Structural parameter configuration method and device of turbo molecular pump and turbo molecular pump

Abstract

The invention relates to the field of vacuum pump design, in particular to a structural parameter configuration method and device of a turbo molecular pump and the turbo molecular pump. The method comprises the steps that design variables are determined according to the blade row type of a target turbo molecular pump; creating a parameter population corresponding to the design variable; generating a new parameter population by using a genetic algorithm; respectively determining performance index values in the new parameter population by adopting a simulation algorithm; and screening out a target parameter group from the new parameter population according to the performance index value, and determining the structure of the target turbo molecular pump. According to the scheme provided by the invention, the corresponding structure parameters can be selected in advance according to the design, so that the blade array structure parameters are optimized in a targeted manner; a genetic algorithm is adopted to find an optimal turbo molecular pump structure, so that blindness and low efficiency of a traditional traversal method are effectively avoided; the genetic algorithm can intelligently search a parameter space and quickly find a parameter combination with excellent performance, so that the efficiency of structural parameter configuration is remarkably improved.

Description

Technical Field

[0001] The present disclosure relates to the field of vacuum pump design, and in particular to a method and device for configuring structural parameters of a turbomolecular pump, and a turbomolecular pump. Background Art

[0002] As a highly efficient vacuum pump, the turbomolecular pump plays a vital role in fields such as metallurgy, electronics, and aerospace. Its operating principle is to transfer momentum to gas molecules through high-speed rotation, causing the gas to flow in a directional manner and achieve vacuum. This unique working principle gives it significant advantages when dealing with high-vacuum environments. Existing design methods for turbomolecular pumps often use a traversal approach, which searches through all possible structural designs within the turbomolecular pump to find the most suitable design. This approach is highly unreliable and requires permutations and combinations of all possible scenarios. Optimization is very time-consuming and fails to identify corresponding alternative solutions based on practical constraints. Summary of the Invention

[0003] The embodiments of the present disclosure provide a method and device for configuring the structural parameters of a turbomolecular pump, and a turbomolecular pump. By comprehensively considering the impact of all parameters on the performance of the turbomolecular pump, the problems of existing turbomolecular pump design methods, such as long design time, high blindness, and lack of alternative solutions to cope with various restrictive conditions, are solved.

[0004] Based on the above problems, in a first aspect, an embodiment of the present disclosure provides a method for configuring structural parameters of a turbomolecular pump, comprising:

[0005] Determining design variables according to the blade row type of the target turbomolecular pump; wherein the design variables include structural parameters of the blade row corresponding to the blade row type;

[0006] Creating a parameter population corresponding to the design variable; wherein the parameter population includes a plurality of parameter groups, each parameter group including a set of values of the structural parameters included in the design variable;

[0007] Optimizing the parameter population using a genetic algorithm to generate a new parameter population that meets preset optimization constraints;

[0008] Determining performance index values for each parameter group in the new parameter population using a simulation algorithm;

[0009] A target parameter group is screened out from the new parameter population according to the performance index value, and the target turbomolecular pump is configured according to the target parameter group to determine the structure of the target turbomolecular pump.

[0010] In conjunction with the first aspect, in a possible implementation, the optimizing the parameter population using a genetic algorithm to generate a new parameter population that meets preset optimization constraints includes:

[0011] Use the created parameter population as the current parameter population; perform multiple iterations, and perform the following steps in each iteration:

[0012] Performing a selection operation on the parameter group in the current parameter population according to a preset selection algorithm to obtain a parent parameter group;

[0013] Performing a crossover operation on the parent parameter group according to a preset crossover algorithm to obtain an intermediate parameter group;

[0014] Performing a mutation operation on the structural parameters of the leaf columns in the intermediate parameter group according to a preset mutation algorithm to obtain a child parameter group;

[0015] For each child parameter group, determining whether the structural parameters of the leaf columns in the child parameter group all meet corresponding preset optimization constraints;

[0016] If there are structural parameters in the child parameter group that do not meet the preset optimization constraint conditions, returning to the step of performing a crossover operation on the parent parameter group according to a preset crossover algorithm;

[0017] If all structural parameters in the offspring parameter group satisfy the preset optimization constraint condition, then the combination of the offspring parameter group and the parent parameter group is determined as a new parameter population;

[0018] The adopting of a simulation algorithm to determine performance index values for each parameter group in the new parameter population includes:

[0019] A simulation algorithm is used to determine the performance index value for the offspring parameter group; if the convergence condition is not met, the next iteration is entered; if the iterative convergence condition is met, the current parameter population is output as a new parameter population.

[0020] In combination with the first aspect, in a possible implementation, the preset optimization constraint condition includes: a value range of at least one structural parameter; or

[0021] The value range of at least one structural parameter and at least one of the following: the value accuracy of the structural parameter and the restriction relationship between preset structural parameters; the restriction relationship between the preset structural parameters is used to characterize the structural limitations of the leaf row in the physical structure.

[0022] In conjunction with the first aspect, in a possible implementation manner, before the step of determining the design variables according to the blade row type of the target turbomolecular pump, the method further includes:

[0023] Determine the structural parameters corresponding to each leaf row type;

[0024] Establishing a structural parameter set; wherein the structural parameter set includes at least one of the following: structural parameters corresponding to each leaf row type, value ranges of the structural parameters, value precisions of the structural parameters, and leaf rows at specific locations applicable to each leaf row type;

[0025] Performing a logic self-check on the set of structural parameters based on a preset self-check logic;

[0026] The preset self-test logic includes:

[0027] In a case where the structural parameter set includes a leaf row at a specific position applicable to the corresponding leaf row type, checking whether all leaf row types are provided with a leaf row at the corresponding specific position; if there is a leaf row type that does not have a leaf row at the corresponding specific position, the self-check fails;

[0028] When the set of structural parameters includes a value range for each structural parameter, and the value range includes a maximum boundary and a minimum boundary, the maximum boundary and the minimum boundary are compared; if the maximum boundary is smaller than the minimum boundary, the self-test fails;

[0029] The restriction relationship between the preset structural parameters is detected. If any restriction relationship between the preset structural parameters does not meet the preset restriction relationship, the self-test fails.

[0030] In conjunction with the first aspect, in one possible implementation, determining the design variables according to the blade row type of the target turbomolecular pump includes:

[0031] Determine the type of blade rows included in the target turbomolecular pump;

[0032] The design variables and the value ranges of the structural parameters contained therein are matched for the leaf row type from the structural parameter set, or the design variables and the value ranges and value precisions of the structural parameters contained therein are matched for the leaf row type.

