CN109947124A - Improve particle swarm algorithm Optimization of Fuzzy PID unmanned helicopter attitude control method - Google Patents
Improve particle swarm algorithm Optimization of Fuzzy PID unmanned helicopter attitude control method Download PDFInfo
- Publication number
- CN109947124A CN109947124A CN201910338682.XA CN201910338682A CN109947124A CN 109947124 A CN109947124 A CN 109947124A CN 201910338682 A CN201910338682 A CN 201910338682A CN 109947124 A CN109947124 A CN 109947124A
- Authority
- CN
- China
- Prior art keywords
- particle
- fuzzy
- population
- factor
- controller
- 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
Abstract
The present invention provides a kind of improvement particle swarm algorithm Optimization of Fuzzy PID unmanned helicopter attitude control methods, the following steps are included: step 1, according to the dynamics and kinematics model design fuzzy attitude controller of the unmanned helicopter that modelling by mechanism method obtains, the error of desired attitude angle He practical attitude angle, error rate are controlled using controller to obtain the parameter adjustment amount of fuzzy attitude controller;Step 2, the quantized factor and proportional factor in fuzzy attitude controller is optimized using improvement particle swarm algorithm;Step 3, the quantized factor and proportional factor after optimization is assigned to fuzzy attitude controller.
Description
Technical field
The present invention relates to a kind of unmanned helicopter control technology, especially a kind of improvement particle swarm algorithm Optimization of Fuzzy PID
Unmanned helicopter attitude control method.
Background technique
Unmanned plane is the abbreviation of push-button aircraft, with have it is man-machine compared with, unmanned plane can be reduced and pilot itself
The related unmanned plane construction weight of weight increases payload, reduces cost, and volume reduces, more concealment, in some special feelings
Unmanned plane is able to carry out the man-machine higher task of the risk that can not be executed under condition, and the flexibility ratio of design is higher.Unmanned helicopter
As one kind of unmanned plane, compared with fixed-wing unmanned plane, flight stability is higher, it can be achieved that VTOL and hovering,
With better mobility and flexibility, can fly in space with a varied topography or narrow, be widely used in military and
Civil field.
The gesture stability of unmanned helicopter is an important subject in unmanned plane field, unmanned helicopter flight control
System generally includes gesture stability and TRAJECTORY CONTROL, and wherein TRAJECTORY CONTROL refers to the control of helicopter position and height, and position and
The variation that the variation of height relies primarily on posture is achieved.Currently, the attitude control method of unmanned helicopter mainly includes line
Property control, a variety of design methods such as nonlinear Control and intelligent control.In linear control method, at present it is most widely used still
Classical PID control, it is although structure is simple, and it is convenient that design is realized, but in practical engineering project, the setting method of relevant parameter
It is relatively complicated, it tends to be difficult to be optimal, so that system cannot get preferable control effect.Fuzzy control is a kind of nonlinear
Control method possesses good control performance, but fuzzy controller also has disadvantage, and quantization and scale factor are determining, are subordinate to
Spending function selection and the formulation of fuzzy reasoning table has great influence to control effect, but relies only on expertise and engineering
Experience obtains, and not can avoid interference caused by specific condition, adaptive ability and control effect are undesirable.
Summary of the invention
The purpose of the present invention is to provide a kind of improvement particle swarm algorithm Optimization of Fuzzy PID unmanned helicopter gesture stability sides
Method realizes effective control to unmanned helicopter posture.
Realize the technical solution of the object of the invention are as follows: a kind of improvement particle swarm algorithm Optimization of Fuzzy PID unmanned helicopter appearance
State control method, comprising the following steps:
Step 1, the dynamics and kinematics model of the unmanned helicopter obtained according to modelling by mechanism method design fuzzy
Attitude controller is controlled to obtain mould using controller to the error of desired attitude angle He practical attitude angle, error rate
Paste the parameter adjustment amount of PID attitude controller;
Step 2, the quantized factor and proportional factor in fuzzy attitude controller is carried out using improvement particle swarm algorithm
Optimization;
Step 3, the quantized factor and proportional factor after optimization is assigned to fuzzy attitude controller.
