Method and system for optimizing operating parameters of numerically controlled lathe

Abstract

The invention relates to the technical field of data processing, in particular to a numerical control lathe operation parameter optimization method and system. The method comprises the steps of collecting a plurality of cutting speed parameters, obtaining a quality factor of a current solution during each iteration according to the plurality of cutting speed parameters in the process of optimizing the cutting speed parameters by using a random hill-climbing algorithm, and obtaining a quality factor of the current solution during each iteration according to the quality factor of the current solution during each iteration. Obtaining the demand degree of the current solution for the neighborhood solution during each iteration; according to the demand degree of the current solution for the neighborhood solutions during each iteration, the number of the neighborhood solutions generated by the current solution during each iteration is obtained, the cutting speed parameters are optimized according to the number of the final neighborhood solutions generated by the current solution during each iteration, and the obtained prediction result is more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for optimizing operating parameters of a numerically controlled lathe. Background Art

[0002] In modern manufacturing, CNC lathes are high-precision and high-efficiency processing equipment used in many industries such as automobiles, aerospace, precision instruments, and mold manufacturing. With the advancement of industrialization, the manufacturing industry has higher and higher requirements for processing accuracy, production efficiency, and cost control. Therefore, improving the cutting efficiency and processing accuracy of CNC lathes, especially through the optimization of operating parameters such as cutting speed, has become one of the key factors in improving competitiveness. Traditional cutting speed optimization methods usually rely on experience. For the ever-changing processing environment and complex workpiece requirements, the effectiveness of traditional methods will be greatly reduced, resulting in the optimization results may not be optimal.

[0003] The patent application document with the current invention publication number CN111091344A proposes a class scheduling method based on a hybrid search of a hill climbing algorithm and parallel perturbation, including: setting basic data, setting class scheduling requirements and rules; calculating the evaluation function and algorithm parameters of the class schedule solution; randomly generating an initial class schedule solution; using a hill climbing algorithm to generate a local optimal class schedule solution and adding it to the optimal solution set; for each solution in the optimal solution set, using a parallel Monte Carlo perturbation to generate multiple neighborhood solutions and using a hill climbing algorithm for all neighborhood solutions to obtain a local optimal neighborhood solution, adding the optimal neighborhood solution to the optimal solution set, retaining multiple optimal solutions with the smallest penalty value of the evaluation function in the optimal solution set, and forming a new optimal solution set; cyclically executing the parallel perturbation and hill climbing algorithms until the algorithms converge and exit, outputting the class schedule solution with the smallest penalty value in the optimal solution set, and generating the corresponding class scheduling table.

[0004] When the random hill climbing algorithm is used to optimize the cutting speed parameters, the random hill climbing algorithm will generate a fixed number of neighborhood solutions in the neighborhood of the current solution for subsequent analysis for each iteration of the parameter optimization process. Therefore, if the quality of the current solution is poor at each iteration, the fixed number of neighborhood solutions may not be sufficient to fully explore the solution space, causing the random hill climbing algorithm to fall into a local optimal solution. Moreover, if the quality of the current solution is good at each iteration, it may be redundant to generate more neighborhood solutions for calculation, which wastes computing resources and reduces the operation efficiency of the algorithm. Summary of the invention

[0005] In order to solve the technical problem that a fixed number of neighborhood solutions in a random hill climbing algorithm may not be sufficient to fully explore the solution space, causing the random hill climbing algorithm to fall into a local optimal solution, the present invention provides a method and system for optimizing the operating parameters of a CNC lathe.

[0006] In a first aspect, the present invention provides a method for optimizing the operating parameters of a CNC lathe, which adopts the following technical solution: A method for optimizing operating parameters of a CNC lathe comprises the following steps: Collecting a number of cutting speed parameters; obtaining a reference data segment of the current solution at each iteration according to the cutting parameter data; obtaining a quality factor of the current solution at each iteration according to the reference data segment; Get the degree to which the current solution requires the neighboring solution at each iteration , Represents the degree of demand of the current solution for the neighborhood solution at the mth iteration; exp() represents an exponential function with a natural constant as the base; Represents the quality factor of the current solution at the mth iteration; Represents the objective function value of the current solution at the m-1th iteration; as well as They represent the range and mean of the objective function values ​​of all neighborhood solutions generated by the current solution at the m-1th iteration; The preset initial solution is used as the current solution in the first iteration, and the number of neighborhood solutions generated by the current solution in the first iteration is obtained, and the number of neighborhood solutions is positively correlated with the degree of demand; according to the number of neighborhood solutions generated by the current solution in the first iteration, the neighborhood solution of the current solution in the first iteration is obtained; the solution corresponding to the minimum value of the objective function value of the current solution in the first iteration and the objective function value of the neighborhood solution of the current solution in the first iteration is used as the current solution in the second iteration, and so on, until the preset number of iterations is reached, and the current solution in the last iteration is used as the optimized cutting speed parameter.

