Metal cutting machining path planning system

Abstract

The invention relates to a metal cutting machining path planning system, and aims to optimize the efficiency and precision of a metal machining process through advanced technical means. The system comprises a plurality of functional modules: an image acquisition module captures a multi-angle high-resolution image of a to-be-processed metal workpiece; the three-dimensional reconstruction module reconstructs a three-dimensional model by using the images; the cutting simulation module simulates the three-dimensional model in a virtual environment and records stress and heat distribution conditions in the cutting process in real time; the intelligent segmentation module divides the machining process into a plurality of stages according to the stress and heat data; the comprehensive optimization module is combined with a genetic algorithm and a simulated annealing algorithm to optimize the cutting path, depth and feeding speed of each machining stage; the feedback adjusting module monitors stress and heat changes in actual machining, and when the stress and heat changes exceed threshold values, cutting parameters are automatically adjusted or machining is paused. According to the system, through comprehensive application of image processing, analog simulation and optimization algorithms, the cutting efficiency and the product quality are remarkably improved.

Description

Technical Field

[0001] The invention relates to the technical field of metal processing, and in particular to a metal cutting processing path planning system. Background Art

[0002] In the existing field of metal cutting processing, traditional path planning systems mainly rely on pre-set parameters and operator experience to determine cutting paths and parameters. These systems usually use basic computer-aided design and manufacturing software (CAD / CAM) to generate cutting paths, and these software usually only provide limited visual information processing capabilities, such as two-dimensional images or simplified three-dimensional model representations. Due to the lack of advanced image processing and data analysis technology, these systems often appear insufficient when dealing with complex workpiece shapes and material properties.

[0003] The main problem with existing technologies is that the cutting path is not accurate enough. In addition, existing systems usually do not integrate advanced algorithms to dynamically adjust cutting parameters, making it difficult to respond to material changes or abnormal conditions in the cutting process in real time, such as stress and heat exceeding safety thresholds. These limitations reduce processing efficiency, increase material waste and potential risk of mechanical failure.

[0004] Therefore, it is necessary to develop a new metal cutting process path planning system. Summary of the invention

[0005] The present application provides a metal cutting process path planning system to improve the efficiency and product quality of metal cutting processes.

[0006] The present application provides a metal cutting process path planning system, comprising:

[0007] An image acquisition module, used for capturing multi-angle high-resolution images of the metal workpiece to be processed from multiple angles;

[0008] A three-dimensional reconstruction module, used to reconstruct a three-dimensional model of the metal workpiece to be processed using the multi-angle high-resolution images;

[0009] The cutting simulation module simulates the cutting process of the reconstructed 3D model in a virtual environment and records the stress and heat distribution during the simulation in real time;

[0010] Intelligent segmentation module, which analyzes the stress and heat data obtained during the simulation process and divides the processing process into multiple stages, and the maximum stress and heat of each stage do not exceed the set safety threshold;

[0011] The comprehensive optimization module uses a hybrid optimization strategy combining genetic algorithm and simulated annealing to simultaneously optimize the cutting path, cutting depth and feed speed of each processing stage. The global search capability of the genetic algorithm is used to generate and optimize the initial solution, and the simulated annealing algorithm is used to perform a local fine search for the optimal solution of each generation to improve the cutting efficiency and ensure the processing accuracy of the final product.

[0012] The feedback adjustment module monitors changes in stress and heat during machining. If it detects that the monitored parameters exceed the preset limits, it adjusts the cutting parameters or pauses the machining to prevent damage.

[0013] Furthermore, the image acquisition module includes:

[0014] A plurality of high-resolution cameras with adjustable angles, wherein the high-resolution cameras can automatically adjust the focal length and shooting angle to capture an all-round image of the workpiece;

[0015] Light compensation unit, used to automatically adjust light intensity and direction when shooting at different angles to ensure consistent image quality.

[0016] Furthermore, the three-dimensional reconstruction module is specifically used for:

[0017] Use stereo matching technology to match feature points of high-resolution images acquired from multiple angles to obtain matching feature points;

[0018] Calculating the position difference of the matching feature points to determine the disparity information between different images;

[0019] Based on the determined parallax information, an accurate three-dimensional model of the metal workpiece to be processed is reconstructed.

[0020] Furthermore, the cutting simulation module is specifically used for:

[0021] importing the accurate 3D model obtained from the 3D reconstruction module into simulation software, which is configured with a simulation program for performing cutting operations and allows setting of initial cutting parameters, including cutting speed, feed rate, cutting depth, and tool type;

[0022] Run the simulation program through the simulation software to simulate the cutting operation in a controlled virtual environment, and use physical and thermodynamic models to calculate the stress distribution and heat generation on the contact interface between the workpiece and the tool in real time;

[0023] Record stress and heat data generated during cutting.

[0024] Furthermore, the feedback adjustment module includes:

[0025] Multi-sensor fusion unit for comprehensive analysis of current measurement data from force sensors, temperature sensors, and vibration sensors;

[0026] The predictive control unit predicts the processing status in the future based on historical data and current measurement data and makes adjustments in advance.

[0027] Furthermore, the intelligent segmentation module is specifically used for:

[0028] According to the following formulas 1 and 2, the stress σ(t) and heat Q(t) data collected from the cutting simulation module are normalized, and the data range is unified to [0, 1] to obtain the normalized stress data σ norm (t) and normalized heat data Q norm (t):

[0029]

[0030]

[0031] Where t represents time; σ min Indicates the minimum stress value in the collected data; σ max Indicates the maximum stress value in the collected data; Q min Indicates the minimum heat value in the collected data; Q max Indicates the maximum heat value in the collected data;

[0032] According to the following formula 3 and formula 4, calculate the stress threshold σ of each processing point thresh (t) and the thermal threshold Q thresh (t):

[0033] σ thresh (t) = κ·(σ norm (t)·exp(-λ·t)+(1-exp(-λ·t))·max(σ norm (t))) (3)

[0034] Q thresh (t) = κ·(Q norm (t)·exp(-λ·t)+(1-exp(-λ·t))·max(Q norm (t))) (4)

[0035] Among them, λ is the attenuation coefficient; κ is the amplification coefficient; σ norm (t) represents normalized stress data; Q norm (t) represents normalized heat data;

[0036] If the stress σ(t) of the current processing point exceeds the stress threshold σ of the current processing pointthresh (t), or the heat of the current processing point Q(t) exceeds the heat threshold Q of the current processing point thresh (t), then mark the point as a segmentation point.

[0037] Furthermore, the comprehensive optimization module is specifically used for:

[0038] Step P101: Initializing a population, wherein each population member represents a potential cutting parameter combination, including cutting path, cutting depth and feed rate; each cutting parameter combination takes into account the physical limitations of the machine and the predetermined processing quality standard;

[0039] Step P102: Performing performance evaluation on each individual in the initial population based on a predefined multi-objective fitness function; wherein the fitness function comprehensively considers cutting efficiency, processing quality, resource utilization and cost control;

[0040] Step P103: Execute the selection process of the genetic algorithm, use non-dominated sorting, sort the individuals according to their performance on each optimization goal, and select individuals with excellent performance to enter the next generation population;

[0041] Step P104: Perform crossover and mutation operations on the selected population, combine simulated annealing algorithm to perform local fine search, adjust the parameters of the individuals after crossover to avoid local optimality, and enhance exploration ability;

[0042] Step P105: Repeat steps P102 to P104 until a predetermined number of iterations is reached or a specific performance indicator is met to ensure that the most optimized cutting path and parameter settings are obtained, thereby improving cutting efficiency and ensuring the accuracy and quality of the processed products.

