Tool edge parameter optimization method based on workpiece-tool performance parameters

Abstract

The application provides a tool edge parameter optimization method based on workpiece-tool performance parameters, and relates to the technical field of tool edge parameter optimization, and the specific steps comprise the following steps: acquiring cutting characteristic parameters and workpiece characteristic parameters under different tool edge parameter combinations; establishing a tool characteristic prediction model, inputting tool edge parameters, and outputting cutting characteristic parameters; randomly combining tool edge parameters under constraint conditions, inputting the prediction model to acquire cutting characteristic parameters; performing data processing and correlation analysis on workpiece combinations, and constructing a functional relationship between cutting characteristics and tool life coefficients and workpiece surface quality coefficients; and iteratively optimizing individuals of an initial population through a genetic algorithm to extract optimal tool edge parameters. The application significantly improves the intelligent level of tool design, not only enables tool design to be optimized in real time according to actual machining conditions, but also effectively deals with different machining conditions, and ensures the best performance of the tool in actual application.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of tool edge parameter optimization, in particular to a tool edge parameter optimization method based on workpiece-tool performance parameters. BACKGROUND

[0002] In the field of metal cutting, tool cutting performance and workpiece performance are closely related. With the increasing requirements of machining precision and efficiency, traditional single-target optimization methods for tools have gradually exposed some shortcomings. Most existing technologies focus on the optimization of tool materials, coating selection or geometric shape design, but these methods often ignore the mutual influence between tool cutting performance and workpiece performance, and fail to consider the joint optimization of tool cutting performance and workpiece performance. Although some researches introduce adaptive algorithms or optimization models, most methods still lack dynamic adjustment of tool cutting performance and workpiece performance in actual machining process, resulting in ineffective improvement of tool life and workpiece surface quality.

[0003] In the prior art, the design method and system of the end mill edge based on the equiangular spiral disclosed in CN118568886A includes the following steps: collecting tool parameters and edge parameters, the tool parameters including tool diameter and tool length, and the edge parameters including edge radius and edge inclination angle; data processing is performed on the tool parameters, and correlation analysis is performed to generate size influence coefficients affecting the edge size; data processing is performed on the edge parameters, and correlation analysis is performed to generate shape influence coefficients affecting the edge shape. This method collects relevant parameters of the edge, optimizes the parameter values of the equiangular spiral function and the geometric characteristics of the edge, generates the curve of the equiangular spiral function according to the geometric characteristics of the tool edge, obtains the geometric shape of the end mill edge through the curve of the equiangular spiral function, and quickly obtains the optimal edge design scheme, improving the precision and efficiency of edge design.

[0004] However, there are still the following deficiencies. As can be seen from the above statements, the existing technology relies on static parameter analysis of tools and workpieces, lacks effective two-way feedback mechanism, which leads to the inability of tool design to be adjusted in real time according to actual machining conditions, and ignores the influence of workpiece characteristics changes on tool performance in the machining process. This one-way information flow makes the tool design not ideal in parameter optimization when facing complex and variable machining conditions.

[0005] The above information disclosed in the background section is only used to enhance the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0006] The purpose of the present invention is to provide a method for optimizing tool edge parameters based on workpiece-tool performance parameters to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for optimizing tool edge parameters based on workpiece-tool performance parameters, comprising the following steps:

[0009] S1. Obtaining tool cutting characteristic parameters and workpiece characteristic parameters under different tool edge parameter combinations, wherein the tool cutting characteristic parameters include cutting speed, feed rate, and cutting depth; the workpiece characteristic parameters include surface temperature, surface hardness, and surface roughness; and the tool edge parameters include rake angle, relief angle, edge radius, and fillet radius. The workpiece characteristic parameters and tool edge parameters are combined to construct individuals of the initial population.

[0010] S2. Construct a tool characteristic prediction model, take the tool edge parameter combination of the initial population individuals as input, and the tool cutting characteristic parameters as label training model, and train the tool characteristic prediction model;

[0011] S3. Establishing constraints on tool edge parameters, randomly combining the tool edge parameters of the initial population individuals under the constraints of the tool edge parameters, and inputting the tool edge parameter combinations of the initial population individuals into the tool characteristic prediction model to obtain tool cutting characteristic parameters;

[0012] S4. Perform data processing and correlation analysis on the workpiece combinations of the initial population individuals to obtain the workpiece surface quality coefficient. Using the cutting speed, feed rate, cutting depth, and upper and lower limits of the ideal range, obtain the deviation values ​​of the cutting speed, feed rate, and cutting depth. Construct a functional relationship between the deviation values ​​of the cutting speed, feed rate, and cutting depth and the tool life coefficient. Construct a functional relationship between the workpiece surface quality coefficient, the tool life coefficient, and the comprehensive evaluation coefficient. The comprehensive evaluation coefficient is used to comprehensively evaluate the workpiece-tool performance.

[0013] S5. Taking the maximization of the comprehensive evaluation coefficient as the objective function, the individuals of the initial population are iteratively optimized through the genetic algorithm under the constraints of the tool edge parameters to obtain the optimal individuals. Based on the optimal individuals, the optimal values ​​of the tool edge parameters are extracted.

