Numerical control machining process parameter optimization method based on improved genetic algorithm

Abstract

The invention discloses a numerical control machining process parameter optimization method based on an improved genetic algorithm, and belongs to the field of mechanical design. The numerical control machining process parameter optimization method based on the improved genetic algorithm further comprises the steps that multiple pieces of sample workpiece data are obtained, wherein the sample workpiece data comprise sample workpiece machining process data, sample workpiece quality requirements and sample workpiece types; based on sample workpiece types, establishing a plurality of workpiece type databases, and summarizing all sample workpiece data; selecting a workpiece type database; based on the sample workpiece processing technology data, establishing an optimization objective function with a sample workpiece quality requirement as an optimization objective; and based on the optimized objective function, defining constraint conditions of sample workpiece processing technology data and sample workpiece quality requirements. The numerical control machining process parameter optimization method based on the improved genetic algorithm has the beneficial effect that the process parameters are optimized in multiple directions.

Description

Technical Field

[0001] The present application relates to the field of mechanical design, and in particular to a method for optimizing CNC machining process parameters based on an improved genetic algorithm. Background Art

[0002] In CNC production and processing, CNC cutting parameters are important factors affecting the workpiece processing process and product quality.

[0003] The reasonable selection and optimization of cutting parameters are directly related to whether the cutting tools and machine tools can be used reasonably. They play an important role in improving productivity, improving machining accuracy and surface quality, and reducing production costs. They are the key to optimizing the entire cutting process. If the process parameters are not selected appropriately, the machining quality of the workpiece will be difficult to guarantee, and the performance of the equipment will also be affected. Therefore, for certain equipment conditions and processing routes, selecting scientific and reasonable cutting parameters is one of the most critical issues in production. In the traditional processing process, the selection of machine tool cutting parameters generally relies on the experience of programmers or reference to existing technical data. This method has great disadvantages:

[0004] (1) There are many factors that affect the CNC machining process. It is difficult to select the most reasonable parameter value based on experience alone in combination with existing equipment and actual machining conditions;

[0005] (2) The professional knowledge levels of programming and design operators vary greatly, and the selection of process parameters is largely limited by their work level and experience;

[0006] (3) The contours of parts processed by CNC are complex and changeable, and the machining allowances are constantly changing. In order to ensure safety, the cutting parameters selected by the operator generally remain unchanged throughout the entire machining process, making it difficult to take into account the changing factors.

[0007] There is no CNC machining process parameter optimization method based on improved genetic algorithm that can optimize process parameters in multiple directions. Summary of the invention

[0008] The content of this application is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this application is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0009] In order to solve the technical problems mentioned in the above background technology section, some embodiments of the present application provide a method for optimizing CNC machining process parameters based on an improved genetic algorithm, and the method for optimizing CNC machining process parameters based on an improved genetic algorithm also includes:

[0010] Acquire a plurality of sample workpiece data, wherein the sample workpiece data includes sample workpiece processing technology data, sample workpiece quality requirements, and sample workpiece types;

[0011] Based on the sample artifact types, multiple artifact type databases are established to summarize all sample artifact data;

[0012] Select an artifact type database;

[0013] Based on the sample workpiece processing data, an optimization objective function is established with the sample workpiece quality requirement as the optimization target;

[0014] Based on the optimization objective function, the constraints of sample workpiece processing data and sample workpiece quality requirements are defined, and a mathematical model for CNC machining process parameter optimization is constructed;

[0015] Based on the improved genetic algorithm, the sample workpiece processing technology data, the sample workpiece quality requirements and the constraints of the sample workpiece processing technology data and the sample workpiece quality requirements are simplified;

[0016] Solve the mathematical model for optimizing CNC machining process parameters to obtain optimized CNC machining process parameters;

[0017] Return to select an artifact type database until each artifact type database has been selected once.

[0018] Furthermore, based on the sample artifact types, multiple artifact type databases are established to summarize all the sample artifact data, including:

[0019] Establish multiple artifact type databases, each of which includes only one sample artifact type;

[0020] Select a sample artifact data;

[0021] Acquire a sample workpiece type of the sample workpiece data, wherein the sample workpiece type includes iron, copper, iron alloy, copper alloy, aluminum and aluminum alloy;

[0022] Based on the sample artifact type of the sample artifact data, incorporating the sample artifact data into a corresponding artifact type database;

[0023] Return to the step of selecting a sample workpiece data until each sample workpiece data has been selected once.

