CN113051735B - Electromagnetic force linear characteristic optimization method for proportional electromagnet - Google Patents
Electromagnetic force linear characteristic optimization method for proportional electromagnet Download PDFInfo
- Publication number
- CN113051735B CN113051735B CN202110279684.3A CN202110279684A CN113051735B CN 113051735 B CN113051735 B CN 113051735B CN 202110279684 A CN202110279684 A CN 202110279684A CN 113051735 B CN113051735 B CN 113051735B
- Authority
- CN
- China
- Prior art keywords
- electromagnetic force
- proportional electromagnet
- optimization
- working
- design
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000013178 mathematical model Methods 0.000 claims abstract description 16
- 238000004088 simulation Methods 0.000 claims abstract description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000012417 linear regression Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000002790 cross-validation Methods 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 238000003050 experimental design method Methods 0.000 claims description 3
- 230000002068 genetic effect Effects 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01F—MAGNETS; INDUCTANCES; TRANSFORMERS; SELECTION OF MATERIALS FOR THEIR MAGNETIC PROPERTIES
- H01F7/00—Magnets
- H01F7/06—Electromagnets; Actuators including electromagnets
- H01F7/08—Electromagnets; Actuators including electromagnets with armatures
- H01F7/121—Guiding or setting position of armatures, e.g. retaining armatures in their end position
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Electromagnetism (AREA)
- Power Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Electromagnets (AREA)
Abstract
The invention discloses a method for optimizing electromagnetic force linear characteristics of a proportional electromagnet, and belongs to the field of optimal design of proportional electromagnets. The method comprises determining design parameters and constraint conditions, defining complex correlation coefficient between current and electromagnetic forceR 2 As an optimization target; then constructing a functional relation between the design parameters and the optimization targets; determining an electromagnetic force linear characteristic optimization mathematical model of the proportional electromagnet; and finally, solving an electromagnetic force linear characteristic optimization mathematical model of the proportional electromagnet to obtain an optimal design solution. The optimization method adopts a method combining numerical simulation and an approximation model, can optimize electromagnetic force linear characteristics of the proportional electromagnet with low cost and high efficiency, and is beneficial to improving product performance of the proportional electromagnet.
Description
Technical Field
The invention belongs to the field of optimization design of proportional electromagnets, and particularly relates to a method for optimizing electromagnetic force linear characteristics of proportional electromagnets.
Background
The electro-mechanical conversion device using the proportional electromagnet as the electro-hydraulic proportional control element is an automatic control element with very wide application, can enable the pressure and the flow of liquid flow to continuously and proportionally follow the control signal to change, and has the advantages of low cost, simple structure, good universality, strong pollution resistance and the like. In order to realize the proportional control characteristic of the proportional electromagnet, the electromagnetic force of the proportional electromagnet is required to have good linear characteristic, namely, the control current and the output electromagnetic force have good linear relation. The optimization of electromagnetic force linear characteristics of the proportional electromagnet at present often depends on experience of a designer, structural parameters are repeatedly modified, and a limited number of parameter combinations are arranged for experimental or numerical simulation analysis so as to select the parameter combination with the best performance, and the optimization efficiency and the optimization degree are low; on the other hand, the relation among the electromagnetic force linear characteristic performance target, constraint and design variable of the proportional electromagnet cannot be expressed explicitly, the optimization problem can be non-convex and strong non-linear, the global optimal solution is difficult to search for by optimizing based on system numerical simulation analysis, and meanwhile, the calculation and analysis cost is high, so that the improvement of the electromagnetic force linear characteristic of the proportional electromagnet faces a certain challenge.
Disclosure of Invention
In order to solve the problems, the invention provides an efficient and low-cost optimization method for electromagnetic force linear characteristics of a proportional electromagnet.
The purpose of the invention is realized in the following way:
a method for optimizing electromagnetic force linear characteristics of a proportional electromagnet comprises the following steps:
step 1, determining design parameters;
step 2, determining constraint conditions;
step 3, defining complex correlation coefficient R between current and electromagnetic force 2 As an optimization target;
step 4, constructing a functional relation between the design parameters and the optimization targets;
step 5, determining a proportional electromagnet electromagnetic force linear characteristic optimization mathematical model;
and step 6, solving a proportional electromagnet electromagnetic force linear characteristic optimization mathematical model to obtain an optimal design solution.