Compared with prior art, the present invention having the advantage that (1) present invention the same fuzzy of improvement particle swarm algorithm
Control, which combines, to be optimized, and is compensated for existing fuzzy PID control method parameter and is chosen excessively dependence expertise and engineering
The shortcomings that experience, meets the needs of modern unmanned helicopter gesture stability, improves control performance;(2) to standard particle group's
Improvement can make algorithm avoid falling into local optimum, judge whether to enter precocity in an iterative process using the performance of fitness value
Convergence state is enriched if being made a variation, being intersected and selection operation using differential evolution algorithm into Premature Convergence state
The diversity of particle populations carries out global optimizing, avoids falling into local optimum.
The invention will be further described with reference to the accompanying drawings of the specification.
Detailed description of the invention
Fig. 1 is flow chart of the method for the present invention.
Fig. 2 is fuzzy-adaptation PID control block diagram in the present invention.
Fig. 3 is fuzzy-adaptation PID control program flow diagram in the present invention.
Fig. 4 is unmanned helicopter Building of Simulation Model block diagram in the present invention.
Fig. 5 is the unmanned helicopter posture angle tracking simulation architecture block diagram of embodiment in the present invention.
Fig. 6 is algorithm of the present invention and common fuzzy-adaptation PID control step response simulation result comparison diagram, wherein (a)
(b) it is roll angle simulation result comparison diagram for pitch angle simulation result comparison diagram, (c) is yaw angle simulation result comparison diagram.
Specific embodiment
A kind of improvement particle swarm algorithm Optimization of Fuzzy PID unmanned helicopter attitude control method, needs to unmanned helicopter
Pitch angle, three roll angle, yaw angle attitude angles control respectively, the parameter for needing to optimize is the amount in fuzzy controller
Change factor Ke、KecAnd scale factor Ku={ K1,K2,K3Five parameters, steps flow chart is essentially identical, as shown in Figure 1, specific packet
Include following steps:
Step 1, the dynamics and kinematics model of unmanned helicopter are obtained using modelling by mechanism method, based on model
Fuzzy attitude controller is designed, structure is as shown in Fig. 2, select unmanned helicopter it is expected attitude angleWith practical attitude angle's
ErrorAnd its error rateAs input variable, by the parameter adjustment amount Δ of the attitude angle PID controller
kp、Δki、ΔkdAs output variable, wherein Δ kp、Δki、ΔkdIt is ratio P, integral I, corresponding three ginsengs of differential D respectively
Number kp、ki、kdVariable quantity.
Step 2, fuzzy attitude controller is optimized using a kind of improvement particle swarm algorithm, optimizes its mould
Quantizing factor K in paste controle、KecAnd scale factor Ku={ K1,K2,K3Five parameters, real coding mode is selected, with position
Set vector intrinsic parameter one-to-one correspondence, optimization process specifically includes the following steps:
Step 2.1, particle swarm algorithm parameter is initialized, it is assumed that in a d dimension search space, initialize a population rule
Mould is the population of N, initializes the position X of group within the allowable rangei=(xi,1 xi,2 … xi,d) and speed Vi=(vi,1
vi,2 … vi,d), wherein i represents i-th of particle in population, xi,dIt is particle i in the position of d dimension, vi,dExist for particle i
The speed of d dimension;
Step 2.2, successively by the corresponding parameter assignment of particle location information each in population to quantizing factor and ratio because
Controller after son operation assignment carries out gesture stability to dummy vehicle, using integral performance index (ITAE) as the mesh of optimizing
Mark, the fitness value of each particle, the individual extreme value and global extremum of more new particle are calculated according to fitness value function;Wherein
The adaptive optimal control angle value that individual extrema representation (individual) the particle i of particle is undergone in search process immediately
Pbest and optimal location Pi=(pi,1 pi,2 … pi,d);Global extremum indicates entire population in all previous iterative process
Adaptive optimal control angle value gbest and optimal location Pg=(pg,1 pg,2 … pg,d);The individual each particle of extreme value has one, the overall situation
The entire population of extreme value only one.
The standard of update is the bigger existing extreme value of substitution of fitness value.
The objective function of integral performance index optimizing is
Fitness value function specific manifestation form is
Wherein, t is time parameter, value of the deviation e that e (t) is given value and real output value is constituted at each moment.