[0033] In conjunction with the first aspect, in one possible implementation, creating a parameter population corresponding to the design variable includes:

[0034] Determining the value of the first structural parameter in each parameter group according to the value range of the first structural parameter included in the design variable; and

[0035] determining the value of the second structural parameter in each parameter group according to a restriction relationship between the second structural parameter included in the design variable and the related first structural parameter;

[0036] The parameter group with determined values is used as the parameter population corresponding to the design variables.

[0037] In conjunction with the first aspect, in a possible implementation manner, screening out a target parameter group from the new parameter population according to the performance indicator value includes:

[0038] Sort the performance index values corresponding to the new parameter population in descending order to obtain a sequence of parameter groups;

[0039] A parameter group is selected from the sequence according to preset requirements and output as a target parameter group.

[0040] In combination with the first aspect, in a possible embodiment, the structural parameters of the blade row include at least one of the following: blade row outer diameter, blade row inner diameter, blade thickness, blade row height, number of blades, blade root inclination angle, and blade tip inclination angle; and / or

[0041] The performance index value includes at least one of the following: maximum compression ratio, maximum Ho coefficient and maximum pumping speed.

[0042] In a second aspect, the present disclosure provides a device for configuring structural parameters of a turbomolecular pump, comprising:

[0043] a first determining module, configured to determine design variables according to a blade row type of a target turbomolecular pump; wherein the design variables include structural parameters of the blade row corresponding to the blade row type;

[0044] A creation module, configured to create a parameter population corresponding to the design variable; wherein the parameter population includes a plurality of parameter groups, each parameter group including a set of values of the structural parameters included in the design variable;

[0045] An optimization module is used to optimize the parameter population using a genetic algorithm to generate a new parameter population that meets preset optimization constraints;

[0046] A second determination module is used to determine performance index values for each parameter group in the new parameter population using a simulation algorithm;

[0047] A screening module is configured to screen out a target parameter group from the new parameter population according to the performance indicator value, and configure the target turbomolecular pump according to the target parameter group to determine the structure of the target turbomolecular pump.

[0048] In a third aspect, the present disclosure provides a turbomolecular pump, the structure of which is obtained based on the method described in any one of the first aspects.

[0049] The beneficial effects of the embodiments of the present disclosure include:

[0050] The present disclosure provides a method, device and turbomolecular pump for configuring the structural parameters of a turbomolecular pump, comprising: determining design variables according to the blade row type of a target turbomolecular pump; wherein the design variables include the structural parameters of the blade row corresponding to the blade row type; creating a parameter population corresponding to the design variables; wherein the parameter population includes multiple parameter groups, each parameter group including a set of values of the structural parameters contained in the design variables; optimizing the parameter population using a genetic algorithm to generate a new parameter population that meets preset optimization constraints; using a simulation algorithm to determine performance index values for the parameter groups in the new parameter population; screening the target parameter group from the new parameter population according to the performance index value, and configuring the target turbomolecular pump according to the target parameter group to determine the structure of the target turbomolecular pump. The present disclosure provides a method, device and turbomolecular pump for configuring the structural parameters of a turbomolecular pump, which can pre-select the corresponding structural parameters according to the design to achieve targeted optimization of the blade row structural parameters; using a genetic algorithm to find the preferred turbomolecular structure, effectively avoiding the blindness and inefficiency of the traditional traversal method. Genetic algorithms can intelligently search the parameter space and quickly find parameter combinations with excellent performance, significantly improving the efficiency of structure determination. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A schematic flow chart of a method for configuring structural parameters of a turbomolecular pump provided in an embodiment of the present disclosure;

[0052] Figure 2 A schematic diagram of a structural parameter configuration device for a turbomolecular pump provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0053] The present disclosure provides a method and apparatus for configuring the structural parameters of a turbomolecular pump, and a turbomolecular pump. Preferred embodiments of the present disclosure are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are intended only to illustrate and explain the present disclosure and are not intended to limit the present disclosure. Furthermore, the embodiments and features within the embodiments of the present disclosure may be combined with one another unless there is a conflict.

[0054] The embodiment of the present disclosure provides a method for configuring the structural parameters of a turbomolecular pump, such as Figure 1 As shown, the following steps can be performed:

[0055] S101. Determine design variables according to the blade row type of the target turbomolecular pump;

[0056] The design variables include the structural parameters of the leaf row corresponding to the leaf row type;

[0057] S102, creating a parameter population corresponding to the design variables;

[0058] The parameter population includes multiple parameter groups, and each parameter group includes a set of values of structural parameters included in the design variables;

[0059] S103, optimizing the parameter population using a genetic algorithm to generate a new parameter population that meets preset optimization constraints;

[0060] S104, using a simulation algorithm to determine performance index values for each parameter group in the new parameter population;

[0061] S105 , selecting a target parameter group from the new parameter population according to the performance index value, and configuring a target turbomolecular pump according to the target parameter group to determine the structure of the target turbomolecular pump.

[0062] In the embodiments disclosed herein, the main structures of a target turbomolecular pump may include a pump body, a rotor array, a stationary array, and a drive device. The pump body is the structural support component of the turbomolecular pump, supporting and protecting the internal components; the drive device may be an electric motor or other device capable of providing power to the rotor array. The rotor and stationary arrays are the core components of a turbomolecular pump and are key to its structural design. The rotor array is a rotor with blades arranged in a tilted, turbine-like pattern. The rotor array can rotate at high speeds driven by a rotating shaft under the drive device. Gas molecules, upon colliding with the high-speed rotating rotor array, acquire a directional velocity, thereby being propelled in a specific direction. The stationary array is fixed within the pump body. The blades can have a complementary orientation to the rotor array and can be arranged in an alternating, step-by-step arrangement. This serves to guide the flow of gas molecules, enabling efficient compression and transmission within the turbomolecular pump. The method for configuring the structural parameters of a turbomolecular pump provided herein primarily targets the configuration of the structural parameters of the rotor and stationary arrays, thereby altering the overall performance of the turbomolecular pump. Furthermore, the design of the turbomolecular pump can be achieved by configuring the structural parameters of the turbomolecular pump.

