Machining parameter automatic optimization method and system for three-axis numerical control machine tool

Abstract

The invention relates to the technical field of numerical control machine tool control, in particular to a machining parameter automatic optimization method and system for a three-axis numerical control machine tool, and the method comprises the specific steps: collecting machine tool parameter data and workpiece parameter data, the machine tool parameter data comprises the current and voltage of the three-axis numerical control machine tool and the wear state of a cutter; the workpiece parameter data comprises workpiece scale, vibration, deflection and surface roughness; based on the machine tool parameter data and the workpiece parameter data, a physical information neural network is adopted to construct a three-axis numerical control machine tool digital twin model, real-time monitoring and feedback are carried out, and the machining efficiency and energy consumption are calculated; a numerical control machine tool machining process model and an energy consumption model are constructed based on the machining efficiency and the energy consumption, the machining efficiency is maximized and the energy consumption is minimized by using an optimization algorithm, the machining process model reflects quality efficiency indexes, and the energy consumption model reflects energy consumption characteristics; and through an optimization function obtained through the optimization algorithm, a control instruction execution module is constructed, and comprehensive factory control is covered.

Description

Technical Field

[0001] The present invention relates to the technical field of CNC machine tool control, and in particular to a method and system for automatically optimizing machining parameters of a three-axis CNC machine tool. Background Art

[0002] In the field of CNC technology control, with the continuous advancement of technology, the methods for automatic optimization of the processing parameters of CNC machine tools are also constantly being updated, but there are still some problems.

[0003] Mathematical methods are the fundamental approach to optimizing machining parameters for three-axis CNC machine tools. Their core objective is to calculate optimal machining parameters by establishing mathematical relationships between the machine tool, cutting tool, and workpiece system. These methods typically aim to quantify the physical phenomena during the cutting process to guide parameter selection. Adaptive control technology is a core area of automated CNC machining parameter optimization, capable of automatically adjusting the machine tool feed rate to the optimal value and monitoring and recording machining parameters in real time. Current technologies primarily utilize optimization algorithms, which, through learning and reasoning, overcome the shortcomings of traditional methods in handling complex, nonlinear, and multi-objective problems. Starting with genetic algorithms and particle swarm optimization, these methods have become increasingly complex.

[0004] The main challenges faced by this technology are high costs, data integrity and representativeness, integration with existing equipment, and inherent limitations of the technology. Furthermore, parameter settings have a significant impact on the results, limiting its robustness in practical applications. This invention improves the automation system architecture, making machine tool parameters more intuitive and easier for operators to control. This enables comprehensive factory control, improves its robustness and interpretability in actual industrial environments, and addresses data sparsity, particularly under the specific operating conditions of three-axis machine tools. To this end, a method and system for automatic optimization of machining parameters for three-axis CNC machine tools are proposed. Summary of the Invention

[0005] The present invention specifically provides a method and system for automatically optimizing machining parameters for three-axis CNC machine tools, which is used to automatically optimize and debug the machining parameters of three-axis CNC machine tools. The specific implementation steps are: first, collecting the parameter data of the three-axis CNC machine tool and various parameter data of the machined workpiece, then using a physical information neural network to construct a digital twin model of the three-axis CNC machine tool based on the parameter data, real-time monitoring and feedback, and calculation of machining efficiency and energy consumption, constructing a CNC machine tool machining process model and an energy consumption model, using an optimization algorithm to maximize machining efficiency and minimize energy consumption, and then constructing a control instruction execution module based on the optimization function derived from the optimization algorithm, covering comprehensive factory control.

[0006] The present invention integrates the characteristics of multi-source data, and through the machining process model and energy consumption model constructed according to machining efficiency and energy consumption, uses the optimization algorithm to accurately calculate the ideal parameter combination that can maximize the machining efficiency. Compared with the traditional setting method that relies on experience or fixed parameter tables, it effectively reduces invalid operations and waiting time in machining, greatly improves the material removal rate or the number of workpieces processed per unit time, improves the machining efficiency of machine tools, provides scientific and accurate machining parameter decision support for operators and production managers, and avoids machining problems caused by lack of human experience or misjudgment.

