Precision Machining Technology Optimization Method for Machine Tool Spindle System

Abstract

This invention discloses a method for optimizing the precision machining process of a machine tool spindle system, relating to the field of machining technology. The method includes: establishing digital communication with the machine tool spindle system and constructing a machining dataset; performing feature analysis on the machining dataset and constructing a penalty factor library mapped to machining parameters; establishing the lifecycle of the machining tool and configuring a tool life state function; acquiring machining tasks, constructing a fitness evaluation function based on the machining tasks, and performing control parameter optimization; establishing an optimization set based on the control parameter optimization results, reconstructing the optimization set based on machining test results, and completing the machining process optimization based on the reconstructed optimization set results. This invention solves the technical problems of low intelligence, limited machining efficiency, and unstable machining quality due to a lack of dynamic adaptability in existing technologies, achieving the technical effect of realizing intelligent control and management of machine tools and improving production efficiency and quality.

Description

Technical Field

[0001] The invention relates to the technical field of mechanical processing, and in particular to a method for optimizing the precision processing technology of a machine tool spindle system. Background Art

[0002] As modern industry's requirements for machine tool processing quality and efficiency continue to increase, intelligence and automation are the development trend of the manufacturing industry. The processing technology of machine tool spindle systems also needs to adapt to it. Improving production efficiency and product quality is also one of the important goals pursued by enterprises.

[0003] The existing technology has technical problems such as low intelligence, limited processing efficiency, and lack of dynamic adaptability resulting in unstable processing quality. Summary of the invention

[0004] The present application provides a method for optimizing the precision machining process of a machine tool spindle system, which is used to solve the technical problems in the prior art such as low intelligence, limited machining efficiency, and lack of dynamic adaptability resulting in unstable machining quality.

[0005] In view of the above problems, the present application provides a method for optimizing the precision machining process of a machine tool spindle system, the method comprising:

[0006] Establish digital communication with the machine tool spindle system, and extract the processing information of the machine tool based on the digital communication to construct a processing data set; perform feature analysis on the processing data set, and construct a penalty factor library mapped with the processing parameters according to the feature analysis results; establish the life cycle of the processing tool, and configure the tool life state function based on the life cycle; obtain a processing task, the processing task includes a material data set of the processing material, cutting removal data, and surface quality requirement data, based on the cutting removal data and surface quality requirement data in the processing task as basic constraints, construct a fitness evaluation function based on the material data set, the tool life state function, and the penalty factor library, and perform control parameter optimization according to the fitness evaluation function and the basic constraints; establish an optimization set according to the control parameter optimization result, and perform processing test with the optimization set, and reconstruct the optimization set according to the processing test result, and complete the processing process optimization according to the optimization set reconstruction result.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] Establish digital communication with the machine tool spindle system and construct a processing data set; perform feature analysis on the processing data set and construct a penalty factor library mapped with processing parameters; establish the life cycle of the processing tool and configure the tool life status function; obtain the processing task, construct a fitness evaluation function based on the processing task, and perform control parameter optimization; establish an optimization set based on the control parameter optimization results, and reconstruct the optimization set based on the processing test results, and complete the processing technology optimization based on the optimization set reconstruction results, thereby achieving the technical effect of realizing intelligent control and management of machine tools and improving production efficiency and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic diagram of a process flow of a precision machining process optimization method for a machine tool spindle system provided in an embodiment of the present application;

[0011] Figure 2 A schematic diagram of a flow chart for performing control parameter optimization in a precision machining process optimization method for a machine tool spindle system provided in an embodiment of the present application;

[0012] Figure 3 A schematic diagram of the process of completing the optimization of control parameters through multiple rounds of search and update iterations in the precision machining process optimization method for a machine tool spindle system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0013] The present application provides a method for optimizing the precision machining process of a machine tool spindle system, which is used to solve the technical problems in the prior art such as low intelligence, limited machining efficiency, and unstable machining quality caused by lack of dynamic adaptability.

[0014] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0015] Embodiment 1

[0016] like Figure 1 As shown, the present application provides a method for optimizing the precision machining process of a machine tool spindle system, the method comprising:

[0017] Step S100: Establish digital communication with the machine tool spindle system, extract processing information of the machine tool based on the digital communication, and construct a processing data set.