[0063] In the disclosed embodiment, the blade rows in the turbomolecular pump can belong to different blade row types. The factors that affect the performance of the turbomolecular pump in different blade row types are design variables. In each blade row type of the turbomolecular pump, there is at least one blade row belonging to that blade row type; blade rows belonging to the same blade row type have the same blade row structural parameters; and blade rows belonging to different blade row types have at least one different blade row structural parameter. In the design phase of the turbomolecular pump, it is necessary to carry out targeted optimization and design of the blade row structural parameters. These blade row structural parameters can jointly define the specific size and shape of each level of the turbomolecular pump blade row.

[0064] The above-mentioned blade row types can be presented as a series consisting of the blade row's structural parameters, with each item in the series corresponding to a blade row's structural parameter. Each blade row's structural parameter represents the numerical value of the corresponding blade row's structure. By changing the value of the blade row's structural parameter, the blade row's structure is altered, thereby changing the blade row's ability to drive gas molecules and further changing the overall turbomolecular pump performance. In actual application, the structural parameters of the corresponding blade row can be selected based on the design optimization direction, and the corresponding parameter range can be set for the structural parameters of the corresponding blade row. At the same time, a fixed value is determined for the structural parameters of other blade rows, thereby determining an optimization direction.

[0065] The number sequences corresponding to all the blade rows in the turbomolecular pump are grouped into a set of numbers according to the order of the blade rows in the turbomolecular pump. This set of numbers can be presented in the form of a matrix, and the number sequence corresponding to each blade row can correspond to a row or column in this set of numbers. This set of numbers is a parameter group, and each parameter group represents a possible configuration scheme for the structural parameters of the turbomolecular pump.

[0066] A collection of multiple parameter groups is called a parameter population, and the parameter population represents various possible configuration schemes of the structural parameters of the turbomolecular pump.

[0067] The correspondence between the leaf row type and the structural parameters of the leaf row can be expressed as a structural design parameter table. A possible table format is shown in Table 1 below.

[0068]

[0069]

[0070] Table 1 Structural design parameters

[0071] In Table 1, the row inner diameter parameter d refers to the row inner diameter or tooth root diameter, the row inner diameter D refers to the row outer diameter or tooth tip diameter, the number of blades z refers to the number of blades (teeth) in each row, the root angle α1 refers to the blade root angle at each row, the tip angle α2 refers to the blade tip angle at each row, the row height h refers to the height of each row, and the blade thickness t refers to the blade thickness of each row. For each blade level, α1 at the tooth root varies linearly to α2 at the tooth tip.

[0072] In Table 1, Y represents the total number of blade rows in the target turbomolecular pump. Because the rotating and stationary blade rows in a turbomolecular pump can be arranged alternately, the number of rotating and stationary blade rows each accounts for half of the turbomolecular pump. Dynamic 1, Dynamic 2, through Dynamic [Y / 2] represent the specific positions of the corresponding rotating blade rows in the target turbomolecular pump. "Dynamic 1" indicates that this type of blade row is applicable to the first stage of the turbomolecular pump, "Dynamic 2" indicates that this type of blade row is applicable to the second stage of the turbomolecular pump, and so on. "Dynamic [Y / 2]" indicates that this type of blade row is applicable to the Y / 2th stage of the turbomolecular pump. Generally, the first stage of a turbomolecular pump can be a moving blade row. Therefore, "Moving 1" can also represent the first-stage blade row, "Moving 2" can represent the third-stage blade row, and "Moving [Y / 2]" can represent the Y-1st-stage blade row. Similarly, "Static 1" indicates that this type of blade row is applicable to the turbomolecular pump and is also the first-stage stationary blade row, "Static 2" indicates that this type of blade row is applicable to the turbomolecular pump and is also the second-stage stationary blade row, and so on. "Static [Y / 2]" indicates that this type of blade row is applicable to the turbomolecular pump and is also the Y / 2nd-stage stationary blade row. Similarly, "Static 1" can also represent the second-stage blade row, "Static 2" can represent the fourth-stage blade row, and "Static [Y / 2]" can represent the Yth-stage blade row. The value of "Static [Y / 2]" can be rounded down, and the value of "Moving [Y / 2]" can be rounded up.

[0073] In Table 1, the leaf row types are numbered (1, 2, and so on, Num) to represent different leaf row types, with Num representing the total number of leaf row types. The design variables for the leaf row series corresponding to the same leaf row type in Table 1 have the same minimum, maximum, and precision parameters. The minimum and maximum values of each parameter indicate the range of values that the parameter can take in subsequent optimization. Values outside this range are illegal. Furthermore, if the minimum and maximum values are not equal, other parameters theoretically have an infinite number of possible values within the range defined by the minimum and maximum values. Therefore, precision constraints must be used to limit these infinite possible values to a finite number during the optimization process. The values of some design variables must conform to practical logic. For example, variables such as the number of blades must be positive integers, and their precision must be multiples of 1.

[0074] By limiting the minimum and maximum values of design variables and their accuracy, a clear range of parameter values and accuracy limits are provided for the subsequent optimization process, ensuring the feasibility of the design and manufacturing accuracy. By providing detailed structural parameter settings for the turbomolecular pump, the performance of the turbomolecular pump obtained after parameter configuration can be ensured to meet the target performance range.

[0075] Furthermore, a genetic algorithm is used to process the parameter population. The genetic algorithm is an optimization algorithm derived from the idea of biological evolution. It simulates mechanisms such as natural selection and genetic variation in nature through algorithms such as selection, crossover and mutation. In this embodiment, after processing the parameter population using a genetic algorithm, a new parameter population can be obtained. By simulating all parameter groups in the new parameter population using a simulation algorithm, the performance index values of the turbomolecular pump represented by all parameter groups in the new parameter population can be obtained. Finally, based on these performance index values, the target parameter group can be screened out from the obtained new parameter population according to the needs, and the structural parameters of the blade row represented by the target parameter group can be determined as the structure of the target turbomolecular pump.

[0076] The above simulation algorithm simulation can be calculated using the Monte Carlo simulation method. The Monte Carlo simulation method is a numerical calculation method based on probability statistics. It solves complex problems through random sampling and repeated experiments. Its core idea is to use the statistical results of a large number of random samples to approximate the true solution. In this embodiment, simulation calculations can be performed by the following method, which is only an example and not a limitation. First, a turbomolecular pump structure can be built, and boundary conditions such as the turbomolecular pump speed and gas temperature can be clarified. The gas molecule velocity distribution function can be randomly sampled to determine the initial velocity and direction of the molecules; then, collisions between molecules and between molecules and internal components of the pump can be considered, and collisions can be handled with corresponding models; the number of molecules passing through a specific cross section can be counted to calculate the flow rate; finally, performance indicators such as compression ratio and pumping efficiency can be calculated based on parameters such as molecular density and velocity distribution combined with gas flow and mechanics principles.

