CN114297793B - Multidisciplinary optimization design method for impeller structure of seawater desalination pump - Google Patents
Multidisciplinary optimization design method for impeller structure of seawater desalination pump Download PDFInfo
- Publication number
- CN114297793B CN114297793B CN202111600810.7A CN202111600810A CN114297793B CN 114297793 B CN114297793 B CN 114297793B CN 202111600810 A CN202111600810 A CN 202111600810A CN 114297793 B CN114297793 B CN 114297793B
- Authority
- CN
- China
- Prior art keywords
- pump
- impeller
- optimization
- software
- fluid
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/124—Water desalination
- Y02A20/131—Reverse-osmosis
Landscapes
- Structures Of Non-Positive Displacement Pumps (AREA)
Abstract
The invention relates to a multidisciplinary optimization design method for a seawater desalination pump impeller structure, which solves the technical problem of how to optimally design an impeller so as to improve the hydraulic efficiency and the operation stability of the seawater desalination pump. The invention is widely used for the design and manufacture of the sea water desalination pump.
Description
Technical Field
The invention relates to the technical field of centrifugal pump design, in particular to a multidisciplinary optimization design method for a seawater desalination pump impeller structure.
Background
Seawater desalination is an important approach to solve the shortage of fresh water resources. As a core component in a seawater desalination system, the seawater desalination pump has important significance for guaranteeing national water safety by improving the running efficiency and stability.
The impeller is used as a main component of the sea water desalination pump, and the structural design is a complex multidisciplinary problem. However, at present, the design and manufacturing process of the impeller only aims at single hydraulic performance improvement, and the problems of structural strength and internal flow are not considered. Therefore, how to optimally design the impeller so as to improve the hydraulic efficiency and the operation stability of the sea water desalination pump is a technical problem to be solved urgently by the person skilled in the art.
Disclosure of Invention
The invention provides a multi-disciplinary optimal design method for the impeller structure of the seawater desalination pump based on fluid mechanics, material mechanics and structural mechanics by adopting an advanced numerical simulation means and an efficient automatic numerical analysis method in order to solve the technical problem of how to optimally design the impeller so as to improve the hydraulic efficiency and the operation stability of the seawater desalination pump.
The invention provides a multidisciplinary optimization design method for a seawater desalination pump impeller structure, which comprises the following steps:
step S1, a three-dimensional model of a fluid domain of the sea water desalination pump is established, wherein the fluid domain comprises a water inlet pipe, an impeller, a guide vane and a water outlet pipe, the impeller uses CFturbo software for parametric modeling, and an impeller solid domain model is simultaneously established in the CFturbo software through Hub/Shroud solids functions according to a two-dimensional assembly diagram of the sea water desalination pump; the water inlet pipe, the guide vane and the water outlet pipe are subjected to three-dimensional modeling through three-dimensional modeling software UG;
step S2, performing grid division on an impeller fluid domain by using TurboGrid software, performing grid division on a water inlet pipe fluid domain, a guide vane fluid domain and a water outlet pipe fluid domain model by using ICEM software, then introducing the grids into ANSYS CFX software, giving corresponding boundary conditions according to the actual running condition of the sea water desalination pump, and performing hydrodynamic analysis and solving to obtain the external characteristics of the pump;
s3, applying pressure field information of a fluid-solid coupling interface in the fluid mechanics analysis solving result to an impeller solid domain as a load, and obtaining a corresponding statics solving result through a Static Structural module in an ANYSY Workbench platform;
s4, selecting main geometric parameters of the impeller structure as optimization variables, and determining the variation range of the optimization variables;
s5, generating n data samples by using a test design method according to the optimized variable and the variation range thereof in the step S4, corresponding to n different impeller structural designs, repeating the steps S2 and S3 by using a batch processing method to obtain corresponding pump external characteristics and statics analysis results to generate a sample library, and determining an optimization target and constraint conditions;
step S6, taking the data of the sample library in the step S5 as a training sample of the BP neural network, so as to obtain a functional relation between an optimization variable and the external characteristic of the pump and a corresponding statics analysis result, and establishing a proxy model;
and S7, judging whether the accuracy of the proxy model meets the requirement, if not, increasing the number n of the data samples in the step S5, and repeating the step S5 and the step S6 until the accuracy meets the requirement. If the precision meets the requirement, the step S8 is carried out;
and S8, solving the agent model obtained in the step S6 by using a multi-target particle swarm algorithm to obtain a global optimal solution, and completing optimization.
