Light beam stabilization and transmission optimization method and platform for laser cutting machine

Abstract

The invention discloses a laser cutting machine light beam stabilization and transmission optimization method and platform, and relates to the technical field of laser cutting, and the method comprises the following steps: carrying out cutting equivalent partition based on current structure attribute information and structure design information of a to-be-cut workpiece to obtain N pieces of workpiece cutting area information; cutting machine control double channels are built and comprise a light beam stability control channel and a light beam transmission control channel, control parameter analysis is conducted on the information of the N workpiece cutting areas in parallel, and N workpiece area cutting control parameters are obtained; and a PID controller is adopted to carry out regulation and control calculation on the N workpiece area cutting control parameters based on the light beam quality parameters and the workpiece cutting surface form data, and the cutting control correction is determined to carry out compensation closed-loop control on the target laser cutting machine. The technical effects that light beam stable control and transmission loss reduction are achieved, the metal cutting precision and stability are improved, and then the workpiece laser cutting quality is ensured are achieved.

Description

Technical Field

[0001] This application relates to the field of laser cutting technology, and particularly to a method and platform for optimizing the beam stability and transmission of a laser cutting machine. Background Art

[0002] As a key technology in modern metal manufacturing, laser cutting technology is developing at an unprecedented speed. However, during the laser cutting process, the instability of the beam and the problem of transmission loss have always been the key factors affecting the quality and efficiency of metal cutting. The instability of the beam may cause problems such as rough edges and deformed cutting surfaces in metal cutting, while transmission loss will reduce the power density of the laser, affecting the cutting depth and speed of the metal. Therefore, how to optimize the beam stability and transmission of a laser cutting machine has become an urgent problem to be solved. Summary of the Invention

[0003] By providing a method and platform for optimizing the beam stability and transmission of a laser cutting machine, this application solves the technical problem in the prior art that the control of the laser cutting beam is unstable and there is transmission loss, resulting in poor metal cutting quality, and achieves the technical effect of realizing beam stability control and reducing transmission loss by building a dual-channel control for the cutting machine to analyze control parameters, improving the metal cutting accuracy and stability, and thus ensuring the quality of laser cutting of workpieces.

[0004] In view of the above problems, in a first aspect, this application provides a method for optimizing the beam stability and transmission of a laser cutting machine. The method includes: 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 to obtain N workpiece cutting area information; performing historical data mining and control analysis on a target laser cutting machine to build a dual-channel control for the cutting machine, where the dual-channel control for the cutting machine includes a beam stability control channel and a beam transmission control channel; using the beam stability 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; monitoring and obtaining beam quality parameters and workpiece cutting surface morphology data in real time, using a PID controller to perform regulation calculation on the N workpiece area cutting control parameters based on the beam quality parameters and workpiece cutting surface morphology data to determine 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] On the other hand, the present application also provides a laser cutting machine beam stability and transmission optimization platform, which includes: a workpiece partitioning module, configured to obtain the 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, configured to perform historical data mining and control analysis based on a target laser cutting machine, and build a dual-channel cutting machine control channel, where the dual-channel cutting machine control channel includes a beam stability control channel and a beam transmission control channel; a control parsing module, configured to use the beam stability control channel and the beam transmission control channel to concurrently perform control parameter parsing on the N workpiece cutting area information to obtain N workpiece area cutting control parameters; a cutting control module, configured to monitor and obtain beam quality parameters and workpiece cutting surface morphology data in real time, use a PID controller to perform regulation calculations on the N workpiece area cutting control parameters based on the beam quality parameters and workpiece cutting surface morphology data to determine a cutting control correction amount, and perform compensated closed-loop control on the target laser cutting machine based on the cutting control correction amount.

[0006] One or more technical solutions provided in the present application have at least the following technical effects or advantages: Due to the technical solution of 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, then performing historical data mining and control analysis based on a target laser cutting machine to build a dual-channel cutting machine control channel, where the dual-channel cutting machine control channel includes a beam stability control channel and a beam transmission control channel, concurrently performing control parameter parsing on the N workpiece cutting area information based on this to obtain N workpiece area cutting control parameters, and at the same time monitoring and obtaining beam quality parameters and workpiece cutting surface morphology data in real time, using a PID controller to perform regulation calculations on the N workpiece area cutting control parameters based on the beam quality parameters and workpiece cutting surface morphology data to determine a cutting control correction amount, and performing compensated closed-loop control on the target laser cutting machine with this. Furthermore, the technical effect of realizing beam stability control and reducing transmission loss, improving metal cutting accuracy and stability, and thus ensuring the laser cutting quality of the workpiece is achieved by building a dual-channel cutting machine control channel for control parameter parsing.

[0007] The above description is only an overview of the technical solutions of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the present application more obvious and understandable, the specific embodiments of the present application are specifically listed below. Description of the Drawings

[0008] Figure 1 It is a flowchart of the method for optimizing the beam stability and transmission of the laser cutting machine of the present application.

[0009] Figure 2 This is a schematic flow chart for obtaining information on the cutting areas of N workpieces in the method for optimizing the beam stability and transmission of the laser cutting machine of this application.

