CN112632723B - Water pump blade parameter acquisition method and device and electronic equipment - Google Patents

Water pump blade parameter acquisition method and device and electronic equipment Download PDF

Info

Publication number
CN112632723B
CN112632723B CN202011530393.9A CN202011530393A CN112632723B CN 112632723 B CN112632723 B CN 112632723B CN 202011530393 A CN202011530393 A CN 202011530393A CN 112632723 B CN112632723 B CN 112632723B
Authority
CN
China
Prior art keywords
parameter
current
combination
condition
value
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
Application number
CN202011530393.9A
Other languages
Chinese (zh)
Other versions
CN112632723A (en
Inventor
陶然
肖若富
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Agricultural University
Original Assignee
China Agricultural University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Agricultural University filed Critical China Agricultural University
Priority to CN202011530393.9A priority Critical patent/CN112632723B/en
Publication of CN112632723A publication Critical patent/CN112632723A/en
Application granted granted Critical
Publication of CN112632723B publication Critical patent/CN112632723B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • 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
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/10—Numerical modelling

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Geometry (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Mathematical Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Computational Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Evolutionary Computation (AREA)
  • Computer Hardware Design (AREA)
  • Mathematical Physics (AREA)
  • Educational Administration (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Algebra (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Control Of Non-Positive-Displacement Pumps (AREA)

Abstract

The application discloses a method and a device for acquiring parameters of a water pump blade and electronic equipment, wherein the method comprises the following steps: obtaining a current parameter set comprising a plurality of current parameter combinations, wherein each current parameter combination comprises parameter values of a plurality of water pump blade parameters; judging whether each current parameter combination in the current parameter set meets the parameter judgment conditions or not so as to obtain a first parameter combination meeting the parameter judgment conditions and a second parameter combination not meeting the parameter judgment conditions; searching for parameter values by taking the parameter value of each water pump blade parameter in the first parameter combination as a search point to obtain a third parameter combination corresponding to each first parameter combination and a fourth parameter combination corresponding to each second parameter combination; and combining the third parameter combination and the fourth parameter combination into a new current parameter set, and judging whether each current parameter combination meets the parameter judgment condition or not again until the search ending condition corresponding to the current parameter set is met.