Preferably, in step S2, the external characteristics are a lift and efficiency external characteristic, and the expression of the lift external characteristic is:
in the formula (1), H is the lift of a pump, and m; p is p in For pump inlet pressure, p out Pump outlet pressure, pa; ρ is density of seawater, kg/m 3 The method comprises the steps of carrying out a first treatment on the surface of the g is gravity acceleration, 9.8m/s -2 ；
The expression of the efficiency external characteristic is:
in the formula (2), eta is the efficiency; q is flow, m 3 S; t is torque, N.m; ω is the angular velocity of the impeller rotation, rad/s.
Preferably, in step S4, the optimized variable of the impeller structure is the impeller inlet diameter D 1 Impeller outlet diameter D 2 Blade inlet setting angle beta b1 Blade outlet setting angle beta b2 Blade wrap angle ψ.
Preferably, in the step S5, the optimization targets are the pump hydraulic efficiency η and the maximum deformation amount l of the impeller structure max Maximum equivalent stress tau max The constraint is that the pump head H fluctuates less than a certain proportion of the prescribed head.
Preferably, the constraint is that the pump head H fluctuates by less than 5% of the prescribed head.
Preferably, in step S7, the criterion for meeting the accuracy requirement is the determination coefficient R in the regression analysis 2 >0.96，R 2 Calculated by the following formula (3):
in the formula (3), n is the number of database samples in the step S5;neural network predictors for i responses, y i For the corresponding actual value in the sample library, +.>For the average of the actual values, the closer the decision coefficient is to 1, the more accurate the proxy model is.
Preferably, in step S5, the test design method is specifically an optimal latin hypercube sampling, implemented by a DOE module in the Isight platform.
Preferably, in step S5, the batch processing method specifically uses the Isight platform to implement the call to different software and record the pump external characteristics and the static analysis result.
The invention has the beneficial effects that the internal flow condition of the impeller structure is improved, and the dynamic and static interference effect between the impeller and the guide vane is effectively relieved, so that the running stability of the pump unit is improved. The complex requirements of the design of the structural reliability and the hydraulic performance of the sea water desalination pump can be effectively balanced, the design level of the sea water desalination pump can be improved, and the hydraulic efficiency and the operation stability of the sea water desalination pump can be further improved.
Further features and aspects of the present invention will become apparent from the following description of specific embodiments with reference to the accompanying drawings.
Drawings
FIG. 1 is a schematic diagram of a three-dimensional fluid domain of a desalination pump.
FIG. 2 is a schematic view of the impeller structure optimization variables.
FIG. 3 is a flow chart of the Isight platform batch process.
Fig. 4 is a schematic view of the optimized impeller structure.
Fig. 5 is a graph showing the comparison of the internal flow fields before and after optimization, in which (a) is the effect before optimization and (b) is the effect after optimization.
Description of the symbols in the drawings:
1. inlet pipe, impeller, guide vane, water outlet pipe.
Detailed Description
The invention discloses a multidisciplinary optimization design method of a seawater desalination pump impeller structure, which combines a test design method, unidirectional steady-state fluid-solid coupling simulation calculation, a BP neural network and a multi-target particle swarm algorithm, designs the seawater desalination pump impeller structure from two aspects of fluid mechanics and structural mechanics, and specifically comprises the following implementation processes:
step S1, a three-dimensional model of a fluid domain of the sea water desalination pump is established, as shown in FIG. 1, the fluid domain comprises a water inlet pipe 1, an impeller 2, a guide vane 3 and a water outlet pipe 4, wherein the impeller uses CFturbo software for parametric modeling, and an impeller solid domain model is simultaneously established in the CFturbo software through Hub/Saroud solids functions according to a two-dimensional assembly diagram (two-dimensional CAD drawing) of the sea water desalination pump; the water inlet pipe, the guide vane and the water outlet pipe are subjected to three-dimensional modeling through three-dimensional modeling software UG.