[0014] Furthermore, the workpiece characteristic parameters and tool edge parameters are spliced ​​together to construct individuals of the initial population of tool edge parameters. The specific process is as follows:

[0015] Collect workpiece characteristic parameters, including workpiece surface temperature , workpiece surface hardness and workpiece surface roughness , the workpiece characteristic parameter combination is calibrated as ,and , Respectively represent the workpiece surface temperature, workpiece surface hardness and workpiece surface roughness in the workpiece characteristic parameter combination, and the initial population formed by splicing is calibrated as , and the initial population , is the first Individuals, is the index of the individual in the initial population, and , is the number of individuals in the initial population, ,in, Respectively The surface temperature, surface hardness, surface roughness, rake angle, back angle, cutting edge radius and fillet radius of each individual workpiece.

[0016] Furthermore, the tool characteristic prediction model is constructed using a deep neural network based on a multilayer perceptron, wherein the deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, and an output layer, wherein the first hidden layer, the second hidden layer, and the third hidden layer each have at least two neurons and each use ReLU as an activation function;

[0017] The process of training the tool characteristic prediction model is as follows:

[0018] The rake angle, back angle, edge radius and fillet radius of the initial population individuals are used as input, and the tool cutting characteristic parameters are used as output labels for training. The mean square error is used as the loss function. When the mean square error is When the tool characteristic prediction model is within the range, the training of the tool characteristic prediction model is completed.

[0019] Furthermore, the workpiece surface temperature, workpiece surface hardness and workpiece surface roughness are subjected to data processing and correlation analysis to obtain the workpiece surface quality coefficient, based on the following formula:

[0020] ;

[0021] in, For the The workpiece surface quality coefficient of each individual workpiece is used to comprehensively evaluate the influence of workpiece characteristic parameters on workpiece surface quality from three levels: workpiece surface temperature, workpiece surface hardness and workpiece surface roughness. is the weight coefficient of the workpiece surface temperature, is the weight coefficient of the workpiece surface hardness, is the weight coefficient of the workpiece surface roughness. On the basis of .

[0022] Furthermore, a functional relationship between the deviation values ​​of cutting speed, feed rate, cutting depth and tool life coefficient is constructed as follows:

[0023] ;

[0024] ;

[0025] in, For the The tool life coefficient of each individual tool is used to comprehensively evaluate the influence of tool cutting characteristic parameters on tool life from three levels: cutting speed, feed rate and cutting depth;

[0026] For the The individual cutting speed deviation value, For the The average cutting speed of each individual is the lower limit of the ideal cutting speed range, is the upper limit of the ideal range of cutting speed, For the The feed deviation value of each individual, For the The average feed amount of each individual, is the lower limit of the ideal feed range, is the upper limit of the ideal feed range, For the The individual cutting depth deviation value, For the The average cutting depth of each individual is the lower limit of the ideal cutting depth range, is the upper limit of the ideal range of cutting depth;

[0027] is the weight of the cutting speed deviation value in evaluating the influence of tool cutting characteristic parameters on tool life, is the weight of the feed deviation value in evaluating the influence of tool cutting characteristic parameters on tool life, is the weight of the cutting depth deviation value in evaluating the influence of tool cutting characteristic parameters on tool life. On the basis of .

[0028] Furthermore, a functional relationship between the workpiece surface quality coefficient, tool life coefficient and comprehensive evaluation coefficient is constructed as follows:

[0029] ;

[0030] in, For the The comprehensive evaluation coefficient of each individual is used to comprehensively evaluate the workpiece-tool performance by combining the workpiece surface quality coefficient and the tool life coefficient;

[0031] and are the weights in the calculation of workpiece surface quality coefficient and tool life coefficient, respectively, and and The specific value of is determined by the hierarchical analysis method.

[0032] Furthermore, the specific process of step S5 is as follows:

[0033] Iterative optimization is performed on the individuals of the initial population. During the iterative optimization process, the constraints of the tool edge parameters are set, that is, the maximum and minimum values ​​of the rake angle, clearance angle, edge radius and fillet radius are set respectively. Within the constraints of the rake angle, clearance angle, edge radius and fillet radius, the tool edge parameters are iteratively optimized. Specifically, the comprehensive evaluation coefficient is set to Sort from large to small and select the comprehensive evaluation coefficient The individuals in the front row are taken as the parents. Through crossover and mutation operations, the genes of the parent individuals are exchanged, combined and mutated to generate new individuals. The tool cutting characteristic parameters of the newly generated individuals are obtained using the tool characteristic prediction model, and their comprehensive evaluation coefficients are calculated. The new individuals and the parents are taken as the new population, and the selection, crossover and mutation operations are repeated until the predetermined number of iterations is reached. The individual corresponding to the maximum comprehensive evaluation coefficient is taken as the optimal combination of tool edge parameters, and the individual corresponding to the maximum comprehensive evaluation coefficient is calibrated as , then the optimal tool edge parameter combination is the rake angle , rear angle , cutting edge radius and fillet radius .