[0043] Furthermore, the predefined multi-objective fitness function adopts the following formula 5:

[0044]

[0045] Where F(x) represents the fitness score; x represents a population member, represents a cutting parameter combination; T(x) represents the cutting time under a given parameter combination; T ref is the reference cutting time, used for standardization; Q(x) represents the machining quality score; Q max is the highest quality score under ideal conditions; R(x) represents resource utilization efficiency; R opt is the optimal resource utilization efficiency; C(x) represents the processing cost; C ref is the reference cost; α, β, γ, δ are weight factors.

[0046] Furthermore, the comprehensive optimization module is also specifically used for:

[0047] In the new population generated by performing crossover and mutation operations, an initial temperature T is defined for each individual x 0 ; Among them, the initial temperature is inversely proportional to the fitness function value of the individual. The lower the fitness, the higher the initial temperature to increase the exploration probability of the search space;

[0048] For each individual, the simulated annealing algorithm is used to iteratively update its cutting parameter combination; wherein, in each iteration k, the current parameter is randomly perturbed according to the following formula 6:

[0049]

[0050] Among them, p k+1 represents the cutting parameter combination at iteration number k+1; p k represents the cutting parameter combination at iteration number k; Δp is the disturbance intensity; rand(-1, 1) is used to generate random numbers in the range of [-1, 1]; τ is the time constant for controlling disturbance reduction;

[0051] Using the Metropolis criterion, if the newly generated cutting parameter combination p k+1 The corresponding fitness function F(p k+1 ) is better than the current parameter p k The fitness F(p k ), then the new parameters are accepted; otherwise, the new parameters are accepted with probability P calculated according to the following formula 7:

[0052]

[0053] Where F represents the multi-objective fitness function; T k represents the temperature at the current iteration number k, which is calculated by the following formula 8:

[0054]

[0055] Where ξ is the cooling rate;

[0056] After each iteration, the system temperature is reduced and T is updated exponentially according to Equation 8. k ;

[0057] Repeat the iterative optimization process until the termination condition is met, wherein the termination condition includes T k falls below a certain threshold or reaches a predetermined number of iterations.

[0058] Furthermore, the crossover operation performed in step P104 specifically includes the following steps:

[0059] Select two parent individuals from the current population, each individual is defined by a set of cutting parameters, including cutting path, cutting depth and feed rate;

[0060] Randomly determine two points in the parameter set of each parent individual as crossover points, which define the boundaries of the parameter segment to be exchanged;

[0061] In two parent individuals, the parameter segment between the first intersection point and the second intersection point is exchanged, wherein the parameter segment includes a cutting path, a cutting depth and a feed speed within a selected interval;

[0062] Through the exchange of the new parameter set, two new offspring individuals are constructed, where each offspring individual inherits the characteristics of two different parent generations, forming a new cutting parameter combination;

[0063] Verification operations are performed to ensure that the cutting parameters in the exchanged offspring individuals meet the physical limitations of mechanical operations and predetermined processing quality standards, and are appropriately adjusted based on the verification results to adapt to the requirements of the cutting equipment.

[0064] The beneficial effects of the present application mainly include: (1) By using multi-angle high-resolution image acquisition and three-dimensional reconstruction modules, the system is able to create an accurate three-dimensional model of the workpiece. This not only improves the accuracy of cutting path planning, but also makes the cutting process more consistent with the physical characteristics of the actual workpiece, thereby improving processing efficiency and reducing material waste. (2) The combination of the cutting simulation module and the feedback adjustment module allows the system to record and analyze stress and heat distribution in real time during the processing process. This enables the system to adjust the cutting parameters or suspend processing in a timely manner when any parameters exceeding the preset safety threshold are detected, effectively preventing potential mechanical damage and processing defects. (3) The introduction of the intelligent segmentation module allows the system to dynamically divide the processing process into multiple stages based on real-time data and set the optimal cutting parameters, such as cutting depth and feed speed, for each stage. This staged optimization method significantly improves the efficiency of the entire processing process and the quality of the finished product. (4) By combining the global search capability of the genetic algorithm with the local fine search capability of the simulated annealing algorithm, the comprehensive optimization module can quickly find high-quality solutions in a wide range of solution spaces. This hybrid optimization strategy not only improves the search efficiency, but also ensures the optimization of the final processing path and parameters, further improving the accuracy of the operation and the effective use of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a schematic diagram of a metal cutting process path planning system provided in the first embodiment of the present application. DETAILED DESCRIPTION

[0066] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0067] The first embodiment of the present application provides a metal cutting process path planning system. Figure 1 , which is a schematic diagram of the first embodiment of the present application. Figure 1 A metal cutting process path planning system is provided in detail for the first embodiment of the present application.

[0068] The metal cutting machining path planning system includes an image acquisition module 101 , a three-dimensional reconstruction module 102 , a cutting simulation module 103 , an intelligent segmentation module 104 , a comprehensive optimization module 105 and a feedback adjustment module 106 .

[0069] The image acquisition module 101 is used to capture multi-angle high-resolution images of the metal workpiece to be processed from multiple angles.

[0070] In the metal cutting process path planning system, the image acquisition module 101 plays a vital role. It is responsible for acquiring multi-angle high-resolution images of the metal workpiece to be processed from multiple angles.

[0071] The image acquisition module 101 includes a set of high-resolution cameras arranged around a predetermined workpiece. Each camera is equipped with a lens capable of wide-angle shooting to ensure that different viewing angles of the workpiece can be covered. The choice of camera and the configuration of the lens are optimized according to the size and complexity of the workpiece to ensure that each captured image can provide the maximum amount of surface details.

[0072] In order to control the image quality and acquisition process, the image acquisition module 101 also includes a centralized control system, which is responsible for synchronizing the triggering timing of each camera to ensure that the image is captured at the best moment. In addition, the control system can also adjust the focus and exposure settings of each camera to adapt to different ambient light conditions and the reflective properties of the material of the workpiece.

[0073] In terms of software, the image acquisition module 101 uses advanced image processing algorithms to pre-process the acquired images. These pre-processing steps include image denoising, contrast enhancement and sharpening, with the goal of improving the image quality and providing the 3D reconstruction module 102 with input data that is as clear as possible.

[0074] In addition, the image acquisition module 101 is also designed with an automatic calibration procedure, which can automatically adjust the angle and distance of the camera according to the position of the workpiece to ensure that all necessary viewing angles are fully covered. This automatic calibration mechanism greatly simplifies the operation process and improves the user-friendliness and efficiency of the system.

