Laser cutting machine beam stabilization and transmission optimization method and platform

Abstract

This application discloses a laser cutting machine beam stabilization and transmission optimization method and platform, relating to the field of laser cutting technology. The method includes: performing cutting equivalent partitioning based on the current structural attribute information and structural design information of the workpiece to be cut to obtain N workpiece cutting area information; establishing a dual-channel cutting machine control, including a beam stabilization control channel and a beam transmission control channel, thereby performing control parameter analysis on the N workpiece cutting area information in parallel to obtain N workpiece area cutting control parameters; using a PID controller to regulate and calculate the N workpiece area cutting control parameters based on beam quality parameters and workpiece cutting surface morphology data, and determining the cutting control correction amount to perform compensatory closed-loop control on the target laser cutting machine. The method achieves the technical effect of achieving beam stabilization control and reducing transmission loss, improving metal cutting accuracy and stability, and thus ensuring the quality of workpiece laser cutting.

Description

Technical Field

[0001] The present application relates to the field of laser cutting technology, and in particular to a method and platform for optimizing the beam stabilization and transmission of a laser cutting machine. Background Art

[0002] Laser cutting technology, a key component of modern metal manufacturing, is developing at an unprecedented pace. However, beam instability and transmission loss remain key factors affecting metal cutting quality and efficiency. Beam instability can lead to rough edges and surface deformation, while transmission loss reduces laser power density, affecting cutting depth and speed. Therefore, optimizing beam stability and transmission in laser cutting machines has become a pressing issue. Summary of the Invention

[0003] This application solves the technical problems of unstable laser cutting beam control and transmission loss in the existing technology, resulting in poor metal cutting quality, by providing a laser cutting machine beam stabilization and transmission optimization method and platform. The application achieves the technical effect of building a dual-channel cutting machine control to analyze control parameters, realize beam stabilization control and reduce transmission loss, improve metal cutting accuracy and stability, and thus ensure the quality of laser cutting of workpieces.

[0004] In view of the above problems, on the first aspect, the present application provides a method for optimizing the beam stabilization and transmission of a laser cutting machine, the method comprising: obtaining the current structural attribute information and structural design information of the workpiece to be cut, performing cutting equivalent partitioning on the current structural attribute information based on the structural design information, and obtaining N workpiece cutting area information; performing historical data mining and control analysis based on the target laser cutting machine, and building a dual-channel cutting machine control, the dual-channel cutting machine control comprising a beam stabilization control channel and a beam transmission control channel; using the beam stabilization control channel and the beam transmission control channel to perform control parameter analysis on the N workpiece cutting area information in parallel, and obtaining N workpiece area cutting control parameters; real-time monitoring to obtain beam quality parameters and workpiece cutting surface morphology data, using a PID controller to regulate and calculate the N workpiece area cutting control parameters based on the beam quality parameters and the workpiece cutting surface morphology data, determining a cutting control correction amount, and performing compensation closed-loop control on the target laser cutting machine based on the cutting control correction amount.

[0005] In another aspect, the application also provides a laser cutting machine beam stabilization and transmission optimization platform, which comprises: a workpiece partition module for obtaining current structural attribute information and structural design information of a workpiece to be cut, performing cutting equivalent partition on the current structural attribute information based on the structural design information, and obtaining N workpiece cutting area information; a dual-channel building module for performing historical data mining and control analysis based on a target laser cutting machine, and building a cutting machine control dual-channel, the cutting machine control dual-channel comprising a beam stabilization control channel and a beam transmission control channel; a control analysis module for performing control parameter analysis on the N workpiece cutting area information in parallel using the beam stabilization control channel and the beam transmission control channel, and obtaining N workpiece area cutting control parameters; and a cutting control module for real-time monitoring and obtaining beam quality parameters and workpiece cutting surface morphology data, performing regulation and control calculation on the N workpiece area cutting control parameters based on the beam quality parameters and the workpiece cutting surface morphology data using a PID controller, determining a cutting control correction amount, and performing compensation closed-loop control on the target laser cutting machine based on the cutting control correction amount.

[0006] The one or more technical solutions provided in the application have at least the following technical effects or advantages:

[0007] Due to the adoption of the current structural attribute information and the structural design information of the workpiece to be cut, the cutting equivalent partition is performed to obtain the N workpiece cutting area information, the historical data mining and control analysis are performed based on the target laser cutting machine, the cutting machine control dual-channel is built, the cutting machine control dual-channel comprises the beam stabilization control channel and the beam transmission control channel, the control parameter analysis is performed on the N workpiece cutting area information in parallel based on this, the N workpiece area cutting control parameters are obtained, the beam quality parameters and the workpiece cutting surface morphology data are real-time monitored and obtained, the regulation and control calculation is performed on the N workpiece area cutting control parameters based on the beam quality parameters and the workpiece cutting surface morphology data using the PID controller, the cutting control correction amount is determined, and the compensation closed-loop control is performed on the target laser cutting machine based on the cutting control correction amount. Thus, the control parameter analysis is performed through the building of the cutting machine control dual-channel, the beam stabilization control and the transmission loss reduction are realized, the metal cutting precision and stability are improved, and the workpiece laser cutting quality is ensured.

[0008] The above description is only a summary of the technical solutions of the application. In order to more clearly understand the technical means of the application, the application can be implemented in accordance with the content of the description, and in order to make the above and other purposes, features and advantages of the application more obvious and easy to understand, the following specific embodiments of the application are described. BRIEF DESCRIPTION OF DRAWINGS

[0009] Figure 1This is a flow chart of the laser cutting machine beam stabilization and transmission optimization method of this application.

