Laser cutting device and control method thereof

Abstract

The invention relates to the technical field of laser cutting, in particular to a laser cutting device and a control method thereof. The method comprises the following steps: collecting data of a laser cutting machine to obtain data of the laser cutting machine; cutting head moving speed data of the laser cutting machine data are extracted, and the cutting head moving speed data are obtained; performing power calculation on the moving speed data of the cutting head to obtain laser power data; spatial modeling is carried out based on the cutting head moving speed data and the laser power data, and a laser cutting machine three-dimensional model is generated; performing cutting path identification on the three-dimensional model of the laser cutting machine to generate cutting path data; and extracting first cutting data of the laser cutting machine data to obtain the first cutting data. Through the Internet of Things technology, the data mapping technology, the data analysis technology and the intelligent control technology, self-adaptive laser cutting control over different materials and thickness conditions is achieved, and therefore the cutting quality and efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the field of laser cutting technology, and in particular to a laser cutting device and a control method thereof. Background Art

[0002] The earliest laser cutting devices mostly relied on carbon dioxide lasers to cut materials through high-energy laser beams. However, with the advancement of science and technology, fiber lasers have gradually become mainstream, with higher photoelectric conversion efficiency, stronger penetration and longer service life, which greatly improves the performance of laser cutting. In addition, the introduction of CNC technology has further promoted the automation and precision control of laser cutting devices, especially in the cutting process of complex graphics, achieving higher flexibility and efficiency. In recent years, the control system of laser cutting devices has also been significantly improved, from traditional manual operation to intelligent control, which has improved the cutting effect to a certain extent. With the integration of emerging technologies such as the Internet of Things and big data, laser cutting equipment has gradually developed towards intelligence and networking, making remote monitoring, fault diagnosis and optimization and upgrading a trend. However, the existing control methods of laser cutting devices are difficult to automatically adjust cutting parameters when dealing with different materials and thicknesses, which affects the quality and efficiency of cutting. Summary of the invention

[0003] Based on this, it is necessary to provide a laser cutting device and a control method thereof to solve at least one of the above technical problems.

[0004] To achieve the above object, a control method for a laser cutting device is provided, the method comprising the following steps:

[0005] Step S1: Collect data of the laser cutting machine to obtain laser cutting machine data; extract cutting head moving speed data of the laser cutting machine data to obtain cutting head moving speed data; perform power calculation on the cutting head moving speed data to obtain laser power data; perform spatial modeling based on the cutting head moving speed data and the laser power data to generate a three-dimensional model of the laser cutting machine; perform cutting path recognition on the three-dimensional model of the laser cutting machine to generate cutting path data;

[0006] Step S2: extracting the first cutting data of the laser cutting machine data to obtain the first cutting data; evaluating the cutting edge smoothness of the first cutting data to obtain edge smoothness data; fine-tuning the cutting path data according to the edge smoothness data to obtain the cutting head movement trajectory; predicting the laser energy distribution of the cutting path data according to the cutting head movement trajectory and the laser power data to obtain predicted laser energy distribution data;

[0007] Step S3: performing a simulated cutting experiment on the laser cutting machine by predicting the laser energy distribution data to obtain simulated cutting experiment data; performing cutting optimization analysis on the simulated cutting experiment data and the predicted laser energy distribution data to generate cutting parameter optimization data; dynamically adjusting the speed and power of the laser cutting machine according to the cutting parameter optimization data to generate speed and power adjustment data;

[0008] Step S4: Perform a secondary cutting operation on the laser cutting machine according to the speed and power adjustment data to generate secondary cutting data; compare the secondary cutting data with the first cutting data to obtain cutting comparison data; predict the optimal cutting parameters of the material thickness for the laser cutting machine according to the cutting comparison data to obtain cutting parameter prediction data; perform intelligent adjustment and control on the laser cutting machine based on the cutting parameter prediction data to generate intelligent adjustment control data; perform cutting control on the laser cutting machine according to the intelligent adjustment control data to generate a laser cutting control plan.

[0009] The present invention collects data on the laser cutting machine, ensures a comprehensive understanding of the laser cutting machine, and provides an accurate basis for subsequent analysis; extracts the cutting head moving speed data and performs power calculation, can accurately obtain laser power data, and provides key parameters for subsequent cutting path planning; based on the cutting head moving speed data and laser power data, spatial modeling is performed to generate a three-dimensional model of the laser cutting machine, which provides an intuitive visual three-dimensional model for the identification and optimization of the cutting path; the cutting path data generated by the cutting path identification provides clear guidance for the cutting operation of the laser cutting machine, ensuring the accuracy and efficiency of the cutting process. After extracting the first cutting data, the smoothness of the cutting edge is evaluated, and the key indicators reflecting the quality of the first cutting can be accurately identified; the cutting path data is fine-tuned according to the edge smoothness data, and the cutting head moving trajectory is optimized, thereby improving the cutting quality; combined with the cutting head moving trajectory and laser power data, the cutting path data is predicted for laser energy distribution, and the predicted laser energy distribution data obtained provides an important reference basis for subsequent simulation cutting experiments. By predicting the laser energy distribution data, a simulated cutting experiment is conducted, and the obtained simulated cutting experiment data clarifies the verification parameters of the subsequent cutting operation experiment; the simulated cutting experiment data is compared and analyzed with the predicted laser energy distribution data, providing adjustment guidance for the operation of the laser cutting machine; the laser cutting machine is dynamically adjusted in speed and power according to the cutting parameter optimization data, ensuring the stability of the cutting process and the consistency of the cutting quality. According to the speed and power adjustment data, a secondary cutting operation is performed, and the generated secondary cutting data provides actual data support for the comparative analysis of the cutting effect; by comparing the secondary cutting data with the first cutting data, the obtained cutting comparison data can intuitively reflect the effect of the cutting parameter adjustment; according to the cutting comparison data, the optimal cutting parameters of the material thickness of the laser cutting machine are predicted, and parameter prediction is provided for the cutting of different material thicknesses; according to the cutting parameter prediction data, intelligent adjustment and control are performed, realizing the automation and intelligent operation of the laser cutting machine, improving the cutting efficiency and quality, and reducing the complexity of the operation, and finally generating a laser cutting control scheme, providing a comprehensive technical scheme for the precise cutting of the laser cutting machine. Therefore, the present invention realizes adaptive laser cutting control for different materials and thickness conditions through Internet of Things technology, data mapping technology, data analysis technology and intelligent control technology, thereby improving the quality and efficiency of cutting.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: collecting data of the laser cutting machine to obtain laser cutting machine data; performing speed feature recognition on the laser cutting machine data to obtain laser cutting machine speed features; performing cutting head moving speed extraction on the laser cutting machine speed features to obtain cutting head moving speed data;