[0024] Furthermore, the optimization objective function is established based on the sample workpiece processing data with the sample workpiece quality requirement as the optimization target, including:

[0025] The sample workpiece processing data is set as a variable of the optimization objective function, and the sample workpiece processing data is shown in Formula 1:

[0026]

[0027] Where n is the spindle speed of the machine tool; f z is the feed per tooth; a p is the axial cutting depth; a e is the radial cutting depth;

[0028] The sample workpiece quality requirement is set as the target of the optimization objective function, and the sample workpiece quality requirement is shown in Formula 2 and Formula 3:

[0029] R a =3.1548n -0.001 f z -10.452 a p -0.8599 a e -4.6697 Formula 2;

[0030] Among them, R a Surface roughness requirement for workpiece;

[0031] σ=-164.7492n -0.0016 f z -211.0374 a p -38.7862 a e -92.8891 Formula 3;

[0032] Among them, σ is the residual stress requirement on the workpiece surface.

[0033] Furthermore, based on the optimization objective function, the sample workpiece processing data and the constraints of the sample workpiece quality requirements are defined, and a mathematical model for optimizing CNC processing parameters is constructed, including:

[0034] Create a machine tool spindle speed constraint as shown in Formula 4:

[0035] h1(x)=nn max ≤0

[0036] h2(x)=n min -n≤0 Formula 4;

[0037] Among them, n max is the maximum speed of the machine tool spindle, in r / min; n min The minimum speed of the machine tool spindle, in r / min;

[0038] Create a feed rate constraint as shown in Formula 5:

[0039] h3(x)=v c -v cmax ≤0

[0040] h4(x)=v cmin -v c ≤0 Formula 5;

[0041] Among them, v c max v is the maximum feed speed allowed during the processing, in mm / min; cmin It is the minimum feed speed allowed during the processing, in mm / min;

[0042] Create the axial cutting depth constraint as shown in Formula 6:

[0043] h5(x)=a p -a pmax ≤0

[0044] h6(x)=a pmin -a p ≤0 Formula 6;

[0045] Among them, a p max The maximum axial cutting depth allowed during the machining process, in mm; a p min It is the minimum axial cutting depth allowed during the machining process, in mm;

[0046] Create a radial cutting depth constraint as shown in Formula 7:

[0047] h7(x)=a eemax -a emax ≤0

[0048] h8(x)=a emin -a eemin ≤0 Formula 7;

[0049] Among them, a eemax is the maximum actual radial cutting depth, in mm; a eemin It is the minimum actual radial cutting depth in mm.

[0050] Furthermore, based on the optimization objective function, the sample workpiece processing data and the constraints of the sample workpiece quality requirements are defined, and a mathematical model for optimizing CNC processing parameters is constructed, including:

[0051] The mathematical model for optimizing CNC machining process parameters is shown in Formula 8:

[0052]

[0053] Furthermore, the sample workpiece processing technology data, the sample workpiece quality requirements and the constraints of the sample workpiece processing technology data and the sample workpiece quality requirements are simplified based on the improved genetic algorithm, including:

[0054] Based on the linear weighted method, each sub-objective function is multiplied by a weight coefficient, and the normalization of each sub-objective is introduced to obtain the weighted objective function to be minimized as shown in Formula 9:

[0055] f(x)=w1n+w2f z +w3a p +w4a e Formula 9;

[0056] Where n is the spindle speed of the machine tool; f z is the feed per tooth; a p is the axial cutting depth; a e is the radial cutting depth; w1 is the weight of the machine tool spindle speed; w2 is the weight of the feed per tooth; w3 is the weight of the axial cutting depth; w4 is the weight of the radial cutting depth.