[0010] Figure 2 This is a flow chart of obtaining N workpiece cutting area information in the laser cutting machine beam stabilization and transmission optimization method of this application.

[0011] Figure 3 This is a schematic diagram of the structure of the laser cutting machine beam stabilization and transmission optimization platform for this application.

[0012] Description of the accompanying drawings: workpiece partitioning module 11, dual-channel construction module 12, control analysis module 13, cutting control module 14. DETAILED DESCRIPTION

[0013] This application solves the technical problems of unstable laser cutting beam control and transmission loss in the existing technology, resulting in poor metal cutting quality, by providing a laser cutting machine beam stabilization and transmission optimization method and platform. The application achieves the technical effect of building a dual-channel cutting machine control to analyze control parameters, realize beam stabilization control and reduce transmission loss, improve metal cutting accuracy and stability, and thus ensure the quality of laser cutting of workpieces.

[0014] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0015] The present application is described below in conjunction with the accompanying drawings.

[0016] Example 1, as Figure 1 As shown, the present application provides a method for beam stabilization and transmission optimization of a laser cutting machine, the method comprising:

[0017] Step S100: obtaining current structural attribute information and structural design information of a workpiece to be cut, performing cutting equivalent partitioning on the current structural attribute information based on the structural design information, and obtaining N workpiece cutting area information.

[0018] like Figure 2 As shown, further, the steps of obtaining N workpiece cutting area information in this application also include:

[0019] key parameter extraction is performed on the current structure attribute information to obtain a workpiece structure attribute parameter set, the workpiece structure attribute parameter set including size shape, material thickness, material type, and material characteristics; the structure design information and the current structure attribute information are cut and compared to determine workpiece to-be-cut region information; each attribute parameter in the workpiece structure attribute parameter set is cut and reference prioritized according to laser cutting process requirements to obtain a structure attribute cutting sequence parameter; the workpiece to-be-cut region information is cut and equivalently partitioned based on the structure attribute cutting sequence parameter to obtain the N workpiece cutting region information.

[0020] Specifically, in processing a laser cutting task of a to-be-cut workpiece, first, current structure attribute information and structure design information of the workpiece need to be obtained and analyzed, where the current structure attribute information includes specific physical characteristics of the workpiece, such as size, shape, material thickness, material type, and material characteristics (such as hardness, thermal conductivity, etc.); the structure design information is workpiece design drawing information, including cutting shape, size, design angle, etc. The current structure attribute information is cut and equivalently partitioned based on the structure design information, that is, the to-be-cut workpiece region is divided into a plurality of regions with similar structure characteristics or functional requirements. Specifically, first, key parameter extraction is performed on the current structure attribute information to obtain a workpiece structure attribute parameter set, the workpiece structure attribute parameter set being a workpiece structure parameter type that has a greater impact on laser cutting, including size shape, material thickness, material type, and material characteristics, and this step is the basis for subsequent analysis and cutting.

[0021] Then, the structure design information and the current structure attribute information are cut and compared to determine which regions in the workpiece need to be cut, and then determine workpiece to-be-cut region information, and this step needs to accurately match design requirements with actual workpiece attributes to ensure the accuracy of cutting. Each attribute parameter in the workpiece structure attribute parameter set is cut and reference prioritized according to laser cutting process requirements, for example, each attribute parameter in the workpiece structure attribute parameter set is cut and reference prioritized according to the degree of influence on laser cutting process precision requirements, and attribute parameters with greater influence are arranged in the front sequence, and then a structure attribute cutting sequence parameter is obtained according to the size of the degree of influence, which is used as a priority sequence for cutting region division reference. Exemplarily, each attribute parameter in the workpiece structure attribute parameter set is sorted as size shape, material thickness, material type, and material characteristics, etc.

[0022] Cutting equivalent partition is performed on the workpiece region to be cut based on the structure attribute cutting sequence parameters, and the workpiece region to be cut is divided into a plurality of regions with similar structure characteristics or functional requirements, to obtain N workpiece cutting region information, i.e., a region set with the same or similar cutting conditions, cutting parameters and cutting effects. Through the equivalent region partition of the workpiece, specific cutting parameter analysis is realized for different structure regions of the workpiece, the cutting process is simplified, and the workpiece cutting quality and cutting efficiency are improved.

[0023] Step S200: Based on the target laser cutting machine, historical data mining and control analysis are performed, and a cutting machine control double channel is built, which includes a beam stability control channel and a beam transmission control channel.

[0024] Further, based on the built cutting machine control double channel, the step of the application further includes:

[0025] Based on the target laser cutting machine, historical data mining is performed, a laser cutting machine working database is obtained, the laser cutting machine working database includes a beam stability control data set and a beam transmission control data set of each cutting path of the historical cutting workpiece; a beam stability control target and a beam transmission control target are obtained, index extraction is performed on the beam stability control target and the beam transmission control target, a beam stability effect evaluation index set and a beam transmission effect evaluation index set are obtained; the beam stability effect evaluation index set and the beam transmission effect evaluation index set are used to respectively perform effect evaluation screening on the beam stability control data set and the beam transmission control data set, to obtain a beam stability control sample set and a beam transmission control sample set; the beam stability control sample set and the beam transmission control sample set are respectively trained and optimized, to obtain a beam stability control channel and a beam transmission control channel; the beam stability control channel and the beam transmission control channel are connected in parallel and integrated, to form the built cutting machine control double channel.