[0075] Furthermore, the image acquisition module comprises:

[0076] A plurality of high-resolution cameras with adjustable angles, wherein the high-resolution cameras can automatically adjust the focal length and shooting angle to capture an all-round image of the workpiece;

[0077] Light compensation unit, used to automatically adjust light intensity and direction when shooting at different angles to ensure consistent image quality.

[0078] In the image acquisition module of this metal cutting machining path planning system, in order to achieve high-quality image capture, the module is equipped with multiple high-resolution cameras with adjustable angles. These cameras are designed and configured to fully cover all viewing angles of the workpiece to be processed in order to obtain sufficient information for subsequent 3D reconstruction and cutting process simulation. Specifically, the camera can not only automatically adjust the focal length to adapt to different shooting distances, but also adjust the shooting angle to ensure detailed capture of the workpiece from multiple directions.

[0079] Each high-resolution camera is equipped with an advanced control system that allows it to automatically adjust its parameters according to the size and complexity of the workpiece. This includes adjusting the focal length, which automatically changes according to the distance of the workpiece from the camera to ensure that the image remains clear at all times; and adjusting the shooting angle to ensure that the detailed features of the workpiece can be captured from the best viewing angle.

[0080] To further ensure image quality, the image acquisition module also includes a light compensation unit. The function of this unit is to automatically adjust the intensity and direction of the light at different shooting angles. This is particularly important because different angles may affect the quality of the image due to shadows and light reflections. The light compensation unit uses a dynamically adjustable light source (such as an LED light) to automatically adjust the projection direction and intensity of the light according to the current camera angle and position to eliminate shadows and reflections, thereby ensuring consistent image quality regardless of the lighting conditions.

[0081] The three-dimensional reconstruction module 102 is used to reconstruct a three-dimensional model of the metal workpiece to be processed using the multi-angle high-resolution images.

[0082] In the metal cutting machining path planning system, the three-dimensional reconstruction module 102 is a key component, which is specially designed to convert the multi-angle high-resolution images collected by the image acquisition module 101 into an accurate three-dimensional model.

[0083] First, the 3D reconstruction module 102 receives multiple high-resolution images provided by the image acquisition module 101, which show the metal workpiece to be processed from different angles. The software inside the module first performs image alignment, identifies and matches the common feature points in these images, which is achieved through advanced image processing algorithms, such as feature matching and stereo vision algorithms. Through these common feature points, the software can calculate the relative position and angle between each image, providing a data basis for constructing accurate 3D spatial relationships.

[0084] Subsequently, the 3D reconstruction process uses multi-view geometry techniques to generate a 3D model of the workpiece. This process involves projecting points from the 2D image back into 3D space and using geometric and algebraic methods to solve the positions of these points in 3D space. Specific techniques include, but are not limited to, triangulation and spatial reconstruction algorithms that can reconstruct a high-precision 3D surface model using image information captured from multiple viewpoints.

[0085] In addition, the 3D reconstruction module 102 also includes optimization algorithms to improve the accuracy and surface quality of the model. These optimization algorithms can reduce noise and errors in the reconstruction process, such as improving the surface texture and geometric details of the model through smoothing and detail enhancement techniques. After the 3D model is completed, it will be transmitted to the cutting simulation module 103 for further processing simulation and analysis.

[0086] Furthermore, the three-dimensional reconstruction module is specifically used for:

[0087] Use stereo matching technology to match feature points of high-resolution images acquired from multiple angles to obtain matching feature points;

[0088] Calculating the position difference of the matching feature points to determine the disparity information between different images;

[0089] Based on the determined parallax information, an accurate three-dimensional model of the metal workpiece to be processed is reconstructed.

[0090] In the metal cutting machining path planning system, the core task of the 3D reconstruction module is to convert the multi-angle high-resolution images provided by the image acquisition module into an accurate 3D model. This module uses stereo matching technology to perform this complex conversion process to ensure that the most accurate 3D information is extracted from the visual data.

[0091] First, the 3D reconstruction module receives images captured by high-resolution cameras with multiple adjustable angles. These images show the metal workpiece to be processed from different perspectives and contain a large amount of visual information. The software in the module first processes these images to identify and match feature points between images. Feature point matching is achieved through an efficient image processing algorithm that can find the same physical markers in different images, such as corners, edges or specific geometric figures on the workpiece.

[0092] After matching the feature points, the module calculates the position differences of these points in each image. The key to this step is to determine the disparity information, which refers to the change in position when the same point is viewed from different camera angles. By accurately measuring these position differences, the module can infer the relative position of each feature point in three-dimensional space.

[0093] The final step is to reconstruct a complete 3D model of the metal workpiece to be machined based on this determined parallax information using complex 3D modeling techniques. This includes using the calculated 3D coordinates of each feature point, combined with all parallax data, to accurately simulate the 3D shape of the workpiece through a geometric construction algorithm. The completed 3D model will contain all the geometric details of the workpiece and can be further used by the cutting simulation module to simulate the machining process.

[0094] The cutting simulation module 103 performs cutting processing simulation on the reconstructed three-dimensional model in a virtual environment, and records the stress and heat distribution during the simulation process in real time.

[0095] The cutting simulation module 103 is a key component of the metal cutting process path planning system, which is responsible for simulating the cutting process of the 3D model of the metal workpiece obtained from the 3D reconstruction module 102 in a virtual environment. Through this module, the system can simulate the stress and heat distribution in the actual cutting process, thereby optimizing and controlling the processing process.

[0096] Specifically, the cutting simulation module 103 first receives the metal workpiece model accurately reconstructed by the 3D reconstruction module. This model not only includes the geometric shape of the workpiece, but also accurately reflects the physical properties and material characteristics of the workpiece, which are indispensable data in the simulation cutting process. Subsequently, the module configures the simulation environment in the control software by setting the virtual cutting tool and determining the cutting parameters (such as cutting speed, depth and feed rate).

[0097] During the simulation, the module uses advanced computational methods to simulate the interaction between the cutting tool and the workpiece. This includes calculating the mechanical behavior during the cutting process, such as the magnitude and distribution of cutting forces, and the heat distribution generated by material removal. In order to accurately simulate these dynamic processes, the module uses the finite element method (FEM) or similar advanced numerical simulation techniques that are capable of handling complex physical and mechanical interactions.

[0098] The module also has a sensor data simulation function, which means that it can record stress and heat data in real time during the simulation process according to the arrangement of virtual sensors. This data is then transmitted to the intelligent segmentation module 104 for further analysis and adjustment of the processing process to ensure that the stress and heat at each processing stage do not exceed the safety threshold.

[0099] Furthermore, the cutting simulation module is specifically used for:

[0100] importing the accurate 3D model obtained from the 3D reconstruction module into simulation software, which is configured with a simulation program for performing cutting operations and allows setting of initial cutting parameters, including cutting speed, feed rate, cutting depth, and tool type;

[0101] Run the simulation program through the simulation software to simulate the cutting operation in a controlled virtual environment, and use physical and thermodynamic models to calculate the stress distribution and heat generation on the contact interface between the workpiece and the tool in real time;

[0102] Record stress and heat data generated during cutting.