As a further illustration of the above optimization method:
further, setting the design parameters in step 1 includes:
cone angle alpha, cone radius r 1 Length of cone l 1 Radius r of skeleton 2 End face gap l when armature reaches maximum displacement 2 The design parameters of the electromagnetic force linear characteristic optimization problem of the proportional electromagnet are as follows:
X=(α,r 1 ,l 1 ,r 2 ,l 2 )。
further, the constraint condition in the step 2 is specifically a value range of each design parameter:
X l ≤X≤X u ;
X l to the lower limit of design parameters, X u Is the upper limit of the design parameters.
Further, in step 3, the complex correlation coefficient R between the current and the electromagnetic force 2 The specific calculation method comprises the following steps:
3.1 determining the operating current of the proportional electromagnet and the operating travel range of the armature, the operating range of the operating current being designated [ i ] a ,i d ]The working stroke of the armature is denoted as x a ,x d ]And equally dividing and dispersing the full working condition plane formed by the working current and the working stroke, thereby obtaining corresponding discrete working condition points (i) n ,x m ) Wherein i is n Represented as operating current i a ,i d ]Is equally divided into any working current and x m For working range of travel [ x ] a ,x d ]Any working stroke corresponding to the equal-divided discrete;
3.2, obtaining electromagnetic force corresponding to each discrete working point under the design parameter X through numerical simulation;
3.3 calculating the average force F (X, i) of the discrete working points with different working strokes and equal working currents under the design parameter X n ) a Obtaining a series of current and electromagnetic force linear regression sample points (i) n ,F(X,i n ) a ) Wherein
F (X, i) n ,x m ) Representing discrete operating points (i) under design parameter X n ,x m ) The corresponding electromagnetic force, f, represents the number of parts of the working stroke divided equally;
3.4 sample points (i) are obtained by least squares n ,F(X,i n ) a ) Performing linear regression to obtain complex correlation coefficient R 2 (X)。
Further, the specific method for constructing the functional relation between the design parameters and the optimization targets in the step 4 comprises the following steps:
4.1, sampling a design space by adopting an optimal Latin hypercube experimental design method to obtain a sample point set A;
4.2 obtaining electromagnetic force of each sample point in the sample point set A corresponding to the discrete working condition point through numerical simulation, and further calculating to obtain a corresponding complex correlation coefficient R 2 Forming a response point set B;
4.3 respectively adopting radial basis function model, neural network model, kriging model and quadratic polynomial model to interpolate or fit the data using sample point set A and response point set B as sample so as to construct design parameter X and complex correlation coefficient R 2 The function relation between the two is selected by a Leave-one-out cross-validation (LOOCV) method, and the approximation model with the highest precision is selected as the final function relation, namely the function relation R between the design parameters and the optimization targets 2 (X)。
Further, in the step 5, the linear characteristic optimization mathematical model of the proportional electromagnet is expressed as follows:
further, in the step 6, solving a linear characteristic optimization mathematical model of electromagnetic force of the proportional electromagnet to obtain an optimal design solution specifically as follows:
solving a proportional electromagnet electromagnetic force linear characteristic optimization mathematical model by adopting a genetic algorithm, an ant colony algorithm or other optimization algorithms, and taking the maximum R 2 And (X) corresponding to X is taken as an optimal design solution.
The invention has the advantages that: the invention relates to a method for optimizing electromagnetic force linear characteristics of a proportional electromagnet, which adopts a method combining numerical simulation and an approximate model and uses a complex correlation coefficient R between current and electromagnetic force 2 As an optimization target, a functional relation between a design variable and the optimization target is constructed based on an approximation model, a complex numerical simulation model or a physical test is replaced, electromagnetic force linear characteristics of the proportional electromagnet can be optimized with low cost and high efficiency, and the product performance of the proportional electromagnet can be improved.
Drawings
FIG. 1 is a flow chart of the invention;
FIG. 2 is a schematic diagram of design parameters;
FIG. 3 is a schematic diagram of the full operating mode of the proportional electromagnet.
Detailed Description
An embodiment is described in detail with reference to fig. 1, and the specific embodiment of the method for optimizing electromagnetic force linear characteristics of a proportional electromagnet according to this embodiment is as follows.