[0010] Figure 3 This is a schematic structural diagram of the platform for optimizing the beam stability and transmission of the laser cutting machine of this application.

[0011] Explanation of reference numerals: workpiece partitioning module 11, dual-channel building module 12, control parsing module 13, cutting control module 14. Detailed implementation manners

[0012] By providing the method and platform for optimizing the beam stability and transmission of the laser cutting machine, this application solves the technical problem in the prior art that the control of the laser cutting beam is unstable and there are losses in transmission, resulting in poor metal cutting quality. It achieves the technical effect of parsing control parameters by building a dual-channel for the cutting machine control, realizing stable beam control and reducing transmission losses, improving the metal cutting accuracy and stability, and thus ensuring the laser cutting quality of the workpiece.

[0013] In order to make the purpose, technical solutions and advantages of this application clearer, the following further details this application in conjunction with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application.

[0014] The following describes this application in conjunction with the drawings in this application.

[0015] Embodiment 1, as Figure 1 shown, this application provides a method for optimizing the beam stability and transmission of a laser cutting machine, and the method includes: Step S100: Obtain the 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 information on N workpiece cutting areas.

[0016] As Figure 2 shown, further, for the step of obtaining information on N workpiece cutting areas, this application step further includes: Extract key parameters from the current structural attribute information of the workpiece to obtain a workpiece structural attribute parameter set, where the workpiece structural attribute parameter set includes dimensional shape, material thickness, material type, and material properties; perform cutting comparison on the structural design information and the current structural attribute information to determine the workpiece area to be cut; sort the attribute parameters in the workpiece structural attribute parameter set according to the requirements of the laser cutting process to obtain a structural attribute cutting sequence parameter; perform cutting equivalent partitioning on the workpiece area to be cut based on the structural attribute cutting sequence parameter to obtain the N workpiece cutting area information.

[0017] Specifically, when processing the laser cutting task of the workpiece to be cut, it is first necessary to obtain and analyze the current structural attribute information and structural design information of the workpiece. Among them, the current structural attribute information includes the specific physical characteristics of the workpiece, such as dimensions, shape, material thickness, material type, and material properties (such as hardness, thermal conductivity, etc.); the structural design information is the workpiece design drawing information, including cutting shape, dimensions, design angle, etc. Based on the structural design information, perform cutting equivalent partitioning on the current structural attribute information, that is, divide the area of the workpiece to be cut into several areas with similar structural characteristics or functional requirements. Specifically: First, extract key parameters from the current structural attribute information to obtain a workpiece structural attribute parameter set. The workpiece structural attribute parameter set is a type of workpiece structural parameter that has a greater impact on laser cutting, including dimensional shape, material thickness, material type, and material properties. This step is the basis for subsequent analysis and cutting.

[0018] Then, perform cutting comparison on the structural design information and the current structural attribute information to determine which areas of the workpiece need to be cut, and then determine the workpiece area to be cut. This step requires precise matching of the design requirements and the actual workpiece attributes to ensure the accuracy of cutting. Sort the attribute parameters in the workpiece structural attribute parameter set according to the requirements of the laser cutting process. For example, according to the degree of influence on the laser cutting process accuracy requirements, sort the attribute parameters in the workpiece structural attribute parameter set for the reference priority of cutting area division, and arrange the attribute parameters with greater influence in the front order. Then, obtain the structural attribute cutting sequence parameter according to the degree of influence, and use this as the priority sequence when referring to the cutting area division. Exemplarily, sort the attribute parameters in the workpiece structural attribute parameter set as dimensional shape, material thickness, material type, and material properties, etc.

[0019] Based on the structure attribute cutting sequence parameters, perform cutting equivalent partitioning on the information of the area to be cut of the workpiece, divide the area to be cut of the workpiece into several areas with similar structural characteristics or functional requirements, and obtain N pieces of workpiece cutting area information, that is, a set of areas with the same or similar cutting conditions, cutting parameters, and cutting effects. Through the equivalent area segmentation of the workpiece, specific cutting parameter analysis is realized for different structural areas of the workpiece, the cutting process is simplified, and thus the cutting quality and cutting efficiency of the workpiece are improved.

[0020] Step S200: Based on the target laser cutting machine, conduct historical data mining and control analysis, and build a dual-channel control for the cutting machine. The dual-channel control for the cutting machine includes a beam stability control channel and a beam transmission control channel.

[0021] Furthermore, for building the dual-channel control for the cutting machine, the steps of this application further include: Based on the target laser cutting machine, conduct historical data mining to obtain the working database of the laser cutting machine. The working database of the laser cutting machine includes the beam stability control data set and the beam transmission control data set of each cutting path of the historical cutting workpieces; obtain the beam stability control target and the beam transmission control target, extract the indicators for the beam stability control target and the beam transmission control target, and obtain the beam stability effect evaluation index set and the beam transmission effect evaluation index set; use the beam stability effect evaluation index set and the beam transmission effect evaluation index set to respectively conduct effect evaluation and screening on the beam stability control data set and the beam transmission control data set to obtain the beam stability control sample set and the beam transmission control sample set; based on the beam stability control sample set and the beam transmission control sample set, conduct training and optimization respectively to obtain the beam stability control channel and the beam transmission control channel; parallelly integrate the beam stability control channel and the beam transmission control channel to form the built dual-channel control for the cutting machine.