[0057] Furthermore, the mathematical model for optimizing the numerical control machining process parameters is solved to obtain the optimized numerical control machining process parameters, including:

[0058] Based on the CNC machining process parameters, multiple 10-bit binary codes are obtained. Each 10-bit binary code includes the spindle speed n of the machine tool; the feed amount f per tooth z ; is the axial cutting depth a p ; is the radial cutting depth a e ;

[0059] Generate an initial population and perform parameter settings, wherein the parameter settings include a population size M and a maximum number of iterations T;

[0060] Calculate the fitness of the population and calculate the fitness F(x) of the objective function f, as shown in Formula 10:

[0061]

[0062] where f max is the maximum value of the objective function f, f min is the minimum value of the objective function f;

[0063] Based on the population size of M, the fitness of individual i is f i , calculate the probability of this individual being selected as p i , as shown in Formula 11:

[0064]

[0065] Determine whether the number of iterations meets the requirements;

[0066] If the number of iterations meets the requirements, the optimal CNC machining process parameters are output;

[0067] If the number of iterations does not meet the requirement, the selection operation, crossover operation and mutation operation are performed in sequence, and then the population fitness is calculated and the fitness F(x) of the objective function f is calculated until the number of iterations meets the requirement.

[0068] The beneficial effect of the present application is that it provides a CNC machining process parameter optimization method based on an improved genetic algorithm for optimizing process parameters in a specific multi-directional manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] The drawings constituting a part of this application are used to provide a further understanding of this application, so that other features, purposes and advantages of this application become more obvious. The drawings and descriptions of the exemplary embodiments of this application are used to explain this application and do not constitute an improper limitation on this application.

[0070] In addition, throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the components and elements are not necessarily drawn to scale.

[0071] In the attached picture:

[0072] Figure 1 It is a flowchart according to an embodiment of the present application. DETAILED DESCRIPTION

[0073] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0074] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0075] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0076] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0077] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0078] like Figure 1 As shown, in one embodiment of the present application, the CNC machining process parameter optimization method based on the improved genetic algorithm also includes the following S100 to S800:

[0079] S100, acquiring a plurality of sample workpiece data, wherein the sample workpiece data includes sample workpiece processing technology data, sample workpiece quality requirements, and sample workpiece types.

[0080] S200: Based on the sample artifact types, multiple artifact type databases are established, and all the sample artifact data are summarized.

[0081] S300, selecting a workpiece type database.

[0082] S400, based on the sample workpiece processing data, an optimization objective function is established with the sample workpiece quality requirement as the optimization target.

[0083] S500, based on the optimization objective function, define the constraints of the sample workpiece processing data and the sample workpiece quality requirements, and build a mathematical model for CNC machining process parameter optimization.

[0084] S600: Simplify sample workpiece processing technology data, sample workpiece quality requirements, and constraints of the sample workpiece processing technology data and the sample workpiece quality requirements based on an improved genetic algorithm.

[0085] S700, solving a mathematical model for optimizing CNC machining process parameters to obtain optimized CNC machining process parameters.

[0086] S800, returning to select a workpiece type database until each workpiece type database has been selected once.

[0087] Specifically, the sample workpiece processing data refers to the parameters of the cutting or milling process performed on the machine tool, including spindle speed, feed rate and other data; the sample workpiece quality requirements include the surface roughness requirements after the workpiece is processed and formed, and the surface residual stress requirements after the workpiece is processed and formed.

[0088] In this embodiment, all sample workpiece data are first classified according to the different types of workpieces, and the same workpiece types are stored in the same database. Then, the sample workpiece processing data in the sample data are adjusted as independent variables, and the sample workpiece quality requirements in the sample data are used as targets, and then an optimization objective function is established. Then, constraint conditions are established based on the sample workpiece processing data, and a mathematical model for optimizing CNC processing parameters is constructed at the same time. The improved genetic algorithm is used to solve the mathematical model for optimizing CNC processing parameters, and then the optimal CNC processing parameters are obtained.

[0089] In one embodiment of the present application, multiple artifact type databases are established based on the sample artifact types, and all the sample artifact data are summarized, including the following S201 to S205:

[0090] S201, establishing a plurality of artifact type databases, each of which includes only one sample artifact type.

[0091] S202, selecting a sample workpiece data.

[0092] S203, obtaining a sample workpiece type of the sample workpiece data, wherein the sample workpiece type includes iron, copper, iron alloy, copper alloy, aluminum and aluminum alloy.

[0093] S204: Based on the sample artifact type of the sample artifact data, the sample artifact data is incorporated into a corresponding artifact type database.

[0094] S205, returning to the step of selecting a sample workpiece data, until each sample workpiece data is selected once.

[0095] In this embodiment, multiple types of databases are established based on material classification, and then sample workpiece data of corresponding material types are stored in the corresponding type of database, so that each sample workpiece data is stored, which is convenient for selecting and screening workpieces of different materials.