Step 2.3, if reaching the number of iterations requirement, end loop program exports optimal solution, if continuing without if
Following steps;
Step 2.4, it updates the speed of each particle of subsequent time and position iterative formula is
vi,j(k+1)=wvi,j(k)+c1r1[pi,j-xi,j(k)]+c2r2[pgs-xi,j(k)]
xi,j(k+1)=xi,j(k)+vi,j(k+1), j=1,2 ..., d
Wherein, k is current iteration number, pi,jFor the optimal location that i-th of particle searches so far, pgsIt is entire
The optimal location that population searches so far, c1And c2The Studying factors being positive, r1And r2It is equally distributed between 0 to 1
Random number, w are inertia weight, are easy precocity for PSO algorithm and the algorithm later period is easy to generate shake near globally optimal solution
Phenomenon is swung, using the linear decrease method of weighting, w is with the variation formula of algorithm iteration number
Wherein, wmaxAnd wminThe maximum value and minimum value of w are respectively indicated, T is maximum number of iterations;
Step 2.5, whether comparison algorithm there is Premature convergence, and step 2 is gone to if not;If algorithm occurs
Premature Convergence then carries out precocious processing to the position of particle, obtains next-generation population, go to step 2.
Wherein, check whether the method for Premature Convergence is that the change of fitness value is influenced according to space clustering change in location to algorithm
Change, the state of population can be tracked according to fitness value.If fiFor the fitness value of i-th of particle, favgIt is current for population
Fitness average value, σ2For population Colony fitness variance, formula is
Wherein f is normalization factor, is
σ2Smaller, population aggregation extent is bigger, more early to fall into Premature Convergence, therefore, works as σ2(C is one to permanent to < C
Number) when, it is handled into precocity.
Precocity processing is is made a variation in conjunction with position of the differential evolution algorithm to particle, is intersected and selection operation, specifically such as
Under:
(1) mutation operation:
Set kth for i-th of variation individual in population as
Yi(k+1)=(yi,1(k+1),yi,2(k+1),...,yi,d(k+1)),
yi,dIt (k+1) is individual Yi(k+1) in d dimension position,
Three different individuals, i.e. X are randomly selected in current populationp(k)、Xq(k) and Xr(k), difference scaling is carried out again
New variation individual is formed to variation individual addition of vectors with one, i.e.,
Yi(k+1)=Xp(k)+F×(Xq(k)-Xr(k))
Wherein, i=1,2 ..., N, p, q, r are 1 random integers into N, and F is zoom factor, generally take 0.5 to 1 it
Between, Xi(k) indicate kth for i-th of individual in population.
(2) crossover operation:
If the individual obtained after intersecting is
Ui(k+1)=(ui,1(k+1),ui,2(k+1),...,ui,d(k+1))
Wherein, CR is crossover probability, is generally taken between 0.8 to 1, jrandFor random number.
(3) selection operation:
Wherein, f () refers to the fitness value of the individual.
Step 3, attitude controller is configured, obtained globally optimal solution location information is assigned in fuzzy controller
Quantizing factor Ke、KecAnd scale factor Kp、Ki、Kd, form complete unmanned helicopter attitude controller, fuzzy-adaptation PID control journey
Sequence process obtains the pid control parameter after adjusting as shown in figure 3, carry out real-time online optimizing, carries out to unmanned helicopter
Gesture stability.
Fig. 4 is that unmanned helicopter Building of Simulation Model block diagram is set gradually fuzzy on this basis according to above-mentioned steps
PID controller, and write program and obtain Optimal Parameters, it is saved in controller design file.Complete fuzzy controller configuration
Afterwards, control system block diagram is built by MATLAB/SIMULINK, as shown in figure 5, carrying out control emulation to attitude angle.
In order to verify the control effect of the controller, the conduct pair of certain type unmanned helicopter is selected in simulation example of the present invention
As setting unmanned helicopter targeted attitude angle as 15 °, the resulting control effect based on Modified particle swarm optimization fuzzy
With the comparison figure of the fuzzy-adaptation PID control of no optimization, as shown in Figure 6, wherein fuzzy-PID be the fuzzy without optimization, PSO-
Fuzzy-PID is Modified particle swarm optimization fuzzy.It can be seen that under improved controller action, posture angular response speed
Faster, stability is more preferable for degree.