[0007] The innovation of the present invention lies in that by analyzing the numerical characteristics of the current solution and its neighborhood solutions at each iteration in the parameter optimization process, the degree of demand of the current solution for the neighborhood solutions at each iteration is obtained, and the degree of demand of the current solution for the neighborhood solutions at each iteration can be accurately evaluated, which helps us dynamically adjust the number of neighborhood solutions generated by the current solution at each iteration, rather than fixing the number unchanged, thereby avoiding resource waste or falling into local optimal solutions in different problem situations. This dynamic adjustment mechanism improves the accuracy and efficiency of the cutting speed parameter optimization process, making the optimization results more in line with actual needs.

[0008] Preferably, the obtaining of the reference data segment of the current solution at each iteration includes: The number of data is preset to B, and the data segment consisting of the B cutting speed parameters at the end of the cutting speed parameter sequence and the current solution at the m-th iteration is recorded as the reference data segment of the current solution at the m-th iteration.

[0009] This facilitates the subsequent acquisition of the quality factor of the current solution at the first iteration based on the reference data segment.

[0010] Preferably, obtaining the quality factor of the current solution at each iteration includes: Get the objective function value of the current solution at the mth iteration; ; In the formula, Represents the quality factor of the current solution at the mth iteration; Represents the objective function value of the current solution at the mth iteration; represents the data variance in the reference data segment of the current solution at the mth iteration; Represents the data variance of the reference data segment of the current solution at the mth iteration, excluding the current solution; exp() represents an exponential function with a natural constant as the base.

[0011] The larger the quality factor is, the more likely the current solution is to become the optimal solution in the first iteration, and the smaller the requirement for the number of neighborhood solutions is.

[0012] Preferably, obtaining the objective function value of the current solution at the mth iteration includes: , represents the objective function value of any solution, It indicates the power of the CNC lathe when machining a workpiece with the same surface roughness as the current workpiece at the cutting speed corresponding to any solution; It represents the machining length within 30 seconds when the cutting speed corresponding to any solution is used to machine a workpiece with the same surface roughness as the current workpiece; norm() represents the normalization function; According to the method for obtaining the objective function value of any solution, the objective function value of the current solution at the mth iteration is obtained.

[0013] The smaller the objective function value is, the more likely the current solution is to become the optimal solution at each iteration.

[0014] Preferably, the obtaining of the number of neighborhood solutions generated by the current solution during the first iteration includes: Get the number of initial neighborhood solutions generated by the current solution at each iteration; If the number of initial neighborhood solutions generated by the current solution at the first iteration is an even number, the number of initial neighborhood solutions generated by the current solution at the first iteration is used as the number of neighborhood solutions generated by the current solution at the first iteration; if the number of initial neighborhood solutions generated by the current solution at the first iteration is an odd number, the number of initial neighborhood solutions generated by the current solution at the first iteration plus one is used as the number of neighborhood solutions generated by the current solution at the first iteration.

[0015] Dynamically adjust the number of neighborhood solutions generated by the current solution at each iteration to avoid wasting resources or falling into local optimal solutions in different problem situations.

[0016] Preferably, the obtaining of the number of initial neighborhood solutions generated by the current solution in each iteration includes: ; In the formula, represents the number of initial neighborhood solutions generated by the current solution at the mth iteration; N represents the number of neighborhood solutions generated by the current solution at each preset iteration; Represents the degree of demand of the current solution for the neighborhood solution at the mth iteration; Represents the ceiling symbol.

[0017] Preferably, the collecting of several cutting speed parameters includes: The preset sampling frequency is 5 seconds / time, the collection time is one hour, a laser speed meter is installed on the current workpiece, and several cutting speed parameters are collected during the process of processing the current workpiece using a CNC machine tool.