Step S2, performing grid division on an impeller fluid domain by using TurboGrid software, performing grid division on a water inlet pipe fluid domain, a guide vane fluid domain and a water outlet pipe fluid domain model by using ICEM software, then introducing the grids into ANSYS CFX software, and giving corresponding boundary conditions according to actual operation conditions of a sea water desalination pump, wherein the boundary conditions are specifically a total pressure inlet (1 atm) and a mass flow outlet, and performing hydrodynamic analysis and solving to obtain the pump lift and efficiency external characteristics, wherein the expression of the lift external characteristics is as follows:
in the formula (1), H is the lift of a pump, and m; p is p in For pump inlet pressure, p out Pump outlet pressure, pa; ρ is density of seawater, kg/m 3 The method comprises the steps of carrying out a first treatment on the surface of the g is gravity acceleration, 9.8m/s -2 。
The expression of the efficiency external characteristic is:
in the formula (2), eta is the efficiency; q is flow, m 3 S; t is torque, N.m; ω is the angular velocity of the impeller rotation, rad/s.
And S3, applying pressure field information of the fluid-solid coupling interface in the fluid mechanics analysis solving result to an impeller solid domain as a load, and obtaining a corresponding statics solving result through a Static Structural module in the ANYSY Workbench platform.
S4, selecting the impeller inlet diameter D of the impeller structure 1 Impeller outlet diameter D 2 Blade inlet setting angle beta b1 Blade outlet setting angle beta b2 And the blade wrap angle psi (shown in fig. 2) as an optimization variable, and determining the variation range of the optimization variable.
Step S5, generating n data samples corresponding to n different leaves by using a test design method according to the optimization variable and the variation range in the step S4The design of the wheel structure, the corresponding pump external characteristics and the statics analysis result are obtained by repeating the steps S2 and S3 by utilizing a batch processing method to generate a sample library, and an optimization target and a constraint condition are determined, wherein the optimization target is pump hydraulic efficiency eta and impeller structure maximum deformation quantity l max Maximum equivalent stress tau max The constraint is that the pump head H fluctuates by less than 5% of the specified head (not limited to 5%, and the ratio can be adjusted according to the actual situation).
It should be noted that the test design method may specifically be implemented by using optimal latin hypercube sampling through DOE modules in the Isight platform.
It should be noted that, the batch processing method may specifically use the Isight platform to implement the call to different software and record the external characteristics of the pump and the static analysis result (as shown in fig. 3).
And S6, taking the data of the sample library in the step S5 as a training sample of the BP neural network, thereby obtaining a functional relation between the optimization variable and the external characteristic of the pump and the corresponding statics analysis result, and establishing a proxy model.
And S7, judging whether the accuracy of the proxy model meets the requirement, if not, increasing the number n of the data samples in the step S5, and repeating the step S5 and the step S6 until the accuracy meets the requirement. And if the precision meets the requirement, the step S8 is performed.
The judgment criterion for meeting the accuracy requirement is that the determination coefficient R in regression analysis 2 >0.96，R 2 Calculated by the following formula (3):
in the formula (3), n is the number of database samples in the step S5;neural network predictors for i responses, y i For the corresponding actual value in the sample library, +.>Is the average of the actual values. The closer the decision coefficient is to 1, the more accurate the proxy model is.
And S8, solving the agent model obtained in the step S6 by using a multi-target particle swarm algorithm to obtain a global optimal solution, and completing optimization.
The following illustrates when the upper and lower limits of the optimization variables and the variation ranges are as indicated in the table in step S4.