[0012] Step S12: Accumulate the cutting head movement speed data to obtain the cutting head speed accumulation data; perform displacement analysis on the cutting head speed accumulation data to obtain the cutting head movement displacement data; perform differential processing on the cutting head movement displacement data to obtain the cutting head speed change rate data; perform power calculation on the cutting head movement speed data according to the cutting head speed change rate data to obtain the laser power data;

[0013] Step S13: performing cutting space association on the cutting head movement speed data and the laser power data to generate space parameter association data; performing geometric analysis on the laser cutting machine data through the space parameter association data to obtain the laser cutting machine geometry data; performing three-dimensional model construction based on the space parameter association data and the laser cutting machine geometry data to generate a three-dimensional model of the laser cutting machine;

[0014] Step S14: performing cutting area analysis on the three-dimensional model of the laser cutting machine to obtain cutting area data; performing cutting path recognition on the cutting area data to generate cutting path data.

[0015] The present invention comprehensively acquires the status information of the laser cutting machine through data collection, and provides basic data for subsequent analysis; identifies the speed characteristics of the laser cutting machine, and accurately captures the key performance indicators of the laser cutting machine; extracts the cutting head movement speed data, and provides direct parameters for the subsequent cutting head motion analysis; performs accumulation processing on the cutting head movement speed data, accumulates the speed change during the cutting process, and provides a basis for displacement analysis; analyzes the cutting head movement displacement data, and can intuitively reflect the movement trajectory of the cutting head during the cutting process; differentially processes the cutting head movement displacement data, and accurately calculates the rate of change of the cutting head speed, and provides key parameters for power calculation; performs power calculation according to the cutting head speed change rate data, and obtains laser power data, and ensures accurate control of cutting energy. By correlating the cutting space and generating spatial parameter correlation data, the moving speed of the cutting head can be effectively combined with the laser power data. The spatial parameter correlation data is used for geometric analysis to obtain the geometric data of the laser cutting machine, providing precise parameters for the construction of the three-dimensional model. A three-dimensional model of the laser cutting machine is constructed to achieve intuitive simulation and analysis of the cutting process and improve the accuracy of cutting path planning. The cutting area analysis of the three-dimensional model of the laser cutting machine is performed to clarify the specific area of ​​the cutting operation. The cutting path data is identified to accurately plan the movement trajectory of the cutting head in the three-dimensional space to ensure the efficiency and accuracy of the cutting process.

[0016] Preferably, step S2 comprises the following steps:

[0017] Step S21: extracting cutting conditions from laser cutting machine data to obtain laser cutting data; identifying timestamps from laser cutting data to obtain cutting timestamp data; determining first cutting of laser cutting data according to cutting timestamp data to obtain first cutting data;

[0018] Step S22: performing edge feature recognition on the first cutting data to obtain first edge feature data; performing cutting contour geometry analysis on the first edge feature data to obtain cutting contour geometry data; performing surface gloss recognition on the cutting contour geometry data to obtain contour surface gloss data; performing smoothness evaluation on the contour surface gloss data to obtain edge smoothness data;

[0019] Step S23: fine-tuning the cutting path data according to the edge smoothness data to obtain the cutting head movement trajectory;

[0020] Step S24: predicting the laser energy distribution of the cutting path data according to the cutting head movement trajectory and the laser power data to obtain predicted laser energy distribution data.

[0021] The present invention ensures a comprehensive record of the cutting process by extracting laser cutting data; identifies cutting timestamp data and accurately identifies the specific time point of the cutting operation, laying the foundation for the timing analysis of the cutting process; determines the first cutting data and clearly distinguishes the order of cutting operations; identifies the first edge feature data and captures the key characteristics of the cutting edge, providing a basis for the evaluation of edge quality. The cutting contour geometry analysis of the first edge feature data provides data support for the control of cutting accuracy; identifies the surface glossiness of the cutting contour geometry data and evaluates the physical properties of the cutting surface; performs smoothness evaluation on the contour surface gloss data and quantifies the smoothness of the cutting edge, providing a key indicator for the optimization of cutting quality; fine-tunes the cutting path data according to the edge smoothness data, optimizes the movement trajectory of the cutting head, and improves the accuracy and cutting quality of the cutting process; combines the movement trajectory of the cutting head and the laser power data to predict the laser energy distribution of the cutting path data, and obtains the predicted laser energy distribution data, providing a scientific basis for achieving efficient and uniform laser cutting.

[0022] Preferably, step S23 includes the following steps:

[0023] Step S231: performing geometric irregularity analysis on the edge smoothness data to obtain edge geometric irregularity data; performing feature mapping on the edge smoothness data according to the edge geometric irregularity data to generate edge smoothness feature data;

[0024] Step S232: Compare the edge smoothness feature data with the preset edge smoothness data to obtain edge deviation data; perform compensation calculation on the edge deviation data to obtain edge deviation compensation data; determine the cutting compensation path parameters on the edge deviation compensation data to obtain path adjustment parameter data;

[0025] Step S233: performing point-by-point correction processing on the cutting path data according to the path adjustment parameter data to obtain point-by-point corrected path data; performing continuity analysis on the point-by-point corrected path data to obtain cutting path continuity data;

[0026] Step S234: fine-tuning the cutting head moving speed and direction of the cutting path data according to the cutting path continuity data to obtain cutting head fine-tuning data;

[0027] Step S235: monitoring the cutting head movement trajectory of the cutting path data according to the cutting head fine-tuning data to obtain the cutting head movement trajectory.

[0028] The present invention performs geometric irregularity analysis on edge smoothness data, which is helpful to identify irregular edges appearing in the cutting process; performs feature mapping on edge smoothness data based on edge geometric irregularity data, which can provide a detailed description of the cutting quality and provide guidance for the optimization of the cutting path; uses edge smoothness feature data to evaluate the quality of the cutting edge, which can improve the cutting accuracy and quality; compares the edge smoothness feature data with preset edge smoothness data, which helps to identify the difference between the actual cutting effect and the expected one; performs compensation calculation on edge deviation data, which can provide accurate compensation values ​​for adjusting the cutting path to improve the cutting quality. The cutting compensation path parameters are determined according to the edge deviation compensation data to ensure the accuracy of the cutting path and improve the cutting quality; the cutting path data is corrected point by point according to the path adjustment parameter data to help ensure the accuracy of each cutting point, thereby improving the overall cutting accuracy; the continuity analysis of the point-by-point correction path data can ensure the smoothness of the cutting path, avoid breakpoints or discontinuities during the cutting process, and improve the efficiency and quality of cutting; the cutting path data is fine-tuned according to the cutting path continuity data to optimize the movement trajectory of the cutting head and reduce cutting defects caused by improper speed and direction; the cutting path data is monitored according to the cutting head fine-tuning data to monitor the movement trajectory of the cutting head, so as to monitor the movement state of the cutting head in real time and ensure the stability of the cutting process and the consistency of the cutting quality.