[0077] As a parameter characterizing the turbomolecular pump's operating capacity, performance indicators can be used as a basis for selecting parameter groups within a new parameter population. In practical applications, factors such as the turbomolecular pump's operating scenario and production costs can also be used as screening criteria to identify suitable parameter groups, taking into account factors that constrain the turbomolecular pump's practical application. The turbomolecular pump can be configured based on the blade row structural parameters within the selected parameter group to obtain the target turbomolecular pump.

[0078] Combining the above steps, the present disclosure achieves comprehensive optimization of the turbomolecular pump structure. The present invention utilizes a genetic algorithm to optimize multiple design variables, whereas the prior art fails to fully consider the impact of multiple variables and thus cannot achieve comprehensive optimization. This method not only improves optimization efficiency but also considers the constraints in actual processing and installation, providing more scientific and efficient guidance for the design of turbomolecular pumps. This method is more efficient than the prior art traversal method, and its advantages are more pronounced when there are many design variables.

[0079] In another embodiment provided by the present disclosure, the above step S103 of "optimizing the parameter population using a genetic algorithm to generate a new parameter population that meets the preset optimization constraints" can be implemented as follows:

[0080] Step 1: Use the created parameter population as the current parameter population; perform multiple iterations, and perform the following steps in each iteration:

[0081] Step 2: Perform a selection operation on the parameter group in the current parameter population according to a preset selection algorithm to obtain a parent parameter group;

[0082] Step 3: Perform a crossover operation on the parent parameter group according to a preset crossover algorithm to obtain an intermediate parameter group;

[0083] Step 4: Perform mutation operations on the structural parameters of the leaf columns in the intermediate parameter group according to the preset mutation algorithm to obtain the offspring parameter group;

[0084] Step 5: For each offspring parameter group, determine whether the structural parameters of the leaf columns in the offspring parameter group all meet the corresponding preset optimization constraints;

[0085] Step 6: If there are structural parameters in the offspring parameter group that do not meet the preset optimization constraints, return to the step of performing a crossover operation on the parent parameter group according to the preset crossover algorithm;

[0086] Step 7: If all structural parameters in the offspring parameter group meet the preset optimization constraints, the combination of the offspring parameter group and the parent parameter group is determined as a new parameter population;

[0087] The above step S104 of "using a simulation algorithm to determine performance index values for each parameter group in the new parameter population" can be implemented as follows:

[0088] A simulation algorithm is used to determine the performance index value for the offspring parameter group; if the convergence condition is not met, the next iteration is entered; if the iterative convergence condition is met, the current parameter population is output as a new parameter population.

[0089] In the disclosed embodiments, a genetic algorithm can be an optimization algorithm based on principles such as natural selection and genetic mechanisms in biological evolution. It simulates the evolution of biological populations to gradually approach the optimal solution to a problem. Genetic algorithms are implemented using a variety of algorithms, including selection, crossover, and mutation algorithms. Before implementing a genetic algorithm, parameters such as the selection strategy, crossover probability, mutation probability, population size, and convergence criteria can be set based on the design objectives.

[0090] A selection algorithm selects individuals with high fitness from a simulated biological population, increasing their chances of inheriting their genetic information to the next generation. In this disclosure, a performance indicator of a turbomolecular pump, represented by a parameter set, can be used as fitness. A selection algorithm can be used to select parameter sets from a parameter population. Selection algorithms can include roulette wheel selection, tournament selection, and random traversal sampling.

[0091] In one possible implementation, taking the tournament selection method as an example, a certain number of parameter groups are selected from the parameter population, these parameter groups are organized into a population, the performance index values between the parameter groups are compared, and individuals with higher performance index values are selected as dominant individuals as the parent parameter group for this genetic algorithm processing.

[0092] The crossover algorithm simulates the genetic recombination process during biological reproduction. By exchanging gene segments from the parent generation and combining them with the parent's gene segments to create offspring, the characteristics of the parent individuals are passed on to the offspring. The crossover operation reshuffles parameter sets to produce new ones. The crossover probability defines the probability of executing a crossover operation—that is, the probability of generating an offspring parameter set from a parent parameter set. The choice of crossover probability should be tailored to the needs of the algorithm. A high crossover probability can accelerate evolution toward the optimal direction but may lead to trapping in a local optimum. A low crossover probability reduces the number of crossovers, relying on mutation operations to explore new areas, which may reduce computational efficiency. Crossover can be implemented in various ways, including single-point crossover, multi-point crossover, and uniform crossover.

[0093] In one possible implementation, taking the single-point crossover method as an example, a crossover point is randomly selected between the structural parameters of the leaf columns in the parent parameter group, and the structural parameters of the leaf columns after the crossover point in the two parent parameter groups are exchanged to obtain two intermediate parameter groups.

[0094] The mutation algorithm simulates the gene mutation phenomenon that may occur in the genetic process of organisms to change the gene values of certain individuals in the simulated biological population to introduce new genetic information. The mutation probability determines the probability of each gene to mutate. Mutation algorithms can include: basic bit mutation, uniform mutation, and boundary mutation. In the present disclosure, each structural parameter of the leaf column in the parameter group is equivalent to each gene of the biological individual. The structural parameter of the leaf column can be changed to a new value according to a certain mutation probability, thereby introducing diversity and avoiding falling into the local optimum. The mutation probability can be much smaller than the crossover probability. A mutation probability that is too high can enhance the global search capability, but may destroy the structural parameters of the existing priority leaf column; a mutation probability that is too low makes it difficult to generate new values and is prone to falling into the local optimal solution.

[0095] In one possible implementation, uniform mutation is used as an example. For each leaf-row structural parameter in the intermediate parameter set, a new value is selected with a certain mutation probability to replace the original leaf-row structural parameter value. The intermediate parameter set undergoing the mutation operation is then converted into a descendant parameter set.