[0103] The cutting simulation module is a key component of the metal cutting process path planning system. It is specially used to simulate cutting operations in a controlled virtual environment to predict various situations that may be encountered during actual processing. The main function of this module is to import the precise 3D model provided by the 3D reconstruction module into the simulation software equipped with a special simulation program, and perform detailed cutting operation simulation on this basis.

[0104] First, the operation of this module begins by importing an accurate 3D model obtained from the 3D reconstruction module into the simulation software. This step is completed through a dedicated data interface to ensure that the data format of the model fully matches the requirements of the simulation software. This 3D model reflects the geometric and physical characteristics of the workpiece to be processed in detail, providing the necessary basis for the subsequent simulation.

[0105] Once the model is successfully imported, the cutting simulation module allows the user to set the initial cutting parameters in the simulation software. These parameters include cutting speed, feed rate, cutting depth and tool type. The settings of these parameters are adjusted according to the specific processing requirements and the characteristics of the workpiece material to ensure the accuracy and practicality of the simulation results. Users can easily enter these parameters through the graphical user interface and can also adjust them as needed to optimize the simulation process.

[0106] Next, the cutting simulation module simulates the cutting operation by running the configured simulation program. During this process, the simulation software uses complex physical and thermodynamic models to calculate the stress distribution and heat generated at the contact interface between the workpiece and the tool in real time. These calculations take into account a variety of factors, including the cutting resistance of the material, the wear state of the tool, the influence of cutting speed and feed rate, etc., all of which are accurately simulated in a controlled virtual environment.

[0107] Finally, all stress and heat data generated during the simulation are recorded. This data is not only used to analyze the effects and potential problems of the cutting operation, but can also be used to further optimize the machining parameters and improve the efficiency and quality of the actual machining. The recorded data can be provided to the user in various formats through the data output interface for in-depth analysis.

[0108] The intelligent segmentation module 104 analyzes the stress and heat data obtained during the simulation process and divides the processing process into multiple stages, and the maximum stress and heat of each stage do not exceed the set safety threshold.

[0109] The intelligent segmentation module 104 plays a core role in the metal cutting process path planning system. It is responsible for processing the stress and heat data from the cutting simulation module 103 so as to intelligently divide the entire process into multiple stages. The main function of this module is to ensure that the stress and heat distribution does not exceed the pre-set safety threshold in each stage of the process, thereby optimizing the entire cutting process, improving the processing efficiency and ensuring the safety of the operation.

[0110] The intelligent segmentation module 104 first receives real-time simulation data, including stress and heat distribution calculated at each simulation time step. The module contains a data processing system that uses advanced data analysis techniques, such as machine learning and pattern recognition algorithms, to analyze this data. Through these techniques, the module is able to identify key trends and abnormal patterns in the data, which is an important basis for dividing the processing stages.

[0111] After determining the basic framework of each processing stage, the intelligent segmentation module 104 will use a series of optimization algorithms to fine-tune the boundaries of each stage. This process involves dynamically evaluating the stress and heat peaks in each stage and adjusting the corresponding cutting parameters, such as cutting speed and feed rate, to ensure that these peaks do not exceed the preset safety threshold. The module can also automatically adjust the cutting path to avoid situations that may cause excessive mechanical stress or heat concentration.

[0112] In addition, the intelligent segmentation module 104 is equipped with a user interface that allows the operator to manually adjust the division of cutting stages and related parameters according to actual conditions. The interface provides an intuitive graphical representation of the stress and heat distribution of each processing stage, as well as any areas that exceed safety thresholds.

[0113] Furthermore, the intelligent segmentation module is specifically used for:

[0114] According to the following formulas 1 and 2, the stress σ(t) and heat Q(t) data collected from the cutting simulation module are normalized, and the data range is unified to [0, 1] to obtain the normalized stress data σ norm (t) and normalized heat data Q norm (t):

[0115]

[0116]

[0117] Where t represents time; σ min Indicates the minimum stress value in the collected data; σ max Indicates the maximum stress value in the collected data; Q min Indicates the minimum heat value in the collected data; Q max Indicates the maximum heat value in the collected data;

[0118] According to the following formula 3 and formula 4, calculate the stress threshold σ of each processing point thresh (t) and the thermal threshold Q thresh (t):

[0119] σ thresh (t) = κ·(σ norm (t)·exp(-λ·t)+(1-exp(-λ·t))·max(σ norm (t))) (3)

[0120] Q thresh (t) = κ·(Q norm (t)·exp(-λ·t)+(1-exp(-λ·t))·max(Q norm(t))) (4)

[0121] Among them, λ is the attenuation coefficient; κ is the amplification coefficient; σ norm (t) represents normalized stress data; Q norm (t) represents normalized heat data;

[0122] If the stress σ(t) of the current processing point exceeds the stress threshold σ of the current processing point thresh (t), or the heat of the current processing point Q(t) exceeds the heat threshold Q of the current processing point thresh (t), then mark the point as a segmentation point.

[0123] In the metal cutting machining path planning system, the intelligent segmentation module undertakes the key task of finely managing the stress and heat data during the machining process. The module uses a series of formulas to normalize and calculate thresholds, thereby effectively monitoring and adjusting the machining operations to ensure the stability and safety of the machining process.

[0124] First, the module uses formula 1 and formula 2 to normalize the stress σ(t) and heat Q(t) data collected by the cutting simulation module. The purpose of normalization is to unify the range of these data to [0, 1], making data processing more unified and convenient. Here t represents time, and the specific formula is:

[0125]

[0126]

[0127] In these two formulas, σ min and σ max Respectively represent the minimum and maximum values ​​of the collected stress data; Q min and Q max It also represents the minimum and maximum values ​​of the collected heat data. t represents time, which is the index of the variable and indicates the specific time of data collection.

[0128] Next, the intelligent segmentation module calculates the stress threshold σ for each processing point using Formula 3 and Formula 4 thresh (t) and the thermal threshold Q thresh (t), these two thresholds are used to determine whether it is necessary to perform operation adjustment or segmentation at a certain point. The specific formula is as follows:

[0129] σ thresh (t) = κ·(σ norm (t)·exp(-λ·t)+(1-exp(-λ·t))·max(σ norm (t))) (3)

[0130] Qthresh (t) = κ·(Q norm (t)·exp(-λ·t)+(1-exp(-λ·t))·max(Q norm (t))) (4)

[0131] In the above formula, λ is the attenuation coefficient, which controls the influence of time so that early abnormal data will not have too much impact on subsequent calculations. κ is the amplification factor, which is used to adjust the sensitivity of the threshold. This design is to allow the system to flexibly adjust when facing changing processing conditions.

[0132] Finally, if the stress σ(t) at any time t exceeds the stress threshold σ thresh (t), or the heat Q(t) exceeds the heat threshold Q thresh (t), the intelligent segmentation module will mark the processing point at that moment as a segmentation point for further processing or adjustment. These thresholds are obtained through experimental data or directly set based on expert knowledge.