[0018] In a second aspect, the present invention provides a CNC lathe operation parameter optimization system, which adopts the following technical solution: A numerically controlled lathe operating parameter optimization system comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the numerically controlled lathe operating parameter optimization method mentioned above is implemented.

[0019] By adopting the above technical solution, the above-mentioned method for optimizing the operating parameters of a CNC lathe is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0020] The present invention has the following technical effects: The purpose of the present invention is to analyze the numerical characteristics of the current solution and its neighborhood solutions in each iteration of the parameter optimization process, and obtain the degree of demand of the current solution for the neighborhood solutions in each iteration. It can accurately evaluate the degree of demand of the current solution for the neighborhood solutions in each iteration, and help us dynamically adjust the number of neighborhood solutions generated by the current solution in each iteration, rather than fixing the number unchanged, so as to avoid wasting resources or falling into local optimal solutions in different problem situations. This dynamic adjustment mechanism improves the accuracy and efficiency of the cutting speed parameter optimization process, so that the optimization results are more in line with actual needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0022] Figure 1It is a method flow chart of a method for optimizing operating parameters of a CNC lathe in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0024] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0025] The embodiment of the present invention discloses a method for optimizing the operating parameters of a CNC lathe, referring to Figure 1 , comprising steps S1 to S4: S1: Collect several cutting speed parameters.

[0026] In an embodiment of the present invention, the preset sampling frequency is 5 seconds / time, the collection time is one hour, a laser speed meter is installed on the current workpiece, and a number of cutting speed parameters are collected during the process of processing the current workpiece using a CNC machine tool. The cutting speed parameters are arranged to obtain a cutting speed parameter sequence.

[0027] S2: According to several cutting speed parameters, the quality factor of the current solution is obtained at each iteration.

[0028] It should be noted that the purpose of the present invention is to use a random hill climbing algorithm to optimize the cutting speed parameters. For the current solution at each iteration in the parameter optimization process, the random hill climbing algorithm will generate a fixed number of neighborhood solutions in the neighborhood of the current solution for subsequent analysis. Therefore, if the quality of the current solution is poor at each iteration, the fixed number of neighborhood solutions may not be enough to fully explore the solution space, causing the random hill climbing algorithm to fall into a local optimal solution. In addition, if the quality of the current solution is good at each iteration, it may be redundant to generate more neighborhood solutions for calculation, which wastes computing resources and reduces the operation efficiency of the algorithm. In response to the above problems, the present invention proposes a method and system for optimizing the operation parameters of a CNC lathe. By analyzing the numerical characteristics of the current solution and its neighborhood solutions at each iteration in the parameter optimization process, the degree of demand of the current solution for the neighborhood solutions at each iteration is obtained; and the number of neighborhood solutions generated by the current solution at each iteration is obtained based on the degree of demand, thereby achieving more accurate and efficient parameter optimization for cutting speed data.

[0029] It should be further explained that, first, the parameters of the random hill climbing algorithm need to be preset, and then the numerical performance of the current solution and the objective function value at each iteration in the parameter optimization process need to be analyzed to obtain the quality factor of the current solution at each iteration. If the numerical performance of the current solution at each iteration is more consistent with the changing characteristics of the time series data, and the objective function value of the current solution at each iteration is smaller, it means that the current solution is more preferred at each iteration, and it is more likely to become the optimal solution, and the quality factor of the current solution will be larger at each iteration.

[0030] In the embodiment of the present invention, the preset initial solution is Y, that is, the current solution is the initial solution in the first iteration, the number of iterations is H, and Y=100 and H=20 are preset. In other embodiments, the implementers can preset the above values ​​according to the specific implementation situation.

[0031] Construct the objective function value of any solution , represents the objective function value of any solution, It indicates the power of the CNC lathe when machining a workpiece with the same surface roughness as the current workpiece at the cutting speed corresponding to any solution; It indicates the machining length within 30 seconds when the cutting speed corresponding to any solution is used to machine a workpiece with the same surface roughness as the current workpiece; The larger the value of , the worse the quality of the solution.