[0029] Preferably, step S24 includes the following steps:

[0030] Step S241: performing time series analysis on the cutting head movement trajectory to obtain trajectory time series data; decomposing the trajectory time series data into small segments to obtain trajectory segmentation data;

[0031] Step S242: performing trajectory behavior pattern recognition on the trajectory segmentation data to obtain trajectory behavior pattern data; performing energy demand analysis on the laser power data according to the trajectory behavior pattern data to obtain cutting energy demand data;

[0032] Step S243: performing laser energy distribution calculation on the cutting energy demand data to obtain laser energy distribution data; performing energy distribution prediction on the cutting path data according to the laser energy distribution data to generate energy prediction distribution data;

[0033] Step S244: Analyze the cutting effect of the energy prediction distribution data on the active material to obtain active material energy data; predict the laser energy distribution of the cutting path data based on the active material energy data to obtain predicted laser energy distribution data.

[0034] The present invention performs time series analysis on the moving trajectory of the cutting head, so as to understand the regularity of speed changes during the cutting process; decomposes the trajectory time series data into small segments, so as to analyze the motion characteristics of the cutting head in different time periods in detail; performs trajectory behavior pattern recognition on the trajectory segmentation data, which is helpful to identify the specific behavior pattern in the cutting process and provide a basis for subsequent optimization; performs energy demand analysis on the laser power data according to the trajectory behavior pattern data, so as to determine the laser energy required in different cutting stages to ensure the cutting quality. Performs laser energy distribution calculation on the cutting energy demand data, so as to achieve reasonable distribution of laser energy and improve cutting efficiency and quality; performs energy distribution prediction on the cutting path data according to the laser energy distribution data, generates energy prediction distribution data, and clearly predicts the energy demand of each point in the actual cutting process; performs cutting material effect analysis on the energy prediction distribution data, so as to evaluate the influence of different energy distribution on the material cutting effect; performs laser energy distribution prediction on the cutting path data according to the energy data of the acting material, and obtains predicted laser energy distribution data, which is helpful to optimize the energy distribution in the cutting process and ensure the uniformity and consistency of the cutting effect.

[0035] Preferably, step S3 comprises the following steps:

[0036] Step S31: performing energy distribution area identification on the predicted laser energy distribution data to obtain predicted energy distribution area data; performing cutting experiment parameter setting on the laser cutting machine according to the predicted energy distribution area data to generate cutting experiment parameter data;

[0037] Step S32: performing a three-dimensional cutting trajectory simulation on the laser cutting machine according to the cutting experiment parameter data to obtain three-dimensional simulated cutting data; performing a simulated cutting experiment on the three-dimensional simulated cutting data to obtain simulated cutting experiment data; performing a laser energy distribution experiment analysis on the simulated cutting experiment data to obtain laser energy distribution experiment data;

[0038] Step S33: cross-comparing the laser energy distribution experimental data with the predicted laser energy distribution data to obtain energy distribution difference data; performing cutting parameter sensitivity analysis on the energy distribution difference data to obtain cutting parameter sensitivity data; performing cutting optimization analysis on the cutting parameter sensitivity data to generate cutting parameter optimization data;

[0039] Step S34: performing speed anomaly detection on the cutting parameter optimization data to generate cutting speed anomaly data; dynamically adjusting the speed of the laser cutting machine according to the cutting speed anomaly data to obtain cutting speed adjustment data; performing power anomaly identification on the cutting parameter optimization data to generate cutting power anomaly data; dynamically adjusting the power of the laser cutting machine according to the cutting power anomaly data to obtain cutting power adjustment data;

[0040] Step S35: Integrate the cutting speed adjustment data and the cutting power adjustment data to obtain speed and power adjustment data.

[0041] The present invention clarifies the energy requirements of different areas through energy distribution area identification, and provides a basis for setting experimental parameters; sets the cutting experimental parameters of the laser cutting machine according to the predicted energy distribution area data, generates cutting experimental parameter data, and ensures the systematicness and accuracy of the experiment; uses the cutting experimental parameter data to simulate the three-dimensional cutting trajectory, which helps to predict the cutting effect before actual cutting; performs simulated cutting experiments on the three-dimensional simulated cutting data to verify the accuracy of the simulation and provide a reference for actual cutting; performs laser energy distribution experimental situation analysis on the simulated cutting experimental data, and evaluates the actual effect of the energy distribution in the experiment. Cross-comparison of the experimental laser energy distribution data with the predicted laser energy distribution data helps to discover the deviation between the experiment and the prediction; cutting parameter sensitivity analysis is performed on the energy distribution difference data to identify the parameters that have a significant impact on the cutting quality; cutting optimization analysis is performed based on the cutting parameter sensitivity data to improve cutting efficiency and quality; speed anomaly detection is performed on the cutting parameter optimization data to identify speed anomalies in the cutting process; the speed of the laser cutting machine is dynamically adjusted based on the cutting speed anomaly data to optimize the cutting speed to improve the cutting quality; power anomaly identification is performed on the cutting parameter optimization data to identify cutting power anomalies; the power of the laser cutting machine is dynamically adjusted based on the cutting power anomaly data to optimize the cutting power to improve cutting efficiency; the cutting speed adjustment data and the cutting power adjustment data are integrated to achieve coordinated optimization of speed and power during the cutting process to ensure the efficiency and stability of the cutting process.