[0133] The comprehensive optimization module 105 adopts a hybrid optimization strategy combining genetic algorithm and simulated annealing to simultaneously optimize the cutting path, cutting depth and feed speed of each processing stage; wherein, the global search capability of the genetic algorithm is used to generate and optimize the initial solution, and the simulated annealing algorithm is used to perform a local fine search for the optimal solution of each generation to improve the cutting efficiency and ensure the processing accuracy of the final product.

[0134] The comprehensive optimization module 105 is one of the core components of the metal cutting process planning system, which is responsible for applying advanced algorithmic strategies to optimize the entire cutting process. This module combines genetic algorithms and simulated annealing algorithms to optimize cutting paths, depths and feed rates at both global and local levels. The design and functional implementation of this module aims to improve the efficiency of the entire cutting process and the processing accuracy of the final product by precisely adjusting each processing stage.

[0135] First, the comprehensive optimization module 105 uses the powerful global search capability of the genetic algorithm to generate an initial solution. In this process, the module creates a population, and each individual in the population represents a set of possible cutting parameter configurations. These parameter configurations are randomly generated according to the specific requirements of the cutting process, including the selection of cutting paths, the setting of cutting depths and feed rates. The genetic algorithm iteratively optimizes these solutions by simulating the process of natural selection - including crossover, mutation and selection - to continuously improve the quality of the overall solution.

[0136] After obtaining a batch of relatively good solutions through the genetic algorithm, the comprehensive optimization module 105 then uses the simulated annealing algorithm to perform a local fine search. The simulated annealing algorithm is suitable for further refining the best solution obtained by the genetic algorithm because it can effectively avoid the solution from falling into the local optimum. This algorithm controls the search process by the temperature drop during the simulated annealing process, gradually reduces the search range of the solution and accurately adjusts the parameters, and finally finds the true optimal solution.

[0137] In addition, the comprehensive optimization module 105 also includes a data processing system that can receive and analyze data from the cutting simulation module 103 and the intelligent segmentation module 104 in real time. These data include stress and heat distribution during the cutting process, as well as the cutting efficiency of each processing stage. By monitoring these key performance indicators in real time, the module can dynamically adjust the cutting parameters to ensure that any situation that exceeds the preset threshold during the processing process is responded to and adjusted in a timely manner.

[0138] Furthermore, the comprehensive optimization module is specifically used for:

[0139] Step P101: Initializing a population, wherein each population member represents a potential cutting parameter combination, including cutting path, cutting depth and feed rate; each cutting parameter combination takes into account the physical limitations of the machine and the predetermined processing quality standard;

[0140] Step P102: Performing performance evaluation on each individual in the initial population based on a predefined multi-objective fitness function; wherein the fitness function comprehensively considers cutting efficiency, processing quality, resource utilization and cost control;

[0141] Step P103: Execute the selection process of the genetic algorithm, use non-dominated sorting, sort the individuals according to their performance on each optimization goal, and select individuals with excellent performance to enter the next generation population;

[0142] Step P104: Perform crossover and mutation operations on the selected population, combine simulated annealing algorithm to perform local fine search, adjust the parameters of the individuals after crossover to avoid local optimality, and enhance exploration ability;

[0143] Step P105: Repeat steps P102 to P104 until a predetermined number of iterations is reached or a specific performance indicator is met to ensure that the most optimized cutting path and parameter settings are obtained, thereby improving cutting efficiency and ensuring the accuracy and quality of the processed products.

[0144] The comprehensive optimization module plays a core role in the metal cutting process path planning system. It uses a combination of genetic algorithm and simulated annealing algorithm to optimize the cutting parameters to ensure the efficiency of the processing process and the quality of the product. The workflow of this module is divided into five main steps. These steps and their specific implementation methods will be explained in detail below.

[0145] First, step P101 involves the initialization of the population. In this step, the module creates a population, each of which represents a potential combination of cutting parameters, including cutting path, cutting depth and feed rate. These parameter combinations are carefully designed to meet the physical limitations of the machine and the predetermined machining quality standards. The size of the population and the initial setting of the parameters are determined according to the actual machining requirements and the capabilities of the machine.

[0146] Next, step P102 evaluates the performance of each individual in the initial population. This evaluation is performed using a predefined multi-objective fitness function that takes into account factors such as cutting efficiency, processing quality, resource utilization, and cost control. The calculation results of the fitness function are used to measure the performance of each individual and provide a basis for subsequent genetic operations.

[0147] Step P103 is the selection process of the genetic algorithm. In this step, the non-dominated sorting method is used to sort the individuals in the population according to their performance on various optimization objectives. This sorting helps determine which individuals should be retained and enter the next generation of the population, thereby ensuring that excellent genes can be passed on.

[0148] Step P104 involves performing crossover and mutation operations on the selected population. In addition, in order to enhance the exploration capability and avoid the solution falling into the local optimum, this step also combines the simulated annealing algorithm to perform local fine search on the individual parameters after crossover. This dual optimization strategy helps the system find a balance between global search and local fine adjustment, and increases the probability of finding the optimal solution.

[0149] Finally, step P105 is to repeat the above steps (P102 to P104) until a predetermined number of iterations is reached or a specific performance index is met. This process ensures that the system can be continuously optimized until the most suitable cutting path and parameter settings are found.

[0150] Furthermore, the crossover operation performed in step P104 specifically includes the following steps:

[0151] Select two parent individuals from the current population, each individual is defined by a set of cutting parameters, including cutting path, cutting depth and feed rate;

[0152] Randomly determine two points in the parameter set of each parent individual as crossover points, which define the boundaries of the parameter segment to be exchanged;

[0153] In two parent individuals, the parameter segment between the first intersection point and the second intersection point is exchanged, wherein the parameter segment includes a cutting path, a cutting depth and a feed speed within a selected interval;

[0154] Through the exchange of the new parameter set, two new offspring individuals are constructed, where each offspring individual inherits the characteristics of two different parent generations, forming a new cutting parameter combination;

[0155] Verification operations are performed to ensure that the cutting parameters in the exchanged offspring individuals meet the physical limitations of mechanical operations and predetermined processing quality standards, and are appropriately adjusted based on the verification results to adapt to the requirements of the cutting equipment.

[0156] In the metal cutting machining path planning system, the comprehensive optimization module generates new population members by performing crossover operations in the genetic algorithm to optimize the cutting parameter combination. This process imitates genetic crossover in natural selection and aims to improve cutting efficiency and machining quality while reducing resource consumption and cost. The following are the detailed implementation steps of the crossover operation:

[0157] First, the system selects two parent individuals from the current population. Each individual is defined by a specific set of cutting parameters, including cutting path, cutting depth and feed rate. These parameters determine the efficiency and quality of the machining process. The selection of two parents for crossover is based on their fitness scores, and individuals with high fitness are usually selected in the hope that their excellent traits can be passed on to the offspring.

[0158] After selecting the parent individuals, the system randomly determines two points in the parameter set of each parent individual as crossover points. These two crossover points define the boundaries of the parameter segment to be exchanged. For example, if the parameter set of a parent individual consists of 10 parameters, the 3rd and 7th parameters may be randomly selected as crossover points.