[0096] Furthermore, the structural parameter value of each leaf column in the offspring parameter group is confirmed by the optimization constraint conditions. For the offspring parameter group in which there are structural parameter items of leaf columns that do not meet the constraint conditions, return to the above step 3 to re-execute the crossover and mutation operations to obtain a new offspring parameter group until the offspring parameter group meets the optimization constraint conditions.

[0097] Afterwards, all the offspring parameter groups and parent parameter groups in this genetic algorithm process are combined into a new parameter population. For the new parameter population, if the convergence condition is not met at this time, the genetic algorithm will continue to be executed on the new parameter population (i.e., enter the next iteration); if the convergence condition is met at this time, the new parameter population will be output.

[0098] The convergence condition here can refer to the number of times the genetic algorithm is executed (the above steps 1 to 7 can be regarded as executing the genetic algorithm once) reaching the set value; it can also refer to the existence of a performance indicator in the new parameter population that refers to a parameter group that reaches the preset target; it can also be other pre-set constraints, which are not limited here.

[0099] In another embodiment provided by the present disclosure, the preset optimization constraint conditions include: a value range of at least one structural parameter; or

[0100] The value range of at least one structural parameter and at least one of the following: the value accuracy of the structural parameter and the restriction relationship between preset structural parameters; the restriction relationship between preset structural parameters is used to characterize the structural limitations of the leaf row in the physical structure.

[0101] In the embodiment of the present disclosure, the value range of the structural parameter of the leaf column may include the maximum and minimum values of the structural parameter value of the corresponding leaf column, as well as a value selected within the range of the maximum and minimum values according to the precision of the structural parameter value of the leaf column.

[0102] The restriction relationship between the preset structural parameters refers to the restriction relationship generated by the physical structure of the blade row, for example, the relationship between the inner diameter and the outer diameter of the blade row, the inner diameter of the blade row should be smaller than the value of the outer diameter.

[0103] Here is an example. Suppose the maximum value of a structural parameter of a leaf column is 120, the minimum value is 100, and the value precision is 5. The value range of the structural parameter of the leaf column may include: 100, 105, 110, 115, 120.

[0104] It is also possible to set a fixed value for the structural parameter of a certain leaf column separately, and not adjust the structural parameter of the leaf column in the subsequent genetic algorithm.

[0105] In another embodiment provided by the present disclosure, before the above step S101 of "determining the design variables according to the blade row type of the target turbomolecular pump", the following steps are also included:

[0106] Step 1: Determine the structural parameters corresponding to each leaf row type;

[0107] Step 2: Establish a set of structural parameters;

[0108] The structural parameter set includes at least one of the following: structural parameters corresponding to each leaf row type, value ranges of each structural parameter, value precisions of each structural parameter, and leaf rows at specific locations applicable to each leaf row type;

[0109] Step 3: Perform a logical self-check on the structure parameter set based on the preset self-check logic;

[0110] The preset self-test logic includes:

[0111] If the structure parameter set includes a leaf row at a specific position applicable to the corresponding leaf row type, check whether all leaf row types are set with leaf rows corresponding to the applicable specific positions; if there is a leaf row type that is not set with a leaf row corresponding to the applicable specific position, the self-check fails;

[0112] When the set of structural parameters includes a value range for each structural parameter, and the value range includes a maximum boundary and a minimum boundary, the maximum boundary and the minimum boundary are compared; if the maximum boundary is smaller than the minimum boundary, the self-test fails;

[0113] The restriction relationship between the preset structural parameters is detected. If any restriction relationship between the preset structural parameters does not meet the preset restriction relationship, the self-test fails.

[0114] In the embodiment of the present disclosure, each leaf row type corresponds to at least one leaf row, and the value ranges of the structural parameters of the leaf rows corresponding to the same leaf row type may be the same and have the same value accuracy.

[0115] The range of blade row parameters can be determined based on factors such as performance requirements and installation scenarios. This range can be determined based on existing experience and practical constraints. For example, if a higher pumping rate is required, a larger blade row diameter can be used; if space is limited but higher performance is required, the number of blade rows can be increased.

[0116] The accuracy of the structural parameters of the blade row can take into account the limitations of processing and assembly accuracy. For example, if the processing accuracy of the blade row thickness can reach 0.1mm, then the accuracy of the corresponding structural parameters of the blade row can be determined to be 0.1, so that the accuracy of the corresponding structural parameters is determined to be within the range obtained according to the accuracy of the value. Assuming that the minimum value of the blade row thickness is 0.8 and the maximum value is 1, then when the accuracy of the value is 0.1, the range of the blade row thickness is 0.8, 0.9, and 1. Determining the corresponding accuracy of the value based on the processing accuracy ensures the feasibility of the optimization results, thereby reducing the risks caused by processing accuracy and installation standard issues in the process of transforming from structural design to manufacturing products, and ensuring the feasibility of the design results. However, these actual constraints are not taken into account in the relevant technologies, resulting in the possibility that the optimization results cannot be directly applied to actual production.

[0117] The purpose of the logical self-check process is to determine whether the obtained set of structural parameters meets the corresponding restriction conditions. If there is a leaf column type without a corresponding leaf column, the self-check is judged to have failed; if the maximum boundary (i.e., the maximum value) in the value range of the obtained structural parameter is less than the minimum boundary (i.e., the minimum value), the self-check is judged to have failed; if any of the restriction relationships between the preset structural parameters do not meet the preset relationship, the self-check is judged to have failed. In the case of self-check failure, the structural parameter set is re-established until the logical self-check is passed.

[0118] Here, a possible logic self-test process is provided as an example in combination with Table 1 above:

[0119] If you move 1, move 2, move 3 until you move If all appear in the second column of Table 1, it means that the turbine pump has a blade row type set for each blade row. If any are missing, it means that the corresponding blade row type has not been set for all blade rows, and the self-test has failed. In this case, you need to set the corresponding blade row type for the blade rows that have not been set.

[0120] For each blade row structural parameter, if the maximum value of the structural parameter is not equal to the minimum value, then calculate (maximum structural parameter - minimum structural parameter) / parameter accuracy. If the calculated value is not a positive integer, it means that the set maximum structural parameter is less than the minimum structural parameter, and the self-test fails. If the minimum blade row outer diameter is not greater than the minimum blade row inner diameter, or the maximum blade row outer diameter is not greater than the maximum blade row inner diameter, it means that the optimization constraints of the blade row inner diameter or blade row outer diameter are incorrectly set, and the self-test fails. For each blade row type, if the minimum value of the blade root inclination angle is greater than the minimum value of the blade tip inclination angle, or the maximum value of the blade root inclination angle is greater than the maximum value of the blade root inclination angle, it means that the optimization constraints of the blade root inclination angle or blade tip inclination angle are incorrectly set, and the self-test fails. If the self-test fails, it is necessary to re-set the constraints for the structural parameters of the corresponding blade row.