[0022] Furthermore, for obtaining the beam stability control channel and the beam transmission control channel, the steps of this application further include: Use a recurrent neural network to conduct model training and cross-validation optimization on the beam stability control sample set to generate an initial stability control analysis model; use a convolutional neural network to conduct model training and cross-validation optimization on the beam transmission control sample set to generate an initial transmission control analysis model; perform overfitting processing on the initial stability control analysis model and the initial transmission control analysis model through L1 regularization to obtain the beam stability control analysis model and the beam transmission control analysis model; respectively embed the beam stability control analysis model and the beam transmission control analysis model into the dual-channel laser data processing to obtain the beam stability control channel and the beam transmission control channel.

[0023] Specifically, historical data mining and control analysis are carried out based on the target laser cutting machine. The target laser cutting machine is a laser cutting machine that performs cutting processing on the workpiece to be cut. Based on the historical data of this cutting machine, a dual-channel cutting machine control system is built. The dual-channel cutting machine control system is used to perform parameter analysis and processing on the beam stability and beam transmission in the workpiece cutting area, including a beam stability control channel and a beam transmission control channel. The specific process of building the dual-channel cutting machine control system is as follows: First, historical data mining is carried out based on the target laser cutting machine to obtain a corresponding laser cutting machine working database. The laser cutting machine working database includes the historical working data of laser cutting machines with the same specification model as the target laser cutting machine, that is, the beam stability control data sets and beam transmission control data sets for each cutting path of the historical cutting workpieces. These data sets detail the area attributes of the cutting workpieces, cutting path information, and executed cutting control parameters, including cutting control parameters related to beam stability such as laser power and cutting speed, cutting control parameters related to beam transmission such as the focal length of the focusing lens and defocus amount, and the stability and transmission conditions of the beam during each cutting process, including but not limited to beam intensity, beam offset, transmission path, speed, beam attenuation, etc.

[0024] Define the beam stability control target and the beam transmission control target, such as the stability of beam intensity, the accuracy of the transmission path, etc. For the above control targets, relevant evaluation indicators are extracted from the database to obtain a beam stability effect evaluation index set, such as beam intensity volatility, position offset, etc.; and a beam transmission effect evaluation index set, such as transmission path deviation, cutting surface quality, etc. These indicators should be able to accurately reflect the beam stability and transmission effect. 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 thresholds or using methods such as cluster analysis, samples with excellent performance (i.e., meeting or exceeding the control target) are selected to form a beam stability control sample set, including the beam stability data set during the cutting process and the corresponding workpiece-related cutting control parameters, and a beam transmission control sample set, including the beam transmission data set during the cutting process and the corresponding workpiece-related cutting control parameters, as the sample basis for subsequent laser cutting parameter analysis and processing.

[0025] Based on the beam stability control sample set and the beam transmission control sample set, training and optimization are carried out respectively. First, a recurrent neural network is designed. Variants such as LSTM or GRU can be selected to adapt to the processing of time series data. The recurrent neural network is used to train the model on the beam stability control sample set. Appropriate hyperparameters (such as learning rate, batch size, number of iterations, etc.) are set according to historical experience. Cross-validation (such as K-fold cross-validation) is used to evaluate the performance of the model. According to the results of cross-validation, the model structure and hyperparameters are adjusted to optimize the model performance and ensure that the model can also perform well on unseen data, generating an initial stability control analysis model. 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 image or feature extraction tasks. The convolutional neural network is used to train the model on the beam transmission control sample set, and cross-validation is also used to evaluate the performance of the model. According to the results of cross-validation, the model structure and hyperparameters are adjusted to optimize the model performance, generating an initial transmission control analysis model.

[0026] Perform overfitting processing on the initial stability control analysis model and the initial transmission control analysis model through L1 regularization (Lasso regression). L1 regularization is achieved by adding the sum of the absolute values of the weights to the loss function. For the initial stability control analysis model (RNN model), on the basis of the original loss function (such as mean squared error MSE), add the sum of the absolute values of all weights multiplied by the regularization coefficient λ. For the initial transmission control analysis model (CNN model), similarly, add the sum of the absolute values of the weights multiplied by the regularization coefficient λ to the original loss function (such as cross-entropy loss). Usually, the best regularization coefficient λ can be found through cross-validation. 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 performance of the validation set the best (or close to the best) as the final regularization coefficient. If λ is too large, it may lead to underfitting of the model (that is, the model is too simple to capture the complex patterns in the data), while 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 the regularization coefficient) to find the best balance point, obtaining the corresponding beam stability control analysis model for analyzing and processing laser cutting control parameters related to beam stability according to the cutting workpiece area information; and the beam transmission control analysis model for analyzing and processing laser cutting control parameters related to beam transmission according to the cutting workpiece area information.