Description

Water pump blade parameter acquisition method and device and electronic equipment
Technical Field
The present disclosure relates to the field of data processing technologies, and in particular, to a method and an apparatus for acquiring parameters of a water pump blade, and an electronic device.
Background
With the development of science and technology, the problem of optimizing the design of the parameters of the equipment in engineering design is more and more focused, and how to seek better parameter design to improve the performance of the equipment based on the original design is the important research point of students.
The hill climbing algorithm is a simpler and efficient optimization algorithm. Since the device parameters are typically multiple, the resulting parameter space is not simply a two-dimensional or three-dimensional space, but rather a more loaded multidimensional space. Therefore, when the hill climbing algorithm is currently applied to search the optimal solution for the parameters of the equipment, a search point is mainly set to 'climb the hill', namely an initial parameter is selected, and the optimal solution in the current round is selected after each round of searching in the hill climbing process until 'climbing to the top', namely the optimal solution is searched.
However, the scheme of setting a search point to climb a mountain to search for the optimal solution has the defect of low searching efficiency, so that the acquisition efficiency of the optimal solution of the equipment parameter is low.
Disclosure of Invention
In view of this, the application provides a method and a device for acquiring parameters of a water pump blade, and an electronic device, which are used for solving the technical problem in the prior art that the acquiring efficiency of an optimal solution of the parameters of the device is low.
For this reason, the application provides a method for obtaining parameters of a water pump blade, the method includes:
obtaining a current parameter set, wherein the current parameter set comprises a plurality of current parameter combinations, and each current parameter combination comprises parameter values of a plurality of water pump blade parameters;
judging whether each current parameter combination in the current parameter set meets corresponding parameter judgment conditions or not to obtain a first parameter combination meeting the parameter judgment conditions and a second parameter combination not meeting the parameter judgment conditions;
searching for parameter values by taking the parameter value of each water pump blade parameter in the first parameter combination as a search point to obtain a third parameter combination corresponding to each first parameter combination and/or obtain a fourth parameter combination corresponding to each second parameter combination;
and forming a new current parameter set by the third parameter set and the fourth parameter set, and returning to judge whether each current parameter set in the new current parameter set meets corresponding parameter judgment conditions or not again until the search ending condition corresponding to the current parameter set is met so as to obtain the parameter set meeting the corresponding parameter judgment condition in the current parameter set.
The above method, preferably, after combining the third parameter combination and the fourth parameter combination to form a new current parameter set, the method further includes:
updating the parameter determination conditions to obtain new parameter determination conditions, wherein the new parameter determination conditions correspond to the new current parameter set.
In the above method, preferably, the parameter determination condition at least includes any one or more of a pump lift threshold and a pump efficiency threshold;
wherein updating the parameter determination condition includes:
and updating the corresponding threshold value in the parameter judgment condition at least according to the water pump lift value and/or the water pump efficiency value corresponding to each first parameter combination.
In the above method, preferably, before returning to determining whether each of the current parameter combinations in the new current parameter set meets the corresponding parameter determination condition, the method further includes:
updating the current iteration times;
obtaining a termination probability value at least according to the current iteration times, wherein the termination probability value at least characterizes the probability of entering local optimal solution search;
returning to judge whether each current parameter combination in the new current parameter set meets corresponding parameter judging conditions or not under the condition that the termination probability value is smaller than a probability threshold value until the search ending condition corresponding to the current parameter set is met;
And ending the current flow under the condition that the termination probability value is larger than or equal to the probability threshold value, and returning to acquire the current parameter set again until the search ending condition corresponding to the current parameter set is met.
Preferably, the method, at least according to the current iteration number, obtains a termination probability value, including:
obtaining a termination probability value corresponding to the current iteration times by using a probability distribution function;
the probability distribution function is established at least based on a preset maximum iteration number, and takes the current iteration number as an independent variable and the termination probability value as an independent variable.
In the above method, preferably, the searching of the parameter values by using the parameter value of each water pump vane parameter in the first parameter combination as a search point is performed to obtain a third parameter combination corresponding to each first parameter combination, including:
and searching the parameter values in the neighborhood corresponding to the parameter values by taking the parameter value of each water pump blade parameter in the first parameter combination as a search point so as to obtain a third parameter combination corresponding to each first parameter combination.
The method, preferably, obtains a fourth parameter combination corresponding to each second parameter combination, including:
And randomly generating corresponding parameter values for each water pump blade parameter to obtain fourth parameter combinations, wherein each fourth parameter combination corresponds to one second parameter combination.
In the above method, preferably, the search end condition includes: the current iteration times are greater than or equal to the preset maximum iteration times, and/or the parameter values of the parameters of each water pump blade are processed.
The application also provides a device for acquiring parameters of the water pump blade, which comprises:
the system comprises a parameter obtaining unit, a parameter setting unit and a parameter setting unit, wherein the parameter obtaining unit is used for obtaining a current parameter set, the current parameter set comprises a plurality of current parameter combinations, and each current parameter combination comprises parameter values of a plurality of water pump blade parameters;
a condition judging unit, configured to judge whether each of the current parameter combinations in the current parameter set satisfies a corresponding parameter judging condition, so as to obtain a first parameter combination that satisfies the parameter judging condition and a second parameter combination that does not satisfy the parameter judging condition;
the combination processing unit is used for searching parameter values by taking the parameter value of each water pump blade parameter in the first parameter combination as a search point so as to obtain a third parameter combination corresponding to each first parameter combination and/or obtain a fourth parameter combination corresponding to each second parameter combination;
And the parameter updating unit is used for combining the third parameter combination and the fourth parameter combination into a new current parameter set, triggering the condition judging unit to judge whether each current parameter combination in the new current parameter set meets the corresponding parameter judging condition or not again until the search ending condition corresponding to the current parameter set is met, so as to obtain the parameter combination meeting the corresponding parameter judging condition in the current parameter set.
The application also provides an electronic device, comprising:
a memory for storing an application program and data generated by the operation of the application program;
a processor for executing the application program to realize:
obtaining a current parameter set, wherein the current parameter set comprises a plurality of current parameter combinations, and each current parameter combination comprises parameter values of a plurality of water pump blade parameters;
judging whether each current parameter combination in the current parameter set meets corresponding parameter judgment conditions or not to obtain a first parameter combination meeting the parameter judgment conditions and a second parameter combination not meeting the parameter judgment conditions;
Searching for parameter values by taking the parameter value of each water pump blade parameter in the first parameter combination as a search point to obtain a third parameter combination corresponding to each first parameter combination and/or obtain a fourth parameter combination corresponding to each second parameter combination;
and forming a new current parameter set by the third parameter set and the fourth parameter set, and returning to judge whether each current parameter set in the new current parameter set meets corresponding parameter judgment conditions or not again until the search ending condition corresponding to the current parameter set is met so as to obtain the parameter set meeting the corresponding parameter judgment condition in the current parameter set.
According to the method, the device and the electronic equipment for acquiring the parameters of the water pump blade, the parameter set comprising the plurality of parameter combinations is obtained, whether each parameter combination meets the corresponding parameter judgment conditions is judged in parallel, the corresponding parameter value is searched, and the parameter combination meeting the corresponding parameter judgment conditions can be obtained until the search ending conditions are met. Therefore, in the method, the device and the system, the multiple parameter combinations are judged and the parameter values are searched in parallel, so that the searching progress of the parameter values is quickened, and the searching efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for obtaining parameters of a water pump blade according to an embodiment of the present application;
FIG. 2 is an exemplary diagram of search ranges and neighborhood ranges for parameter values in an embodiment of the present application;
FIG. 3 is an exemplary diagram of parameter combinations in an embodiment of the present application;
fig. 4 to fig. 5 are respectively another flowchart of a method for obtaining parameters of a water pump blade according to the first embodiment of the present application;
fig. 6 is a schematic structural diagram of a device for obtaining parameters of a water pump blade according to a second embodiment of the present disclosure;
fig. 7 is another schematic structural diagram of a device for obtaining parameters of a water pump blade according to a second embodiment of the present disclosure;
fig. 8 is a schematic structural diagram of an electronic device according to a third embodiment of the present application;
FIG. 9 is a flowchart illustrating an example of an embodiment of the present application in a practical application;
Fig. 10 is an exemplary diagram of a relationship between the number of iterations and the termination probability in the embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
Referring to fig. 1, a flowchart of a method for obtaining parameters of a water pump blade according to an embodiment of the present application is provided, and the method may be applied to an electronic device capable of performing data processing, such as a computer or a server. The technical scheme in the embodiment is mainly used for improving the efficiency of acquiring the parameters of the water pump blade.
