A Sanitary Pump Impeller Optimization Design Method Based on Intelligent Optimization Algorithm
By using intelligent optimization algorithms to parametrically model and numerically simulate the impeller of the sanitary pump, key design parameters are optimized, solving the problem of low efficiency in sanitary pumps and achieving efficient digital design and cost reduction.
Patent Information
- Application Number
- CN202311701870.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-12
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2043-12-12
AI Technical Summary
The efficiency of existing sanitary pumps is generally low, around 50%, and there is a need to improve the performance of the equipment.
Intelligent optimization algorithms are used to perform parametric modeling and numerical simulation of the sanitary pump impeller, optimize key design parameters such as the impeller placement angle and blade wrap angle, and automatically find the optimal design scheme by combining intelligent algorithms such as genetic algorithms.
It significantly improves the efficiency of sanitary pumps, reduces manufacturing costs, and achieves digitally optimized design.
Smart Images

Figure CN117669092B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of centrifugal pump technology, specifically a sanitary pump impeller optimization design method based on intelligent optimization algorithms. Background Technology
[0002] Sanitary pumps are centrifugal pumps specifically designed for food, pharmaceutical, biotechnology, and other hygiene-related applications. They are commonly used to transport food, pharmaceutical products, biological products, beverages, and other liquid or semi-solid materials that require high hygiene standards during production and processing. Currently, the efficiency of sanitary pump systems is generally low, around 50%. Therefore, there is significant room for improvement in system efficiency. The impeller is a crucial flow-through component of a sanitary pump, and optimizing its design to enhance pump system performance is of great importance. Summary of the Invention
[0003] To address the problems of existing technologies, this invention provides a sanitary pump impeller optimization design method based on intelligent optimization algorithms. The method uses intelligent algorithms to directly obtain the optimal design scheme, significantly improving the efficiency of optimization design and effectively reducing production and manufacturing costs.
[0004] This invention provides a method for optimizing the design of a sanitary pump impeller based on an intelligent optimization algorithm, comprising the following steps:
[0005] Step 1: Determine whether the various flow components of the sanitary pump to be optimized already have specific design parameters.
[0006] Step 2: If specific design parameters are available, parametric modeling is performed directly; if specific design parameters are not available, a scanning device is used to scan the pump device entity to obtain its 3D model, and then its 3D model is imported into reverse engineering software for reverse design to obtain its specific design parameters; the scanning device is one or more of structured light scanner, CT scanner, and 3D camera, and the reverse modeling software includes CFturbo, Bladegen, and Geomagic Design X.
[0007] Step 3: Based on the design parameters, perform parametric modeling of the sanitary pump. Optimize the design of the semi-open impeller, the flow component that has the greatest impact on the device's performance. Select the parameters that have the most significant impact on performance as design variables, and use its head H and efficiency E as optimization objectives. The parameters that have the most significant impact on performance include the impeller's rear cover plate installation angle β. 1s Front cover inlet placement angle β 2h β, the angle of the rear cover outlet 2h Front cover outlet placement angle β 2sThe blade wrap angle φ is one of the parameters selected. The main reason for choosing these five parameters is that they directly determine the shape of the semi-open impeller, thus affecting the flow pattern of the medium during operation. The quality of the flow pattern directly impacts the efficiency of the pump unit. The parametric modeling software used includes Creo, NX UG, SolidWorks, and CATIA.
[0008] Step 4: Determine the range of variation of design variables to form a reasonable feasible region, use experimental design to obtain an appropriate number of groups, perform 3D modeling and mesh generation of design parameters, and perform numerical simulation calculations to obtain its head H and efficiency E. The modeling to numerical simulation calculation is carried out through a program called by code. The experimental designs used include fully randomized design, randomized block design, repeated measurement design, response surface design, and hybrid design. The mesh generation software used includes OpenFOAM, ANSYSICEM, HyperMesh, and Fluent mesh. The numerical simulation software used includes ANSYS, OpenFOAM, Star-CCM+, Fluent, and MATLAB.