[0032] According to the method for obtaining the objective function value of any solution, the objective function value of the current solution at the mth iteration is obtained; The B cutting speed parameters at the end of the cutting speed parameter sequence and the data segment formed by the current solution at the mth iteration are recorded as the reference data segment of the current solution at the mth iteration; in an embodiment of the present invention, the preset number of data B=60, and in other embodiments, the implementer can preset the value of the number of data B according to the specific implementation situation.

[0033] Get the quality factor of the current solution at each iteration: ; In the formula, Represents the quality factor of the current solution at the mth iteration; Represents the objective function value of the current solution at the mth iteration; represents the data variance in the reference data segment of the current solution at the mth iteration; represents the data variance of the reference data segment of the current solution at the mth iteration except the current solution; exp() represents an exponential function with a natural constant as the base; Represents the contribution of the current solution to the data variance in the reference data segment of the current solution. The larger the value, the greater the contribution of the current solution at the mth iteration to the data variance in its reference data segment, which means that the value of the current solution at the mth iteration is more prominent and less consistent with the characteristics of time series data changes, which means that the current solution at the mth iteration is less likely to become the optimal solution, and the corresponding quality factor will be smaller; The larger the value is, the larger the objective function value of the current solution at the m-th iteration is, that is, the more prominent the value of the current solution at the m-th iteration is and the less it conforms to the characteristics of the time series data change. The current solution at the m-th iteration is less likely to become the optimal solution, and the quality factor of the current solution at the m-th iteration will be smaller.

[0034] S3: According to the quality factor of the current solution at each iteration, the degree of demand of the current solution for the neighborhood solution at each iteration is obtained; according to the degree of demand of the current solution for the neighborhood solution at each iteration, the number of neighborhood solutions generated by the current solution at each iteration is obtained.

[0035] It should be noted that it is known that the quality factor of the current solution at each iteration is obtained. This indicator is obtained based on the numerical performance of the current solution at each iteration and the analysis of the objective function value. However, the number of neighborhood solutions that the current solution needs to generate for any iteration is not only determined by the quality of the current solution itself, but also needs to refer to the quality of the neighborhood solutions generated in the previous iteration. That is, if the quality factor of the current solution obtained from its own numerical performance and the objective function value analysis at this iteration is very large, but the quality of the neighborhood solutions generated in the corresponding previous iteration is very low, the number of neighborhood solutions that the current solution needs to generate at this iteration should also be larger; therefore, it is necessary to analyze the performance of the objective function values ​​of all neighborhood solutions of the current solution at the previous iteration corresponding to the current solution at this iteration, and optimize the quality factor of the current solution at this iteration to obtain the degree of demand for neighborhood solutions by the current solution at this iteration.

[0036] It should be further explained that, the larger the objective function value of all neighborhood solutions of the current solution in the previous iteration of this iteration, that is, the worse the quality, then the more neighborhood solutions the current solution needs to generate in this iteration should be, to ensure that a neighborhood solution with better quality can be selected from as many neighborhood solutions as possible; and the more unified the objective function values ​​of all neighborhood solutions of the current solution in the previous iteration of this iteration, the more likely the algorithm is to fall into a local optimal solution, then the more neighborhood solutions the current solution needs to generate in this iteration should be, to avoid falling into a local optimal solution.

[0037] In this embodiment of the present invention, the degree of demand of the current solution for the neighborhood solution is obtained at each iteration: ; In the formula, Represents the degree of demand of the current solution for the neighborhood solution at the mth iteration; exp() represents an exponential function with a natural constant as the base; Represents the quality factor of the current solution at the mth iteration; Represents the objective function value of the current solution at the m-1th iteration; Represents the range of the objective function values ​​of all neighborhood solutions generated by the current solution at the m-1th iteration; Represents the mean of the objective function values ​​of all neighborhood solutions generated by the current solution at the m-1th iteration; The smaller the value is, the worse the quality of the current solution at the mth iteration is. Then the current solution at the mth iteration should require more neighborhood solutions to facilitate more efficient and accurate finding of the optimal solution in the future. Therefore, the current solution at the mth iteration has a greater demand for neighborhood solutions. Represents the quality of all neighboring solutions of the current solution in the previous iteration of the m-th iteration. The larger the value, the worse the quality of all neighboring solutions of the current solution in the previous iteration of the m-th iteration. Then the number of neighboring solutions that need to be generated for the current solution in the m-th iteration should be more to ensure that a better quality neighboring solution can be selected from as many neighboring solutions as possible. Then the current solution in the m-th iteration will have a greater demand for neighboring solutions. Represents the range of the objective function values ​​of all neighboring solutions of the current solution in the previous iteration of the mth iteration. The smaller this value is, the more uniform the objective function values ​​of all neighboring solutions of the current solution in the previous iteration of the mth iteration are, and the more likely the algorithm is to fall into a local optimal solution. In this case, it is necessary to increase the number of neighboring solutions in the mth iteration for deeper exploration, and the greater the demand of the current solution for neighboring solutions in the mth iteration. It should be noted that when obtaining the demand of the current solution for neighboring solutions in the first iteration, , as well as Set the value of to 1.