Step one, determining design parameters
The design parameters mainly comprise: cone angle alpha, cone radius r 1 Length of cone l 1 Radius r of skeleton 2 End face gap l when armature reaches maximum displacement 2 As shown in fig. 2, the design parameters of the electromagnetic force linear characteristic optimization problem of the proportional electromagnet are as follows
X=(α,r 1 ,l 1 ,r 2 ,l 2 )。
Step two, determining constraint conditions
The constraint is specifically the range of values of the design parameters, i.e
X l ≤X≤X u ;
Wherein X is l To the lower limit of design parameters, X u Is the upper limit of the design parameters.
Step three, defining currentComplex correlation coefficient R between electromagnetic forces 2 As an optimization target
Complex correlation coefficient R between current and electromagnetic force 2 The specific calculation method comprises the following steps:
3.1 determining the operating current of the proportional electromagnet and the operating travel range of the armature, the operating range of the operating current being designated [ i ] a ,i d ]The working stroke of the armature is denoted as x a ,x d ]And equally dividing and dispersing the full working condition plane formed by the working current and the working stroke, thereby obtaining corresponding discrete working condition points (i) n ,x m ) Wherein i is n Represented as operating current i a ,i d ]Is equally divided into any working current and x m For working range of travel [ x ] a ,x d ]Any corresponding working stroke is equally divided and dispersed, as shown in figure 3;
3.2, obtaining electromagnetic force corresponding to each discrete working point under the design parameter X through numerical simulation;
3.3 calculating the average force F (X, i) of the discrete working points with different working strokes and equal working currents under the design parameter X n ) a Obtaining a series of current and electromagnetic force linear regression sample points (i) n ,F(X,i n ) a ) Wherein
Wherein F (X, i) n ,x m ) Representing discrete operating points (i) under design parameter X n ,x m ) The corresponding electromagnetic force, f, represents the number of parts of the working stroke divided equally;
3.4 sample points (i) are obtained by least squares n ,F(X,i n ) a ) Performing linear regression to obtain complex correlation coefficient R 2 (X)。
Step four, constructing a functional relation between design parameters and optimization targets
4.1, sampling a design space by adopting an optimal Latin hypercube experimental design method to obtain a sample point set A;
4.2 obtaining electromagnetic force of each sample point in the sample point set A corresponding to the discrete working condition point through numerical simulation, and further calculating to obtain a corresponding complex correlation coefficient R 2 Forming a response point set B;
4.3 respectively adopting radial basis function model, neural network model, kriging model and quadratic polynomial model to interpolate or fit the data using sample point set A and response point set B as sample so as to construct design parameter X and complex correlation coefficient R 2 The function relation between the two is selected by a leave-one-out cross-validation (LOOCV) method, and the approximation model with the highest precision is selected as the final function relation, namely the function relation R between the design parameters and the optimization targets 2 (X)。
Step five, determining a proportional electromagnet electromagnetic force linear characteristic optimization mathematical model
The electromagnetic force linear characteristic optimization mathematical model of the proportional electromagnet is specifically expressed as follows:
and step six, solving a proportional electromagnet electromagnetic force linear characteristic optimization mathematical model to obtain an optimization design solution.
Solving a proportional electromagnet electromagnetic force linear characteristic optimization mathematical model by adopting a genetic algorithm, an ant colony algorithm or other optimization algorithms, and taking the maximum R 2 And (X) corresponding to X is taken as an optimal design solution.