[0009] Step 5: Apply an approximate model to the variables and the optimization objective and train it step by step to ensure its accuracy; the approximate model can be implemented using one or more of the following methods: polynomial fitting, interpolation, neural network, and nonlinear regression.
[0010] Step Six: Using the accurate model trained in the previous step, automatically optimize it using an intelligent optimization algorithm. Set the number of iterations. If a suitable solution set is obtained, find the optimal solution and determine its optimal design parameters. If no suitable solution set is obtained, return to Step Three to readjust the feasible region of the design variables and continue optimization. The intelligent optimization algorithm employs one or more of the following: genetic algorithm, particle swarm optimization, simulated annealing algorithm, artificial immune system algorithm, and differential evolution algorithm.
[0011] The beneficial effects of this invention are as follows: It provides a sanitary pump impeller optimization design method based on intelligent optimization algorithm, which realizes the digital intelligent optimization design of the semi-open impeller of sanitary pump from three-dimensional modeling to mesh generation numerical simulation and design optimization. It changes the traditional human experience selection and uses intelligent algorithm to directly obtain the optimal design scheme, which significantly improves the efficiency of optimization design and effectively reduces the production and manufacturing cost. Attached Figure Description
[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0013] Figure 1 A flowchart of a sanitary pump impeller optimization design method based on intelligent optimization algorithm;
[0014] Figure 2 A 3D model of a sanitary pump;
[0015] Figure 3 A 3D model of the optimized semi-open impeller of the sanitary pump;
[0016] Figure 4 This is a comparison chart of the external characteristic curves before and after optimization. Detailed Implementation
[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0018] This invention provides a method for optimizing the design of sanitary pump impellers based on intelligent optimization algorithms, such as... Figure 1 As shown, it includes the following steps:
[0019] Step 1: Determine whether the various flow components of the sanitary pump to be optimized already have specific design parameters.
[0020] Step 2: If specific design parameters are available, parametric modeling is performed directly; if specific design parameters are not available, a scanning device is used to scan the pump device entity to obtain its 3D model, and then its 3D model is imported into reverse engineering software for reverse design to obtain its specific design parameters; the scanning device is one or more of structured light scanner, CT scanner, and 3D camera, and the reverse modeling software includes CFturbo, Bladegen, and Geomagic Design X.
[0021] Step 3: Based on the design parameters, perform parametric modeling of the sanitary pump. Optimize the design of the semi-open impeller, the flow component that has the greatest impact on the device's performance. Select the parameters that have the most significant impact on performance as design variables, and use its head H and efficiency E as optimization objectives. The parameters that have the most significant impact on performance include the impeller's rear cover plate installation angle β. 1s Front cover inlet placement angle β 2h β, the angle of the rear cover outlet 2h Front cover outlet placement angle β 2sThe blade wrap angle φ is one of the parameters selected. The main reason for choosing these five parameters is that they directly determine the shape of the semi-open impeller, thus affecting the flow pattern of the medium during operation. The quality of the flow pattern directly impacts the efficiency of the pump unit. The parametric modeling software used includes Creo, NX UG, SolidWorks, and CATIA.
[0022] Step 4: Determine the range of variation of design variables to form a reasonable feasible region, use experimental design to obtain an appropriate number of groups, perform 3D modeling and mesh generation of design parameters, and perform numerical simulation calculations to obtain its head H and efficiency E. The modeling to numerical simulation calculation is carried out through a program called by code. The experimental designs used include fully randomized design, randomized block design, repeated measurement design, response surface design, and hybrid design. The mesh generation software used includes OpenFOAM, ANSYSICEM, HyperMesh, and Fluent mesh. The numerical simulation software used includes ANSYS, OpenFOAM, Star-CCM+, Fluent, and MATLAB.