Specifically, the method in this embodiment may include the following steps:
step 101: a current set of parameters is obtained.
The current parameter set may include a plurality of current parameter combinations, and each current parameter combination includes parameter values of a plurality of water pump blade parameters.
The parameters of the water pump blade can be any multiple of parameters such as a blade front cover plate inlet mounting angle, a front cover plate outlet mounting angle, a front cover plate inlet wrap angle, a front cover plate outlet wrap angle, a rear cover plate inlet mounting angle, a rear cover plate outlet mounting angle, a rear cover plate inlet wrap angle, a rear cover plate outlet wrap angle and the like.
Specifically, in this embodiment, a plurality of parameter values may be obtained for each water pump blade parameter in a respective search range through a random algorithm, so as to form a plurality of current parameter combinations, where each current parameter combination includes a parameter value of each water pump blade parameter.
The search range of each water pump blade parameter may be understood as a parameter range between a maximum value and a minimum value of each water pump blade parameter, and in this embodiment, parameter values of corresponding water pump blade parameters are randomly generated within the search range, so as to obtain a current parameter combination, and a plurality of current parameter combinations obtained through multiple random generation form a current parameter set.
In a specific implementation, the parameter values of at least one water pump blade parameter are different among different current parameter combinations. Here, the current parameter set may be expressed as Fn (n=1, 2,3, etc.), where the maximum value N of N is the number of current parameter combinations in the current parameter set, where each current parameter set sentence in Fn includes a plurality of parameter values, each parameter value corresponds to one water pump blade parameter, and the parameter values of at least one water pump blade parameter between different current parameter combinations, such as F1 and F3, are different. While for each current parameter combination a corresponding water pump blade may be designed, which may be denoted as Rn (n=1, 2, 3).
Step 102: judging whether each current parameter combination in the current parameter set meets the corresponding parameter judgment condition or not so as to obtain a first parameter combination meeting the parameter judgment condition and a second parameter combination not meeting the parameter judgment condition.
The parameter optimization conditions in this embodiment may include one or more performance thresholds, where the performance thresholds represent minimum values on corresponding performance indexes when the water pump operates with parameter values of each water pump blade parameter in the current parameter combination, and based on this, the parameter judgment conditions in this embodiment may be: the performance value when the water pump operates according to the parameter value in the current parameter combination is greater than or equal to the corresponding performance threshold.
Based on this, in this embodiment, the performance value may be calculated by taking the parameter value in each current parameter combination as the parameter of the water pump blade during actual running, where the calculated performance value may be a value on one or more performance indexes, and then comparing the calculated performance value with the corresponding performance threshold, where the current parameter combination satisfies the corresponding parameter determination condition if the performance value is greater than or equal to the performance threshold, where the current parameter combination is recorded as the first parameter combination, and if the performance is less than the performance threshold, the current parameter combination does not satisfy the corresponding parameter determination condition, where the current parameter combination is recorded as the second parameter combination, thereby implementing the determination of the parameter determination condition.
Taking the performance threshold including the pump lift threshold and the pump efficiency threshold as an example, the parameter determination conditions in this embodiment are: the pump lift value of the pump when the pump operates according to the parameter value in the current parameter combination is greater than or equal to the pump lift threshold value, and the pump efficiency value of the pump when the pump operates according to the parameter value in the current parameter combination is greater than or equal to the pump efficiency threshold value. Based on this, in this embodiment, the calculation of the pump lift value and the water pump efficiency value is performed for each current parameter combination, specifically, the calculation may be performed through a numerical simulation algorithm, for example, the calculation of the pump lift value and the water pump efficiency value is performed for each R in Rn, where Hn and ηn represent the pump lift value and the water pump efficiency value respectively, based on this, the obtained pump lift value and the pump lift threshold corresponding to each current parameter combination are determined, and the obtained pump efficiency value and the water pump efficiency threshold corresponding to each current parameter combination are determined, so as to obtain a determination result whether each current parameter combination meets the parameter determination condition, and therefore, each current parameter combination is marked as the first parameter combination or the second parameter combination according to the determination result.
It should be noted that the number of the first parameter combinations may be any number between 0 and N, and the number of the second parameter combinations may be any number between 0 and Nn, but the sum of the number of the first parameter combinations and the number of the second parameter combinations is the same as the number of the current parameter combinations in the current parameter set.
That is, in step 102, all the current parameter combinations in the current parameter set may be denoted as the first parameter combination, all the current parameter combinations in the current parameter set may be denoted as the second parameter combination, some of the current parameter combinations may be denoted as the first parameter combination, and the remaining current parameter combinations may be denoted as the second parameter combination.
Step 103: and searching the parameter values by taking the parameter value of each water pump blade parameter in the first parameter combination as a search point so as to obtain a third parameter combination corresponding to each first parameter combination.
Because the first parameter set is a parameter set satisfying the corresponding parameter determination condition, it is indicated that the parameter value in the first parameter set may be the optimal solution of the parameter set or a parameter value close to the optimal solution of the parameter set, and based on this, in this embodiment, the parameter values in the first parameter set are respectively used as search points to search for parameter values, so that a possibly better parameter set, that is, a third parameter set, may be obtained.
In particular, in this embodiment, the parameter value in each first parameter combination may be used as a search point, and the search of the parameter value is performed in a search range corresponding to the parameter of the water pump blade to which the parameter value belongs, so as to obtain a third parameter combination corresponding to each first parameter combination.
In a further preferred implementation manner, in this embodiment, a neighborhood corresponding to each parameter value may be first determined in a search range corresponding to a water pump blade parameter to which each parameter value in each first parameter combination belongs, and may also be referred to as a neighborhood range. For example, the neighborhood range corresponding to the parameter value on the water pump blade parameter is 5% or 10% of the search range corresponding to the water pump blade parameter, as shown in fig. 2, based on this, when the parameter value search is performed in this embodiment, the parameter value of each water pump blade parameter in each first parameter combination may be used as a search point, and the search of the parameter value is performed in the neighborhood, i.e. the neighborhood range corresponding to the parameter value, so as to obtain the search value corresponding to each parameter value in each first parameter combination, and further form a corresponding third parameter combination. Therefore, the search amount is reduced through the search of the neighborhood range, the search progress is quickened, and the search efficiency is improved.
Step 104: a fourth parameter combination corresponding to each second parameter combination is obtained.
In this embodiment, the second parameter combinations are parameter combinations that do not satisfy the parameter determination conditions, that is, the water pump cannot achieve better performance under the second parameter combinations, so that each second parameter combination that does not satisfy the parameter determination conditions is discarded, and a corresponding fourth parameter combination is obtained.
Specifically, in this embodiment, a random algorithm may be used to perform random search for each second parameter combination in a search range corresponding to each water pump blade parameter, so as to obtain a parameter value, thereby forming a fourth parameter combination. In particular, reference may be made to the manner of obtaining the current parameter combinations in the current parameter set in step 101, for example, for each water pump blade parameter, a corresponding parameter value is randomly generated, for example, in a search range corresponding to the water pump blade parameter, so as to obtain fourth parameter combinations, where each fourth parameter combination corresponds to one second parameter combination, as shown in fig. 3.
Step 105: and (3) combining the third parameter combination and the fourth parameter combination into a new current parameter set, which can be represented by Tn (n=1, 2, 3.), returning to the re-execution step 102, and further judging whether each current parameter combination in the new current parameter set meets the corresponding parameter judgment condition or not until the search ending condition corresponding to the current parameter set is met, so as to obtain the parameter combination meeting the corresponding parameter judgment condition in the current parameter set.
Specifically, in this embodiment, after the parameter determination condition is determined in step 102, it may be determined whether the cable end condition is satisfied, if the search end condition is satisfied, the current processing flow may be directly ended, the solution in this embodiment is not further executed, and if the search end condition is not satisfied, the solution in this embodiment is continuously executed in a loop until the search end condition is satisfied.
And when the search ending condition is met, marking the parameter combination meeting the corresponding parameter judgment condition in the current parameter set as an optimal solution of the parameter combination.
It should be noted that, when the search end condition is satisfied, only one parameter combination satisfying the parameter determination condition may exist in the current parameter set, and only one optimal solution, that is, one global optimal solution, is present at this time; or, in the case that the search end condition is satisfied, there may be a plurality of parameter combinations satisfying the parameter determination condition in the current parameter set, where there are a plurality of optimal solutions, that is, a plurality of global optimal solutions; or, in the case that the search end condition is satisfied, there may not be a parameter combination satisfying the parameter determination condition in the current parameter set, where the first parameter combination that has been searched for the parameter value last time may be used as the optimal solution, and of course, the first parameter combination may be one or more, that is, one or more globally optimal solutions.