[0026] Further, based on the built cutting machine control double channel, the step of the application further includes:

[0027] A recurrent neural network is used to train and cross-verify and optimize the model of the beam stability control sample set, to generate an initial stability control analysis model; a convolutional neural network is used to train and cross-verify and optimize the model of the beam transmission control sample set, to generate an initial transmission control analysis model; L1 regularization is used to perform overfitting processing on the initial stability control analysis model and the initial transmission control analysis model, to obtain a beam stability control analysis model and a beam transmission control analysis model; the beam stability control analysis model and the beam transmission control analysis model are respectively embedded into a laser data processing double channel, to obtain the beam stability control channel and the beam transmission control channel.

[0028] Specifically, based on the target laser cutting machine, historical data mining and control analysis are performed, wherein the target laser cutting machine is a laser cutting machine that cuts the workpiece to be cut. Based on the historical data of the laser cutting machine, a cutting machine control double channel is built, which is used for parameter analysis and processing of the beam stability and beam transmission of the workpiece cutting area, including a beam stability control channel and a beam transmission control channel. The specific construction process of the cutting machine control double channel is as follows: first, based on the target laser cutting machine, historical data mining is performed to obtain a corresponding laser cutting machine working database. The laser cutting machine working database includes historical working data of the laser cutting machine of the same specification and model as the target laser cutting machine, i.e., beam stability control data sets and beam transmission control data sets of each cutting path of the historical cutting workpiece. These data sets record in detail the cutting workpiece region attributes, cutting path information, and executed cutting control parameters, including laser power associated with beam stability, cutting speed, and other cutting control parameters, focusing lens focal length and defocusing amount associated with beam transmission, and beam stability and transmission in each cutting process, including but not limited to beam intensity, beam offset, transmission path, speed, and beam attenuation.

[0029] The beam stability control target and the beam transmission control target are determined, such as the stability of the beam intensity and the accuracy of the transmission path. For the above control targets, relevant evaluation indexes are extracted from the database to obtain a beam stability effect evaluation index set, such as beam intensity fluctuation rate and position offset, and a beam transmission effect evaluation index set, such as transmission path deviation and cutting surface quality. These indexes should accurately reflect the stability and transmission effect of the beam. The beam stability effect evaluation index set and the beam transmission effect evaluation index set are used to evaluate and screen the beam stability control data set and the beam transmission control data set, respectively. By setting a threshold or using clustering analysis, samples that perform well (i.e., meet or exceed the control target) are screened out to form a beam stability control sample set, including beam stability data set and corresponding workpiece associated cutting control parameters in the cutting process, and a beam transmission control sample set, including beam transmission data set and corresponding workpiece associated cutting control parameters in the cutting process, which serve as a sample basis for subsequent laser cutting parameter analysis and processing.

[0030] Based on the light beam stability control sample set and the light beam transmission control sample set, first, a recurrent neural network is designed, which can select variants such as LSTM or GRU to adapt to the processing of time series data, and the recurrent neural network is used for model training of the light beam stability control sample set, and appropriate hyperparameters (such as learning rate, batch size, iteration number, etc.) are set according to historical experience, and cross-validation (such as K-fold cross-validation) is used to evaluate the performance of the model, and according to the results of cross-validation, the model structure and hyperparameters are adjusted to optimize the model performance, and ensure that the model also performs well on unseen data, and an initial stability control analysis model is generated. At the same time, according to historical experience, a convolutional neural network is designed, including convolutional layers, pooling layers, fully connected layers, etc., to adapt to the task of image or feature extraction, and the convolutional neural network is used for model training of the light beam transmission control sample set, and cross-validation is also used to evaluate the performance of the model, and according to the results of cross-validation, the model structure and hyperparameters are adjusted to optimize the model performance, and an initial transmission control analysis model is generated.

[0031] The initial stability control analysis model and the initial transmission control analysis model are subjected to overfitting processing by L1 regularization (Lasso regression), and L1 regularization is realized by adding the sum of the absolute values of the weights in the loss function. For the initial stability control analysis model (RNN model), on the basis of the original loss function (such as mean square error MSE), the sum of the absolute values of all weights is added multiplied by the regularization coefficient λ. For the initial transmission control analysis model (CNN model), similarly, on the basis of the original loss function (such as cross-entropy loss), the sum of the absolute values of the weights is added multiplied by the regularization coefficient λ. Generally, the best regularization coefficient λ can be found by cross-validation, and during the cross-validation process, different λ values are tried, and the performance of the model on the validation set is evaluated. Select the λ value that makes the validation set performance best (or close to best) as the final regularization coefficient. If λ is too large, the model may be underfit (i.e. the model is too simple and cannot capture complex patterns in the data), and if λ is too small, it may not effectively prevent overfitting. Apply L1 regularization to the initial stability control analysis model and the initial transmission control analysis model respectively, retrain the model, and adjust the regularization parameters (such as regularization coefficient) to find the best balance point, and obtain the corresponding light beam stability control analysis model for analyzing and processing laser cutting control parameters related to light beam stability according to the cutting workpiece region information; and the light beam transmission control analysis model for analyzing and processing laser cutting control parameters related to light beam transmission according to the cutting workpiece region information.

[0032] The light beam stability control analysis model and the light beam transmission control analysis model that meet the performance standards after training processing are respectively embedded into a laser data processing double channel, wherein the laser data processing double channel is a data processing channel for analyzing laser cutting control parameters of workpiece region information, the light beam stability control analysis model and the light beam transmission control analysis model are respectively placed and embedded into one of the data processing channels in the laser data processing double channel, to obtain a model-embedded light beam stability control channel for laser cutting control parameter analysis related to light beam stability by the light beam stability control analysis model, and a light beam transmission control channel for laser cutting control parameter analysis related to light beam transmission by the light beam transmission control analysis model. The light beam stability control channel and the light beam transmission control channel are parallelly integrated to form a cutting machine control double channel for inputting the workpiece region information into the two channels for parallel processing by the respective models and outputting corresponding control analysis results. The cutting machine control double channel realizes coordinated and synchronous analysis of the stability control and transmission control of the light beam, and further ensures accurate control in the laser cutting process.

