CN112987572A - Priori knowledge-based particle swarm optimization method for adaptive ball bar system - Google Patents
Priori knowledge-based particle swarm optimization method for adaptive ball bar system Download PDFInfo
- Publication number
- CN112987572A CN112987572A CN202110219269.9A CN202110219269A CN112987572A CN 112987572 A CN112987572 A CN 112987572A CN 202110219269 A CN202110219269 A CN 202110219269A CN 112987572 A CN112987572 A CN 112987572A
- Authority
- CN
- China
- Prior art keywords
- adaptive
- particle swarm
- particle
- algorithm
- formula
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000002245 particle Substances 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000005457 optimization Methods 0.000 title claims abstract description 23
- 230000003044 adaptive effect Effects 0.000 title claims description 20
- 230000008859 change Effects 0.000 claims abstract description 11
- 230000010354 integration Effects 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000035772 mutation Effects 0.000 claims description 7
- 150000001875 compounds Chemical class 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 4
- 230000009191 jumping Effects 0.000 claims description 3
- 230000010485 coping Effects 0.000 abstract description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000005034 decoration Methods 0.000 description 2
- 230000008034 disappearance Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 230000000087 stabilizing effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The invention provides a priori knowledge-based particle swarm optimization method for a self-adaptive ball bar system, which improves a particle swarm algorithm by improving nonlinear inertia weight, using a self-adaptive change strategy containing a variation factor and combining the priori knowledge with a fitness function of traditional performance integration, and finds a balance position to stabilize the ball bar system by using a proportional-integral-derivative controller of the improved particle swarm optimization algorithm for the ball bar system; the invention provides a priori knowledge-based particle swarm optimization method for a self-adaptive ball bar system, which adopts the idea of fusing the priori knowledge into an improved particle swarm optimization method, fully utilizes the result of each iteration of an algorithm, and improves the interference coping capability of the ball bar system and the operation efficiency of the algorithm.
Description
Technical Field
The invention relates to a priori knowledge-based particle swarm optimization method for a self-adaptive ball bar system, and belongs to the field of swarm intelligence optimization control.
Background
The ball rod system consists of a metal ball and a track for the metal ball to freely roll, has the characteristics of nonlinearity, open loop instability, underactuation and the like, and has the advantages of very complex movement of a small ball on a guide rail, higher control difficulty and great challenge.
In order to solve the difficulty of controlling a club system, more and more engineers and technicians have recently proposed various club system control schemes with a view to studying an optimal club system control method to better and more quickly balance the club system.
Chinese patent No.: CN109782595A discloses a network predictive control method for a club system based on an event trigger mechanism, which compensates time lag caused by network transmission by using the network predictive control method according to a reconstruction system state, designs a controller uk and sends a control instruction to an actuator of the club system to achieve a control target, thereby actively compensating the network time lag and effectively saving bandwidth resources.
Chinese patent No.: CN105589332A discloses a method for balancing a club based on SFLA fuzzy controller, which focuses on the optimization of SFLA algorithm on parameters, and introduces expert experience into the rule base of the fuzzy controller, so as to use the optimized fuzzy controller to control the club system to reach a balanced state.
However, in the actual club problem, the influence of the environmental factors such as voltage pulse, mechanical friction, and slip disturbance may occur, and complete disappearance of the random disturbance may not be guaranteed, and the conventional method has low adaptability to the disturbances, and the complicated club system with unstable open loop may have difficulty in coping with the disturbances, thereby causing control failure. Meanwhile, the trapping of a local optimal solution is avoided, and the improvement of the searching efficiency and precision of the optimal solution is of great importance. Therefore, how to overcome the interference in the operation process of the club system and quickly and accurately obtain the control parameters of the club system and the like is an unsolved problem.
Disclosure of Invention
The invention aims to provide a priori knowledge-based particle swarm optimization method for an adaptive ball bar system, and aims to solve the related technical problems in the prior art.