[0096] In one embodiment of the present application, the step of establishing an optimization objective function with the sample workpiece quality requirement as the optimization target based on the sample workpiece processing data includes the following steps S401 to S402:

[0097] S401, setting sample workpiece processing data as variables of the optimization objective function, the sample workpiece processing data is as shown in Formula 1:

[0098]

[0099] Where n is the spindle speed of the machine tool; f z is the feed per tooth; a pis the axial cutting depth; a e Radial cutting depth.

[0100] S402, setting the sample workpiece quality requirement as the target of the optimization objective function, the sample workpiece quality requirement is as shown in Formula 2 and Formula 3:

[0101] R a =3.1548n -0.001 f z -10.452 a p -0.8599 a e -4.6697 Formula 2;

[0102] Among them, R a Surface roughness requirement for workpiece;

[0103] σ=-164.7492n -0.0016 f z -211.0374 a p -38.7862 a e -92.8891 Formula 3;

[0104] Among them, σ is the residual stress requirement on the workpiece surface.

[0105] In this embodiment, the requirements for workpiece surface roughness and workpiece surface residual stress are correspondingly refined. The workpiece surface roughness and workpiece surface residual stress are set based on the machine tool spindle speed, feed per tooth, axial cutting depth and radial cutting depth, so that the independent variable and the target are associated.

[0106] In one embodiment of the present application, based on the optimization objective function, the sample workpiece processing data and the sample workpiece quality requirements are defined, and a numerical control processing parameter optimization mathematical model is constructed, including the following S501 to S504:

[0107] S501, create a machine tool spindle speed constraint as shown in Formula 4:

[0108] h1(x)=nn max ≤0

[0109] h2(x)=n min -n≤0 Formula 4;

[0110] Among them, n max is the maximum speed of the machine tool spindle, in r / min; n min It is the minimum speed of the machine tool spindle, in r / min.

[0111] S502, create a feed speed constraint as shown in Formula 5:

[0112] h3(x)=v c -v cmax ≤0

[0113] h4(x)=v cmin -v c ≤0 Formula 5;

[0114] Among them, v cmax v is the maximum feed speed allowed during the processing, in mm / min; cmin It is the minimum feed speed allowed during the processing, in mm / min.

[0115] S503, create an axial cutting depth constraint as shown in Formula 6:

[0116] h5(x)=a p -a pmax ≤0

[0117] h6(x)=a pmin -a p ≤0 Formula 6;

[0118] Among them, a pmax The maximum axial cutting depth allowed during the machining process, in mm; a pmin It is the minimum axial cutting depth allowed during the machining process, in mm.

[0119] S504, create radial cutting depth constraint as shown in formula 7:

[0120] h7(x)=a eemax -a emax ≤0

[0121] h8(x)=a emin -a eemin ≤0 Formula 7;

[0122] Among them, a eemax is the maximum actual radial cutting depth, in mm; a eemin It is the minimum actual radial cutting depth in mm.

[0123] In this embodiment, the setting of the constraints for the machine tool spindle speed, feed per tooth, axial cutting depth and radial cutting depth are all based on the same type of sample workpieces. Because the material properties of different sample workpiece types are different, the constraint ranges of the parameters are different.

[0124] In one embodiment of the present application, based on the optimization objective function, the sample workpiece processing data and the sample workpiece quality requirements are defined, and a numerical control processing parameter optimization mathematical model is constructed, including the following S505:

[0125] S505, constructing a mathematical model for optimizing CNC machining process parameters as shown in Formula 8:

[0126]

[0127] In this embodiment, the CNC machining process parameter optimization mathematical model mainly includes three parts: design variable X, objective function F(X) and constraint function h(X). Design variable X is a function of objective function F(X), and constraint function h(X) is a boundary condition that limits design variable X.

[0128] In one embodiment of the present application, the simplification of sample workpiece processing data, sample workpiece quality requirements, and constraints of the sample workpiece processing data and the sample workpiece quality requirements based on the improved genetic algorithm includes the following step S601:

[0129] S601, based on the linear weighted method, each sub-objective function is multiplied by a weight coefficient, and the normalization of each sub-objective is introduced to obtain the weighted objective function to be minimized as shown in Formula 9:

[0130] f(x)=w1n+w2f z +w3a p +w4a e Formula 9;

[0131] Where n is the spindle speed of the machine tool; f z is the feed per tooth; a p is the axial cutting depth; a e is the radial cutting depth; w1 is the weight of the machine tool spindle speed; w2 is the weight of the feed per tooth; w3 is the weight of the axial cutting depth; w4 is the weight of the radial cutting depth.