[0033] Step S300: The N workpiece region cutting control parameters are obtained by parallel control parameter analysis of the N workpiece cutting region information by the light beam stability control channel and the light beam transmission control channel.

[0034] Further, the N workpiece region cutting control parameters are obtained, and the step of the application further includes:

[0035] Attribute parameters of the N workpiece cutting region information are extracted to obtain N cutting region attribute parameters, the N cutting region attribute parameters include size and shape, material thickness, material type and material characteristics, cutting path information of N regions is determined based on the N cutting region attribute parameters, the N cutting region attribute parameters and the N region cutting path information are subjected to cutting control analysis by the light beam stability control channel and the light beam transmission control channel in parallel to obtain N region light beam stability control parameters and N region light beam transmission control parameters, and the N workpiece region cutting control parameters are obtained based on the N region light beam stability control parameters and the N region light beam transmission control parameters.

[0036] Further, the N region cutting path information is determined, and the step of the application further includes:

[0037] According to the characteristic information of the N cutting region attribute parameters, an N-region cutting path planning algorithm is selected; the N-region cutting path planning algorithm is used to respectively perform cutting path optimization on the N cutting region attribute parameters to obtain N-region optimal cutting paths; the N-region optimal cutting paths are corrected according to the distribution characteristics of the N workpiece cutting region information to determine N-region cutting path information.

[0038] Further, the determination of the N-region cutting path information further includes:

[0039] According to the distribution characteristics of the N workpiece cutting region information, cutting path constraint information is determined, the cutting path constraint information including region cutting sequence, cutting path conflict and cutting direction limitation; the N-region optimal cutting paths are corrected based on the cutting path constraint information to determine the N-region cutting path information.

[0040] Specifically, the N workpiece cutting region information is controlled by the light beam stabilization control channel and the light beam transmission control channel in parallel. First, attribute parameters of the N workpiece cutting region information are extracted, and key parameters are digitally described to obtain corresponding N cutting region attribute parameters, including size and shape, material thickness, material type and material characteristics, which provide basic data for subsequent cutting path planning and cutting control analysis. Then, cutting path planning is performed based on the N cutting region attribute parameters. The specific planning process is as follows: according to the characteristic information of the N cutting region attribute parameters, a suitable N-region cutting path planning algorithm is selected. For example, for regions with regular shape and uniform material, a simple greedy algorithm or dynamic programming algorithm can be selected; for regions with complex shape and variable material, a more complex genetic algorithm or simulated annealing algorithm may be considered. The selected algorithm should fully consider cutting efficiency, material utilization rate and cutting quality and other factors. The N-region cutting path planning algorithm is used to respectively perform cutting path optimization on the N cutting region attribute parameters to obtain corresponding N-region optimal cutting paths. The purpose of this step is to find the optimal cutting path in each cutting region to maximize cutting efficiency and material utilization rate. The cutting path optimization result is evaluated to check whether the cutting path meets the cutting requirements such as precision and surface quality. If the requirements are not met, the algorithm parameters need to be adjusted or other algorithms are selected to perform optimization again.

[0041] To ensure the practicality of the cutting path, the preferred cutting path of the N regions is modified according to the distribution characteristics of the N workpiece cutting region information, such as the relative position between regions, shape difference, material change, etc. These distribution characteristics will have an important impact on the modification and constraint determination of the cutting path. First, according to the distribution characteristics of the N workpiece cutting region information, the cutting path constraint information is determined, which includes region cutting sequence, determination of the cutting sequence of different cutting regions to optimize cutting efficiency and reduce cutting conflict; cutting path conflict, identify and avoid potential conflicts between cutting paths to ensure the safety and smooth progress of the cutting process; and cutting direction limit, according to the characteristics of the material and the performance of the cutting machine, determine the limitation conditions of the cutting direction to improve the cutting quality and efficiency. Based on the cutting path constraint information, the preferred cutting path of the N regions is constrained and modified, and the impact of these constraint information on the preferred cutting path is evaluated, which may involve analysis of the potential negative impact on cutting efficiency, material utilization and cutting quality. According to the specific content and impact degree of the constraint information, targeted modification strategies are developed. This may include adjusting the cutting sequence, optimizing the cutting path to avoid conflict, adjusting the cutting direction to meet the limitation conditions, etc. On the basis of the preferred cutting path, specific modification operations are carried out according to the developed modification strategies, including re-planning of the cutting path, adjustment of the cutting parameters, etc. The modified cutting path is verified to ensure that they meet all the constraint conditions, and then the modified N region cutting path information is determined, which clearly and accurately reflects the key information of each cutting region, such as cutting path, cutting sequence, cutting direction, etc., to maintain the balance of cutting efficiency, material utilization and cutting quality as much as possible.

