Multi-stage centrifugal pump rotor dynamics optimization method and device, medium and equipment

Abstract

The invention relates to a multi-stage centrifugal pump rotor dynamics optimization method and device, a medium and equipment. The method comprises the steps that geometric parameters and position parameters of parts influencing the hydraulic efficiency of a multi-stage centrifugal pump are obtained; establishing a pump rotor geometric model; establishing a pump rotor grid model; establishing a pump rotor system finite element calculation model; carrying out orthogonal table design on the geometric parameters and the position parameters to form a typical characteristic parameter orthogonal table, and calculating the first-order inherent frequency of the pump rotor system under each characteristic parameter combination; determining the upper limit and the lower limit of each of the geometric parameters and the position parameters according to known conditions, and generating a full-factor test orthogonal table through software; importing the full-factor test orthogonal table and the first-order inherent frequency of the pump rotor system into a BP neural network for fitting; and the fitted BP neural network is imported into a Matlab genetic algorithm calculation program for optimization, and a geometric parameter and position parameter combination enabling the first-order inherent frequency of the pump rotor system to be maximum is obtained.

Description

Technical Field

[0001] The invention relates to a method, a device, a medium and equipment for optimizing the rotor dynamics of a multi-stage centrifugal pump, and belongs to the technical field of multi-stage centrifugal pumps. Background Art

[0002] As a key fluid conveying equipment, the working principle of multistage centrifugal pump is to convert mechanical energy into pressure potential energy and kinetic energy of the conveying liquid medium. It is widely used in many industries such as metallurgy, chemical industry, petroleum, nuclear power, electric power, urban construction and national defense and military industry. With the rapid development of industry, the speed of multistage centrifugal pumps has been continuously improved, rapidly increasing from zero to thousands of revolutions per minute. When the rotor components of high-speed pumps approach or reach the critical speed, the rotor system often vibrates, thereby generating noise, reducing the working efficiency of the machine, and seriously causing the rotor to become unstable and cause accidents, making it an issue that cannot be ignored to ensure the safety and stability of the rotor system under operating conditions. In the early days, due to the low speed, small head and low power of the pump, the main cause of vibration was the eccentricity of the impeller, that is, the center of the impeller and the center of the shaft section were not on the same horizontal line. In order to solve this vibration problem, the static balancing method was adopted. However, as my country's pump industry develops towards high speed, high head and high power, it has brought interference from various uncertain factors, resulting in the vibration problem of the pump group becoming the main issue of concern to many scholars. Therefore, ensuring the stable and efficient operation of multistage centrifugal pumps has a positive impact on the development of my country's manufacturing industry.

[0003] The critical speed analysis of multistage pumps belongs to the category of rotor dynamics. In the dynamic analysis of pump rotor components, calculating the critical speed of rotor bending vibration is the starting point of this invention. At present, the methods for critical speed analysis of multistage centrifugal pump rotor systems mainly include modal analysis, transfer matrix method and finite element method.

[0004] In the design and analysis of traditional multi-stage centrifugal pumps, the parameters for optimizing the dynamic performance of the pump rotor are generally selected by optimizing the main structural parameters of the pump, such as the geometric parameters of the pump shaft, the position of the inducer and impeller and other components on the pump shaft, etc. However, for multi-stage centrifugal pumps that have been mass-produced by manufacturers, most of the above parameters have been determined, and there is very little room for optimization. At the same time, with the dynamic performance of the multi-stage centrifugal pump as the optimization goal, changing the design of the pump shaft and other main components will affect the hydraulic performance of the multi-stage centrifugal pump. The hydraulic performance parameters of the multi-stage centrifugal pumps that have been mass-produced by manufacturers, such as efficiency and pump shaft power, can already meet the actual operation requirements. Therefore, optimizing the pump shaft components such as bearing position and model can improve its dynamic performance without changing the hydraulic performance of the multi-stage centrifugal pump.