[0023] Step 5: Apply an approximate model to the variables and the optimization objective and train it step by step to ensure its accuracy; the approximate model can be implemented using one or more of the following methods: polynomial fitting, interpolation, neural network, and nonlinear regression.
[0024] Step Six: Using an intelligent optimization algorithm, the accurate model trained in the previous step is automatically optimized. The number of iterations is set. If a suitable solution set is obtained, an optimal solution is found, and its optimal design parameters are determined. If no suitable solution set is obtained, the process returns to Step Three to readjust the feasible region of the design variables and continues optimization. The intelligent optimization algorithm employs one or more of the following: genetic algorithm, particle swarm optimization, simulated annealing algorithm, artificial immune system algorithm, and differential evolution algorithm. Finally, based on the obtained optimal design parameters, a model is designed as follows: Figure 2 The sanitary pump shown.
[0025] This embodiment describes a semi-open impeller optimization design for a sanitary pump, including:
[0026] The sanitary pump to be optimized does not have specific design parameters;
[0027] The sanitary pump was scanned with a 3D camera to obtain its original 3D model. The semi-open impeller was imported into CFturbo for reverse modeling, and its original impeller data and rear cover plate placement angle β were obtained from it. 1h The front cover inlet angle β is 18.2°. 1s The rear cover outlet placement angle is 15.3°. 2h The front cover outlet placement angle is 24.6°. 2sWith a blade wrap angle of 25.4° and a blade wrap angle of φ of 106°, the flow components of this three-dimensional model were meshed in ICEM, and the pump was imported into ANSYS for numerical simulation calculation, which yielded a head of 40.7m and an efficiency of 53.85%.
[0028] Based on design experience, the feasible domains of the above four variables are shown in Table 1 below.
[0029] Table 1
[0030]
[0031] Based on the obtained feasible region, 40 design schemes were obtained through orthogonal experiments using the iSight platform, as shown in Table 2 below:
[0032] Table 2
[0033]
[0034]
[0035] Based on the design parameters in the table, a script program written in Python is used to import the above design parameters into CFturbo to model and obtain a three-dimensional model of a semi-open impeller. The structural mesh is then generated using Fluent mesh, and the initial impeller mesh is replaced in ANSYS to complete numerical simulation calculations to obtain its head and efficiency, until all schemes have been calculated.
[0036] Based on the simulation data, an artificial neural network is used to train an approximate model of five design variables and two optimization objectives to obtain a mathematical model that accurately reflects the relationship between the design variables and the optimization objectives.
[0037] Based on the existing artificial neural network model, a genetic algorithm is used to automatically optimize the model. The crossover probability used in the algorithm is 0.9, the initial population is set to 120, and the number of iterations is set to 600.
[0038] After one round of algorithmic optimization, the optimal solution was selected based on the optimized Pareto front solution. The optimized design parameters were then determined, including the rear cover placement angle β. 1h The front cover inlet angle β is 19.36°. 1s The rear cover outlet placement angle β is 17.95°. 2h The front cover outlet placement angle is 25.38°. 2s With a blade wrap angle of 20° and a blade wrap angle of φ of 104.1°, the optimized design of the semi-open impeller completes the three-dimensional shape as follows: Figure 3ANSYS numerical calculations showed that the head under standard operating conditions was 43.3m and the efficiency was 57.62%, representing a 2.6m increase in head and a 3.77% increase in efficiency compared to the unoptimized head. The external characteristic comparison chart is shown below. Figure 4 .