[0042] The N cutting region attribute parameters and the N region cutting path information are analyzed for cutting control in parallel using the beam stability control channel and the beam transmission control channel, and the corresponding N region beam stability control parameters, such as laser power and cutting speed, and N region beam transmission control parameters, such as focusing lens focal length and defocusing amount, are obtained after analysis and processing. Based on the N region beam stability control parameters and N region beam transmission control parameters, the cutting control parameters for each workpiece region, i.e. N workpiece region cutting control parameters, are obtained, which will constitute a complete instruction set for the cutting process to control the laser cutting of each region of the workpiece and guide the operation of the cutting equipment, ensuring the smooth progress of the cutting process and the stable and reliable cutting quality. The workpiece region is cut specifically to improve the accuracy of cutting control, and then the laser cutting effect is ensured.

[0043] Step S400: Real-time monitoring of the light beam quality parameters and the workpiece cutting surface morphology data, using a PID controller to regulate and calculate the N workpiece region cutting control parameters based on the light beam quality parameters and the workpiece cutting surface morphology data, determine the cutting control correction amount, and compensate for the closed-loop control of the target laser cutting machine based on the cutting control correction amount.

[0044] Further, the determination of the cutting control correction amount, the step of the application also includes:

[0045] Based on the light beam quality parameters and the workpiece cutting surface morphology data, the workpiece cutting quality is predicted, and the workpiece cutting prediction quality parameters are obtained; using a PID controller to regulate and analyze the workpiece cutting prediction quality parameters and the workpiece cutting expected quality parameters, determine the cutting control correction amount.

[0046] Further, the determination of the cutting control correction amount, the step of the application also includes:

[0047] The parameters of the PID controller are extracted to obtain controller parameter information, including proportional control, integral control and differential control; based on the controller parameter information, the PID controller is iteratively verified and optimized to obtain a PID optimized controller; the difference between the workpiece cutting prediction quality parameters and the workpiece cutting expected quality parameters is taken as the quality deviation parameter, and the PID optimized controller is used to analyze the cutting regulation of the quality deviation parameter to determine the cutting control correction amount.

[0048] Specifically, high-precision sensors are used to real-time monitor and obtain light beam quality parameters such as beam mode, power density, and energy density, to ensure the synchronization of the sensor and the laser beam, so as to accurately capture the dynamic changes of the laser beam during the cutting process; the morphology data of the workpiece cutting surface is monitored in real time by visual sensors or image processing technology, such as the roughness, width, and inclination of the cutting surface. In order to ensure the closed-loop regulation of the workpiece laser cutting, a PID controller is used to regulate and calculate the N workpiece region cutting control parameters based on the light beam quality parameters and the workpiece cutting surface morphology data. First, based on the light beam quality parameters and the workpiece cutting surface morphology data, the workpiece cutting quality is predicted, specifically: based on historical cutting data and machine learning algorithms (such as neural networks, support vector machines, etc.), a workpiece cutting quality prediction model is established, the real-time monitored light beam quality parameters and the workpiece cutting surface morphology data, and related cutting control parameters (such as laser power, cutting speed, gas flow, etc.) are input, and the prediction model is used to predict the workpiece cutting quality, and the workpiece cutting prediction quality parameters are obtained. These prediction quality parameters may include roughness prediction value, width prediction value, etc.

[0049] According to the desired requirements of workpiece cutting, the workpiece cutting desired quality parameters are set, which should be consistent with the actual production needs. The PID controller is used to control and analyze the workpiece cutting predicted quality parameters and workpiece cutting desired quality parameters, and the control process is as follows: the PID controller is composed of proportional control term (P), integral control term (I) and differential control term (D). The key parameters of the PID controller are extracted to obtain the controller parameter information, which includes the proportional control term, the integral control term and the differential control term. The proportional control term is responsible for providing control output according to the size of the current error; the integral control term is responsible for eliminating steady-state error and making the system output finally stable at the set value; the differential control term is responsible for predicting the trend of error change and adjusting in advance to suppress overshoot and oscillation. The selection of these parameters will directly affect the stability and response speed of the system.

[0050] Based on the controller parameter information, the PID controller is iteratively verified and optimized. First, according to the system characteristics and requirements, the search range of the proportional control term, the integral control term and the differential control term is determined, and the search space, i.e. the numerical selection range of the controller parameters, is obtained. Then, a mathematical model of the workpiece cutting process is established, which can be a continuous time or discrete time system. This model will be used to simulate and verify the performance of the PID controller. Intelligent optimization algorithms such as ant colony algorithm and particle swarm optimization algorithm (PSO) can be used to search for the best PID parameter combination. These algorithms simulate certain behaviors in nature (such as ants searching for food and particles moving in the search space) to iteratively find the optimal solution. The parameters and state of the optimization algorithm are initialized. In each iteration, the simulation is run according to the current parameter combination, and the performance indicators (such as steady-state error, rise time, overshoot, etc.) are calculated. The state of the optimization algorithm (such as pheromone concentration, particle position and velocity, etc.) is updated according to the performance indicators. The iteration process is repeated until the convergence condition is met or the maximum number of iterations is reached. After the iteration is completed, the optimal parameter combination of the proportional control term, the integral control term and the differential control term is output, and the optimized PID optimization controller is obtained.