[0007] A method for optimizing machining parameters for a three-axis CNC machine tool comprises the following steps: collecting machine tool parameter data and workpiece parameter data, wherein the machine tool parameter data include the current, voltage, and tool wear status of the three-axis CNC machine tool, and the workpiece parameter data include the workpiece size, vibration frequency, deflection, and surface roughness; constructing a digital twin model of the three-axis CNC machine tool based on the machine tool parameter data and the workpiece parameter data, performing real-time monitoring and feedback, and calculating machining efficiency and energy consumption; constructing a machining process model and an energy consumption model of the CNC machine tool based on the machining efficiency and energy consumption, and using an optimization algorithm to maximize machining efficiency and minimize energy consumption, wherein the machining process model monitors the quality efficiency indicators of the machining process, and the energy consumption model monitors the energy consumption of the machining process; constructing a control instruction execution system based on the optimization function derived from the optimization algorithm, wherein the control instruction execution system is used to run the optimized parameters, adaptively cover comprehensive factory control, and realize collaborative scheduling of multiple machine tools through a distributed network interface.

[0008] Preferably, the process of collecting machine tool parameter data and workpiece parameter data includes: The current, voltage and tool wear status of the die cutting tool are collected as machine tool parameter data; the workpiece size, vibration frequency, deflection and surface roughness of the workpiece are collected as workpiece parameter data, and the collected data are preprocessed.

[0009] Preferably, the process of constructing a digital twin model of a three-axis CNC machine tool based on the machine tool parameter data and the workpiece parameter data, performing real-time monitoring and feedback, and calculating machining efficiency and energy consumption includes: Use deep learning algorithms to fuse the collected multi-source data, automatically identify and remove noise and outliers, extract characteristic parameters that have a key impact on processing efficiency and energy consumption, build a fusion data set, use a large amount of historical data to train the model, adjust the network weights and biases, and monitor the performance of the model in real time during the training process. As the machine tool operation and processing conditions change, new data is collected regularly to update and retrain the model.

[0010] Preferably, the process of constructing a machining process model and an energy consumption model based on machining efficiency and energy consumption includes: The processing data collected and accumulated in real time in the digital twin model is used to train the processing process model, and the preliminary model based on physical laws is corrected and optimized so that the model can reflect the complex nonlinear processing efficiency relationship in the actual processing process; the input variables and corresponding energy consumption data of the actual processing process collected in the digital twin model are used to train and optimize the energy consumption model established based on the basic relationship, and the parameters of the model are estimated and adjusted to fit the relationship between actual energy consumption and each input variable.

[0011] Preferably, the process of using an optimization algorithm to maximize processing efficiency and minimize energy consumption includes: Select the simulated annealing algorithm, retrieve the processing efficiency after the correction and optimization of the processing model, and retrieve the energy consumption data after the correction and optimization of the energy consumption model, perform weighted summation, determine the weight coefficient according to the priority in the actual production scenario, obtain the optimization function, integrate the constructed processing process model and energy consumption model into the optimization algorithm, use the processing parameters as the decision variables and the objective function as the optimization direction, run the optimization algorithm, obtain the combination of maximizing processing efficiency and minimizing energy consumption, analyze and verify it, and give the machine tool control instructions to be integrated into the computer.

[0012] Preferably, the weighted sum of quality efficiency indicators and energy consumption characteristics is retrieved to obtain an optimization function. The control instruction execution system is adaptively covered to achieve full factory control, and multi-machine tool collaborative scheduling is achieved through a distributed network interface. The implementation process includes: Based on the optimal processing parameters obtained by the optimization function, corresponding control instructions are generated, and the generated control instructions are converted into an executable instruction format for CNC machine tools. The instructions are security-checked and sent to the control instruction execution system. The control instruction execution system transmits the instructions to multiple CNC machine tools through a distributed network interface to achieve factory-level collaborative control.