[0159] After the intersection point is determined, the system exchanges the parameter segments between the first intersection point and the second intersection point in the two parent individuals. This includes all parameters such as cutting path, cutting depth and feed rate within the selected interval. The result of this operation is two new child individuals, each of which inherits the parameter characteristics from two different parents.

[0160] The new parameter set obtained by parameter exchange is used to construct two new offspring individuals. These new individuals theoretically combine the advantages of the original parent individuals and may show better performance than any parent. This is the core of genetic algorithms in seeking optimization solutions through crossover and recombination.

[0161] After the crossover operation is completed, the system performs a verification operation to ensure that the cutting parameters in the exchanged offspring individuals not only meet the physical limitations of the mechanical operation, but also meet the predetermined processing quality standards. This step is necessary because the crossover operation may produce unrealistic or inefficient parameter combinations. If the resulting parameters do not meet the equipment or processing requirements, the system will make appropriate adjustments. Adjustments may include fine-tuning the cutting parameters, or in extreme cases, discarding unsuitable offspring individuals.

[0162] Through this series of detailed operation steps, the metal cutting processing path planning system can effectively apply genetic algorithms to optimize cutting parameters, improve production efficiency, reduce costs, and ensure that the processing process meets quality standards.

[0163] Furthermore, the predefined multi-objective fitness function adopts the following formula 5:

[0164]

[0165] Where F(x) represents the fitness score; x represents a population member, represents a cutting parameter combination; T(x) represents the cutting time under a given parameter combination; T ref is the reference cutting time, used for standardization; Q(x) represents the machining quality score; Q max is the highest quality score under ideal conditions; H(x) represents resource utilization efficiency; R opt is the optimal resource utilization efficiency; C(x) represents the processing cost; C ref is the reference cost; α, β, γ, δ are weight factors.

[0166] In the metal cutting process path planning system, the predefined multi-objective fitness function is used to evaluate the effectiveness and efficiency of each population member, that is, the cutting parameter combination. The purpose of this function design is to comprehensively consider the four key factors of cutting time, processing quality, resource utilization efficiency and processing cost to ensure that the selected parameter combination can maximize production efficiency and minimize cost.

[0167] Formula F(x) is used to calculate the fitness score for a given cutting parameter combination x. It is calculated based on the weighted sum of the following key performance indicators:

[0168] 1. T(x) represents the cutting time under a given parameter combination, which reflects the length of time required to complete a certain amount of work. The smaller this indicator is, the higher the production efficiency is. For standardization, the cutting time T(x) is referenced by the cutting time T ref Normalized, the calculation formula is The exponential function is used here to emphasize the importance of cutting time in fitness evaluation. The shorter the time, the greater the contribution of this item to fitness. ref Obtained through experimental data, or set directly based on expert knowledge.

[0169] Cutting time is the time required to complete a certain task using a specific combination of cutting parameters. This usually includes cutting speed, feed rate and cutting depth. For example, suppose there is a task to cut a metal rod with a length of 100mm, using a cutting speed of 50mm / s, a feed rate of 0.5mm / rev and a cutting depth of 2mm. Assume that the effective cutting length of each round-trip cut is 95mm (due to the process of cutting in and out). The cutting time can be calculated by dividing the total length by the effective length of each cut, and then multiplying it by the time required for a single cut. If each round trip (cutting in both directions) is considered as one cut, then the cutting time T(x) will be (100 / 95)×2×(95 / 50) seconds.

[0170] 2. Q(x) represents the processing quality score, which is an indicator to measure the quality of processed products. The closer this score is to the highest quality score Q max , indicating that the processing quality is better. The processing quality is calculated using a logarithmic function This approach provides greater sensitivity at lower quality scores, with diminishing gains as quality increases. max Obtained through experimental data, or set directly based on expert knowledge.

[0171] The machining quality score can be based on a comprehensive assessment of multiple factors such as surface roughness, dimensional accuracy and shape tolerance. For example, if the measured surface roughness of the workpiece is 0.8 microns when the cutting parameters are set to a certain speed and feed rate, and the optimal surface roughness is 0.5 microns, the quality score can be given based on the ratio of the actual roughness to the optimal value. If the highest quality score is defined as 100 points, then Q(x) can be 100×(0.5 / 0.8).

[0172] 3. R(x) represents resource utilization efficiency, which is different from the optimal resource utilization efficiency R opt The square root of the ratio Used to evaluate the efficiency of resource use. The square root is used here to reduce the excessive impact of high efficiency and maintain the balance of the evaluation.

[0173] Resource utilization efficiency usually refers to the comprehensive utilization efficiency of materials, energy and time in the processing process. For example, if a parameter combination allows the task to be completed with less electricity and raw materials, the combination has high resource utilization efficiency. Specifically, if the energy consumption of a certain combination is 4 kWh, and the average energy consumption of similar tasks is 5 kWh, the resource utilization efficiency R(x) can be expressed as 5 / 4 or a corresponding percentage. opt It is the optimal resource utilization efficiency, obtained through experimental data or set directly based on expert knowledge.

[0174] 4. C(x) represents the processing cost, which is calculated by referring to the cost C ref To evaluate the efficiency of the cost, the calculation method is The result of this calculation will be subtracted from the total fitness to indicate that the lower the cost, the higher the fitness.

[0175] The processing cost includes material cost, energy cost, labor cost, etc. For example, if the material cost of processing a component is 10 yuan, the energy cost is 2 yuan, and the labor cost is 8 yuan, then the total cost C(x) is 20 yuan. If the reference cost (i.e., the budget or industry standard cost) is 25 yuan, the ratio of the actual cost to the reference cost can indicate the cost efficiency.

[0176] Finally, the weight factors α, β, γ, and δ are associated with the above four evaluation indicators, respectively, and are used to adjust the influence of each indicator in the fitness function. The setting of these weight factors varies based on the specific processing conditions and optimization goals.

[0177] Furthermore, the comprehensive optimization module is also specifically used for:

[0178] In the new population generated by performing crossover and mutation operations, an initial temperature T is defined for each individual x 0 ; Among them, the initial temperature is inversely proportional to the fitness function value of the individual. The lower the fitness, the higher the initial temperature to increase the exploration probability of the search space;

[0179] For each individual, the simulated annealing algorithm is used to iteratively update its cutting parameter combination; wherein, in each iteration k, the current parameter is randomly perturbed according to the following formula 6:

[0180]

[0181] Among them, p k+1 represents the cutting parameter combination at iteration number k+1; p k represents the cutting parameter combination at iteration number k; Δp is the disturbance intensity; rand(-1, 1) is used to generate random numbers in the range of [-1, 1]; τ is the time constant for controlling disturbance reduction;

[0182] Using the Metropolis criterion, if the newly generated cutting parameter combination p k+1 The corresponding fitness function F(p k+1 ) is better than the current parameter p k The fitness F(p k ), then the new parameters are accepted; otherwise, the new parameters are accepted with probability P calculated according to the following formula 7:

[0183]

[0184] Where F represents the multi-objective fitness function; T k represents the temperature at the current iteration number k, which is calculated by the following formula 8:

[0185]

[0186] Where ξ is the cooling rate;

[0187] After each iteration, the system temperature is reduced and T is updated exponentially according to Equation 8. k ;

[0188] Repeat the iterative optimization process until the termination condition is met, wherein the termination condition includes T k falls below a certain threshold or reaches a predetermined number of iterations.