[0027] Embed the beam stability control analysis model and the beam transmission control analysis model with qualified performance after training into the dual channels of laser data processing respectively. The dual channels of laser data processing are data processing channels for analyzing laser cutting control parameters of the information of the cutting workpiece area. Place and embed the beam stability control analysis model and the beam transmission control analysis model into one of the data processing channels in the dual channels of laser data processing respectively to obtain the beam stability control channel after model embedding, which is used to analyze the laser cutting control parameters related to beam stability through the beam stability control analysis model; and the beam transmission control channel, which is used to analyze the laser cutting control parameters related to beam transmission through the beam transmission control analysis model. Combine the beam stability control channel and the beam transmission control channel in parallel to form the dual channels of the cutting machine control, which is used to input the information of the cutting workpiece area into the two channels respectively, and perform parallel processing by their respective models and output the corresponding control analysis results. Realize the coordinated and synchronous analysis of the beam stability control and the beam transmission control through the dual channels of the cutting machine control, so as to ensure the precise control during the laser cutting process.

[0028] Step S300: Use the beam stability control channel and the beam transmission control channel to parallelly analyze the control parameters of the N workpiece cutting area information to obtain the cutting control parameters of the N workpiece areas.

[0029] Furthermore, for obtaining the cutting control parameters of the N workpiece areas, the steps of this application further include: Extract the attribute parameters of the N workpiece cutting area information to obtain N cutting area attribute parameters, where the N cutting area attribute parameters include size and shape, material thickness, material type, and material characteristics; based on the N cutting area attribute parameters, plan the cutting path to determine the N area cutting path information; use the beam stability control channel and the beam transmission control channel to parallelly perform cutting control analysis on the N cutting area attribute parameters and the N area cutting path information to obtain N area beam stability control parameters and N area beam transmission control parameters; based on the N area beam stability control parameters and the N area beam transmission control parameters, form and obtain the cutting control parameters of the N workpiece areas.

[0030] Furthermore, for determining the N area cutting path information, the steps of this application further include: According to the characteristic information of the N cutting area attribute parameters, select N area cutting path planning algorithms; use the N area cutting path planning algorithms to respectively optimize the cutting paths of the N cutting area attribute parameters to obtain N area optimal cutting paths; modify the N area optimal cutting paths according to the distribution characteristics of the N workpiece cutting area information to determine the N area cutting path information.

[0031] Furthermore, the step of determining the cutting path information of the N regions in this application further includes: According to the distribution characteristics of the cutting area information of the N workpieces, determine the cutting path constraint information, where the cutting path constraint information includes the area cutting sequence, cutting path conflict, and cutting direction limitation; based on the cutting path constraint information, correct the preferred cutting paths of the N regions to determine the cutting path information of the N regions.

[0032] Specifically, the beam stability control channel and the beam transmission control channel are used in parallel to analyze the control parameters of the cutting area information of the N workpieces. First, extract the attribute parameters of the cutting area information of the N workpieces, digitally describe their key parameters, and obtain the corresponding cutting area attribute parameters of the N regions. The cutting area attribute parameters of the N regions include size and shape, material thickness, material type, and material properties, etc., providing basic data for subsequent cutting path planning and cutting control analysis. Then, based on the cutting area attribute parameters of the N regions, perform cutting path planning. The specific planning process is as follows: according to the characteristic information of the cutting area attribute parameters of the N regions, select appropriate cutting path planning algorithms for the N regions. For example, for regions with regular shapes and uniform materials, simple greedy algorithms or dynamic programming algorithms can be selected; for regions with complex shapes and variable materials, more complex genetic algorithms or simulated annealing algorithms may need to be considered. The selected algorithm should be able to fully consider factors such as cutting efficiency, material utilization rate, and cutting quality. Use the cutting path planning algorithms for the N regions to optimize the cutting paths of the cutting area attribute parameters of the N regions respectively, and obtain the corresponding preferred cutting paths of the N regions. The purpose of this step is to find the optimal cutting path within each cutting area to maximize cutting efficiency and material utilization rate. Evaluate the cutting path optimization results to check whether the cutting path meets the cutting requirements, such as accuracy, surface quality, etc. If the requirements are not met, the algorithm parameters need to be adjusted or other algorithms need to be selected to re-optimize.

[0033] To ensure the practical applicability of the cutting path, according to the distribution characteristics of the N workpiece cutting area information, such as the relative position between areas, shape differences, material changes, etc., the preferred cutting paths for the N areas are corrected. These distribution characteristics will have an important impact on the correction and determination of cutting path constraints. First, according to the distribution characteristics of the N workpiece cutting area information, the cutting path constraint information is determined. The cutting path constraint information includes the area cutting sequence, determining the cutting sequence of different cutting areas to optimize cutting efficiency and reduce cutting conflicts; cutting path conflicts, identifying and avoiding potential conflicts between cutting paths to ensure the safety and smooth progress of the cutting process; and cutting direction restrictions. According to the characteristics of the material and the performance of the cutting machine, the limiting conditions of the cutting direction are determined to improve cutting quality and efficiency. Based on the cutting path constraint information, the preferred cutting paths for the N areas are constrained and corrected, and the impact of these constraint information on the preferred cutting paths is evaluated, which may involve the analysis of potential negative impacts on cutting efficiency, material utilization rate, and cutting quality. According to the specific content and impact degree of the constraint information, a targeted correction strategy is formulated. This may include adjusting the cutting sequence, optimizing the cutting path to avoid conflicts, adjusting the cutting direction to meet the limiting conditions, etc. On the basis of the preferred cutting paths, specific correction operations are carried out according to the formulated correction strategy, including re-planning the cutting path, adjusting the cutting parameters, etc. The corrected cutting paths are verified to ensure that they meet all the constraint conditions, and then the cutting path information of the N areas after correction is determined, which clearly and accurately reflects the key information such as the cutting path, cutting sequence, cutting direction, etc. of each cutting area, so as to maintain the balance of cutting efficiency, material utilization rate, and cutting quality as much as possible.