[0051] The difference between the workpiece cutting predicted quality parameter and the workpiece cutting expected quality parameter is taken as a quality deviation parameter, and the optimal PID control parameter combination is applied to the PID controller. According to the acceptance range of the cutting quality, a reasonable quality deviation threshold is set. When the quality deviation exceeds this threshold, the PID optimization controller is triggered to regulate. Based on the cutting regulation analysis of the PID optimization controller on the quality deviation parameter, the calculated quality deviation parameter is taken as the input signal to the PID optimization controller, and the PID optimization controller is used to calculate the cutting control correction amount according to the input quality deviation parameter and the PID control algorithm. The cutting control correction amount is determined, which may include the adjustment amount of laser power, the change amount of cutting speed, or the increase or decrease amount of gas flow, etc. Based on the cutting control correction amount, the target laser cutting machine is compensated for closed-loop control, and the related parameters of the laser cutting machine are adjusted according to the cutting control correction amount output by the PID controller. The adjusted cutting quality parameter is continuously monitored to evaluate the regulation effect. If the adjusted cutting quality still does not meet the requirements (i.e. the quality deviation is still above the threshold), the quality deviation is calculated again and input to the PID controller for a new round of regulation calculation. Through multiple iterative adjustments, the optimal cutting parameter combination is gradually approached until the cutting quality meets the requirements. Key data such as quality deviation parameter, cutting control correction amount, and adjusted cutting parameter are recorded during the entire regulation process. These data can be used for subsequent analysis and evaluation to improve the cutting control strategy or optimize the parameters of the PID controller. When the cutting quality is stable and meets the requirements, the regulation process of the PID controller is ended. Through accurate closed-loop control of the laser cutting machine, stable control of the light beam and reduction of transmission loss are realized, the metal cutting precision and stability are improved, and the workpiece laser cutting quality is ensured, thereby improving the cutting production efficiency.

[0052] In summary, the laser cutting machine light beam stabilization and transmission optimization method provided by the present application has the following technical effects:

[0053] The current structural attribute information and structural design information of the workpiece to be cut are adopted to perform cutting equivalent partitioning to obtain N workpiece cutting region information, historical data mining and control analysis are performed based on a target laser cutting machine, a cutting machine control double channel is built, the cutting machine control double channel includes a light beam stability control channel and a light beam transmission control channel, based on this, the N workpiece cutting region information is controlled in parallel to obtain N workpiece region cutting control parameters, light beam quality parameters and workpiece cutting surface morphology data are monitored and obtained in real time, a PID controller is adopted to perform regulation and control calculation on the N workpiece region cutting control parameters based on the light beam quality parameters and the workpiece cutting surface morphology data, a cutting control correction amount is determined, and the target laser cutting machine is compensated and controlled in a closed loop according to the cutting control correction amount. Further, the technical effect of ensuring the quality of laser cutting of the workpiece is achieved by building the cutting machine control double channel to perform control parameter analysis, realizing light beam stability control and transmission loss reduction, improving metal cutting precision and stability, and further ensuring the quality of laser cutting of the workpiece.

[0054] In the embodiment two, based on the same inventive concept as the laser cutting machine light beam stability and transmission optimization method in the foregoing embodiments, the present application also provides a laser cutting machine light beam stability and transmission optimization platform, as shown in Figure 3 The platform includes:

[0055] The workpiece partitioning module 11 is configured to obtain the current structural attribute information and structural design information of the workpiece to be cut, perform cutting equivalent partitioning on the current structural attribute information based on the structural design information, and obtain N workpiece cutting region information.

[0056] The double channel building module 12 is configured to perform historical data mining and control analysis based on a target laser cutting machine, and build a cutting machine control double channel, the cutting machine control double channel includes a light beam stability control channel and a light beam transmission control channel.

[0057] The control analysis module 13 is configured to perform control parameter analysis on the N workpiece cutting region information in parallel by using the light beam stability control channel and the light beam transmission control channel, and obtain N workpiece region cutting control parameters.

[0058] The cutting control module 14 is configured to monitor and obtain light beam quality parameters and workpiece cutting surface morphology data in real time, perform regulation and control calculation on the N workpiece region cutting control parameters based on the light beam quality parameters and the workpiece cutting surface morphology data by using a PID controller, determine a cutting control correction amount, and perform compensation and closed loop control on the target laser cutting machine based on the cutting control correction amount.

[0059] Further, the workpiece partitioning module 11 is further configured to perform the following steps:

[0060] The current structure attribute information is subjected to key parameter extraction to obtain a workpiece structure attribute parameter set, the workpiece structure attribute parameter set including size shape, material thickness, material type and material characteristics; the structure design information and the current structure attribute information are subjected to cutting comparison to determine workpiece cutting region information; the attribute parameters in the workpiece structure attribute parameter set are subjected to cutting reference priority sequencing according to laser cutting process requirements to obtain structure attribute cutting sequence parameters; the workpiece cutting region information is subjected to cutting equivalent partitioning based on the structure attribute cutting sequence parameters to obtain the N workpiece cutting region information.

[0061] Further, the double-channel building module 12 is further used to execute the following steps:

[0062] Based on the target laser cutting machine, historical data mining is performed to obtain a laser cutting machine working database, the laser cutting machine working database including a beam stability control data set and a beam transmission control data set of each cutting path of a historical cutting workpiece; a beam stability control target and a beam transmission control target are obtained, index extraction is performed on the beam stability control target and the beam transmission control target to obtain a beam stability effect evaluation index set and a beam transmission effect evaluation index set; the beam stability effect evaluation index set and the beam transmission effect evaluation index set are respectively used to perform effect evaluation screening on the beam stability control data set and the beam transmission control data set to obtain a beam stability control sample set and a beam transmission control sample set; the beam stability control sample set and the beam transmission control sample set are respectively trained and optimized to obtain a beam stability control channel and a beam transmission control channel; the beam stability control channel and the beam transmission control channel are connected in parallel to form the cutting machine control double channel.