[0189] In the metal cutting machining path planning system, the comprehensive optimization module uses a simulated annealing algorithm combined with a genetic algorithm to optimize the cutting parameter combination. This method aims to find the best cutting path, depth and speed while taking into account cutting efficiency and cost control.

[0190] This module first defines an initial temperature T for each newly generated population member. 0 This temperature is set inversely proportional to the fitness function value of each individual, which means that individuals with lower fitness (i.e. individuals with unsatisfactory current parameter combinations) will be assigned higher initial temperatures. This setting allows the search process to explore more solutions that may not seem ideal at first glance but are potentially beneficial, thereby increasing the probability of finding the global optimal solution.

[0191] In each iteration, the individual cutting parameter combinations are updated with random perturbations using Equation 6:

[0192]

[0193] here:

[0194] p k+1 is the cutting parameter combination after iteration.

[0195] pk is the current cutting parameter combination.

[0196] Δp is the preset disturbance intensity, which determines the range of parameter variation.

[0197] rand(-1, 1) generates a random number between -1 and 1, providing randomness.

[0198] τ is a time constant that controls how quickly the perturbation decreases with the number of iterations, simulating a “cooling down” process.

[0199] After each parameter update, the new parameter combination p k+1 The fitness of will be calculated by the multi-objective fitness function F and combined with the current parameter p k The acceptance of new parameters is based on the Metropolis criterion, that is, if the new parameter has better fitness, the new parameter is accepted; if it is worse, the new parameter is accepted according to the following probability:

[0200]

[0201] The temperature T in the iteration k The exponential decay is updated according to the following formula to simulate the annealing process:

[0202]

[0203] ξ is the cooling rate, which controls how fast the temperature drops.

[0204] The entire optimization process will continue until a termination condition is met - usually the temperature drops below a certain threshold or a predetermined number of iterations is reached.

[0205] In this way, the comprehensive optimization module can effectively find the optimal combination of cutting parameters in a wide search space, aiming to improve cutting efficiency and reduce machining costs while ensuring high quality and precision of the machining process.

[0206] The feedback adjustment module 106 monitors changes in stress and heat during the machining process, and if it is detected that the monitored parameters exceed preset limits, the cutting parameters are adjusted or the machining is suspended to prevent damage.

[0207] The feedback adjustment module 106 plays a vital monitoring and adjustment role in the metal cutting process path planning system, ensuring that the stress and heat during the entire process remain within the safe threshold. The module is designed to monitor and dynamically respond to any potential risks in the cutting process in real time, thereby improving processing efficiency and product quality while ensuring the safety of equipment and operators.

[0208] In specific implementation, the feedback adjustment module 106 first receives real-time data from the cutting simulation module 103, which includes the stress and heat distribution of the workpiece measured in the virtual cutting environment. These data are calculated by a high-precision simulation algorithm and can accurately reflect the physical phenomena that may occur in the actual cutting process.

[0209] Once the data is received, the analysis system inside the module will immediately evaluate whether the stress and heat exceed the pre-set safety threshold. This evaluation process involves complex data processing and analysis techniques, such as threshold analysis and trend prediction algorithms, to ensure that any abnormal conditions that may cause equipment damage or product quality problems can be accurately identified.

[0210] If any parameter is detected to be out of limit, the feedback adjustment module 106 will automatically trigger a response mechanism. This includes adjusting cutting parameters, such as changing cutting speed, adjusting feed rate or modifying cutting depth, and pausing the machining process when necessary. The adjustment strategy is implemented based on advanced control algorithms that can optimize cutting parameters based on specific monitoring data and preset response rules to quickly restore operating conditions to a safe range.

[0211] In addition, the module is equipped with a user interface that allows operators to monitor real-time data streams and current system status, as well as manually override automatic response mechanisms. This feature is particularly important because it provides operators with an additional level of control, ensuring that manual intervention is possible in complex or unusual situations.

[0212] Furthermore, the feedback adjustment module includes:

[0213] Multi-sensor fusion unit for comprehensive analysis of current measurement data from force sensors, temperature sensors, and vibration sensors;

[0214] The predictive control unit predicts the processing status in the future based on historical data and current measurement data and makes adjustments in advance.

[0215] In the metal cutting machining path planning system, the feedback adjustment module plays a vital role to ensure the accuracy and safety of the entire machining process. This module consists of two key components: a multi-sensor fusion unit and a predictive control unit. The design and functions of these components are intended to provide real-time and forward-looking adjustment measures to deal with various problems that may arise during the machining process.

[0216] The multi-sensor fusion unit is designed to comprehensively process data from different types of sensors, including force sensors, temperature sensors, and vibration sensors. These sensors measure the force, temperature, and vibration during the machining process, which are key indicators for evaluating the current machining status. The multi-sensor fusion unit integrates these multi-source data through advanced data fusion techniques, such as Kalman filtering or neural network algorithms. This fusion processing not only enhances the reliability of the data, but also improves the accuracy of monitoring, allowing the system to analyze the mutual influence between various sensor readings.

[0217] The predictive control unit uses this integrated data, combined with historical processing data, to predict the processing status in the future through advanced predictive models. This prediction is usually based on machine learning algorithms, such as support vector machines or artificial neural networks, which can learn from past operation data and predict future trends. The design of the predictive control unit enables the system to proactively make adjustments before potential problems are detected, such as changing cutting speeds, adjusting feed rates, or pausing operations to avoid possible failures or damage.

[0218] Although the present application is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present application. Any technical personnel in this field may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.

Claims

1. A metal cutting process path planning system, characterized in that: include: An image acquisition module, used for capturing multi-angle high-resolution images of the metal workpiece to be processed from multiple angles; A three-dimensional reconstruction module, used to reconstruct a three-dimensional model of the metal workpiece to be processed using the multi-angle high-resolution images; The cutting simulation module simulates the cutting process of the reconstructed 3D model in a virtual environment and records the stress and heat distribution during the simulation in real time; Intelligent segmentation module, which analyzes the stress and heat data obtained during the simulation process and divides the processing process into multiple stages, and the maximum stress and heat of each stage do not exceed the set safety threshold; The comprehensive optimization module uses a hybrid optimization strategy combining genetic algorithm and simulated annealing to simultaneously optimize the cutting path, cutting depth and feed speed of each processing stage. The global search capability of the genetic algorithm is used to generate and optimize the initial solution, and the simulated annealing algorithm is used to perform a local fine search for the optimal solution of each generation to improve the cutting efficiency and ensure the processing accuracy of the final product. The feedback adjustment module monitors changes in stress and heat during machining. If it detects that the monitored parameters exceed the preset limits, it adjusts the cutting parameters or pauses the machining to prevent damage.