[0132] In one embodiment of the present application, solving the CNC machining process parameter optimization mathematical model to obtain optimized CNC machining process parameters includes the following steps S701 to S707:

[0133] S701, encoding is performed based on the CNC machining process parameters to obtain multiple 10-bit binary codes, each of which includes the machine tool spindle speed n; the feed per tooth f z ; is the axial cutting depth a p ; is the radial cutting depth a e .

[0134] S702, generating an initial population and performing parameter settings, wherein the parameter settings include a population size M and a maximum number of iterations T.

[0135] S703, calculate the fitness of the population, and calculate the fitness F(x) of the objective function f, as shown in Formula 10:

[0136]

[0137] where f max is the maximum value of the objective function f, f min is the minimum value of the objective function f.

[0138] S704, based on the population size of M, the fitness of individual i is f i , calculate the probability of this individual being selected as p i , as shown in Formula 11:

[0139]

[0140] S705, judging whether the number of iterations meets the requirement.

[0141] S706: If the number of iterations meets the requirement, the optimal CNC machining process parameters are output.

[0142] S707, if the number of iterations does not meet the requirement, then perform the selection operation, crossover operation and mutation operation in sequence and then return to calculate the fitness of the population and calculate the fitness F(x) of the objective function f until the number of iterations meets the requirement.

[0143] In this embodiment, the improved genetic algorithm is used to encode the CNC machining process parameters in the CNC machining process and then establish an initial population. Then, the size of the population and the maximum number of iterations are adjusted, and the fitness of the population is calculated. Then, the probability of each individual being selected is calculated, and whether the number of iterations is reached is used as the condition for terminating the iteration. If the number of iterations is reached, the optimized CNC machining process parameters are output. If the number of iterations is not reached, the selection operation, crossover operation and mutation operation are performed in sequence, and then the population fitness calculation is returned again.

[0144] Compared with the CNC machining process parameters before optimization, the optimized CNC machining process parameters improve the efficiency and accuracy of the CNC machining process parameter optimization design, can use the cutting tools and machine tools more reasonably, and improve the processing accuracy, surface quality and production efficiency of the products.

[0145] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A method for optimizing CNC machining process parameters based on an improved genetic algorithm, characterized in that: The CNC machining process parameter optimization method based on the improved genetic algorithm also includes: Acquire a plurality of sample workpiece data, wherein the sample workpiece data includes sample workpiece processing technology data, sample workpiece quality requirements, and sample workpiece types; Based on the sample artifact types, multiple artifact type databases are established to summarize all sample artifact data; Select an artifact type database; Based on the sample workpiece processing data, an optimization objective function is established with the sample workpiece quality requirement as the optimization target; Based on the optimization objective function, the constraints of sample workpiece processing data and sample workpiece quality requirements are defined, and a mathematical model for CNC machining process parameter optimization is constructed; Based on the improved genetic algorithm, the sample workpiece processing technology data, the sample workpiece quality requirements and the constraints of the sample workpiece processing technology data and the sample workpiece quality requirements are simplified; Solve the mathematical model for optimizing CNC machining process parameters to obtain optimized CNC machining process parameters; Return to select an artifact type database until each artifact type database has been selected once.

2. The method for optimizing CNC machining process parameters based on improved genetic algorithm according to claim 1, characterized in that: Based on the sample artifact types, multiple artifact type databases are established to summarize all the sample artifact data, including: Establish multiple artifact type databases, each of which includes only one sample artifact type; Select a sample artifact data; Acquire a sample workpiece type of the sample workpiece data, wherein the sample workpiece type includes iron, copper, iron alloy, copper alloy, aluminum and aluminum alloy; Based on the sample artifact type of the sample artifact data, incorporating the sample artifact data into a corresponding artifact type database; Return to the step of selecting a sample workpiece data until each sample workpiece data has been selected once.