[0042] Preferably, step S4 comprises the following steps:

[0043] Step S41: performing application implementation processing on the speed and power adjustment data to obtain application implementation adjustment data; performing a secondary cutting operation on the laser cutting machine according to the application implementation adjustment data to generate secondary cutting data;

[0044] Step S42: Compare the secondary cutting data with the first cutting data to obtain cutting comparison data;

[0045] Step S43: performing variability analysis on the cutting comparison data to obtain cutting variability data; performing material adaptability evaluation on the cutting variability data to obtain material adaptability evaluation data; performing material thickness cutting parameter analysis on the material adaptability evaluation data to obtain material thickness cutting parameters; predicting the optimal cutting parameters of the material thickness for the laser cutting machine according to the material thickness cutting parameters to obtain cutting parameter prediction data;

[0046] Step S44: performing intelligent adjustment control on the laser cutting machine according to the cutting parameter prediction data to generate intelligent adjustment control data;

[0047] Step S45: Control the laser cutting machine according to the intelligently adjusted control data to generate a laser cutting control solution.

[0048] The present invention applies and processes the speed and power adjustment data to ensure the operability of the adjustment parameters; performs secondary cutting operation of the laser cutting machine according to the application and implementation adjustment data to verify the actual effect of the adjustment parameters; obtains cutting comparison data by comparing the secondary cutting data with the first cutting data. Variability analysis is performed on the cutting comparison data to identify the instability factors in the cutting process; material adaptability evaluation is performed on the cutting variability data to determine the matching degree between the material and the cutting parameters; material thickness cutting parameter analysis is performed based on the material adaptability evaluation data to provide customized cutting solutions for materials of different thicknesses; the optimal cutting parameters of the material thickness of the laser cutting machine are predicted based on the material thickness cutting parameters to optimize the cutting settings; the laser cutting machine is intelligently adjusted and controlled based on the cutting parameter prediction data to generate intelligent adjustment control data to achieve automatic optimization of the cutting parameters; the laser cutting machine is cut and controlled based on the intelligent adjustment control data to generate a laser cutting control solution to ensure the accuracy and efficiency of the cutting process and improve the cutting quality and production efficiency.

[0049] Preferably, step S42 includes the following steps:

[0050] Step S421: performing multi-parameter parallel analysis on the secondary cutting data to obtain secondary cutting parallel data, wherein the secondary cutting parallel data includes secondary cutting speed data, secondary cutting power data and secondary cutting quality data;

[0051] Step S422: performing feature alignment processing on the first cutting data to generate cutting feature alignment data, wherein the cutting feature alignment data includes cutting speed feature alignment data, cutting power feature alignment data and cutting quality feature alignment data;

[0052] Step S423: Synchronously compare the secondary cutting speed data with the cutting speed feature alignment data to obtain cutting speed comparison data; perform performance matching on the secondary cutting power data with the cutting power feature alignment data to obtain cutting power comparison data; perform quality comparison on the secondary cutting quality data with the cutting quality feature alignment data to obtain cutting quality comparison data;

[0053] Step S424: Integrate the cutting speed comparison data, the cutting power comparison data and the cutting quality comparison data to obtain cutting comparison data.

[0054] The present invention performs multi-parameter parallel analysis on the secondary cutting data to obtain secondary cutting parallel data including secondary cutting speed, power and quality, which can comprehensively analyze the parameters of the secondary cutting; performs feature alignment processing on the first cutting data to generate cutting feature alignment data, including feature alignment of speed, power and quality, to ensure comparability with the secondary cutting data and provide a benchmark for subsequent analysis. Synchronously comparing the secondary cutting speed data with the cutting speed feature alignment data helps to identify the improvement effect of the cutting speed; performing performance matching on the secondary cutting power data with the cutting power feature alignment data can evaluate the optimization effect of the power setting; performing quality comparison on the secondary cutting quality data with the cutting quality feature alignment data, so as to measure the improvement of the cutting quality; integrating the cutting speed comparison data, the cutting power comparison data and the cutting quality comparison data to obtain comprehensive cutting comparison data, which provides a comprehensive perspective for evaluating the overall performance of the secondary cutting and the first cutting.

[0055] Preferably, step S44 includes the following steps:

[0056] Step S441: performing material property analysis on the cutting parameter prediction data to obtain cutting material data; correlating the material thickness with the cutting parameters on the cutting material data to obtain cutting material correlation data;

[0057] Step S442: performing adaptive logic control on the laser cutting machine according to the cutting material related data to obtain adaptive logic control data;

[0058] Step S443: performing real-time dynamic cutting adjustment on the adaptive logic control data to obtain dynamic cutting adjustment data; performing multi-dimensional synchronous control on the laser cutting machine according to the dynamic cutting adjustment data to obtain multi-dimensional synchronous control data;

[0059] Step S444: performing multi-objective optimization on the multi-dimensional synchronous control data to obtain multi-objective optimization control data; performing real-time performance monitoring on the laser cutting machine according to the multi-objective optimization control data to obtain real-time performance feedback data;

[0060] Step S445: Perform intelligent feedback correction and regulation on the laser cutting machine according to the real-time performance feedback data to generate intelligent adjustment control data.

[0061] The present invention performs material property analysis on the cutting parameter prediction data, which can deeply understand the response of different materials to the cutting parameters; associates the cutting material data with the material thickness and cutting parameters, and provides customized cutting strategies for materials of different thicknesses; performs adaptive logic control on the laser cutting machine according to the cutting material association data, so that the cutting machine can intelligently respond to the characteristics of different materials; performs real-time dynamic cutting adjustment on the adaptive logic control data to ensure the adaptability and flexibility of the cutting process. Perform multi-dimensional synchronous control according to the dynamic cutting adjustment data to achieve the coordinated optimization of speed, power and quality during the cutting process; perform multi-objective optimization on the multi-dimensional synchronous control data to further improve the cutting efficiency and quality; perform real-time performance monitoring on the laser cutting machine according to the multi-objective optimization control data to provide a basis for subsequent adjustments; perform intelligent feedback correction control on the laser cutting machine according to the real-time performance feedback data to generate intelligent adjustment control data, achieve closed-loop optimization of the cutting process, and ensure the stability and reliability of the cutting quality.

[0062] In this specification, a laser cutting device is provided, including a control system for executing the above-mentioned control method of the laser cutting device, the control system including:

[0063] The cutting path recognition module is used to collect data from the laser cutting machine to obtain laser cutting machine data; extract the cutting head moving speed data from the laser cutting machine data to obtain the cutting head moving speed data; perform power calculation on the cutting head moving speed data to obtain laser power data; perform spatial modeling based on the cutting head moving speed data and the laser power data to generate a three-dimensional model of the laser cutting machine; perform cutting path recognition on the three-dimensional model of the laser cutting machine to generate cutting path data;

[0064] The laser energy distribution prediction module is used to extract the first cutting data of the laser cutting machine data to obtain the first cutting data; evaluate the cutting edge smoothness of the first cutting data to obtain edge smoothness data; fine-tune the cutting path data according to the edge smoothness data to obtain the cutting head movement trajectory; predict the laser energy distribution of the cutting path data according to the cutting head movement trajectory and the laser power data to obtain the predicted laser energy distribution data;

[0065] The cutting speed and power adjustment module is used to perform a simulated cutting experiment on the laser cutting machine by predicting the laser energy distribution data to obtain simulated cutting experiment data; perform cutting optimization analysis on the simulated cutting experiment data and the predicted laser energy distribution data to generate cutting parameter optimization data; perform dynamic speed and power adjustment on the laser cutting machine according to the cutting parameter optimization data to generate speed and power adjustment data;

[0066] The laser cutting intelligent adjustment control module is used to perform a secondary cutting operation on the laser cutting machine according to the speed and power adjustment data to generate secondary cutting data; compare the secondary cutting data with the first cutting data to obtain cutting comparison data; predict the optimal cutting parameters of the material thickness of the laser cutting machine according to the cutting comparison data to obtain cutting parameter prediction data; perform intelligent adjustment control on the laser cutting machine based on the cutting parameter prediction data to generate intelligent adjustment control data; perform cutting control on the laser cutting machine according to the intelligent adjustment control data to generate a laser cutting control plan.

[0067] The present invention collects data of the laser cutting machine through the cutting path identification module, ensures a comprehensive understanding of the laser cutting machine, and provides an accurate basis for subsequent analysis; extracts the cutting head movement speed data and performs power calculation, can accurately obtain the laser power data, and provides key parameters for subsequent cutting path planning; based on the cutting head movement speed data and laser power data, the three-dimensional model of the laser cutting machine generated by spatial modeling provides an intuitive visual three-dimensional model for the identification and optimization of the cutting path; the cutting path data generated by the cutting path identification provides clear guidance for the cutting operation of the laser cutting machine, ensuring the accuracy and efficiency of the cutting process. After the first cutting data is extracted by the laser energy distribution prediction module, the smoothness of the cutting edge is evaluated, and the key indicators reflecting the quality of the first cutting can be accurately identified; the cutting path data is fine-tuned according to the edge smoothness data, and the cutting head movement trajectory is optimized, thereby improving the cutting quality; combined with the cutting head movement trajectory and laser power data, the cutting path data is predicted for laser energy distribution, and the predicted laser energy distribution data obtained provides an important reference basis for subsequent simulation cutting experiments. Through the cutting speed and power adjustment module, simulated cutting experiments are carried out according to the predicted laser energy distribution data. The obtained simulated cutting experiment data clarifies the verification parameters of the subsequent cutting operation experiment; the simulated cutting experiment data is compared and analyzed with the predicted laser energy distribution data to provide adjustment guidance for the operation of the laser cutting machine; the laser cutting machine is dynamically adjusted in speed and power according to the cutting parameter optimization data to ensure the stability of the cutting process and the consistency of the cutting quality. Through the laser cutting intelligent adjustment control module, secondary cutting operations are carried out according to the speed and power adjustment data, and the generated secondary cutting data provide actual data support for the comparative analysis of the cutting effect; by comparing the secondary cutting data with the first cutting data, the obtained cutting comparison data can intuitively reflect the effect of the cutting parameter adjustment; according to the cutting comparison data, the optimal cutting parameters of the material thickness of the laser cutting machine are predicted, and parameter prediction is provided for the cutting of different material thicknesses; intelligent adjustment and control are carried out according to the cutting parameter prediction data, realizing the automation and intelligent operation of the laser cutting machine, improving the cutting efficiency and quality, while reducing the complexity of the operation, and finally generating a laser cutting control solution, providing a comprehensive technical solution for the precise cutting of the laser cutting machine. Therefore, the present invention realizes adaptive laser cutting control for different materials and thicknesses through Internet of Things technology, data mapping technology, data analysis technology and intelligent control technology, thereby improving the quality and efficiency of cutting. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 A schematic flow chart of a control method for a laser cutting device;

[0069] Figure 2 for Figure 1Detailed implementation steps of step S2 in the flowchart;

[0070] Figure 3 for Figure 2 Detailed implementation steps of step S23;

[0071] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0072] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0073] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0074] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0075] To achieve this, please refer to Figures 1 to 3 , a control method for a laser cutting device, the method comprising the following steps:

[0076] Step S1: Collect data of the laser cutting machine to obtain laser cutting machine data; extract cutting head moving speed data of the laser cutting machine data to obtain cutting head moving speed data; perform power calculation on the cutting head moving speed data to obtain laser power data; perform spatial modeling based on the cutting head moving speed data and the laser power data to generate a three-dimensional model of the laser cutting machine; perform cutting path recognition on the three-dimensional model of the laser cutting machine to generate cutting path data;

[0077] Step S2: extracting the first cutting data of the laser cutting machine data to obtain the first cutting data; evaluating the cutting edge smoothness of the first cutting data to obtain edge smoothness data; fine-tuning the cutting path data according to the edge smoothness data to obtain the cutting head movement trajectory; predicting the laser energy distribution of the cutting path data according to the cutting head movement trajectory and the laser power data to obtain predicted laser energy distribution data;

[0078] Step S3: performing a simulated cutting experiment on the laser cutting machine by predicting the laser energy distribution data to obtain simulated cutting experiment data; performing cutting optimization analysis on the simulated cutting experiment data and the predicted laser energy distribution data to generate cutting parameter optimization data; dynamically adjusting the speed and power of the laser cutting machine according to the cutting parameter optimization data to generate speed and power adjustment data;

[0079] Step S4: Perform a secondary cutting operation on the laser cutting machine according to the speed and power adjustment data to generate secondary cutting data; compare the secondary cutting data with the first cutting data to obtain cutting comparison data; predict the optimal cutting parameters of the material thickness for the laser cutting machine according to the cutting comparison data to obtain cutting parameter prediction data; perform intelligent adjustment and control on the laser cutting machine based on the cutting parameter prediction data to generate intelligent adjustment control data; perform cutting control on the laser cutting machine according to the intelligent adjustment control data to generate a laser cutting control plan.