[0034] The beam stability control channel and the beam transmission control channel are used in parallel to perform cutting control analysis on the N cutting area attribute parameters and the N area cutting path information, and the corresponding N area beam stability control parameters after analysis and processing are obtained, such as laser power, cutting speed, etc.; and N area beam transmission control parameters, such as focal length of the focusing lens, defocus amount, etc. Based on the N area beam stability control parameters and the N area beam transmission control parameters, the cutting control parameters for each workpiece area are formed, that is, the cutting control parameters for the N workpiece areas. These parameters will constitute a complete instruction set for the cutting process to be used for laser cutting control of each area of the workpiece, guiding the operation of the cutting equipment, ensuring the smooth progress of the cutting process and the stable and reliable cutting quality. Achieve targeted cutting of the workpiece area, improve the accuracy of cutting control, and then ensure the laser cutting effect.

[0035] Step S400: Monitor and obtain beam quality parameters and workpiece cutting surface morphology data in real time. Use a PID controller to perform regulation calculations on 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 compensated closed-loop control on the target laser cutting machine based on the cutting control correction amount.

[0036] Furthermore, for determining the cutting control correction amount, the steps of this application further include: Predict the workpiece cutting quality based on the beam quality parameters and workpiece cutting surface morphology data to obtain workpiece cutting predicted quality parameters; use a PID controller to perform regulation analysis on the workpiece cutting predicted quality parameters and workpiece cutting desired quality parameters to determine the cutting control correction amount.

[0037] Furthermore, for determining the cutting control correction amount, the steps of this application further include: Extract the parameters of the PID controller to obtain controller parameter information, where the controller parameter information includes a proportional control term, an integral control term, and a derivative control term; perform iterative verification and optimization on the PID controller based on the controller parameter information to obtain a PID optimized controller; use the difference between the workpiece cutting predicted quality parameters and workpiece cutting desired quality parameters as a quality deviation parameter, and perform cutting regulation analysis on the quality deviation parameter based on the PID optimized controller to determine the cutting control correction amount.

[0038] Specifically, use a high-precision sensor to monitor and obtain beam quality parameters in real time, such as beam mode, power density, energy density, etc., and ensure the synchronization between the sensor and the laser beam to accurately capture the dynamic changes of the laser beam during the cutting process; use a vision sensor or image processing technology to monitor the morphology data of the workpiece cutting surface in real time, such as the roughness, width, inclination, etc. of the cutting surface. To ensure the closed-loop regulation of workpiece laser cutting, use a PID controller to perform regulation calculations on the cutting control parameters of the N workpiece areas based on the beam quality parameters and workpiece cutting surface morphology data. First, predict the workpiece cutting quality based on the beam quality parameters and workpiece cutting surface morphology data. Specifically: establish a workpiece cutting quality prediction model based on historical cutting data and machine learning algorithms (such as neural networks, support vector machines, etc.), input the beam quality parameters and workpiece cutting surface morphology data monitored in real time, as well as relevant cutting control parameters (such as laser power, cutting speed, gas flow, etc.), and use the prediction model to predict the workpiece cutting quality and output the workpiece cutting predicted quality parameters. These predicted quality parameters may include predicted values of the roughness of the cutting surface, width, etc.

[0039] According to the expected requirements of workpiece cutting, set the expected quality parameters for workpiece cutting, and these expected quality parameters should conform to the actual production requirements. Use a PID controller to conduct regulation and analysis on the predicted quality parameters and the expected quality parameters of workpiece cutting. The specific regulation process is as follows: The PID controller consists of a proportional control term (P), an integral control term (I), and a derivative control term (D). Extract key parameters from the PID controller to obtain controller parameter information. The controller parameter information includes the proportional control term, which is responsible for providing a control output according to the magnitude of the current error; the integral control term, which is responsible for eliminating the steady-state error and making the system output finally stable at the set value; the derivative control term, which is responsible for predicting the change trend of the error and making adjustments in advance to suppress overshoot and oscillation. The selection of these parameters will directly affect the stability and response speed of the system.