The present invention is capable of other and further embodiments and its several details are capable of modification and variation in light of the present invention, as will be apparent to those skilled in the art, without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (3)
1. The electromagnetic force linear characteristic optimization method of the proportional electromagnet is characterized by comprising the following steps of:
step 1, determining design parameters;
step 2, determining constraint conditions;
step 3, defining complex correlation coefficient R between current and electromagnetic force 2 As an optimization target;
step 4, constructing a functional relation between the design parameters and the optimization targets;
step 5, determining a proportional electromagnet electromagnetic force linear characteristic optimization mathematical model;
step 6, solving a proportional electromagnet electromagnetic force linear characteristic optimization mathematical model to obtain an optimization design solution;
the constraint condition in the step 2 is specifically the value range of each design parameter, namely
X l ≤X≤X u ,
Wherein X is a design parameter, X l To the lower limit of design parameters, X u Is the upper limit of the design parameters;
the complex correlation coefficient R between the current and the electromagnetic force in the step 3 2 The specific calculation method comprises the following steps:
3.1 determining the operating current of the proportional electromagnet and the operating travel range of the armature, the operating range of the operating current being designated [ i ] a ,i d ]The working stroke of the armature is denoted as x a ,x d ]And equally dividing and dispersing the full working condition plane formed by the working current and the working stroke, thereby obtaining corresponding discrete working condition points (i) n ,x m ) Wherein i is n Represented as operating current i a ,i d ]Is equally divided into any working current and x m For working range of travel [ x ] a ,x d ]Any working stroke corresponding to the equal-divided discrete;
3.2, obtaining electromagnetic force corresponding to each discrete working point under the design parameter X through numerical simulation;
3.3 calculating the average force F (X, i) of the discrete working points with different working strokes and equal working currents under the design parameter X n ) a Obtaining a series of current and electromagnetic force linear regression sample points (i) n ,F(X,i n ) a ) Wherein
Wherein F (X, i) n ,x m ) Representing discrete operating points (i) under design parameter X n ,x m ) The corresponding electromagnetic force, f, represents the number of parts of the working stroke divided equally;
3.4 sample points (i) are obtained by least squares n ,F(X,i n ) a ) Performing linear regression to obtain complex correlation coefficient R 2 (X);
The specific method for constructing the functional relation between the design parameters and the optimization targets in the step 4 is as follows:
4.1, sampling a design space by adopting an optimal Latin hypercube experimental design method to obtain a sample point set A;
4.2 obtaining electromagnetic force of each sample point in the sample point set A corresponding to the discrete working condition point through numerical simulation, and further calculating to obtain a corresponding complex correlation coefficient R 2 Forming a response point set B;
4.3 respectively adopting radial basis function model, neural network model, kriging model and quadratic polynomial model to interpolate or fit the data using sample point set A and response point set B as sample so as to construct design parameter X and complex correlation coefficient R 2 The function relation between the two is selected by a Leave-one-out cross-validation (LOOCV) method, and the approximation model with the highest precision is selected as the function relation R between the design parameters and the optimization targets 2 (X);
In the step 5, the linear characteristic optimization mathematical model of the proportional electromagnet is expressed as follows:
2. the method for optimizing electromagnetic force linear characteristics of proportional electromagnet according to claim 1, wherein the design parameters in step 1 include: cone angle alpha, cone radius r 1 Length of cone l 1 Radius r of skeleton 2 End face gap l when armature reaches maximum displacement 2 The design parameters of the electromagnetic force linear characteristic optimization problem of the proportional electromagnet are as follows
X=(α,r 1 ,l 1 ,r 2 ,l 2 )。
3. The method for optimizing the electromagnetic force linear characteristics of the proportional electromagnet according to claim 1, wherein the step 6 is characterized in that the method for solving the mathematical model for optimizing the electromagnetic force linear characteristics of the proportional electromagnet is as follows: adopting genetic algorithm, ant colony algorithm or other optimization algorithm to solve electromagnetic force horizontal characteristic optimization mathematical model of proportional electromagnet, and taking maximum R 2 And (X) corresponding to X is taken as an optimal design solution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110279684.3A CN113051735B (en) | 2021-03-16 | 2021-03-16 | Electromagnetic force linear characteristic optimization method for proportional electromagnet |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110279684.3A CN113051735B (en) | 2021-03-16 | 2021-03-16 | Electromagnetic force linear characteristic optimization method for proportional electromagnet |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113051735A CN113051735A (en) | 2021-06-29 |