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] The present invention significantly enhances the intelligent level of tool design by establishing a two-way feedback relationship between workpiece characteristic parameters and tool cutting characteristic parameters. This mechanism not only enables real-time optimization of tool design based on actual machining conditions, but also effectively responds to different machining conditions, ensuring optimal tool performance in actual applications. Furthermore, with the help of an intelligent tool characteristic prediction model, it is possible to more accurately predict the cutting performance of the tool under specific workpieces and machining conditions, thereby reducing unnecessary trial and error costs and improving accuracy in the design phase.

[0036] In addition, comprehensive evaluation of tool and workpiece performance is aimed at achieving higher resource utilization efficiency during the machining process, reducing energy consumption and material costs, and thus improving production efficiency and product quality. The use of genetic algorithms for optimization can quickly explore the global optimal solution, which is especially suitable for complex multi-dimensional parameter spaces, avoiding the local optimal solution trap that may occur in traditional methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 Schematic diagram of the overall method of the present invention. DETAILED DESCRIPTION

[0038] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to specific embodiments.

[0039] It should be noted that, unless otherwise defined, the technical or scientific terms used in the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0040] Example 1:

[0041] See also Figure 1 , the present invention provides a technical solution:

[0042] A method for optimizing tool edge parameters based on workpiece-tool performance parameters, comprising the following steps:

[0043] S1. Obtaining tool cutting characteristic parameters and workpiece characteristic parameters under different tool edge parameter combinations, wherein the tool cutting characteristic parameters include cutting speed, feed rate, and cutting depth; the workpiece characteristic parameters include surface temperature, surface hardness, and surface roughness; and the tool edge parameters include rake angle, relief angle, edge radius, and fillet radius. The workpiece characteristic parameters and tool edge parameters are combined to construct individuals of the initial population.

[0044] S2. Construct a tool characteristic prediction model, take the tool edge parameter combination of the initial population individuals as input, and the tool cutting characteristic parameters as label training model, and train the tool characteristic prediction model;

[0045] S3. Establishing constraints on tool edge parameters, randomly combining the tool edge parameters of the initial population individuals under the constraints of the tool edge parameters, and inputting the tool edge parameter combinations of the initial population individuals into the tool characteristic prediction model to obtain tool cutting characteristic parameters;

[0046] S4. Perform data processing and correlation analysis on the workpiece combinations of the initial population individuals to obtain the workpiece surface quality coefficient. Using the cutting speed, feed rate, cutting depth, and upper and lower limits of the ideal range, obtain the deviation values ​​of the cutting speed, feed rate, and cutting depth. Construct a functional relationship between the deviation values ​​of the cutting speed, feed rate, and cutting depth and the tool life coefficient. Construct a functional relationship between the workpiece surface quality coefficient, the tool life coefficient, and the comprehensive evaluation coefficient. The comprehensive evaluation coefficient is used to comprehensively evaluate the workpiece-tool performance.

[0047] S5. Taking the maximization of the comprehensive evaluation coefficient as the objective function, the individuals of the initial population are iteratively optimized through the genetic algorithm under the constraints of the tool edge parameters to obtain the optimal individuals. Based on the optimal individuals, the optimal values ​​of the tool edge parameters are extracted.

[0048] Based on the above embodiment, the rake angle refers to the angle between the cutting edge of the tool and the rake face of the tool. The larger the rake angle, the lower the cutting force and cutting temperature of the tool during cutting, and the better the cutting performance of the workpiece material.

[0049] The back angle refers to the angle between the cutting edge of the tool and the back face of the tool. The back angle affects the cutting strength and wear resistance of the tool. A larger back angle is beneficial to reduce the friction between the tool and the workpiece.

[0050] The cutting edge radius refers to the smoothness of the tool edge, which affects the stress distribution generated during the cutting process. An appropriate cutting edge radius can improve the tool's durability and cutting quality.

[0051] The fillet radius refers to the radius of the transition part of the tool edge. Similar to the edge radius, it also helps to reduce cutting forces and wear.

[0052] The design of the rake angle and relief angle affects the heat and friction generated during the cutting process. A larger rake angle tends to reduce cutting temperature, which helps improve tool life and workpiece quality.

[0053] The cutting characteristics of the tool (such as cutting speed and feed rate) are affected by the edge parameters, which in turn affect the surface hardness of the workpiece. Reasonable cutting parameters can avoid excessive wear and hardness loss.

[0054] Cutting edge parameters, especially cutting edge radius and fillet radius, have a direct impact on the surface smoothness of the workpiece. A smaller radius may lead to finer cutting particles and increase surface roughness, while proper rounding treatment can improve surface quality.

[0055] The settings of the rake angle and clearance angle will affect the cutting efficiency and applicable cutting speed of the tool. A larger rake angle can usually increase the cutting speed, while a suitable clearance angle can maintain better tool stability.

[0056] The combination of rake angle and back angle affects the feed rate of the tool during cutting. An appropriate rake angle helps reduce cutting resistance, thereby increasing the feed rate and improving production efficiency.

[0057] The design of the cutting edge radius and fillet radius of the tool will affect the selection of cutting depth. A larger cutting edge radius may increase the cutting depth capability, but may also lead to an increase in the surface roughness of the workpiece.

[0058] Based on the above embodiment, the equipment and method for collecting the workpiece surface temperature, workpiece surface hardness and workpiece surface roughness are as follows:

[0059] Aim the infrared thermometer at the area where the tool contacts the workpiece and record the surface temperature of the workpiece.

[0060] Using a Rockwell hardness tester, place the sample on the test platform of the Rockwell hardness tester, apply the initial load, maintain it for a period of time, then apply the measuring load and read the surface hardness value of the workpiece.

[0061] Using a surface roughness tester, place the surface roughness tester on the surface of the workpiece and measure along the surface. The instrument will automatically collect surface profile data and calculate the surface roughness of various workpieces.

[0062] The equipment and method for collecting cutting speed, feed rate, cutting depth, rake angle, back angle, cutting edge radius and fillet radius are as follows:

[0063] Use a tachometer to measure the actual speed of the tool's rotating axis and calculate the cutting speed (V=π×D×n, where D is the tool diameter and n is the speed).

[0064] On CNC machine tools, the feed rate is monitored and recorded by the numerical control system.

[0065] On CNC machine tools, use an electronic depth gauge or vernier caliper to measure the distance between the tool and the workpiece surface and record the actual cutting depth.

[0066] Use an optical microscope to observe and measure the rake angle of the tool edge.

[0067] Fix the tool on the measuring table and use an optical microscope to measure the tool's clearance angle.

[0068] Place the tool under an optical microscope to observe the cutting edge curve and use a vernier caliper to measure the cutting edge radius.

[0069] Place the tool under an optical microscope and measure the radius of the rounded part of the tool edge.

[0070] On the basis of the above embodiment, after collecting the workpiece surface temperature, workpiece surface hardness, workpiece surface roughness, cutting speed, feed rate, cutting depth, rake angle, back angle, cutting edge radius and fillet radius, the above parameters are respectively subjected to maximum-minimum normalization processing, and then the normalized data is used for subsequent analysis and processing, so that in the subsequent analysis and processing process, various data are analyzed and processed under the same dimension, avoiding the problem of some data being ignored due to different dimensions.

[0071] Among them, the infrared thermometer, Rockwell hardness tester, surface roughness tester, tachometer, CNC machine tool, electronic depth meter, and optical microscope can all adopt models of existing equipment and are not limited here.

[0072] The workpiece surface temperature, workpiece surface hardness and workpiece surface roughness, cutting speed, feed rate, cutting depth, rake angle, back angle, cutting edge radius and fillet radius are all multiple groups (such as 3 groups). The same data measured multiple times are averaged, and the final average value is used as the corresponding data in the workpiece material characteristic parameters, tool cutting characteristic parameters, and tool cutting edge parameters, so as to avoid accidental errors in taking individual points.

[0073] On the basis of the above embodiment, the workpiece characteristic parameters and the tool edge parameters are spliced ​​together to construct individuals of the initial population of tool edge parameters. The specific process is as follows:

[0074] Collect workpiece characteristic parameters, including workpiece surface temperature , workpiece surface hardness and workpiece surface roughness , the workpiece characteristic parameter combination is calibrated as ,and , Represent the workpiece surface temperature, workpiece surface hardness and workpiece surface roughness in the workpiece combination respectively, and the initial population formed by the splicing is calibrated as , and the initial population , is the first Individuals, is the index of the individual in the initial population, and , is the number of individuals in the initial population, ,in, Respectively The surface temperature, surface hardness, surface roughness, rake angle, back angle, cutting edge radius and fillet radius of each individual workpiece.

[0075] Based on the above embodiment, the tool characteristic prediction model is constructed using a deep neural network based on a multilayer perceptron, wherein the deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, and an output layer, wherein the first hidden layer, the second hidden layer, and the third hidden layer each have at least two neurons and each use ReLU as an activation function;

[0076] In this embodiment, the input features of the deep learning network of the multilayer perceptron include four features: rake angle, back angle, cutting edge radius, and fillet radius.

[0077] The structure of the deep learning network of multilayer perceptron is:

[0078] Input layer: receives input of 4 features;

[0079] The first hidden layer has 64 neurons and uses ReLU as the activation function.

[0080] The second hidden layer has 32 neurons and also uses the ReLU activation function.

[0081] The third hidden layer has 16 neurons and uses the ReLU activation function.

[0082] Output layer: has a single neuron and tool cutting characteristic parameters.

[0083] The process of training the tool characteristic prediction model is as follows:

[0084] The rake angle, back angle, edge radius and fillet radius of the initial population individuals are used as input, and the tool cutting characteristic parameters are used as output labels for training. The mean square error is used as the loss function. When the mean square error is When the tool characteristic prediction model is within the range, the training of the tool characteristic prediction model is completed.

[0085] Based on the above examples, the correlations between surface temperature, surface hardness, and surface roughness and the surface quality of the workpiece are as follows:

[0086] When the tool works at high temperature, the wear rate tends to accelerate, resulting in unstable cutting, which in turn affects the surface quality of the workpiece. Therefore, there is a positive correlation between the surface temperature of the workpiece and the surface quality of the workpiece.

[0087] Within a certain range, materials with higher surface hardness are generally more resistant to wear and deformation and have better surface quality. Therefore, there is a positive correlation between the surface hardness and the surface quality of the workpiece.

[0088] The higher the surface roughness, the greater the surface unevenness, which will directly affect the surface quality of the workpiece, reducing its smoothness and overall aesthetics. Therefore, the surface roughness of the workpiece and the surface quality of the workpiece are negatively correlated.

[0089] According to the correlation between the workpiece surface temperature, workpiece surface hardness, workpiece surface roughness and workpiece surface quality, the workpiece surface temperature, workpiece surface hardness and workpiece surface roughness are subjected to data processing and correlation analysis to obtain the workpiece surface quality coefficient. The formula is as follows:

[0090] ;

[0091] in, For the The workpiece surface quality coefficient of each individual workpiece is used to comprehensively evaluate the influence of workpiece characteristic parameters on workpiece surface quality from three levels: workpiece surface temperature, workpiece surface hardness and workpiece surface roughness. The larger the workpiece surface quality coefficient, the better the workpiece surface quality.

[0092] is the weight coefficient of the workpiece surface temperature, is the weight coefficient of the workpiece surface hardness, is the weight coefficient of workpiece surface roughness;

[0093] The reason for setting the above function form to express the functional relationship between the workpiece surface quality coefficient and the workpiece surface temperature, workpiece surface hardness and workpiece surface roughness is as follows:

[0094] First, by weighting the surface temperature and hardness in the numerator, the formula fully reflects the positive impact of temperature and hardness on surface quality. Meanwhile, surface roughness is included in the denominator, indicating its negative impact. Overall, this design enables the quality coefficient to comprehensively evaluate the surface quality of a workpiece.

[0095] Second, due to The larger it is, the better the surface quality of the workpiece. Therefore, this function form makes the calculation results of the quality coefficient have clear physical meaning. High temperature and hardness values ​​(after weight adjustment) help to improve the quality coefficient, while higher roughness will reduce its value.

[0096] Third, by introducing the weight coefficient ( ), the importance of each factor in the workpiece surface quality assessment can be flexibly adjusted according to different application scenarios or specific needs, making the assessment process more accurate and adaptable to different workpiece characteristics.

[0097] Since in many processing processes, surface temperature directly affects the physical properties of materials, such as plasticity, toughness and fluidity. Higher temperatures tend to help the material form and reduce defects, thereby improving surface quality. Especially in metal processing and heat treatment processes, temperature changes have a particularly significant impact on surface quality. Therefore, the weight coefficient maximum;

[0098] Surface hardness affects the wear resistance, scratch resistance and fatigue resistance of materials, and usually plays an important role in surface quality assessment. However, compared with temperature, the influence of hardness is relatively small, because the improvement of hardness is usually related to a specific treatment process, and not all processing processes can significantly improve hardness. Therefore, the weight coefficient Less than the weight coefficient ;

[0099] Surface roughness is usually regarded as a negative factor affecting surface quality. Excessive roughness will lead to increased friction, decreased fatigue life and the appearance of surface defects. Although the importance of roughness to the final surface quality cannot be ignored, its weight coefficient in the comprehensive evaluation is usually small, because good temperature and hardness management can offset the negative impact of roughness to a certain extent. Therefore, the weight coefficient Minimum.

[0100] In summary, the weight coefficient of the workpiece surface temperature is greater than the weight coefficient of the workpiece surface hardness, and the weight coefficient of the workpiece surface hardness is greater than the weight coefficient of the workpiece surface roughness, that is, On the basis of .

[0101] As an implementation method, The value range is an open interval of 0.4-0.5. The value range is an open interval of 0.3-0.4. The value range is an open interval of 0.2-0.3. The specific value is set by technical personnel according to actual conditions and is not limited here.

[0102] Based on the above embodiment, a functional relationship between the deviation value of cutting speed, feed rate, cutting depth and tool life coefficient is constructed as follows:

[0103] ;

[0104] ;

[0105] in, For the The individual cutting speed deviation value is used to measure the degree to which the cutting speed deviates from the ideal range. The smaller the cutting speed deviation value, the more ideal the cutting speed, and then the smaller the tool life coefficient, the longer the tool life. For the The average cutting speed of each individual is the lower limit of the ideal cutting speed range, It is the upper limit of the ideal range of cutting speed;

[0106] For the The feed deviation value of each individual is used to measure the degree to which the feed rate deviates from the ideal range. The smaller the feed deviation value, the more ideal the feed rate, and then the smaller the tool life coefficient, the longer the tool life. For the The average feed amount of each individual, is the lower limit of the ideal feed range, is the upper limit of the ideal feed range;

[0107] For the The individual cutting depth deviation value is used to measure the degree to which the cutting depth deviates from the ideal range. The smaller the cutting depth deviation value, the more ideal the cutting depth, and then the smaller the tool life coefficient, the longer the tool life. For the The average cutting depth of each individual is the lower limit of the ideal cutting depth range, is the upper limit of the ideal range of cutting depth;

[0108] It should be noted that the ideal lower and upper limits of the cutting speed, feed rate, and cutting depth can be obtained from the technical manual of tool processing.

