Energy consumption optimization method and system for CNC machine tools

Abstract

The present application provides an energy consumption optimization method and system for CNC machine tools, which relates to the field of data processing technology. The method includes: taking material attribute information and machine tool attribute information as constraints, performing correlation analysis between cutting parameters and cutting specific energy, and constructing a cutting specific energy prediction model; taking expected surface roughness as a quality constraint, and minimizing cutting specific energy and tool wear as the optimization purpose, constructing a comprehensive cutting evaluation function; based on the comprehensive cutting evaluation function, the cutting specific energy prediction model and the cutting process twin model, optimizing the cutting parameters to obtain optimized cutting parameters. This application can solve the technical problems that the existing energy consumption optimization methods for CNC cutting machine tools often focus on energy saving while ignoring other important factors such as cutting quality, resulting in poor accuracy and comprehensiveness of cutting parameter settings, and poor practicality of energy consumption optimization schemes, and can achieve the technical goal of multi-objective optimization of equipment energy consumption, cutting quality and tool wear.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an energy consumption optimization method and system for a CNC machine tool. Background Art

[0002] As an important production machine for industrial products, CNC machine tools not only consume a lot of energy, but also have low energy utilization, which means there is a lot of room for energy saving. However, CNC machine tools have many internal components, and the energy consumption structure under different working conditions is also very different. Traditional manufacturing has always relied on the experience of professional technicians to set process parameters. When making energy-saving improvements, it usually only considers how to reduce energy consumption and cannot achieve multi-objective optimization.

[0003] In summary, the existing energy consumption optimization methods for CNC cutting machine tools often focus on energy saving, while ignoring other important factors such as cutting quality. They are unable to accurately achieve the expected effect of multi-objective optimization, resulting in poor accuracy and comprehensiveness of cutting parameter settings, and causing technical problems such as poor practicality of energy consumption optimization solutions. Summary of the invention

[0004] The purpose of this application is to provide an energy consumption optimization method and system for CNC machine tools, so as to solve the problem that the energy consumption optimization methods of existing CNC cutting machine tools often focus on energy saving while ignoring other important factors such as cutting quality, and cannot accurately achieve the expected effect of multi-objective optimization, resulting in poor accuracy and comprehensiveness of cutting parameter settings, and causing technical problems such as poor practicality of energy consumption optimization solutions.

[0005] In view of the above problems, the present application provides an energy consumption optimization method and system for a CNC machine tool.

[0006] In a first aspect, the present application provides an energy consumption optimization method for a CNC machine tool, which is implemented by an energy consumption optimization system for a CNC machine tool, wherein the method includes: obtaining material property information and expected processing indicators of a target product, wherein the expected processing indicators include expected surface roughness; reading the machine tool property information and cutting parameters of the CNC machine tool, and using the material property information and the machine tool property information as constraints to perform correlation analysis between cutting parameters and cutting specific energy, and construct a cutting specific energy prediction model, wherein the cutting specific energy is the ratio of the total energy consumption of the cutting material to the volume of the removed material; based on digital twin technology, cutting simulation modeling is performed according to the material property information and the machine tool property information to generate a cutting processing twin model; using the expected surface roughness as a quality constraint and minimizing the cutting specific energy and tool wear as the optimization purpose, a comprehensive cutting evaluation function is constructed; based on the comprehensive cutting evaluation function, the cutting specific energy prediction model and the cutting processing twin model, the cutting parameters are optimized using a black hole mutation algorithm to obtain optimized cutting parameters, and the target product is cut according to the optimized cutting parameters.

[0007] In the second aspect, the present application also provides an energy consumption optimization system for a CNC machine tool, which is used to execute an energy consumption optimization method for a CNC machine tool as described in the first aspect, wherein the system includes: an information acquisition module, which is used to acquire material property information and expected processing indicators of a target product, wherein the expected processing indicators include expected surface roughness; a cutting energy ratio prediction model construction module, which is used to read the machine tool property information and cutting parameters of the CNC machine tool, and perform correlation analysis between cutting parameters and cutting energy ratios based on the material property information and the machine tool property information as constraints, and construct a cutting energy ratio prediction model, wherein the cutting energy ratio is the ratio of the total energy consumption of cutting materials to the volume of removed materials. ; A cutting processing twin model generation module, which is used to perform cutting simulation modeling based on the digital twin technology and the material property information and the machine tool property information to generate a cutting processing twin model; a comprehensive cutting evaluation function construction module, which is used to construct a comprehensive cutting evaluation function with the expected surface roughness as the quality constraint and the minimization of cutting specific energy and tool wear as the optimization purpose; a cutting parameter optimization module, which is used to optimize the cutting parameters based on the comprehensive cutting evaluation function, the cutting specific energy prediction model and the cutting processing twin model using a black hole mutation algorithm to obtain optimized cutting parameters, and cut the target product according to the optimized cutting parameters.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] By acquiring material property information and expected processing indicators of the target product, wherein the expected processing indicators include expected surface roughness; reading the machine tool property information and cutting parameters of the CNC machine tool, taking the material property information and the machine tool property information as constraints, performing correlation analysis between cutting parameters and cutting specific energy, and constructing a cutting specific energy prediction model, wherein the cutting specific energy is the ratio of the total energy consumption of the cutting material to the volume of the removed material; based on the digital twin technology, performing cutting simulation modeling according to the material property information and the machine tool property information, and generating a cutting processing twin model; taking the expected surface roughness as the quality constraint, and minimizing the cutting specific energy and tool wear as the optimization purpose, constructing a comprehensive cutting evaluation function; based on the comprehensive cutting evaluation function, the cutting specific energy prediction model and the cutting processing twin model, using the black hole mutation algorithm to optimize the cutting parameters, obtaining optimized cutting parameters, and cutting the target product according to the optimized cutting parameters. That is to say, by taking material attribute information and machine tool attribute information as constraints, the correlation analysis between cutting parameters and cutting specific energy is performed, and the cutting specific energy prediction model is constructed based on the correlation analysis results; on the other hand, based on the digital twin technology, cutting simulation modeling is performed according to the material attribute information and machine tool attribute information to generate a cutting processing twin model; then, taking the expected surface roughness as the quality constraint, minimizing the cutting specific energy and tool wear as the optimization purpose, a comprehensive cutting evaluation function is constructed to provide a basis for achieving the technical goal of multi-objective optimization of equipment energy consumption, cutting quality and tool wear; further based on the comprehensive cutting evaluation function, the cutting specific energy prediction model and the cutting processing twin model, the black hole mutation algorithm is used to optimize the cutting parameters to obtain the optimized cutting parameters; finally, the target product is cut according to the optimized cutting parameters. It can improve the rationality, accuracy and comprehensiveness of the cutting parameter setting, achieve the technical goal of multi-objective optimization of equipment energy consumption, cutting quality and tool wear, and thus improve the practicality and rationality of the energy consumption optimization scheme under the premise of ensuring cutting quality.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0012] Figure 1 A schematic flow chart of an energy consumption optimization method for a CNC machine tool according to the present application;

