CN116383912A - Micro motor structure optimization method and system for improving control precision - Google Patents
Micro motor structure optimization method and system for improving control precision Download PDFInfo
- Publication number
- CN116383912A CN116383912A CN202310646274.7A CN202310646274A CN116383912A CN 116383912 A CN116383912 A CN 116383912A CN 202310646274 A CN202310646274 A CN 202310646274A CN 116383912 A CN116383912 A CN 116383912A
- Authority
- CN
- China
- Prior art keywords
- optimization
- variable
- parameters
- preset
- parameter
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 228
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000013433 optimization analysis Methods 0.000 claims abstract description 20
- 230000008878 coupling Effects 0.000 claims description 37
- 238000010168 coupling process Methods 0.000 claims description 37
- 238000005859 coupling reaction Methods 0.000 claims description 37
- 238000012216 screening Methods 0.000 claims description 18
- 238000005315 distribution function Methods 0.000 claims description 9
- 230000006978 adaptation Effects 0.000 claims description 6
- 238000012106 screening analysis Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 11
- 238000004883 computer application Methods 0.000 abstract description 2
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 210000002569 neuron Anatomy 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
-
- 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
-
- 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
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Computer Hardware Design (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Electric Motors In General (AREA)
Abstract
The invention discloses a micro motor structure optimization method and a micro motor structure optimization system for improving control precision, and relates to the technical field of computer application, wherein the method comprises the following steps: obtaining M variable parameters based on a preset optimization variable, and extracting a first variable parameter; randomly generating an initial optimization parameter set of the first variable parameter, wherein the initial optimization parameter set comprises N parameters; carrying out weight assignment on the N parameters to obtain N coefficients, and carrying out optimization analysis on the N parameters by combining a preset optimization rule to obtain a first variable optimization decision; and adding the first variable optimization decision to a structural optimization scheme, and carrying out structural optimization on the miniature motor based on the structural optimization scheme. The technical problems that in the prior art, structural optimization accuracy aiming at a miniature motor is insufficient, and then structural optimization quality of the miniature motor is low are solved. The technical effects of improving the structural optimization accuracy, reliability and adaptability of the miniature motor and improving the structural optimization quality of the miniature motor are achieved.
Description
Technical Field
The invention relates to the technical field of computer application, in particular to a miniature motor structure optimization method and system for improving control precision.
Background
The miniature motor has small volume and capacity, and the output power is lower than hundreds of watts. With the wide application of the micro-motor, the structural optimization of the micro-motor is widely paid attention to. In the prior art, the structural optimization accuracy of the miniature motor is insufficient, and then the technical problem of low structural optimization quality of the miniature motor is caused. The research design of the method for optimizing the high-quality structure of the miniature motor has very important practical significance.
Disclosure of Invention
The application provides a micro motor structure optimization method and system for improving control precision. The technical problems that in the prior art, structural optimization accuracy aiming at a miniature motor is insufficient, and then structural optimization quality of the miniature motor is low are solved. The technical effects of improving the structural optimization accuracy, reliability and adaptability of the miniature motor and improving the structural optimization quality of the miniature motor are achieved.
In view of the above, the present application provides a method and a system for optimizing a micro motor structure for improving control accuracy.
In a first aspect, the present application provides a method for optimizing a micro-motor structure for improving control accuracy, where the method is applied to a micro-motor structure optimizing system for improving control accuracy, and the method includes: screening and analyzing structural parameters of the miniature motor to obtain preset optimization variables, wherein the preset optimization variables comprise M variables, and the integer of M is more than 6 and less than or equal to 10; acquiring actual variable parameters of the miniature motor based on the M variables to obtain M variable parameters, and extracting a first variable parameter in the M variable parameters; randomly generating an initial optimization parameter set of the first variable parameter, wherein the initial optimization parameter set comprises N parameters, and N is smaller than a first preset step number of the first variable parameter; carrying out weight assignment on the N parameters to obtain N coefficients, and carrying out optimization analysis on the N parameters by combining a preset optimization rule to obtain a first variable optimization decision; and adding the first variable optimization decision to a structural optimization scheme, and carrying out structural optimization on the miniature motor based on the structural optimization scheme.
In a second aspect, the present application further provides a micro-motor structure optimization system for improving control accuracy, wherein the system includes: the parameter screening analysis module is used for screening and analyzing structural parameters of the miniature motor to obtain preset optimization variables, wherein the preset optimization variables comprise M variables and integers, wherein M is more than 6 and less than or equal to 10; the variable parameter extraction module is used for acquiring actual variable parameters of the miniature motor based on the M variables to obtain M variable parameters and extracting a first variable parameter in the M variable parameters; the initial optimization parameter generation module is used for randomly generating an initial optimization parameter set of the first variable parameter, wherein the initial optimization parameter set comprises N parameters, and N is smaller than a first preset step number of the first variable parameter; the optimization analysis module is used for carrying out weight assignment on the N parameters to obtain N coefficients, and carrying out optimization analysis on the N parameters by combining a preset optimization rule to obtain a first variable optimization decision; the structure optimization module is used for adding the first variable optimization decision to a structure optimization scheme and carrying out structure optimization on the miniature motor based on the structure optimization scheme.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
obtaining a preset optimization variable by screening and analyzing structural parameters of the miniature motor; acquiring actual variable parameters of the miniature motor through a preset optimization variable to obtain M variable parameters, and extracting a first variable parameter in the M variable parameters; generating an initial optimization parameter set based on the first variable parameter; performing weight assignment on the initial optimization parameter set to obtain N coefficients, and performing optimization analysis on the N parameters by combining a preset optimization rule to obtain a first variable optimization decision; and adding the first variable optimization decision to a structural optimization scheme, and carrying out structural optimization on the miniature motor based on the structural optimization scheme. The technical effects of improving the structural optimization accuracy, reliability and adaptability of the miniature motor and improving the structural optimization quality of the miniature motor are achieved.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly described below. It is apparent that the figures in the following description relate only to some embodiments of the present disclosure and are not limiting of the present disclosure.