[0018] Specifically, establishing digital communication with the machine tool spindle system is the basis for realizing the extraction of processing information and building a processing data set. Through digital communication, data transmission and interaction between the machine tool spindle system and other devices or systems can be realized. Establishing digital communication includes determining the communication protocol, selecting a communication protocol suitable for the machine tool spindle system, such as TCP / IP, etc.; establishing a physical connection, connecting the machine tool spindle system with other devices or systems by wired or wireless means; configuring communication parameters, setting communication parameters such as IP address, port number, etc. according to the requirements of the communication protocol; realizing data transmission, realizing data transmission between the machine tool spindle system and other devices or systems through programming or using corresponding communication software. After completing the establishment of digital communication, the extraction of processing information can be carried out, including the following steps: determining the information to be extracted, according to the needs of processing technology optimization, determining the processing information to be extracted from the machine tool spindle system, such as spindle speed, feed speed, cutting force, etc.; writing a data extraction program. Use the corresponding programming language and tools to write a data extraction program to realize the real-time collection of machine tool processing information. Data collection and storage: Run the data extraction program to collect the processing information of the machine tool in real time and store it in a database or file for subsequent analysis and processing. Finally, the processing data set is constructed by sorting and organizing the extracted processing information. This data set will contain various processing information of the machine tool under different processing conditions, provide data support for subsequent processing technology optimization, realize intelligent control and management of machine tools, improve production efficiency and quality, and reduce production costs.

[0019] Step S200: performing feature analysis on the processing data set, and constructing a penalty factor library mapped with processing parameters according to the feature analysis results.

[0020] Specifically, feature analysis of the processing data set is to gain an in-depth understanding of the characteristics and laws of the data in order to better construct a penalty factor library mapped with the processing parameters. Feature analysis can include the following aspects: data cleaning and preprocessing, cleaning and preprocessing the processing data set, removing noise and abnormal data, ensuring the accuracy and reliability of the data, including data filtering, missing value processing, outlier detection and other operations; feature extraction, extracting features that can reflect the processing process from the processing data set, these features include but are not limited to spindle speed, feed speed, cutting force, cutting temperature, processing time, etc. The method of feature extraction can be selected according to the specific situation, such as statistical analysis, signal processing, machine learning, etc.; feature selection, selecting the extracted features, selecting the features that have a greater impact on the processing process, feature selection can be achieved by calculating the importance score of the features, correlation analysis, cluster analysis and other methods, selecting important features can reduce the data dimension and improve the accuracy and efficiency of the model; feature analysis, analyzing the selected features to understand the relationship and law between the features. This can be achieved by drawing feature distribution diagrams, calculating the correlation between features, performing principal component analysis and other methods. Feature analysis can help us better understand the processing process and find potential problems and optimization space. Constructing a penalty factor library mapped with processing parameters based on the feature analysis results includes the following steps: determining the type and number of penalty factors, according to the characteristics and requirements of the processing process, determining the type and number of penalty factors, the type of penalty factor can be selected according to the specific situation, such as linear penalty factor, nonlinear penalty factor, etc., and the number of penalty factors can be determined according to the number and importance of features; constructing a penalty factor library, according to the feature analysis results, constructing a penalty factor library mapped with processing parameters, the penalty factor library is represented as a matrix or table, where the rows represent processing parameters, the columns represent features, and the elements in the matrix represent the corresponding penalty factors. Optimizing the penalty factor library, optimizing the constructed penalty factor library, adjusting the weights and thresholds of the penalty factors to improve the accuracy and efficiency of the model. Optimizing the penalty factor library can be achieved through experimental design, parameter adjustment, model training and other methods. Based on the penalty factor library, the processing parameters can be optimized to find the optimal combination of processing parameters to improve processing quality, accuracy and efficiency.

[0021] Step S300: establishing a life cycle of a machining tool, and configuring a tool life state function based on the life cycle;

[0022] Specifically, the life cycle of a tool can be divided into a running-in period, a stable period, and a wear period. When establishing the life cycle of a machining tool, it is necessary to determine the time nodes of each stage and the performance characteristics of the tool. The specific steps for configuring a tool life status function based on the life cycle are as follows: Determine the formula of the tool life status function. According to the life cycle characteristics of the tool, construct a formula for the tool life status function, which should be able to reflect the performance changes of the tool at different stages. Define the function parameters. In the formula, some parameters need to be defined to describe the performance and life cycle of the tool. These parameters include the initial performance of the tool, the end time node of the running-in period, the end time node of the stable period, the expected total life of the tool, the rate index of performance increase during the running-in period, the coefficient of performance attenuation during the stable period, etc. Determine the current time node. In practical applications, it is necessary to determine the current time node so as to calculate the current tool performance index according to the tool life status function. Calculate the tool performance index. Substitute the current time node into the tool life status function to calculate the current tool performance index. This index can reflect the performance status of the tool at the current stage. By establishing the life cycle of a machining tool and configuring the tool life status function, we can better understand the law of tool performance changes and provide a basis for optimizing the machining process. For example, the processing parameters can be adjusted according to the performance status of the tool to improve the processing efficiency and quality; or the tool can be replaced in time when the tool performance drops to a certain level to avoid affecting the processing quality and production efficiency.