[0013] A machining parameter optimization system for three-axis CNC machine tools, comprising: Data collection module: used to collect machine tool parameter data and workpiece parameter data; Digital twin module: monitors and feeds back machine tool parameter data and workpiece parameter data, performs real-time detection and feedback, and calculates processing efficiency and energy consumption; Process model and energy consumption model modules: reflect the complex nonlinear relationship between processing efficiency in the actual processing process and fit the relationship between actual energy consumption and various input variables; Optimization algorithm module: Use the optimization algorithm to maximize processing efficiency and minimize energy consumption, retrieve and perform weighted summation to obtain the optimization function; Control instruction execution system module: Build adaptive control instruction execution, execute the best optimization parameter plan, and transmit instructions to multiple CNC machine tools at the same time to achieve factory-level collaborative control.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. The machining process model and energy consumption model proposed in this invention enable refined control of the energy consumption of various machine tool components. This reduces the average energy consumption of three-axis CNC machine tools during machining, saving companies substantial energy costs in long-term production. Using an optimization algorithm, the ideal parameter combination that maximizes machining efficiency is accurately calculated. This effectively reduces ineffective machining operations and waiting time, significantly increasing the material removal rate or the number of workpieces processed per unit time, and thus improving machine tool machining efficiency.

[0015] 2. The optimization algorithm proposed in the present invention analyzes the machining process model and energy consumption model, and while pursuing the maximization of machining efficiency, fully considers the minimization of energy consumption. Through real-time monitoring and feedback mechanisms, the system can adjust machining parameters in a timely manner to adapt to changes in the workpiece and machine tool status, preventing energy waste caused by severe tool wear and motor overload due to unreasonable parameters, further improving energy utilization efficiency and reducing economic losses and environmental pressures caused by unnecessary energy consumption.

[0016] 3. The optimization function proposed in this invention constructs control instructions by taking the machining efficiency after correction and optimization of the machining model and the energy consumption data after correction and optimization of the energy consumption model, taking a weighted sum of these, and constructing a control instruction. This control instruction execution system not only optimizes and controls the parameters of a single machine tool, but also focuses on comprehensive factory control coverage. Through deep integration with the factory production management system, it achieves closed-loop control of the entire process, from production planning and machining task allocation to machine tool operation execution. This improves the coordination and efficiency of the factory's overall production operations, enabling enterprises to respond to complex production model requirements such as high-variety and small-batch production in a more flexible and efficient manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flow chart of a method for automatically optimizing machining parameters for a three-axis CNC machine tool, as proposed in an embodiment of the present invention; Figure 2 A process diagram for obtaining an optimized function for an embodiment of the present invention; Figure 3 A module diagram of a machining parameter automatic optimization system for three-axis CNC machine tools is proposed for the embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0019] In the existing technology, the processing parameter optimization technology of three-axis CNC machine tools mainly adopts adaptive control technology. Through learning and reasoning, they overcome the shortcomings of traditional methods in dealing with complex, nonlinear and multi-objective problems. Starting from genetic algorithms and particle swarm optimization, the complexity continues to increase, but the high cost, data integrity and representativeness, integration with existing equipment and the limitations of the technology itself are the main challenges it faces. In addition, the parameter setting has a great impact on the results, which also limits its robustness in practical applications. The present invention makes improvements in the automation system architecture, making the machine tool parameters more intuitive and easier for operators to control, realizing comprehensive factory control.

[0020] The present invention relates to the field of CNC machine tool control technology, and specifically to a method and system for automatically optimizing machining parameters for three-axis CNC machine tools. The method and system are suitable for further optimizing the machining parameters of three-axis CNC machine tools, improving machining efficiency and reducing energy consumption. To illustrate the effectiveness of the method and system of the present invention, a specific description will be given in conjunction with the accompanying drawings of this embodiment and the following embodiments.