FIG. 1 is a schematic flow chart of a method for optimizing a micro motor structure for improving control accuracy;
FIG. 2 is a schematic flow chart of obtaining a predetermined optimization variable in a method for optimizing a micro-motor structure for improving control accuracy;
fig. 3 is a schematic structural diagram of a micro motor structure optimization system for improving control accuracy.
Reference numerals illustrate: the system comprises a parameter screening analysis module 11, a variable parameter extraction module 12, an initial optimization parameter generation module 13, an optimization analysis module 14 and a structure optimization module 15.
Detailed Description
The application provides a micro motor structure optimization method and system for improving control precision. The technical problems that in the prior art, structural optimization accuracy aiming at a miniature motor is insufficient, and then structural optimization quality of the miniature motor is low are solved. The technical effects of improving the structural optimization accuracy, reliability and adaptability of the miniature motor and improving the structural optimization quality of the miniature motor are achieved.
Example 1
Referring to fig. 1, the present application provides a method for optimizing a micro-motor structure for improving control accuracy, where the method is applied to a micro-motor structure optimizing system for improving control accuracy, and the method specifically includes the following steps:
step S100: screening and analyzing structural parameters of the miniature motor to obtain preset optimization variables, wherein the preset optimization variables comprise M variables, and the integer of M is more than 6 and less than or equal to 10;
further, as shown in fig. 2, step S100 of the present application further includes:
step S110: obtaining a structure variable set of the miniature motor, wherein the structure variable set comprises P structure variables, and P is an integer greater than 1;
step S120: randomly extracting a first structural variable and a second structural variable in the P structural variables;
step S130: performing coupling analysis on the first structural variable and the second structural variable to obtain a first coupling index;
step S140: if the first coupling index is smaller than a preset coupling threshold value, adding the first structural variable to a candidate optimization variable list;
step S150: and acquiring a preset optimizing channel threshold, and screening the candidate optimizing variable list based on the preset optimizing channel threshold to obtain the preset optimizing variable.
Specifically, based on the miniature motor, the structural variable collection is carried out, and the structural variable set is obtained. The set of structural variables includes P structural variables, and P is an integer greater than 1. For example, the P structural variables include a number of structural variables such as armature winding number, brush size parameter, armature outer diameter, stand height, armature length, etc. of the micro motor. And then, randomly selecting based on the P structural variables to obtain a first structural variable and a second structural variable, and performing coupling analysis on the first structural variable and the second structural variable to obtain a first coupling index. The first structural variable and the second structural variable are any two different structural variables in the P structural variables. The first coupling index is data information characterizing a correlation between the first and second structural variables. The greater the correlation between the first and second structural variables, the higher the corresponding first coupling index, the lower the independence of the first structural variable.
Illustratively, when the first and second structural variables are subjected to the coupling analysis, a big data query is performed based on the first and second structural variables, and a plurality of sets of construction data are obtained. Each set of construction data includes a first historical structure variable, a second historical structure variable, a first historical coupling index. The random 70% of the data information in the plurality of sets of build data is divided into training data sets. Random 30% of the data information in the plurality of sets of build data is divided into test data sets. Based on the BP neural network, cross-monitoring training is carried out on the training data set, and a coupling analysis model is obtained. And taking the test data set as input information, inputting the input information into the coupling analysis model, and updating parameters of the coupling analysis model through the test data set. The BP neural network is a multi-layer feedforward neural network trained according to an error back propagation algorithm. The BP neural network comprises an input layer, a plurality of layers of neurons and an output layer. The BP neural network can perform forward calculation and backward calculation. When calculating in the forward direction, the input information is processed layer by layer from the input layer through a plurality of layers of neurons and is turned to the output layer, and the state of each layer of neurons only affects the state of the next layer of neurons. If the expected output cannot be obtained at the output layer, the reverse calculation is carried out, the error signal is returned along the original connecting path, and the weight of each neuron is modified to minimize the error signal. The coupling analysis model comprises an input layer, an implicit layer and an output layer. And inputting the first structural variable and the second structural variable into a coupling analysis model, and performing coupling index matching on the first structural variable and the second structural variable through the coupling analysis model to obtain a first coupling index.