[0005] Therefore, under the condition that the parameters of the main components of the centrifugal pump, such as the pump shaft, inducer, and impeller, are fixed and do not affect its hydraulic performance such as head efficiency, the influence of the geometric parameters and position of components such as bearings and bushings on the dynamics of the centrifugal pump rotor system is analyzed. A multi-stage centrifugal pump rotor dynamics optimization method with fixed pump shaft parameters is formed. It is of great significance for calculating the critical speed of the pump rotor system and avoiding high-speed pump rotor components approaching or reaching the critical speed, and provides theoretical guidance for achieving stable operation of multi-stage centrifugal pumps. Summary of the invention

[0006] In response to the above technical problems, the present invention provides a method, device, medium and equipment for optimizing the rotor dynamics of a multi-stage centrifugal pump. The method analyzes and optimizes the geometric parameters and positions of components such as bearings and bushings to ensure hydraulic performance such as head efficiency while avoiding high-speed pump rotor components from approaching or reaching the critical speed, thereby ensuring the safe and reliable operation of the multi-stage centrifugal pump.

[0007] To achieve the above object, the present invention adopts the following technical solutions: A multi-stage centrifugal pump rotor dynamics optimization method, comprising: Obtain the geometric parameters and position parameters of the components that affect the hydraulic efficiency of the multi-stage centrifugal pump; Use 3D geometric modeling software to geometrically model the components that affect the hydraulic efficiency of the multi-stage centrifugal pump, add them to the corresponding positions of the pump shaft, and establish the pump rotor geometric model; Import the pump rotor geometric model into the meshing software for meshing and establish the pump rotor mesh model; In the pump rotor mesh model, gap stiffness constraints are imposed on the components that affect the hydraulic efficiency of the multi-stage centrifugal pump, axial displacement constraints are imposed on the bearings, and a finite element calculation model of the pump rotor system is established; The geometric parameters and position parameters are designed into an orthogonal table to form an orthogonal table of typical characteristic parameters, and the first-order natural frequency of the pump rotor system under each characteristic parameter combination is calculated according to the finite element calculation model of the pump rotor system; Determine the upper and lower limits of each parameter in the geometric parameters and location parameters according to known conditions, select the lowest level, the middle level and the highest level within the upper and lower limits, and generate the orthogonal table of the full factorial experiment through the software; The full factorial test orthogonal table and the first-order natural frequency of the pump rotor system are imported into the BP neural network for fitting; The fitted BP neural network was imported into the Matlab genetic algorithm calculation program for optimization, and the combination of geometric parameters and position parameters that maximized the first-order natural frequency of the pump rotor system was obtained.

[0008] In the multi-stage centrifugal pump rotor dynamics optimization method, preferably, the components affecting the hydraulic efficiency of the multi-stage centrifugal pump include: bearings and bushings; the geometric parameters and position parameters include: bearing width, bushing suction section position, bearing span, bushing suction section length and bushing length.

[0009] The multi-stage centrifugal pump rotor dynamics optimization method preferably applies gap stiffness constraints to components that affect the hydraulic efficiency of the multi-stage centrifugal pump in the pump rotor grid model, applies axial displacement constraints at the bearings, and establishes a finite element calculation model of the pump rotor system. The specific steps are as follows: In the pump rotor mesh model, gap stiffness constraints are applied at locations including the bushing suction section, bushing, impeller mouth ring, balance drum, and rotor interior, and axial displacement constraints are applied at the bearings to establish a finite element calculation model of the pump rotor system.

[0010] The multi-stage centrifugal pump rotor dynamics optimization method preferably designs an orthogonal table of geometric parameters and position parameters to form an orthogonal table of typical characteristic parameters, and calculates the first-order natural frequency of the pump rotor system under each characteristic parameter combination according to the finite element calculation model of the pump rotor system. The specific steps are as follows: In the established finite element calculation model of the pump rotor system, the bearing width, bushing suction section position, bearing span, bushing suction section length and bushing length are changed, and constraint stiffness is added at the corresponding positions to calculate the first-order natural vibration frequency of the pump rotor system.