[0063] Further, the double-channel building module 12 is further used to execute the following steps:

[0064] The beam stability control sample set is subjected to model training and cross-validation optimization using a recurrent neural network to generate an initial stability control analysis model; the beam transmission control sample set is subjected to model training and cross-validation optimization using a convolutional neural network to generate an initial transmission control analysis model; the initial stability control analysis model and the initial transmission control analysis model are subjected to overfitting processing through L1 regularization to obtain a beam stability control analysis model and a beam transmission control analysis model; the beam stability control analysis model and the beam transmission control analysis model are respectively embedded into a laser data processing double channel to obtain the beam stability control channel and the beam transmission control channel.

[0065] Further, the control analysis module 13 is further used to execute the following steps:

[0066] Attribute parameter extraction is performed on the N workpiece cutting region information to obtain N cutting region attribute parameters, the N cutting region attribute parameters including size shape, material thickness, material type, and material characteristics; cutting path planning is performed based on the N cutting region attribute parameters to determine N region cutting path information; the N cutting region attribute parameters and the N region cutting path information are analyzed for cutting control in parallel using the light beam stability control channel and the light beam transmission control channel to obtain N region light beam stability control parameters and N region light beam transmission control parameters; and the N region light beam stability control parameters and the N region light beam transmission control parameters are combined to obtain the N workpiece region cutting control parameters.

[0067] Further, the control analysis module 13 is further configured to perform the following steps:

[0068] According to the characteristic information of the N cutting region attribute parameters, N region cutting path planning algorithms are selected; the N region cutting path planning algorithms are used to perform cutting path optimization on the N cutting region attribute parameters respectively to obtain N region optimal cutting paths; and the N region optimal cutting paths are corrected according to the distribution characteristics of the N workpiece cutting region information to determine the N region cutting path information.

[0069] Further, the control analysis module 13 is further configured to perform the following steps:

[0070] According to the distribution characteristics of the N workpiece cutting region information, cutting path constraint information is determined, the cutting path constraint information including region cutting sequence, cutting path conflict, and cutting direction limitation; the N region optimal cutting paths are corrected based on the cutting path constraint information to determine the N region cutting path information.

[0071] Further, the cutting control module 14 is further configured to perform the following steps:

[0072] Based on the light beam quality parameters and the workpiece cutting surface shape data, workpiece cutting quality prediction is performed to obtain workpiece cutting predicted quality parameters; and the workpiece cutting predicted quality parameters and workpiece cutting expected quality parameters are analyzed for regulation and control using a PID controller to determine a cutting control correction amount.

[0073] Further, the cutting control module 14 is further configured to perform the following steps:

[0074] The PID controller is parameter extracted to obtain controller parameter information, the controller parameter information including a proportional control item, an integral control item and a differential control item; the PID controller is iteratively verified and optimized based on the controller parameter information to obtain a PID optimized controller; a difference between the workpiece cutting predicted quality parameter and the workpiece cutting expected quality parameter is taken as a quality deviation parameter, and the quality deviation parameter is analyzed for cutting control based on the PID optimized controller to determine the cutting control correction amount.

[0075] The foregoing Figure 1 The various variations and specific examples of the laser cutting machine beam stabilization and transmission optimization method in Embodiment One are equally applicable to the laser cutting machine beam stabilization and transmission optimization platform of this embodiment. Through the foregoing detailed description of the laser cutting machine beam stabilization and transmission optimization method, those skilled in the art can clearly understand the implementation method of the laser cutting machine beam stabilization and transmission optimization platform in this embodiment. Therefore, in the interest of brevity, the implementation method of the laser cutting machine beam stabilization and transmission optimization platform in this embodiment will not be described in detail here.

[0076] The present specification and drawings are merely exemplary of the present application and are not intended to limit the scope of the present application. It should be noted that any person skilled in the art can easily think of changes or replacements within the scope of the technology disclosed in the present application, which should be covered by the scope of protection of the present application. In some cases, the actions or steps described in the present application can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

Claims

1. Laser cutting machine beam stabilization and transmission optimization method, characterized in that: The method comprises: Acquire current structural attribute information and structural design information of a workpiece to be cut, and perform cutting equivalent partitioning on the current structural attribute information based on the structural design information to obtain N workpiece cutting area information; Based on the target laser cutting machine, historical data mining and control analysis are carried out to build a cutting machine control dual channel, which includes a beam stabilization control channel and a beam transmission control channel; Using the beam stabilization control channel and the beam transmission control channel in parallel to perform control parameter analysis on the N workpiece cutting area information to obtain N workpiece area cutting control parameters; Real-time monitoring is performed to obtain beam quality parameters and workpiece cutting surface morphology data, and a PID controller is used to adjust and calculate the cutting control parameters of the N workpiece areas based on the beam quality parameters and the workpiece cutting surface morphology data, to determine the cutting control correction amount, and to perform compensation closed-loop control on the target laser cutting machine based on the cutting control correction amount.

2. The laser cutting machine beam stabilization and transmission optimization method according to claim 1, characterized in that: The obtaining of N workpiece cutting area information includes: Extracting key parameters from the current structural attribute information to obtain a workpiece structural attribute parameter set, wherein the workpiece structural attribute parameter set includes size and shape, material thickness, material type, and material properties; Cut and compare the structural design information and the current structural attribute information to determine the area information of the workpiece to be cut; According to the laser cutting process requirements, each attribute parameter in the workpiece structural attribute parameter set is sorted by cutting reference priority to obtain a structural attribute cutting sequence parameter; The information of the area to be cut of the workpiece is subjected to cutting equivalent partitioning based on the structural attribute cutting sequence parameters to obtain the N workpiece cutting area information.