[0080] The present invention collects data on the laser cutting machine, ensures a comprehensive understanding of the laser cutting machine, and provides an accurate basis for subsequent analysis; extracts the cutting head moving speed data and performs power calculation, can accurately obtain laser power data, and provides key parameters for subsequent cutting path planning; based on the cutting head moving speed data and laser power data, spatial modeling is performed to generate a three-dimensional model of the laser cutting machine, which provides an intuitive visual three-dimensional model for the identification and optimization of the cutting path; the cutting path data generated by the cutting path identification provides clear guidance for the cutting operation of the laser cutting machine, ensuring the accuracy and efficiency of the cutting process. After extracting the first cutting data, the smoothness of the cutting edge is evaluated, and the key indicators reflecting the quality of the first cutting can be accurately identified; the cutting path data is fine-tuned according to the edge smoothness data, and the cutting head moving trajectory is optimized, thereby improving the cutting quality; combined with the cutting head moving trajectory and laser power data, the cutting path data is predicted for laser energy distribution, and the predicted laser energy distribution data obtained provides an important reference basis for subsequent simulation cutting experiments. By predicting the laser energy distribution data, a simulated cutting experiment is conducted, and the obtained simulated cutting experiment data clarifies the verification parameters of the subsequent cutting operation experiment; the simulated cutting experiment data is compared and analyzed with the predicted laser energy distribution data, providing adjustment guidance for the operation of the laser cutting machine; the laser cutting machine is dynamically adjusted in speed and power according to the cutting parameter optimization data, ensuring the stability of the cutting process and the consistency of the cutting quality. According to the speed and power adjustment data, a secondary cutting operation is performed, and the generated secondary cutting data provides actual data support for the comparative analysis of the cutting effect; by comparing the secondary cutting data with the first cutting data, the obtained cutting comparison data can intuitively reflect the effect of the cutting parameter adjustment; according to the cutting comparison data, the optimal cutting parameters of the material thickness of the laser cutting machine are predicted, and parameter prediction is provided for the cutting of different material thicknesses; according to the cutting parameter prediction data, intelligent adjustment and control are performed, realizing the automation and intelligent operation of the laser cutting machine, improving the cutting efficiency and quality, and reducing the complexity of the operation, and finally generating a laser cutting control scheme, providing a comprehensive technical scheme for the precise cutting of the laser cutting machine. Therefore, the present invention realizes adaptive laser cutting control for different materials and thickness conditions through Internet of Things technology, data mapping technology, data analysis technology and intelligent control technology, thereby improving the quality and efficiency of cutting.

[0081] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a control method of a laser cutting device of the present invention. In this example, the control method of a laser cutting device includes the following steps:

[0082] Step S1: Collect data of the laser cutting machine to obtain laser cutting machine data; extract cutting head moving speed data of the laser cutting machine data to obtain cutting head moving speed data; perform power calculation on the cutting head moving speed data to obtain laser power data; perform spatial modeling based on the cutting head moving speed data and the laser power data to generate a three-dimensional model of the laser cutting machine; perform cutting path recognition on the three-dimensional model of the laser cutting machine to generate cutting path data;

[0083] In the embodiment of the present invention, high-precision sensors such as laser power meters, current sensors, and displacement sensors are used to monitor and record key data of the laser cutting machine in the working process in real time to obtain laser cutting machine data, including parameters such as laser power, current, and moving distance of the cutting head; the moving speed data of the laser cutting head is extracted from the laser cutting machine data to obtain the moving speed data of the cutting head; the power of the moving speed data of the cutting head is calculated to obtain the laser power data. Professional 3D modeling software, such as SolidWorks, is used to perform spatial modeling based on the moving speed data of the cutting head and the laser power data, including the motion trajectory of the cutting head and the effect of the laser, thereby generating a 3D model of the laser cutting machine; laser cutting control software such as LightBurn or LaserGRBL is used to identify the cutting path of the 3D model of the laser cutting machine to generate cutting path data; specifically, the cutting path of the laser cutting machine is identified using the laser cutting control software, including parameters such as cutting direction, speed, and power.

[0084] Step S2: extracting the first cutting data of the laser cutting machine data to obtain the first cutting data; evaluating the cutting edge smoothness of the first cutting data to obtain edge smoothness data; fine-tuning the cutting path data according to the edge smoothness data to obtain the cutting head movement trajectory; predicting the laser energy distribution of the cutting path data according to the cutting head movement trajectory and the laser power data to obtain predicted laser energy distribution data;

[0085] In an embodiment of the present invention, the first cutting data is extracted from the laser cutting machine data, specifically using a data acquisition system, such as a mes system, which is connected to the laser cutting machine to monitor and record various parameters in the cutting process in real time, and the extracted data includes key parameters such as cutting speed, laser power, and focus position; the first cutting data is evaluated for the smoothness of the cutting edge, and the edge smoothness is an important indicator for measuring the cutting quality, which directly affects the precision and appearance quality of the cut parts; the edge smoothness data is calculated using a linear filtering technology, such as a Gaussian filtering technology. The cutting path data is fine-tuned according to the edge smoothness data, specifically, using professional CAM software, such as 3D One Cut, to adjust the cutting path according to the edge smoothness data, thereby optimizing the moving trajectory of the cutting head; combining the moving trajectory of the cutting head and the laser power data, using a laser energy following control device, such as a GLAD laser system and physical optics simulation software, the cutting path data is predicted for laser energy distribution, and the light energy output is further predicted according to the real-time position of the cutting head and the preset power parameters, thereby obtaining predicted laser energy distribution data.

[0086] Step S3: performing a simulated cutting experiment on the laser cutting machine by predicting the laser energy distribution data to obtain simulated cutting experiment data; performing cutting optimization analysis on the simulated cutting experiment data and the predicted laser energy distribution data to generate cutting parameter optimization data; dynamically adjusting the speed and power of the laser cutting machine according to the cutting parameter optimization data to generate speed and power adjustment data;

[0087] In an embodiment of the present invention, a laser energy distribution detection technology based on image processing is used to perform distribution detection on the predicted laser energy distribution data, specifically, the energy density distribution and energy attenuation of the laser after atmospheric transmission are qualitatively and quantitatively analyzed; then, a simulated cutting experiment is performed on the laser cutting machine by predicting the laser energy distribution data, specifically, a laser cutting processing simulation, including key operation simulations such as laser power and scanning speed; using a multi-objective cutting data generation algorithm for CNC machine tools, the simulated cutting experiment data is compared and analyzed with the predicted laser energy distribution data, specifically, the calculation of cutting processing states such as cutting force and dynamic cutting vibration, as well as the actual cutting laser energy distribution, thereby generating cutting parameter optimization data; according to the cutting parameter optimization data, the laser cutting machine performs dynamic speed and power adjustment, specifically, the adjustment of the cutting machine operating voltage and clock frequency is achieved through the DVFS (Dynamic Voltage and Frequency Scaling) dynamic voltage and frequency adjustment technology, and finally the speed and power adjustment data is generated.