Table 1 optimization variables and upper and lower bound ranges
100 groups of design samples are generated in a decision domain by adopting optimal Latin hypercube sampling, and automatic numerical analysis of fluid mechanics and structural mechanics is carried out on the 100 samples by using a batch processing method based on an Isight platform. The calculation verification shows that 96 design samples are valid design samples, and 4 design samples are invalid design samples (namely design samples which cannot be modeled or are wrongly calculated).
A mathematical model between an optimization variable and an optimization target is established through a single hidden layer feedforward neural network, the model is solved by utilizing a multi-target particle swarm algorithm to obtain a pareto front, an optimal solution is finally selected on the pareto front according to actual requirements (an optimized impeller structure is shown in fig. 4), and compared with an original model, the efficiency of the optimized model is improved by 4.5%, the maximum equivalent stress is reduced by 10.2%, and the maximum deformation is reduced by 5.8%. The internal flow field pairs of the middle sections of the impellers before and after optimization are shown in fig. 5, so that the internal flow condition of the impeller structure after optimization is obviously improved, and the dynamic and static interference effect between the impellers and the guide vanes is effectively relieved, so that the running stability of the pump unit is improved.
The above description is only for the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art.
Claims (1)
1. The multidisciplinary optimization design method for the impeller structure of the seawater desalination pump is characterized by comprising the following steps of:
step S1, a three-dimensional model of a fluid domain of the sea water desalination pump is established, wherein the fluid domain comprises a water inlet pipe, an impeller, a guide vane and a water outlet pipe, the impeller uses CFturbo software for parametric modeling, and an impeller solid domain model is simultaneously established in the CFturbo software through Hub/Shroud solids functions according to a two-dimensional assembly diagram of the sea water desalination pump; the water inlet pipe, the guide vane and the water outlet pipe are subjected to three-dimensional modeling through three-dimensional modeling software UG;
step S2, performing grid division on an impeller fluid domain by using TurboGrid software, performing grid division on a water inlet pipe fluid domain, a guide vane fluid domain and a water outlet pipe fluid domain model by using ICEM software, then introducing the grids into ANSYS CFX software, giving corresponding boundary conditions according to the actual running condition of the sea water desalination pump, and performing hydrodynamic analysis and solving to obtain the external characteristics of the pump; the external characteristics are lift and efficiency external characteristics, and the expression of the lift external characteristics is:
in the formula (1), H is the lift of a pump, and m; p is p in For pump inlet pressure, p out Pump outlet pressure, pa; ρ is density of seawater, kg/m 3 The method comprises the steps of carrying out a first treatment on the surface of the g is gravity acceleration, 9.8m/s -2 ；
The expression of the efficiency external characteristic is:
in the formula (2), eta is the efficiency; q is flow, m 3 S; t is torque, N.m; omega is the angular velocity of the impeller rotation, rad/s;
s3, applying pressure field information of a fluid-solid coupling interface in the fluid mechanics analysis solving result to an impeller solid domain as a load, and obtaining a corresponding statics solving result through a Static Structural module in an ANYSY Workbench platform;
s4, selecting main geometric parameters of the impeller structure as optimization variables, and determining the variation range of the optimization variables; the optimized variable of the impeller structure is the diameter D of the impeller inlet 1 Impeller outlet diameter D 2 Blade inlet setting angle beta b1 Blade outlet setting angle beta b2 Blade wrap angle psi;