Specifically, the search end condition may include: the current iteration number is greater than or equal to the preset maximum iteration number, and/or the parameter value of each water pump blade parameter is processed.
The current iteration number may be updated after step 102 and before step 105 returns to step 102, where the current iteration number is actually the number of times of determining the parameter preference condition in this embodiment, and may also be the number of times of performing parameter value search and/or parameter combination acquisition after the parameter determination condition is determined. Based on this, the maximum iteration number is preconfigured in this embodiment, and when the current iteration number reaches the maximum iteration number, the iteration can be ended, and the parameter value search and the optimal solution judgment are not performed continuously.
In addition, the parameter value of each water pump blade parameter is processed to be: the parameter values in the search range corresponding to each water pump blade parameter are searched or obtained, and are subjected to judgment of the parameter judgment conditions. Based on this, in this embodiment, after a plurality of iterations, the parameter values in the search range corresponding to each water pump blade parameter are processed, and then it is determined that all the parameter values in the search range have undergone judgment of the parameter judgment condition, so that no iteration needs to be continued, and at this time, the iteration is ended.
According to the method for acquiring the parameters of the water pump blade, provided by the embodiment of the invention, the parameter set comprising the plurality of parameter combinations is obtained, and then whether each parameter combination meets the corresponding parameter judgment condition is judged in parallel, and the corresponding parameter value is searched until the search ending condition is met, so that the parameter combination meeting the corresponding parameter judgment condition can be obtained. Therefore, in the method, the device and the system, the multiple parameter combinations are judged and the parameter values are searched in parallel, so that the searching progress of the parameter values is quickened, and the searching efficiency is improved.
Further, in order to improve the accuracy of the optimal solution of the parameter combination, in this embodiment, the parameter determination condition is updated in each iteration, specifically, after the third parameter combination and the fourth parameter combination are combined into a new current parameter set in step 105, the embodiment may further include the following steps, as shown in fig. 4:
step 106: the parameter determination conditions are updated to obtain new parameter determination conditions.
Wherein the new parameter decision condition corresponds to the new current parameter set.
In a specific implementation, when the judgment of the parameter judgment condition is performed for the first time, that is, when the parameter judgment condition is iterated for the first time, the parameter judgment condition may be a preset condition, for example, the parameter judgment condition includes any one or more of a preset pump lift threshold value and a pump efficiency threshold value, and may specifically be: the water pump lift value when the water pump operates according to the parameter value in the current parameter combination is greater than or equal to a preset water pump lift threshold value, and/or the water pump efficiency value when the water pump operates according to the parameter value in the current parameter combination is greater than or equal to a preset water pump efficiency threshold value.
In the second iteration and subsequent iterations, which are the second determination of the parameter determination condition, the parameter determination condition is an updated condition, for example, the updated parameter determination condition includes any one or more of an updated pump lift threshold value and an updated pump efficiency threshold value, and specifically may be: the pump lift value when the pump operates according to the parameter value in the current parameter combination is greater than or equal to the updated pump lift threshold value, and/or the pump efficiency value when the pump operates according to the parameter value in the current parameter combination is greater than or equal to the updated pump efficiency threshold value.
Specifically, in the present embodiment, when updating the parameter determination conditions, the following manner may be specifically implemented:
and updating the corresponding threshold value in the parameter judgment condition at least according to the pump lift value and/or the pump efficiency value corresponding to each first parameter combination.
The first parameter combinations may include the first parameter combinations determined by the last parameter determination condition determination, and may also include all the first parameter combinations determined by each parameter determination condition determination.
That is, in this embodiment, the parameter determination conditions are updated according to the first parameter combinations that meet the parameter determination conditions determined in the historical iterations, specifically, the corresponding threshold values in the parameter determination conditions are updated by the pump lift value and/or the pump efficiency value calculated by numerical simulation for each of the first parameter combinations.
Specifically, in this embodiment, the water pump lift value and/or the water pump efficiency value calculated by each first parameter combination may be weighted and summed according to the weight value corresponding to each first parameter combination to update the corresponding threshold in the parameter determination condition. The weight value corresponding to each first parameter combination may be set according to a specific rule, where the weight value may be related to the current iteration number corresponding to the first parameter combination, for example, the weight value of the first parameter combination obtained in the first iteration is smaller than the weight value of the first parameter combination obtained in the second iteration. And the sum of the weight values corresponding to all the first parameter combinations is 1. In a specific implementation, the number of first parameter combinations participating in the updating of the parameter determination condition in each iteration may be varied, and thus the weight value corresponding to each first parameter combination may be varied in each iteration, but the sum of the weight values corresponding to all the first parameter combinations remains unchanged. For example, in the second iteration, the number of first parameter combinations obtained in the first iteration is 2, and at this time, the weight values corresponding to the two first parameter combinations are respectively 0.5; in the third iteration, the first parameter combinations obtained in the first iteration are 2, and the first parameter combinations obtained in the second iteration are 1, and at this time, the weight values corresponding to the three first parameter combinations are respectively: 0.25, 0.25 and 0.5, wherein the weight values corresponding to the 2 first parameter combinations obtained in the first iteration are changed from 0.5 to 0.25, and the weight values corresponding to the 1 first parameter combinations obtained in the second iteration are all 0.5, and although the weight values may be changed, the sum of the weight values corresponding to all the first parameter combinations is unchanged.
In one implementation, the parameter determination conditions are: when the pump is operated according to the parameter value in the current parameter combination and the pump lift value is greater than or equal to the pump lift threshold value, all the first parameter combinations determined when the parameter judgment condition is judged each time are obtained in the embodiment, and taking the current iteration number as the third iteration as an example, all the first parameter combinations determined when the parameter judgment condition is judged for the first time and the second time are obtained in the embodiment; then, respectively carrying out numerical simulation calculation on each first parameter combination to obtain water pump lift values corresponding to each first parameter combination, and then carrying out average value acquisition on the water pump lift values, wherein the weight value corresponding to each first parameter combination is the same and the sum of the weight values is 1, so that an updated water pump lift threshold value is obtained, and based on the updated water pump lift threshold value, the parameter judgment condition is updated as follows: the water pump is operated according to the parameter value in the current parameter combination, and the water pump lift value is greater than or equal to the updated water pump lift threshold value;
in another implementation, the parameter determination conditions are: when the water pump is operated according to the parameter value in the current parameter combination and the water pump efficiency value is greater than or equal to the water pump efficiency threshold, all the first parameter combinations determined when the parameter judgment condition is judged each time are obtained in the embodiment, and taking the current iteration number as the fourth iteration as an example, all the first parameter combinations determined when the parameter judgment condition is judged for the first time, the second time and the third time are obtained in the embodiment; then, respectively carrying out numerical simulation calculation on each first parameter combination to obtain water pump efficiency values corresponding to each first parameter combination, and then carrying out weighted summation on the water pump efficiency values according to the weight values corresponding to each first parameter combination, wherein at the moment, the weight values corresponding to each first parameter combination can be different but the sum of the weight values is 1, so that an updated water pump efficiency threshold value is obtained, and based on the updated water pump efficiency threshold value, the parameter judgment conditions are updated as follows: the water pump efficiency value when the water pump operates according to the parameter value in the current parameter combination is greater than or equal to the updated water pump efficiency threshold value;
In another implementation, the parameter determination conditions are: when the pump lift value of the pump is greater than or equal to the pump lift threshold value according to the parameter value in the current parameter combination and the pump efficiency value of the pump is greater than or equal to the pump efficiency threshold value according to the parameter value in the current parameter combination, all the first parameter combinations determined when the parameter judgment condition is judged each time are obtained in the embodiment, and taking the current iteration number as a second iteration as an example, all the first parameter combinations determined when the parameter judgment condition is judged for the first time are obtained in the embodiment; then, respectively carrying out numerical simulation calculation on each first parameter combination to obtain a water pump lift value and a water pump efficiency value corresponding to each first parameter combination, respectively carrying out weighted summation on the water pump lift value and the water pump efficiency value according to the weight value corresponding to each first parameter combination to obtain an updated water pump lift threshold value and an updated water pump efficiency threshold value, and updating the parameter judgment condition based on the updated water pump lift value and the updated water pump efficiency threshold value: the pump lift value of the pump when operated according to the parameter value in the current parameter combination is greater than or equal to the updated pump lift threshold value, and the pump efficiency value of the pump when operated according to the parameter value in the current parameter combination is greater than or equal to the updated pump efficiency threshold value.