A particle swarm optimization method of a self-adaptive ball rod system based on prior knowledge is characterized in that a particle swarm algorithm is improved by improving nonlinear inertia weight, using a self-adaptive change strategy containing variation factors and combining a fitness function of the prior knowledge and traditional performance integration, an improved particle swarm optimization algorithm is used for finding a balance position for stabilizing the ball rod system, and the specific steps are as follows:
step 1: designing a proportional speed compensator, and controlling an internal motor control loop with small influence on the control effect of the club system according to the time domain requirement;
step 2: designing a PID controller of an outer ring ball arm control loop according to the ball arm system structure;
and step 3: three parameters K of outer ring PID controllerp,Ki,KdRespectively serving as three input variables, regarding the three input variables as a group of solutions of a three-dimensional space, and setting the dimension of the particle swarm as the number of the input variables;
and 4, step 4: preliminarily determining a group of solutions according to a Z-N setting method, preliminarily determining the possible ranges of three parameters in the group of solutions, setting PSO algorithm parameters, initializing the particle swarm size, the dimension, the maximum iteration times, the initial particle position and velocity, the minimum value and the maximum value of position coordinates, the minimum value and the maximum value of velocity scale and the control index precision;
and 5: guiding a group of preliminarily obtained solutions by using a fitness function combining prior knowledge and traditional performance integration;
step 6: and (3) carrying out particle velocity updating calculation according to a formula:
location update calculation:
in the formula (I), the compound is shown in the specification,
representing the velocity of the ith particle at the t-th iteration,
indicating the position of the ith particle at the time of the t-th iteration,
indicating the individual optima of the ith particle at the t-th iteration,
represents the global optimum at the t-th iteration, ω is the inertial weight, c1、c2For learning factor, it is generally 2, r1、r2Random numbers in the intervals (0,1) respectively;
and 7: calculating the respective fitness value of the particles according to the selected fitness function, obtaining the individual optimal fPbest and the global optimal fGbest in the evolution of the generation by using a self-adaptive change strategy containing a variation factor, comparing the individual optimal fPbest and the global optimal fGbest in the evolution of the generation with the fPbest and the fGbest of the previous generation, updating the individual optimal fPbest and the global optimal fGbest in the evolution of the generation, and recording the optimal solution of the generation;
and 8: judging a result, and if the ending condition is met, jumping out of the cycle; otherwise, repeating the steps (6) to (9);
and step 9: outputting a global optimal solution to obtain 3 optimal outer loop PID controller parameter values;
step 10: and observing the control result of the operation of the ball bar system, and judging that the ball is stabilized at the position of the cross bar by looking up the outer ring PID controller after algorithm optimization, wherein if the ball is stabilized at the designated position, the judgment is successful, and otherwise, the judgment is failed.
Preferably, the particle swarm initialization scale is 40, the dimension is 3, the maximum iteration number is 50, the initial particle position is set to be a solving value of a traditional Z-N integer method, the initial velocity is 0, the position coordinate is 0 and 80 at the minimum, the velocity scale is 4 and 4 at the minimum, and the control index precision is 0.0001.
Preferably, the POS algorithm is a nonlinear inertial weight, the inertial weight ω beingIterThe expression is as follows:
in the formula, ωMaxIs the maximum value of the inertial weight, ωMinIs the minimum value of the inertial weight, Iter represents the current iteration number, IterMaxRepresenting the maximum number of iterations。
Preferably, according to the inertial weight ωIterThe expression calculates the velocity formula of the particle:
preferably, the PSO algorithm includes an adaptive elite variation strategy with a variation factor, and based on a perturbation function of a standard cauchy distribution and key parameters of the club system, f (xm) is calculated:
in the formula, hc represents the Hill parameter and is defined as follows:
in the formula (I), the compound is shown in the specification,
is the average value of the ith particle in the jth dimension space at the Iter iteration,
thereafter, the optimum Pbest of all particles is calculatedjDistance r (j) from the mean to the j-th dimension:
obtaining an adaptive variation parameter xm (j):
finally, obtaining an updating formula of the adaptive change strategy of Gbest:
Gbest*＝Gbest+F(xm)
in the formula, Gbest represents a value of Gbest after being adjusted by variation.