[0023] Step S400: Obtain a processing task, wherein the processing task includes a material data set of processing materials, cutting removal data, and surface quality requirement data; based on the cutting removal data and surface quality requirement data in the processing task as basic constraints, a fitness evaluation function is constructed based on the material data set, tool life state function, and penalty factor library; and control parameter optimization is performed according to the fitness evaluation function and the basic constraints.

[0024] Specifically, the processing task is obtained. The processing task includes the material data set of the processing material, such as the hardness, strength and other characteristics of the material; the cutting removal data, that is, the amount of material that needs to be removed from the workpiece; the surface quality requirement data, such as surface roughness, accuracy and other requirements. The basic constraints are determined to be the cutting removal data as a constraint, which limits the amount of material that can be removed during the processing process, and the surface quality requirement data as a constraint, which stipulates the quality standard that the workpiece surface should achieve after processing. The fitness evaluation function is constructed. The fitness evaluation function comprehensively considers the material data set, the tool life state function and the penalty factor library; the material data set is used to reflect the influence of the characteristics of the processing material on the processing process. Different materials may require different processing parameters to achieve the best processing effect; the tool life state function describes the wear of the tool during the processing process. The wear of the tool will affect the processing quality and efficiency, so the tool life needs to be considered in the fitness evaluation function; the penalty factor library contains various possible penalty factors for processing errors and defects. These penalty factors are used to penalize the processing results that do not meet the requirements, so as to guide the optimization algorithm to find a better control parameter combination. Execute control parameter optimization, use fitness evaluation function and basic constraints, and find the optimal control parameter combination through optimization algorithm. The control parameters include cutting speed, feed speed, cutting depth, tool angle, etc. The goal of the optimization algorithm is to make the fitness evaluation function reach the optimal value under the premise of satisfying the basic constraints. This means finding a set of control parameters so that the machining process can meet the requirements of cutting removal and surface quality, and maximize machining efficiency and tool life. Through control parameter optimization, a more stable machining parameter combination can be found to improve the stability and reliability of the machining process.

[0025] Step S500: establishing an optimization set according to the control parameter optimization result, performing a processing test with the optimization set, reconstructing the optimization set according to the processing test result, and completing the processing technology optimization according to the optimization set reconstruction result.

[0026] Specifically, an optimization set is established based on the control parameter optimization results, and the obtained control parameter optimization results are carefully sorted and classified. According to specific rules and standards, similar control parameter combinations are summarized into an optimization set. Each optimization set represents a potential optimal processing solution. The processing test is carried out with the optimization set, and a control parameter combination is selected from the optimization set. The combination is applied in the actual processing test, and all data in the processing process are fully recorded, including but not limited to processing time, processing quality, tool wear status, etc. The same processing test is carried out on each control parameter combination in the optimization set in turn. The optimal set is reconstructed according to the processing test results, and the processing test results are deeply analyzed and evaluated. Based on the evaluation results, the advantages and disadvantages of each control parameter combination are accurately judged, and the control parameter combinations with unsatisfactory effects are eliminated. The combinations with outstanding performance are retained, and the retained control parameter combinations are adjusted and optimized to construct a new optimal set. The processing technology optimization is completed according to the optimal set reconstruction results. The reconstructed optimal set is regarded as the final optimization result. The optimal control parameter combination is selected from the new optimal set. These parameters are actually applied to the actual processing and production process. The actual effect of the processing technology is continuously and closely monitored and evaluated, and further optimized and adjusted according to actual needs to achieve continuous optimization of the processing technology, significantly improve processing quality and efficiency, effectively reduce costs, and better meet production needs.

[0027] In one possible implementation, Figure 2 As shown, step S400 further includes:

[0028] Step S410: constructing a tolerant solution space based on the basic constraints, wherein the tolerant solution space is obtained by tolerantly expanding a basic solution space, and the basic solution space is set by the basic constraints.

[0029] Step S420: performing solution aggregation and clustering on the tolerant solution space to establish solution aggregation and clustering clusters.

[0030] Step S430: obtaining the size of each cluster in the solution clustering, and performing region segmentation of the solution clustering according to a preset ratio to establish a region segmentation result, wherein each region segmentation result maps a selection probability.

[0031] Step S440: performing probability selection based on the corresponding selection probability in the region segmentation result, and constructing an initial solution set according to the probability selection result.

[0032] Step S450: performing control parameter optimization using the initial solution set, the tolerant solution space, and the fitness evaluation function.