Further, a determination is made as to whether the first coupling index is less than a predetermined coupling threshold. If the first coupling index is less than the predetermined coupling threshold, the first structural variable is added to the candidate optimization variable list. And screening the candidate optimization variable list based on a preset optimization channel threshold to obtain a preset optimization variable. Wherein the predetermined coupling threshold comprises a predetermined coupling index threshold. The candidate optimization variable list includes a plurality of structural variables arranged in order of coupling index from small to large. And, the plurality of structural variables in the candidate optimization variable list are each less than a predetermined coupling threshold. The preset optimizing channel threshold comprises the maximum number of structural variables which can be optimized simultaneously by the micro motor structure optimizing system for improving the control precision. For example, the predetermined optimization channel threshold is M, an integer of 6 < M.ltoreq.10. The predetermined optimization variables then include the first M variables in the candidate optimization variable list. The technical effect of determining the preset optimization variable with lower coupling and higher independence by screening and analyzing the structural parameters of the miniature motor is achieved, so that the control precision of structural optimization of the miniature motor is improved.
Step S200: acquiring actual variable parameters of the miniature motor based on the M variables to obtain M variable parameters, and extracting a first variable parameter in the M variable parameters;
step S300: randomly generating an initial optimization parameter set of the first variable parameter, wherein the initial optimization parameter set comprises N parameters, and N is smaller than a first preset step number of the first variable parameter;
further, step S300 of the present application further includes:
step S310: respectively obtaining a first upper value limit and a first lower value limit of the first variable parameter;
step S320: and obtaining a first step of the first variable parameter, and combining the first upper value limit and the first lower value limit to obtain the first preset step number.
Specifically, parameter acquisition is performed on the micro motor according to M variables, and M variable parameters are obtained. The M variable parameters comprise actual variable parameters of M variables corresponding to the miniature motor. For example, the M variables include air gap length, magnet steel height, armature outer diameter, wire guide width, armature yoke height, unit height, armature length. The M variable parameters comprise an air gap length parameter, a magnetic steel height parameter, an armature outer diameter parameter, a wire width parameter, an armature yoke height parameter, a unit height parameter and an armature length parameter of the miniature motor.
Further, each of the M variable parameters is set as the first variable parameter, respectively. And acquiring big data based on the first variable parameters to obtain an initial optimized parameter set of the first variable parameters. The initial optimization parameter set comprises N parameters corresponding to the first variable parameters, and N is smaller than a first preset step number of the first variable parameters. That is, the initial optimization parameter set includes N historical parameters corresponding to the first variable parameter.
And when the first preset step number is determined, carrying out the most value inquiry based on the first variable parameter, and determining a first upper value limit and a first lower value limit. The first upper value limit is the maximum value of the first variable parameter. The first lower value limit is the minimum value of the first variable parameter. Then, a first step of the first variable parameter is determined based on the big data query. The first step is the structural accuracy value of the first variable parameter. And carrying out difference value calculation on the first upper limit and the first lower limit to obtain an upper limit-lower limit value difference, and outputting the ratio of the upper limit-lower limit value difference to the first step as a first preset step number. The method achieves the technical effects of determining the initial optimization parameter set of the first variable parameter and providing data support for the follow-up optimization analysis of the initial optimization parameter set.
Step S400: carrying out weight assignment on the N parameters to obtain N coefficients, and carrying out optimization analysis on the N parameters by combining a preset optimization rule to obtain a first variable optimization decision;
further, step S400 of the present application further includes:
step S410: extracting a preset optimization constraint in the preset optimization rule, wherein the preset optimization constraint refers to the control precision of the miniature motor;
specifically, the predetermined optimization rule includes a predetermined optimization constraint. The predetermined optimization constraint refers to the control accuracy of the micro-motor. The control accuracy includes control frequency and control error rate.
Step S420: and constructing an adaptability function according to the preset optimization constraint and the N coefficients, wherein the adaptability function is as follows:
wherein the said
Means that said first variable parameter +.>
Is said +.>
Refers to controlling the frequency, said +.>
Refers to controlling the error rate, said +.>
Means that the control frequency +.>
Weight of>
Means that the control error rate +.>
Weight of>
Refers to the +.>
A coefficient;
step S430: and screening the N parameters according to the fitness function to obtain the first variable optimization decision.
Further, step S430 of the present application further includes:
step S431: respectively obtaining N fitness of the N parameters according to the fitness function;
step S432: comparing the N fitness degrees and determining a maximum fitness degree and a minimum fitness degree;
step S433: acquiring a predetermined solution set expansion interval, wherein the predetermined solution set expansion interval comprises a maximum expansion interval and a minimum expansion interval;
specifically, the fitness calculation is performed on the N parameters based on the fitness function, and N fitness is determined. And carrying out the maximum screening based on the N fitness degrees, and determining the maximum fitness degree and the minimum fitness degree. Then, a preset solution set expansion interval is set, wherein the preset solution set expansion interval comprises a maximum expansion interval and a minimum expansion interval. The maximum expansion interval comprises the maximum expansion solution set number, the minimum expansion interval comprises the minimum expansion solution set number, and the specific maximum expansion solution set number and the minimum expansion solution set number can be set and determined according to actual conditions.
In the fitness function, the
Refers to the first variable parameter->
Is adapted to the degree of fit of the (a), i.e. the
N fitness for the N parameters of the output, said +.>
For the control frequency corresponding to the N parameters of the input, the
For N parameter pairs inputControl error rate of the response, said +.>
For the preset determined control frequency +.>
Weight of>
For the preset determined control error rate +.>
Weight of>
Refers to the +.>
And coefficients. The N coefficients are N parameter weight values corresponding to the N parameters obtained by carrying out weight assignment on the N parameters.