[0011] A second aspect of the present invention provides a multi-stage centrifugal pump rotor dynamics optimization device, comprising: A first processing unit is used to obtain geometric parameters and position parameters of components that affect the hydraulic efficiency of the multi-stage centrifugal pump; The second processing unit is used to geometrically model the components that affect the hydraulic efficiency of the multi-stage centrifugal pump using three-dimensional geometric modeling software, and add them to the corresponding positions of the pump shaft to establish a pump rotor geometric model; The third processing unit is used to import the pump rotor geometric model into the meshing software to perform meshing and establish the pump rotor mesh model; The fourth processing unit is used to apply gap stiffness constraints to components that affect the hydraulic efficiency of the multi-stage centrifugal pump in the pump rotor grid model, apply axial displacement constraints at the bearings, and establish a finite element calculation model of the pump rotor system; The fifth processing unit is used to design an orthogonal table of geometric parameters and position parameters to form an orthogonal table of typical characteristic parameters, and calculate the first-order natural frequency of the pump rotor system under each characteristic parameter combination according to the finite element calculation model of the pump rotor system; The sixth processing unit is used to determine the upper and lower limits of each parameter in the geometric parameters and the position parameters according to known conditions, and select the lowest level, the middle level and the highest level within the upper and lower limits, and generate an orthogonal table of the full factorial experiment through software; The seventh processing unit is used to import the full factor test orthogonal table and the first-order natural frequency of the pump rotor system into the BP neural network for fitting; The eighth processing unit is used to import the fitted BP neural network into the Matlab genetic algorithm calculation program for optimization, so as to obtain the combination of geometric parameters and position parameters that maximizes the first-order natural frequency of the pump rotor system.

[0012] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any one of the above-mentioned methods for optimizing the rotor dynamics of a multi-stage centrifugal pump.

[0013] A fourth aspect of the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any one of the steps of the multi-stage centrifugal pump rotor dynamics optimization method described above when executing the computer program.

[0014] The present invention adopts the above technical solution, which has the following advantages: 1. Structural parameter manufacturing error and measurement error. The parameters concerned by the present invention, such as bearing model, bearing span, bushing length, etc., have a greater impact on the first-order natural vibration frequency of the pump rotor system, and the optimization method is more practical.

[0015] 2. In the design and analysis of traditional multi-stage centrifugal pumps, the parameters for optimizing the dynamic performance of the pump rotor are generally selected to optimize the pump shaft geometry parameters, bearing span and other parameters, and the optimization method is to manually select different parameter values ​​for calculation. For multi-stage centrifugal pump products that have been mass-produced by manufacturers, the main structure of the pump, such as the pump shaft geometry parameters, the inducer structure and its position on the pump shaft, the impeller structure and its position on the pump shaft, etc., have been determined, and there is very little room for optimization. The structure and position of these main components also affect the hydraulic performance parameters of the pump. To improve the dynamic performance of the pump rotor, the structure and position of these main components are changed. The overall structure of the pump must be redesigned to meet the operating requirements for its head, efficiency, and shaft power. To improve the dynamic performance of this type of centrifugal pump rotor system without affecting its head, efficiency, and shaft power requirements, it is only possible to start with the optimization of the structural parameters and position parameters of components such as bearings and bushings. The present invention targets multi-stage centrifugal pump products that have been mass-produced by manufacturers, selects the structural parameters and positions of components such as bearings and bushings as optimization parameters, uses BP neural network to fit the relationship between the optimal parameters and the first-order natural frequency of the pump rotor system, and uses a genetic algorithm to find the parameter combination with the largest first-order natural frequency of the pump rotor system, thus forming a multi-stage centrifugal pump rotor dynamics optimization method with fixed pump shaft parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of a multi-stage centrifugal pump rotor dynamics optimization method provided by an embodiment of the present invention; Figure 2 A schematic diagram of a multi-stage centrifugal pump provided in this embodiment of the present invention; Figure 3 A geometric modeling model of a multistage centrifugal pump and its rotor system provided in this embodiment of the present invention; Figure 4 An automatic mesh generation model for a rotor system in a multi-stage centrifugal pump provided in this embodiment of the present invention; Figure 5 A schematic diagram of applying gap stiffness at positions such as the bushing suction section, bushing, impeller ring, balance drum, rotor, etc., and applying axial displacement constraints at two bearings provided in this embodiment of the present invention; Figure 6 This is a comparison chart between the predicted value of the neural network trained by BP and the true value of the sample; The reference numerals are as follows: 1-bearing; 2-bushing suction section; 3-rotor; 4-balance drum; 5-impeller; 6-inducer. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention is described clearly and completely below. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work are within the scope of protection of the present invention.