[0033] Specifically, the basic constraint setting is to determine a feasible solution space range based on the basic constraints such as the cutting removal data and the surface quality requirement data in the machining task. This basic solution space is the set of all possible solutions that meet all basic constraints. Tolerant expansion is to perform tolerant expansion on the basis of the basic solution space. The purpose of tolerant expansion is to increase the diversity of solutions so that a better solution can be found in the subsequent optimization process. The way of tolerant expansion is to add a certain degree of tolerance on the boundary of the basic solution space, or to randomly generate some new solutions in the basic solution space. Construct a tolerant solution space, and the solution space after tolerant expansion is called a tolerant solution space. The tolerant solution space contains the basic solution space and the new solutions obtained by tolerant expansion. The role of the tolerant solution space is to have a wider search range and avoid generating too many invalid solutions. By constructing a tolerant solution space, the optimization process can be prevented from falling into the local optimal solution to a certain extent, and the efficiency and accuracy of the optimization can be improved. At the same time, the size and shape of the tolerant solution space will also affect the optimization results, so it needs to be reasonably set according to the specific problem.

[0034] The tolerant solution space is subjected to solution clustering to establish solution clustering clusters. First, the clustering parameters are determined. The number of clusters is determined according to specific problems and requirements to determine the number of clusters into which the solution is to be clustered. The distance metric is to select a suitable distance metric method to measure the similarity or difference between solutions. Common distance metrics include Euclidean distance, Manhattan distance, etc. The connection method is to determine the connection method used when merging clusters. Common connection methods include the shortest distance method, the longest distance method, the average distance method, etc. Initialize clustering and treat each solution as an independent cluster. Calculate the inter-cluster distance. According to the selected distance metric, calculate the distance between each cluster and other clusters. Merge clusters, select the two clusters with the closest distance to merge, and update the features of the merged cluster, such as the center or representative point of the cluster. Repeat the process of calculating the inter-cluster distance and merging clusters until the specified number of clusters is reached or other termination conditions are met. Establish a solution clustering cluster, and the final cluster is the solution clustering cluster. Through the hierarchical clustering algorithm, the solutions in the tolerant solution space are divided into different clusters, and the solutions in each cluster have a high similarity. This can help to better understand the structure and distribution of the space and provide valuable information for subsequent analysis and processing. In addition, it is also possible to consider using other clustering algorithms or combining multiple methods to obtain more comprehensive and accurate solution clustering results.

[0035] To determine the size of the cluster, it is necessary to determine the size of each cluster in the solution clustering cluster, which can be achieved by counting the number of solutions or other related indicators within the cluster. Set a preset ratio. According to specific needs and problems, set the preset ratio for regional segmentation. This ratio will determine the number or size of clusters in each region. Select a clustering algorithm. In the hierarchical clustering algorithm, you can choose a bottom-up aggregation strategy or a top-down splitting strategy. The aggregation strategy starts with each sample point as a separate cluster and gradually merges similar clusters; the splitting strategy starts with all data being classified into one category and gradually splits dissimilar clusters. Calculate the similarity between clusters. According to the selected clustering algorithm, calculate the similarity between clusters. Commonly used similarity calculation methods include minimum distance, maximum distance, average distance, etc. These methods measure the similarity between clusters based on the distance or other features of sample points within the cluster. Perform clustering. According to the calculated inter-cluster similarity, use the hierarchical clustering algorithm to cluster the solution clustering clusters. During the clustering process, merge or split the clusters according to the preset ratio until the desired regional segmentation result is achieved. Establish the regional segmentation results, save the segmented regions as the results, and map a selection probability to each region for subsequent analysis or processing. Through the above steps, use the hierarchical clustering algorithm to segment the solution clusters and establish the corresponding regional segmentation results, so that we can better understand the spatial distribution and provide a basis for further analysis and decision-making.

[0036] Probabilistic selection is performed based on the corresponding selection probability in the region segmentation result, and an initial solution set is constructed. First, the size of the initial solution set is determined according to the requirements of the problem and the actual situation. For example, 10 solutions need to be selected as the initial solution set. Obtain the region segmentation result and the selection probability. Assume that the cluster clusters of the solution have been obtained through the hierarchical clustering algorithm, and the size of each cluster has been determined. At the same time, the cluster clusters are segmented according to the preset ratio, and a selection probability is assigned to each region. Probabilistic selection is performed: For each region, a random number is generated according to its selection probability. According to the size of the random number, it is determined whether to select the solution in the region. If the region is selected, a solution is randomly selected from the region and added to the initial solution set until the initial solution set reaches a predetermined size. According to the needs of the specific problem, the initial solution set can be further processed or optimized, such as removing duplicate solutions, sorting or filtering solutions, etc. The quality and diversity of the initial solution set have an important impact on the subsequent optimization process. Therefore, according to the characteristics of the problem and the requirements of the algorithm, the region segmentation, the setting of the selection probability, and the processing of the initial solution set can be adjusted and optimized.