Claims (6)
1. a kind of improvement particle swarm algorithm Optimization of Fuzzy PID unmanned helicopter attitude control method, which is characterized in that including following
Step:
Step 1, the dynamics and kinematics model of the unmanned helicopter obtained according to modelling by mechanism method design fuzzy posture
Controller is controlled to obtain fuzzy using controller to the error of desired attitude angle He practical attitude angle, error rate
The parameter adjustment amount of attitude controller;
Step 2, excellent to the quantized factor and proportional factor progress in fuzzy attitude controller using particle swarm algorithm is improved
Change;
Step 3, the quantized factor and proportional factor after optimization is assigned to fuzzy attitude controller.
2. requiring the method according to right 1, which is characterized in that unmanned helicopter is selected it is expected attitude angleWith practical posture
AngleErrorAnd its error rateAs the input variable of PID attitude controller, by fuzzy posture
The parameter adjustment amount Δ k of controllerp、Δki、ΔkdAs output variable, wherein Δ kp、Δki、ΔkdIt is ratio P, integral respectively
I, the corresponding three parameter k of differential Dp、ki、kdVariable quantity.
3. requiring the method according to right 1, which is characterized in that using improvement particle swarm algorithm to fuzzy gesture stability
The scale factor K of devicee、KecWith quantizing factor Ku={ K1,K2,K3Five parameters optimize, optimization process specifically includes following
Step:
Step 2.1, particle swarm algorithm parameter is initialized, it is assumed that in a d dimension search space, initializing a population scale is
The population of N initializes the position X of group within the allowable rangei=(xi,1 xi,2…xi,d) and speed Vi=(vi,1 vi,2…
vi,d), wherein i represents i-th of particle in population, xi,dIt is particle i in the position of d dimension, vi,dIt is particle i in d dimension
Speed;
Step 2.2, successively by the corresponding parameter assignment of particle location information each in population to quantized factor and proportional factor, fortune
Controller after row assignment carries out gesture stability to dummy vehicle, using integral performance index as the target of optimizing, according to suitable
Response value function calculates the fitness value of each particle, the bigger particle extreme value of fitness value is replaced existing extreme value, and update
The global extremum of particle;Wherein
The objective function of integral performance index optimizing is
Fitness value function specific manifestation form is
Wherein, t is time parameter, value of the deviation e that e (t) is given value and real output value is constituted at each moment;
Step 2.3, if reaching the number of iterations requirement, end loop program exports optimal solution, if continuing step without if
2.4;
Step 2.4, speed and the position of each particle of subsequent time are updated;
Step 2.5, whether comparison algorithm there is Premature convergence, and step 2.2 is gone to if not;If algorithm occurs early
Ripe convergence then carries out precocious processing to the position of particle, obtains next-generation population, go to step 2.2.
4. according to the method described in claim 3, it is characterized in that, each grain of subsequent time is updated in step 2.4 according to the following formula
The speed of son and position:
vi,j(k+1)=wvi,j(k)+c1r1[pi,j-xi,j(k)]+c2r2[pgs-xi,j(k)]
xi,j(k+1)=xi,j(k)+vi,j(k+1), j=1,2 ..., d
Wherein, k is current iteration number, pi,jFor the optimal location that i-th of particle searches so far, pgsFor entire particle
The optimal location that group searches so far, c1And c2The Studying factors being positive, r1And r2It is equally distributed random between 0 to 1
Number, w is inertia weight
Wherein, wmaxAnd wminThe maximum value and minimum value of w are respectively indicated, T is maximum number of iterations.
5. according to the method described in claim 3, it is characterized in that, whether step 2.5 comparison algorithm there is Premature convergence
Detailed process are as follows:
Obtain population Colony fitness variance σ2
Wherein, fiFor the fitness value of i-th of particle, favgFor the current fitness average value of population, f is normalization factor,
If σ2, there is Premature convergence in < C, and C is constant.
6. according to the method described in claim 5, it is characterized in that, the processing of precocity described in step 2.5 is in conjunction with differential evolution
Algorithm makes a variation to the position of particle, intersect and selection operation, detailed process include:
(1) mutation operation:
Set kth for i-th of variation individual in population as
Yi(k+1)=(yi,1(k+1),yi,2(k+1),...,yi,d(k+1))
yi,dIt (k+1) is individual Yi(k+1) in d dimension position,
Three different individuals are randomly selected in current population, carry out difference scaling again with one to variation individual addition of vectors
New variation individual is formed, i.e.,
Yi(k+1)=Xp(k)+F×(Xq(k)-Xr(k))
Wherein, i=1,2 ..., N, p, q, r are 1 random integers into N, and F is zoom factor, are generally taken between 0.5 to 1, Xi
(k) indicate kth for i-th of individual in population;
(2) crossover operation:
The individual obtained after intersection is
Ui(k+1)=(ui,1(k+1),ui,2(k+1),...,ui,d(k+1))
Wherein, CR is crossover probability, is generally taken between 0.8 to 1, jrandFor random number.