[0018] Unless otherwise defined, the technical or scientific terms used in the present invention shall have the usual meanings understood by persons with ordinary skills in the field to which the present invention belongs. The words "first", "second", "third", "fourth" and similar terms used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Words such as "include" or "comprise" and the like mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Words such as "connect" or "connected" and the like are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect.

[0019] For ease of description, spatially relative terms may be used herein to describe the relationship of one element or feature relative to another element or feature as shown in the figures, such as "inside", "outside", "inner side", "outer side", "below", "above", etc. Such spatially relative terms are intended to include different orientations of the device in use or operation in addition to the orientation depicted in the figures.

[0020] In the design and analysis of traditional multi-stage centrifugal pumps, the parameters for optimizing the dynamic performance of the pump rotor are generally selected by optimizing the main structural parameters of the pump, such as the geometric parameters of the pump shaft, the position of the inducer and impeller and other components on the pump shaft, etc. However, for multi-stage centrifugal pumps that have been mass-produced by manufacturers, most of the above parameters have been determined, and there is very little room for optimization. At the same time, with the dynamic performance of the multi-stage centrifugal pump as the optimization goal, changing the design of the pump shaft and other main components will affect the hydraulic performance of the multi-stage centrifugal pump. The hydraulic performance parameters of the multi-stage centrifugal pumps that have been mass-produced by manufacturers, such as efficiency and pump shaft power, can already meet the actual operation requirements. Therefore, optimizing the pump shaft components such as bearing position and model can improve its dynamic performance without changing the hydraulic performance of the multi-stage centrifugal pump.

[0021] Based on the above technical problems, the present invention provides a method, device, medium and equipment for optimizing the rotor dynamics of a multi-stage centrifugal pump. The method analyzes and optimizes the geometric parameters and positions of components such as bearings and bushings to ensure hydraulic performance such as head efficiency, avoid high-speed pump rotor components approaching or reaching the critical speed, and ensure the safe and reliable operation of the multi-stage centrifugal pump.

[0022] like Figure 1 As shown, the multi-stage centrifugal pump rotor dynamics optimization method provided by the present invention includes the following specific steps: Step 1: Optimization parameter selection Since the pump shaft geometry, inducer structure, impeller structure and its position parameters in the pump can affect the hydraulic performance of the pump, if these main components are modified with the goal of improving the dynamic performance of the pump rotor, the multi-stage centrifugal pump products that have been mass-produced must be redesigned to take into account the head, efficiency, shaft power and other operating requirements, which is a huge workload. Therefore, in order to improve the dynamic performance of this type of centrifugal pump rotor system without affecting its hydraulic performance requirements, it can only start with the optimization of the structural parameters and position parameters of components such as bearings and bushings.

[0023] Starting with the CAD design drawing of a cryogenic submersible pump, the bearing width was selected based on structural analysis. l , Bushing suction section position L D , bearing span L , bushing suction section length and bushing (guide vane) length are optimized.

[0024] 1. Bearing width l : Check the bearing model table to select the width range limited by the original design bearing diameter.