[0121] In another embodiment provided by the present disclosure, the above step S101 of “determining the design variables according to the blade row type of the target turbomolecular pump” can be implemented as follows:

[0122] Step 1, determining the blade row type included in the target turbomolecular pump;

[0123] Step 2: Match the design variables and the value ranges of the structural parameters contained therein for the leaf column type from the structural parameter set, or match the design variables and the value ranges and value precisions of the structural parameters contained therein for the leaf column type.

[0124] In the disclosed embodiment, all blade row types used in the target turbomolecular pump can be first determined. A corresponding blade row type is then determined for each blade row in the turbomolecular pump. Based on the blade row structural parameters included in each design variable in the blade row type, the value range and accuracy of the corresponding blade row structural parameters are then determined.

[0125] In another embodiment provided by the present disclosure, the above step S102 of “creating a parameter population corresponding to the design variables” can be implemented as follows:

[0126] Step 1: determining the value of the first structural parameter in each parameter group according to the value range of the first structural parameter included in the design variables; and

[0127] Step 2: determining the value of the second structural parameter in each parameter group according to the constraint relationship between the second structural parameter included in the design variable and the related first structural parameter;

[0128] Step 3: The parameter group with determined values is used as the parameter population corresponding to the design variable.

[0129] In the disclosed embodiment, the first structural parameter may be a structural parameter of the leaf row that needs to be determined among the design variables. The first structural parameter may be determined based on the value range and value precision of the structural parameter of the leaf row. The value of the first structural parameter may be determined to be within a numerical interval [0, M1] based on the maximum and minimum values and value precision of the corresponding leaf row structural parameter, where the value of M1 is shown in the following formula (1).

[0130]

[0131] Among them, A 1max is the maximum value of the structural parameter of the corresponding leaf column, A 1min is the minimum value of the structural parameter of the corresponding item leaf column, and δ1 is the value accuracy of the structural parameter of the corresponding item leaf column.

[0132] A value X1 is randomly selected from the numerical interval [0, M1], which may be an integer; then a corresponding value N1 of the first structural parameter may be expressed as shown in the following formula (2).

[0133] N1=A 1min + X1×δ1 (2)

[0134] Furthermore, the second structural parameter may be a structural parameter of the blade row that is required to determine the corresponding blade row type in the design variables and is restricted by the first structural parameter, for example, the relationship between the blade row inner diameter and the blade row outer diameter.

[0135] A value interval [0, M2] may also be determined for the value of the second structural parameter, where the value of M2 is shown in the following formula (3).

[0136]

[0137] Among them, A 2max is the maximum value of the structural parameter of the corresponding item leaf column of the second structural parameter, N1 is a value of the first structural parameter that constitutes a restriction relationship for the second structural parameter, and δ2 is the value accuracy of the structural parameter of the corresponding item leaf column.

[0138] Similarly, an integer X2 is randomly selected from the numerical interval [0, M2]; then a corresponding value N2 of the second structural parameter can be shown as the following formula (4).

[0139] N2= N1+ (X2+n) ×δ2 (4)

[0140] Here, n is a special restriction imposed on the first and second structural parameters. For example, if the first structural parameter is the inner diameter of the blade row and the second structural parameter is the outer diameter of the blade row, to avoid the difference between the inner and outer diameters falling below a reasonable value during the value selection process, n can be set to keep the difference between the inner and outer diameters within a practically acceptable range.

[0141] Based on the above method, a possible value for the structural parameters of all blade rows included in a blade row can be determined, forming a number array. Furthermore, based on the blade row type of the target turbomolecular pump, a set of structural parameters corresponding to all blade rows of the target turbomolecular pump is determined. The arrays corresponding to all blade rows are combined to form a parameter set representing a turbomolecular pump structural design solution.

[0142] The same method can be used to obtain parameter groups corresponding to multiple possible target turbomolecular pump design schemes. These parameter groups can form a parameter population, which can be used as the initial parameter group for subsequent genetic algorithm operations.

[0143] In another embodiment provided by the present disclosure, the above step S105 of "screening the target parameter group from the new parameter population according to the performance indicator value" can be implemented as follows:

[0144] Step 1: Sort the performance index values corresponding to the new parameter population in descending order to obtain a sequence of parameter groups;

[0145] Step 2: Select a parameter group from the sequence according to preset requirements and output it as the target parameter group.

[0146] In the embodiment of the present disclosure, when the convergence condition is met, each parameter group in the new parameter population obtained corresponds to an alternative turbomolecular pump design scheme. The parameter groups in the new parameter population are simulated to obtain the performance index value of each parameter group. The simulation calculation here can use the Monte Carlo simulation method. Furthermore, the parameter groups in the parameter population can be sorted based on the level of the performance index value, and the parameter groups with high performance index values can be ranked at the top. All parameter groups are analyzed from front to back. For the turbomolecular pump corresponding to each parameter group, the factors affecting its applicable working scenario, processing and production difficulty, actual production cost, etc. can be combined and analyzed to select a suitable turbomolecular pump structure from multiple perspectives. For example, the new parameter population is sorted in descending order according to the obtained performance index value, and the parameter group with the highest performance index value is selected as the design scheme of the turbomolecular pump. If the parameter group ranked first is not suitable for use due to high manufacturing cost, the parameter group with the second highest performance index value can be considered as the final design scheme.

[0147] Designers can select the corresponding design scheme according to the application characteristics of different fields, so as to achieve a more scientific and efficient structural design of the turbomolecular pump. This not only improves the design efficiency, but also enhances the performance and reliability of the turbomolecular pump.

[0148] In another embodiment provided by the present disclosure, the structural parameters of the blade row include at least one of the following: blade row outer diameter, blade row inner diameter, blade thickness, blade row height, number of blades, blade root inclination angle and blade tip inclination angle; and / or

[0149] The performance index value includes at least one of the following: maximum compression ratio, maximum Ho coefficient and maximum pumping speed.