(3) selection operation:
The individual obtained after selection operation is
Wherein, f () refers to the fitness value of the individual.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910338682.XA CN109947124A (en) | 2019-04-25 | 2019-04-25 | Improve particle swarm algorithm Optimization of Fuzzy PID unmanned helicopter attitude control method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910338682.XA CN109947124A (en) | 2019-04-25 | 2019-04-25 | Improve particle swarm algorithm Optimization of Fuzzy PID unmanned helicopter attitude control method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109947124A true CN109947124A (en) | 2019-06-28 |
Family
ID=67016148
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910338682.XA Pending CN109947124A (en) | 2019-04-25 | 2019-04-25 | Improve particle swarm algorithm Optimization of Fuzzy PID unmanned helicopter attitude control method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109947124A (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110502860A (en) * | 2019-08-28 | 2019-11-26 | 河南科技大学 | Unmanned helicopter based on particle swarm algorithm controls optimization method |
CN110543101A (en) * | 2019-10-09 | 2019-12-06 | 福建工程学院 | method and device for optimizing fan fuzzy controller based on genetic algorithm |
CN110704948A (en) * | 2019-09-24 | 2020-01-17 | 江西慧识智能科技有限公司 | Design method of intelligent controller of unmanned aerial vehicle |
CN110780592A (en) * | 2019-10-21 | 2020-02-11 | 上海海事大学 | Control method of six-degree-of-freedom platform based on differential evolution particle swarm algorithm |
CN111221245A (en) * | 2020-02-13 | 2020-06-02 | 广东工业大学 | Setting machine fuzzy PID tension control parameter self-tuning method based on PSO |
CN111413863A (en) * | 2020-03-27 | 2020-07-14 | 南京理工大学 | Particle swarm fuzzy Smith temperature control method based on 3D printing nozzle |
CN111679685A (en) * | 2020-06-19 | 2020-09-18 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle total energy based flight control method and device |
CN111695194A (en) * | 2020-05-12 | 2020-09-22 | 南京航空航天大学 | Embedded hardware-based unmanned helicopter flight control improved PSO algorithm verification method |
CN113110061A (en) * | 2021-04-30 | 2021-07-13 | 华南农业大学 | Intelligent irrigation fuzzy control method and system based on improved particle swarm optimization |
CN113341689A (en) * | 2021-04-29 | 2021-09-03 | 中国人民解放军海军工程大学 | Improved micro gas turbine fuzzy PID control method based on optimization algorithm |
CN113515048A (en) * | 2021-08-13 | 2021-10-19 | 华中科技大学 | Method for establishing fuzzy self-adaptive PSO-ELM sound quality prediction model |
CN113641097A (en) * | 2021-08-30 | 2021-11-12 | 东南大学 | Particle swarm algorithm-based parameter optimization method for unmanned aerial vehicle flight control system |
CN113759722A (en) * | 2021-09-13 | 2021-12-07 | 桂林电子科技大学 | Parameter optimization method for active disturbance rejection controller of unmanned aerial vehicle |
CN115079113A (en) * | 2022-08-22 | 2022-09-20 | 国家海洋技术中心 | Ground wave radar directional diagram measuring method and system based on unmanned ship |
CN115741692A (en) * | 2022-11-17 | 2023-03-07 | 山东大学 | High-precision control method and system for hydraulic mechanical arm based on data driving |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8185259B2 (en) * | 2010-08-23 | 2012-05-22 | King Fahd University Of Petroleum & Minerals | Fuzzy logic-based control method for helicopters carrying suspended loads |
CN103853881A (en) * | 2014-02-12 | 2014-06-11 | 四川大学 | Water turbine parameter identification method based on self-adaptive chaotic and differential evolution particle swarm optimization |
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 |
CN103984980A (en) * | 2014-01-28 | 2014-08-13 | 中国农业大学 | Method for predicting temperature extreme value in greenhouse |
CN105281615A (en) * | 2015-11-12 | 2016-01-27 | 广西师范大学 | Method for optimizing brushless DC motor fuzzy controller based on improved particle swarm algorithm |
CN106990792A (en) * | 2017-05-23 | 2017-07-28 | 西北工业大学 | Mix the multiple no-manned plane collaboration sequential coupling task distribution method of gravitation search algorithm |