[0025] like Figure 2 , 3 The bearing diameter of the case pump CAD design is 70mm. After checking the bearing model list, the width range of the bearing with an inner diameter of 70mm is [10mm, 51mm].

[0026] 2. Bushing suction section position L D : The position of the bushing suction section will affect the overall stiffness of the pump rotor component, and then affect the first-order natural frequency of the pump rotor component. The distance between the bushing suction section 2 and the top of the rotor is measured and used as the limit value of the bushing suction section position for optimization.

[0027] like Figure 2 , 3 The position limit value of the bushing suction section 2 in the case drawing is 122mm, and the position optimization range of the bushing suction section 2 is [107mm, 122mm] (the original design value is 107mm).

[0028] 3. Bearing span L :Bearing 1 changes the stiffness of the pump rotor system. If there is more than one bearing 1 on the pump rotor system, the span between different bearings 1 needs to be measured. L , by optimizing the span LTo optimize the vibration natural frequency of the pump rotor system, it is necessary to determine the movable distance of bearing 1 at different pump shaft positions to determine the limit value of the bearing span.

[0029] like Figure 3 As shown in the case CAD drawing, the bearing at the balance drum 4 cannot be moved, but the bearing 1 at the end of the shaft can be moved, and the bearing span range is [880mm, 912mm].

[0030] 4. Length of the bushing suction section 2: According to research, bushings come in many specifications and can also be customized by manufacturers. Therefore, the length of the bushing can be set according to the length limit of the shaft in the CAD design drawing.

[0031] like Figure 2 , 3 As shown in the case CAD drawing, the length range of the bushing suction section 2 is [48mm, 63mm].

[0032] 5. Bushing (guide vane) length: According to research, bushings come in many specifications and can also be customized by manufacturers. Therefore, the length of the bushing can be set according to the length limit of the shaft in the CAD design drawing.

[0033] like Figure 2 , 3 As shown in the case CAD drawing, the length range of the bushing (guide vane) is [80mm, 92mm].

[0034] Figure 2 , 3 This is the case pump in the solution of the present invention. It should be noted that the CAD design drawing is a collection of parts that do not affect the hydraulic performance of the pump.

[0035] According to the manufacturer's CAD design drawings, professional 3D geometric modeling software such as Solidworks and ProE are used to geometrically model the components that affect the hydraulic efficiency of the pump, such as the inducer and impeller, and add them to the corresponding positions of the pump shaft.

[0036] Import the pump rotor geometry created by the 3D geometry software into the meshing software for meshing. Typical meshing software includes ICEM, ANSYS Workbench's built-in Mesh module, etc. The case pump uses ANSYS Workbench's built-in Mesh module for automatic meshing. Figure 4 shown.

[0037] Figure 4 They are respectively the Solidworks case pump rotor system geometric modeling model, and the case pump rotor system uses Workbench mesh for automatic meshing.

[0038] The gap stiffness is applied at the positions of the bushing suction section 2, bushing (guide vane), impeller ring, balance drum 4, rotor 3, etc., and the axial displacement constraint is applied at the two bearings 1. The axial displacement constraint and gap stiffness are applied as follows: Figure 5 shown.

[0039] Subsequently, in the established finite element calculation model of the pump rotor system, the bearing width, bushing suction section position, bearing span, bushing suction section length and bushing (guide vane) length were changed, and constraint stiffness was added at the corresponding positions to calculate the first-order natural frequency of the pump rotor system.

[0040] Step 2: Orthogonal Experimental Design As mentioned above, a total of five parameters, namely bearing width, bushing suction section position, bearing span, bushing suction section length and bushing (guide vane) length, were selected to optimize the vibration natural frequency of the pump rotor. The five parameters can form infinite combinations within their respective value ranges. In order to reduce the amount of calculation, it is necessary to design an orthogonal table for these five parameters, form an orthogonal table of typical characteristic parameters, and calculate the first-order natural frequency of the pump rotor system under each characteristic parameter combination. This can ensure the balanced dispersion and neat comparability of the parameter combination, and at the same time greatly reduce the amount of calculation. The orthogonal table design can be automatically formed through SPSS software.

[0041] The upper and lower limits of each parameter are determined according to known conditions, and the lowest level, middle level and highest level are selected within the upper and lower limits of the parameters. 16 sets of full-factor experimental orthogonal tables are generated by SPSS, and the first-order natural frequency of the pump rotor system under each parameter combination is calculated by FLUENT to form the training parameters of the BP neural network.

[0042] Table 1 is the orthogonal table of 16 groups of full factorial experiments for the case pump.

[0043] Table 1

[0044] Step 3: BP neural network fitting The full factor test orthogonal table and the first-order natural frequency of the pump rotor system calculated by the corresponding finite element calculation model of the pump rotor system are imported into the BP neural network for fitting. The error of the neural network model after fitting is as follows: Figure 6As shown in the figure, the model average absolute error MAE is: 0.065425 (less than 0.1 is accurate); the mean square error MSE is: 0.0053062 (less than 0.1 is accurate); the root mean square error RMSEP is: 0.072843 (less than 0.1 is accurate); the determination coefficient R2 is: 0.74649; the residual prediction residual RPD is: 1.9861; the average absolute percentage error MAPE is: 0.1314. The model accuracy is very high, and it can be considered that the neural network model fitted by Matlab can be used to fit the relationship between the five optimization parameters and the first-order natural frequency of the pump rotor system.

[0045] Step 4: Genetic Algorithm Optimization The advantage of genetic algorithms is that they can automatically acquire and accumulate search space information. Unlike general optimization methods, they do not have specific requirements for the required objective function. They only need a non-negative fitness function that can be compared. They can be used for optimization problems where the objective function is not differentiable or the derivative of the objective function is difficult to find. They also have inherent implicit parallelism. Genetic optimization algorithms do not directly process the actual values ​​of the optimization variables, but can process multiple individuals in the group at the same time, which increases the probability of finding the global optimum. The following optimization model is established when optimizing the first-order natural frequency of the pump rotor system: The BP neural network fitted in the previous section was imported into the Matlab genetic algorithm calculation program for optimization. The final optimized result was: l 51mm, bushing suction section position L D The bearing span is 112mm L The range is 900mm, the length of the liner suction section is 62mm, and the liner length is 88.5mm. The first-order natural frequency of the optimized pump rotor system is 249Hz.

[0046] The five optimized characteristic parameters are brought into the established finite element calculation model of the pump rotor system, and the positions and lengths of the bearings and bushings are adjusted to compound the optimized parameters. It is calculated that the first-order natural frequency of the optimized pump rotor system is 243.39 Hz, which is not much different from the 249 Hz natural frequency optimized by the genetic algorithm. The optimized first-order critical speed is 1529.3 rad / s, which is farther away from the rated speed of the pump shaft by 306.6 rad / s than the first-order critical speed before optimization of 936.66 rad / s.

[0047] The present invention proposes a rotor dynamics optimization method for a multi-stage centrifugal pump with fixed pump shaft parameters. Compared with the pump rotor system dynamics optimization method involved in the prior art, it has the following advantages: The manufacturing error and measurement error of structural parameters, the parameters such as bearing model, bearing span, bushing length, etc. that the present invention focuses on, have a greater impact on the first-order natural vibration frequency of the pump rotor system, and the optimization method is more practical.

[0048] In the design and analysis of traditional multi-stage centrifugal pumps, the parameters for optimizing the dynamic performance of the pump rotor are generally selected to optimize the pump shaft geometry parameters, bearing span and other parameters, and the optimization method is to manually select different parameter values ​​for calculation. For multi-stage centrifugal pump products that have been mass-produced by manufacturers, the main structure of the pump, such as the pump shaft geometry parameters, the inducer structure and its position on the pump shaft, the impeller structure and its position on the pump shaft, etc., have been determined, and there is very little room for optimization. The structure and position of these main components also affect the hydraulic performance parameters of the pump. To improve the dynamic performance of the pump rotor, the structure and position of these main components are changed. The overall structure of the pump must be redesigned to meet the operating requirements for its head, efficiency, and shaft power. To improve the dynamic performance of this type of centrifugal pump rotor system without affecting its head, efficiency, and shaft power requirements, it is only possible to start with the optimization of the structural parameters and position parameters of components such as bearings and bushings. The present invention targets multi-stage centrifugal pump products that have been mass-produced by manufacturers, selects the structural parameters and positions of components such as bearings and bushings as optimization parameters, uses BP neural network to fit the relationship between the optimal parameters and the first-order natural frequency of the pump rotor system, and uses a genetic algorithm to find the parameter combination with the largest first-order natural frequency of the pump rotor system, thus forming a multi-stage centrifugal pump rotor dynamics optimization method with fixed pump shaft parameters.

[0049] A second aspect of the present invention provides a multi-stage centrifugal pump rotor dynamics optimization device, comprising: A first processing unit is used to obtain geometric parameters and position parameters of components that affect the hydraulic efficiency of the multi-stage centrifugal pump; The second processing unit is used to geometrically model the components that affect the hydraulic efficiency of the multi-stage centrifugal pump using three-dimensional geometric modeling software, and add them to the corresponding positions of the pump shaft to establish a pump rotor geometric model; The third processing unit is used to import the pump rotor geometric model into the meshing software to perform meshing and establish the pump rotor mesh model; The fourth processing unit is used to apply gap stiffness constraints to components that affect the hydraulic efficiency of the multi-stage centrifugal pump in the pump rotor grid model, apply axial displacement constraints at the bearings, and establish a finite element calculation model of the pump rotor system; The fifth processing unit is used to design an orthogonal table of geometric parameters and position parameters to form an orthogonal table of typical characteristic parameters, and calculate the first-order natural frequency of the pump rotor system under each characteristic parameter combination according to the finite element calculation model of the pump rotor system; The sixth processing unit is used to determine the upper and lower limits of each parameter in the geometric parameters and the position parameters according to known conditions, and select the lowest level, the middle level and the highest level within the upper and lower limits, and generate an orthogonal table of the full factorial experiment through software; The seventh processing unit is used to import the full factor test orthogonal table and the first-order natural frequency of the pump rotor system into the BP neural network for fitting; The eighth processing unit is used to import the fitted BP neural network into the Matlab genetic algorithm calculation program for optimization, so as to obtain the combination of geometric parameters and position parameters that maximizes the first-order natural frequency of the pump rotor system.

[0050] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any one of the above-mentioned methods for optimizing the rotor dynamics of a multi-stage centrifugal pump.

[0051] A fourth aspect of the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any one of the steps of the multi-stage centrifugal pump rotor dynamics optimization method described above when executing the computer program.

[0052] The present invention is described in terms of flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to specific embodiments. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0053] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0054] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0055] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing rotor dynamics of a multistage centrifugal pump, characterized in that: include: Obtain the geometric parameters and position parameters of the components that affect the hydraulic efficiency of the multi-stage centrifugal pump; Use 3D geometric modeling software to geometrically model the components that affect the hydraulic efficiency of the multi-stage centrifugal pump, add them to the corresponding positions of the pump shaft, and establish the pump rotor geometric model; Import the pump rotor geometric model into the meshing software for meshing and establish the pump rotor mesh model; In the pump rotor mesh model, gap stiffness constraints are imposed on the components that affect the hydraulic efficiency of the multi-stage centrifugal pump, axial displacement constraints are imposed on the bearings, and a finite element calculation model of the pump rotor system is established; The geometric parameters and position parameters are designed into an orthogonal table to form an orthogonal table of typical characteristic parameters, and the first-order natural frequency of the pump rotor system under each characteristic parameter combination is calculated according to the finite element calculation model of the pump rotor system; Determine the upper and lower limits of each parameter in the geometric parameters and location parameters according to known conditions, select the lowest level, the middle level and the highest level within the upper and lower limits, and generate the orthogonal table of the full factorial experiment through the software; The full factorial test orthogonal table and the first-order natural frequency of the pump rotor system are imported into the BP neural network for fitting; The fitted BP neural network was imported into the Matlab genetic algorithm calculation program for optimization, and the combination of geometric parameters and position parameters that maximized the first-order natural frequency of the pump rotor system was obtained.