Therefore, in this embodiment, the parameter determination conditions are iteratively updated according to the parameter combinations satisfying the parameter determination conditions in the historical iterations, that is, the parameter values considered as the optimized parameter combinations, so that the parameter determination conditions are continuously optimized along with the iterations, and further, the accuracy of the parameter combinations satisfying the parameter determination conditions screened out in each iteration is improved, and therefore, the accuracy of the parameter combinations satisfying the parameter determination conditions obtained when the search is finally finished is improved.
In one implementation, to avoid trapping in the locally optimal solution in this embodiment, before step 105 returns to step 102, the following steps may be further included in this embodiment, as shown in fig. 5:
step 107: updating the current iteration number.
In this embodiment, the current iteration number may be increased by 1, so as to implement updating of the current iteration number.
In the initial state, that is, when the judgment of the parameter judgment condition is not started, the initial current iteration number is 0, and each time the judgment of the parameter judgment condition is performed, that is, each time the judgment is returned to step 102, before the judgment is performed again, an update is performed, and each time the update is performed, the current iteration number is added by 1.
Step 108: and obtaining a termination probability value at least according to the current iteration times.
Wherein the termination probability value characterizes at least the probability of entering a locally optimal solution search.
In a specific implementation, in this embodiment, probability calculation may be performed according to the current iteration number to obtain the termination probability value.
For example, in this embodiment, a probability distribution function using the current iteration number as an independent variable and using the termination probability value as a dependent variable may be established, so as to obtain the termination probability value corresponding to the current iteration number by using the probability distribution function.
Wherein the probability distribution function is established based at least on a preset maximum number of iterations. For example, in this embodiment, after the probability distribution function is established, the values of the plurality of coefficients in the probability distribution function are configured according to the maximum iteration number, and then, after the updated current iteration number is used, the termination probability value is solved by using the probability distribution function, so as to obtain the termination probability value corresponding to the current iteration number.
It can be seen that the maximum number of iterations is different, the values of the coefficients in the probability distribution function are different, and the corresponding obtained termination probability values are different. After the maximum number of iterations is determined, the values of the coefficients in the probability distribution function are determined, based on which the resulting termination probability value of the probability distribution function is continuously changing with increasing number of current iterations in each iteration.
Specifically, the probability distribution function may be an exponential function, based on which the termination probability value obtained by the probability distribution function is continuously increased as the current iteration number increases.
For example, the probability distribution function is represented by the following formula (1):
wherein x is the current iteration number, a, b and c are coefficients in the probability distribution function respectively, specifically obtained through the maximum iteration number, and Y (x) is a termination probability value.
Based on this, in the case where the current iteration number is 0, 1, and 2, that is, in the previous three iterations, the termination probability value takes a value of 0, and then, as the iteration proceeds, the termination probability value grows exponentially with the increase of the current iteration number x, and when the current iteration number approaches infinity, the termination probability value obtained by the probability distribution function approaches 1.
Step 109: judging whether the termination probability value is smaller than a probability threshold value, if so, returning to the re-executing step 102 to judge whether each current parameter combination in the new current parameter set meets the corresponding parameter judging condition or not until the search ending condition corresponding to the current parameter set is met; if the termination probability value is greater than or equal to the probability threshold, the current flow is ended, and the re-execution step 101 is returned to re-acquire the current parameter set until the search end condition corresponding to the current parameter set is satisfied.
Therefore, in this embodiment, the stopping probability value that increases exponentially with the current iteration number avoids being trapped in the iteration loop of the locally optimal solution of the parameter combination, thereby improving the reliability of obtaining the optimal solution of the parameter combination.
Referring to fig. 6, a schematic structural diagram of a device for acquiring parameters of a water pump blade according to a second embodiment of the present application may be configured in an electronic device capable of performing data processing, such as a computer or a server. The technical scheme in the embodiment is mainly used for improving the efficiency of acquiring the parameters of the water pump blade.
Specifically, the apparatus in this embodiment may include the following units:
a parameter obtaining unit 601, configured to obtain a current parameter set, where the current parameter set includes a plurality of current parameter combinations, and each of the current parameter combinations includes parameter values of a plurality of water pump blade parameters;
a condition judging unit 602, configured to judge whether each of the current parameter combinations in the current parameter set satisfies a corresponding parameter judging condition, so as to obtain a first parameter combination that satisfies the parameter judging condition and a second parameter combination that does not satisfy the parameter judging condition;
A combination processing unit 603, configured to search for a parameter value with a parameter value of each water pump vane parameter in the first parameter combinations as a search point, so as to obtain a third parameter combination corresponding to each first parameter combination, and/or obtain a fourth parameter combination corresponding to each second parameter combination;
and a parameter updating unit 604, configured to combine the third parameter combination and the fourth parameter combination to form a new current parameter set, and trigger the condition determining unit to determine whether each current parameter combination in the new current parameter set meets a corresponding parameter determination condition again, until a search end condition corresponding to the current parameter set is met, so as to obtain a parameter combination in the current parameter set that meets the corresponding parameter determination condition.
As can be seen from the above-mentioned scheme, in the device for acquiring parameters of a water pump blade provided in the second embodiment of the present application, by acquiring a parameter set including a plurality of parameter combinations, further determining whether each parameter combination satisfies a corresponding parameter determination condition in parallel, and searching for a corresponding parameter value until a search end condition is satisfied, a parameter combination satisfying the corresponding parameter determination condition can be obtained. Therefore, in the method, the device and the system, the multiple parameter combinations are judged and the parameter values are searched in parallel, so that the searching progress of the parameter values is quickened, and the searching efficiency is improved.
In one implementation, after the parameter updating unit 604 combines the third parameter combination and the fourth parameter combination into a new current parameter set, the condition determining unit 602 is further configured to: updating the parameter determination conditions to obtain new parameter determination conditions, wherein the new parameter determination conditions correspond to the new current parameter set.
Optionally, the parameter determination condition at least comprises any one or more of a pump lift threshold value and a pump efficiency threshold value;
wherein, the condition judgment unit 602 is specifically configured to, when updating the parameter judgment condition: and updating the corresponding threshold value in the parameter judgment condition at least according to the water pump lift value and/or the water pump efficiency value corresponding to each first parameter combination.
In one implementation, the apparatus in this embodiment may further include the following units including, as shown in fig. 7:
a termination judging unit 605, configured to update the current iteration number before the parameter updating unit 604 judges whether each of the current parameter combinations in the new current parameter set satisfies a corresponding parameter judging condition by the retriggering condition judging unit 602; obtaining a termination probability value at least according to the current iteration times, wherein the termination probability value at least characterizes the probability of entering local optimal solution search; in the case that the termination probability value is smaller than the probability threshold value, the trigger condition judging unit 602 judges whether each current parameter combination in the new current parameter set meets the corresponding parameter judging condition again until the search ending condition corresponding to the current parameter set is met; and when the termination probability value is greater than or equal to the probability threshold value, ending the current flow, and triggering the parameter obtaining unit 601 to re-obtain the current parameter set until the search ending condition corresponding to the current parameter set is met.
Optionally, the termination judging unit 605 is specifically configured to, when obtaining the termination probability value at least according to the current iteration number: obtaining a termination probability value corresponding to the current iteration times by using a probability distribution function; the probability distribution function is established at least based on a preset maximum iteration number, and takes the current iteration number as an independent variable and the termination probability value as an independent variable.
Of course, the termination determination unit 605 is also configured to determine whether the search end condition is satisfied.
In one implementation manner, when the combination processing unit 603 searches for a parameter value with a parameter value of each water pump vane parameter in the first parameter combination as a search point to obtain a third parameter combination corresponding to each first parameter combination, the combination processing unit is specifically configured to: and searching the parameter values in the neighborhood corresponding to the parameter values by taking the parameter value of each water pump blade parameter in the first parameter combination as a search point so as to obtain a third parameter combination corresponding to each first parameter combination.
In one implementation manner, the combination processing unit 603 is specifically configured to, when obtaining the fourth parameter combination corresponding to each of the second parameter combinations: and randomly generating corresponding parameter values for each water pump blade parameter to obtain fourth parameter combinations, wherein each fourth parameter combination corresponds to one second parameter combination.
In one implementation, the search end condition includes: the current iteration times are greater than or equal to the preset maximum iteration times, and/or the parameter values of the parameters of each water pump blade are processed.
It should be noted that, the specific implementation of each unit in this embodiment may refer to the corresponding content in the foregoing, which is not described in detail herein.