CN107392388A (en) * | 2017-07-31 | 2017-11-24 | 南昌航空大学 | A kind of method for planning no-manned plane three-dimensional flight path using artificial fish-swarm algorithm is improved |
CN108763779A (en) * | 2018-05-31 | 2018-11-06 | 太原理工大学 | A kind of method that the particle cluster algorithm of application enhancements controls quadrotor drone |
-
2019
- 2019-04-25 CN CN201910338682.XA patent/CN109947124A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8185259B2 (en) * | 2010-08-23 | 2012-05-22 | King Fahd University Of Petroleum & Minerals | Fuzzy logic-based control method for helicopters carrying suspended loads |
CN103984980A (en) * | 2014-01-28 | 2014-08-13 | 中国农业大学 | Method for predicting temperature extreme value in greenhouse |
CN103853881A (en) * | 2014-02-12 | 2014-06-11 | 四川大学 | Water turbine parameter identification method based on self-adaptive chaotic and differential evolution particle swarm optimization |
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 |
CN105281615A (en) * | 2015-11-12 | 2016-01-27 | 广西师范大学 | Method for optimizing brushless DC motor fuzzy controller based on improved particle swarm algorithm |
CN106990792A (en) * | 2017-05-23 | 2017-07-28 | 西北工业大学 | Mix the multiple no-manned plane collaboration sequential coupling task distribution method of gravitation search algorithm |
CN107392388A (en) * | 2017-07-31 | 2017-11-24 | 南昌航空大学 | A kind of method for planning no-manned plane three-dimensional flight path using artificial fish-swarm algorithm is improved |
CN108763779A (en) * | 2018-05-31 | 2018-11-06 | 太原理工大学 | A kind of method that the particle cluster algorithm of application enhancements controls quadrotor drone |
Non-Patent Citations (3)
Title |
---|
于鸿达: "一种基于差分进化混合粒子群算法的多无人机航迹规划", 《电光与控制》 * |
段凤阳: "无人机姿态控制器设计及仿真", 《计算机测量与控制》 * |
汪阳华: "基于粒子群算法的锅炉主蒸汽压力模糊PID 控制", 《湖南工业大学学报》 * |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110502860A (en) * | 2019-08-28 | 2019-11-26 | 河南科技大学 | Unmanned helicopter based on particle swarm algorithm controls optimization method |
CN110502860B (en) * | 2019-08-28 | 2022-10-14 | 河南科技大学 | Unmanned helicopter control optimization method based on particle swarm algorithm |
CN110704948A (en) * | 2019-09-24 | 2020-01-17 | 江西慧识智能科技有限公司 | Design method of intelligent controller of unmanned aerial vehicle |
CN110543101A (en) * | 2019-10-09 | 2019-12-06 | 福建工程学院 | method and device for optimizing fan fuzzy controller based on genetic algorithm |
CN110780592A (en) * | 2019-10-21 | 2020-02-11 | 上海海事大学 | Control method of six-degree-of-freedom platform based on differential evolution particle swarm algorithm |
CN111221245A (en) * | 2020-02-13 | 2020-06-02 | 广东工业大学 | Setting machine fuzzy PID tension control parameter self-tuning method based on PSO |
CN111221245B (en) * | 2020-02-13 | 2023-04-07 | 广东工业大学 | Setting machine fuzzy PID tension control parameter self-tuning method based on PSO |
CN111413863A (en) * | 2020-03-27 | 2020-07-14 | 南京理工大学 | Particle swarm fuzzy Smith temperature control method based on 3D printing nozzle |
CN111413863B (en) * | 2020-03-27 | 2023-04-07 | 南京理工大学 | Particle swarm fuzzy Smith temperature control method based on 3D printing nozzle |
CN111695194A (en) * | 2020-05-12 | 2020-09-22 | 南京航空航天大学 | Embedded hardware-based unmanned helicopter flight control improved PSO algorithm verification method |
CN111679685A (en) * | 2020-06-19 | 2020-09-18 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle total energy based flight control method and device |
CN111679685B (en) * | 2020-06-19 | 2023-04-07 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle total energy based flight control method and device |
CN113341689A (en) * | 2021-04-29 | 2021-09-03 | 中国人民解放军海军工程大学 | Improved micro gas turbine fuzzy PID control method based on optimization algorithm |
CN113110061A (en) * | 2021-04-30 | 2021-07-13 | 华南农业大学 | Intelligent irrigation fuzzy control method and system based on improved particle swarm optimization |
CN113515048A (en) * | 2021-08-13 | 2021-10-19 | 华中科技大学 | Method for establishing fuzzy self-adaptive PSO-ELM sound quality prediction model |