[0037] Clearly define the control parameters and objectives that need to be optimized, such as minimizing costs, maximizing efficiency, etc. According to the optimization objectives, design a fitness function to evaluate the quality of each solution. The fitness function should be able to reflect the relationship between the solution and the objective. Use a genetic algorithm to iteratively optimize the initial solution set. The main operations of the genetic algorithm include selection, crossover, and mutation; Selection: According to the fitness function, select some better solutions from the current solution set as parents. Crossover: Perform crossover operations on the parents to generate new child solutions. Mutation: Perform mutation operations on the child solutions to introduce a certain degree of randomness and increase the diversity of the solution set. Add the newly generated child solutions to the solution set and evaluate their quality according to the fitness function. The termination condition is to determine whether to stop the optimization process based on the preset termination condition. The termination condition is to reach the maximum number of iterations, the solution set converges, etc. After the optimization process is completed, select the solution with the best fitness from the solution set as the final control parameter optimization result. In the process of executing the control parameter optimization, it is necessary to pay attention to the reasonable setting of the parameters of the genetic algorithm, including population size, crossover probability, mutation probability, etc., to balance the algorithm's search ability and convergence speed. Analyze and verify the optimization results to ensure their rationality and effectiveness.

[0038] Through these steps, search and optimization can be performed in the solution space, the possibility of finding the optimal solution can be improved, and the effective optimization of control parameters can be achieved.

[0039] In one possible implementation, Figure 3 As shown, step S450 further includes:

[0040] Step S451: Evaluate the fitness of the initial solution set based on the fitness evaluation function, and generate update constraints according to the fitness evaluation results, wherein the update constraints include adaptive mutation constraints and search update constraints.

[0041] Step S452: performing adaptive mutation update on the initial solution set based on the adaptive mutation constraint to generate a first update result.

[0042] Step S453: performing a search update in the tolerant solution space based on the search update constraint to generate a second update result.

[0043] Step S454: completing a round of search and update according to the first update result and the second update result, and completing the optimization of control parameters based on multiple rounds of search and update iterations.

[0044] Specifically, the initial solution set is first evaluated for fitness based on the fitness evaluation function. The fitness evaluation function is used to measure the quality of each solution. The genetic algorithm is used to convert the individual's phenotype into a fitness value, so as to perform genetic operations such as selection, crossover and mutation. According to the fitness value of the individual, the probability or amplitude of mutation is determined. Individuals with higher fitness values ​​have a smaller probability or amplitude of mutation to maintain their excellent characteristics, while individuals with lower fitness values ​​have a larger probability or amplitude of mutation to increase the diversity of search. According to the fitness value, the range or direction of search in the solution space is determined. Individuals with higher fitness values ​​conduct more detailed searches near them, while individuals with lower fitness values ​​search in a wider area. The specific update constraints can be adjusted according to the characteristics of the problem and the design of the algorithm. For example, methods such as adaptive mutation rate, dynamic search range, and fitness-based crossover probability can be used. By generating update constraints based on the fitness evaluation results, the genetic algorithm can be guided to pay more attention to individuals and regions with higher fitness during the search process, while maintaining a certain diversity, so as to improve the algorithm's search efficiency and the possibility of finding the optimal solution.

[0045] According to the adaptive mutation constraint, each individual in the initial solution set is mutated. Mutation operation refers to the random change of certain genes of an individual to generate new individuals. There are many ways of mutation, such as randomly changing the value of the gene, exchanging the position of the gene, etc. The adaptive mutation constraint stipulates the probability and amplitude of mutation. If the fitness of an individual is high, then its mutation probability is small and the amplitude of mutation is also small to maintain its excellent characteristics; if the fitness of an individual is low, then its mutation probability is large and the amplitude of mutation is also large to increase its diversity and exploration ability. By performing adaptive mutation operation on each individual in the initial solution set, a series of new individuals are obtained, which constitute the first update result. Compared with the individuals in the initial solution set, the individuals in the first update result may have changed in some genes, thus having different characteristics and fitness. The first update result will be used for subsequent genetic algorithm operations, such as selection and crossover, to further optimize the solution set and approach the optimal solution.

[0046] According to the search update constraints, a search is performed in the tolerant solution space to find a better solution. The search update constraints may include restrictions on the scope, step size, direction, etc. of the solution. For example, the constraints may stipulate that the search can only be performed within a certain area, or that the movement can only be performed in a specific direction. When searching in the tolerant solution space, different search strategies can be used, such as random search, gradient descent, simulated annealing, etc. These search strategies can be selected according to the characteristics and requirements of the problem. Through the search update in the tolerant solution space, a series of new solutions are obtained, which constitute the second update result. The solutions in the second update result may be closer to the optimal solution than the solutions in the initial solution set.