[0038] It should be noted that the degree of demand of the current solution for the neighborhood solutions at each iteration is known, and then the number of neighborhood solutions generated by the current solution at each iteration needs to be adapted according to the indicator; wherein, the greater the degree of demand of the current solution for the neighborhood solutions at any iteration, the lower the quality of the current solution at that iteration, and the more neighborhood solutions generated by the current solution at that iteration, so as to ensure that the algorithm can complete the parameter optimization more efficiently and accurately. In this embodiment of the present invention, the number of initial neighborhood solutions generated by the current solution in each iteration is obtained: ; In the formula, represents the number of initial neighborhood solutions generated by the current solution at the mth iteration; N represents the number of neighborhood solutions generated by the current solution at each preset iteration; Represents the degree of demand of the current solution for the neighborhood solution at the mth iteration; Represents a round-up symbol; in the embodiment of the present invention, the number of neighborhood solutions N generated by the current solution in each iteration is preset to be 10. In other embodiments, the implementer may preset the number N according to the specific implementation situation.

[0039] If the number of initial neighborhood solutions generated by the current solution at each iteration is an even number, the number of initial neighborhood solutions generated by the current solution at each iteration is used as the number of neighborhood solutions generated by the current solution at each iteration; if the number of initial neighborhood solutions generated by the current solution at each iteration is an odd number, the number of initial neighborhood solutions generated by the current solution at each iteration is added by one as the number of neighborhood solutions generated by the current solution at each iteration.

[0040] S4: Optimize the cutting speed parameters according to the number of final neighborhood solutions generated by the current solution at each iteration.

[0041] In the embodiment of the present invention, the number of neighborhood solutions generated by the current solution in each iteration is obtained, and thus the cutting speed parameters of the CNC lathe are optimized according to the optimized random hill climbing algorithm.

[0042] In the embodiment of the present invention, according to the method for obtaining the number of final neighborhood solutions generated by the current solution in each iteration, the process of optimizing the cutting speed parameters is: The preset initial solution is used as the current solution at the first iteration, and the number of neighborhood solutions generated by the current solution at the first iteration is obtained; according to the number of neighborhood solutions generated by the current solution at the first iteration, the neighborhood solution of the current solution at the first iteration is obtained; the solution corresponding to the minimum value of the objective function value of the current solution at the first iteration and the objective function value of the neighborhood solution of the current solution at the first iteration is used as the current solution at the second iteration; Obtain the number of neighborhood solutions generated by the current solution in the second iteration; obtain the neighborhood solution of the current solution in the second iteration according to the number of neighborhood solutions generated by the current solution in the second iteration; take the solution corresponding to the minimum value of the objective function value of the current solution in the second iteration and the objective function value of the neighborhood solution of the current solution in the second iteration as the current solution in the third iteration; And so on, until the number of iterations is reached, and the current solution at the last iteration is used as the optimized cutting speed parameter.

[0043] It should be noted that the method of obtaining the neighborhood solutions of the current solution at each iteration according to the number of neighborhood solutions generated by the current solution at each iteration is a well-known technology in the random hill climbing algorithm, and will not be described in detail in the embodiments of the present invention.

[0044] An embodiment of the present invention further discloses a CNC lathe operating parameter optimization system, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a CNC lathe operating parameter optimization method according to the present invention is implemented.

