Tool operation optimization method and system for CNC machining center

Abstract

The present application provides a method for optimizing tool operations for a CNC machining center. The method first performs data preprocessing on the collected machining center operation data. Subsequently, based on these data, the ant colony algorithm is used to optimize the machining paths of different tools on the material in the machining center. After the machining paths are determined, the particle swarm optimization method is used to calculate the working parameters of different tools and generate the optimal working parameters of the tools. Finally, according to production requirements and the optimal working parameters, the working parameters of the machining center when using different tools to process materials are dynamically adjusted. The present application optimizes the tool operations of a CNC machining center by combining the ant colony algorithm and the particle swarm optimization algorithm, and can optimize the tool processing flow and improve production efficiency during the production process.

Description

Technical Field

[0001] The present application relates to the field of automated machining technology, and in particular to a tool operation optimization method and system for a CNC machining center. Background Art

[0002] A machining center is a CNC machine tool that integrates milling, drilling, boring, tapping and other processing functions. Its core is the CNC system (CNC), which automatically controls the relative movement of the tool and the workpiece through pre-programmed processing procedures to achieve high-precision and high-efficiency processing of complex parts. The application of machining centers is not limited to traditional manufacturing, but also widely covers aerospace, automobile manufacturing, mold processing, electronic information and other fields, aiming to improve production efficiency, product quality, reduce production costs, and reduce labor intensity.

[0003] At present, machining centers usually include several key components, including machine tool body, CNC system, automatic tool changer (ATC) and auxiliary devices. Among them: the machine tool body includes mechanical structure parts such as bed, worktable, spindle, etc.; the CNC system controls the core of the machining center, and controls the operation and coordination of the equipment through programming and algorithms; the automatic tool changer realizes the automatic replacement of multiple tools to improve machining efficiency; auxiliary devices such as cooling system, chip removal system, etc., ensure the smooth progress of the machining process.

[0004] Although automated machining centers have obvious advantages in many aspects, existing machining center automation systems mostly rely on pre-recorded machining programs and use preset paths and parameters when using cutting tools for machining. They lack the ability to make dynamic adjustments based on actual machining conditions, resulting in difficulty in optimizing tool processing and improving efficiency when faced with complex and changeable machining paths during the production process.

[0005] Therefore, there is an urgent need for an optimization method that can optimize the tool operation process during the production process. Summary of the invention

[0006] The present application provides a tool operation optimization method and system for a CNC machining center. By combining an ant colony algorithm and a particle swarm optimization algorithm, the tool operation of the CNC machining center is optimized, which can optimize the tool processing flow and improve production efficiency during the production process.

[0007] To solve the above technical problems, in the first aspect, the present application provides a tool operation optimization method for a CNC machining center, the method comprising the following steps: performing data preprocessing based on the collected machining center operation data; optimizing the processing paths of different tools on materials in the machining center using an ant colony algorithm based on the machining center operation data; calculating the working parameters of different tools used in the machining center based on the processing paths using a particle swarm optimization method to generate the optimal working parameters of the tools; and dynamically adjusting the working parameters when using different tools in the machining center to process materials based on the production requirements and the optimal working parameters.

[0008] In an optional scheme of the first aspect, when performing data preprocessing, the method includes the following steps: performing data cleaning based on the collected machining center operation data, wherein the data cleaning includes at least one of outlier and missing value processing; performing data standardization processing based on the operation data that has undergone data cleaning; and performing preset feature extraction based on the operation data that has undergone data standardization processing.

[0009] In an optional solution of the first aspect, when the ant colony algorithm is used to optimize the machining paths of different tools on the material in the machining center, the method includes the following steps: initializing the ant colony, including: defining the number of ant colonies , pheromone matrix , pheromone volatility coefficient and the heuristic function ; According to the tool processing position and tool processing time contained in the machining center operation data, a distance matrix is ​​constructed ; Calculate the probability of ants moving between various processing positions of the material:

[0010]

[0011] Each ant selects the next processing position according to the movement probability to complete the path construction, where: From position To location The probability of moving For location To location The pheromone matrix on the path; For location To location The heuristic function is defined as , For location and location The distance between and are the weight parameters of the pheromone matrix and the heuristic function, A set of automated devices that ants can choose to visit; after completing the path construction, update the pheromone concentration:

[0012]

[0013] in: For the path The pheromone increment in the ant path is calculated; the path construction and pheromone update are repeated until the preset number of iterations is reached, and then the optimal tool processing path is output.

[0014] In an optional solution of the first aspect, when generating the optimal working parameters, the method includes the following steps:

[0015] Initialize the particle swarm, including: defining the number of particles , the initial position of each particle , each particle speed , the optimal position of each particle and the global optimal position ; Update the velocity of each particle:

[0016]

[0017] in, For particles In time speed, is the inertia weight, which controls the inertia of the speed; and is the learning factor, which controls the speed at which the particle approaches its own optimal position and the global optimal position; and To increase the randomness of a random number uniformly distributed in the interval [0,1], update the position of each particle:

[0018]

[0019] The speed and position of each particle are updated repeatedly until the preset number of iterations is reached, and then the optimal working parameters of the machining center using different tools are output.

[0020] In an optional solution of the first aspect, after updating the speed and position of each particle, the method further comprises the following steps: generating the fitness of the new position of each particle: , and then update the local optimal position of each particle according to the fitness of the new position of each particle:

[0021]

[0022] Compare the local best positions of all particles, and then update the global best position according to the local best position of the best particle:

[0023]

[0024] in, , is the time step The optimal particle position in the local optimal position, is the particle with the best fitness; To return the index that minimizes the function , For particles in time step The fitness value of the local optimal position, is the particle index, from 1 to ; Repeatedly update the speed, position, local optimal position and global optimal position of each particle until the preset number of iterations is reached, and then output the global optimal position as the optimal working parameter of the machining center using different tools.