2. The multi-stage centrifugal pump rotor dynamics optimization method according to claim 1, characterized in that: The components that affect the hydraulic efficiency of a multistage centrifugal pump include bearings and bushings; the geometric parameters and position parameters include bearing width, bushing suction section position, bearing span, bushing suction section length, and bushing length.

3. The multi-stage centrifugal pump rotor dynamics optimization method according to claim 2, characterized in that: In the pump rotor mesh model, gap stiffness constraints are applied to the components that affect the hydraulic efficiency of the multi-stage centrifugal pump, axial displacement constraints are applied to the bearings, and a finite element calculation model of the pump rotor system is established. The specific steps are as follows: In the pump rotor mesh model, gap stiffness constraints are applied at locations including the bushing suction section, bushing, impeller mouth ring, balance drum, and rotor interior, and axial displacement constraints are applied at the bearings to establish a finite element calculation model of the pump rotor system.

4. The multi-stage centrifugal pump rotor dynamics optimization method according to claim 3, characterized in that: The geometric parameters and position parameters are designed into an orthogonal table to form an orthogonal table of typical characteristic parameters, and the first-order natural frequency of the pump rotor system under each characteristic parameter combination is calculated according to the finite element calculation model of the pump rotor system. The specific steps are as follows: In the established finite element calculation model of the pump rotor system, the bearing width, bushing suction section position, bearing span, bushing suction section length and bushing length are changed, and constraint stiffness is added at the corresponding positions to calculate the first-order natural vibration frequency of the pump rotor system.

5. A multi-stage centrifugal pump rotor dynamics optimization device, characterized in that: include: A first processing unit is used to obtain geometric parameters and position parameters of components that affect the hydraulic efficiency of the multi-stage centrifugal pump; The second processing unit is used to geometrically model the components that affect the hydraulic efficiency of the multi-stage centrifugal pump using three-dimensional geometric modeling software, and add them to the corresponding positions of the pump shaft to establish a pump rotor geometric model; The third processing unit is used to import the pump rotor geometric model into the meshing software to perform meshing and establish the pump rotor mesh model; The fourth processing unit is used to apply gap stiffness constraints to components that affect the hydraulic efficiency of the multi-stage centrifugal pump in the pump rotor grid model, apply axial displacement constraints at the bearings, and establish a finite element calculation model of the pump rotor system; The fifth processing unit is used to design an orthogonal table of geometric parameters and position parameters to form an orthogonal table of typical characteristic parameters, and calculate the first-order natural frequency of the pump rotor system under each characteristic parameter combination according to the finite element calculation model of the pump rotor system; The sixth processing unit is used to determine the upper and lower limits of each parameter in the geometric parameters and the position parameters according to known conditions, and select the lowest level, the middle level and the highest level within the upper and lower limits, and generate an orthogonal table of the full factorial experiment through software; The seventh processing unit is used to import the full factor test orthogonal table and the first-order natural frequency of the pump rotor system into the BP neural network for fitting; The eighth processing unit is used to import the fitted BP neural network into the Matlab genetic algorithm calculation program for optimization, so as to obtain the combination of geometric parameters and position parameters that maximizes the first-order natural frequency of the pump rotor system.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the multi-stage centrifugal pump rotor dynamics optimization method according to any one of claims 1 to 4 are implemented.

7. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the multi-stage centrifugal pump rotor dynamics optimization method according to any one of claims 1 to 4 are implemented.

Images