Preferably, a new performance criterion is established according to the adaptive elite mutation strategy of the mutation factors:
in the formula, k1、k2、k3Setting the weighting factor to k as the weighting factor according to the structure of the club system and the specific experimental results1＝20、k2＝10、k3＝2。
Has the advantages that: the invention provides a priori knowledge-based particle swarm optimization method for a self-adaptive ball bar system, which adopts the idea of fusing the priori knowledge into an improved particle swarm optimization method, fully utilizes the result of each iteration of an algorithm, improves the interference coping capability of the ball bar system and the operation efficiency of the algorithm, and has the following advantages compared with the prior art:
1) the method is faster and more efficient, the control on the club system is more accurate, the solving precision can be rapidly improved, and the effect is more excellent;
2) the club system controller optimized by the algorithm has stronger robustness, stronger comprehensive adaptability, more appropriate transition process and improved self-adaptation level;
3) the PSO algorithm combined with the priori knowledge improves the anti-interference capability of the ball bar system, enhances the global search capability of the particles, reduces the possibility of falling into the local optimum and improves the convergence speed of the particles.
Drawings
FIG. 1 is a schematic flow chart of a prior knowledge-based particle swarm optimization method for an adaptive ball bar system.
Detailed Description
The invention is described below with reference to the accompanying drawings, which are intended to cover several modifications and embodiments of the invention. .
A particle swarm optimization method of a self-adaptive ball rod system based on prior knowledge is characterized in that a particle swarm algorithm is improved by improving nonlinear inertia weight, using a self-adaptive change strategy containing variation factors and combining a fitness function of the prior knowledge and traditional performance integration, an improved particle swarm optimization algorithm is used for finding a balance position for stabilizing the ball rod system, and the specific steps are as follows:
step 1: designing a proportional speed compensator, and controlling an internal motor control loop with small influence on the control effect of the club system according to the time domain requirement;
step 2: designing a PID controller of an outer ring ball arm control loop according to the ball arm system structure;
and step 3: three parameters K of outer ring PID controllerp,Ki,KdRespectively serving as three input variables, regarding the three input variables as a group of solutions of a three-dimensional space, and setting the dimension of the particle swarm as the number of the input variables;
and 4, step 4: preliminarily determining a group of solutions according to a Z-N setting method, preliminarily determining the possible ranges of three parameters in the group of solutions, setting PSO algorithm parameters, initializing the particle swarm size, the dimension, the maximum iteration times, the initial particle position and velocity, the minimum value and the maximum value of position coordinates, the minimum value and the maximum value of velocity scale and the control index precision;
and 5: guiding a group of preliminarily obtained solutions by using a fitness function combining prior knowledge and traditional performance integration;
step 6: and (3) carrying out particle velocity updating calculation according to a formula:
location update calculation:
in the formula (I), the compound is shown in the specification,
representing the velocity of the ith particle at the t-th iteration,
indicating the position of the ith particle at the time of the t-th iteration,
indicating the individual optima of the ith particle at the t-th iteration,
represents the global optimum at the t-th iteration, ω is the inertial weight, c1、c2For learning factor, it is generally 2, r1、r2Random numbers in the intervals (0,1) respectively;
and 7: calculating the respective fitness value of the particles according to the selected fitness function, obtaining the individual optimal fPbest and the global optimal fGbest in the evolution of the generation by using a self-adaptive change strategy containing a variation factor, comparing the individual optimal fPbest and the global optimal fGbest in the evolution of the generation with the fPbest and the fGbest of the previous generation, updating the individual optimal fPbest and the global optimal fGbest in the evolution of the generation, and recording the optimal solution of the generation;
and 8: judging a result, and if the ending condition is met, jumping out of the cycle; otherwise, repeating the steps (6) to (9);
and step 9: outputting a global optimal solution to obtain 3 optimal outer loop PID controller parameter values;
step 10: and observing the control result of the operation of the ball bar system, and judging that the ball is stabilized at the position of the cross bar by looking up the outer ring PID controller after algorithm optimization, wherein if the ball is stabilized at the designated position, the judgment is successful, and otherwise, the judgment is failed.