[0021] Example 1 The present application discloses a method and system for automatically optimizing machining parameters for a three-axis CNC machine tool. Figure 1 As shown. Factory A processes aviation parts. Faced with the task of processing high-precision, complex-shaped titanium alloy aircraft engine blades, it needs to use a three-axis CNC machine tool. First, the machine tool parameter data and workpiece parameter data are collected. The machine tool parameter data include the current and voltage of the three-axis CNC machine tool and the tool wear status. The workpiece parameter data include the workpiece size, vibration frequency, deflection and surface roughness. Based on the machine tool parameter data and workpiece parameter data, a physical information neural network is used to construct a three-axis CNC machine tool digital twin model for real-time monitoring and feedback, and to calculate the processing efficiency and energy consumption. Based on the processing efficiency and energy consumption, a CNC machine tool processing process model and an energy consumption model are constructed. An optimization algorithm is used to maximize processing efficiency and minimize energy consumption. The processing process model monitors the quality efficiency indicators of the processing process, and the energy consumption model monitors the energy consumption of the processing process. The optimization function obtained by the optimization algorithm is used to construct a control instruction execution module to cover comprehensive factory control.

[0022] Furthermore, the machine tool parameter data and the workpiece parameter data are collected. Corresponding to the above steps, the specific implementation process includes: The current and voltage data of the die cutting tools during operation are collected as a key component of the machine tool parameter data. The tool wear status is also monitored and quantified into monitorable parameter data. Current and voltage data reflect the operating load and status of electrical equipment such as the machine tool motor, while tool wear directly affects machining accuracy and surface quality. Comprehensive workpiece parameters are collected, including dimensions, vibration frequency, deflection, and surface roughness. These parameters reflect the workpiece's state and machining quality from various perspectives. A generative adversarial network (GAN) is used to preprocess the machine tool and workpiece parameter data, automatically and adaptively learning and removing complex, nonlinear noise and outliers.

[0023] This embodiment performs data collection operations and specifies the specific content and methods of data collection to ensure that the collected multi-dimensional data comprehensively and accurately reflects the real-time status of the three-axis CNC machine tool and the workpieces it processes. This precise data collection provides high-quality raw data for the subsequent construction of digital twin models, machining process models, and energy consumption models. The comprehensive collection of workpiece parameters enables the optimization system to more accurately grasp the impact of the machining process on workpiece quality, helping to improve the accuracy and reliability of the model, enabling the model to better simulate and predict the actual conditions during the machining process, and providing a solid basis for the optimization algorithm.

[0024] Furthermore, based on the machine tool parameter data and workpiece parameter data, a digital twin model of a three-axis CNC machine tool is constructed to monitor and feedback in real time, and calculate the processing efficiency and energy consumption. Corresponding to the above steps, the specific implementation process includes: The collected data is preprocessed through noise removal, normalization, and feature extraction. This removes noise and eliminates interfering information, ensuring that the data accurately reflects the actual machining state. Normalization converts data of varying dimensions and numerical ranges to a unified scale, preparatory to subsequent data analysis and modeling. A convolutional neural network is used to identify characteristic parameters that critically impact machining efficiency and energy consumption. This multidimensional data is then fused to inform the subsequent construction of accurate digital twin models, machining process models, and energy consumption models. The model is then trained using extensive historical data, adjusting the network weights and biases to construct the digital twin model. During training, model performance is monitored in real time to ensure that it accurately simulates and predicts actual machining behavior. As machine operation and machining conditions change, new data is regularly collected, and the model is updated and retrained to maintain accuracy and adaptability.

[0025] This embodiment builds a digital twin model to implement a mechanism for real-time monitoring of model performance and regular collection of new data to update and retrain the model, so that the digital twin model can promptly capture changes in the machine tool operating status and processing conditions. This real-time and adaptable nature ensures that the model can maintain good predictive performance under different processing tasks and working conditions, providing accurate real-time data support for the optimization algorithm, thereby achieving dynamic optimization and precise control of the processing process.