3. The laser cutting machine beam stabilization and transmission optimization method according to claim 1, characterized in that: The dual-channel control of the cutting machine includes: Perform historical data mining based on the target laser cutting machine to obtain a laser cutting machine working database, wherein the laser cutting machine working database includes a beam stabilization control data set and a beam transmission control data set of each cutting path of the historical cutting workpiece; Obtaining a beam stabilization control target and a beam transmission control target, performing index extraction on the beam stabilization control target and the beam transmission control target, and obtaining a beam stabilization effect evaluation index set and a beam transmission effect evaluation index set; Using the beam stabilization effect evaluation index set and the beam transmission effect evaluation index set to respectively perform effect evaluation and screening on the beam stabilization control data set and the beam transmission control data set to obtain a beam stabilization control sample set and a beam transmission control sample set; Performing training and optimization based on the beam stabilization control sample set and the beam transmission control sample set to obtain a beam stabilization control channel and a beam transmission control channel; The beam stabilization control channel and the beam transmission control channel are integrated in parallel to form the cutting machine control dual channel.

4. The laser cutting machine beam stabilization and transmission optimization method according to claim 3, characterized in that: The obtaining of the beam stabilization control channel and the beam transmission control channel includes: Using a recurrent neural network to perform model training and cross-validation tuning on the beam stabilization control sample set to generate an initial stabilization control analysis model; Using a convolutional neural network to perform model training and cross-validation tuning on the beam transmission control sample set to generate an initial transmission control analysis model; performing overfitting processing on the initial stabilization control analysis model and the initial transmission control analysis model through L1 regularization to obtain a beam stabilization control analysis model and a beam transmission control analysis model; The beam stabilization control analysis model and the beam transmission control analysis model are respectively embedded into the laser data processing dual channels to obtain the beam stabilization control channel and the beam transmission control channel.

5. The laser cutting machine beam stabilization and transmission optimization method according to claim 1, characterized in that: The obtaining of N workpiece area cutting control parameters includes: Extracting attribute parameters of the N workpiece cutting area information to obtain N cutting area attribute parameters, wherein the N cutting area attribute parameters include size and shape, material thickness, material type, and material properties; Perform cutting path planning based on the N cutting area attribute parameters to determine cutting path information of the N areas; Using the beam stabilization control channel and the beam transmission control channel in parallel to perform cutting control analysis on the N cutting area attribute parameters and the N area cutting path information, to obtain N area beam stabilization control parameters and N area beam transmission control parameters; Based on the N regional beam stabilization control parameters and the N regional beam transmission control parameters, the N workpiece regional cutting control parameters are obtained.

6. The laser cutting machine beam stabilization and transmission optimization method according to claim 5, characterized in that: The determining of N area cutting path information includes: Selecting N area cutting path planning algorithms according to characteristic information of the N cutting area attribute parameters; Using the N area cutting path planning algorithm to optimize the cutting paths of the N cutting area attribute parameters respectively, to obtain the N area optimal cutting paths; The N-area preferred cutting paths are modified according to the distribution characteristics of the N workpiece cutting area information to determine the N-area cutting path information.

7. The laser cutting machine beam stabilization and transmission optimization method according to claim 6, characterized in that: The determining of N area cutting path information includes: Determining cutting path constraint information according to distribution characteristics of the N workpiece cutting area information, wherein the cutting path constraint information includes area cutting order, cutting path conflict, and cutting direction restriction; Based on the cutting path constraint information, constraint correction is performed on the N-area preferred cutting paths to determine the N-area cutting path information.

8. The laser cutting machine beam stabilization and transmission optimization method according to claim 1, characterized in that: Determining the cutting control correction amount includes: Predicting the workpiece cutting quality based on the beam quality parameters and the workpiece cutting surface morphology data to obtain the workpiece cutting prediction quality parameters; A PID controller is used to regulate and analyze the workpiece cutting predicted quality parameters and the workpiece cutting expected quality parameters to determine the cutting control correction amount.

9. The laser cutting machine beam stabilization and transmission optimization method according to claim 8, characterized in that: Determining the cutting control correction amount includes: Extracting parameters of the PID controller to obtain controller parameter information, wherein the controller parameter information includes a proportional control item, an integral control item, and a differential control item; Performing iterative verification and optimization on the PID controller based on the controller parameter information to obtain a PID optimized controller; The difference between the workpiece cutting predicted quality parameter and the workpiece cutting expected quality parameter is used as a quality deviation parameter, and the quality deviation parameter is subjected to cutting control analysis based on the PID optimization controller to determine the cutting control correction amount.

10. Laser cutting machine beam stabilization and transmission optimization platform, characterized by: For implementing the laser cutting machine beam stabilization and transmission optimization method according to any one of claims 1 to 9, the platform comprises: A workpiece partitioning module is used to obtain current structural attribute information and structural design information of the workpiece to be cut, and perform cutting equivalent partitioning on the current structural attribute information based on the structural design information to obtain N workpiece cutting area information; A dual-channel building module is used to perform historical data mining and control analysis based on the target laser cutting machine, and to build a dual-channel cutting machine control system, which includes a beam stabilization control channel and a beam transmission control channel. a control analysis module, configured to perform control parameter analysis on the N workpiece cutting area information in parallel using the beam stabilization control channel and the beam transmission control channel to obtain N workpiece area cutting control parameters; The cutting control module is used to monitor and obtain beam quality parameters and workpiece cutting surface morphology data in real time, adopt a PID controller to adjust and calculate the cutting control parameters of the N workpiece areas based on the beam quality parameters and workpiece cutting surface morphology data, determine the cutting control correction amount, and perform compensation closed-loop control on the target laser cutting machine based on the cutting control correction amount.

Images