Preferably, the particle swarm initialization scale is 40, the dimension is 3, the maximum iteration number is 50, the initial particle position is set to be a solving value of a traditional Z-N integer method, the initial velocity is 0, the position coordinate is 0 and 80 at the minimum, the velocity scale is 4 and 4 at the minimum, and the control index precision is 0.0001.
Preferably, the POS algorithm is a nonlinear inertial weight, the inertial weight ω beingIterThe expression is as follows:
in the formula, ωMaxIs the maximum value of the inertial weight, ωMinIs the minimum value of the inertial weight, Iter represents the current iteration number, IterMaxThe maximum number of iterations is indicated.
Preferably, according to the inertial weight ωIterThe expression calculates the velocity formula of the particle:
preferably, the PSO algorithm includes an adaptive elite variation strategy with a variation factor, and based on a perturbation function of a standard cauchy distribution and key parameters of the club system, f (xm) is calculated:
in the formula, hc represents the Hill parameter and is defined as follows:
in the formula (I), the compound is shown in the specification,
is the average value of the ith particle in the jth dimension space at the Iter iteration,
thereafter, the optimum Pbest of all particles is calculatedjDistance r (j) from the mean to the j-th dimension:
obtaining an adaptive variation parameter xm (j):
finally, obtaining an updating formula of the adaptive change strategy of Gbest:
Gbest*＝Gbest+F(xm)
in the formula, Gbest represents a value of Gbest after being adjusted by variation.
Preferably, a new performance criterion is established according to the adaptive elite mutation strategy of the mutation factors:
in the formula, k1、k2、k3Setting the weighting factor to k as the weighting factor according to the structure of the club system and the specific experimental results1＝20、k2＝10、k3＝2。
The traditional inertia weight of the PSO algorithm is a fixed numerical value, in a nonlinear ball bar system, the balance of local search and global search of particles is broken possibly, so that the particles are trapped into local optimum early, in order to improve the overall optimizing capability of the system and reduce the possibility of trapping into the local optimum solution, the overall searching capability and the convergence speed of the particles are improved, the particles have stronger overall optimizing and local searching capabilities at the same time, and the overall performance of the PSO algorithm is improved.
In the practical ball arm problem, the influence of environmental factors such as voltage pulse, mechanical friction, sliding interference and the like can be caused, the complete disappearance of random interference can not be ensured, the adaptability of the traditional method for dealing with the interference is low, and the complicated ball arm system with unstable open loop can hardly deal with the interference to cause control failure.
In order to deal with the interferences, the ITAE is used as a part of the performance index, and the real-time overshoot, the rise time, the adjustment time and the peak time of the system are added, so that the performance parameters obtained in each iteration process of the system are utilized as fully as possible.
The search rate of the improved inertia weight can be adaptively changed along with the change of the iteration number in the inertia weight calculation. When the iteration times are small, the inertia weight is correspondingly large, and the particles can be effectively prevented from falling into local optimum; when the iteration times are larger, the inertia weight is correspondingly smaller, and the search accuracy can be better improved.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and decorations can be made without departing from the invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (6)
1. A particle swarm optimization method of a self-adaptive ball rod system based on prior knowledge is characterized in that a particle swarm algorithm is improved by improving nonlinear inertia weight, using a self-adaptive change strategy containing variation factors and combining a fitness function of the prior knowledge and traditional performance integration, a proportional integral derivative controller of the ball rod system is found by using the improved particle swarm optimization algorithm, and a balance position is found to enable the ball rod system to be stable, and the method specifically comprises the following steps:
step 1: designing a proportional speed compensator, and controlling an internal motor control loop with small influence on the control effect of the club system according to the time domain requirement;