[0013] Figure 2 A schematic diagram of a process for constructing a cutting specific energy prediction model in an energy consumption optimization method for a CNC machine tool in the present application;

[0014] Figure 3 This is a structural schematic diagram of an energy consumption optimization system for a CNC machine tool in the present application.

[0015] Description of reference numerals:

[0016] Information acquisition module 11, cutting specific energy prediction model construction module 12, cutting process twin model generation module 13, comprehensive cutting evaluation function construction module 14, cutting parameter optimization module 15. DETAILED DESCRIPTION

[0017] This application provides an energy consumption optimization method and system for CNC machine tools, which solves the problem that the energy consumption optimization methods of existing CNC cutting machine tools often focus on energy saving, while ignoring other important factors such as cutting quality, and cannot accurately achieve the expected effect of multi-objective optimization, resulting in poor accuracy and comprehensiveness of cutting parameter settings, and poor practicality of energy consumption optimization solutions. The rationality, accuracy and comprehensiveness of cutting parameter settings can be improved, and the technical goals of multi-objective optimization of equipment energy consumption, cutting quality and tool wear can be achieved, thereby improving the practicality and rationality of energy consumption optimization solutions while ensuring cutting quality.

[0018] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0019] Embodiment 1

[0020] Please see attached Figure 1The present application provides an energy consumption optimization method for a CNC machine tool, wherein the method is applied to an energy consumption optimization system for a CNC machine tool, and the method specifically comprises the following steps:

[0021] Step 1: Obtain material property information and expected processing indicators of the target product, wherein the expected processing indicators include expected surface roughness.

[0022] Specifically, the material property information and expected processing indicators of the target product are obtained, wherein the target product is the product to be cut, and the material property information includes the material chemical composition and material performance parameters. The material chemical composition refers to the chemical elements contained in the material and their relative proportions; the material performance parameters include material strength, material hardness and other parameters. Among them, the expected processing indicators include the expected surface roughness. The expected surface roughness refers to the surface quality level of the workpiece that is expected to be achieved during the CNC machine tool cutting operation. Surface roughness is an important indicator to measure the flatness of the workpiece surface, which directly affects the subsequent performance and appearance quality of the workpiece.

[0023] Step 2: Read the machine tool attribute information and cutting parameters of the CNC machine tool, perform correlation analysis between the cutting parameters and the cutting specific energy based on the material attribute information and the machine tool attribute information, and construct a cutting specific energy prediction model, wherein the cutting specific energy is the ratio of the total energy consumption of the cutting material to the volume of the removed material.

[0024] Specifically, the machine tool attribute information and cutting parameters of the CNC machine tool are read, wherein the machine tool attribute information includes data such as the type, performance, service life, maintenance status, tool type and quality of the machine tool; the cutting parameters are key parameters used to control the cutting process during CNC machine tool processing, which directly affect the processing efficiency, processing quality and machine tool energy consumption, including cutting speed, feed rate and back cutting amount. The cutting speed refers to the speed at which the tool moves relative to the workpiece per unit time, the feed rate refers to the feed speed of the tool relative to the workpiece per unit time, and the back cutting amount refers to the depth to which the tool enters the workpiece during each cutting.

[0025] Then, the material attribute information and the machine tool attribute information are used as search constraints, and information retrieval is performed online to obtain a sample data set, wherein the sample data includes sample cutting parameters, sample cutting energy consumption set, and sample removal volume set; further, the correlation analysis between cutting parameters and cutting specific energy is performed based on the sample data set, wherein cutting specific energy refers to the ratio of the total energy consumption of cutting materials to the volume of removed materials, which is an important indicator for measuring energy efficiency in the cutting process, and the BP neural network is trained based on the correlation analysis results and the sample data set to construct a cutting specific energy prediction model. By constructing a cutting specific energy prediction model, the accuracy and efficiency of cutting specific energy prediction can be improved, providing support for subsequent cutting parameter optimization.

[0026] Step three: Based on the digital twin technology, cutting simulation modeling is performed according to the material property information and the machine tool property information to generate a cutting processing twin model.

[0027] Specifically, digital twin technology is a technology that simulates and predicts the behavior and performance of physical entities by creating digital copies of physical entities in a virtual environment. Then, based on the digital twin technology, cutting simulation modeling is performed according to the material property information and the machine tool property information. First, the virtual model of the workpiece and the tool is created using CAD software, and the tool path and cutting parameters are created using CAM software; then, the cutting parameters are set in the virtual environment, such as cutting speed, feed rate, back cutting amount, etc., and the physical behavior in the cutting process, such as cutting force, cutting temperature, tool wear, etc., is simulated; then, the simulation model is run to simulate the actual cutting process, including the interaction between the tool and the workpiece, cutting force, cutting temperature, chip formation and discharge, etc., to generate a cutting processing twin model. By constructing a cutting processing twin model based on digital twin technology, support is provided for the prediction of cutting surface roughness and tool wear in the subsequent cutting parameter optimization process.

[0028] Step 4: Taking the expected surface roughness as the quality constraint and minimizing the cutting specific energy and tool wear as the optimization objective, a comprehensive cutting evaluation function is constructed.

[0029] Step 5: Based on the comprehensive cutting evaluation function, the cutting specific energy prediction model and the cutting process twin model, the cutting parameters are optimized using the black hole mutation algorithm to obtain the optimized cutting parameters, and the target product is cut according to the optimized cutting parameters.