[0040] Based on the controller parameter information, conduct iterative verification and optimization on the PID controller. First, according to the system characteristics and requirements, determine the search ranges of the proportional control term, the integral control term, and the derivative control term to obtain a search space, that is, the numerical selection range of the controller parameters. Then establish a mathematical model of the workpiece cutting process, 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 the ant colony algorithm and the particle swarm optimization algorithm (PSO) can be used to search for the optimal PID parameter combination. These algorithms iteratively search for the optimal solution by simulating a certain behavior in nature (such as ants looking for food, particles moving in the search space). Initialize the parameters and states of the optimization algorithm. In each iteration, run the simulation according to the current parameter combination and calculate the performance indicators (such as steady-state error, rise time, overshoot, etc.). Update the state of the optimization algorithm (such as pheromone concentration, particle position, and velocity, etc.) according to the performance indicators. Repeat the iterative process until the convergence condition is met or the maximum number of iterations is reached. After the iteration ends, output the parameter combination of the optimal proportional control term, integral control term, and derivative control term to obtain the optimized PID optimization controller.

[0041] The difference between the predicted quality parameter of workpiece cutting and the desired quality parameter of workpiece cutting is used as the quality deviation parameter, and the optimal PID control parameter combination is applied to the PID controller. According to the acceptance range of cutting quality, a reasonable quality deviation threshold is set. When the quality deviation exceeds this threshold, the PID optimization controller is triggered for regulation. Based on the PID optimization controller, cutting regulation analysis is carried out on the quality deviation parameter, and the calculated quality deviation parameter is used as the input signal to be transmitted to the PID optimization controller. The PID optimization controller calculates the cutting control correction amount according to the input quality deviation parameter according to the PID control algorithm, determines the cutting control correction amount, and the correction amount may include the adjustment amount of laser power, the change amount of cutting speed, or the increase or decrease amount of gas flow, etc. And based on the cutting control correction amount, closed-loop compensation control is carried out on the target laser cutting machine, and the relevant parameters of the laser cutting machine are adjusted according to the cutting control correction amount output by the PID controller. Continue to monitor the adjusted cutting quality parameter to evaluate the regulation effect. If the adjusted cutting quality still does not meet the requirements (that is, the quality deviation is still above the threshold), the quality deviation is calculated again and input into the PID controller for a new round of regulation calculation. Through multiple iterative adjustments, the best cutting parameter combination is gradually approached until the cutting quality meets the requirements. Record the key data in the whole regulation process, such as quality deviation parameter, cutting control correction amount, adjusted cutting parameters, etc. 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 the precise closed-loop control of the laser cutting machine, beam stability control and transmission loss reduction are realized, the metal cutting accuracy and stability are improved, and thus the laser cutting quality of the workpiece is ensured and the cutting production efficiency is improved.

[0042] In summary, the laser cutting machine beam stability and transmission optimization method provided by this application has the following technical effects: Due to the adoption of the technical solution of performing cutting equivalent partitioning based on the current structural attribute information and structural design information of the workpiece to be cut, obtaining N workpiece cutting area information, then performing historical data mining and control analysis based on the target laser cutting machine, building a dual-channel cutting machine control system, where the dual-channel cutting machine control system includes a beam stability control channel and a beam transmission control channel, based on which the control parameters of the N workpiece cutting area information are parsed in parallel to obtain N workpiece area cutting control parameters, and at the same time, the beam quality parameters and workpiece cutting surface morphology data are monitored and acquired in real time, and a PID controller is used to perform regulation calculations on the N workpiece area cutting control parameters based on the beam quality parameters and workpiece cutting surface morphology data to determine the cutting control correction amount, so as to perform compensation closed-loop control on the target laser cutting machine. Furthermore, the technical effect of realizing beam stability control and reducing transmission loss, improving the metal cutting accuracy and stability, and thus ensuring the workpiece laser cutting quality is achieved by building a dual-channel cutting machine control system for control parameter parsing.

[0043] Embodiment 2. Based on the same inventive concept as the laser cutting machine beam stability and transmission optimization method in the foregoing embodiment, the present invention also provides a laser cutting machine beam stability and transmission optimization platform, as Figure 3 shown, the platform includes: A workpiece partitioning module 11, configured to obtain the 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.

[0044] A dual-channel building module 12, configured to perform historical data mining and control analysis based on the target laser cutting machine, and build a dual-channel cutting machine control system, where the dual-channel cutting machine control system includes a beam stability control channel and a beam transmission control channel.

[0045] A control parsing module 13, configured to use the beam stability control channel and the beam transmission control channel to parse the control parameters of the N workpiece cutting area information in parallel to obtain N workpiece area cutting control parameters.

[0046] A cutting control module 14, configured to monitor and acquire the beam quality parameters and workpiece cutting surface morphology data in real time, use a PID controller to perform regulation calculations on the N workpiece area cutting control parameters based on the beam quality parameters and workpiece cutting surface morphology data to 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.

[0047] Furthermore, the workpiece partitioning module 11 is further configured to perform the following steps: Extract key parameters from the current structural attribute information to obtain a workpiece structural attribute parameter set, where the workpiece structural attribute parameter set includes dimensional shape, material thickness, material type, and material properties; perform cutting comparison on the structural design information and the current structural attribute information to determine the workpiece area to be cut information; sort the attribute parameters in the workpiece structural attribute parameter set according to the requirements of the laser cutting process to obtain a structural attribute cutting sequence parameter; perform cutting equivalent partitioning on the workpiece area to be cut information based on the structural attribute cutting sequence parameter to obtain the N workpiece cutting area information.