[0150] In the disclosed embodiment, the structural parameters of the blade row may include: blade row outer diameter, blade row inner diameter, blade thickness, blade row height, number of blades, blade root inclination angle, and blade tip inclination angle. A restrictive relationship exists between the blade row outer diameter and the blade row inner diameter: the blade row outer diameter should be greater than the blade row inner diameter; a restrictive relationship exists between the blade root inclination angle and the blade tip inclination angle inner diameter: the blade root inclination angle can be greater than or equal to the blade tip inclination angle.

[0151] In the disclosed embodiments, the performance indicators for turbomolecular pump design and optimization may include: maximum compression ratio, maximum Ho coefficient, and maximum pumping speed. The maximum compression ratio of a turbomolecular pump represents the highest degree of compression the turbomolecular pump can achieve for a specific gas under specific conditions; the maximum Ho coefficient represents the ratio of the gas molecular flow rates on the intake and exhaust sides of the turbomolecular pump during operation; and the maximum pumping speed represents the maximum gas extraction rate the turbomolecular pump can achieve under specific conditions.

[0152] The present disclosure also provides a device for configuring the structural parameters of a turbomolecular pump, such as Figure 2 Shown, including:

[0153] The first determination module 201 is configured to determine design variables according to the blade row type of the target turbomolecular pump; wherein the design variables include structural parameters of the blade row corresponding to the blade row type.

[0154] The creation module 202 is used to create a parameter population corresponding to the design variables; wherein the parameter population includes multiple parameter groups, and each parameter group includes a set of values of the structural parameters included in the design variables.

[0155] The optimization module 203 is used to optimize the parameter population using a genetic algorithm to generate a new parameter population that meets preset optimization constraints.

[0156] The second determining module 204 is configured to determine performance indicator values for each parameter group in the new parameter population using a simulation algorithm.

[0157] The screening module 205 is used to screen out a target parameter group from the new parameter population according to the performance index value, and configure a target turbomolecular pump according to the target parameter group to determine the structure of the target turbomolecular pump.

[0158] In another embodiment provided by the present disclosure, the optimization module 203 is used to use the created parameter population as the current parameter population; perform multiple iterations, and perform the following steps in each iteration: perform a selection operation on the parameter group in the current parameter population according to a preset selection algorithm to obtain a parent parameter group; perform a crossover operation on the parent parameter group according to a preset crossover algorithm to obtain an intermediate parameter group; perform a mutation operation on the structural parameters of the leaf column in the intermediate parameter group according to a preset mutation algorithm to obtain a child parameter group; for each child parameter group, determine whether the structural parameters of the leaf column in the child parameter group all meet the corresponding preset optimization constraints; if there are structural parameters in the child parameter group that do not meet the preset optimization constraints, return to the step of performing a crossover operation on the parent parameter group according to the preset crossover algorithm; if the structural parameters in the child parameter group all meet the preset optimization constraints, determine the combination of the child parameter group and the parent parameter group as a new parameter population.

[0159] The second determination module 204 is used to determine the performance index value for the offspring parameter group using a simulation algorithm; if the convergence condition is not met, the next iteration is entered; if the iteration convergence condition is met, the current parameter population is output as a new parameter population.

[0160] In another embodiment provided by the present disclosure, the preset optimization constraint conditions include: a value range of at least one structural parameter; or a value range of at least one structural parameter and at least one of the following: a restrictive relationship between the value accuracy of the structural parameter and the preset structural parameter; the restrictive relationship between the preset structural parameters is used to characterize the structural constraints of the leaf row in the physical structure.

[0161] In another embodiment provided by the present disclosure, the structural parameter configuration device of the turbomolecular pump further includes:

[0162] The third determination module is used to determine the structural parameters corresponding to each leaf row type.

[0163] A module is established to establish a set of structural parameters.

[0164] The structural parameter set includes at least one of the following: structural parameters corresponding to each leaf row type, value ranges of each structural parameter, value precision of each structural parameter, and leaf rows at specific locations applicable to each leaf row type.

[0165] The self-check module is used to perform a logic self-check on the structure parameter set based on a preset self-check logic.

[0166] Among them, the preset self-check logic includes: when the structural parameter set includes a leaf column at a specific position applicable to the corresponding leaf column type, checking whether the leaf column types are all set with leaf columns at the corresponding applicable specific position; if there is a leaf column type that is not set with a leaf column at the corresponding applicable specific position, the self-check fails; when the structural parameter set includes a value range for each structural parameter, and the value range includes a maximum boundary and a minimum boundary, comparing the maximum boundary and the minimum boundary; if there is a case where the maximum boundary is smaller than the minimum boundary, the self-check fails; detecting the restriction relationship between the preset structural parameters, if any restriction relationship between the preset structural parameters does not meet the preset restriction relationship, the self-check fails.

[0167] In another embodiment provided by the present disclosure, the first determining module 201 is configured to determine the type of blade rows included in the target turbomolecular pump;

[0168] The design variables and the value ranges of the structural parameters contained therein are matched for the leaf column type from the structural parameter set, or the design variables and the value ranges and value precisions of the structural parameters contained therein are matched for the leaf column type.

[0169] In another embodiment provided by the present disclosure, a creation module 202 is used to determine the value of the first structural parameter in each parameter group based on the value range of the first structural parameter included in the design variable; and to determine the value of the second structural parameter in each parameter group based on the restriction relationship between the second structural parameter included in the design variable and the related first structural parameter; and the parameter group with the determined value is used as the parameter population corresponding to the design variable.

[0170] In another embodiment provided by the present disclosure, the screening module 205 is used to sort the performance indicator values corresponding to the new parameter population in descending order to obtain a sequence of parameter groups; select a parameter group from the sequence according to preset requirements and output it as a target parameter group.

[0171] In another embodiment provided by the present disclosure, the structural parameters of the blade row include at least one of the following: blade row outer diameter, blade row inner diameter, blade thickness, blade row height, number of blades, blade root inclination angle and blade tip inclination angle; and / or the performance index value includes at least one of the following: maximum compression ratio, maximum Ho coefficient and maximum pumping speed.

[0172] The embodiment of the present disclosure further provides a turbomolecular pump, the structure of which is obtained based on any embodiment of the above-mentioned method for configuring the structural parameters of a turbomolecular pump.

[0173] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments of the present disclosure can be implemented through hardware or by means of software plus a necessary general hardware platform. Based on this understanding, the technical solutions of the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of the various embodiments of the present disclosure.

[0174] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of a preferred embodiment, and the modules or processes in the accompanying drawings are not necessarily required for implementing the present disclosure.