[0030] Specifically, the expected surface roughness is used as the quality constraint condition of cutting processing, minimizing the cutting specific energy and tool wear is used as the optimization purpose, and a matching weight is set according to the relative importance of each evaluation index in the comprehensive evaluation to construct a comprehensive cutting evaluation function. By constructing a comprehensive cutting evaluation function, the technical goal of multi-objective optimization can be achieved in the optimization of cutting parameters, thereby improving energy utilization efficiency and reducing tool costs while ensuring processing quality.

[0031] Then, the fitness of the cutting parameters is evaluated based on the comprehensive cutting evaluation function, the cutting specific energy of the cutting parameters is predicted by the cutting specific energy prediction model, the surface roughness and tool wear of the cutting parameters are predicted by the cutting processing twin model, and the cutting parameter constraint threshold is used as the optimization space. The cutting parameters are optimized using the black hole mutation algorithm to obtain the optimized cutting parameters. Finally, according to the optimized cutting parameters, the CNC machine tool is controlled to perform cutting processing on the target product. By constructing a comprehensive cutting evaluation function and optimizing the cutting parameters based on the comprehensive cutting evaluation function, the rationality, accuracy and comprehensiveness of the cutting parameter setting can be improved, and the technical goals of multi-objective optimization of equipment energy consumption, cutting quality and tool wear can be achieved, thereby improving the practicality and rationality of the energy consumption optimization plan while ensuring the cutting quality.

[0032] The energy consumption optimization method of a CNC machine tool is applied to an energy consumption optimization system of a CNC machine tool, which can solve the technical problem that the energy consumption optimization method of existing CNC cutting machine tools often focuses on energy saving while ignoring other important factors such as cutting quality, and cannot accurately achieve the expected effect of multi-objective optimization, resulting in poor accuracy and comprehensiveness of cutting parameter settings, resulting in poor practicality of energy consumption optimization solutions. First, the material property information and expected processing indicators of the target product are obtained, wherein the expected processing indicators include the expected surface roughness; then, the machine tool property information and cutting parameters of the CNC machine tool are read, and the correlation analysis between the cutting parameters and the cutting specific energy is performed with the material property information and the machine tool property information as constraints, and a cutting specific energy prediction model is constructed, wherein the cutting specific energy is the ratio of the total energy consumption of the cutting material to the volume of the removed material; then, based on the digital twin technology, cutting simulation modeling is performed according to the material property information and the machine tool property information to generate a cutting processing twin model; next, with the expected surface roughness as the quality constraint and minimizing the cutting specific energy and tool wear as the optimization purpose, a comprehensive cutting evaluation function is constructed; finally, based on the comprehensive cutting evaluation function, the cutting specific energy prediction model and the cutting processing twin model, the cutting parameters are optimized using the black hole mutation algorithm to obtain the optimized cutting parameters, and the target product is cut according to the optimized cutting parameters. By taking material attribute information and machine tool attribute information as constraints, the correlation analysis between cutting parameters and cutting specific energy is performed, and a cutting specific energy prediction model is constructed based on the correlation analysis results; on the other hand, based on digital twin technology, cutting simulation modeling is performed according to material attribute information and machine tool attribute information to generate a cutting processing twin model; then, taking the expected surface roughness as the quality constraint, minimizing cutting specific energy and tool wear as the optimization purpose, a comprehensive cutting evaluation function is constructed to provide a basis for achieving the technical goal of multi-objective optimization of equipment energy consumption, cutting quality and tool wear; further based on the comprehensive cutting evaluation function, cutting specific energy prediction model and cutting processing twin model, the black hole mutation algorithm is used to optimize the cutting parameters to obtain the optimized cutting parameters; finally, the target product is cut according to the optimized cutting parameters. It can improve the rationality, accuracy and comprehensiveness of cutting parameter settings, achieve the technical goal of multi-objective optimization of equipment energy consumption, cutting quality and tool wear, and thus improve the practicality and rationality of the energy consumption optimization scheme under the premise of ensuring cutting quality.

[0033] Furthermore, a cutting specific energy prediction model is constructed, as shown in the attached Figure 2 As shown, step 2 of this application includes:

[0034] The material attribute information is used as a material constraint, and the machine tool attribute information is used as an equipment constraint. Information retrieval is performed based on big data to obtain a sample data set, wherein the sample data includes a sample cutting parameter, a sample cutting energy consumption set, and a sample removal volume set; multiple sample cutting specific energies are calculated based on the sample cutting energy consumption set and the sample removal volume set, and the mean value of the sample cutting specific energies is obtained by performing mean calculation, wherein the cutting specific energy is the ratio of the total energy consumption of the cutting material to the volume of the removed material; the deviation values ​​of the multiple sample cutting specific energies and the mean value of the sample cutting specific energies are calculated respectively, and the sample with a deviation value less than a predetermined deviation threshold is selected as a qualified sample cutting specific energy, and the multiple qualified sample cutting specific energies are set as qualified sample cutting specific energies. The mean of the specific energy is set as the standard sample cutting specific energy; multiple standard sample cutting specific energies of multiple sample cutting parameters are obtained in turn, and a sample training set is constructed according to the multiple sample cutting parameters and the multiple standard sample cutting specific energies; the sample training set is divided into N equal parts, and is selected N times with replacement to construct a first training set, and is iteratively selected N times to obtain N training sets; with the sample cutting parameters as input and the standard sample cutting specific energy as supervision, the BP neural network is supervised and trained using the N training sets to obtain N convergent cutting specific energy prediction units to build a cutting specific energy prediction model, wherein the output of the cutting specific energy prediction model is the mean of the output results of the N convergent cutting specific energy prediction units.

[0035] Specifically, first, the material attribute information is used as the material constraint, and the machine tool attribute information is used as the equipment constraint, and information retrieval is performed based on big data, that is, the sample data set is deeply analyzed by using big data technology and information retrieval technology, and the sample data set closest to the target processing conditions is found through comparison and correlation analysis, and the sample data set is obtained, wherein the sample data includes sample cutting parameters, sample cutting energy consumption set and sample removal volume set, and the sample removal volume refers to the removal volume of the material. Then, the cutting specific energy is calculated based on the sample cutting energy consumption set and the sample removal volume set, wherein the cutting specific energy is the ratio of the total energy consumption of the cutting material to the volume of the removed material, and multiple sample cutting specific energies are obtained; further, the average of the multiple sample cutting specific energies is calculated to obtain the average of the sample cutting specific energies.