step 2: designing a PID controller of an outer ring ball arm control loop according to the ball arm system structure;
and step 3: three parameters K of outer ring PID controllerp,Ki,KdRespectively serving as three input variables, regarding the three input variables as a group of solutions of a three-dimensional space, and setting the dimension of the particle swarm as the number of the input variables;
and 4, step 4: preliminarily determining a group of solutions according to a Z-N setting method, preliminarily determining the possible ranges of three parameters in the group of solutions, setting PSO algorithm parameters, initializing the particle swarm size, the dimension, the maximum iteration times, the initial particle position and velocity, the minimum value and the maximum value of position coordinates, the minimum value and the maximum value of velocity scale and the control index precision;
and 5: guiding a group of preliminarily obtained solutions by using a fitness function combining prior knowledge and traditional performance integration;
step 6: and (3) carrying out particle velocity updating calculation according to a formula:
location update calculation:
in the formula, Vi tRepresenting the velocity of the ith particle at the t-th iteration,
indicating the position of the ith particle at the time of the t-th iteration,
indicating the individual optima of the ith particle at the t-th iteration,
represents the global optimum at the t-th iteration, ω is the inertial weight, c1、c2For learning factor, it is generally 2, r1、r2Random numbers in the intervals (0,1) respectively;
and 7: calculating the respective fitness value of the particles according to the selected fitness function, obtaining the individual optimal fPbest and the global optimal fGbest in the evolution of the generation by using a self-adaptive change strategy containing a variation factor, comparing the individual optimal fPbest and the global optimal fGbest in the evolution of the generation with the fPbest and the fGbest of the previous generation, updating the individual optimal fPbest and the global optimal fGbest in the evolution of the generation, and recording the optimal solution of the generation;
and 8: judging a result, and if the ending condition is met, jumping out of the cycle; otherwise, repeating the steps (6) to (9);
and step 9: outputting a global optimal solution to obtain 3 optimal outer loop PID controller parameter values;
step 10: and observing the control result of the operation of the ball bar system, and judging that the ball is stabilized at the position of the cross bar by looking up the outer ring PID controller after algorithm optimization, wherein if the ball is stabilized at the designated position, the judgment is successful, and otherwise, the judgment is failed.
2. The method for optimizing the particle swarm of the adaptive ball bar system based on the priori knowledge is characterized in that the particle swarm is initialized to be 40 in scale, the dimension is 3, the maximum iteration number is 50, the initial position of the particle is set to be a solved value of a traditional Z-N integral method, the initial speed is 0, the position coordinate is 0 and 80 at minimum, the speed scale is-4 and 4 at maximum, and the control index precision is 0.0001.
3. The method for optimizing the particle swarm of the adaptive ball bar system based on the priori knowledge as claimed in claim 1, wherein the POS algorithm is a nonlinear inertial weight, and the inertial weight ω is an inertial weight ωIterThe expression is as follows:
in the formula, ωMaxIs the maximum value of the inertial weight, ωMinIs the minimum value of the inertial weight, Iter represents the current iteration number, IterMaxThe maximum number of iterations is indicated.
4. The POS algorithm of claim 3, wherein the inertial weight ω is based onIterCalculating the speed of the particle by expressionDegree formula:
5. the particle swarm optimization method for the adaptive club system based on the priori knowledge as claimed in claim 1, wherein the PSO algorithm comprises an adaptive elite variation strategy with variation factors, and f (xm) is calculated based on a perturbation function of a standard cauchy distribution and key parameters of the club system:
in the formula, hc represents the Hill parameter and is defined as follows:
in the formula (I), the compound is shown in the specification,
is the average value of the ith particle in the jth dimension space at the Iter iteration,
thereafter, the optimum Pbest of all particles is calculatedjDistance r (j) from the mean to the j-th dimension:
obtaining an adaptive variation parameter xm (j):
finally, obtaining an updating formula of the adaptive change strategy of Gbest:
Gbest*＝Gbest+F(xm)
in the formula, Gbest represents a value of Gbest after being adjusted by variation.