2. The metal cutting machining path planning system according to claim 1, characterized in that: The image acquisition module comprises: A plurality of high-resolution cameras with adjustable angles, wherein the high-resolution cameras can automatically adjust the focal length and shooting angle to capture an all-round image of the workpiece; Light compensation unit, used to automatically adjust light intensity and direction when shooting at different angles to ensure consistent image quality.

3. The metal cutting machining path planning system according to claim 1, characterized in that: The three-dimensional reconstruction module is specifically used for: Use stereo matching technology to match feature points of high-resolution images acquired from multiple angles to obtain matching feature points; Calculating the position difference of the matching feature points to determine the disparity information between different images; Based on the determined parallax information, an accurate three-dimensional model of the metal workpiece to be processed is reconstructed.

4. The metal cutting machining path planning system according to claim 1, characterized in that: The cutting simulation module is specifically used for: importing the accurate 3D model obtained from the 3D reconstruction module into simulation software, which is configured with a simulation program for performing cutting operations and allows setting of initial cutting parameters, including cutting speed, feed rate, cutting depth, and tool type; Run the simulation program through the simulation software to simulate the cutting operation in a controlled virtual environment, and use physical and thermodynamic models to calculate the stress distribution and heat generation on the contact interface between the workpiece and the tool in real time; Record stress and heat data generated during cutting.

5. The metal cutting machining path planning system according to claim 1, characterized in that: The feedback adjustment module comprises: Multi-sensor fusion unit for comprehensive analysis of current measurement data from force sensors, temperature sensors, and vibration sensors; The predictive control unit predicts the processing status in the future based on historical data and current measurement data and makes adjustments in advance.

6. The metal cutting machining path planning system according to claim 1, characterized in that: The intelligent segmentation module is specifically used for: According to the following formulas 1 and 2, the stress σ(t) and heat Q(t) data collected from the cutting simulation module are normalized, and the data range is unified to [0,1] to obtain the normalized stress data σ norm (t) and normalized heat data Q norm (t): Where t represents time; σ min Represents the minimum stress value in the collected data; σ max Indicates the maximum stress value in the collected data; Q min Indicates the minimum heat value in the collected data; Q max Indicates the maximum heat value in the collected data; According to the following formula 3 and formula 4, calculate the stress threshold σ of each processing point thresh (t) and the thermal threshold Q thresh (t): s thresh (t)=κ·(σ norm (t)·exp(-λ·t)+(1-exp(-λ·t))·max(p norm (t))) (3) Q thresh (t)=κ·(Q norm (t)·exp(-λ·t)+(1-exp(-λ·t))·max(Q norm (t))) (4) Among them, λ is the attenuation coefficient; κ is the amplification coefficient; σ norm (t) represents normalized stress data; Q norm (t) represents normalized heat data; If the stress σ(t) of the current processing point exceeds the stress threshold σ of the current processing point thresh (t), or the heat of the current processing point Q(t) exceeds the heat threshold Q of the current processing point thresh (t), then mark the point as a segmentation point.

7. The metal cutting machining path planning system according to claim 1, characterized in that: The comprehensive optimization module is specifically used for: Step P101: Initializing a population, wherein each population member represents a potential cutting parameter combination, including cutting path, cutting depth and feed rate; each cutting parameter combination takes into account the physical limitations of the machine and the predetermined processing quality standard; Step P102: Performing performance evaluation on each individual in the initial population based on a predefined multi-objective fitness function; wherein the fitness function comprehensively considers cutting efficiency, processing quality, resource utilization and cost control; Step P103: Execute the selection process of the genetic algorithm, use non-dominated sorting, sort the individuals according to their performance on each optimization goal, and select individuals with excellent performance to enter the next generation population; Step P104: Perform crossover and mutation operations on the selected population, combine simulated annealing algorithm to perform local fine search, adjust the parameters of the individuals after crossover to avoid local optimality, and enhance exploration ability; Step P105: Repeat steps P102 to P104 until a predetermined number of iterations is reached or a specific performance indicator is met to ensure that the most optimized cutting path and parameter settings are obtained, thereby improving cutting efficiency and ensuring the accuracy and quality of the processed products.

8. The metal cutting machining path planning system according to claim 7, characterized in that: The predefined multi-objective fitness function adopts the following formula 5: Where F(z) represents the fitness score; x represents a population member, which represents a cutting parameter combination; T(x) represents the cutting time under a given parameter combination; T ref is the reference cutting time, used for standardization; Q(x) represents the machining quality score; Q max is the highest quality score under ideal conditions; R(x) represents resource utilization efficiency; R opt is the optimal resource utilization efficiency; C(x) represents the processing cost; C ref is the reference cost; α, β, γ, δ are weight factors.

9. The metal cutting machining path planning system according to claim 8, characterized in that: The comprehensive optimization module is also specifically used for: In the new population generated by performing crossover and mutation operations, an initial temperature T0 is defined for each individual x; the initial temperature is inversely proportional to the fitness function value of the individual. The lower the fitness, the higher the initial temperature, so as to increase the exploration probability of the search space; For each individual, the simulated annealing algorithm is used to iteratively update its cutting parameter combination; wherein, in each iteration k, the current parameter is randomly perturbed according to the following formula 6: Among them, p k+1 represents the cutting parameter combination at iteration number k+1; p k represents the cutting parameter combination at iteration number k; Δp is the disturbance intensity; rand(-1,1) is used to generate random numbers in the range [-1,1]; τ is the time constant for controlling disturbance reduction; Using the Metropolis criterion, if the newly generated cutting parameter combination p k+1 The corresponding fitness function F(p k+1 ) is better than the current parameter p k The fitness F(p k ), then the new parameters are accepted; otherwise, the new parameters are accepted with probability P calculated according to the following formula 7: Where F represents the multi-objective fitness function; T k represents the temperature at the current iteration number k, which is calculated by the following formula 8: Where ξ is the cooling rate; After each iteration, the system temperature is reduced and T is updated exponentially according to Equation 8. k ; Repeat the iterative optimization process until the termination condition is met, wherein the termination condition includes T k falls below a certain threshold or reaches a predetermined number of iterations.

10. The metal cutting machining path planning system according to claim 9, characterized in that: The crossover operation performed in step P104 specifically includes the following steps: Select two parent individuals from the current population, each individual is defined by a set of cutting parameters, including cutting path, cutting depth and feed rate; Randomly determine two points in the parameter set of each parent individual as crossover points, which define the boundaries of the parameter segment to be exchanged; In two parent individuals, the parameter segment between the first intersection point and the second intersection point is exchanged, wherein the parameter segment includes a cutting path, a cutting depth and a feed speed within a selected interval; Through the exchange of the new parameter set, two new offspring individuals are constructed, where each offspring individual inherits the characteristics of two different parent generations, forming a new cutting parameter combination; Verification operations are performed to ensure that the cutting parameters in the exchanged offspring individuals meet the physical limitations of mechanical operations and predetermined processing quality standards, and are appropriately adjusted based on the verification results to adapt to the requirements of the cutting equipment.

Images