[0175] Those skilled in the art will appreciate that the modules in the devices of the embodiments may be distributed in the devices of the embodiments as described in the embodiments, or may be located in one or more devices different from the embodiments with corresponding changes. The modules of the above embodiments may be combined into one module or further split into multiple submodules.

[0176] The serial numbers of the above-mentioned embodiments of the present disclosure are for description only and do not represent the advantages or disadvantages of the embodiments.

[0177] Obviously, those skilled in the art may make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is intended to include such modifications and variations.

Claims

1. A method for configuring the structural parameters of a turbomolecular pump, characterized in that: include: Determining design variables according to the blade row type of the target turbomolecular pump; wherein the design variables include structural parameters of the blade row corresponding to the blade row type; Creating a parameter population corresponding to the design variable; wherein the parameter population includes a plurality of parameter groups, each parameter group including a set of values of the structural parameters included in the design variable; Optimizing the parameter population using a genetic algorithm to generate a new parameter population that meets preset optimization constraints; Determining performance index values for each parameter group in the new parameter population using a simulation algorithm; A target parameter group is screened out from the new parameter population according to the performance index value, and the target turbomolecular pump is configured according to the target parameter group to determine the structure of the target turbomolecular pump.

2. The method according to claim 1, wherein The method of optimizing the parameter population using a genetic algorithm to generate a new parameter population that meets preset optimization constraints includes: Use the created parameter population as the current parameter population; perform multiple iterations, and perform the following steps in each iteration: Performing a selection operation on the parameter group in the current parameter population according to a preset selection algorithm to obtain a parent parameter group; Performing a crossover operation on the parent parameter group according to a preset crossover algorithm to obtain an intermediate parameter group; Performing a mutation operation on the structural parameters of the leaf columns in the intermediate parameter group according to a preset mutation algorithm to obtain a child parameter group; For each child parameter group, determining whether the structural parameters of the leaf columns in the child parameter group all meet corresponding preset optimization constraints; If there are structural parameters in the child parameter group that do not meet the preset optimization constraint conditions, returning to the step of performing a crossover operation on the parent parameter group according to a preset crossover algorithm; If all structural parameters in the offspring parameter group satisfy the preset optimization constraint condition, then the combination of the offspring parameter group and the parent parameter group is determined as a new parameter population; The adopting of a simulation algorithm to determine performance index values for each parameter group in the new parameter population includes: A simulation algorithm is used to determine the performance index value for the offspring parameter group; if the convergence condition is not met, the next iteration is entered; if the iterative convergence condition is met, the current parameter population is output as a new parameter population.

3. The method according to claim 2, wherein The preset optimization constraint conditions include: a value range of at least one structural parameter; or The value range of at least one structural parameter and at least one of the following: the value accuracy of the structural parameter and the restriction relationship between preset structural parameters; the restriction relationship between the preset structural parameters is used to characterize the structural limitations of the leaf row in the physical structure.

4. The method according to claim 3, wherein Before the step of determining the design variables according to the blade row type of the target turbomolecular pump, the method further includes: Determine the structural parameters corresponding to each leaf row type; Establishing a structural parameter set; wherein the structural parameter set includes at least one of the following: structural parameters corresponding to each leaf row type, value ranges of the structural parameters, value precisions of the structural parameters, and leaf rows at specific locations applicable to each leaf row type; Performing a logic self-check on the set of structural parameters based on a preset self-check logic; The preset self-test logic includes: In a case where the structural parameter set includes a leaf row at a specific position applicable to the corresponding leaf row type, checking whether all leaf row types are provided with a leaf row at the corresponding specific position; if there is a leaf row type that is not provided with a leaf row at the corresponding specific position, the self-check fails; When the set of structural parameters includes a value range for each structural parameter, and the value range includes a maximum boundary and a minimum boundary, the maximum boundary and the minimum boundary are compared; if the maximum boundary is smaller than the minimum boundary, the self-test fails; The restriction relationship between the preset structural parameters is detected. If any restriction relationship between the preset structural parameters does not meet the preset restriction relationship, the self-test fails.

5. The method according to claim 4, wherein The step of determining the design variables according to the blade row type of the target turbomolecular pump includes: Determine the type of blade rows included in the target turbomolecular pump; The design variables and the value ranges of the structural parameters contained therein are matched for the leaf row type from the structural parameter set, or the design variables and the value ranges and value precisions of the structural parameters contained therein are matched for the leaf row type.

6. The method according to claim 5, wherein The creating of a parameter population corresponding to the design variables comprises: Determining the value of the first structural parameter in each parameter group according to the value range of the first structural parameter included in the design variable; as well as determining the value of the second structural parameter in each parameter group according to a restriction relationship between the second structural parameter included in the design variable and the related first structural parameter; The parameter group with determined values is used as the parameter population corresponding to the design variables.

7. The method according to claim 1, wherein The step of selecting a target parameter group from the new parameter population according to the performance indicator value includes: Sort the performance index values corresponding to the new parameter population in descending order to obtain a sequence of parameter groups; A parameter group is selected from the sequence according to preset requirements and output as a target parameter group.

8. The method according to claim 1, wherein The structural parameters of the blade row include at least one of the following: blade row outer diameter, blade row inner diameter, blade thickness, blade row height, blade number, blade root inclination angle and blade tip inclination angle; and / or The performance index value includes at least one of the following: maximum compression ratio, maximum Ho coefficient and maximum pumping speed.

9. A device for configuring the structural parameters of a turbomolecular pump, characterized in that: include: a first determining module, configured to determine design variables according to a blade row type of a target turbomolecular pump; wherein the design variables include structural parameters of the blade row corresponding to the blade row type; A creation module, configured to create a parameter population corresponding to the design variable; wherein the parameter population includes a plurality of parameter groups, each parameter group including a set of values of the structural parameters included in the design variable; An optimization module is used to optimize the parameter population using a genetic algorithm to generate a new parameter population that meets preset optimization constraints; A second determination module is used to determine performance index values for each parameter group in the new parameter population using a simulation algorithm; A screening module is configured to screen out a target parameter group from the new parameter population according to the performance indicator value, and configure the target turbomolecular pump according to the target parameter group to determine the structure of the target turbomolecular pump.

10. A turbomolecular pump, characterized in that: The structure of the turbomolecular pump is obtained based on the method according to any one of claims 1 to 8.

Images