6. The adaptive elite mutation strategy according to claim 5, characterized in that new performance criteria are established according to the adaptive elite mutation strategy for mutation factors:
in the formula, k1、k2、k3Setting the weighting factor to k as the weighting factor according to the structure of the club system and the specific experimental results1＝20、k2＝10、k3＝2。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110219269.9A CN112987572B (en) | 2021-02-26 | 2021-02-26 | Particle swarm optimization method of adaptive ball bar system based on priori knowledge |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110219269.9A CN112987572B (en) | 2021-02-26 | 2021-02-26 | Particle swarm optimization method of adaptive ball bar system based on priori knowledge |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112987572A true CN112987572A (en) | 2021-06-18 |
| CN112987572B CN112987572B (en) | 2022-07-22 |
Family
ID=76351153
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110219269.9A Expired - Fee Related CN112987572B (en) | 2021-02-26 | 2021-02-26 | Particle swarm optimization method of adaptive ball bar system based on priori knowledge |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112987572B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114764413A (en) * | 2022-03-21 | 2022-07-19 | 中国电子科技集团公司第五十四研究所 | Self-adaptive engine system for interfering electromagnetic signals |
| CN114781499A (en) * | 2022-04-08 | 2022-07-22 | 上海人工智能创新中心 | Method for constructing ViT model-based intensive prediction task adapter |
| CN116880163A (en) * | 2023-09-07 | 2023-10-13 | 北京英沣特能源技术有限公司 | Intelligent data center cold source regulation and control method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203241748U (en) * | 2012-11-20 | 2013-10-16 | 北京石油化工学院 | Ball bar control device based on infrared sensors for range finding and servo steering engine |
| CN103809458A (en) * | 2014-03-04 | 2014-05-21 | 福州大学 | Magneto-rheological damping control method based on improved leapfrogging algorithm |
| US20140214742A1 (en) * | 2013-01-30 | 2014-07-31 | Harris Corporation | Distributed multi-layer particle swarm optimization based cognitive network |
| CN104897769A (en) * | 2015-06-02 | 2015-09-09 | 上海电力学院 | Magnetic flux leakage testing defect reconstruction method based on improved particle swarm optimization algorithm |
| CN105426954A (en) * | 2015-08-20 | 2016-03-23 | 武汉科技大学 | Particle swarm optimization method based on multi-strategy synergistic function |
| CN105589332A (en) * | 2016-01-20 | 2016-05-18 | 中国矿业大学 | Method for balancing ball-beam system based on SFLA fuzzy controller |
| CN111381600A (en) * | 2018-12-28 | 2020-07-07 | 陕西师范大学 | UUV path planning method based on particle swarm optimization |
| CN111582510A (en) * | 2020-05-13 | 2020-08-25 | 中国民用航空飞行学院 | Intelligent identification method and system based on support vector machine and civil aircraft engine |
-
2021
- 2021-02-26 CN CN202110219269.9A patent/CN112987572B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203241748U (en) * | 2012-11-20 | 2013-10-16 | 北京石油化工学院 | Ball bar control device based on infrared sensors for range finding and servo steering engine |
| US20140214742A1 (en) * | 2013-01-30 | 2014-07-31 | Harris Corporation | Distributed multi-layer particle swarm optimization based cognitive network |
| CN103809458A (en) * | 2014-03-04 | 2014-05-21 | 福州大学 | Magneto-rheological damping control method based on improved leapfrogging algorithm |
| CN104897769A (en) * | 2015-06-02 | 2015-09-09 | 上海电力学院 | Magnetic flux leakage testing defect reconstruction method based on improved particle swarm optimization algorithm |
| CN105426954A (en) * | 2015-08-20 | 2016-03-23 | 武汉科技大学 | Particle swarm optimization method based on multi-strategy synergistic function |
| CN105589332A (en) * | 2016-01-20 | 2016-05-18 | 中国矿业大学 | Method for balancing ball-beam system based on SFLA fuzzy controller |
| CN111381600A (en) * | 2018-12-28 | 2020-07-07 | 陕西师范大学 | UUV path planning method based on particle swarm optimization |
| CN111582510A (en) * | 2020-05-13 | 2020-08-25 | 中国民用航空飞行学院 | Intelligent identification method and system based on support vector machine and civil aircraft engine |
Non-Patent Citations (5)
| Title |
|---|