Referring to fig. 8, a schematic structural diagram of an electronic device according to a third embodiment of the present application may be an electronic device capable of performing data processing, such as a computer or a server. The technical scheme in the embodiment is mainly used for improving the efficiency of acquiring the parameters of the water pump blade.
Specifically, the electronic device in this embodiment may include the following structure:
a memory 801 for storing an application program and data generated by the running of the application program;
a processor 802, configured to execute the application program to implement:
obtaining a current parameter set, wherein the current parameter set comprises a plurality of current parameter combinations, and each current parameter combination comprises parameter values of a plurality of water pump blade parameters;
judging whether each current parameter combination in the current parameter set meets corresponding parameter judgment conditions or not to obtain a first parameter combination meeting the parameter judgment conditions and a second parameter combination not meeting the parameter judgment conditions;
Searching for parameter values by taking the parameter value of each water pump blade parameter in the first parameter combination as a search point to obtain a third parameter combination corresponding to each first parameter combination and/or obtain a fourth parameter combination corresponding to each second parameter combination;
and forming a new current parameter set by the third parameter set and the fourth parameter set, triggering the condition judging unit to judge whether each current parameter set in the new current parameter set meets corresponding parameter judging conditions or not again until the search ending condition corresponding to the current parameter set is met, so as to obtain the parameter set meeting the corresponding parameter judging conditions in the current parameter set.
As can be seen from the above, in the electronic device provided in the third embodiment of the present application, by obtaining a parameter set including a plurality of parameter combinations, further determining whether each parameter combination satisfies a corresponding parameter determination condition in parallel, and searching for a corresponding parameter value, until a search end condition is satisfied, a parameter combination satisfying the corresponding parameter determination condition may be obtained. Therefore, in the method, the device and the system, the multiple parameter combinations are judged and the parameter values are searched in parallel, so that the searching progress of the parameter values is quickened, and the searching efficiency is improved.
It should be noted that, the specific implementation of the processor in this embodiment may refer to the corresponding content in the foregoing, which is not described in detail herein.
Based on the technical scheme in the embodiment, the following describes the optimized searching process of the parameters of the water pump blade in detail:
the inventor of the present application, after studying the hill climbing algorithm, found that: the hill climbing algorithm is a simpler and efficient optimization algorithm. In the mountain climbing optimization process, searching is started from a random point, and the optimal solution in the neighborhood is selected as the current solution until the local optimal solution is searched. The algorithm has the advantages that the optimal solution can be simply and efficiently searched, and also has some problems that the algorithm is easy to sink into local optimal and is difficult to jump out, and the selection of the initial point position has great influence on the finally obtained optimal solution. If the initial point is selected to be just near the global highest value, then a globally optimal solution can be obtained. If the initial point is selected to be near a locally high value, the best solution searched out may be a locally optimal solution, but not a globally optimal solution.
In addition, in the process of applying the hill climbing algorithm, a search point is mainly set to "climb the hill" until "climb to the top", that is, an optimal value is searched, but if there are a plurality of "tops", limitations occur, and therefore, a plurality of search points need to be set in parallel. In the design of hydraulic machinery, the hill climbing algorithm has a great limitation. Because of the large number of design parameters and performance parameters involved in water pump design, the parameter space is not simply two-dimensional or three-dimensional space, but rather is a more complex multidimensional space, and many of the parallel searches are ineffective. Thus, there may be a case of long-term but invalid search. Meanwhile, each time searching is performed within the maximum searching range, the searching time is too long, and the searching is low.
Based on the defects, the inventor of the application further researches, based on the analysis of the hill climbing algorithm and the required improvement direction, proposes a heuristic search optimization scheme which can be used for the optimization design of the water pump, and the heuristic search optimization scheme can also be called as a global dynamic criterion optimization algorithm.
Specifically, the global dynamic criterion optimization algorithm for the design of the parameters of the water pump blade, provided by the inventor of the application, is suitable for the multi-parameter single-target or multi-parameter multi-target nonlinear relation optimization problem, and has high-efficiency parallelism, dynamic criterion and termination capability. The method can optimize the design parameter combination of the water pump, quickly and efficiently searches out the optimal value in the design parameter combination of the blade, improves the speed of the optimization design of the water pump, and specifically comprises the following characteristics:
(1) Setting an initial judging condition at the beginning of optimization, firstly screening results, namely initially setting parameter judging conditions in the prior art, and aiming at screening out the searched worse data and reducing useless searching.
(2) The parameter judgment conditions are changed continuously along with each round of search, so that the quality and the speed of optimization are improved continuously, and the method is favorable for obtaining the optimal solution rapidly.
(3) In the searching process, multipoint parallel searching can be performed, so that the searching efficiency is improved.
(4) After iteration exceeds a certain number of times, judging whether to terminate the current search or not with a certain probability, and if so, re-performing random search to avoid trapping in a local optimal solution, so that a global optimal solution is obtained finally.
In specific implementation, the main process of the global dynamic criterion optimization algorithm provided by the application is as follows: randomly searching a limited number of points within the design parameter range; setting a judging condition aiming at a certain random point, and judging whether the judging condition accords with the random point; if not, stopping searching the point, and if so, performing the next round of searching in the neighborhood of the point. The judging conditions of the new round of searching are required to be changed according to the searching result of the previous round, so that the judging conditions are continuously improved, and the optimizing quality is improved. In order to avoid trapping in a local optimal trap, stopping operation with a certain probability, namely stopping current searching, re-randomly searching, repeating the above processes until the maximum iteration times are reached, and searching an optimal solution.
Based on the method, the global dynamic criterion optimization algorithm can be used for optimizing the design parameters of the water pump, and the optimization algorithm can perform optimization of the design parameter combination due to the strong nonlinear relation between the design parameter combination and the performance, so that the optimal value in the design parameter combination can be quickly and efficiently searched, and the efficiency of optimizing the design of the water pump is improved. A flow chart of the global dynamic algorithm is shown in fig. 9.
The specific implementation mode of the global dynamic criterion optimization algorithm comprises the following steps:
(1) First, n groups of parameter combinations are randomly generated as starting points in the respective optimization ranges (namely the search ranges) of a plurality of optimization parameters (namely the parameters of the water pump blades), and are expressed as F in Where i refers to the ith round of search, n refers to the number of each round of search, and n=1, 2,3, … …. For each set of parameters F 1n Carrying out corresponding result solving to obtain each group F 1n Results R of (2) 1n Such as pump lift values and pump efficiency values.
(2) Setting the judgment condition of each round as R it Then the initial performance determination condition is R 1t Each set of parameters F is then compared 1n The result R obtained 1n Whether or not the initial determination condition R is satisfied 1t . If the decision condition is met, the set of parameters is retained and then searched in a small range neighborhood of each parameter, the search range should not exceed 5% of the respective parameter range. If the decision condition is not met, the set of parameters is discarded, a set of parameters is regenerated, and the next round of search is performed. The set of parameters satisfying the decision condition resulting from each round of search is denoted as T in The number of groups satisfying the judgment condition is m in total i A group.
(3) For the second round of search, new parameter F 2n Will be used for result solving to obtain corresponding R 2n . Taking the average value of the parameters meeting the judgment conditions obtained by the first round of search and the initial judgment conditions as the judgment condition R of the second round of search 2t Namely the following formula (2):
continuing to determine whether the result of the second round satisfies the determination condition, if so, then preserving the set of parameters, then at F 2n The search range should not exceed 5% of the respective parameter range. If the decision condition is not satisfied, the set of parameters is discarded, a set of parameters is regenerated, and the next round of searching is performed.
(4) For the third round of searching, the judging condition needs to be continuously changed into the second round of judging condition and m obtained by the second round of searching 2 The group meeting the average value of the criterion values, i.e. R 3t Is represented by formula (3):
the aim of continuously changing the judging conditions is to continuously improve the optimizing quality and optimizing speed, and the method is favorable for quickly obtaining the optimizing result.
(5) For the (i+1) th round of search, the judgment conditions are the (i) th round of judgment conditions and m obtained by the (i) th round of search i The group satisfies the average value of the judgment condition values, R (i+1)t Represented by the following formula (4):
(6) In order to avoid trapping in a locally optimal solution, a certain probability needs to be set in the searching process to terminate the current searching. The probability Y has a certain functional relation with the iteration times x, and the Y (x) function has the following characteristics: (a) as the number of iterations x increases, the termination probability Y increases; (b) As the number of iterations x approaches + -infinity, the termination probability Y approaches 1. According to the above feature, the Y (x) function can be written as formula (1) above. The relationship between Y and x is shown in fig. 10.
Wherein, a, b and c are constants, and the specific values of a, b and c can be correspondingly adjusted according to the maximum iteration times, so that the distribution of termination probability is adjusted, and the application range of the algorithm is wider.
(7) The maximum number of iterations is set. Repeating the steps until the maximum iteration number is reached. Finally, an optimized sample is obtained, and the optimization target is achieved.
In conclusion, the steps (1) - (7) are sequentially executed, a global dynamic criterion optimization algorithm can be developed, and optimization of design parameters and optimization design of performance of the guide vane type mixed flow pump are completed.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (9)