[0036] Then, the deviation values ​​of multiple sample cutting specific energies and the mean of sample cutting specific energies are calculated respectively to obtain multiple deviation values, and the sample cutting specific energies whose deviation values ​​are less than the predetermined deviation threshold are further selected as qualified sample cutting specific energies, wherein the predetermined deviation threshold can be set according to the actual situation, to obtain multiple qualified sample cutting specific energies, and finally the mean of multiple qualified sample cutting specific energies is set as the standard sample cutting specific energy. The same method is used for iterative analysis to obtain multiple standard sample cutting specific energies of multiple sample cutting parameters, and a sample training set is constructed based on multiple sample cutting parameters and multiple standard sample cutting specific energies. Then the sample training set is divided into N parts, while ensuring that each part of the data is balanced in content, to obtain N data sets; then, N data sets are selected with replacement N times to construct the first training set, and the same method is used to iteratively select N times to obtain N training sets.

[0037] BP neural network is a multi-layer feedforward neural network, which consists of an input layer, a hidden layer (one or more) and an output layer, wherein each layer consists of multiple neurons, and the neurons are connected by weights. Each neuron receives input from the neurons in the previous layer, and after being processed by a nonlinear activation function, it is output to the next layer. An initial cutting energy prediction unit is constructed based on the BP neural network, wherein the initial cutting energy prediction unit is a neural network model that can be iteratively optimized in the BP neural network, wherein the input data of the initial cutting energy prediction unit is the cutting parameter, and the output data is the cutting energy. Then, the sample cutting parameters are used as input, the standard sample cutting energy is used as supervision, and the BP neural network is supervised and trained using N training sets. The training can be performed using the existing gradient descent algorithm and the loss function to obtain N converged cutting energy prediction units that meet the preset convergence constraints, wherein the preset convergence constraints are the expected output accuracy index, which can be set according to actual needs. Then, a cutting energy prediction model is constructed based on the N converged cutting energy prediction units, wherein the output of the cutting energy prediction model is the mean of the output results of the N converged cutting energy prediction units. By constructing a cutting specific energy prediction model based on N convergent cutting specific energy prediction units, the prediction error of a single model can be reduced and the accuracy and reliability of cutting specific energy prediction can be improved.

[0038] Further, a comprehensive cutting evaluation function is constructed. Step 4 of this application includes:

[0039] The expression of the comprehensive cutting evaluation function is: ;in, is the evaluation fitness of the i-th cutting parameter, is the cutting quality weight, is the energy consumption weight, is the equipment loss weight, is the expected surface roughness, is the simulated surface roughness after the i-th cutting parameter simulation, is the predicted cutting specific energy of the i-th cutting parameter, is the simulated tool wear coefficient after the simulated machining with the i-th cutting parameter.

[0040] Specifically, in the comprehensive cutting evaluation function, is the evaluation fitness of the i-th cutting parameter. The i-th cutting parameter represents any cutting parameter. The greater the fitness, the better the comprehensive evaluation effect of the cutting parameter. is the cutting quality weight, is the energy consumption weight, is the equipment loss weight, where the sum of the cutting quality weight, energy consumption weight and equipment loss weight is 1. It is set according to the relative importance of each evaluation index in the comprehensive evaluation. The higher the relative importance, the greater the weight corresponding to the index. is the expected surface roughness, is the simulated surface roughness after the i-th cutting parameter simulation, is the predicted cutting specific energy of the i-th cutting parameter, is the simulated tool wear coefficient after the i-th cutting parameter simulation, where the larger the tool wear coefficient, the higher the tool wear degree. By constructing a comprehensive cutting evaluation function, the technical goal of multi-objective optimization can be achieved in the optimization of cutting parameters, thereby improving energy utilization efficiency and reducing tool costs while ensuring processing quality.

[0041] Further, based on the comprehensive cutting evaluation function, the cutting specific energy prediction model and the cutting process twin model, the cutting parameters are optimized using a black hole mutation algorithm. Step five of this application includes:

[0042] Obtain parameter constraint thresholds of cutting parameters, wherein the cutting parameters include cutting speed, feed rate and back cutting amount; randomly generate multiple initial cutting parameters based on the parameter constraint thresholds, wherein the initial cutting parameters satisfy a predetermined uniformity constraint and a predetermined quantity constraint; simulate cutting according to the multiple initial cutting parameters through the cutting processing twin model to obtain multiple cutting simulation results, wherein the cutting simulation results include simulated surface roughness and simulated tool wear coefficient; predict the multiple initial cutting parameters through the cutting specific energy prediction model, and output multiple predicted cutting specific energies; based on the multiple cutting simulation results and the multiple predicted cutting specific energies, evaluate the multiple initial cutting parameters using the comprehensive cutting evaluation function to obtain multiple fitnesses; according to the multiple fitnesses, optimize the multiple initial cutting parameters using the black hole mutation algorithm to obtain optimized cutting parameters.

[0043] Specifically, the cutting parameters include cutting speed, feed rate and back cutting depth, and the parameter constraint threshold of the cutting parameters is obtained. The parameter constraint threshold refers to the adjustment range of the cutting parameters, including the cutting speed constraint threshold, the feed rate constraint threshold and the back cutting depth constraint threshold; then a parameter is randomly selected from the cutting speed constraint threshold, the feed rate constraint threshold and the back cutting depth constraint threshold to combine to obtain the first initial cutting parameter, and multiple initial cutting parameters are obtained using the same method, wherein the initial cutting parameters satisfy a predetermined uniform constraint and a predetermined quantity constraint, and the predetermined uniform constraint means that the similarity between the initial cutting parameters is less than a predetermined threshold, thereby ensuring that the initial cutting parameters have high randomness and balance; the predetermined quantity constraint refers to the expected number of initial cutting parameters, which can be set according to demand.

[0044] Then, the cutting is simulated according to multiple initial cutting parameters through the cutting processing twin model to obtain multiple cutting simulation results, which include simulated surface roughness and simulated tool wear coefficient; wherein, if there is a situation where the simulated surface roughness in the initial cutting parameters does not meet the expected surface roughness, the initial cutting parameters are discarded, and the same number of initial cutting parameters are randomly generated to supplement them to meet the predetermined quantity constraints; on the other hand, the multiple initial cutting parameters are predicted by the cutting specific energy prediction model, and multiple predicted cutting specific energies are output; then, the multiple cutting simulation results and the multiple predicted cutting specific energies are evaluated according to the comprehensive cutting evaluation function to obtain multiple fitness of the multiple initial cutting parameters; finally, according to the multiple fitness, the black hole mutation algorithm is used to optimize the multiple initial cutting parameters to obtain the optimized cutting parameters.