[0088] Step S4: Perform a secondary cutting operation on the laser cutting machine according to the speed and power adjustment data to generate secondary cutting data; compare the secondary cutting data with the first cutting data to obtain cutting comparison data; predict the optimal cutting parameters of the material thickness for the laser cutting machine according to the cutting comparison data to obtain cutting parameter prediction data; perform intelligent adjustment and control on the laser cutting machine based on the cutting parameter prediction data to generate intelligent adjustment control data; perform cutting control on the laser cutting machine according to the intelligent adjustment control data to generate a laser cutting control plan.

[0089] In an embodiment of the present invention, a numerical control system is used to adjust the power and speed of the laser cutting machine according to the initial cutting data. For example, for thicker materials, the power needs to be increased and the speed needs to be reduced to ensure complete penetration; while for thinner materials, the power needs to be reduced and the speed needs to be increased to improve production efficiency; after adjusting the cutting parameters, the laser cutting machine is subjected to a secondary cutting operation to generate secondary cutting data. By comparing the secondary cutting data with the first cutting data, the change in cutting quality is evaluated, including the smoothness of the cutting edge, cutting accuracy, and the affected area of ​​the material, and the cutting comparison data is obtained; the optimal cutting parameters under different material thicknesses are predicted through the cutting comparison data, and the optimal laser power, cutting speed and focus position are predicted through prediction algorithm technology, such as decision tree and support vector machine algorithm technology, to obtain cutting parameter prediction data; the laser cutting machine is intelligently adjusted based on the cutting parameter prediction data, including automatic adjustment of laser power, change of cutting speed and adjustment of focus position, etc.; the distance sensor and cutting head focus monitoring function integrated in the CutBox Pro platform of Precitec are used, and the focus position is compensated through the BeamTec function to obtain intelligent adjustment control data; the laser cutting machine is cut and controlled according to the intelligent adjustment control data, and a laser cutting control plan is generated to perform laser cutting control operations.

[0090] Preferably, step S1 comprises the following steps:

[0091] Step S11: collecting data of the laser cutting machine to obtain laser cutting machine data; performing speed feature recognition on the laser cutting machine data to obtain laser cutting machine speed features; performing cutting head moving speed extraction on the laser cutting machine speed features to obtain cutting head moving speed data;

[0092] Step S12: Accumulate the cutting head movement speed data to obtain the cutting head speed accumulation data; perform displacement analysis on the cutting head speed accumulation data to obtain the cutting head movement displacement data; perform differential processing on the cutting head movement displacement data to obtain the cutting head speed change rate data; perform power calculation on the cutting head movement speed data according to the cutting head speed change rate data to obtain the laser power data;

[0093] Step S13: performing cutting space association on the cutting head movement speed data and the laser power data to generate space parameter association data; performing geometric analysis on the laser cutting machine data through the space parameter association data to obtain the laser cutting machine geometry data; performing three-dimensional model construction based on the space parameter association data and the laser cutting machine geometry data to generate a three-dimensional model of the laser cutting machine;

[0094] Step S14: performing cutting area analysis on the three-dimensional model of the laser cutting machine to obtain cutting area data; performing cutting path recognition on the cutting area data to generate cutting path data.

[0095] In an embodiment of the present invention, data is collected through an MES system (manufacturing execution system) connected to a laser cutting machine. Specifically, the system monitors the working status of the laser cutting machine in real time, including key parameters such as cutting speed, power, and cutting head position, thereby obtaining laser cutting machine data; machine vision technology, such as the SensiCut intelligent material sensing platform, is used to identify the speed characteristics of the laser cutting machine during the cutting process, specifically by analyzing the image generated by the interaction between the laser and the material in unit time to obtain the speed characteristics of the laser cutting machine; sensor technology, such as Precitec's distance sensor, is used to monitor the moving speed of the cutting head of the laser cutting machine in real time to obtain the moving speed data of the cutting head; the moving speed data of the cutting head is accumulated and analyzed in combination with the displacement to obtain the moving displacement data of the cutting head; further, the moving displacement data of the cutting head is differentiated to obtain the speed change rate data of the cutting head; then, according to the speed change rate data of the cutting head, and using physical formulas, the laser power is calculated for the moving speed data of the cutting head to ensure that the energy input in the cutting process matches the material removal rate, thereby obtaining the laser power data. Using spatial statistical technology, such as ArcGIS Pro tools, the cutting head movement speed data and laser power data are spatially associated to generate spatial parameter association data; using Zonal Geometry (zonal geometric statistics), the laser cutting machine data is geometrically analyzed according to the spatial parameter association data to obtain the laser cutting machine geometric data, wherein the geometric analysis includes analyzing the geometric features such as the area, perimeter, thickness and centroid of each partition; based on the spatial parameter association data and the laser cutting machine geometric data, and using CAD / CAM software, a three-dimensional model of the laser cutting machine is constructed; the cutting area analysis of the three-dimensional model of the laser cutting machine is performed to obtain the cutting area data; then, the path analysis technology is used to identify the cutting path of the cutting area data to generate the cutting path data.

[0096] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0097] Step S21: extracting cutting conditions from laser cutting machine data to obtain laser cutting data; identifying timestamps from laser cutting data to obtain cutting timestamp data; determining first cutting of laser cutting data according to cutting timestamp data to obtain first cutting data;

[0098] Step S22: performing edge feature recognition on the first cutting data to obtain first edge feature data; performing cutting contour geometry analysis on the first edge feature data to obtain cutting contour geometry data; performing surface gloss recognition on the cutting contour geometry data to obtain contour surface gloss data; performing smoothness evaluation on the contour surface gloss data to obtain edge smoothness data;

[0099] Step S23: fine-tuning the cutting path data according to the edge smoothness data to obtain the cutting head movement trajectory;

[0100] Step S24: predicting the laser energy distribution of the cutting path data according to the cutting head movement trajectory and the laser power data to obtain predicted laser energy distribution data.