| LANLAN KANG等: "Uniform Opposition-Based Particle Swarm", 《2018 9TH INTERNATIONAL SYMPOSIUM ON PARALLEL ARCHITECTURES, ALGORITHMS AND PROGRAMMING (PAAP)》 * |
| YUNYI JIANG等: "Adaptive Control of Ball and Beam System Using Knowledge-Based Particle Swarm Optimization", 《2021 INTERNATIONAL CONFERENCE ON AUTOMATION, ROBOTICS AND APPLICATIONS》 * |
| ZHANG JH等: "A novel PSO algorithm based on an incremental-PID-controlled search strategy", 《METHODOLOGIES AND APPLICATION》 * |
| 李万等: "改进粒子群算法优化LSTM神经网络的铁路客运量预测", 《铁道科学与工程学报》 * |
| 葛双冶等: "基于改进CPSO的动态阴影环境下光伏MPPT仿真研究", 《电力系统保护与控制》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114764413A (en) * | 2022-03-21 | 2022-07-19 | 中国电子科技集团公司第五十四研究所 | Self-adaptive engine system for interfering electromagnetic signals |
| CN114781499A (en) * | 2022-04-08 | 2022-07-22 | 上海人工智能创新中心 | Method for constructing ViT model-based intensive prediction task adapter |
| CN114781499B (en) * | 2022-04-08 | 2024-05-31 | 上海人工智能创新中心 | Method for constructing ViT model-based intensive prediction task adapter |
| CN116880163A (en) * | 2023-09-07 | 2023-10-13 | 北京英沣特能源技术有限公司 | Intelligent data center cold source regulation and control method and system |
| CN116880163B (en) * | 2023-09-07 | 2023-12-05 | 北京英沣特能源技术有限公司 | Intelligent data center cold source regulation and control method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112987572B (en) | 2022-07-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112987572B (en) | Particle swarm optimization method of adaptive ball bar system based on priori knowledge | |
| CN110632922B (en) | Path planning method based on bat algorithm and reinforcement learning | |
| CN111222286A (en) | Parameter optimization method based on power transmission line state estimation | |
| CN112039391B (en) | Motor drive control system of high-voltage circuit breaker | |
| CN110531614B (en) | Novel brushless DC motor fuzzy neural network PI controller | |
| CN116520909A (en) | High-value consumable cabinet temperature control method for optimizing fuzzy PID parameters by Harris eagle algorithm | |
| CN111552183A (en) | Six-legged robot obstacle avoidance method based on adaptive weight reinforcement learning | |
| CN112012875B (en) | Optimization method of PID control parameters of water turbine regulating system | |
| CN113885328A (en) | Nuclear power tracking control method based on integral reinforcement learning | |
| CN116841207A (en) | Winding machine tension networked iteration learning control method based on machine learning optimization | |
| CN114696340A (en) | Wind power frequency modulation gradual inertia control method based on deep learning | |
| CN110361974B (en) | Water turbine speed regulating system optimization method based on BP-FOA hybrid algorithm | |
| CN118428441A (en) | PID control algorithm based on improved enhanced dung beetle algorithm and counter-propagating neural network mixed optimization | |
| Cai et al. | Solution of ackley function based on particle swarm optimization algorithm | |
| CN115618497A (en) | Aerofoil optimization design method based on deep reinforcement learning | |
| CN114611373A (en) | PSO improved algorithm based on variant sigmoid function and particle variation | |
| CN113792485A (en) | Simulated annealing particle swarm algorithm based on self-adaptive initial temperature setting | |
| CN113158131A (en) | Rockfall gradient optimization algorithm | |
| CN114167909B (en) | Main steam temperature linear active disturbance rejection cascade control method based on improved bacterial colony | |
| CN117826713B (en) | Improved reinforcement learning AGV path planning method | |
| CN118605648B (en) | Closed bus temperature monitoring management method combining hybrid optimization and fuzzy control | |
| CN117930662A (en) | Servo system parameter optimization calculation method based on MIMO-BRB-PSO | |
| CN118092195B (en) | Multi-agent cooperative control method for improving IQL based on cooperative training model | |
| CN115309051B (en) | Numerical control vertical lathe servo system and multi-mode multi-target self-optimizing control method thereof | |
| CN117724333A (en) | Flue gas oxygen content DMC+PID cascade control method based on improved hawk algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220722 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |