Cutter and coating combination recommendation system and method based on workpiece parameters

Abstract

The invention provides a tool and coating combination recommendation system and method based on workpiece parameters, and relates to the technical field of tool and coating combinings.The method comprises the steps that a test module collects machining performance data under different parameter combinations and covering tool characteristics and cutting performance data of workpieces, a prediction model building module trains a performance prediction model, and the performance prediction model builds a performance prediction model; the simulation module randomly combines parameters to generate initial population individuals and inputs the initial population individuals into the model to obtain data, the data processing module processes the obtained data and generates a life evaluation coefficient, a quality evaluation coefficient and a comprehensive evaluation coefficient, and the iterative optimization module optimizes the initial population by means of a genetic algorithm with the purpose of minimizing the comprehensive evaluation coefficient. And a recommendation module selects an optimal combination and recommends the optimal combination to the user according to the optimal values. According to the method, the actual testing frequency is greatly reduced, and the optimal matching scheme of the cutter and the coating, which can prolong the service life of the cutter, reduce the machining cost and improve the machining quality and is suitable for different machining scenes, is quickly and accurately found.

Description

Technical Field

[0001] The present invention relates to the technical field of tool and coating combinations, and specifically to a recommendation system and method for tool and coating combinations based on workpiece parameters. Background Art

[0002] With the development of advanced manufacturing technologies and high-performance materials, coating technologies and tool structural forms have made significant progress. The combination of tool edges and coatings plays a crucial role in machining, directly affecting tool service life and machining quality. For example, a micro-arc structure on the tool edge can reduce the cutting resistance of high-strength steel and enhance coating adhesion. The TiAlN coating has good high-temperature stability, enabling the tool to maintain good anti-wear ability during milling heat generation. The combination of a micro-arc edge and a TiAlN coating can reduce cutting heat, extend tool life, and improve production efficiency. Moreover, the tool has stable performance and high cutting quality in high-temperature and high-stress environments.

[0003] In the prior art, when selecting tool edge structures and coating combinations, there is a lack of scientific and effective methods, often relying on a large number of cumbersome actual tests and repeated adjustments. This not only consumes time and effort but also makes it difficult to ensure finding the best matching solution every time. Due to this unreasonable selection, serious technical defects are exposed during machining.

[0004] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide a recommendation system and method for tool and coating combinations based on workpiece parameters to solve the problems raised in the above background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions: A recommendation system for tool and coating combinations based on workpiece parameters, comprising: A test module for performing machining tests on workpieces to be machined with known workpiece parameters under combinations of tool parameters and coating parameters, and determining machining performance data corresponding to each parameter combination based on the machining tests. The machining performance data includes tool characteristic data and cutting performance data of the workpiece; A prediction model construction module for constructing a performance prediction model, using combinations of tool parameters and coating parameters and workpiece parameters of the workpiece to be machined as input features, and using tool characteristic data and cutting performance data of the workpiece as output labels to train the performance prediction model; A simulation module, which is used to randomly combine tool parameters and coating parameters to construct individuals in the initial population, input the individuals of the initial population and the workpiece parameters of the workpiece to be processed into the trained performance prediction model, and obtain tool characteristic data and cutting performance data of the workpiece; A data processing module, which is used to process the tool characteristic data to generate a life evaluation coefficient for evaluating the length of tool life, process the cutting performance data of the workpiece to generate a quality evaluation coefficient for evaluating the quality of the workpiece, and perform linear processing on the life evaluation coefficient and the quality evaluation coefficient to generate a comprehensive evaluation coefficient; An iterative optimization module, which is used to orient towards minimizing the comprehensive evaluation coefficient, iteratively optimize the individuals of the initial population through a genetic algorithm to obtain the optimal individuals, and extract the optimal values of the tool parameters and coating parameters based on the optimal individuals; A recommendation module, which is used to select the optimal combination of the tool and coating corresponding to the optimal values and recommend it to the user. Furthermore, the workpiece parameters are the workpiece material types, and the workpiece material types include low-carbon steel, medium-carbon steel, high-carbon steel, stainless steel, aluminum alloy, copper alloy, titanium alloy, nickel-based alloy, plastic, ceramic, and composite material; the tool parameters include the tool material type and the edge form type, the tool material types include high-speed steel, cemented carbide, ceramic material, cubic boron nitride, and polycrystalline diamond, the edge form types include straight edge, arc edge, chamfered edge, serrated edge, and micro-edge fillet, and the coating parameters include the coating material type and the coating thickness, and the coating material types include titanium nitride, titanium carbonitride, aluminum titanium nitride, chromium nitride, and diamond coating.

[0007] Furthermore, the tool characteristic data includes the flank wear width and the cutting force increase amplitude, and the cutting performance data of the workpiece includes the workpiece surface roughness and the residual stress.

[0008] Furthermore, define the workpiece material set as , , is the th workpiece material type, is the index of the workpiece material type, is the number of workpiece material types; Randomly combine the tool parameters and coating parameters to construct individuals in the initial population. The specific process is as follows: Define the tool material set as , , is the th tool material type, is the index of the tool material type, is the number of tool material types; Define the edge form set as , , is the th edge form type, is the index of the edge form type, is the number of edge form types; Define the coating material set as , , is the th coating material type, is the index of the coating material type, is the number of coating material types; Define the coating thickness set as , , is the th coating thickness, is the index of the coating thickness, is the number of coating thicknesses; Calibrate the initial population as , and the initial population , is the th individual in the initial population, is the index of the individual in the initial population, and , is the number of individuals in the initial population, , where are respectively the tool material type, edge form type, coating material type, and coating thickness of the th individual.

[0009] Furthermore, process the tool characteristic data to generate a life evaluation coefficient for evaluating the length of tool life. The formula is as follows: where is the life evaluation coefficient of the th individual. The life evaluation coefficient is used to comprehensively evaluate the length of tool life by combining two indicators: flank wear width and cutting force increase. is the flank wear width of the th individual, is the cutting force increase of the th individual, is the index of the individual in the initial population; In the formula, is the weight coefficient of the flank wear width, is the weight coefficient of the cutting force increase. On the basis of , let .

[0010] Furthermore, the cutting performance data of the workpiece are processed to generate a quality evaluation coefficient for evaluating the quality of the workpiece. The formula is as follows: where is the quality evaluation coefficient of the th individual. The quality evaluation coefficient is used to comprehensively evaluate the quality of the workpiece by combining two indicators: the surface roughness and residual stress of the workpiece. is the surface roughness of the workpiece of the th individual, is the residual stress of the workpiece of the th individual; In the formula, is the weight coefficient of the surface roughness of the workpiece, is the weight coefficient of the residual stress. On the basis of , let .

[0011] Furthermore, the life evaluation coefficient and the quality evaluation coefficient are linearly processed to generate a comprehensive evaluation coefficient. The formula is as follows: where is the comprehensive evaluation coefficient of the th individual. The comprehensive evaluation coefficient is used to comprehensively evaluate the overall performance of the tool and coating combination by combining two indicators: the life evaluation coefficient and the quality evaluation coefficient; In the formula, is the weight coefficient of the life evaluation coefficient, is the weight coefficient of the quality evaluation coefficient, and and are specifically determined by the analytic hierarchy process.

[0012] Furthermore, the specific steps of the iterative optimization module are as follows: Taking the minimization of the comprehensive evaluation coefficient as the optimization goal, the initial population is iteratively optimized, that is, selection, crossover, and mutation operations are performed on the individuals in the initial population . During the iterative optimization process, constraint conditions need to be set, that is, the maximum and minimum values of the coating thickness are set. Within the constraint range of the coating thickness, the initial population Iterative optimization, specifically, select individuals with comprehensive evaluation coefficients in the top ranks as parents. The top ranks refer to individuals in the top 50% of the comprehensive evaluation coefficients. Through crossover operations, exchange and combine the genes of parental individuals to generate new individuals. Repeat the selection and crossover operations until the predetermined number of iterations is reached; After iterative optimization of the initial population mark the optimal individual as , and the optimal values of the tool parameters and coating parameters are the edge form type , coating material type , coating thickness .

[0013] To achieve the above object, the present invention also provides the following technical solutions: A recommendation method for a tool and coating combination based on workpiece parameters, the method is generated based on any one of the above-mentioned recommendation systems for a tool and coating combination based on workpiece parameters, and the specific steps include: S1. Under the combination of tool parameters and coating parameters, conduct machining tests on workpieces to be machined with known workpiece parameters, and determine the machining performance data corresponding to each parameter combination based on the machining tests. The machining performance data includes tool characteristic data and cutting performance data of the workpiece; S2. Build a performance prediction model, use the combination of tool parameters and coating parameters and the workpiece parameters of the workpiece to be machined as input features, and use the tool characteristic data and cutting performance data of the workpiece as output labels to train the performance prediction model; S3. Randomly combine the tool parameters and coating parameters to construct individuals in the initial population, and input the individuals in the initial population and the workpiece parameters of the workpiece to be machined into the trained performance prediction model to obtain the tool characteristic data and cutting performance data of the workpiece; S4. Process the tool characteristic data to generate a life evaluation coefficient for evaluating the length of tool life, process the cutting performance data of the workpiece to generate a quality evaluation coefficient for evaluating the quality of the workpiece, and linearly process the life evaluation coefficient and the quality evaluation coefficient to generate a comprehensive evaluation coefficient; S5. Guided by minimizing the comprehensive evaluation coefficient, iteratively optimize the individuals in the initial population through a genetic algorithm to obtain the optimal individual, and based on the optimal individual, extract the optimal values of the tool parameters and coating parameters; S6. Select the optimal combination of the tool and coating corresponding to the optimal value and recommend it to the user.

[0014] Compared with the prior art, the beneficial effects of the present invention are: The test module of the present invention collects machining performance data under different parameter combinations. The prediction model construction module trains a model based on this data that can accurately analyze the relationship between parameters and performance. The simulation construction module randomly combines parameters to generate individuals, inputs them into the model to obtain machining performance data. The data processing module generates life, quality evaluation coefficients, and a comprehensive evaluation coefficient. The iterative optimization module uses a genetic algorithm to optimize with the goal of minimizing the comprehensive evaluation coefficient, extracts the optimal values of tool and coating parameters, and the recommendation module gives the optimal combination. The entire process forms a scientific and efficient closed loop, greatly reducing the number of actual tests, and quickly and accurately finding the best matching solution for tools and coatings that can extend tool life, reduce machining costs, improve machining quality, and are applicable to different machining scenarios, solving the defects existing in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a block diagram of the module composition of the present invention; Figure 2 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to specific embodiments.

[0017] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meaning understood by those with ordinary skills in the field to which the present invention belongs. The "first", "second", and similar terms used in the present invention do not indicate any order, quantity, or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or objects appearing before this term cover the elements or objects listed after this term and their equivalents, without excluding other elements or objects. The terms such as "connected" or "linked" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", "right", etc. are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0018] Embodiment 1: Please refer to Figure 1 , the present invention provides a technical solution: A recommendation system for tool and coating combinations based on workpiece parameters, comprising: A test module, which is used to perform machining tests on workpieces to be machined with known workpiece parameters under combinations of tool parameters and coating parameters, and determine the machining performance data corresponding to each parameter combination based on the machining tests. The machining performance data includes tool characteristic data and the cutting performance data of the workpiece; Based on the above embodiments, the workpiece parameters are the workpiece material type, which includes low-carbon steel, medium-carbon steel, high-carbon steel, stainless steel, aluminum alloy, copper alloy, titanium alloy, nickel-based alloy, plastic, ceramic, and composite material; the tool parameters include the tool material type and the edge form type. The tool material type includes high-speed steel, cemented carbide, ceramic material, cubic boron nitride, and polycrystalline diamond. The edge form type includes straight edge, arc edge, chamfered edge, serrated edge, and micro-edge fillet. The coating parameters include the coating material type and the coating thickness. The coating material type includes titanium nitride, titanium carbonitride, aluminum titanium nitride, chromium nitride, and diamond coating.

[0019] Among them, low-carbon steel, medium-carbon steel, high-carbon steel, stainless steel, aluminum alloy, copper alloy, titanium alloy, nickel-based alloy, plastic, ceramic, and composite material are assigned values of 01, 02, 03, 04, 05, 06, 07, 08, 09, 10, 11 in sequence; High-speed steel, cemented carbide, ceramic material, cubic boron nitride, and polycrystalline diamond are assigned values of 01, 02, 03, 04, 05 in sequence; Straight edge, arc edge, chamfered edge, serrated edge, and micro-edge fillet are assigned values of 01, 02, 03, 04, 05 in sequence; Titanium nitride, titanium carbonitride, aluminum titanium nitride, chromium nitride, and diamond coating are assigned values of 01, 02, 03, 04, 05 in sequence.

[0020] Based on the above embodiments, the tool characteristic data includes the flank wear width and the cutting force increase amplitude, and the cutting performance data of the workpiece includes the workpiece surface roughness and the residual stress.

[0021] Based on the above embodiments, the methods for collecting the flank wear width, the cutting force increase amplitude, the workpiece surface roughness, and the residual stress are as follows: Using a tool microscope, before workpiece machining, measure the initial wear width of the flank. After the tool finishes machining the workpiece, disassemble the tool from the machine tool and place it on the workbench of the measuring instrument. Observe the flank through the lens of a microscope or a projector and measure the final wear width of the flank. Subtract the initial wear width of the flank from the final wear width of the flank to obtain the flank wear width; Install a piezoelectric dynamometer at the spindle part of the machine tool. Just before the tool cuts into the workpiece and the cutting process has not entered a stable state, collect the cutting force at this time as the initial cutting force value. During the workpiece machining process, collect the cutting force data every 10 minutes. Convert the force signal into a digital signal through a data acquisition system and record it. According to the initial cutting force value and the cutting force at different times, calculate the absolute value of the change in the cutting force between the latter moment and the former moment, and then calculate the ratio of the absolute value of the change in the cutting force between adjacent moments to the initial cutting force value to obtain the cutting force increase amplitude; After the workpiece machining is completed, a surface roughness measuring instrument with a diamond stylus on its probe is used. The probe is placed on the cutting surface of the workpiece to be machined, and the stylus is slowly moved along the measured surface. The stylus will move up and down with the microscopic undulations of the surface. This movement is converted into an electrical signal by a sensor, and then through an amplifier and a data processing system, the numerical value of the surface roughness of the workpiece is finally obtained; After the workpiece machining is completed, the surface of the workpiece is irradiated with X-rays. When the X-rays are incident on the crystal material, diffraction will occur. Due to the existence of residual stress, the crystal lattice will be distorted, resulting in a change in the diffraction angle. By measuring the change in the diffraction angle and according to the relevant stress-strain relationship formula, the residual stress on the surface of the workpiece is calculated.

[0022] The flank wear width, cutting force increase, surface roughness of the workpiece, and residual stress collected need to be normalized. Through normalization, the data of different indicators are unified into the range of 0 to 1, eliminating the influence of dimension and value range, making these data comparable and consistent in subsequent analysis operations.

[0023] The prediction model construction module is used to construct a performance prediction model. Using the combination of workpiece parameters, tool parameters, and coating parameters as input features, and tool characteristic data and workpiece performance data as output labels, the performance prediction model is trained; On the basis of the above embodiments, the performance prediction model is composed of a deep learning network based on a multi-layer perceptron. The deep neural network of the multi-layer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, and an output layer. The first hidden layer, the second hidden layer, and the third hidden layer all have at least two neurons and all use ReLU as the activation function; In the performance prediction model, the input features of the deep learning network of the multi-layer perceptron include: the combination of tool parameters and coating parameters, and the workpiece parameters of the workpiece to be machined, a total of 3 groups of features.

[0024] The structure of the deep learning network of the multi-layer perceptron is as follows: Input layer: Receives 3 groups of features; First hidden layer: Has 128 neurons and uses ReLU as the activation function; Second hidden layer: Has 64 neurons and also uses the ReLU activation function; Third hidden layer: Has 32 neurons and uses the ReLU activation function; Output layer: Has 2 neurons and outputs tool characteristic data and workpiece performance data.

[0025] The process of training the performance prediction model is as follows: Using the combination of tool parameters and coating parameters, and the workpiece parameters of the workpiece to be machined as input quantities, training is carried out with tool characteristic data and workpiece cutting performance data as output labels, and the mean square error is used as the loss function. When the mean square error is within the range, the training of the performance prediction model is completed.

[0026] A simulation module for constructing a performance prediction model, using the combination of tool parameters and coating parameters, and the workpiece parameters of the workpiece to be machined as input features, and using tool characteristic data and workpiece cutting performance data as output labels to train the performance prediction model; On the basis of the above embodiments, define the workpiece material set as , , is the th workpiece material type, is the index of the workpiece material type, is the number of workpiece material types; Randomly combine the tool parameters and coating parameters to construct individuals in the initial population. The specific process is as follows: Define the tool material set as , , is the th tool material type, is the index of the tool material type, is the number of tool material types; Define the edge form set as , , is the th edge form type, is the index of the edge form type, is the number of edge form types; Define the coating material set as , , is the th coating material type, is the index of the coating material type, is the number of coating material types; Define the coating thickness set as , , is the th coating thickness, is the index of the coating thickness, is the number of coating thicknesses; Calibrate the initial population as , and the initial population , is the th individual in the initial population, is the index of the individual in the initial population, and , is the number of individuals in the initial population, , where are respectively the tool material type, edge form type, coating material type, and coating thickness of the th individual.

[0027] The data processing module is used to process the tool characteristic data to generate a life evaluation coefficient for evaluating the length of tool life, process the cutting performance data of the workpiece to generate a quality evaluation coefficient for evaluating the quality of the workpiece, and perform linear processing on the life evaluation coefficient and the quality evaluation coefficient to generate a comprehensive evaluation coefficient; On the basis of the above embodiment, the tool characteristic data is processed to generate a life evaluation coefficient for evaluating the length of tool life, and the formula is as follows: Where is the life evaluation coefficient of the th individual. The life evaluation coefficient is used to comprehensively evaluate the length of tool life by combining two indicators of flank wear width and cutting force increase. The smaller the life evaluation coefficient, the longer the tool life; is the flank wear width of the th individual, is the cutting force increase of the th individual; On this basis, it should be noted that an increase in the flank wear width means that the friction between the flank of the tool and the surface of the workpiece intensifies, the wear degree of the tool increases, the sharpness of the cutting edge decreases, the energy consumption during cutting increases, resulting in an increase in cutting force, a decrease in machining accuracy, and a reduction in the time the tool can continue to work normally. Therefore, the tool life decreases; an increase in the cutting force increase indicates that the load borne by the tool during cutting increases, which will accelerate the wear of the tool, making the tool more prone to failure forms such as breakage and chipping, thereby shortening the service life of the tool. Therefore, the above weighted summation formula is used to characterize the functional relationship between the life evaluation coefficient and the flank wear width , and the cutting force increase .

[0028] In the formula, is the weight coefficient of the flank wear width, is the weight coefficient of the cutting force increase; Since the flank wear width is a direct manifestation of tool wear and has a more direct and close relationship with tool life, as the flank wear width increases, the shape and size of the cutting edge of the tool will change, directly affecting the cutting performance, resulting in problems such as decreased machining accuracy and poor surface quality. In severe cases, the tool will lose its cutting ability.

[0029] During most cutting processes, the change in flank wear width is relatively stable and regular, and it is easier to predict and evaluate through experiments and experience. In contrast, the increase in cutting force is affected by various factors, such as the inhomogeneity of the workpiece material, small fluctuations in cutting parameters, vibration of the machining system, etc., and its change may be more complex and unstable. Therefore, when evaluating tool life, the flank wear width is more reliable, and assigning a larger weight to it can more accurately reflect the actual situation of tool life.

[0030] Therefore, on the basis of let .

[0031] As an implementation method, The value range of is 0.5 - 1, and the value range of

[0032] is 0 - 0.5. The specific values are set by technicians according to the actual situation and are not limited here. Among them, is the quality evaluation coefficient of the th individual. The quality evaluation coefficient is used to comprehensively evaluate the quality of the workpiece by combining two indicators of workpiece surface roughness and residual stress. And the smaller the quality evaluation coefficient, the better the workpiece quality; is the workpiece surface roughness of the th individual, is the residual stress of the th individual; On this basis, it should be noted that an increase in the workpiece surface roughness means an increase in the microscopic undulation degree of the workpiece surface, which will have a negative impact on various properties of the workpiece. An increase in surface roughness will lead to a decrease in mating accuracy and affect the overall operation stability of the equipment. In terms of corrosion resistance, a rough surface is more likely to accumulate corrosive substances, accelerating the corrosion process of the workpiece, thereby reducing the service life of the workpiece and resulting in a decrease in workpiece quality; the residual stress An increase will cause the internal stress of the workpiece to be in an unstable stress state. When the workpiece is subjected to an external load, the residual stress and the external load are superimposed, which may cause the local stress to exceed the yield strength of the material, resulting in deformation or even cracking of the workpiece. Especially under alternating loads, the residual stress will significantly reduce the fatigue life of the workpiece and lead to a decline in workpiece quality. Therefore, the above weighted summation formula is used to characterize the quality evaluation coefficient and the surface roughness of the workpiece , residual stress The functional relationship between them

[0033] In the formula is the weight coefficient of the surface roughness of the workpiece is the weight coefficient of the residual stress Relatively speaking, the processing technology may be easier to control the residual stress, or the residual stress can be adjusted and optimized more effectively during the processing, making the influence of the residual stress on the workpiece quality relatively small. For the surface roughness, due to the limitations of the processing technology, it is difficult to achieve the ideal accuracy, and its fluctuation has a greater impact on the workpiece quality. For example, in some precision grinding processes, although the residual stress can be controlled by adjusting the process parameters, the surface roughness is greatly affected by factors such as the grit size of the grinding wheel and the grinding parameters, and it is difficult to accurately control. At this time, it is necessary to increase the weight of the surface roughness .

[0034] Therefore, on the basis of , let .

[0035] As an implementation method The value range of is 0.5 - 1 The value range of is 0 - 0.5. The specific values are set by technicians according to the actual situation and are not limited here

[0036] On the basis of the above embodiments, the life evaluation coefficient and the quality evaluation coefficient are linearly processed to generate a comprehensive evaluation coefficient. The formula is as follows Among them is the comprehensive evaluation coefficient of the th individual. The comprehensive evaluation coefficient is used to comprehensively evaluate the overall performance of the tool and coating combination by combining two indicators of the life evaluation coefficient and the quality evaluation coefficient. And the smaller the comprehensive evaluation coefficient, the longer the life of the tool itself while ensuring the workpiece quality, and the better the overall performance of the combination On this basis, it should be noted that the life evaluation coefficient Decrease means that the tool life is relatively extended, the wear degree of the tool during cutting is slowed down, the wear width of the flank face is reduced, and the increase in cutting force is also correspondingly smaller, enabling the tool to perform cutting operations more stably. While meeting the processing requirements, it reduces the cost of frequent tool replacement and the impact on processing efficiency, improving the overall performance of the tool and coating combination; quality evaluation coefficient Decrease indicates that the workpiece has better quality, the surface roughness of the workpiece is reduced, and the micro-undulation degree is decreased, which is conducive to improving the fitting accuracy of the workpiece and enhancing the overall operation stability of the equipment. At the same time, the residual stress is reduced, making the internal stress state of the workpiece more stable. When bearing external loads, it is not easy to cause problems such as deformation or cracking, significantly improving the service life and reliability of the workpiece, and improving the overall performance of the tool and coating combination. Therefore, the above weighted summation formula is used to characterize the comprehensive evaluation coefficient and life evaluation coefficient 、quality evaluation coefficient The functional relationship between them

[0037] In the formula, Is the weight coefficient of the life evaluation coefficient, Is the weight coefficient of the quality evaluation coefficient, and And The specific values are determined by the analytic hierarchy process. The specific logic is as follows: Mark the two indicators of the life evaluation coefficient and the quality evaluation coefficient, determine the numerical values of the relative importance between each pair through the nine-scale method, and construct a judgment matrix. Among them, mark the index of the life evaluation coefficient as 1 and the index of the quality evaluation coefficient as 2. The constructed judgment matrix Is: Among them, 、 Both represent the index of the coefficient, and , , indicating that the coefficient with index Is more important to the comprehensive evaluation coefficient than the coefficient with index v, The specific numerical value is determined by relevant experts using the 1-9 scoring method, Indicates that the coefficient with index Is extremely important to the comprehensive evaluation coefficient compared to the coefficient with index v, Indicates that the coefficient with index Is extremely unimportant to the comprehensive evaluation coefficient compared to the coefficient with index v; Divide each element value in the judgment matrix by the sum of its column to obtain a normalized judgment matrix. Calculate the mean value of each row element value in the normalized judgment matrix, take the mean value of the first row element value as the proportional coefficient of the life evaluation coefficient, and take the mean value of the second row element value as the proportional coefficient of the quality evaluation coefficient. Under the constraint condition that the sum of the scaled values is equal to 1, perform equal-proportion scaling on the two proportional coefficients, and take the scaled values as the weights of the corresponding coefficients.

[0038] The iterative optimization module is used to iteratively optimize the individuals in the initial population through the genetic algorithm with the goal of minimizing the comprehensive evaluation coefficient, obtain the optimal individual, and extract the optimal values of the tool parameters and coating parameters based on the optimal individual. Based on the above embodiments, the specific steps of the iterative optimization module are as follows: With the comprehensive evaluation coefficient minimized as the optimization goal, perform iterative optimization on the initial population , that is, perform selection and crossover operations on the individuals in the initial population . During the iterative optimization process, set constraint conditions, that is, set the maximum and minimum values of the coating thickness. Within the constraint range of the coating thickness, perform iterative optimization on the initial population . Specifically, select the individuals with the top comprehensive evaluation coefficients as the parents. The top refers to the individuals in the top 50% of the comprehensive evaluation coefficients. Through the crossover operation, exchange and combine the genes of the parent individuals to generate new individuals. Repeat the selection and crossover operations until the predetermined number of iterations is reached. After performing iterative optimization on the initial population , label the optimal individual as . The optimal values of the tool parameters and coating parameters are the edge form type , the coating material type , and the coating thickness .

[0039] The recommendation module is used to select the optimal combination of the tool and coating corresponding to the optimal value and recommend it to the user.