[0047] The first update result is generated through adaptive mutation operation, which represents a random exploration and change of the existing solution, introducing some new possibilities. The second update result is obtained by targeted search in the tolerant solution space under the search update constraint, which focuses more on finding a better solution in a specific direction or range. These two update results are combined to form the comprehensive update result of this round. Then, enter the next round of search update. In the new round, fitness evaluation, adaptive mutation and search update operations are continued based on the results of the previous round. With the continuous progress of rounds of search updates, the solution set gradually evolves in a better direction. Through multiple rounds of iterations, the quality of the solution is continuously optimized, and finally the optimization of the control parameters is achieved.

[0048] In one possible implementation, step S454 further includes:

[0049] Step S4541: Perform fitness adaptation elimination on the first update result and the second update result.

[0050] Step S4542: Update the initial solution set according to the fitness adaptation elimination results to complete a round of search update.

[0051] Specifically, using a genetic algorithm, the fitness function is used to evaluate the quality of individuals in the population. Through the fitness function, the individuals in the first update result and the second update result can be evaluated and compared, so as to perform fitness adaptation elimination. According to the requirements and objectives of the problem, a suitable fitness function is determined. The fitness function should be able to accurately reflect the quality of the individual. For example, for a maximization problem, the fitness function should be proportional to the objective function; for a minimization problem, the fitness function should be inversely proportional to the objective function. Using the determined fitness function, the fitness value of each individual in the first update result and the second update result is calculated respectively. The individuals in the first update result and the second update result are sorted according to the fitness value. Individuals with higher fitness are selected and retained, and individuals with lower fitness are eliminated. Different elimination strategies are adopted according to the specific situation. A common strategy is to select a certain proportion of individuals with higher fitness to be retained, or to set a fitness threshold, and only individuals with fitness exceeding the threshold can be retained. Update the initial solution set according to the eliminated individuals. The retained individuals are used as the new initial solution set for the next round of search updates. Through fitness adaptation elimination, better individuals can be gradually screened out during the search process, improving the search efficiency and convergence speed of the algorithm.

[0052] First, based on the fitness adaptation elimination results, if an individual is retained in the elimination process, it becomes part of the updated initial solution set. Then, these retained individuals replace the relatively low fitness parts in the initial solution set. For example, if the fitness of some individuals in the initial solution set is significantly lower than that of the individuals retained in the first and second update results, then these better individuals are used to replace them. In the update process, how to replace is determined according to specific rules and strategies, such as complete replacement or replacement in a certain proportion. After completing this series of operations, a round of search update is completed. The initial solution set at this time is different from the initial solution set of the previous round, and contains individuals with more potential after fitness screening and elimination. This is repeated continuously, and the initial solution set is optimized and improved in each round, so that the solution set gradually converges to the direction of the optimal solution.

[0053] In a possible implementation, step S400 further includes:

[0054] Step S460: Construct the formula of tool life status function as follows:

[0055] .

[0056] in, is the tool life status function, The end time of tool running-in period. is the end time node of the tool stabilization period, is the expected total tool life, Characterizes the initial performance of a new knife, Characterizes the highest performance of the tool after running-in, An index that characterizes the rate of increase in performance during the running-in period, The coefficient that characterizes the performance attenuation during the stable period, Represents the current time node, It is the performance decay rate index during the wear period.

[0057] Specifically, A tool life status function is defined as the tool life status function. It is the end time node of the tool running-in period, indicating that the tool enters the stable period from the running-in period. is the end time node of the tool stability period, indicating the end time node of the tool stability period, after which the tool enters the wear period. is the expected total life of the tool, is the expected total life of the tool, Characterize the initial performance of a new tool, which is the initial state of the tool when it is just put into use. Characterizes the maximum performance of the tool after running-in. It indicates the maximum performance of the tool after running-in. This is the best performance level that the tool can achieve after the running-in period. The rate index that characterizes the performance increase during the running-in period determines the speed at which the tool performance improves during the running-in period. The coefficient that characterizes the performance attenuation during the stable period is the coefficient of the performance attenuation during the stable period, which reflects the degree to which the performance of the tool gradually decreases during the stable period. Characterizes the current time node, indicating the current time node, through which it can be determined which stage of the tool life cycle is, is the performance decay rate index during the wear period, which is used to describe how fast the performance of the tool degrades after entering the wear period. This function comprehensively considers all stages of tool life and related parameters, and can more accurately reflect the status and performance of the tool at different time points. For example, at a specific time, the function can be used to calculate the performance level of the tool at this time, thereby providing a basis for tool use, maintenance and replacement decisions. Combining the tool life state function and the fitness function, for example, during the running-in period of the tool, a lower feed speed and rotation speed are selected to reduce tool wear; during the stable period of the tool, the feed speed and rotation speed are appropriately increased to improve processing efficiency. The performance and processing quality of the tool can be considered more comprehensively, thereby realizing the precision machining process optimization of the machine tool spindle system.

[0058] In a possible implementation, step S400 further includes:

[0059] Step S470: Establish a fitness function as follows:

[0060] .

[0061] .

[0062] in, is the fitness function, is the feed speed, is the rotation speed, is the cutting depth, is the total number of feeds, is the current time node, is the processing quality adaptation value under the current parameters, Characterization The penalty factor value of the feed, is the tool performance index at the current time node, is an interactive function, which represents the matching degree between machining parameters and tool status. , , are the weight coefficients of processing quality, penalty factor and interaction term respectively.

[0063] Specifically, is the fitness function, represents the fitness function itself, The feed speed will affect the machining process. The speed is also an important processing parameter. is the cutting depth, which is the key cutting variable. is the total number of feeds, is the current time node, is the processing quality adaptation value under the current parameters, reflecting the processing quality level achieved under the current processing parameters. Characterization The penalty factor value of the feed is a factor used to adjust or penalize a specific feed situation. It is the tool performance index at the current time node, reflecting the performance status of the tool at the current moment. is an interactive function, which is an indicator of the matching degree between machining parameters and tool status. It measures the matching degree between machining parameters and tool status. , , are the weight coefficients of machining quality, penalty factor and interaction term, respectively. These weight coefficients can be used to adjust the importance of each factor in the fitness function. The fitness function comprehensively considers multiple aspects such as machining parameters (feed speed, rotation speed, cutting depth), machining quality, tool performance and their interrelationships, aiming to comprehensively evaluate the machining effect and adaptability under specific parameters and conditions, so as to play a role in the subsequent optimization or decision-making process.

[0064] In a possible implementation, step S500 further includes:

[0065] Step S510: tracing the abnormal impact according to the processing test result, configuring the optimization factor according to the abnormal impact tracing result, and compensating the fitness evaluation function based on the optimization factor.

[0066] Step S520: re-evaluate the optimal set according to the compensated fitness evaluation function to complete the optimal set reconstruction.

[0067] Specifically, tracing the source of abnormal impacts based on processing test results refers to finding out the factors that may cause abnormalities through analyzing processing test data. These factors may include quality problems of raw materials, failure of processing equipment, unreasonable processing technology, etc. Configuring optimization factors based on the results of abnormal impact tracing refers to determining corresponding optimization measures based on the abnormal factors found. For example, if the failure of processing equipment is the cause of the abnormality, the equipment is repaired or replaced; if the unreasonable processing technology is the cause of the abnormality, the process is optimized. Compensating the fitness evaluation function based on the optimization factor refers to adding the optimization factor as a compensation item to the fitness evaluation function to improve the accuracy and reliability of the fitness evaluation function. For example, if the failure of processing equipment is the cause of the abnormality, the failure rate of the equipment can be added to the fitness evaluation function as a compensation item; if the unreasonable processing technology is the cause of the abnormality, the complexity of the process can be added to the fitness evaluation function as a compensation item.

[0068] In a possible implementation, the digital communication between the machine tool spindle system and the monitoring module further includes:

[0069] The monitoring module is used to monitor the processing of the optimal set reconstruction result.

[0070] The consistency between the processing monitoring results and the optimal set reconstruction results is certified.

[0071] Report processing anomalies based on consistency deviations.

[0072] Specifically, the monitoring module is used to closely monitor the actual processing process corresponding to the optimal set reconstruction result. This monitoring process may involve real-time data collection and observation of various processing parameters, processing status, product quality, etc. The processing monitoring results are carefully compared and authenticated with the previously obtained optimal set reconstruction results. This is to verify whether the actual processing situation is consistent with the expected optimal set reconstruction results. If a consistency deviation is found during the comparison process, that is, there is a significant difference between the actual processing monitoring results and the expected optimal set reconstruction results, a processing abnormality will be reported based on this deviation. This means that some unexpected problems or changes may have occurred during the processing process, causing the actual situation to deviate from expectations. This reported processing abnormality can attract the attention of relevant personnel in a timely manner so that they can quickly take measures to troubleshoot the problem, adjust the processing process, or make other necessary interventions to ensure the smooth progress of the processing and the stability of product quality. For example, if the monitoring finds that the quality of the actual processed product is inconsistent with the quality standard expected by the optimal set reconstruction result, a quality abnormality alarm can be issued in time so that corresponding quality control measures can be taken to correct the deviation.