[0048] Further, the dual-channel building module 12 is further configured to perform the following steps: Mine historical data based on the target laser cutting machine to obtain a laser cutting machine working database, where the laser cutting machine working database includes a beam stability control data set and a beam transmission control data set for each cutting path of the historical cutting workpiece; obtain a beam stability control target and a beam transmission control target, extract indicators from 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; use the beam stability effect evaluation index set and the beam transmission effect evaluation index set to perform effect evaluation and screening on the beam stability control data set and the beam transmission control data set respectively to obtain a beam stability control sample set and a beam transmission control sample set; perform training and optimization on the beam stability control sample set and the beam transmission control sample set respectively to obtain a beam stability control channel and a beam transmission control channel; perform parallel integration on the beam stability control channel and the beam transmission control channel to form the dual-channel for building the cutting machine control.

[0049] Further, the dual-channel building module 12 is further configured to perform the following steps: Use a recurrent neural network to perform model training and cross-validation optimization on the beam stability control sample set to generate an initial stability control analysis model; use a convolutional neural network to perform model training and cross-validation optimization on the beam transmission control sample set to generate an initial transmission control analysis model; perform overfitting processing on the initial stability control analysis model and the initial transmission control analysis model through L1 regularization to obtain a beam stability control analysis model and a beam transmission control analysis model; embed the beam stability control analysis model and the beam transmission control analysis model into the dual-channel of laser data processing respectively to obtain the beam stability control channel and the beam transmission control channel.

[0050] Further, the control analysis module 13 is further configured to perform the following steps: Extract the attribute parameters of the cutting area information of the N workpieces to obtain N cutting area attribute parameters, where the N cutting area attribute parameters include size and shape, material thickness, material type, and material properties; plan the cutting path based on the N cutting area attribute parameters to determine the cutting path information of N areas; use the beam stability 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 stability control parameters and N area beam transmission control parameters; based on the N area beam stability control parameters and the N area beam transmission control parameters, form and obtain the cutting control parameters of the N workpiece areas.

[0051] Further, the control analysis module 13 is further configured to perform the following steps: According to the characteristic information of the N cutting area attribute parameters, select N area cutting path planning algorithms; use the N area cutting path planning algorithms to optimize the cutting paths of the N cutting area attribute parameters respectively to obtain N area optimal cutting paths; correct the N area optimal cutting paths according to the distribution characteristics of the N workpiece cutting area information to determine the cutting path information of N areas.

[0052] Further, the control analysis module 13 is further configured to perform the following steps: According to the distribution characteristics of the N workpiece cutting area information, determine the cutting path constraint information, where the cutting path constraint information includes area cutting sequence, cutting path conflict, and cutting direction limitation; perform constraint correction on the N area optimal cutting paths based on the cutting path constraint information to determine the cutting path information of N areas.

[0053] Further, the cutting control module 14 is further configured to perform the following steps: Predict the cutting quality of the workpiece based on the beam quality parameters and the workpiece cutting surface morphology data to obtain the predicted cutting quality parameters of the workpiece; use a PID controller to perform regulation and analysis on the predicted cutting quality parameters of the workpiece and the expected cutting quality parameters of the workpiece to determine the cutting control correction amount.

[0054] Further, the cutting control module 14 is further configured to perform the following steps: Extract parameters of the PID controller to obtain controller parameter information, where the controller parameter information includes a proportional control term, an integral control term, and a derivative control term; perform iterative verification and optimization on the PID controller based on the controller parameter information to obtain a PID optimized controller; use the difference between the predicted quality parameter of workpiece cutting and the desired quality parameter of workpiece cutting as a quality deviation parameter, and perform cutting control analysis on the quality deviation parameter based on the PID optimized controller to determine the cutting control correction amount.

[0055] The foregoing Figure 1 All the various change modes and specific examples of the laser cutting machine beam stability and transmission optimization method in Embodiment 1 are equally applicable to the laser cutting machine beam stability and transmission optimization platform of this embodiment. Through the foregoing detailed description of the laser cutting machine beam stability and transmission optimization method, those skilled in the art can clearly know the implementation method of the laser cutting machine beam stability and transmission optimization platform in this embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0056] This specification and the drawings are only exemplary descriptions of the present application, but the protection scope of the present application is not limited thereto. It should be noted that any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all of them should be covered within the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be executed in a different order from that in the embodiment and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. Method for optimizing beam stability and transmission of a laser cutting machine, characterized in that, The method includes: 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; Based on the target laser cutting machine, performing historical data mining and control analysis, and building a dual-channel cutting machine control, where the dual-channel cutting machine control includes a beam stability control channel and a beam transmission control channel; Using the beam stability control channel and the beam transmission control channel to perform parallel parsing of the control parameters for the N workpiece cutting area information to obtain N workpiece area cutting control parameters; Real-time monitoring and obtaining beam quality parameters and workpiece cutting surface morphology data, using a PID controller to perform regulation calculation on the N workpiece area cutting control parameters based on the beam quality parameters and 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.