CN113051735B true CN113051735B (en) | 2024-01-26 |
Family
ID=76512838
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110279684.3A Active CN113051735B (en) | 2021-03-16 | 2021-03-16 | Electromagnetic force linear characteristic optimization method for proportional electromagnet |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113051735B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113051734B (en) * | 2021-03-16 | 2024-02-13 | 长沙理工大学 | Electromagnetic force average variation coefficient-based electromagnetic force horizontal characteristic optimization method for proportional electromagnet |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106250658A (en) * | 2016-08-29 | 2016-12-21 | 国网冀北电力有限公司电力科学研究院 | On-load switch electromagnetic mechanism quick calculation method based on RBF |
CN107016142A (en) * | 2016-03-18 | 2017-08-04 | 哈尔滨工业大学 | Electromagnetic relay quick calculation method based on Kriging models |
CN110399668A (en) * | 2019-07-17 | 2019-11-01 | 西安工业大学 | A method of rapidly and accurately solving calutron output characteristics |
CN110442931A (en) * | 2019-07-19 | 2019-11-12 | 兰州理工大学 | A kind of motor multi-objective optimization design of power method based on RSM |
-
2021
- 2021-03-16 CN CN202110279684.3A patent/CN113051735B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107016142A (en) * | 2016-03-18 | 2017-08-04 | 哈尔滨工业大学 | Electromagnetic relay quick calculation method based on Kriging models |
CN106250658A (en) * | 2016-08-29 | 2016-12-21 | 国网冀北电力有限公司电力科学研究院 | On-load switch electromagnetic mechanism quick calculation method based on RBF |
CN110399668A (en) * | 2019-07-17 | 2019-11-01 | 西安工业大学 | A method of rapidly and accurately solving calutron output characteristics |
CN110442931A (en) * | 2019-07-19 | 2019-11-12 | 兰州理工大学 | A kind of motor multi-objective optimization design of power method based on RSM |
Non-Patent Citations (3)
Title |
---|
Research on Key Factors and Their Interaction Effects of Electromagnetic Force of High-Speed Solenoid Valve;Peng Liu 等;《the Scientific World Journal》;1-14 * |
高速电磁阀电磁力全工况关键参数相关性分析;范立云 等;《农业工程学报》;第31卷(第6期);89-96 * |
高速电磁阀电磁力近似模型的构建与分析;刘鹏 等;《农业工程学报》;第31卷(第6期);96-101 * |
Also Published As
Publication number | Publication date |
---|---|
CN113051735A (en) | 2021-06-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113051735B (en) | Electromagnetic force linear characteristic optimization method for proportional electromagnet | |
CN109460629A (en) | A kind of cooling fan performance optimization method based on approximate model method | |
CN110414114B (en) | Multi-objective multi-parameter optimization design method for U-shaped ground heat exchanger | |
CN105574586B (en) | General-purpose aircraft boat material needing forecasting method based on MPSO-BP networks | |
CN115758891B (en) | Airfoil flow field prediction method based on converter decoder network | |
CN114926026B (en) | Target distribution optimization method for multi-dimensional feature deep learning | |
CN110162895A (en) | A kind of two stage high energy efficiency ship form optimization design method | |
CN112364560A (en) | Intelligent prediction method for working hours of mine rock drilling equipment | |
CN116484495A (en) | Pneumatic data fusion modeling method based on test design | |
CN113051734B (en) | Electromagnetic force average variation coefficient-based electromagnetic force horizontal characteristic optimization method for proportional electromagnet | |
CN109894495A (en) | A kind of extruder method for detecting abnormality and system based on energy consumption data and Bayesian network | |
CN112966389B (en) | Multi-objective optimization method for electromagnetic force horizontal characteristics of proportional electromagnet | |
CN108228977B (en) | Helicopter vibration characteristic conversion method based on flight state parameters | |
CN110245740A (en) | A kind of particle group optimizing method based on sequence near-optimal | |
CN116305574A (en) | Test design method based on neural network model | |
CN108446452A (en) | A kind of mixed-flow pump impeller Robust Optimal Design | |
CN113051736B (en) | Proportional electromagnet reset spring stiffness design method | |
CN103218493A (en) | Fast isogeometric analysis numerical simulation method based on multiple grids | |
Yang et al. | A novel adaptive gradient compression approach for communication-efficient Federated Learning | |
CN115334592A (en) | IoT user perception task unloading method based on quantum behavior particle swarm optimization strategy | |
Zhu et al. | Hybrid of genetic algorithm and simulated annealing for support vector regression optimization in rainfall forecasting | |
He et al. | An improved Fruit Fly Optimization Algorithm and its application in wet flue gas desulfurization system | |
Jin-Yue et al. | Research on the non-linear function fitting of RBF neural network | |
CN111274682A (en) | Digital microfluidic chip online test path optimization method based on frog-leaping algorithm | |
CN105068423B (en) | Method for realizing intelligent parameter identification of steam turbine and speed regulating system thereof by one key |
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 |