[0109] in, For the The tool life coefficient of each individual tool is used to comprehensively evaluate the influence of tool cutting characteristic parameters on tool life from three levels: cutting speed, feed rate and cutting depth. The smaller the tool life coefficient, the longer the tool life.

[0110] The reason for setting the above function form to express the functional relationship between the tool life coefficient and the deviation value of cutting speed, feed rate and cutting depth is as follows:

[0111] First, cutting is a complex physical process involving the interaction of multiple variables. During the cutting process, cutting speed, feed rate and cutting depth are key parameters that affect tool performance and life. Therefore, it is crucial to quantify how deviations in these parameters affect tool life.

[0112] Second, each cutting parameter (cutting speed, feed rate, cutting depth) has an ideal range, usually provided by the tool manufacturer. These ideal values ​​are fully tested and verified to ensure the best cutting performance and tool life.

[0113] By defining the deviation value ( ), the gap between actual parameters and ideal parameters can be quantified, and the calculation method of the deviation value (piecewise function) can reflect the performance impact in different situations.

[0114] Third, deviations in cutting speed, feed rate, and cutting depth will directly affect the friction and temperature between the tool and the workpiece, thereby affecting the wear rate of the tool. For example, excessive cutting speed may cause the tool to overheat and shorten its life.

[0115] Ideal cutting parameters can improve cutting efficiency, reduce processing time and energy consumption. An increase in deviation values ​​usually means a decrease in processing efficiency, which affects production costs and tool life.

[0116] Fourth, the tool life coefficient is obtained by weighted summation of the deviation values ​​( ), a comprehensive evaluation of the effects of cutting speed, feed rate and cutting depth on tool life can be achieved. This functional relationship allows the quantification of the specific impact of each deviation on tool life.

[0117] By adjusting the weight coefficient ( ), which can be optimized and adjusted according to different materials, tools and processing conditions to adapt to various processing environments.

[0118] Where, are all preset proportional coefficients. Specifically, it is the weight of the cutting speed deviation value in evaluating the impact of tool cutting characteristic parameters on tool life. Specifically, it is the weight of the feed deviation value in evaluating the impact of tool cutting characteristic parameters on tool life. Specifically, it is the weight of the cutting depth deviation value in evaluating the influence of the tool cutting characteristic parameters on the tool life;

[0119] The higher the cutting speed deviation value, the greater the friction between the tool and the workpiece and the heat generated by cutting. High temperature can cause softening of the tool material and accelerate wear. The feed rate directly affects the cutting amount per unit time. High feed rate will increase the cutting force. Although high feed rate deviation value will cause the tool to wear out quickly, its influence is usually reflected through the cutting force applied and the physical bearing capacity of the tool, which is not as direct and fast as the generation of heat and changes in material properties. Therefore, when evaluating tool life, cutting speed is usually given a higher weight .

[0120] The feed rate directly determines the amount of material removed per tool revolution. High feed rate deviation value will significantly increase the cutting force, causing the tool to wear out quickly. An increase in cutting depth deviation value will result in greater cutting load, which will affect the durability and service life of the tool.

[0121] The feed rate directly determines the amount of material removed per tool revolution. Therefore, in actual machining, adjusting the feed rate can quickly affect the cutting load of the tool and the material removal efficiency. High feed rate deviation value will immediately cause the tool to withstand greater cutting force and accelerate wear. Although cutting depth also has an important influence on the load of the tool, its effect is often influenced by cutting speed, material properties and other parameters of the cutting process, which means that the influence of cutting depth is not as direct and obvious as that of feed rate.

[0122] Therefore, although both feed rate and cutting depth have an important influence on tool life, the directness and sensitivity of feed rate in affecting tool wear and life make its influence considered more significant, greater than .

[0123] In summary, the weight coefficient of cutting speed deviation value is greater than that of feed rate deviation value, and the weight coefficient of feed rate deviation value is greater than that of cutting depth deviation value, i.e. in , let .

[0124] As an embodiment, the value range of which is an open interval of 0.4-0.5, the value range of which is an open interval of 0.3-0.4, the value range of which is an open interval of 0.2-0.3, and the specific value is set by the technical personnel according to the actual situation, which is not limited here.

[0125] On the basis of the above embodiment, the functional relationship of the workpiece surface quality coefficient, the tool life coefficient and the comprehensive evaluation coefficient is constructed, and the formula is as follows:

[0126] ;

[0127] in, For the The comprehensive evaluation coefficient of each individual is used to combine the workpiece surface quality coefficient and the tool life coefficient to comprehensively evaluate the workpiece-tool performance. The larger the comprehensive evaluation coefficient, the better the workpiece-tool performance, that is, the better the workpiece surface quality and the longer the tool life.

[0128] It should be noted that the workpiece surface quality coefficient The larger the value, the better the surface quality of the workpiece and the tool life coefficient The larger the value, the shorter the tool life. Therefore, the comprehensive evaluation coefficient and workpiece surface quality coefficient Positive correlation, comprehensive evaluation coefficient and tool life coefficient There is a negative correlation, so the calculation formula of the comprehensive evaluation coefficient in the above form is set;

[0129] Where, and are the weights in the calculation of workpiece surface quality coefficient and tool life coefficient, respectively, and and The specific value of is determined by the hierarchical analysis method, and the specific logic is as follows:

[0130] The two indicators of workpiece surface quality coefficient and tool life coefficient are marked, and the relative importance between them is determined by the nine-scale method to construct a judgment matrix, in which the index of workpiece surface quality coefficient is marked as 1 and the index of tool life coefficient is marked as 2. The constructed judgment matrix for:

[0131] ;

[0132] in, 、 denotes the index of the coefficient, and , , indicating that the index is The importance of the coefficient of index v to the comprehensive evaluation coefficient is The specific value is determined by relevant experts using a 1-9 scoring method. Indicates that the index is The coefficient of is extremely important for the comprehensive evaluation coefficient compared to the coefficient with index v. Indicates that the index is The coefficient of is extremely unimportant to the comprehensive evaluation coefficient compared to the coefficient with index v;

[0133] Each element value in the judgment matrix is ​​divided by the sum of its columns to obtain a normalized judgment matrix. The mean of the element values ​​in each row of the normalized judgment matrix is ​​calculated, and the mean of the element values ​​in the first row is used as the proportional coefficient of the workpiece surface quality coefficient, and the mean of the element values ​​in the second row is used as the proportional coefficient of the tool life coefficient. With the constraint that the sum of the scaled values ​​is equal to 1, the two proportional coefficients are scaled proportionally, and the values ​​obtained after scaling are used as the weights of the corresponding coefficients.

[0134] Based on the above embodiment, the specific process of step S5 is as follows:

[0135] Iterative optimization is performed on the individuals of the initial population. During the iterative optimization process, the constraints of the tool edge parameters are set, that is, the maximum and minimum values ​​of the rake angle, clearance angle, edge radius and fillet radius are set respectively. Within the constraints of the rake angle, clearance angle, edge radius and fillet radius, the tool edge parameters are iteratively optimized. Specifically, the comprehensive evaluation coefficient is set to Sort from large to small and select the comprehensive evaluation coefficient The individuals in the front row are regarded as parents, and the front row refers to the individuals in the comprehensive evaluation coefficient. The first 50% of individuals are exchanged, combined and mutated by crossover and mutation operations, and new individuals are generated. The tool cutting characteristic parameters of the newly generated individuals are obtained by using the tool characteristic prediction model, and their comprehensive evaluation coefficients are calculated. The new individuals and the parents are used as a new population, and the selection, crossover and mutation operations are repeated until the predetermined number of iterations is reached. The individual corresponding to the maximum comprehensive evaluation coefficient is taken as the optimal combination of tool edge parameters, and the individual corresponding to the maximum comprehensive evaluation coefficient is calibrated as , then the optimal tool edge parameter combination is the rake angle , rear angle , cutting edge radius and fillet radius .

[0136] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0137] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art will appreciate that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented by computer software, electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0138] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, and may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment as needed.

[0139] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A method for optimizing tool edge parameters based on workpiece-tool performance parameters, characterized in that; The specific steps include: S1. Obtaining tool cutting characteristic parameters and workpiece characteristic parameters under different tool edge parameter combinations, wherein the tool cutting characteristic parameters include cutting speed, feed rate, and cutting depth; the workpiece characteristic parameters include surface temperature, surface hardness, and surface roughness; and the tool edge parameters include rake angle, relief angle, edge radius, and fillet radius. The workpiece characteristic parameters and tool edge parameters are combined to construct individuals of the initial population. S2. Construct a tool characteristic prediction model, take the tool edge parameter combination of the initial population individuals as input, and the tool cutting characteristic parameters as label training model, and train the tool characteristic prediction model; S3. Establishing constraints on tool edge parameters, randomly combining the tool edge parameters of the initial population individuals under the constraints of the tool edge parameters, and inputting the tool edge parameter combinations of the initial population individuals into the tool characteristic prediction model to obtain tool cutting characteristic parameters; S4. Perform data processing and correlation analysis on the workpiece combinations of the initial population individuals to obtain the workpiece surface quality coefficient. Using the cutting speed, feed rate, cutting depth, and upper and lower limits of the ideal range, obtain the deviation values ​​of the cutting speed, feed rate, and cutting depth. Construct a functional relationship between the deviation values ​​of the cutting speed, feed rate, and cutting depth and the tool life coefficient. Construct a functional relationship between the workpiece surface quality coefficient, the tool life coefficient, and the comprehensive evaluation coefficient. The comprehensive evaluation coefficient is used to comprehensively evaluate the workpiece-tool performance. S5. Taking the maximization of the comprehensive evaluation coefficient as the objective function, the individuals of the initial population are iteratively optimized through the genetic algorithm under the constraints of the tool edge parameters to obtain the optimal individuals. Based on the optimal individuals, the optimal values ​​of the tool edge parameters are extracted.