[0040] Please refer to Figure 2 , the present invention also provides a technical solution: A method for recommending a tool and coating combination based on workpiece parameters, which is generated based on any one of the above-mentioned recommendation systems for a tool and coating combination based on workpiece parameters. The specific steps include: S1. Under the combination of tool parameters and coating parameters, perform a machining test on the workpiece to be machined with known workpiece parameters, and determine the machining performance data corresponding to each parameter combination based on the machining test. The machining performance data includes tool characteristic data and the cutting performance data of the workpiece. S2. Construct a performance prediction model, using the combination of tool parameters and coating parameters, and the workpiece parameters of the workpiece to be machined as input features, and using the tool characteristic data and the cutting performance data of the workpiece as output labels, and train the performance prediction model; S3. Randomly combine the tool parameters and coating parameters to construct individuals in the initial population, input the individuals in the initial population and the workpiece parameters of the workpiece to be machined into the trained performance prediction model, and obtain the tool characteristic data and the cutting performance data of the workpiece; S4. Process the tool characteristic data to generate a life evaluation coefficient for evaluating the length of tool life, process the cutting performance data of the workpiece to generate a quality evaluation coefficient for evaluating the quality of the workpiece, and perform linear processing on the life evaluation coefficient and the quality evaluation coefficient to generate a comprehensive evaluation coefficient; S5. Guided by minimizing the comprehensive evaluation coefficient, iteratively optimize the individuals in the initial population through a genetic algorithm to obtain the optimal individual, and based on the optimal individual, extract the optimal values of the tool parameters and coating parameters; S6. Select the optimal combination of the tool and coating corresponding to the optimal values and recommend it to the user.

[0041] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0042] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. 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 can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0043] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0044] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application.

Claims

1. A recommendation system for tool and coating combinations based on workpiece parameters, characterized in that: Including: A test module, which is used to perform machining tests on a workpiece to be machined with known workpiece parameters under different combinations of tool parameters and coating parameters, and determine the machining performance data corresponding to each parameter combination based on the machining tests. The machining performance data includes tool characteristic data and the cutting performance data of the workpiece. A prediction model construction module, which is used to construct a performance prediction model, and uses the combination of tool parameters and coating parameters and the workpiece parameters of the workpiece to be machined as input features, and uses the tool characteristic data and the cutting performance data of the workpiece as output labels to train the performance prediction model. A simulation module, which is used to randomly combine the tool parameters and coating parameters to construct individuals in the initial population, and input the individuals in the initial population and the workpiece parameters of the workpiece to be machined into the trained performance prediction model to obtain the tool characteristic data and the cutting performance data of the workpiece. A data processing module, which is used to process the tool characteristic data to generate a life evaluation coefficient for evaluating the length of tool life, process the cutting performance data of the workpiece to generate a quality evaluation coefficient for evaluating the quality of the workpiece, and perform linear processing on the life evaluation coefficient and the quality evaluation coefficient to generate a comprehensive evaluation coefficient. An iterative optimization module, which is used to iteratively optimize the individuals in the initial population through a genetic algorithm with the goal of minimizing the comprehensive evaluation coefficient, obtain the optimal individual, and extract the optimal values of the tool parameters and coating parameters based on the optimal individual. A recommendation module, which is used to select the optimal combination of the tool and coating corresponding to the optimal value and recommend it to the user.

2. The recommended system for tool and coating combinations based on workpiece parameters according to claim 1, characterized in that: The workpiece parameters are the workpiece material type, which includes low-carbon steel, medium-carbon steel, high-carbon steel, stainless steel, aluminum alloy, copper alloy, titanium alloy, nickel-based alloy, plastic, ceramic, and composite material; the tool parameters include the tool material type and the edge form type. The tool material type includes high-speed steel, cemented carbide, ceramic material, cubic boron nitride, and polycrystalline diamond, and the edge form type includes straight edge, arc edge, chamfered edge, serrated edge, and micro-edge fillet. The coating parameters include the coating material type and the coating thickness. The coating material type includes titanium nitride, titanium carbonitride, aluminum titanium nitride, chromium nitride, and diamond coating.

3. The recommended system for tool and coating combinations based on workpiece parameters according to claim 1, wherein: The tool characteristic data includes the flank wear width and the cutting force increase, and the cutting performance data of the workpiece includes the surface roughness of the workpiece and the residual stress.

4. The recommended system for tool and coating combinations based on workpiece parameters according to claim 2, characterized in that: Define the workpiece material set as , , as the th workpiece material type, is the index of the workpiece material type, is the number of workpiece material types; Randomly combine the tool parameters and coating parameters to construct individuals in the initial population. The specific process is as follows: Define the set of tool materials as , , is the th type of tool material, is the index of the tool material type, is the number of tool material types; Define the set of edge forms as , , is the th edge form type, is the index of the edge form type, is the number of edge form types; Define the set of coating materials as , , be the th type of coating material, be the index of the coating material type, be the number of coating material types; Define the coating thickness set as , , is the th coating thickness, is the index of the coating thickness, is the number of coating thicknesses; Calibrate the initial population as , and the initial population , is the th individual in the initial population, is the index of the individual in the initial population, and , is the number of individuals in the initial population, , where are respectively the tool material type, edge form type, coating material type, and coating thickness of the th individual.