[0026] Furthermore, a machining process model and an energy consumption model are constructed based on machining efficiency and energy consumption. The implementation process includes: The digital twin model collects various types of machining process data in real time, including machine tool and workpiece parameters, as input variables. Simultaneously, machining efficiency is used as the output variable. A preliminary machining process model is constructed based on the cutting force model. This preliminary model is then modified and optimized using a support vector machine algorithm. By analyzing a large amount of historical machining data, deviations and errors in the preliminary model are identified and corrected, enabling the model to reflect the complex nonlinear relationships in the actual machining process. Input variables from the actual machining process, including cutting speed, feed rate, and depth of cut, as well as corresponding energy consumption data, including spindle motor energy consumption and feed motor energy consumption, are collected from the digital twin model. Based on this data, the basic relationships of the energy consumption model are established. A linear regression model is typically used to preliminarily fit the relationship between energy consumption and the input variables. The energy consumption model is trained using a data-driven modeling approach. By adjusting the model parameters, the model is better aligned with the actual energy consumption data, improving its prediction accuracy. During the training process, the machining data collected and accumulated in real time within the digital twin model is used to train the machining process model. By integrating a structural causal model, the model can identify the true causal variables that influence machining efficiency and energy consumption, providing an interpretable basis for optimization decisions.

[0027] The constructed machining process model and energy consumption model are used as simulators of the enhanced learning environment, and the weighted functions of machining efficiency and energy consumption are used as reward functions. Strategy learning is performed in the simulation environment of the digital twin model. The strategy learning can dynamically adjust the machining parameters according to the real-time monitored machine tool parameter data and workpiece parameter data to achieve adaptive updates and improve data processing efficiency. The digital twin model, the machining process model and the energy consumption model form a dynamic two-way self-correcting closed-loop mechanism. The digital twin model serves as the core of real-time data aggregation and state mapping. Its monitoring data not only trains and optimizes the machining process model and the energy consumption model, but also the prediction results and optimization suggestions of the two models will be fed back to the digital twin model in real time, driving the update of the digital twin state and virtual simulation, thereby forming more accurate digital mapping and more effective guidance. When the digital twin model, processing model and energy consumption model perform two-way self-correction, an assessment of prediction uncertainty is introduced. By quantifying the uncertainty of the model prediction results, a more cautious parameter adjustment strategy is automatically triggered when the prediction uncertainty is high. When the prediction uncertainty is low, a bolder adjustment of the processing parameters is allowed to further optimize the processing efficiency and energy consumption, making the dynamic adjustment of the processing parameters more intelligent and flexible, and better able to cope with the complex and changeable actual processing environment.

[0028] The machining process model of this embodiment can more accurately capture the complex nonlinear relationship between various parameters in the machining process by correcting and optimizing the preliminary model based on physical laws; the energy consumption model uses a data-driven modeling method to train and optimize the energy consumption model, which can more accurately fit the relationship between actual energy consumption and various input variables; the machining process model and the energy consumption model improve machining efficiency, accurately predict and optimize energy consumption, reduce machining time and scrap rate, reduce production costs, reduce the energy consumption of machine tools, and reduce production costs and environmental impact.

[0029] Furthermore, the process of using the optimization algorithm to maximize processing efficiency and minimize energy consumption includes: The constructed machining process model and energy consumption model are integrated into the optimization algorithm, with machining parameters as decision variables. These two models provide predicted values for machining efficiency and energy consumption, respectively, as components of the optimization algorithm's objective function. Starting with an initial solution, the model uses a multi-objective optimization algorithm based on a dynamic game strategy. This multi-objective optimization algorithm treats the machining process as a dynamic game between multiple decision-makers, adjusting the strategies of each decision-maker in real time. In each iteration, the algorithm decides whether to accept a new solution based on the combination of machining efficiency and energy consumption of the current solution. If the new solution's objective function value is better, the new solution is accepted; if the new solution's objective function value is slightly worse, the new solution is also accepted with a certain probability to avoid falling into a local optimum, thus achieving a dynamic balance between machining efficiency and energy consumption under different working conditions and constraints.

[0030] The optimization algorithm of this embodiment effectively avoids local optimality and improves the global nature of the optimization results. In three-axis CNC machine tool processing, simultaneous optimization of machining efficiency and energy consumption can significantly improve machining efficiency. During the optimization process, the obtained optimization results are analyzed and verified in real time. By comparing and evaluating them with actual machining data, it is ensured that the optimized machining parameters can effectively improve machining efficiency and reduce energy consumption in actual production.

[0031] Furthermore, the optimization function obtained by the optimization algorithm is as follows: Figure 2 , through the control instruction execution module, the parameters are optimized and operated. Corresponding to the above steps, the specific implementation includes: Corrected and optimized machining efficiency data is retrieved from the optimized machining process model, and corrected and optimized energy consumption data is retrieved from the energy consumption model. The retrieved machining efficiency and energy consumption data are weighted and summed to form an optimization function. This function comprehensively considers machining efficiency and energy consumption, reflecting the balance between the two. Weight coefficients are determined based on the priorities in the actual production scenario. Depending on the scenario, machining efficiency is given a higher weight, while energy consumption is given a lower weight. The optimal machining parameters are calculated based on the optimization function. This optimization function then constructs a multi-objective optimization function, aiming to find a set of Pareto optimal solutions. Each point in this solution set represents a trade-off between efficiency and energy consumption. This Pareto frontier provides the operator or higher-level control system with a range of optimal options, rather than just a single optimal combination. Within these Pareto optimal solutions, human decision-making is performed based on the most pressing needs, while intelligent selection is performed by the upper-level system.

[0032] After that, the corresponding control instructions are generated and converted into G-code format that can be recognized and executed by CNC machine tools. The instructions are then safety checked to ensure that the instructions will not cause machine tool overtravel, collision or other safety issues; the instruction execution module has a built-in human multimodal semantic understander and interactive instruction generation system, which can not only understand the operator's more complex intentions, but also combine these intentions with physical information neural network models to generate more accurate processing parameters and instructions. The system can reversely convert the generated G-code instructions into natural language descriptions that are easy for the operator to understand, and combine with the digital twin model for visual simulation, providing real-time interpretation of instruction execution and visual feedback of potential impacts, greatly enhancing the depth and efficiency of human-machine collaboration.

[0033] The control instructions that have passed security verification are sent to the control instruction execution system. The control instruction execution system transmits the instructions to multiple CNC machine tools through a distributed network interface to achieve factory-level collaborative control. Blockchain is used as the underlying architecture of the control instruction execution system. In order to achieve data sharing and preset, smart contracts are deployed on the blockchain to define and execute rules. The smart contract verifies the uploaded parameters according to the preset rules. The parameters that pass the verification will be added to the blockchain ledger and become part of the shared data; if the verification fails, the smart contract will refuse to store the data and feedback error information to the uploading user.

[0034] By constructing a control instruction execution module, this embodiment can accurately convert the optimized processing parameters into instructions executable by the machine tool, ensuring that the optimization strategy is effectively executed. The optimized processing parameters can significantly improve processing efficiency, reduce processing time and scrap rate. At the same time, stable processing parameters help to improve the processing quality of the workpiece, ensuring that indicators such as dimensional accuracy and surface roughness meet the requirements. Through a distributed network interface, it can achieve coordinated scheduling of multiple CNC machine tools, thereby improving the overall production efficiency and equipment utilization of the factory.

[0035] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

[0036] Example 2 The present application discloses a federated learning collaborative optimization method and system for energy storage battery safety control. Factory B manufactures automotive parts and needs to process large quantities of aluminum alloy engine cylinders efficiently and energy-efficiently. Traditional processing methods are difficult to simultaneously meet the production requirements of high efficiency, low energy consumption, and stable quality. Therefore, a method and system for automatic optimization of processing parameters for three-axis CNC machine tools is required. Figure 3 A module diagram of a processing parameter automatic optimization system for three-axis CNC machine tools. The system includes a data collection module, a digital twin module, a processing process model and energy consumption model module, an optimization algorithm module and a control instruction execution system module.

[0037] Furthermore, the data collection module collects machine tool and workpiece parameter data. This includes real-time sensor data collection of the three-axis CNC machine tool's current and voltage, tool wear, and workpiece dimensions, vibration frequency, deflection, and surface roughness during machining. The collected machine tool and workpiece parameter data are preprocessed to remove redundant information and noise.

[0038] Furthermore, a digital twin model of a three-axis CNC machine tool, using a physical information neural network, was constructed using the digital twin module to monitor and calculate machining efficiency and energy consumption in real time. A convolutional neural network algorithm was used to identify and remove outliers, extracting characteristic parameters related to machining efficiency and energy consumption, such as current, voltage, and tool wear status. The model was then trained using extensive historical data, adjusting the network weights and biases to construct the digital twin model. In subsequent training, the data was regularly updated and the model was retrained.

[0039] Furthermore, the machining process model and energy consumption model modules are used to construct a machining process model and an energy consumption model. Using the real-time processing data collected in the digital twin model as input variables and machining efficiency as output variables, a preliminary machining process model is constructed based on the cutting force model. Using the real-time energy consumption data as input variables, a preliminary energy consumption model is established. A data-driven modeling approach is used to train the energy consumption model. By adjusting the model parameters and fitting the actual energy consumption data, the model's accuracy is improved.

[0040] Furthermore, an optimization algorithm module was used to maximize machining efficiency and minimize energy consumption. A simulated annealing algorithm was selected as the optimization algorithm, and the established machining process model and energy consumption model were integrated into the algorithm. Using machining parameters such as cutting speed, feed rate, and depth of cut as decision variables, the optimization algorithm was run to obtain the optimal machining parameter combination that maximizes machining efficiency and minimizes energy consumption under the current working conditions.

[0041] Furthermore, the control instruction execution system module is used to construct an adaptive control instruction execution method and implement the optimal optimization parameter solution. A control instruction execution module is constructed based on the optimization function, generating control instructions and converting them into an instruction format that the machine tool can recognize. After a safety check, the instructions are sent to multiple machine tools in the workshop via a distributed network interface, achieving coordinated scheduling. The optimized processing parameters improve the machining efficiency of the engine cylinder block and reduce energy consumption, effectively improving the workshop's production efficiency and energy utilization efficiency, while ensuring the quality of the cylinder block processing and significantly reducing production costs.

[0042] The embodiment of the present application uses an automatic optimization system for processing parameters of three-axis CNC machine tools to perform modular integrated data management of the data collection module, digital twin module, processing process model and energy consumption model module, optimization algorithm module and control instruction execution system module, and comprehensive factory control, making more effective and reasonable decisions for the automatic optimization of the processing parameters of three-axis CNC machine tools.

[0043] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for automatic optimization of machining parameters for three-axis CNC machine tools, characterized in that: The following steps are involved: Collecting machine tool parameter data and workpiece parameter data, wherein the machine tool parameter data includes the current and voltage of the three-axis CNC machine tool and the tool wear status, and the workpiece parameter data includes the workpiece size, vibration frequency, deflection and surface roughness; Based on the machine tool parameter data and workpiece parameter data, a digital twin model of a three-axis CNC machine tool is constructed to provide real-time monitoring and feedback, and calculate processing efficiency and energy consumption; Constructing a CNC machine tool machining process model and an energy consumption model based on the machining efficiency and energy consumption, and using an optimization algorithm to maximize machining efficiency and minimize energy consumption, wherein the machining process model monitors the quality efficiency index of the machining process, and the energy consumption model monitors the energy consumption of the machining process; The optimization function is derived by taking the weighted sum of quality efficiency indicators and energy consumption characteristics, adaptively covering the entire factory control through the control instruction execution system, and realizing collaborative scheduling of multiple machine tools through a distributed network interface.