[0025] In an optional scheme of the first aspect, when dynamically adjusting the working parameters when using different tools to process materials in a machining center, the method includes the following steps: calculating the real-time position of the tool according to production requirements and the machining path; adjusting the machining center to the optimal working parameters when using the corresponding tool according to the real-time position of the tool; repeatedly calculating the real-time position of the tool and adjusting the optimal working parameters of the machining center until the tool completes machining of all positions in the machining path.

[0026] In an optional solution of the first aspect, when calculating the real-time position of the tool, the method includes the following steps:

[0027] Initialize the tool position; based on production requirements and processing paths, obtain the processing time required for the tool to move from one position to the next ,in, Indicates the tool position To location Processing time; according to the current time of the location and the time it takes to transfer between locations , update the tool position in real time:

[0028]

[0029] in, is the time interval, For time The position of the tool when For the tool from position To location processing time.

[0030] In an optional solution of the first aspect, when dynamically adjusting the working parameters when using different tools to process materials in a machining center, the method further includes the following steps:

[0031] Based on the operation data of the machining center, the energy consumption distribution of the machining center when using different cutting tools for processing under different production tasks is analyzed; the influence of each feature on energy consumption is evaluated using the feature importance analysis method, and the analysis results including the key factors affecting energy consumption are generated; based on the analysis results and the optimal working parameters of the machining center, an energy consumption optimization strategy is generated; based on production demand and the energy consumption optimization strategy, the working parameters of the machining center when using different cutting tools to process materials are dynamically adjusted.

[0032] In an optional solution of the first aspect, after generating the optimal energy consumption strategy, the method comprises the following steps:

[0033] According to the energy consumption optimization strategy, simulate and adjust the working parameters when using different tools to process materials in the machining center to generate an optimized production plan; calculate the energy consumption change rate of the production plan before and after optimization:

[0034]

[0035] Calculate the change rate of production efficiency of the production plan before and after optimization:

[0036]

[0037] in For energy consumption, For production efficiency; determine whether the energy consumption change rate of the production plan before and after optimization is reduced and / or whether the production efficiency change rate is improved. If so, adjust the working parameters when using different tools to process materials in the machining center according to the optimized production plan. If not, readjust the energy consumption optimization strategy.

[0038] In a second aspect, the present application provides a tool operation optimization system for a CNC machining center, comprising:

[0039] The data processing module is used to perform data preprocessing based on the collected machining center operation data; the path optimization module is used to optimize the processing paths of different tools on materials in the machining center using an ant colony algorithm based on the machining center operation data; the parameter optimization module is used to calculate the working parameters of different tools used in the machining center based on the processing paths using a particle swarm optimization method to generate the optimal working parameters of the tools; the equipment control module is used to dynamically adjust the working parameters of different tools used in the machining center to process materials based on the optimal automated equipment working parameters.

[0040] It should be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings, which are incorporated herein and form a part of the specification, illustrate one or more embodiments of the present application and, together with the description, serve to explain the principles of the present application and to enable one of ordinary skill in the relevant art to make and use the present application.

[0042] Figure 1 is a flow chart of a tool operation optimization method according to some embodiments of the present application.

[0043] Figure 2 is a flowchart of a data preprocessing method according to some embodiments of the present application.

[0044] Figure 3 It is a flowchart of a method for optimizing a processing path using an ant colony algorithm according to some embodiments of the present application.

[0045] Figure 4 It is a schematic diagram of the path length distribution in the ant colony algorithm according to some embodiments of the present application.

[0046] Figure 5 It is a flow chart of a method for optimizing working parameters using a particle swarm method according to some embodiments of the present application.

[0047] Figure 6 It is a schematic diagram of the particle optimization process in the particle swarm method according to some embodiments of the present application.

[0048] Figure 7 It is a flowchart of a first method for dynamically adjusting working parameters of a machining center according to some embodiments of the present application.

[0049] Figure 8 is a flowchart of a method for calculating the real-time position of a tool according to some embodiments of the present application.

[0050] Fig. 9 It is a flowchart of a second method for dynamically adjusting working parameters of a machining center according to some embodiments of the present application.

[0051] Fig.10 It is a flowchart of a method for generating an optimal energy consumption strategy according to some embodiments of the present application.

[0052] Fig.11 It is a connection diagram of a tool operation optimization system according to some embodiments of the present application.

[0053] Fig.12 It is a connection diagram between a control unit and a sensor unit according to some embodiments of the present application.

[0054] Fig.13 This is a schematic diagram of module connections of a control unit according to some embodiments of the present application.

[0055] Fig.14 It is a schematic diagram of the structure of a terminal device according to some embodiments of the present application.

[0056] Explanation of the reference numerals: 10. Machining center; 20. Sensor unit; 30. Control unit; 201. Position sensor; 202. Force sensor; 203. Vibration sensor; 204. Temperature and humidity sensor; 205. Acoustic wave sensor; 206. Displacement sensor; 301. Data processing module; 302. Path optimization module; 303. Parameter optimization module; 304. Equipment control module. DETAILED DESCRIPTION

[0057] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present application will be more comprehensive and complete and fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application.

[0058] For ease of understanding, the machining center 10 is briefly introduced first.

[0059] The machining center 10 is a highly automated multifunctional CNC machine tool, which is widely used in high-precision machining of complex parts. Its main components include a CNC system, a machine tool body, an automatic tool changer (ATC) and various auxiliary devices.

[0060] Specifically, the CNC system is the core of the machining center 10, responsible for interpreting the machining program and issuing control instructions. It is connected to the machine tool body, automatic tool changer (ATC) and various auxiliary devices included in the machining center 10 to control the various movements and functions of the machine tool and ensure the precise execution of the entire production process; the CNC system usually includes a computer, various control modules and an operating interface (HMI). The computer and various control modules are used to process CNC codes and generate corresponding control signals; the operating interface provides a human-computer interaction interface, and the operator inputs the machining program through the operating interface, monitors the machining process, and adjusts the machining parameters.

[0061] Specifically, the machine tool body is the mechanical structure part of the machining center 10, which provides a stable machining platform and necessary motion functions. The machine tool body usually includes a bed, a worktable, a spindle and a servo mechanism, wherein the bed is the basic part of the machine tool, providing a solid and stable support structure, usually made of cast iron or high-strength steel to ensure rigidity and stability during the machining process; the worktable is a plane for mounting the workpiece, which can move on multiple axes and cooperate with the spindle for multi-directional machining, and the worktable can be fixed or rotating to meet different machining requirements; the spindle is the core component that drives the tool to rotate, and the spindle speed and power directly affect the machining efficiency and accuracy; the servo structure usually includes a servo drive and a servo motor, which are used to precisely control the movement of each axis.

[0062] Specifically, the automatic tool changer (ATC) is one of the key components of the machining center 10, which is used to realize the automatic replacement of multiple tools, improve machining efficiency and automation level; ATC usually includes a tool magazine and a manipulator, where the tool magazine stores multiple tools, and the tool magazine capacity ranges from a few to dozens of tools. Common forms include chain type, disc type and umbrella type; the manipulator is a device for automatically changing tools, which can quickly and accurately transfer tools from the tool magazine to the spindle or from the spindle back to the tool magazine. Specific tool changing process: The CNC system controls the manipulator to perform tool changing operations according to the preset program, including tool identification, grasping, transfer and installation. The whole process usually takes only a few seconds.

[0063] Specifically, auxiliary devices ensure the smooth progress of the machining process and improve the machining quality and efficiency. Auxiliary devices usually include cooling devices, chip removal devices, lubrication devices, protective devices and measuring devices, among which: cooling devices usually include coolant pumps, coolant nozzles and coolant recovery devices, which are used to cool the tool and workpiece during the cutting process, reduce heat accumulation, prevent tool overheating and thermal deformation of the workpiece; chip removal systems usually include chip conveyors, chip belts and chip boxes, which are used to promptly remove metal chips generated by cutting, keep the machining area clean, and prevent metal chips from accumulating and affecting machining quality and equipment operation; lubrication systems usually include centralized lubrication devices and automatic lubrication devices, which are used to lubricate various moving parts of the machine tool, reduce friction, and extend equipment life; protective devices usually include machine tool covers, door locks and safety gratings, which are used to protect the safety of operators, prevent chips and coolant splashing, and ensure the safety of the machining environment; measuring devices include online measurement systems and tool setting instruments, which are used to monitor the workpiece size and tool position in real time, perform precision correction and error compensation, and improve machining accuracy.

[0064] Therefore, reference Figure 1 As shown, in some embodiments, the tool operation optimization method for a CNC machining center 10 involved in the present application includes the following steps:

[0065] S1: Perform data preprocessing based on the collected operation data of the machining center 10.

[0066] Specifically, the operation data of the machining center 10 includes production plan, sensor data, tool parameters (such as tool material hardness, dimensional parameters, and tool cutting speed, feed rate, cutting depth processing parameters, etc.), processing time, energy consumption data and the operating status of the machining center 10; wherein, the sensor data includes but is not limited to position data, cutting force and clamping force data, vibration data, temperature data, acoustic wave data and displacement data, and the sensor data is collected by position sensors, cutting force sensors, clamping force sensors, acceleration sensors, temperature sensors, acoustic wave sensors and displacement sensors installed in the machining center 10.

[0067] In the actual implementation process, reference Figure 2 As shown, the data preprocessing includes the following steps:

[0068] S11: performing data cleaning based on the collected operation data of the machining center 10, wherein the data cleaning includes at least one of abnormal value processing and missing value processing.

[0069] Specifically, outliers in the operation data of the machining center 10 are identified and processed by outlier processing. In this embodiment, the three-times standard deviation method is used for outlier processing:

[0070] Calculate the mean of the 10 operation data of the machining center: ,in is the mean of the 10 operation data of the machining center, is the total number of data points of the machining center 10 operation data, This is the number of operation data of machining center 10 data points;

[0071] Calculate the standard deviation of the machining center 10 operation data: ;

[0072] According to the mean and standard deviation of the operation data of machining center 10, it is determined whether there are data points in the operation data of machining center 10 that fall within the range of the mean minus three times the standard deviation, that is: , the meaning of this formula is: if ,but is an outlier; if not, the data points outside the range are judged as outliers, and then all the data points judged as outliers are deleted; where, Usually 3 is taken, but the debugger can adjust it according to the actual situation.

[0073] Missing data is filled or deleted through missing value processing. When filling missing data, in this embodiment, reference is made to the interpolation method or the mean filling method for missing value processing. If the data of the operation data of the machining center 10 is linear data, the linear interpolation method is used; if the data of the operation data of the machining center 10 is complex data, the spline interpolation method is used.

[0074] S12: Perform data standardization processing based on the cleaned operation data.

[0075] Specifically, data standardization converts data into a standard normal distribution or a required standard form. Data standardization usually uses Min-Max standardization or Z-score standardization, where:

[0076] The Min-Max method is used for data normalization:

[0077]

[0078] in, The data of the machining center 10 has been standardized. The operation data of machining center 10 after data cleaning is shown in the figure. is the minimum value of the machining center 10 operation data, It is the maximum value of the operation data of machining center 10;

[0079] The Z-score method is used to standardize the data:

[0080]

[0081] in, is the original data, is the data mean, is the standard deviation of the data; after being standardized by Z-score, the data will have the characteristics of a mean of 0 and a standard deviation of 1, so that data of different dimensions can be compared at the same level.

[0082] S13: Extracting preset features based on the operation data that has undergone data standardization.

[0083] Specifically, the preset feature extraction adopts key feature extraction, including but not limited to the variance selection method and the correlation coefficient method for feature selection, and then the principal component analysis method is used to transform the original features into new features; the variance selection method is used to select features with larger variance, and the correlation coefficient method is used to calculate the Pearson correlation coefficient between each feature and the target variable, and then the features with higher correlation with the target variable are selected.

[0084] For example: Assume that there is a simple set of data normalized for a machining center 10, including cutting force, spindle speed, and feed speed, and the goal is to optimize the surface quality during machining; first, calculate the correlation coefficient between each feature and the surface quality, and select features with larger correlation coefficients, such as cutting force and feed speed; second, use the principal component analysis method to convert the original three-dimensional data (such as cutting force, spindle speed, feed speed) into two-dimensional data, maximize the variance of the operation data, thereby reducing the dimension of the data and reducing the computational complexity.

[0085] S2: According to the operation data of the machining center 10, an ant colony algorithm is used to optimize the machining paths of different tools in the machining center 10 on the material.

[0086] Specifically, refer to Figure 3 , Figure 4 As shown, when the ant colony algorithm is used to optimize the machining paths of different tools on the material in the machining center 10, the following steps are included:

[0087] S21: Initialize the ant colony, including:

[0088] Defining the number of ant colonies , which is usually related to the scale of the problem. For example, for 10 processing locations, the number of ants is usually set to 20.

[0089] Initialize the pheromone matrix is a positive matrix with an initial value of .

[0090] Defining the pheromone volatility coefficient (0< <1).

[0091] Define the heuristic function .

[0092] S22: Construct a distance matrix based on the tool processing position and tool processing time included in the operation data of the machining center 10 ,in, For location and location The distance between.

[0093] S23: Calculate the probability of ants moving between various processing positions of the material:

[0094]

[0095] Each ant selects the next processing position according to the movement probability to complete the path construction.

[0096] in: From position To location The probability of moving For location To location The pheromone matrix on the path; For location To location The heuristic function is defined as ; and are the weight parameters of the pheromone matrix and the heuristic function, A collection of automated devices that ants can choose to access.

[0097] S24: After completing the path construction, update the pheromone concentration:

[0098]

[0099] in: For the path The pheromone increment in the ant path;

[0100] S25: Determine whether the preset number of iterations is reached or other termination conditions are met (such as the path is no longer optimized). If so, execute S26; if not, return to execute S23.

[0101] The preset number of iterations or other termination conditions are set by the debugger according to actual needs.

[0102] S26: Output the optimal tool processing path, that is, the path with the highest pheromone concentration.

[0103] Tool path optimization through ant colony algorithm can effectively solve complex path optimization problems and improve processing efficiency and quality. This method uses the foraging behavior of ants to simulate the combination of pheromone concentration and heuristic function. Through multiple iterations and pheromone updates, the optimal processing path is finally found.

[0104] S3: According to the machining path, a particle swarm optimization method is used to calculate the working parameters of different tools used by the machining center 10 to generate the optimal working parameters of the tools.

[0105] Specifically, refer to Figure 5 , Figure 6 As shown, when generating the optimal working parameters, the method includes the following steps:

[0106] S31: Initialize the particle swarm, including:

[0107] Define the number of particles .

[0108] Initialize the initial position of each particle , where the initial position of each particle is randomly generated in the search space, and the position represents the working parameters of the tool (such as speed, feed rate, depth, etc.).

[0109] Initialize each particle's velocity , where the initial velocity of each particle is randomly generated within a set range, and the velocity represents the amount of change in parameter adjustment.

[0110] Initialize the optimal position of each particle ,Initially, the optimal position of each particle is set to its initial position.

[0111] Initialize the global best position ,Initially, the global optimal position is set to the particle position with the best fitness among all particles.

[0112] S32: Update the velocity of each particle:

[0113]

[0114] in, For particles In time speed, is the inertia weight, which controls the inertia of the speed; and is the learning factor, which controls the speed at which the particle approaches its own optimal position and the global optimal position; and It is a random number uniformly distributed in the interval [0,1] to increase randomness.

[0115] S33: Update the position of each particle:

[0116]

[0117] S34: Generate the fitness of each particle's new position: , and then update the local optimal position of each particle according to the fitness of the new position of each particle:

[0118]

[0119] Among them, the fitness function It can be defined according to the specific goal of tool working parameter optimization; for example, minimizing machining time, minimizing tool wear or improving machining accuracy, etc., which is specifically set by the debugging personnel according to actual needs and costs.

[0120] S35: Compare the local optimal positions of all particles, and then update the global optimal position according to the local optimal position of the optimal particle:

[0121]

[0122] in, , is the time step The optimal particle position in the local optimal position, is the particle with the best fitness; To return the index that minimizes the function , For particles in time step The fitness value of the local optimal position, is the particle index, from 1 to ;

[0123] S36: Determine whether the preset number of iterations is reached or other termination conditions are met (such as the fitness value no longer improves). If so, execute S37; if not, return to execute S32.

[0124] The preset number of iterations or other termination conditions are set by the debugger according to actual needs.

[0125] S37: Output the global optimal position as the optimal working parameter of the machining center 10 using different tools.

[0126] By optimizing the tool working parameters through the particle swarm optimization method, we can explore the multi-dimensional search space and find the tool working parameter combination used by the machining center 10 that minimizes the machining time or optimizes the machining quality. Through multiple iterations and group collaboration, we can eventually find the global optimal solution to improve the machining efficiency and quality.

[0127] S4: Dynamically adjusting the working parameters of the machining center 10 when using different tools to process materials according to the production requirements and the optimal working parameters.

[0128] Specifically, refer to Figure 7 As shown, when dynamically adjusting the working parameters when using different tools to process materials in the machining center 10, the method includes the following steps:

[0129] S41: Calculate the real-time position of the tool according to production requirements and processing path.

[0130] Among them, reference Figure 8 As shown, when calculating the real-time position of the tool, the method includes the following steps:

[0131] S411: Initialize tool position;

[0132] S412: According to production requirements and processing paths, obtain the processing time required for the tool to move from one position to the next ,in, Indicates the tool position To location Processing time;

[0133] S413: Current time based on location and the time it takes to transfer between locations , update the tool position in real time:

[0134]

[0135] in, is the time interval, For time The position of the tool when For the tool from position To location Processing time; when the tool leaves the position and arrive at the location The updated position at the moment is .

[0136] S42: According to the real-time position of the tool, the machining center 10 is adjusted to the optimal working parameters when using the corresponding tool.

[0137] S43: Repeat S41-S42 until the tool completes machining of all positions in the machining path.

[0138] For example, suppose there are three devices , , , the tool processing path is , the processing time between positions is: 3 seconds, is 4 seconds, and the selected time interval The location is updated every 10 seconds, thus:

[0139] Initialization time , tool position .

[0140] Real-time location updates:

[0141] 0 to 3 seconds (the tool is in position ): , , .

[0142] 3 to 7 seconds (tool from Processing to , and in ): Seconds, the tool reaches the position , , , , .

[0143] 7 to 11 seconds (tool from Processing to , and in ): Seconds, the tool reaches the position , , , , .

[0144] Finished processing: seconds, the tool passes through all positions and completes the machining path.

[0145] Through the above steps, the position of the tool can be calculated in real time, and the working parameters of the machining center 10 can be dynamically adjusted according to the tool and its position to optimize the efficiency and energy consumption of the machining center 10.

[0146] In some embodiments, reference Fig. 9 As shown, when dynamically adjusting the working parameters when using different tools to process materials in the machining center 10, the method also includes the following steps:

[0147] S44: Analyze the energy consumption distribution of the machining center 10 when using different tools for machining under different production tasks according to the operation data of the machining center 10.

[0148] Among them, the evaluation indicators are defined as:

[0149] Energy consumption : Represents the total energy consumption in the production process.

[0150] Production efficiency : Indicates the number of products produced per unit time.

[0151] Energy consumption and production efficiency before and after optimization: respectively , , , .

[0152] Calculate energy consumption: , For the Energy consumption of each device during the production process; Calculate production efficiency: total processing quantity divided by production time;

[0153] Then all the calculated energy consumption data are statistically analyzed.

[0154] S45: Use the feature importance analysis method to evaluate the impact of each feature on energy consumption and generate analysis results including key factors affecting energy consumption.

[0155] Among them, the features include processing time, cutting speed, feed speed, tool type, processing material, processing depth, etc.; the feature importance analysis method usually uses the existing decision tree and random forest methods to evaluate the impact of each feature on energy consumption, so as to obtain the importance score of each feature, and then generate analysis results including key factors affecting energy consumption based on the feature importance score.

[0156] S46: Generate an energy consumption optimization strategy based on the analysis results and the optimal working parameters of the machining center 10.

[0157] Among them, according to the results of feature importance analysis, the features that have the greatest impact on energy consumption are identified, and then corresponding energy consumption optimization strategies are formulated. For example, optimizing cutting speed and feed speed, selecting appropriate tool types, optimizing processing paths and processing depths, etc.

[0158] S47: Dynamically adjust the working parameters of the machining center 10 when using different tools to process materials according to production requirements and energy consumption optimization strategies.

[0159] For example, the energy consumption data of the machining center 10 is collected in real time, and then the cutting speed, feed speed and other working parameters are dynamically adjusted in accordance with the energy consumption optimization strategy, so as to ensure the machining quality while minimizing the energy consumption during the machining process.

[0160] In some embodiments, reference Fig.10 As shown, after generating the optimal energy consumption strategy, the method includes the following steps:

[0161] S461: According to the energy consumption optimization strategy, simulate and adjust the working parameters of the machining center 10 when using different tools to process materials, and generate an optimized production plan.

[0162] S462: Calculate the energy consumption change rate of the production plan before and after optimization:

[0163]

[0164] Calculate the change rate of production efficiency of the production plan before and after optimization:

[0165]

[0166] in For energy consumption, For production efficiency, is the energy consumption before optimization, For optimized energy consumption, Production efficiency before optimization, Optimized production efficiency.

[0167] S463: Determine whether the energy consumption change rate of the production plan before and after optimization is reduced and / or whether the production efficiency change rate is improved;

[0168] S464: If the energy consumption is reduced and / or the production efficiency is improved, the optimized production plan is accepted, and according to the optimized production plan, the working parameters when using different tools to process materials in the machining center 10 are actually adjusted.

[0169] S465: If the energy consumption does not decrease and the production efficiency does not increase, the energy consumption optimization strategy is readjusted.

[0170] Fig.11 A connection diagram of the tool operation optimization system of the present application is shown. Fig.11 In the example, the tool operation optimization system for a CNC machining center 10 involved in the present application includes the above-mentioned machining center 10, and further includes:

[0171] The sensor unit 20 includes a position sensor 201 , a force sensor 202 , a vibration sensor 203 , a temperature and humidity sensor 204 , an acoustic wave sensor 205 and a displacement sensor 206 .

[0172] Fig.12 A schematic diagram showing a connection between the control unit and the sensor unit in the present application is shown. Fig.12 In the example, the position sensor 201 , the force sensor 202 , the vibration sensor 203 , the temperature and humidity sensor 204 , the acoustic wave sensor 205 , and the displacement sensor 206 of the sensor unit 20 are connected to the control unit 30 .

[0173] Specifically, the position sensor 201 includes an encoder and a limit switch. The encoder is installed on the servo structure of the machining center 10 and is used to accurately measure the position and speed of each moving axis of the machining center 10 and provide feedback signals to the CNC system to achieve closed-loop control and ensure machining accuracy; the limit switch detects the extreme position of each moving axis of the machining center 10 to prevent the moving axes of the machining center 10 from overtravel.

[0174] The force sensor 202 includes a cutting force sensor and a clamping sensor. The cutting force sensor is installed on the tool or spindle of the machining center 10 to monitor the changes in the cutting force in real time. Through the feedback of the cutting force, it is convenient to optimize the cutting parameters and prevent tool overload and workpiece deformation. The clamping force sensor is used to monitor the clamping force of the workpiece clamping device to ensure the stability and safety of the workpiece during the machining process.

[0175] The vibration sensor 203 adopts an accelerometer and is installed on the spindle, tool or workbench of the machining center 10 to obtain vibration data. By analyzing the vibration data, problems such as tool wear and spindle balance can be detected to prevent the reduction of machining accuracy and equipment damage caused by vibration.

[0176] The temperature and humidity sensor 204 is installed on the spindle, tool and cooling system of the machining center 10 to monitor the temperature and humidity changes of the spindle, tool and cooling system of the machining center 10 in real time.

[0177] The acoustic wave transmitter 205 is installed on the spindle or workpiece fixture of the machining center 10 to monitor the acoustic wave signals generated during the machining process. By analyzing the acoustic emission signals, tool wear, cracks, cutting abnormalities, etc. can be detected.

[0178] The displacement sensor 206 adopts a laser displacement sensor, which is used to measure the surface profile and size of the workpiece with high precision, and assist in online quality inspection and error compensation.

[0179] The control unit 30 is connected to the sensor unit 20 and the machining center 10 and is used to control the sensor unit 20 to cooperate with the machining center 10 to process the product.

[0180] Fig.13 A schematic diagram of module connection of the control unit in the present application is shown. It should be understood that the implementation of the control unit 30 can be performed by dividing multiple modules, for example, it can be performed synchronously or asynchronously in multiple modules. It should be understood that the specific functions performed by these modules correspond to the steps covered by the tool operation optimization method above.

[0181] exist Fig.13 In the example, the control unit 30 includes a data processing module 301, a path optimization module 302, a parameter optimization module 303 and a device control module 304.

[0182] The data processing module 301 is used to perform data preprocessing based on the collected operation data of the machining center 10 .

[0183] Specifically, when performing data preprocessing, the data processing module 301 can also be used to perform data cleaning based on the collected machining center operation data, wherein the data cleaning includes at least one of abnormal value processing and missing value processing; perform data standardization processing based on the operation data that has undergone data cleaning; and perform preset feature extraction based on the operation data that has undergone data standardization processing.

[0184] The path optimization module 302 is used to optimize the processing paths of different tools on the material in the machining center 10 by using an ant colony algorithm according to the operation data of the machining center 10 .

[0185] Specifically, the path optimization module 302 can also be used to initialize the ant colony when using the ant colony algorithm to optimize the processing paths of different tools on the material in the machining center; construct a distance matrix based on the tool processing position and tool processing time contained in the machining center operation data; calculate the movement probability of ants between various processing positions of the material, and each ant selects the next processing position according to the movement probability to complete the path construction; after completing the path construction, update the pheromone concentration; repeat the path construction and pheromone update until the preset number of iterations is reached, and then output the optimal tool processing path.

[0186] The parameter optimization module 303 is used to calculate the working parameters of different tools used by the machining center 10 according to the machining path by using a particle swarm optimization method, and generate the optimal working parameters of the tools.

[0187] Specifically, when generating the optimal working parameters of the tool, the parameter optimization module 303 can also be used to initialize the particle group; update the speed of each particle; update the position of each particle; generate the fitness of each particle's new position, and then update the local optimal position of each particle according to the fitness of each particle's new position; compare the local optimal positions of all particles, and then update the global optimal position according to the local optimal position of the optimal particle; repeatedly update the speed, position, local optimal position and global optimal position of each particle until a preset number of iterations is reached, and then output the global optimal position as the optimal working parameter of the machining center using different tools.

[0188] The equipment control module 304 is used to dynamically adjust the working parameters of the machining center 10 when using different tools to process materials according to the optimal automation equipment working parameters.

[0189] Specifically, when the equipment control module 304 dynamically adjusts the working parameters when using different tools to process materials in the machining center, it can also be used to calculate the real-time position of the tool according to production needs and machining paths; adjust the machining center to the optimal working parameters when using the corresponding tool according to the real-time position of the tool; repeatedly calculate the real-time position of the tool and adjust the optimal working parameters of the machining center until the tool completes machining of all positions in the machining path.

[0190] The equipment control module 304 can also be used to initialize the tool position when calculating the real-time position of the tool; obtain the processing time required for the tool to move from one position to the next according to production requirements and processing paths; and update the tool position in real time according to the current time of the position and the transmission time between positions.

[0191] In some embodiments, when the equipment control module 304 dynamically adjusts the working parameters of the machining center when using different tools to process materials, it can also be used to analyze the energy consumption distribution of the machining center when using different tools for processing under different production tasks based on the machining center's operation data; use the feature importance analysis method to evaluate the impact of each feature on energy consumption, and generate analysis results including key factors affecting energy consumption; generate an energy consumption optimization strategy based on the analysis results and the optimal working parameters of the machining center; and dynamically adjust the working parameters of the machining center when using different tools to process materials based on production needs and the energy consumption optimization strategy.

[0192] After generating the optimal energy consumption strategy, the equipment control module 304 simulates the adjustment of the working parameters when using different tools to process materials in the machining center according to the energy consumption optimization strategy, and generates an optimized production plan; calculates the energy consumption change rate of the production plan before and after optimization, and calculates the production efficiency change rate of the production plan before and after optimization; determines whether the energy consumption change rate of the production plan before and after optimization is reduced and / or the production efficiency change rate is increased. If so, adjust the working parameters when using different tools to process materials in the machining center according to the optimized production plan; if not, readjust the energy consumption optimization strategy.

[0193] Fig.14 A block diagram of a terminal device 40 of the present application is shown. In some embodiments, the terminal device 40 includes a processor 401 and a memory 402, wherein the number of the processor 401 and the memory 402 can be one or more. The memory 402 is coupled to the processor 401 and is used to store a computer program or instruction 403 executed by the processor 401. When the computer program or instruction 403 is executed by the processor 401, the terminal device 40 performs any of the tool operation optimization methods described in the foregoing.

[0194] Specifically, the processor 401 communicates with the memory 402, and the memory 402 may include a read-only memory and a random access memory, and provides instructions and data to the processor 401. In addition, a part of the memory 402 may also include a non-volatile random access memory (NVRAM). In the memory 402, operation instructions, executable modules, data structures or their subsets, or even their extension sets are stored. These operation instructions cover various operations for implementing various operations. The tool operation optimization method described in the embodiment of the present application can be applied to the processor 401, or implemented by the processor 401. The processor 401 can be any applicable computer processor, such as a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device (FPGA), etc. In an embodiment of the present application, the processor 401 is responsible for executing each step of the tool operation optimization method.

[0195] The computer program or instructions 403 include a computer program for executing a computer process on a computing device. In some embodiments, the computer program or instructions 403 are provided using a signal bearing medium. The signal bearing medium may include one or more program instructions that, when executed by one or more processors 401, may provide the functions or portions of the functions described in the above embodiments of the tool operation optimization method. Thus, for example, one or more features in the tool operation optimization method may be undertaken by one or more instructions associated with the signal bearing medium.

[0196] In some embodiments, the present application further provides a computer-readable storage medium storing a computer program, which, when executed by the processor 401, implements any of the tool operation optimization methods described above.

[0197] Specifically, a computer-readable storage medium refers to a medium that can be read by a computer system, such as a hard disk, a solid-state drive, an optical disk, a flash drive, etc. In some embodiments of the present application, the computer-readable storage medium stores a set of computer programs, which are executed by the processor 401 to implement the various steps and functions described in the tool operation optimization method. These computer programs may include operating systems, embedded software, applications, etc., for controlling and managing the process of the method. By reading and executing the programs stored on the computer-readable storage medium, the computer system can effectively implement the tool operation optimization method of the present application.

[0198] In some embodiments, the present application further provides a computer program product, which includes computer executable instructions. When the computer executable instructions are executed by a processor, the computer implements the tool operation optimization method described in any of the above items.

[0199] Specifically, a computer program product is a product storing computer executable instructions, the purpose of which is to implement the various steps and functions described in the tool operation optimization method when executed by the processor 401 of the computer system. The computer executable instructions may include an operating system, an application program, an embedded software, etc., to control and manage the process of the method. By using such a computer program product, a user can execute the tool operation optimization method of the present application on a computer system.

[0200] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A tool operation optimization method for a CNC machining center, characterized in that: The following steps are involved: Perform data preprocessing based on the collected machining center operation data; According to the operation data of the machining center, an ant colony algorithm is used to optimize the machining paths of different tools on the material in the machining center; According to the machining path, a particle swarm optimization method is used to calculate the working parameters of different tools used in the machining center, and the optimal working parameters of the tools are generated; Dynamically adjust the working parameters of the machining center when using different tools to process materials according to production needs and optimal working parameters; Among them, the particle swarm optimization method is used to optimize the tool working parameters, explore the multi-dimensional search space, and find the tool working parameter combination used by the machining center that achieves the best machining quality; Among them, when dynamically adjusting the working parameters when using different tools to process materials in a machining center, it includes: Calculate the real-time position of the tool according to production requirements and processing paths; According to the real-time position of the tool, the machining center is adjusted to the optimal working parameters when using the corresponding tool; Repeatedly calculate the real-time position of the tool and adjust the optimal working parameters of the machining center until the tool completes machining of all positions in the machining path; Among them, when dynamically adjusting the working parameters when using different tools to process materials in a machining center, it includes: According to the operation data of the machining center, analyze the energy consumption distribution of the machining center when using different tools for different production tasks; Use the feature importance analysis method to evaluate the impact of each feature on energy consumption and generate analysis results including key factors affecting energy consumption; the feature importance analysis method uses a decision tree or random forest method to evaluate the impact of each feature on energy consumption, so as to obtain the importance score of each feature, and then generate analysis results including key factors affecting energy consumption based on the feature importance score; According to the analysis results and the optimal working parameters of the machining center, an energy consumption optimization strategy is generated; wherein, according to the feature importance analysis results, the features that have the greatest impact on energy consumption are identified, and then a corresponding energy consumption optimization strategy is formulated; Dynamically adjust the working parameters of machining centers using different tools to process materials according to production needs and energy consumption optimization strategies; After generating the optimal energy consumption strategy, the method comprises the following steps: According to the energy consumption optimization strategy, simulate and adjust the working parameters of the machining center when using different tools to process materials, and generate optimized production plans; Calculate the energy consumption change rate of the production plan before and after optimization: ， Calculate the change rate of production efficiency of the production plan before and after optimization: ， in For energy consumption, For production efficiency; Determine whether the energy consumption change rate of the production plan before and after optimization is reduced and / or whether the production efficiency change rate is improved. If so, adjust the working parameters of the machining center when using different tools to process materials according to the optimized production plan. If not, readjust the energy consumption optimization strategy.

2. The tool operation optimization method for a CNC machining center according to claim 1, characterized in that: When performing data preprocessing, the method comprises the following steps: Performing data cleaning based on the collected machining center operation data, wherein the data cleaning includes at least one of abnormal value processing and missing value processing; Perform data standardization based on the cleaned operation data; Perform preset feature extraction based on the job data that has undergone data standardization.

3. The tool operation optimization method for a CNC machining center according to claim 1 or 2, characterized in that: When the ant colony algorithm is used to optimize the machining paths of different tools on the material in the machining center, the method includes the following steps: Initialize the ant colony, including: defining the number of ant colonies , pheromone matrix , pheromone volatility coefficient and the heuristic function ; Construct a distance matrix based on the tool processing position and tool processing time contained in the machining center operation data ; Calculate the probability of ants moving between various processing positions of the material: ， Each ant selects the next processing position according to the movement probability to complete the path construction, where: From position To location The probability of moving For location To location The pheromone matrix on the path; For location To location The heuristic function is defined as , For location and location The distance between and are the weight parameters of the pheromone matrix and the heuristic function, A collection of automated devices that ants can choose to access; After completing the path building, update the pheromone concentration: ， in: For the path The pheromone increment in the ant path; Repeat path construction and pheromone update until the preset number of iterations is reached, and then output the optimal tool processing path.

4. The tool operation optimization method for a CNC machining center according to claim 3, characterized in that: When generating the optimal operating parameters, the method comprises the following steps: Initialize the particle swarm, including: defining the number of particles , the initial position of each particle , each particle speed , the optimal position of each particle and the global optimal position ; Update the velocity of each particle: ， in, For particles In time speed, is the inertia weight, which controls the inertia of the speed; and is the learning factor, which controls the speed at which the particle approaches its own optimal position and the global optimal position; and To increase randomness, the random numbers are uniformly distributed in the interval [0,1]; Update the position of each particle: ； The speed and position of each particle are updated repeatedly until the preset number of iterations is reached, and then the optimal working parameters of the machining center using different tools are output.

5. The tool operation optimization method for a CNC machining center according to claim 4, characterized in that: After updating the velocity and position of each particle, the method further comprises the following steps: Generate the fitness of each particle's new position: , and then update the local optimal position of each particle according to the fitness of the new position of each particle: ； Compare the local best positions of all particles, and then update the global best position according to the local best position of the best particle: ， in, , is the time step The optimal particle position in the local optimal position, is the particle with the best fitness; To return the index that minimizes the function , For particles in time step The fitness value of the local optimal position, is the particle index, from 1 to ; The speed, position, local optimal position and global optimal position of each particle are repeatedly updated until the preset number of iterations is reached, and then the global optimal position is output as the optimal working parameter of the machining center using different tools.

6. The tool operation optimization method for a CNC machining center according to claim 1, characterized in that: When calculating the real-time position of the tool, the method includes the following steps: Initialize tool position; According to production requirements and processing paths, obtain the processing time required for the tool to move from one position to the next ,in, Indicates the tool position To location Processing time; Current time based on location and the time it takes to transfer between locations , update the tool position in real time: ， in, is the time interval, For time The position of the tool when For the tool from position To location processing time.

7. A tool operation optimization system for a CNC machining center using the method according to any one of claims 1 to 6, characterized in that: include: A data processing module is used to perform data preprocessing based on the collected machining center operation data; A path optimization module, used to optimize the processing paths of different tools on the material in the machining center by using an ant colony algorithm according to the operation data of the machining center; A parameter optimization module, used to calculate the working parameters of different tools used by the machining center according to the machining path by using a particle swarm optimization method, and generate the optimal working parameters of the tools; The equipment control module is used to dynamically adjust the working parameters of the machining center when using different tools to process materials according to the optimal working parameters of the automation equipment.

Images