s5, generating n data samples by using a test design method according to the optimized variable and the variation range thereof in the step S4, corresponding to n different impeller structural designs, repeating the steps S2 and S3 by using a batch processing method to obtain corresponding pump external characteristics and statics analysis results to generate a sample library, and determining an optimization target and constraint conditions; the optimization target is the hydraulic efficiency eta of the pump and the maximum deformation quantity l of the impeller structure max Maximum equivalent stress tau max The constraint condition is that the fluctuation of the pump lift H is less than 5% of the specified lift; the test design method is specifically implemented by a DOE module in an Isight platform through optimal Latin hypercube sampling; the batch processing method specifically comprises the steps of calling different software by using an Isight platform and recording external characteristics and statics analysis results of the pump;
step S6, taking the data of the sample library in the step S5 as a training sample of the BP neural network, so as to obtain a functional relation between an optimization variable and the external characteristic of the pump and a corresponding statics analysis result, and establishing a proxy model;
step S7, judging whether the accuracy of the agent model meets the requirement, if not, increasing the number n of the data samples in the step S5, repeating the step S5 and the step S6 until the accuracy meets the requirement, and if so, entering the step S8; the judgment criterion for meeting the accuracy requirement is that the determination coefficient R in regression analysis 2 >0.96，R 2 Calculated by the following formula (3):
in the formula (3), n is the number of database samples in the step S5;neural network predictors for i responses, y i For the corresponding actual value in the sample library, +.>For the average value of the actual values, the closer the decision coefficient is to 1, the more accurate the proxy model is indicated;
and S8, solving the agent model obtained in the step S6 by using a multi-target particle swarm algorithm to obtain a global optimal solution, and completing optimization.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111600810.7A CN114297793B (en) | 2021-12-24 | 2021-12-24 | Multidisciplinary optimization design method for impeller structure of seawater desalination pump |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111600810.7A CN114297793B (en) | 2021-12-24 | 2021-12-24 | Multidisciplinary optimization design method for impeller structure of seawater desalination pump |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114297793A CN114297793A (en) | 2022-04-08 |
| CN114297793B true CN114297793B (en) | 2023-07-25 |
Family
ID=80970437
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111600810.7A Active CN114297793B (en) | 2021-12-24 | 2021-12-24 | Multidisciplinary optimization design method for impeller structure of seawater desalination pump |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114297793B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101679188B1 (en) * | 2015-09-18 | 2016-11-25 | 한국생산기술연구원 | High efficiency optimal design method of single channel pump impeller and high efficiency single channel pump impeller designed by the method |
| KR101679186B1 (en) * | 2015-07-29 | 2016-12-07 | 한국생산기술연구원 | Optimal design method of impeller for centrifugal and mixed flow pump, impeller of centrifugal and mixed flow pump and centrifugal and mixed flow pump by the method |
| CN106874542A (en) * | 2017-01-04 | 2017-06-20 | 滨州东瑞机械有限公司 | A kind of hydraulic turbine impeller multi-state multi-objective optimization design of power method |
| CN109002680A (en) * | 2018-10-28 | 2018-12-14 | 扬州大学 | A kind of multidisciplinary automatic optimizing design method of axial-flow pump impeller |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101956711B (en) * | 2010-10-27 | 2012-11-07 | 江苏大学 | Computational fluid dynamics (CFD)-based centrifugal pump multi-working condition hydraulic power optimization method |
| CN103939389B (en) * | 2014-04-16 | 2016-04-27 | 江苏大学 | A kind of guide-vane centrifugal pump multi-operating mode Hydraulic Design Method |
| CN105201901B (en) * | 2015-10-19 | 2017-08-04 | 江苏大学 | Centrifugal pump impeller waterpower and construction design method based on fluid and structural simulation |
| CN106529072B (en) * | 2016-11-25 | 2020-03-06 | 江苏大学 | Comprehensive design method of high-temperature and high-pressure centrifugal pump impeller based on multidisciplinary optimization |
| CN107882771B (en) * | 2017-10-18 | 2020-06-26 | 江苏大学 | Optimal design method of jet type self-priming centrifugal pump |
| CN108710764B (en) * | 2018-05-23 | 2022-06-21 | 江苏大学 | Double-suction pump multi-objective optimization design method based on hybrid approximation model |