2. The method for optimizing the beam stability and transmission of a laser cutting machine according to claim 1, wherein The obtaining of the N workpiece cutting area information includes: Extracting key parameters from the current structural attribute information to obtain a workpiece structural attribute parameter set, where the workpiece structural attribute parameter set includes dimensional shape, material thickness, material type, and material properties; Performing cutting comparison between the structural design information and the current structural attribute information to determine the workpiece to-be-cut area information; Sorting the attribute parameters in the workpiece structural attribute parameter set according to the cutting reference priority requirements of the laser cutting process to obtain a structural attribute cutting sequence parameter; Performing cutting equivalent partitioning on the workpiece to-be-cut area information based on the structural attribute cutting sequence parameter to obtain the N workpiece cutting area information.

3. The method for optimizing the beam stability and transmission of a laser cutting machine according to claim 1, characterized in that, The building of the dual-channel cutting machine control includes: Based on the target laser cutting machine, performing historical data mining to obtain a laser cutting machine working database, where the laser cutting machine working database includes a beam stability control data set and a beam transmission control data set for each cutting path of the historical cutting workpieces; Obtaining the beam stability control target and the beam transmission control target, extracting indicators from 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; Using the beam stability effect evaluation index set and the beam transmission effect evaluation index set to perform effect evaluation and screening on the beam stability control data set and the beam transmission control data set respectively to obtain a beam stability control sample set and a beam transmission control sample set; Based on the beam stability control sample set and the beam transmission control sample set, performing training and optimization respectively to obtain a beam stability control channel and a beam transmission control channel; Performing parallel integration on the beam stability control channel and the beam transmission control channel to form the built dual-channel cutting machine control.

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

5. The method for optimizing the beam stability and transmission of a laser cutting machine according to claim 1, wherein The obtaining of the N workpiece area cutting control parameters includes: Attribute parameters of the N workpiece cutting area information are extracted to obtain N cutting area attribute parameters, and the N cutting area attribute parameters include size and shape, material thickness, material type, and material characteristics; Based on the N cutting area attribute parameters, cutting path planning is performed to determine N area cutting path information; The beam stable control channel and the beam transmission control channel are used 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 stable control parameters and N area beam transmission control parameters; Based on the N area beam stable control parameters and the N area beam transmission control parameters, the N workpiece area cutting control parameters are formed and obtained.

6. The method for optimizing the beam stability and transmission of a laser cutting machine according to claim 5, wherein The determination of the N area cutting path information includes: According to the characteristic information of the N cutting area attribute parameters, N area cutting path planning algorithms are selected; The N area cutting path planning algorithms are used to perform cutting path optimization on the N cutting area attribute parameters respectively to obtain N area optimal cutting paths; According to the distribution characteristics of the N workpiece cutting area information, the N area optimal cutting paths are corrected to determine the N area cutting path information.

7. The method for optimizing beam stability and transmission of a laser cutting machine according to claim 6, characterized in that, The determination of the N area cutting path information includes: According to the distribution characteristics of the N workpiece cutting area information, cutting path constraint information is determined, and the cutting path constraint information includes area cutting sequence, cutting path conflict, and cutting direction limitation; Based on the cutting path constraint information, the N area optimal cutting paths are constrained and corrected to determine the N area cutting path information.

8. The method for optimizing the beam stability and transmission of a laser cutting machine according to claim 1, wherein The determination of the cutting control correction amount includes: Based on the beam quality parameters and the workpiece cutting surface morphology data, workpiece cutting quality prediction is performed to obtain workpiece cutting predicted quality parameters; A PID controller is used to perform regulation and control analysis on the workpiece cutting predicted quality parameters and the workpiece cutting desired quality parameters to determine the cutting control correction amount.

9. The method for optimizing the beam stability and transmission of a laser cutting machine according to claim 8, characterized in that, The determination of the cutting control correction amount includes: Parameters of the PID controller are extracted to obtain controller parameter information, and the controller parameter information includes a proportional control term, an integral control term, and a derivative control term; Based on the controller parameter information, iterative verification and optimization of the PID controller are performed to obtain a PID optimized controller; The difference between the workpiece cutting predicted quality parameters and the workpiece cutting desired quality parameters is used as a quality deviation parameter, and based on the PID optimized controller, cutting regulation and control analysis is performed on the quality deviation parameter to determine the cutting control correction amount.

10. Laser cutting machine beam stability and transmission optimization platform, characterized in that, For implementing the method for optimizing the beam stability and transmission of the laser cutting machine according to any one of claims 1-9, the platform includes: A workpiece partitioning module, configured to obtain the 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, configured to perform historical data mining and control analysis based on the target laser cutting machine, and build a dual-channel control for the cutting machine, where the dual-channel control for the cutting machine includes a beam stability control channel and a beam transmission control channel; A control parsing module, configured to use the beam stability control channel and the beam transmission control channel to perform parallel control parameter parsing on the N workpiece cutting area information to obtain N workpiece area cutting control parameters; A cutting control module, configured to monitor and obtain the beam quality parameters and the workpiece cutting surface morphology data in real time, use a PID controller to perform regulation calculation on the N workpiece area cutting control parameters based on the beam quality parameters and the workpiece cutting surface morphology data, determine a cutting control correction amount, and perform compensated closed-loop control on the target laser cutting machine based on the cutting control correction amount.

Images