[0045] Further, according to multiple fitnesses, a black hole mutation algorithm is used to optimize multiple initial cutting parameters to obtain optimized cutting parameters. The present application also includes the following steps:

[0046] The multiple initial cutting parameters are regarded as multiple initial solutions. Based on multiple fitnesses, the multiple initial solutions are arranged from large to small according to the fitnesses to generate an initial solution sequence. The first Q initial solutions in the initial solution sequence are regarded as black holes, and the last M initial solutions are regarded as planets, where the sum of Q and M is the number of initial solutions, and M is much larger than Q. The absorption radius of the Q black holes is calculated respectively, where the absorption radius is the ratio of the fitness of the black hole to the sum of the fitness of the M planets, and the black hole will absorb the planet within the absorption radius. With the Q black holes as the optimization direction, the first preset adjustment step size is used to optimize the optimization direction. A global optimization is performed on the M planets, and after one movement is completed, the number of stars is supplemented based on the parameter constraint threshold, wherein the supplemented number is the number of planets absorbed by the black hole, and the supplemented planets are not within the absorption radius of the black hole; within the Q black holes, a local optimization is performed on the M planets based on a second preset adjustment step size, and the Q black holes are updated based on the local optimization results; the global and local collaborative optimization is iterated until the predetermined optimization number constraint is met, Q current black holes are output, and the black hole with the largest fitness among the Q current black holes is selected and set as the optimized cutting parameter.

[0047] Specifically, first, multiple initial cutting parameters are regarded as multiple initial solutions, and then the multiple initial solutions are arranged from large to small according to the fitness to generate an initial solution sequence; then the first Q initial solutions in the initial solution sequence are regarded as black holes, and the last M initial solutions are regarded as planets, where the sum of Q and M is the number of initial solutions, and M is much larger than Q; then the absorption radii of the Q black holes are calculated respectively, where the absorption radius of the black hole is the ratio of the fitness of the black hole to the sum of the fitness of the M planets, and the black hole will absorb the planets within the absorption radius.

[0048] Then, taking the Q black holes as the optimization direction, the M planets are globally optimized according to the first preset adjustment step, that is, the planets are moved toward the position of the black hole according to the first preset adjustment step, wherein after one movement is completed, the black hole will absorb the planets within the absorption radius, so it is necessary to supplement the number of stars based on the parameter constraint threshold, wherein the supplementary number is the number of planets absorbed by the black hole, and the supplemented planets are not within the absorption radius of the black hole; further, within the Q black holes, the M planets are locally optimized based on the second preset adjustment step, and the Q black holes are updated according to the local optimization results. The global and local alternating collaborative optimization is continuously iterated until the predetermined optimization number constraint is met, and the predetermined optimization number constraint can be set according to the actual situation, for example: the predetermined optimization number constraint is set to 100 times, the Q current black holes are output, and the black hole with the largest fitness among the Q current black holes is selected as the optimized cutting parameter.

[0049] By using the black hole mutation algorithm to optimize the cutting parameters, since the algorithm takes into account both global optimization and local optimization and has a strong global convergence ability, it can avoid falling into the local optimum and improve the precision, accuracy and comprehensiveness of cutting parameter optimization.

[0050] Further, the first preset adjustment step size and the second preset adjustment step size are set, and the present application further includes the following steps:

[0051] Acquire multiple sample cutting parameters, evaluate the multiple sample cutting parameters based on the comprehensive cutting evaluation function, and determine multiple sample fitnesses; based on a single analysis principle, perform sensitivity analysis on a single cutting indicator according to the multiple sample cutting parameters and the multiple sample fitnesses, and determine multiple sensitivity coefficients, wherein the sensitivity coefficient corresponds to the single cutting indicator one-to-one; optimize the initial preset adjustment step length based on the multiple sensitivity coefficients to obtain a first preset adjustment step length, wherein the sensitivity coefficient is inversely correlated with the adjustment step length; configure a second preset adjustment step length according to the first preset adjustment step length mapping, wherein the second preset adjustment step length is smaller than the first preset adjustment step length.

[0052] Specifically, multiple sample cutting parameters are obtained based on big data retrieval, and then the multiple sample cutting parameters are evaluated based on the comprehensive cutting evaluation function to determine multiple sample fitness. Then, based on the principle of single variable analysis, according to multiple sample cutting parameters and multiple sample fitness, sensitivity analysis is performed on cutting speed, feed rate, back cutting amount and sample fitness respectively. The principle of single variable analysis is a statistical method used to study the influence of an independent variable on a dependent variable. In this analysis, researchers usually only change the value of one independent variable while keeping other variables unchanged to observe the changes in the dependent variable. This method can help researchers determine whether there is a significant correlation or causal relationship between the independent variable and the dependent variable; multiple sensitivity coefficients are determined based on the results of sensitivity analysis. The sensitivity coefficient is a quantitative indicator to measure the sensitivity of a certain cutting parameter to fitness. The larger its value, the more significant the influence of the cutting parameter on fitness.

[0053] The initial preset adjustment step includes an initial cutting speed adjustment step, an initial feed amount adjustment step and an initial back cutting amount adjustment step; then the initial cutting speed adjustment step, the initial feed amount adjustment step and the initial back cutting amount adjustment step are optimized according to multiple sensitivity coefficients, wherein the sensitivity coefficient is inversely correlated with the adjustment step, that is, the larger the sensitivity coefficient, the smaller the corresponding adjustment step, which is used to improve the optimization accuracy of important indicators in the optimization process and obtain a first preset adjustment step; on the other hand, a second preset adjustment step is configured according to the first preset adjustment step mapping, wherein the second preset adjustment step is smaller than the first preset adjustment step, for example: the correlation coefficient between the second preset adjustment step and the first preset adjustment step can be set to a constant between 0.4 and 0.8, that is, the second preset adjustment step is a constant times the first preset adjustment step.