[0045] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0046] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory, a dynamic random access memory, a static random access memory, an enhanced dynamic random access memory, a high bandwidth memory, a hybrid storage cube, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0047] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0048] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for optimizing the operating parameters of a CNC lathe, characterized in that: Includes steps: Collecting a number of cutting speed parameters; obtaining a reference data segment of the current solution at each iteration according to the cutting parameter data; obtaining a quality factor of the current solution at each iteration according to the reference data segment; Get the degree to which the current solution requires the neighboring solution at each iteration , Represents the degree of demand of the current solution for the neighborhood solution at the mth iteration; exp() represents an exponential function with a natural constant as the base; Represents the quality factor of the current solution at the mth iteration; Represents the objective function value of the current solution at the m-1th iteration; as well as They represent the range and mean of the objective function values ​​of all neighborhood solutions generated by the current solution at the m-1th iteration; The preset initial solution is used as the current solution in the first iteration, and the number of neighborhood solutions generated by the current solution in the first iteration is obtained, and the number of neighborhood solutions is positively correlated with the degree of demand; according to the number of neighborhood solutions generated by the current solution in the first iteration, the neighborhood solution of the current solution in the first iteration is obtained; the solution corresponding to the minimum value of the objective function value of the current solution in the first iteration and the objective function value of the neighborhood solution of the current solution in the first iteration is used as the current solution in the second iteration, and so on, until the preset number of iterations is reached, and the current solution in the last iteration is used as the optimized cutting speed parameter.

2. A method for optimizing operating parameters of a CNC lathe according to claim 1, characterized in that: The step of obtaining the reference data segment of the current solution at each iteration includes: The number of data is preset to B, and the data segment consisting of the B cutting speed parameters at the end of the cutting speed parameter sequence and the current solution at the m-th iteration is recorded as the reference data segment of the current solution at the m-th iteration.

3. A method for optimizing operating parameters of a CNC lathe according to claim 1, characterized in that: The obtaining of the quality factor of the current solution at each iteration includes: Get the objective function value of the current solution at the mth iteration; ； In the formula, Represents the quality factor of the current solution at the mth iteration; Represents the objective function value of the current solution at the mth iteration; represents the data variance in the reference data segment of the current solution at the mth iteration; Represents the data variance of the reference data segment of the current solution at the mth iteration, excluding the current solution; exp() represents an exponential function with a natural constant as the base.

4. A method for optimizing operating parameters of a CNC lathe according to claim 3, characterized in that: The obtaining of the objective function value of the current solution at the mth iteration includes: , represents the objective function value of any solution, It indicates the power of the CNC lathe when machining a workpiece with the same surface roughness as the current workpiece at the cutting speed corresponding to any solution; It represents the machining length within 30 seconds when the cutting speed corresponding to any solution is used to machine a workpiece with the same surface roughness as the current workpiece; norm() represents the normalization function; According to the method for obtaining the objective function value of any solution, the objective function value of the current solution at the mth iteration is obtained.

5. The method for optimizing the operating parameters of a CNC lathe according to claim 1, characterized in that: The obtaining of the number of neighborhood solutions generated by the current solution during the first iteration includes: Get the number of initial neighborhood solutions generated by the current solution at each iteration; If the number of initial neighborhood solutions generated by the current solution at the first iteration is an even number, the number of initial neighborhood solutions generated by the current solution at the first iteration is used as the number of neighborhood solutions generated by the current solution at the first iteration; if the number of initial neighborhood solutions generated by the current solution at the first iteration is an odd number, the number of initial neighborhood solutions generated by the current solution at the first iteration plus one is used as the number of neighborhood solutions generated by the current solution at the first iteration.

6. A method for optimizing operating parameters of a CNC lathe according to claim 5, characterized in that: The method of obtaining the number of initial neighborhood solutions generated by the current solution at each iteration includes: ； In the formula, represents the number of initial neighborhood solutions generated by the current solution at the mth iteration; N represents the number of neighborhood solutions generated by the current solution at each preset iteration; Represents the degree of demand of the current solution for the neighborhood solution at the mth iteration; Represents the ceiling symbol.

7. A method for optimizing operating parameters of a CNC lathe according to claim 1, characterized in that: The collecting of several cutting speed parameters includes: The preset sampling frequency is 5 seconds / time, the collection time is one hour, a laser speed meter is installed on the current workpiece, and several cutting speed parameters are collected during the process of processing the current workpiece using a CNC machine tool.

8. A CNC lathe operation parameter optimization system, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for optimizing operating parameters of a CNC lathe according to any one of claims 1 to 7 is implemented.

Images