3. The method for optimizing CNC machining process parameters based on improved genetic algorithm according to claim 2, characterized in that: The method of establishing an optimization objective function with the sample workpiece quality requirement as the optimization target based on the sample workpiece processing data includes: The sample workpiece processing data is set as a variable of the optimization objective function, and the sample workpiece processing data is shown in Formula 1: X=[n,f z , a p ,a e ] Formula 1; Where n is the spindle speed of the machine tool; fz is the feed per tooth; ap is the axial cutting depth; ae is the radial cutting depth; The sample workpiece quality requirement is set as the target of the optimization objective function, and the sample workpiece quality requirement is shown in Formula 2 and Formula 3: Ra = 3.1548n-0.001fz-10.452ap-0.8599ae-4.6697 Formula 2; Among them, Ra is the surface roughness requirement of the workpiece; σ=-164.7492n -0.0016 f z -211.0374 a p -38.7862 a e -92.8891 Formula 3; Among them, σ is the residual stress requirement on the workpiece surface.

4. The method for optimizing CNC machining process parameters based on improved genetic algorithm according to claim 3 is characterized in that: Based on the optimization objective function, the constraints of sample workpiece processing data and sample workpiece quality requirements are defined, and a mathematical model for CNC processing parameter optimization is constructed, including: Create a machine tool spindle speed constraint as shown in Formula 4: Among them, nmax is the maximum speed of the machine tool spindle, in r / min; nmin is the minimum speed of the machine tool spindle, in r / min; Create a feed rate constraint as shown in Formula 5: Among them, vcmax is the maximum feed speed allowed during the processing, in mm / min; vcmin is the minimum feed speed allowed during the processing, in mm / min; Create the axial cutting depth constraint as shown in Formula 6: Among them, apmax is the maximum axial cutting depth allowed during the processing, in mm; apmin is the minimum axial cutting depth allowed during the processing, in mm; Create a radial cutting depth constraint as shown in Formula 7: Among them, aeemax is the maximum actual radial cutting depth, in mm; aeemin is the minimum actual radial cutting depth, in mm.

5. The method for optimizing CNC machining process parameters based on improved genetic algorithm according to claim 4 is characterized in that: Based on the optimization objective function, the constraints of sample workpiece processing data and sample workpiece quality requirements are defined, and a mathematical model for CNC processing parameter optimization is constructed, including: The mathematical model for optimizing CNC machining process parameters is shown in Formula 8:

6. The method for optimizing CNC machining process parameters based on improved genetic algorithm according to claim 5, characterized in that: The method of simplifying the sample workpiece processing data, the sample workpiece quality requirements and the constraints of the sample workpiece processing data and the sample workpiece quality requirements based on the improved genetic algorithm includes: Based on the linear weighted method, each sub-objective function is multiplied by a weight coefficient, and the normalization of each sub-objective is introduced to obtain the weighted objective function to be minimized as shown in Formula 9: f(x)=w1n+w2f z +w3a p +w4a e Formula 9; Among them, n is the spindle speed of the machine tool; fz is the feed per tooth; ap is the axial cutting depth; ae is the radial cutting depth; w1 is the weight of the spindle speed of the machine tool; w2 is the weight of the feed per tooth; w3 is the weight of the axial cutting depth; w4 is the weight of the radial cutting depth.

7. The method for optimizing CNC machining process parameters based on improved genetic algorithm according to claim 6, characterized in that: The method of solving the CNC machining process parameter optimization mathematical model to obtain the optimized CNC machining process parameters includes: Based on the CNC machining process parameters, multiple 10-bit binary codes are obtained by encoding, and each 10-bit binary code includes the machine tool spindle speed n; the feed per tooth fz; the axial cutting depth ap; and the radial cutting depth ae; Generate an initial population and perform parameter settings, wherein the parameter settings include a population size M and a maximum number of iterations T; Calculate the fitness of the population and the fitness F(x) of the objective function f, as shown in Formula 10: where f max is the maximum value of the objective function f, f min is the minimum value of the objective function f; Based on the population size of M, the fitness of individual i is f i , calculate the probability of this individual being selected as p i , as shown in Formula 11: Determine whether the number of iterations meets the requirements; If the number of iterations meets the requirements, the optimal CNC machining process parameters are output; If the number of iterations does not meet the requirement, the selection operation, crossover operation and mutation operation are performed in sequence, and then the population fitness is calculated and the fitness F(x) of the objective function f is calculated until the number of iterations meets the requirement.

Images