5. The recommended system for tool and coating combinations based on workpiece parameters according to claim 3, characterized in that: Process the tool characteristic data to generate a life evaluation coefficient for evaluating the length of tool life. The formula is as follows: Among them, is the tool life evaluation coefficient of the -th individual. The tool life evaluation coefficient is used to comprehensively evaluate the tool life by combining two indicators: the flank wear width and the cutting force increase. is the flank wear width of the -th individual. is the cutting force increase of the -th individual. is the index of the individual in the initial population. In the formula, is the weight coefficient of the flank wear width, is the weight coefficient of the cutting force increase amplitude. Based on , let .

6. The recommended system for tool and coating combinations based on workpiece parameters according to claim 5, characterized in that: Process the cutting performance data to generate a quality evaluation coefficient for evaluating the quality of the workpiece. The formula is as follows: Among them, is the quality evaluation coefficient of the th individual. The quality evaluation coefficient is used to comprehensively evaluate the quality of the workpiece by combining two indicators of the surface roughness and residual stress of the workpiece. is the surface roughness of the workpiece of the th individual, and is the residual stress of the th individual. In the formula, is the weight coefficient of the workpiece surface roughness, is the weight coefficient of the residual stress. On the basis of , let .

7. The recommended system for tool and coating combinations based on workpiece parameters according to claim 6, characterized in that: Perform linear processing on the life evaluation coefficient and the quality evaluation coefficient to generate a comprehensive evaluation coefficient. The formula is as follows: Among them, is the comprehensive evaluation coefficient of the th individual. The comprehensive evaluation coefficient is used to comprehensively evaluate the overall performance of the tool and coating combination by combining two indicators, namely the life evaluation coefficient and the quality evaluation coefficient. In the formula, is the weight coefficient of the life evaluation coefficient, is the weight coefficient of the quality evaluation coefficient, and and The specific values of are determined by the analytic hierarchy process.

8. The recommended system for tool and coating combinations based on workpiece parameters according to claim 7, characterized in that: The specific steps of the iterative optimization module are as follows: Taking the minimization of the comprehensive evaluation coefficient as the optimization goal, the initial population is iteratively optimized, that is, the individuals in the initial population are selected and crossed. During the iterative optimization process, constraint conditions need to be set, that is, the maximum and minimum values of the coating thickness are set. Within the constraint range of the coating thickness, the initial population is iteratively optimized. Specifically, the individuals with the top comprehensive evaluation coefficients are selected as the parents. The top refers to the individuals in the top 50% of the comprehensive evaluation coefficients. Through the crossing operation, the genes of the parent individuals are exchanged and combined to generate new individuals. The selection and crossing operations are repeated until the predetermined number of iterations is reached; After iterative optimization of the initial population the optimal individual is designated as , and the optimal values of the tool parameters and coating parameters are the tool material type , the edge form type , the coating material type , and the coating thickness .

9. A method for recommending a tool and coating combination based on workpiece parameters, the method being generated based on a recommendation system for a tool and coating combination based on workpiece parameters according to any one of claims 1-8, characterized in that: The specific steps include: S1. Perform machining tests on a workpiece to be machined with known workpiece parameters under the combination of tool parameters and coating parameters, and determine the machining performance data corresponding to each parameter combination based on the machining tests. The machining performance data includes tool characteristic data and the cutting performance data of the workpiece. S2. Construct a performance prediction model, using the combination of tool parameters and coating parameters, and the workpiece parameters of the workpiece to be machined as input features, and using the tool characteristic data and the cutting performance data of the workpiece as output labels, and train the performance prediction model; S3. Randomly combine the tool parameters and coating parameters to construct individuals in the initial population, input the individuals in the initial population and the workpiece parameters of the workpiece to be machined into the trained performance prediction model, and obtain the tool characteristic data and the cutting performance data of the workpiece; S4. Process the tool characteristic data to generate a life evaluation coefficient for evaluating the length of tool life, process the cutting performance data of the workpiece to generate a quality evaluation coefficient for evaluating the quality of the workpiece, and linearly process the life evaluation coefficient and the quality evaluation coefficient to generate a comprehensive evaluation coefficient; S5. Guided by minimizing the comprehensive evaluation coefficient, iteratively optimize the individuals in the initial population through the genetic algorithm, obtain the optimal individuals, and based on the optimal individuals, extract the optimal values of the tool parameters and coating parameters; S6. Select the optimal combination of the tool and coating corresponding to the optimal value and recommend it to the user.

Images