1. A method for obtaining parameters of a water pump blade, the method comprising:
obtaining a current parameter set, wherein the current parameter set comprises a plurality of current parameter combinations, and each current parameter combination comprises parameter values of a plurality of water pump blade parameters;
Judging whether each current parameter combination in the current parameter set meets corresponding parameter judgment conditions or not to obtain a first parameter combination meeting the parameter judgment conditions and a second parameter combination not meeting the parameter judgment conditions;
searching for parameter values by taking the parameter value of each water pump blade parameter in the first parameter combination as a search point to obtain a third parameter combination corresponding to each first parameter combination, and obtaining a fourth parameter combination corresponding to each second parameter combination;
forming a new current parameter set by the third parameter set and the fourth parameter set, and returning to judge whether each current parameter set in the new current parameter set meets corresponding parameter judgment conditions or not again until search ending conditions corresponding to the current parameter set are met so as to obtain parameter combinations meeting corresponding parameter judgment conditions in the current parameter set;
wherein before returning to the judging whether each of the current parameter combinations in the new current parameter set satisfies the corresponding parameter judgment condition, the method further comprises:
Updating the current iteration times;
obtaining a termination probability value at least according to the current iteration times, wherein the termination probability value at least characterizes the probability of entering local optimal solution search;
returning to judge whether each current parameter combination in the new current parameter set meets corresponding parameter judging conditions or not under the condition that the termination probability value is smaller than a probability threshold value until the search ending condition corresponding to the current parameter set is met;
and ending the current flow under the condition that the termination probability value is greater than or equal to the probability threshold value, and returning to acquire the current parameter set again until the search ending condition corresponding to the current parameter set is met.
2. The method of claim 1, wherein after combining the third parameter combination and the fourth parameter combination into a new current parameter set, the method further comprises:
updating the parameter determination conditions to obtain new parameter determination conditions, wherein the new parameter determination conditions correspond to the new current parameter set.
3. The method according to claim 2, wherein the parameter determination condition comprises at least any one or more of a pump lift threshold and a pump efficiency threshold;
Wherein updating the parameter determination condition includes:
and updating the corresponding threshold value in the parameter judgment condition at least according to the water pump lift value and/or the water pump efficiency value corresponding to each first parameter combination.
4. The method of claim 1, wherein obtaining a termination probability value based at least on the current number of iterations comprises:
obtaining a termination probability value corresponding to the current iteration times by using a probability distribution function;
the probability distribution function is established at least based on a preset maximum iteration number, and takes the current iteration number as an independent variable and the termination probability value as an independent variable.
5. The method according to claim 1, wherein searching for parameter values with the parameter value of each water pump vane parameter in the first parameter combination as a search point to obtain a third parameter combination corresponding to each first parameter combination includes:
and searching the parameter values in the neighborhood corresponding to the parameter values by taking the parameter value of each water pump blade parameter in the first parameter combination as a search point so as to obtain a third parameter combination corresponding to each first parameter combination.
6. The method of claim 1, wherein obtaining a fourth parameter combination corresponding to each of the second parameter combinations comprises:
and randomly generating corresponding parameter values for each water pump blade parameter to obtain fourth parameter combinations, wherein each fourth parameter combination corresponds to one second parameter combination.
7. The method of claim 1, wherein the search ending condition comprises: the current iteration times are greater than or equal to the preset maximum iteration times, and/or the parameter values of the parameters of each water pump blade are processed.
8. An apparatus for obtaining parameters of a water pump vane, the apparatus comprising:
the system comprises a parameter obtaining unit, a parameter setting unit and a parameter setting unit, wherein the parameter obtaining unit is used for obtaining a current parameter set, the current parameter set comprises a plurality of current parameter combinations, and each current parameter combination comprises parameter values of a plurality of water pump blade parameters;
a condition judging unit, configured to judge whether each of the current parameter combinations in the current parameter set satisfies a corresponding parameter judging condition, so as to obtain a first parameter combination that satisfies the parameter judging condition and a second parameter combination that does not satisfy the parameter judging condition;
The combination processing unit is used for searching the parameter values by taking the parameter value of each water pump blade parameter in the first parameter combination as a search point so as to obtain a third parameter combination corresponding to each first parameter combination and obtain a fourth parameter combination corresponding to each second parameter combination;
a parameter updating unit, configured to combine the third parameter combination and the fourth parameter combination to form a new current parameter set, and trigger the condition judging unit to judge whether each current parameter combination in the new current parameter set meets a corresponding parameter judging condition again, until a search ending condition corresponding to the current parameter set is met, so as to obtain a parameter combination in the current parameter set meeting the corresponding parameter judging condition;
wherein, before returning to the step of re-judging whether each current parameter combination in the new current parameter set meets the corresponding parameter judgment condition, the parameter updating unit is further configured to:
updating the current iteration times;
obtaining a termination probability value at least according to the current iteration times, wherein the termination probability value at least characterizes the probability of entering local optimal solution search;
Returning to judge whether each current parameter combination in the new current parameter set meets corresponding parameter judging conditions or not under the condition that the termination probability value is smaller than a probability threshold value until the search ending condition corresponding to the current parameter set is met;
and ending the current flow under the condition that the termination probability value is greater than or equal to the probability threshold value, and returning to acquire the current parameter set again until the search ending condition corresponding to the current parameter set is met.
9. An electronic device, comprising:
a memory for storing an application program and data generated by the operation of the application program;
a processor for executing the application program to realize:
obtaining a current parameter set, wherein the current parameter set comprises a plurality of current parameter combinations, and each current parameter combination comprises parameter values of a plurality of water pump blade parameters;
judging whether each current parameter combination in the current parameter set meets corresponding parameter judgment conditions or not to obtain a first parameter combination meeting the parameter judgment conditions and a second parameter combination not meeting the parameter judgment conditions;
Searching for parameter values by taking the parameter value of each water pump blade parameter in the first parameter combination as a search point to obtain a third parameter combination corresponding to each first parameter combination, and obtaining a fourth parameter combination corresponding to each second parameter combination;
forming a new current parameter set by the third parameter set and the fourth parameter set, and returning to judge whether each current parameter set in the new current parameter set meets corresponding parameter judgment conditions or not again until search ending conditions corresponding to the current parameter set are met so as to obtain parameter combinations meeting corresponding parameter judgment conditions in the current parameter set;
wherein the processor is further configured to, before returning to re-determine whether each of the current parameter combinations in the new current parameter set meets a corresponding parameter determination condition:
updating the current iteration times;
obtaining a termination probability value at least according to the current iteration times, wherein the termination probability value at least characterizes the probability of entering local optimal solution search;
returning to judge whether each current parameter combination in the new current parameter set meets corresponding parameter judging conditions or not under the condition that the termination probability value is smaller than a probability threshold value until the search ending condition corresponding to the current parameter set is met;
And ending the current flow under the condition that the termination probability value is greater than or equal to the probability threshold value, and returning to acquire the current parameter set again until the search ending condition corresponding to the current parameter set is met.
CN202011530393.9A 2020-12-22 2020-12-22 Water pump blade parameter acquisition method and device and electronic equipment Active CN112632723B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011530393.9A CN112632723B (en) 2020-12-22 2020-12-22 Water pump blade parameter acquisition method and device and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011530393.9A CN112632723B (en) 2020-12-22 2020-12-22 Water pump blade parameter acquisition method and device and electronic equipment