2. The automatic optimization method for machining parameters of a three-axis CNC machine tool according to claim 1, characterized in that: The process of collecting machine tool parameter data and workpiece parameter data includes: The current, voltage and tool wear status of the die cutting tool are collected as machine tool parameter data; the workpiece size, vibration frequency, deflection and surface roughness of the workpiece are collected as workpiece parameter data, and data preprocessing operations are performed.

3. The automatic optimization method for machining parameters of a three-axis CNC machine tool according to claim 1, characterized in that: The process of constructing a three-axis CNC machine tool digital twin model based on the machine tool parameter data and workpiece parameter data, performing real-time monitoring and feedback, and calculating processing efficiency and energy consumption includes: The collected multi-source data is fused again using deep learning algorithms to automatically identify and remove noise and outliers, extract characteristic parameters that have a key impact on processing efficiency and energy consumption, build a fusion data set, use a large amount of historical data to train the model, adjust the network weights and biases, and monitor the performance of the model in real time during the training process. As the machine tool operation and processing conditions change, new data is collected regularly to update and retrain the model.

4. The automatic optimization method for machining parameters of a three-axis CNC machine tool according to claim 1, characterized in that: The process of constructing a CNC machine tool machining process model and an energy consumption model based on the machining efficiency and energy consumption includes: The real-time collected and accumulated processing data are used to train the processing process model, so that the model can reflect the complex nonlinear processing efficiency relationship in the actual processing process; the collected input variables and corresponding energy consumption data in the actual processing process are used to fit the relationship between the actual energy consumption and each input variable.

5. The automatic optimization method for machining parameters of a three-axis CNC machine tool according to claim 1, characterized in that: The process of using the optimization algorithm to maximize processing efficiency and minimize energy consumption includes: The constructed machining process model and energy consumption model are integrated into the optimization algorithm. The machining parameters are used as decision variables. The optimization algorithm is run to obtain the combination that maximizes machining efficiency and minimizes energy consumption, and then it is analyzed and verified.

6. The method for automatic optimization of machining parameters for a three-axis CNC machine tool according to claim 1, characterized in that: The optimization function is derived by taking the weighted sum of quality efficiency indicators and energy consumption characteristics. The control instruction execution system adaptively covers comprehensive factory control and realizes multi-machine tool collaborative scheduling through a distributed network interface. The implementation process includes: The processing efficiency after correction and optimization of the processing model is retrieved, and the energy consumption data after correction and optimization of the energy consumption model is retrieved, and their weighted sum is taken. The weight coefficient is determined according to the priority in the actual production scenario to obtain the optimization function. The optimal processing parameters are calculated according to the optimization function, and the corresponding control instructions are generated.

7. An automatic optimization system for machining parameters of three-axis CNC machine tools, characterized in that: Includes the following modules: Data collection module: used to collect machine tool parameter data and workpiece parameter data; Digital twin module: monitors and feeds back machine tool parameter data and workpiece parameter data, performs real-time detection and feedback, and calculates processing efficiency and energy consumption; Process model and energy consumption model modules: reflect the complex nonlinear relationship between processing efficiency in the actual processing process and fit the relationship between actual energy consumption and various input variables; Optimization algorithm module: Use the optimization algorithm to maximize processing efficiency and minimize energy consumption, retrieve and perform weighted summation to obtain the optimization function; Control instruction execution system module: Build adaptive control instruction execution, execute the best optimization parameter plan, and transmit instructions to multiple CNC machine tools at the same time to achieve factory-level collaborative control.

Images