[0054] Further, based on the local optimization result, the Q black holes are updated, and the present application further includes the following steps:

[0055] Identify Q black holes. If there is a planet with a fitness greater than the black hole fitness in the same black hole, the black hole body is updated and replaced with the planet. If the number of planets in a single black hole meets the preset threshold, multiple planets are evaluated based on fitness and residence time, and multiple planets with smaller evaluation coefficients are eliminated, where the fitness is proportional to the evaluation coefficient and the residence time is inversely proportional to the evaluation coefficient.

[0056] Specifically, when updating Q black holes based on the local optimization results, first, Q black holes are identified, and the fitness of the planets in the black holes is calculated based on the comprehensive cutting evaluation function. If in the same black hole, there is a planet whose fitness is greater than the fitness of the black hole body, the black hole body is updated and replaced by the planet; if the number of planets in a single black hole meets the preset number threshold, multiple planets are evaluated based on fitness and residence time, wherein the fitness is proportional to the evaluation coefficient, and the residence time is inversely proportional to the evaluation coefficient, that is, the greater the fitness, the greater the evaluation coefficient, and the shorter the residence time, the greater the evaluation coefficient, and the residence time is the time the planet exists in the black hole, and the evaluation coefficients of multiple planets are obtained, and then multiple planets with smaller evaluation coefficients are eliminated, wherein the number of eliminated planets is the number of planets exceeding the preset number threshold.

[0057] In summary, the energy consumption optimization method of a CNC machine tool provided in this application has the following technical effects:

[0058] 1. By taking material attribute information and machine tool attribute information as constraints, the correlation analysis between cutting parameters and cutting specific energy is performed, and a cutting specific energy prediction model is constructed based on the correlation analysis results; on the other hand, based on digital twin technology, cutting simulation modeling is performed according to material attribute information and machine tool attribute information to generate a cutting processing twin model; then, taking the expected surface roughness as the quality constraint, minimizing cutting specific energy and tool wear as the optimization purpose, a comprehensive cutting evaluation function is constructed to provide a basis for achieving the technical goal of multi-objective optimization of equipment energy consumption, cutting quality and tool wear; further based on the comprehensive cutting evaluation function, cutting specific energy prediction model and cutting processing twin model, the black hole mutation algorithm is used to optimize the cutting parameters to obtain the optimized cutting parameters; finally, the target product is cut according to the optimized cutting parameters. It can improve the rationality, accuracy and comprehensiveness of cutting parameter settings, achieve the technical goal of multi-objective optimization of equipment energy consumption, cutting quality and tool wear, and thus improve the practicality and rationality of the energy consumption optimization scheme under the premise of ensuring cutting quality.

[0059] 2. By constructing a comprehensive cutting evaluation function, the technical goal of multi-objective optimization can be achieved in the optimization of cutting parameters, thereby improving energy utilization efficiency and reducing tool costs while ensuring processing quality.

[0060] 3. By using the black hole mutation algorithm to optimize the cutting parameters, since the algorithm takes into account both global optimization and local optimization and has a strong global convergence ability, it can avoid falling into the local optimum and improve the precision, accuracy and comprehensiveness of cutting parameter optimization.

[0061] Embodiment 2

[0062] Based on the energy consumption optimization method of a CNC machine tool in the aforementioned embodiment, the present application also provides an energy consumption optimization system for a CNC machine tool, please refer to the attached Figure 3 , the system comprising:

[0063] The information acquisition module 11 is used to acquire material property information and expected processing indicators of the target product, wherein the expected processing indicators include expected surface roughness.

[0064] The cutting specific energy prediction model building module 12 is used to read the machine tool attribute information and cutting parameters of the CNC machine tool, perform correlation analysis between the cutting parameters and the cutting specific energy based on the material attribute information and the machine tool attribute information, and build a cutting specific energy prediction model, wherein the cutting specific energy is the ratio of the total energy consumption of the cutting material to the volume of the removed material.

[0065] The cutting process twin model generation module 13 is used to perform cutting simulation modeling based on the material property information and the machine tool property information to generate a cutting process twin model based on the digital twin technology.

[0066] The comprehensive cutting evaluation function construction module 14 is used to construct a comprehensive cutting evaluation function with the expected surface roughness as the quality constraint and minimizing the cutting specific energy and tool wear as the optimization purpose.

[0067] The cutting parameter optimization module 15 is used to optimize the cutting parameters based on the comprehensive cutting evaluation function, the cutting specific energy prediction model and the cutting process twin model using a black hole mutation algorithm to obtain optimized cutting parameters, and perform cutting process on the target product according to the optimized cutting parameters.

[0068] Furthermore, the cutting specific energy prediction model building module 12 in the system is also used for:

[0069] The material attribute information is used as a material constraint, and the machine tool attribute information is used as an equipment constraint. Information retrieval is performed based on big data to obtain a sample data set, wherein the sample data includes a sample cutting parameter, a sample cutting energy consumption set, and a sample removal volume set; multiple sample cutting specific energies are calculated based on the sample cutting energy consumption set and the sample removal volume set, and the mean value of the sample cutting specific energies is obtained by performing mean calculation, wherein the cutting specific energy is the ratio of the total energy consumption of the cutting material to the volume of the removed material; the deviation values ​​of the multiple sample cutting specific energies and the mean value of the sample cutting specific energies are calculated respectively, and the sample with a deviation value less than a predetermined deviation threshold is selected as a qualified sample cutting specific energy, and the multiple qualified sample cutting specific energies are set as qualified sample cutting specific energies. The mean of the specific energy is set as the standard sample cutting specific energy; multiple standard sample cutting specific energies of multiple sample cutting parameters are obtained in turn, and a sample training set is constructed according to the multiple sample cutting parameters and the multiple standard sample cutting specific energies; the sample training set is divided into N equal parts, and is selected N times with replacement to construct a first training set, and is iteratively selected N times to obtain N training sets; with the sample cutting parameters as input and the standard sample cutting specific energy as supervision, the BP neural network is supervised and trained using the N training sets to obtain N convergent cutting specific energy prediction units to build a cutting specific energy prediction model, wherein the output of the cutting specific energy prediction model is the mean of the output results of the N convergent cutting specific energy prediction units.

[0070] Furthermore, the comprehensive cutting evaluation function construction module 14 in the system is also used for:

[0071] The expression of the comprehensive cutting evaluation function is: ;in, is the evaluation fitness of the i-th cutting parameter, is the cutting quality weight, is the energy consumption weight, is the equipment loss weight, is the expected surface roughness, is the simulated surface roughness after the i-th cutting parameter simulation, is the predicted cutting specific energy of the i-th cutting parameter, is the simulated tool wear coefficient after the simulated machining with the i-th cutting parameter.

[0072] Furthermore, the cutting parameter optimization module 15 in the system is also used for:

[0073] Obtain parameter constraint thresholds of cutting parameters, wherein the cutting parameters include cutting speed, feed rate and back cutting amount; randomly generate multiple initial cutting parameters based on the parameter constraint thresholds, wherein the initial cutting parameters satisfy a predetermined uniformity constraint and a predetermined quantity constraint; simulate cutting according to the multiple initial cutting parameters through the cutting processing twin model to obtain multiple cutting simulation results, wherein the cutting simulation results include simulated surface roughness and simulated tool wear coefficient; predict the multiple initial cutting parameters through the cutting specific energy prediction model, and output multiple predicted cutting specific energies; based on the multiple cutting simulation results and the multiple predicted cutting specific energies, evaluate the multiple initial cutting parameters using the comprehensive cutting evaluation function to obtain multiple fitnesses; according to the multiple fitnesses, optimize the multiple initial cutting parameters using the black hole mutation algorithm to obtain optimized cutting parameters.

[0074] Furthermore, the cutting parameter optimization module 15 in the system is also used for:

[0075] The multiple initial cutting parameters are regarded as multiple initial solutions. Based on multiple fitnesses, the multiple initial solutions are arranged from large to small according to the fitnesses to generate an initial solution sequence. The first Q initial solutions in the initial solution sequence are regarded as black holes, and the last M initial solutions are regarded as planets, where the sum of Q and M is the number of initial solutions, and M is much larger than Q. The absorption radius of the Q black holes is calculated respectively, where the absorption radius is the ratio of the fitness of the black hole to the sum of the fitness of the M planets, and the black hole will absorb the planet within the absorption radius. With the Q black holes as the optimization direction, the first preset adjustment step size is used to optimize the optimization direction. A global optimization is performed on the M planets, and after one movement is completed, the number of stars is supplemented based on the parameter constraint threshold, wherein the supplemented number is the number of planets absorbed by the black hole, and the supplemented planets are not within the absorption radius of the black hole; within the Q black holes, a local optimization is performed on the M planets based on a second preset adjustment step size, and the Q black holes are updated based on the local optimization results; the global and local collaborative optimization is iterated until the predetermined optimization number constraint is met, Q current black holes are output, and the black hole with the largest fitness among the Q current black holes is selected and set as the optimized cutting parameter.

[0076] Furthermore, the cutting parameter optimization module 15 in the system is also used for:

[0077] Acquire multiple sample cutting parameters, evaluate the multiple sample cutting parameters based on the comprehensive cutting evaluation function, and determine multiple sample fitnesses; based on a single analysis principle, perform sensitivity analysis on a single cutting indicator according to the multiple sample cutting parameters and the multiple sample fitnesses, and determine multiple sensitivity coefficients, wherein the sensitivity coefficient corresponds to the single cutting indicator one-to-one; optimize the initial preset adjustment step length based on the multiple sensitivity coefficients to obtain a first preset adjustment step length, wherein the sensitivity coefficient is inversely correlated with the adjustment step length; configure a second preset adjustment step length according to the first preset adjustment step length mapping, wherein the second preset adjustment step length is smaller than the first preset adjustment step length.

[0078] Furthermore, the cutting parameter optimization module 15 in the system is also used for:

[0079] Identify Q black holes. If there is a planet with a fitness greater than the black hole fitness in the same black hole, the black hole body is updated and replaced with the planet. If the number of planets in a single black hole meets the preset threshold, multiple planets are evaluated based on fitness and residence time, and multiple planets with smaller evaluation coefficients are eliminated, where the fitness is proportional to the evaluation coefficient and the residence time is inversely proportional to the evaluation coefficient.

[0080] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The energy consumption optimization method and specific examples of a CNC machine tool in the aforementioned embodiment 1 are also applicable to an energy consumption optimization system of a CNC machine tool in this embodiment. Through the aforementioned detailed description of the energy consumption optimization method of a CNC machine tool, those skilled in the art can clearly know the energy consumption optimization system of a CNC machine tool in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0081] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0082] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A method for optimizing energy consumption of a CNC machine tool, characterized in that: The method comprises: Obtaining material property information and expected processing indicators of a target product, wherein the expected processing indicators include expected surface roughness; Reading the machine tool attribute information and cutting parameters of the CNC machine tool, performing correlation analysis between the cutting parameters and the cutting specific energy based on the material attribute information and the machine tool attribute information, and constructing a cutting specific energy prediction model, wherein the cutting specific energy is the ratio of the total energy consumption of the cutting material to the volume of the removed material; Based on the digital twin technology, cutting simulation modeling is performed according to the material property information and the machine tool property information to generate a cutting processing twin model; Taking the expected surface roughness as the quality constraint and minimizing the cutting specific energy and tool wear as the optimization purpose, a comprehensive cutting evaluation function is constructed; Based on the comprehensive cutting evaluation function, the cutting specific energy prediction model and the cutting process twin model, the cutting parameters are optimized by using a black hole mutation algorithm to obtain optimized cutting parameters, and the target product is cut according to the optimized cutting parameters; Among them, the cutting specific energy prediction model is constructed, including: Taking the material attribute information as material constraint and the machine tool attribute information as equipment constraint, information retrieval is performed based on big data to obtain a sample data set, wherein the sample data includes a sample cutting parameter, a sample cutting energy consumption set and a sample removal volume set; Based on the sample cutting energy consumption set and the sample removal volume set, a plurality of sample cutting specific energies are calculated, and an average value of the sample cutting specific energies is obtained by performing an average calculation, wherein the cutting specific energy is the ratio of the total energy consumption of the cutting material to the volume of the removed material; Calculate the deviations of multiple sample cutting specific energies from the average of the sample cutting specific energies respectively, select the sample cutting specific energies with the deviations less than the predetermined deviation threshold as qualified sample cutting specific energies, and set the average of the multiple qualified sample cutting specific energies as the standard sample cutting specific energy; Sequentially obtain a plurality of standard sample cutting specific energies of a plurality of sample cutting parameters, and construct a sample training set according to the plurality of sample cutting parameters and the plurality of standard sample cutting specific energies; Divide the sample training set into N equal parts, select N times with replacement, construct the first training set, and iterate N times to obtain N training sets; Taking the sample cutting parameters as input and the standard sample cutting specific energy as supervision, the BP neural network is supervised and trained using N training sets to obtain N convergent cutting specific energy prediction units to build a cutting specific energy prediction model, wherein the output of the cutting specific energy prediction model is the average of the output results of the N convergent cutting specific energy prediction units; Among them, the comprehensive cutting evaluation function is constructed, including: The expression of the comprehensive cutting evaluation function is: ； in, is the evaluation fitness of the i-th cutting parameter, is the cutting quality weight, is the energy consumption weight, is the equipment loss weight, is the expected surface roughness, is the simulated surface roughness after the i-th cutting parameter simulation, is the predicted cutting specific energy of the i-th cutting parameter, is the simulated tool wear coefficient after the simulated machining with the i-th cutting parameter.