[0073] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0074] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0075] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A precision machining process optimization method for a machine tool spindle system, characterized in that: The method comprises: Establishing digital communication with a machine tool spindle system, and extracting machining information of the machine tool based on the digital communication to construct a machining data set; Performing feature analysis on the processing data set, and constructing a penalty factor library mapped to the processing parameters according to the feature analysis results; Establishing a life cycle of a machining tool, and configuring a tool life state function based on the life cycle; Acquire a machining task, wherein the machining task includes a material data set, cutting removal data, and surface quality requirement data of a machining material, use the cutting removal data and surface quality requirement data in the machining task as basic constraints, construct a fitness evaluation function based on the material data set, a tool life state function, and a penalty factor library, and perform control parameter optimization according to the fitness evaluation function and the basic constraints; Establishing an optimization set according to the optimization results of the control parameters, performing a processing test with the optimization set, reconstructing the optimization set according to the processing test results, and completing the processing technology optimization according to the reconstruction results of the optimization set; The tool life status function configured based on the life cycle further includes: The formula for constructing the tool life status function is as follows: ； in, is the tool life status function, The end time of tool running-in period. is the end time node of the tool stabilization period, is the expected total tool life, Characterizes the initial performance of a new knife, Characterizes the highest performance of the tool after running-in, An index that characterizes the rate of increase in performance during the running-in period, The coefficient that characterizes the performance attenuation during the stable period, Represents the current time node, is the performance decay rate index during the wear period; The fitness evaluation function is constructed based on the material data set, the tool life state function, and the penalty factor library, and further includes: Establish the fitness function as follows: ； ； in, is the fitness function, is the feed speed, is the rotation speed, is the cutting depth, is the total number of feeds, is the current time node, is the processing quality adaptation value under the current parameters, Characterization The penalty factor value of the feed, is the tool performance index at the current time node, is an interactive function, which represents the matching degree between machining parameters and tool status. , , are the weight coefficients of processing quality, penalty factor and interaction term respectively.

2. The method for optimizing the precision machining process of a machine tool spindle system according to claim 1, characterized in that: The performing of control parameter optimization according to the fitness evaluation function and the basic constraints further includes: Constructing a tolerant solution space based on the basic constraints, wherein the tolerant solution space is obtained by tolerantly expanding a basic solution space, and the basic solution space is set by the basic constraints; Performing solution aggregation and clustering on the tolerant solution space to establish solution aggregation and clustering clusters; Obtain the size of each cluster in the solution clustering cluster, and perform region segmentation of the solution clustering cluster according to a preset ratio to establish a region segmentation result, wherein each region segmentation result maps a selection probability; Performing probability selection based on the corresponding selection probability in the region segmentation result, and constructing an initial solution set according to the probability selection result; The control parameter optimization is performed using the initial solution set, the tolerant solution space, and the fitness evaluation function.

3. The method for optimizing the precision machining process of a machine tool spindle system according to claim 2, characterized in that: The performing of control parameter optimization using the initial solution set, the tolerant solution space, and the fitness evaluation function also includes: Based on the fitness evaluation function, the fitness of the initial solution set is evaluated, and an update constraint is generated according to the fitness evaluation result, wherein the update constraint includes an adaptive mutation constraint and a search update constraint; Performing adaptive mutation update on the initial solution set based on the adaptive mutation constraint to generate a first update result; Perform search update in the tolerant solution space based on the search update constraint to generate a second update result; A round of search and update is completed according to the first update result and the second update result, and control parameter optimization is completed based on multiple rounds of search and update iterations.

4. The method for optimizing the precision machining process of a machine tool spindle system according to claim 3, characterized in that: The step of completing a round of search update according to the first update result and the second update result further includes: Performing fitness adaptation elimination on the first update result and the second update result; The initial solution set is updated according to the fitness adaptation elimination results to complete a round of search update.

5. The method for optimizing the precision machining process of a machine tool spindle system according to claim 1, characterized in that: The processing test is performed on the optimal set, and the optimal set is reconstructed according to the processing test result, and further includes: Tracing the source of abnormal impact according to the processing test results, configuring optimization factors according to the abnormal impact tracing results, and compensating the fitness evaluation function based on the optimization factors; The optimal set is re-evaluated according to the compensated fitness evaluation function to complete the optimal set reconstruction.

6. The method for optimizing the precision machining process of a machine tool spindle system according to claim 1, characterized in that: The machine tool spindle system is in digital communication with the monitoring module, and the method further comprises: Processing and monitoring of the optimal set reconstruction results are performed through the monitoring module; Conduct consistency certification on processing monitoring results and optimal set reconstruction results; Report processing anomalies based on consistency deviations.

Images