| CN109145461B (en) * | 2018-08-28 | 2023-07-11 | 江苏大学 | Matching optimization design method for overflow parts of high-pressure seawater desalination pump |
| CN110175340B (en) * | 2018-11-16 | 2023-06-02 | 湘潭大学 | Pneumatic robust optimization design method suitable for centrifugal compressor impeller under uncertain working conditions |
-
2021
- 2021-12-24 CN CN202111600810.7A patent/CN114297793B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101679186B1 (en) * | 2015-07-29 | 2016-12-07 | 한국생산기술연구원 | Optimal design method of impeller for centrifugal and mixed flow pump, impeller of centrifugal and mixed flow pump and centrifugal and mixed flow pump by the method |
| KR101679188B1 (en) * | 2015-09-18 | 2016-11-25 | 한국생산기술연구원 | High efficiency optimal design method of single channel pump impeller and high efficiency single channel pump impeller designed by the method |
| CN106874542A (en) * | 2017-01-04 | 2017-06-20 | 滨州东瑞机械有限公司 | A kind of hydraulic turbine impeller multi-state multi-objective optimization design of power method |
| CN109002680A (en) * | 2018-10-28 | 2018-12-14 | 扬州大学 | A kind of multidisciplinary automatic optimizing design method of axial-flow pump impeller |
Non-Patent Citations (2)
| Title |
|---|
| Xijin Ma ; Xinkai Li ; Dengfeng Yang.Multi-objective Optimization design of the multiphase pump boosting cell. 2011 Second International Conference on Mechanic Automation and Control Engineering.2011,全文. * |
| 基于CFD技术的高压泵液力端优化设计;叶晓琰;杨孙圣;许建强;胡敬宁;;排灌机械(第06期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114297793A (en) | 2022-04-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Application of different surrogate models on the optimization of centrifugal pump | |
| Pei et al. | Multiparameter optimization for the nonlinear performance improvement of centrifugal pumps using a multilayer neural network | |
| Tong et al. | Internal flow structure, fault detection, and performance optimization of centrifugal pumps | |
| Wang et al. | Multiobjective optimization design and performance prediction of centrifugal pump based on orthogonal test | |
| CN112417773B (en) | Multidisciplinary optimization design method, device and equipment of multistage axial flow expander | |
| CN111486116A (en) | Method and system for designing three-dimensional flow impeller of low-specific-speed centrifugal blower | |
| Heo et al. | High-efficiency design of a mixed-flow pump using a surrogate model | |
| CN106529072B (en) | Comprehensive design method of high-temperature and high-pressure centrifugal pump impeller based on multidisciplinary optimization | |
| CN111400941A (en) | Numerical prediction method for internal reflux and reflux vortex cavitation of vane pump | |
| CN107676273A (en) | A kind of low efficient centrifugal impeller of pump numerical optimization of shaking | |
| Kang et al. | A study on the multi-objective optimization of impeller for high-power centrifugal compressor | |
| CN114297793B (en) | Multidisciplinary optimization design method for impeller structure of seawater desalination pump | |
| Rong et al. | Improving the hydraulic performance of a high-speed submersible axial flow pump based on CFD technology | |
| Nguyen et al. | Hydrodynamic optimization of the impeller and diffuser vane of an axial-flow pump | |
| CN113536709A (en) | Turbulence model correction method based on turbulence modeling machine learning | |
| Siwek et al. | Numerical and experimental study of centrifugal fan flow structures and their relationship with machine efficiency | |
| Carolus | Design guidelines for low pressure axial fans based on CFD-trained meta-models | |
| CN112163289B (en) | Axial flow impeller cavitation characteristic calculation method based on delay type separation vortex simulation | |
| CN114925481A (en) | Hydraulic model library centrifugal pump performance improving method based on energy efficiency index | |
| Grapsas et al. | Numerical study and optimal blade design of a centrifugal pump by evolutionary algorithms | |
| Wang et al. | Multiobjective optimization design and experimental study of desulfurization dust removal centrifugal pump based on immune particle swarm algorithm | |
| CN111079367B (en) | Axial flow pump spoke optimization design method suitable for different water inlet taper pipes | |
| CN112761969A (en) | Optimization method for structural parameters of centrifugal pump | |
| CN114201926B (en) | Centrifugal pump performance curve sample acquisition method and application thereof in machine learning | |
| CN116384009B (en) | Simulation prediction method, device and equipment for energy efficiency level of canned motor pump |
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 |