2. The method for optimizing energy consumption of a CNC machine tool according to claim 1, characterized in that: Based on the comprehensive cutting evaluation function, the cutting specific energy prediction model and the cutting process twin model, the cutting parameters are optimized using a black hole mutation algorithm, including: Obtaining parameter constraint thresholds of cutting parameters, wherein the cutting parameters include cutting speed, feed rate, and back cutting amount; Randomly generate a plurality of initial cutting parameters based on a parameter constraint threshold, wherein the initial cutting parameters satisfy a predetermined uniformity constraint and a predetermined quantity constraint; Simulating cutting according to a plurality of initial cutting parameters using the cutting processing twin model to obtain a plurality of cutting simulation results, wherein the cutting simulation results include a simulated surface roughness and a simulated tool wear coefficient; Predicting a plurality of initial cutting parameters by using the cutting specific energy prediction model, and outputting a plurality of predicted cutting specific energies; Based on multiple cutting simulation results and multiple predicted cutting specific energies, multiple initial cutting parameters are evaluated using the comprehensive cutting evaluation function to obtain multiple fitness levels; According to multiple fitnesses, the black hole mutation algorithm is used to optimize multiple initial cutting parameters to obtain the optimized cutting parameters.

3. The method for optimizing energy consumption of a CNC machine tool according to claim 2, characterized in that: According to multiple fitness, the black hole mutation algorithm is used to optimize multiple initial cutting parameters to obtain the optimized cutting parameters, including: The multiple initial cutting parameters are regarded as multiple initial solutions, and based on multiple fitnesses, the multiple initial solutions are arranged from large to small according to the fitnesses to generate an initial solution sequence; The first Q initial solutions in the initial solution sequence are regarded as black holes, and the last M initial solutions are regarded as planets, where the sum of Q and M is the number of initial solutions, and M is much larger than Q; Calculate the absorption radius of Q black holes respectively, where the absorption radius is the ratio of the fitness of the black hole to the sum of the fitness of the M planets, and the black hole will absorb the planets within the absorption radius; Taking Q black holes as the optimization direction, perform global optimization on M planets according to the first preset adjustment step size, and after one move is completed, supplement the number of stars based on the parameter constraint threshold, where the supplementary number is the number of planets absorbed by the black hole, and the supplemented planets are not within the absorption radius of the black hole; In the Q black holes, locally optimizing the M planets based on a second preset adjustment step size, and updating the Q black holes based on the local optimization results; Iterate the global and local collaborative optimization until the predetermined optimization number constraint is met, output Q current black holes, and select the black hole with the largest fitness among the Q current black holes to set as the optimized cutting parameter.

4. The method for optimizing energy consumption of a CNC machine tool according to claim 3, characterized in that: Setting a first preset adjustment step and a second preset adjustment step includes Acquire multiple sample cutting parameters, evaluate the multiple sample cutting parameters based on the comprehensive cutting evaluation function, and determine multiple sample fitnesses; Based on the single analysis principle, according to multiple sample cutting parameters and multiple sample fitness, sensitivity analysis is performed on single cutting indicators respectively to determine multiple sensitivity coefficients, wherein the sensitivity coefficients correspond to single cutting indicators one by one; Optimizing the initial preset adjustment step length based on multiple sensitivity coefficients to obtain a first preset adjustment step length, wherein the sensitivity coefficient is inversely correlated with the adjustment step length; A second preset adjustment step is configured according to the first preset adjustment step mapping, wherein the second preset adjustment step is smaller than the first preset adjustment step.

5. The method for optimizing energy consumption of a CNC machine tool according to claim 3, characterized in that: Based on the local optimization results, Q black holes are updated, including: Identify Q black holes. If there is a planet with a fitness greater than the black hole fitness in the same black hole, the black hole body is updated and replaced with the planet. If the number of planets in a single black hole meets the preset threshold, multiple planets are evaluated based on fitness and residence time, and multiple planets with smaller evaluation coefficients are eliminated, where the fitness is proportional to the evaluation coefficient and the residence time is inversely proportional to the evaluation coefficient.

6. An energy consumption optimization system for a CNC machine tool, characterized in that: The system is used to implement the method for optimizing energy consumption of a numerically controlled machine tool as described in any one of claims 1 to 5, comprising: An information acquisition module, used to acquire material property information and expected processing indicators of a target product, wherein the expected processing indicators include expected surface roughness; A cutting specific energy prediction model building module is used to read the machine tool attribute information and cutting parameters of the CNC machine tool, perform correlation analysis between the cutting parameters and the cutting specific energy based on the material attribute information and the machine tool attribute information, and build a cutting specific energy prediction model, wherein the cutting specific energy is the ratio of the total energy consumption of the cutting material to the volume of the removed material; A cutting process twin model generation module, used for performing cutting simulation modeling based on the material property information and the machine tool property information to generate a cutting process twin model based on the digital twin technology; A comprehensive cutting evaluation function construction module is used to construct a comprehensive cutting evaluation function with the expected surface roughness as a quality constraint and minimizing cutting specific energy and tool wear as an optimization purpose; The cutting parameter optimization module is used to optimize the cutting parameters based on the comprehensive cutting evaluation function, the cutting specific energy prediction model and the cutting process twin model using a black hole mutation algorithm to obtain optimized cutting parameters, and perform cutting process on the target product according to the optimized cutting parameters.

Images