
CN114765439A (en) | Continuous rotary motor system simplified dynamic flexible variable structure PD composite control method based on friction compensation | |
CN109657778B (en) | Improved multi-swarm global optimal-based adaptive pigeon swarm optimization method | |
Su et al. | Multi-interceptor target allocation based on improved particle swarm optimization algorithm |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20091007 |