Step S434: constructing a solution set expansion constraint function according to the maximum fitness, the minimum fitness, the maximum expansion interval and the minimum expansion interval, wherein the solution set expansion constraint function is as follows:
wherein the said
Means +.>
An extended solution of the generation of the individual parameters, said +.>
Means that said first variable parameter +.>
Middle->
Adaptation of the individual parameters, said +.>
Refers to the maximum fitness, the
Means said minimum fitness, said ++>
Means said maximum expansion interval, said +.>
Means the minimum extension interval, the +.>
Is directed downward rounding;
step S435: performing solution set expansion on the N fitness values according to the solution set expansion constraint function to obtain N groups of solution set expansion results;
further, step S435 of the present application further includes:
step S4351: constructing a D-dimensional search space according to the preset optimization constraint, wherein the dimension of the D-dimensional search space is the same as the number of the preset optimization constraint, and the boundary value of the D-dimensional search space is the constraint assignment result of the preset optimization constraint;
step S4352: inputting the N parameters into the D-dimensional search space for distribution, and obtaining an initial distribution result of the initial optimization parameter set;
step S4353: acquiring an initial standard deviation, and constructing a solution set expansion distribution function according to the initial standard deviation, wherein the initial standard deviation is used for representing the maximum deviation degree of expansion parameters and initial parameters;
step S4354: traversing the initial distribution result based on a solution set expansion distribution function and the solution set expansion constraint function, and performing solution set expansion in the D-dimensional search space to obtain the N groups of solution set expansion results.
Specifically, a solution set expansion constraint function is constructed based on the maximum fitness, the minimum fitness, the maximum expansion interval, and the minimum expansion interval. In the solution set expansion constraint function, the
For the N parameters of the output +.>
An extended solution of the generation of the individual parameters, said +.>
For the first variable parameter entered +.>
Middle->
Adaptation of the individual parameters, said +.>
For maximum adaptation of the input, said +.>
For minimum fitness of the input, said +.>
For the maximum expansion interval of the input, said +.>
For the minimum extension interval of the input, said +.>
Is directed downward rounding.
Further, a D-dimensional search space is constructed based on predetermined optimization constraints. And inputting the N parameters into the D-dimensional search space for distribution, and obtaining an initial distribution result of the initial optimized parameter set. Then, a solution set expansion distribution function is constructed according to the initial standard deviation. Traversing the initial distribution result based on the solution set expansion distribution function and the solution set expansion constraint function, and performing solution set expansion in the D-dimension search space to obtain N groups of solution set expansion results. The dimension of the D-dimensional search space is the same as the number of the preset optimization constraints, and the boundary value of the D-dimensional search space is the constraint assignment result of the preset optimization constraints. The initial standard deviation is used for representing the maximum deviation degree between the expansion parameters and the initial parameters, and can be determined by self-adaptive setting.
The solution set expansion distribution function is:
wherein, the liquid crystal display device comprises a liquid crystal display device,
standard deviation at the time of expansion of the g generation; g is expansion algebra; />
Is the final standard deviation; />
Characterizing the maximum deviation degree of the extended solution and the initial solution for the initial standard deviation; />
The method is a custom maximum expansion algebra; w is a nonlinear adjustment factor, and can be determined according to self-adaptive setting of actual conditions; />
Is the standard deviation; />
Is->
The s-th expansion object of the initial solution is distributed in the D-dimensional search space; />
Characterization->
The maximum value of the number of the expansion solutions of the initial solution is a self-defined parameter; />
Characterization->
The minimum value of the number of the expansion solutions of the initial solution is the output value of the expansion constraint function of the solution set, and the expansion standard deviation of any generation is the same.
Step S436: and carrying out optimization analysis on the N groups of solution set expansion results and the N parameters to obtain the first variable optimization decision.
Further, step S436 of the present application further includes:
step S4361: taking the N groups of solution set expansion results and the N parameters as a first solution set, counting the total number of the first solution set, and recording the total number as a first iterative solution set number;
step S4362: acquiring a predetermined solution set threshold, and if the number of the first iterative solution sets is larger than the predetermined solution set threshold, sequencing the first solution sets to obtain a first solution set sequence;
step S4363: determining a first iterative solution based on the first solution set sequence;
step S4364: iterating the first iterative solution until a predetermined iteration number threshold is met, adding the iterative solution obtained therefrom to the first variable optimization decision.
Step S500: and adding the first variable optimization decision to a structural optimization scheme, and carrying out structural optimization on the miniature motor based on the structural optimization scheme.
Specifically, the N-group solution set expansion result and the N parameters are set as a first solution set, and the total number of the first solution sets is output as a first iterative solution set number. A determination is made as to whether the first iterative solution set number is greater than a predetermined solution set threshold. The predetermined solution set threshold comprises a predetermined iterative solution set number threshold. And if the number of the first iterative solution sets is larger than a preset solution set threshold, sequencing the first solution sets according to the fitness to obtain a first solution set sequence. The first solution set sequence is output as a first iterative solution. And repeatedly iterating the first iteration solution until the preset iteration number threshold is met, and adding the first iteration solution meeting the preset iteration number threshold to the first variable optimization decision. The predetermined iteration number threshold comprises a preset determined iteration number threshold. The first variable optimization decision includes a first iterative solution that satisfies a predetermined iteration number threshold. And then adding the first variable optimization decision to the structural optimization scheme, and carrying out structural optimization on the miniature motor according to the structural optimization scheme. The structural optimization reliability of the miniature motor is achieved, and the technical effect of structural optimization quality of the miniature motor is improved.
In summary, the micro motor structure optimization method for improving the control precision provided by the application has the following technical effects:
1. obtaining a preset optimization variable by screening and analyzing structural parameters of the miniature motor; acquiring actual variable parameters of the miniature motor through a preset optimization variable to obtain M variable parameters, and extracting a first variable parameter in the M variable parameters; generating an initial optimization parameter set based on the first variable parameter; performing weight assignment on the initial optimization parameter set to obtain N coefficients, and performing optimization analysis on the N parameters by combining a preset optimization rule to obtain a first variable optimization decision; and adding the first variable optimization decision to a structural optimization scheme, and carrying out structural optimization on the miniature motor based on the structural optimization scheme. The technical effects of improving the structural optimization accuracy, reliability and adaptability of the miniature motor and improving the structural optimization quality of the miniature motor are achieved.
2. The structure parameters of the miniature motor are screened and analyzed to determine the preset optimization variables with lower coupling and higher independence, so that the control precision of the structural optimization of the miniature motor is improved.
Example two
Based on the same inventive concept as the micro motor structure optimization method for improving the control precision in the foregoing embodiment, the invention also provides a micro motor structure optimization system for improving the control precision, referring to fig. 3, the system includes:
the parameter screening analysis module 11 is used for screening and analyzing structural parameters of the miniature motor to obtain preset optimization variables, wherein the preset optimization variables comprise M variables, and the integer of M is more than 6 and less than or equal to 10;
the variable parameter extraction module 12 is configured to acquire actual variable parameters of the micro motor based on the M variables, obtain M variable parameters, and extract a first variable parameter of the M variable parameters;
an initial optimization parameter generation module 13, where the initial optimization parameter generation module 13 is configured to randomly generate an initial optimization parameter set of the first variable parameter, where the initial optimization parameter set includes N parameters, and N is less than a first predetermined number of steps of the first variable parameter;
the optimization analysis module 14 is configured to perform weight assignment on the N parameters to obtain N coefficients, and perform optimization analysis on the N parameters in combination with a predetermined optimization rule to obtain a first variable optimization decision;
the structure optimization module 15 is configured to add the first variable optimization decision to a structure optimization scheme, and perform structure optimization on the micro motor based on the structure optimization scheme.
Further, the system further comprises:
the structure variable set acquisition module is used for acquiring a structure variable set of the miniature motor, wherein the structure variable set comprises P structure variables, and P is an integer greater than 1;
the structure variable determining module is used for randomly extracting a first structure variable and a second structure variable in the P structure variables;
the coupling analysis module is used for carrying out coupling analysis on the first structural variable and the second structural variable to obtain a first coupling index;
the first execution module is used for adding the first structural variable to a candidate optimization variable list if the first coupling index is smaller than a preset coupling threshold value;
the preset optimization variable determining module is used for acquiring a preset optimization channel threshold, and screening the candidate optimization variable list based on the preset optimization channel threshold to obtain the preset optimization variable.
Further, the system further comprises:
the second execution module is used for respectively acquiring a first upper value limit and a first lower value limit of the first variable parameter;
the first preset step number determining module is used for obtaining a first step of the first variable parameter and combining the first value upper limit and the first value lower limit to obtain the first preset step number.
Further, the system further comprises:
a predetermined optimization constraint obtaining module, configured to extract a predetermined optimization constraint in the predetermined optimization rule, where the predetermined optimization constraint refers to control accuracy of the micro motor;
the fitness function construction module is used for constructing a fitness function according to the preset optimization constraint and the N coefficients, wherein the fitness function is as follows:
wherein the said
Means that said first variable parameter +.>
Is said +.>
Refers to controlling the frequency, said +.>
Refers to controlling the error rate, said +.>
Means that the control frequency +.>
Weight of>
Means that the control error rate +.>
Weight of>
Refers to the +.>
A coefficient;
and the third execution module is used for screening the N parameters according to the fitness function to obtain the first variable optimization decision.
Further, the system further comprises:
the fitness determining module is used for respectively obtaining N fitness of the N parameters according to the fitness function;
the fitness comparison module is used for comparing the N fitness degrees and determining the maximum fitness degree and the minimum fitness degree;
the fourth execution module is used for acquiring a preset solution set expansion interval, wherein the preset solution set expansion interval comprises a maximum expansion interval and a minimum expansion interval;
the fifth execution module is configured to construct a solution set expansion constraint function according to the maximum fitness, the minimum fitness, the maximum expansion interval and the minimum expansion interval, where the solution set expansion constraint function is as follows:
wherein the said
Means +.>
An extended solution of the generation of the individual parameters, said +.>
Means that said first variable parameter +.>
Middle->
Adaptation of the individual parameters, said +.>
Refers to the maximum fitness, the
Means said minimum fitness, said ++>
Means said maximum expansion interval, said +.>
Means the minimum extension interval, the +.>
Is directed downward rounding;
the solution set expansion module is used for carrying out solution set expansion on the N adaptation degrees according to the solution set expansion constraint function to obtain N groups of solution set expansion results;
and the sixth execution module is used for carrying out optimization analysis on the N groups of solution set expansion results and the N parameters to obtain the first variable optimization decision.
Further, the system further comprises:
the seventh execution module is used for taking the N groups of solution set expansion results and the N parameters as a first solution set, counting the total number of the first solution set and recording the total number as a first iterative solution set number;
the first solution set sequence obtaining module is used for obtaining a preset solution set threshold, and if the number of the first iteration solution sets is larger than the preset solution set threshold, the first solution sets are ordered to obtain a first solution set sequence;
a first iterative solution determination module for determining a first iterative solution based on the first solution set sequence;
and an eighth execution module for iterating the first iterative solution until a predetermined iteration number threshold is met, adding the iterative solution obtained therefrom to the first variable optimization decision.
Further, the system further comprises:
the search space construction module is used for constructing a D-dimensional search space according to the preset optimization constraint, wherein the dimension of the D-dimensional search space is the same as the number of the preset optimization constraint, and the boundary value of the D-dimensional search space is the constraint assignment result of the preset optimization constraint;
the initial distribution result obtaining module is used for inputting the N parameters into the D-dimensional search space for distribution to obtain an initial distribution result of the initial optimization parameter set;
a ninth execution module, configured to obtain an initial standard deviation, and construct a solution set extended distribution function according to the initial standard deviation, where the initial standard deviation is used to characterize a maximum deviation degree between an extended parameter and an initial parameter;
and the tenth execution module is used for traversing the initial distribution result based on a solution set expansion distribution function and the solution set expansion constraint function, and carrying out solution set expansion in the D-dimensional search space to obtain the N groups of solution set expansion results.
The micro motor structure optimization system for improving the control precision provided by the embodiment of the invention can execute the micro motor structure optimization method for improving the control precision provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
All the included modules are only divided according to the functional logic, but are not limited to the above-mentioned division, so long as the corresponding functions can be realized; in addition, the specific names of the functional modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present invention.
The application provides a micro motor structure optimization method for improving control precision, wherein the method is applied to a micro motor structure optimization system for improving control precision, and the method comprises the following steps: obtaining a preset optimization variable by screening and analyzing structural parameters of the miniature motor; acquiring actual variable parameters of the miniature motor through a preset optimization variable to obtain M variable parameters, and extracting a first variable parameter in the M variable parameters; generating an initial optimization parameter set based on the first variable parameter; performing weight assignment on the initial optimization parameter set to obtain N coefficients, and performing optimization analysis on the N parameters by combining a preset optimization rule to obtain a first variable optimization decision; and adding the first variable optimization decision to a structural optimization scheme, and carrying out structural optimization on the miniature motor based on the structural optimization scheme. The technical problems that in the prior art, structural optimization accuracy aiming at a miniature motor is insufficient, and then structural optimization quality of the miniature motor is low are solved. The technical effects of improving the structural optimization accuracy, reliability and adaptability of the miniature motor and improving the structural optimization quality of the miniature motor are achieved.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (8)
1. The miniature motor structure optimization method for improving the control precision is characterized by comprising the following steps of:
screening and analyzing structural parameters of the miniature motor to obtain preset optimization variables, wherein the preset optimization variables comprise M variables, and the integer of M is more than 6 and less than or equal to 10;
acquiring actual variable parameters of the miniature motor based on the M variables to obtain M variable parameters, and extracting a first variable parameter in the M variable parameters;
randomly generating an initial optimization parameter set of the first variable parameter, wherein the initial optimization parameter set comprises N parameters, and N is smaller than a first preset step number of the first variable parameter;
carrying out weight assignment on the N parameters to obtain N coefficients, and carrying out optimization analysis on the N parameters by combining a preset optimization rule to obtain a first variable optimization decision;
and adding the first variable optimization decision to a structural optimization scheme, and carrying out structural optimization on the miniature motor based on the structural optimization scheme.
2. The method for optimizing a structure of a micro-machine according to claim 1, wherein the step of performing a screening analysis on the structural parameters of the micro-machine to obtain a predetermined optimization variable comprises:
obtaining a structure variable set of the miniature motor, wherein the structure variable set comprises P structure variables, and P is an integer greater than 1;
randomly extracting a first structural variable and a second structural variable in the P structural variables;
performing coupling analysis on the first structural variable and the second structural variable to obtain a first coupling index;
if the first coupling index is smaller than a preset coupling threshold value, adding the first structural variable to a candidate optimization variable list;
and acquiring a preset optimizing channel threshold, and screening the candidate optimizing variable list based on the preset optimizing channel threshold to obtain the preset optimizing variable.
3. The method of claim 1, wherein the randomly generating the initial optimized parameter set for the first variable parameter, wherein the initial optimized parameter set includes N parameters, N being less than a first predetermined number of steps for the first variable parameter, comprises:
respectively obtaining a first upper value limit and a first lower value limit of the first variable parameter;
and obtaining a first step of the first variable parameter, and combining the first upper value limit and the first lower value limit to obtain the first preset step number.
4. The method of claim 1, wherein the performing weight assignment on the N parameters to obtain N coefficients, and performing optimization analysis on the N parameters in combination with a predetermined optimization rule to obtain a first variable optimization decision, includes:
extracting a preset optimization constraint in the preset optimization rule, wherein the preset optimization constraint refers to the control precision of the miniature motor;
and constructing an adaptability function according to the preset optimization constraint and the N coefficients, wherein the adaptability function is as follows:
and screening the N parameters according to the fitness function to obtain the first variable optimization decision.
5. The method of claim 4, wherein the filtering the N parameters according to the fitness function to obtain the first variable optimization decision comprises:
respectively obtaining N fitness of the N parameters according to the fitness function;
comparing the N fitness degrees and determining a maximum fitness degree and a minimum fitness degree;
acquiring a predetermined solution set expansion interval, wherein the predetermined solution set expansion interval comprises a maximum expansion interval and a minimum expansion interval;
constructing a solution set expansion constraint function according to the maximum fitness, the minimum fitness, the maximum expansion interval and the minimum expansion interval, wherein the solution set expansion constraint function is as follows:
performing solution set expansion on the N fitness values according to the solution set expansion constraint function to obtain N groups of solution set expansion results;
and carrying out optimization analysis on the N groups of solution set expansion results and the N parameters to obtain the first variable optimization decision.
6. The method of claim 5, wherein performing an optimization analysis on the N sets of solution set expansion results and the N parameters to obtain the first variable optimization decision comprises:
taking the N groups of solution set expansion results and the N parameters as a first solution set, counting the total number of the first solution set, and recording the total number as a first iterative solution set number;
acquiring a predetermined solution set threshold, and if the number of the first iterative solution sets is larger than the predetermined solution set threshold, sequencing the first solution sets to obtain a first solution set sequence;
determining a first iterative solution based on the first solution set sequence;
iterating the first iterative solution until a predetermined iteration number threshold is met, adding the iterative solution obtained therefrom to the first variable optimization decision.
7. The method of claim 5, wherein performing solution set expansion on the N fitness values according to the solution set expansion constraint function to obtain N sets of solution set expansion results, comprises:
constructing a D-dimensional search space according to the preset optimization constraint, wherein the dimension of the D-dimensional search space is the same as the number of the preset optimization constraint, and the boundary value of the D-dimensional search space is the constraint assignment result of the preset optimization constraint;
inputting the N parameters into the D-dimensional search space for distribution, and obtaining an initial distribution result of the initial optimization parameter set;
acquiring an initial standard deviation, and constructing a solution set expansion distribution function according to the initial standard deviation, wherein the initial standard deviation is used for representing the maximum deviation degree of expansion parameters and initial parameters;
traversing the initial distribution result based on a solution set expansion distribution function and the solution set expansion constraint function, and performing solution set expansion in the D-dimensional search space to obtain the N groups of solution set expansion results.
8. A micro-machine structural optimization system for improving control accuracy, characterized in that it is adapted to perform the method of any one of claims 1 to 7, said system comprising:
the parameter screening analysis module is used for screening and analyzing structural parameters of the miniature motor to obtain preset optimization variables, wherein the preset optimization variables comprise M variables and integers, wherein M is more than 6 and less than or equal to 10;
the variable parameter extraction module is used for acquiring actual variable parameters of the miniature motor based on the M variables to obtain M variable parameters and extracting a first variable parameter in the M variable parameters;
the initial optimization parameter generation module is used for randomly generating an initial optimization parameter set of the first variable parameter, wherein the initial optimization parameter set comprises N parameters, and N is smaller than a first preset step number of the first variable parameter;
the optimization analysis module is used for carrying out weight assignment on the N parameters to obtain N coefficients, and carrying out optimization analysis on the N parameters by combining a preset optimization rule to obtain a first variable optimization decision;
the structure optimization module is used for adding the first variable optimization decision to a structure optimization scheme and carrying out structure optimization on the miniature motor based on the structure optimization scheme.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310646274.7A CN116383912B (en) | 2023-06-02 | 2023-06-02 | Micro motor structure optimization method and system for improving control precision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310646274.7A CN116383912B (en) | 2023-06-02 | 2023-06-02 | Micro motor structure optimization method and system for improving control precision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116383912A true CN116383912A (en) | 2023-07-04 |
| CN116383912B CN116383912B (en) | 2023-08-11 |
Family
ID=86971417
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310646274.7A Active CN116383912B (en) | 2023-06-02 | 2023-06-02 | Micro motor structure optimization method and system for improving control precision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116383912B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116822098A (en) * | 2023-08-18 | 2023-09-29 | 广州誉鑫精密部件有限公司 | Intelligent monitoring control method and system for welding |
| CN117085284A (en) * | 2023-07-19 | 2023-11-21 | 国网辽宁省电力有限公司电力科学研究院 | Pneumatic oil-discharging nitrogen-injecting fire-extinguishing parameter regulation and control method and system based on environment monitoring |
| CN117350598A (en) * | 2023-11-16 | 2024-01-05 | 张家港广大特材股份有限公司 | Gear steel process control method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002224621A (en) * | 2001-08-16 | 2002-08-13 | Kikai Yo | Structure for optimizing micro flat vibrating motor |
| CN104038135A (en) * | 2014-06-27 | 2014-09-10 | 沈阳工业大学 | Novel torque motor structure parameter optimization method |
| CN112600375A (en) * | 2020-12-14 | 2021-04-02 | 东南大学 | Multi-objective optimization method of novel alternating-pole brushless hybrid excitation motor |
| CN114253157A (en) * | 2021-12-21 | 2022-03-29 | 华中科技大学 | Motor multi-parameter optimization method and system based on second-order sensitivity analysis |
| CN114329809A (en) * | 2021-11-16 | 2022-04-12 | 上海电力大学 | Optimized modeling method and system for electro-magnetic doubly salient reluctance motor |
| CN116050603A (en) * | 2022-12-31 | 2023-05-02 | 华中科技大学 | Method and equipment for predicting and optimizing deformation of undercut tunnel based on hybrid intelligent method |
-
2023
- 2023-06-02 CN CN202310646274.7A patent/CN116383912B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002224621A (en) * | 2001-08-16 | 2002-08-13 | Kikai Yo | Structure for optimizing micro flat vibrating motor |
| CN104038135A (en) * | 2014-06-27 | 2014-09-10 | 沈阳工业大学 | Novel torque motor structure parameter optimization method |
| CN112600375A (en) * | 2020-12-14 | 2021-04-02 | 东南大学 | Multi-objective optimization method of novel alternating-pole brushless hybrid excitation motor |
| CN114329809A (en) * | 2021-11-16 | 2022-04-12 | 上海电力大学 | Optimized modeling method and system for electro-magnetic doubly salient reluctance motor |
| CN114253157A (en) * | 2021-12-21 | 2022-03-29 | 华中科技大学 | Motor multi-parameter optimization method and system based on second-order sensitivity analysis |
| CN116050603A (en) * | 2022-12-31 | 2023-05-02 | 华中科技大学 | Method and equipment for predicting and optimizing deformation of undercut tunnel based on hybrid intelligent method |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117085284A (en) * | 2023-07-19 | 2023-11-21 | 国网辽宁省电力有限公司电力科学研究院 | Pneumatic oil-discharging nitrogen-injecting fire-extinguishing parameter regulation and control method and system based on environment monitoring |
| CN117085284B (en) * | 2023-07-19 | 2024-04-05 | 国网辽宁省电力有限公司电力科学研究院 | Pneumatic oil-discharging nitrogen-injecting fire-extinguishing parameter regulation and control method and system based on environment monitoring |
| CN116822098A (en) * | 2023-08-18 | 2023-09-29 | 广州誉鑫精密部件有限公司 | Intelligent monitoring control method and system for welding |
| CN116822098B (en) * | 2023-08-18 | 2024-01-16 | 广州誉鑫精密部件有限公司 | Intelligent monitoring control method and system for welding |
| CN117350598A (en) * | 2023-11-16 | 2024-01-05 | 张家港广大特材股份有限公司 | Gear steel process control method and system |
| CN117350598B (en) * | 2023-11-16 | 2024-04-02 | 张家港广大特材股份有限公司 | Gear steel process control method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116383912B (en) | 2023-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116383912B (en) | Micro motor structure optimization method and system for improving control precision | |
| Knowles | ParEGO: A hybrid algorithm with on-line landscape approximation for expensive multiobjective optimization problems | |
| CN110929164A (en) | Interest point recommendation method based on user dynamic preference and attention mechanism | |
| CN112508243B (en) | Training method and device for multi-fault prediction network model of power information system | |
| CN109543693A (en) | Weak labeling data noise reduction method based on regularization label propagation | |
| CN114626585A (en) | Urban rail transit short-time passenger flow prediction method based on generation of countermeasure network | |
| Zhao et al. | A hybrid learning method for constructing compact rule-based fuzzy models | |
| CN114781688A (en) | Method, device, equipment and storage medium for identifying abnormal data of business expansion project | |
| Chen et al. | A new multiobjective evolutionary algorithm for community detection in dynamic complex networks | |
| Dror et al. | Modeling Uncertainty: an examination of stochastic theory, methods, and applications | |
| CN116993513A (en) | Financial wind control model interpretation method and device and computer equipment | |
| CN116993548A (en) | Incremental learning-based education training institution credit assessment method and system for LightGBM-SVM | |
| Zahoor et al. | Evolutionary computation technique for solving Riccati differential equation of arbitrary order | |
| CN116611911A (en) | Credit risk prediction method and device based on support vector machine | |
| CN115908909A (en) | Evolutionary neural architecture searching method and system based on Bayes convolutional neural network | |
| CN113761365B (en) | Data processing system for determining target information | |
| CN114581086A (en) | Phishing account detection method and system based on dynamic time sequence network | |
| Rashid et al. | Optimization of electromagnetic devices using computational intelligence techniques | |
| CN113656707A (en) | Financing product recommendation method, system, storage medium and equipment | |
| EP1223547B1 (en) | Method and device for network inference | |
| Qu et al. | Two-stage coevolution method for deep CNN: A case study in smart manufacturing | |
| Jin | Simulation-based retrospective optimization of stochastic systems: a family of algorithms | |
| CN116798521B (en) | Abnormality monitoring method and abnormality monitoring system for immune cell culture control system | |
| CN112508303B (en) | OD passenger flow prediction method, device, equipment and readable storage medium | |
| CN115630772B (en) | Comprehensive energy detection and distribution method, system, equipment and storage medium |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230921 Address after: 300452 No. 26, Bohai 33rd Road, Lingang Economic Zone, Binhai New Area, Tianjin Patentee after: HELI TECH ENERGY Co.,Ltd. Address before: 300000 902-b, building 5, No. 158, Xisan Road, Tianjin pilot free trade zone (Airport Economic Zone), Binhai New Area, Tianjin (trust No. 652 of Tianjin xinzhijia business secretary Co., Ltd.) Patentee before: Deep blue (Tianjin) Intelligent Manufacturing Co.,Ltd. |
|
| TR01 | Transfer of patent right |