[0039] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, for the device embodiments, the above descriptions are merely preferred embodiments of the present invention. Since they are fundamentally similar to the method embodiments, the descriptions are relatively simple, and relevant parts can be referred to the descriptions of the method embodiments. The above descriptions are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention, without departing from the principle of the present invention, should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. A method for optimizing the design of a sanitary pump impeller based on an intelligent optimization algorithm, characterized in that, Includes the following steps: Step 1: Determine whether the various flow-through components of the sanitary pump to be optimized already have specific design parameters; Step 2: If specific design parameters are available, parametric modeling is performed directly; if specific design parameters are not available, a scanning device is used to scan the pump device entity to obtain its 3D model, and then its 3D model is imported into reverse engineering software for reverse design to obtain its specific design parameters. Step 3: Based on the design parameters, perform parametric modeling of the sanitary pump, optimize the design of the semi-open impeller, the flow component that has the greatest impact on the performance of the device, select the parameters that have the most important impact on its performance as design variables, and optimize its head H and efficiency E as optimization objectives. Step 4: Determine the range of variation of the design variables to form a reasonable feasible region, use experimental design to obtain an appropriate number of groups, perform three-dimensional modeling and mesh generation of the design parameters, and perform numerical simulation calculations to obtain its head H and efficiency E. The modeling to numerical simulation calculation is carried out by calling a program written in code. Step 5: Approximate the variables and the optimization objective using a model and train it step by step to ensure its accuracy; Step Six: The accurate model trained in the previous step is automatically optimized using an intelligent optimization algorithm. The number of iterations is set. If a suitable solution set is obtained, an optimal solution is found from it, and its optimal design parameters are obtained. If no suitable solution set is obtained, the process returns to Step Three to readjust the feasible region of the design variables and continues optimization.
2. The sanitary pump impeller optimization design method based on intelligent optimization algorithm according to claim 1, characterized in that: The scanning device described in step two uses one or more of the following: structured light scanner, CT scanner, and 3D camera. The reverse modeling software includes CFturbo, Bladegen, and Geomagic Design X.
3. The sanitary pump impeller optimization design method based on intelligent optimization algorithm according to claim 1, characterized in that: The most important parameter affecting performance, as mentioned in step three, includes the impeller's rear cover plate mounting angle. Front cover inlet placement angle Rear cover outlet placement angle Front cover outlet placement angle , blade wrap angle φ.
4. The sanitary pump impeller optimization design method based on intelligent optimization algorithm according to claim 1 or 3, characterized in that: The parametric modeling software used in step three includes Creo, NX UG, SolidWorks, and CATIA.
5. The sanitary pump impeller optimization design method based on intelligent optimization algorithm according to claim 1, characterized in that: The experimental designs used in step four include fully randomized design, randomized block design, repeated measures design, response surface design, and hybrid design. The mesh generation software used includes OpenFOAM, ANSYS ICEM, HyperMesh, and Fluent mesh. The numerical simulation software used includes ANSYS, OpenFOAM, Star-CCM+, Fluent, and MATLAB.
6. The sanitary pump impeller optimization design method based on intelligent optimization algorithm according to claim 1 or 5, characterized in that: Step four involves importing experimental design parameters into modeling software to generate a three-dimensional model, then dividing the three-dimensional model into a mesh and performing numerical simulation calculations to obtain the head and efficiency of the sanitary pump. This process is repeated until the experimental scheme calculation is completed. The program uses Python, Java, C++, or MATLAB as its code language.
7. The sanitary pump impeller optimization design method based on intelligent optimization algorithm according to claim 1, characterized in that: The approximate model in step five is implemented using one or more of the following methods: polynomial fitting, interpolation, neural networks, and nonlinear regression.
8. The sanitary pump impeller optimization design method based on intelligent optimization algorithm according to claim 1, characterized in that: The intelligent optimization algorithm in step six adopts one or more of the following: genetic algorithm, particle swarm optimization, simulated annealing algorithm, artificial immune system algorithm, and differential evolution algorithm.
Citation Information
Patent Citations
A multi-stage centrifugal pump impeller intelligent optimization method based on improved particle swarm optimization algorithm
CN109145491A
Matching optimization method for improving performance and hump instability of large vertical centrifugal pump
CN113177271A