2. The tool edge parameter optimization method based on workpiece-tool performance parameters according to claim 1, characterized in that: The workpiece characteristic parameters and tool edge parameters are spliced ​​together to construct individuals of the initial population of tool edge parameters. The specific process is as follows: Collect workpiece characteristic parameters, including workpiece surface temperature , workpiece surface hardness and workpiece surface roughness , the workpiece characteristic parameter combination is calibrated as ,and , Respectively represent the workpiece surface temperature, workpiece surface hardness and workpiece surface roughness in the workpiece characteristic parameter combination, and the initial population formed by splicing is calibrated as , and the initial population , is the first Individuals, is the index of the individual in the initial population, and , is the number of individuals in the initial population, ,in, Respectively The surface temperature, surface hardness, surface roughness, rake angle, back angle, cutting edge radius and fillet radius of each individual workpiece.

3. The method for optimizing tool edge parameters based on workpiece-tool performance parameters according to claim 1, characterized in that: The tool characteristic prediction model is constructed using a deep neural network based on a multilayer perceptron, wherein the deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, and an output layer, wherein the first hidden layer, the second hidden layer, and the third hidden layer each have at least two neurons and each use ReLU as an activation function; The process of training the tool characteristic prediction model is as follows: The rake angle, back angle, edge radius and fillet radius of the initial population individuals are used as input, and the tool cutting characteristic parameters are used as output labels for training. The mean square error is used as the loss function. When the mean square error is When the tool characteristic prediction model is within the range, the training of the tool characteristic prediction model is completed.

4. The method for optimizing tool edge parameters based on workpiece-tool performance parameters according to claim 2, wherein: The workpiece surface temperature, workpiece surface hardness and workpiece surface roughness are processed and correlated to obtain the workpiece surface quality coefficient based on the following formula: ； in, For the The workpiece surface quality coefficient of each individual workpiece is used to comprehensively evaluate the influence of workpiece characteristic parameters on workpiece surface quality from three levels: workpiece surface temperature, workpiece surface hardness and workpiece surface roughness. is the weight coefficient of the workpiece surface temperature, is the weight coefficient of the workpiece surface hardness, is the weight coefficient of the workpiece surface roughness. On the basis of .

5. The method for optimizing tool edge parameters based on workpiece-tool performance parameters according to claim 4, characterized in that: Construct a functional relationship between the deviation values ​​of cutting speed, feed rate, cutting depth and tool life coefficient, the formula is as follows: ； ； in, For the The tool life coefficient of each individual tool is used to comprehensively evaluate the influence of tool cutting characteristic parameters on tool life from three levels: cutting speed, feed rate and cutting depth; For the The individual cutting speed deviation value, For the The average cutting speed of each individual is the lower limit of the ideal cutting speed range, is the upper limit of the ideal range of cutting speed, For the The feed deviation value of each individual, For the The average feed amount of each individual, is the lower limit of the ideal feed range, is the upper limit of the ideal feed range, For the The individual cutting depth deviation value, For the The average cutting depth of each individual is the lower limit of the ideal cutting depth range, is the upper limit of the ideal range of cutting depth; is the weight of the cutting speed deviation value in evaluating the influence of tool cutting characteristic parameters on tool life, is the weight of the feed deviation value in evaluating the influence of tool cutting characteristic parameters on tool life, is the weight of the cutting depth deviation value in evaluating the influence of tool cutting characteristic parameters on tool life. On the basis of .

6. The method for optimizing tool edge parameters based on workpiece-tool performance parameters according to claim 5, characterized in that: Construct the functional relationship between the workpiece surface quality coefficient, tool life coefficient and comprehensive evaluation coefficient. The formula is as follows: ； in, For the The comprehensive evaluation coefficient of each individual is used to comprehensively evaluate the workpiece-tool performance by combining the workpiece surface quality coefficient and the tool life coefficient; and are the weights in the calculation of workpiece surface quality coefficient and tool life coefficient, respectively, and and The specific value of is determined by the hierarchical analysis method.

7. The method for optimizing tool edge parameters based on workpiece-tool performance parameters according to claim 6, characterized in that: The specific process of step S5 is as follows: Iterative optimization is performed on the individuals of the initial population. During the iterative optimization process, the constraints of the tool edge parameters are set, that is, the maximum and minimum values ​​of the rake angle, clearance angle, edge radius and fillet radius are set respectively. Within the constraints of the rake angle, clearance angle, edge radius and fillet radius, the tool edge parameters are iteratively optimized. Specifically, the comprehensive evaluation coefficient is set to Sort from large to small and select the comprehensive evaluation coefficient The individuals in the front row are taken as the parents. Through crossover and mutation operations, the genes of the parent individuals are exchanged, combined and mutated to generate new individuals. The tool cutting characteristic parameters of the newly generated individuals are obtained using the tool characteristic prediction model, and their comprehensive evaluation coefficients are calculated. The new individuals and the parents are taken as the new population, and the selection, crossover and mutation operations are repeated until the predetermined number of iterations is reached. The individual corresponding to the maximum comprehensive evaluation coefficient is taken as the optimal combination of tool edge parameters, and the individual corresponding to the maximum comprehensive evaluation coefficient is calibrated as , then the optimal tool edge parameter combination is the rake angle , rear angle , cutting edge radius and fillet radius .

Images