CN113515048B (en) * | 2021-08-13 | 2023-04-07 | 华中科技大学 | Method for establishing fuzzy self-adaptive PSO-ELM sound quality prediction model |
CN113641097A (en) * | 2021-08-30 | 2021-11-12 | 东南大学 | Particle swarm algorithm-based parameter optimization method for unmanned aerial vehicle flight control system |
CN113759722A (en) * | 2021-09-13 | 2021-12-07 | 桂林电子科技大学 | Parameter optimization method for active disturbance rejection controller of unmanned aerial vehicle |
CN113759722B (en) * | 2021-09-13 | 2024-03-29 | 桂林电子科技大学 | Unmanned aerial vehicle active disturbance rejection controller parameter optimization method |
CN115079113A (en) * | 2022-08-22 | 2022-09-20 | 国家海洋技术中心 | Ground wave radar directional diagram measuring method and system based on unmanned ship |
CN115741692A (en) * | 2022-11-17 | 2023-03-07 | 山东大学 | High-precision control method and system for hydraulic mechanical arm based on data driving |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109947124A (en) | Improve particle swarm algorithm Optimization of Fuzzy PID unmanned helicopter attitude control method | |
CN110308649B (en) | PID parameter optimization method based on PSO-SOA fusion algorithm and applied to industrial process control | |
CN111552314B (en) | Self-adaptive formation tracking control method for multiple unmanned aerial vehicles | |
CN107272403A (en) | A kind of PID controller parameter setting algorithm based on improvement particle cluster algorithm | |
CN108319286A (en) | A kind of unmanned plane Air Combat Maneuvering Decision Method based on intensified learning | |
CN109725644A (en) | A kind of hypersonic aircraft linear optimization control method | |
CN109669475A (en) | Multiple no-manned plane three-dimensional formation reconfiguration method based on artificial bee colony algorithm | |
CN105607473B (en) | The attitude error Fast Convergent self-adaptation control method of small-sized depopulated helicopter | |
CN113885320B (en) | Aircraft random robust control method based on mixed quantum pigeon swarm optimization | |
CN111722533A (en) | Sliding mode prediction fault-tolerant control method for multi-time-lag system containing sensor faults | |
CN110399697B (en) | Aircraft control distribution method based on improved genetic learning particle swarm algorithm | |
CN117093033A (en) | Resistance heating furnace temperature control system for optimizing PID parameters based on particle swarm optimization | |
CN108763779A (en) | A kind of method that the particle cluster algorithm of application enhancements controls quadrotor drone | |
CN108453737B (en) | Robot action track acquisition system and method based on neural network | |
CN114237268A (en) | Unmanned aerial vehicle strong robust attitude control method based on deep reinforcement learning | |
Lu et al. | Design of quadrotor hovering controller based on improved particle swarm optimization | |
CN112799429A (en) | Multi-missile cooperative attack guidance law design method based on reinforcement learning | |
CN116432539A (en) | Time consistency collaborative guidance method, system, equipment and medium | |
CN116227338A (en) | Variable wing aircraft track optimization method based on self-adaptive sparrow searching pseudo-spectrum method | |
CN110554707A (en) | Q learning automatic parameter adjusting method for aircraft attitude control loop | |
Mandala et al. | Optimization of two degree of freedom PID controller for quadrotor with stochastic fractal search algorithm | |
CN113110061B (en) | Intelligent irrigation fuzzy control method and system based on improved particle swarm optimization | |
CN114047778A (en) | Small airplane short-distance automatic landing transverse and lateral control method | |
CN106597847B (en) | Maneuvering load controller based on recurrent neural network and control method thereof | |
CN114859719A (en) | Graph neural network-based reinforcement learning cluster bee-congestion control method |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190628 |
|
WD01 | Invention patent application deemed withdrawn after publication |