Publications (2)

Publication Number Publication Date
CN112632723A CN112632723A (en) 2021-04-09
CN112632723B true CN112632723B (en) 2024-04-16

Family

ID=75321021

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011530393.9A Active CN112632723B (en) 2020-12-22 2020-12-22 Water pump blade parameter acquisition method and device and electronic equipment

Country Status (1)

Country Link
CN (1) CN112632723B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006171948A (en) * 2004-12-14 2006-06-29 Fuji Electric Holdings Co Ltd Solution search method, solution search device, solution search program and recording medium
CN102855328A (en) * 2012-09-18 2013-01-02 浪潮(北京)电子信息产业有限公司 Parallel variable neighborhood search method
CN106326005A (en) * 2016-01-21 2017-01-11 华南师范大学 Automatic parameter tuning method for iterative MapReduce operation
CN107341277A (en) * 2016-04-29 2017-11-10 中国科学院微电子研究所 Parameter fitness method and parameter fitting system based on particle swarm optimization algorithm

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006171948A (en) * 2004-12-14 2006-06-29 Fuji Electric Holdings Co Ltd Solution search method, solution search device, solution search program and recording medium
CN102855328A (en) * 2012-09-18 2013-01-02 浪潮(北京)电子信息产业有限公司 Parallel variable neighborhood search method
CN106326005A (en) * 2016-01-21 2017-01-11 华南师范大学 Automatic parameter tuning method for iterative MapReduce operation
CN107341277A (en) * 2016-04-29 2017-11-10 中国科学院微电子研究所 Parameter fitness method and parameter fitting system based on particle swarm optimization algorithm

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
禁忌搜索算法的参数选择及其收敛特性分析;赵鹤群;王鹏宇;李磊;;自动化技术与应用;20130225(第02期);全文 *

Also Published As

Publication number Publication date
CN112632723A (en) 2021-04-09

Similar Documents

Publication Publication Date Title
CN110378419B (en) Image set expansion method, device, equipment and readable storage medium
KR20110096236A (en) Apparatus and method for clustering using mutual information between clusters
Kirsopp et al. Case and feature subset selection in case-based software project effort prediction
CN112540849A (en) Parameter configuration optimization method and system for distributed computing operation
CN115469851A (en) Automatic parameter adjusting method for compiler
CN112632723B (en) Water pump blade parameter acquisition method and device and electronic equipment
CN114880806A (en) New energy automobile sales prediction model parameter optimization method based on particle swarm optimization
CN110691000B (en) Web service combination method based on fusion of FAHP and planning graph
CN112395273A (en) Data processing method and device and storage medium
Lian et al. Filter pruning via separation of sparsity search and model training
CN115906303A (en) Planar microwave filter design method and device based on machine learning
CN114298414A (en) Equipment system efficiency prediction and index optimization method
CN116611493B (en) Hardware perception hybrid precision quantization method and system based on greedy search
CN114926701A (en) Model training method, target detection method and related equipment
CN109934917B (en) Parallelization point cloud generation DEM method based on machine learning prediction computation strength
CN112633516B (en) Performance prediction and machine learning compiling optimization method and device
CN115345303A (en) Convolutional neural network weight tuning method, device, storage medium and electronic equipment
Cheng et al. Robust Actor-Critic With Relative Entropy Regulating Actor
CN114565033A (en) Method and system for constructing characteristic parameter system of energy storage operation condition and storage medium
CN109446665B (en) Nonlinear frequency modulation signal optimization method and device and storage medium
CN108734267A (en) Compression method and device, terminal, the storage medium of deep neural network model
CN113656153A (en) Improved artificial bee colony algorithm for cloud computing task scheduling
CN111312267A (en) Voice style conversion method, device, equipment and storage medium
KR102542311B1 (en) Apparatus and method for adaptive graph traversal based on workload analysis
CN118036697B (en) Model data processing method, apparatus 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