[0101] In an embodiment of the present invention, an extraction technology is used to extract the cutting situation of the laser cutting machine data to obtain the laser cutting data; the laser cutting data is time-marked, and it is ensured that each data corresponds to the time when it occurs, so as to obtain the cutting timestamp data; further, the FROM_UNIXTIME() function of the MySQL database is used to convert the Unix timestamp into a readable date and time format; then, the timestamp data is sorted, and the data record of the first cutting operation is identified to obtain the first cutting data; image processing technology, such as edge detection algorithm, is used to perform edge feature recognition on the first cutting data to obtain the first edge feature data; the geometric analysis tool in the CAD / CAM software is used to perform cutting contour geometric analysis on the identified edge feature data to obtain the geometric data of the cutting contour. Through machine vision technology, such as Halcon and OpenCV technology, the surface glossiness of the cutting contour geometry data is identified; specifically, the surface reflection characteristics of the cutting contour geometry data are analyzed to obtain the contour surface gloss data; based on the surface gloss data, the edge smoothness is evaluated using statistical methods or machine learning algorithms to determine the cutting quality and obtain edge smoothness data; the cutting path is fine-tuned according to the edge smoothness data to optimize the movement trajectory of the cutting head to improve the cutting accuracy; in combination with the cutting head movement trajectory and laser power data, a deep learning algorithm, such as deep model predictive control (DL-MPC), is used to predict the laser energy distribution of the cutting path data to obtain predicted laser energy distribution data.

[0102] As an example of the present invention, refer to Figure 3As shown, in this example, step S23 includes:

[0103] Step S231: performing geometric irregularity analysis on the edge smoothness data to obtain edge geometric irregularity data; performing feature mapping on the edge smoothness data according to the edge geometric irregularity data to generate edge smoothness feature data;

[0104] Step S232: Compare the edge smoothness feature data with the preset edge smoothness data to obtain edge deviation data; perform compensation calculation on the edge deviation data to obtain edge deviation compensation data; determine the cutting compensation path parameters on the edge deviation compensation data to obtain path adjustment parameter data;

[0105] Step S233: performing point-by-point correction processing on the cutting path data according to the path adjustment parameter data to obtain point-by-point corrected path data; performing continuity analysis on the point-by-point corrected path data to obtain cutting path continuity data;

[0106] Step S234: fine-tuning the cutting head moving speed and direction of the cutting path data according to the cutting path continuity data to obtain cutting head fine-tuning data;

[0107] Step S235: monitoring the cutting head movement trajectory of the cutting path data according to the cutting head fine-tuning data to obtain the cutting head movement trajectory.

[0108] In an embodiment of the present invention, machine vision technology is used to capture a high-resolution image of a cutting edge, and an edge detection algorithm, such as the Canny algorithm, is used to identify and quantify the irregularity of edge smoothness data to obtain edge geometric irregularity data; a feature extraction technique, such as principal component analysis, is used to perform feature mapping on edge smoothness data according to the edge geometric irregularity data to generate edge smoothness feature data; an edge deviation data set is calculated by comparing an edge smoothness feature data set with preset edge smoothness data, and specifically, a statistical analysis method is used to determine the deviation between an actual edge and an ideal edge to obtain edge deviation data; a numerical optimization algorithm, such as a linear programming or nonlinear optimization algorithm, is applied to perform compensation calculation on the edge deviation data to obtain edge deviation compensation data, and the edge deviation compensation data is used to adjust cutting parameters to correct the deviation. Using a path planning algorithm, such as the A* algorithm or the Rapidly-exploring Random Tree, the cutting compensation path parameters are determined according to the edge deviation compensation data, which are specifically used to guide the laser cutting head to move along the optimized path to obtain the path adjustment parameter data; using the interpolation algorithm in the numerical control system, the cutting path data is corrected point by point to generate point-by-point correction path data; using CAD / CAM software, the point-by-point correction path data is simulated, the continuity of the cutting path is analyzed, and the cutting path continuity data is generated; according to the cutting path continuity data, the motion controller is used to fine-tune the cutting head movement speed and direction, generate a cutting head fine-tuning data set, and specifically optimize the movement of the cutting head to improve the cutting quality and efficiency; using a machine vision system and sensor technology, such as high-speed camera, the cutting head movement trajectory is monitored on the cutting path data according to the cutting head fine-tuning data to obtain the cutting head movement trajectory.

[0109] Preferably, step S24 includes the following steps:

[0110] Step S241: performing time series analysis on the cutting head movement trajectory to obtain trajectory time series data; decomposing the trajectory time series data into small segments to obtain trajectory segmentation data;

[0111] Step S242: performing trajectory behavior pattern recognition on the trajectory segmentation data to obtain trajectory behavior pattern data; performing energy demand analysis on the laser power data according to the trajectory behavior pattern data to obtain cutting energy demand data;

[0112] Step S243: performing laser energy distribution calculation on the cutting energy demand data to obtain laser energy distribution data; performing energy distribution prediction on the cutting path data according to the laser energy distribution data to generate energy prediction distribution data;

[0113] Step S244: Analyze the cutting effect of the energy prediction distribution data on the active material to obtain active material energy data; predict the laser energy distribution of the cutting path data based on the active material energy data to obtain predicted laser energy distribution data.

[0114] In an embodiment of the present invention, a time series analysis method is used to perform a time series analysis on the movement trajectory of the cutting head to obtain trajectory time series data, wherein the trajectory time series data includes the position, velocity and acceleration information of the cutting head at each time point; signal processing technology, such as wavelet transform, is applied to decompose the trajectory time series data into small segments to specifically identify small changes and irregularities in the cutting process, thereby obtaining a trajectory segmentation data set; a machine learning algorithm, such as a hidden Markov model (HMM) or a long short-term memory network (LSTM), is used to analyze the trajectory segmentation data, specifically including identifying the regularity and abnormal patterns of the cutting head movement to obtain trajectory behavior pattern data; the trajectory behavior pattern data and the laser power data are combined, and an energy demand analysis algorithm is applied to perform energy demand analysis on the laser power data to obtain cutting energy demand data. Numerical optimization techniques, such as linear programming or dynamic programming, are used to calculate the laser energy distribution of the cutting energy demand data; specifically, the energy distribution of the cutting head in different cutting stages is calculated to obtain the laser energy distribution data; based on the laser energy distribution data, a prediction algorithm, such as a support vector machine (SVM) or a random forest, is used to predict the energy distribution of the cutting path data to generate energy prediction distribution data; based on the energy prediction distribution data and material properties, finite element analysis (FEA) or computational fluid dynamics (CFD) software is used to analyze the cutting effect on the material to obtain the energy data of the material; based on the energy data of the material, a prediction algorithm, such as a neural network or a deep learning model, is again used to predict the laser energy distribution of the cutting path data to obtain the predicted laser energy distribution data.

[0115] Preferably, step S3 comprises the following steps:

[0116] Step S31: performing energy distribution area identification on the predicted laser energy distribution data to obtain predicted energy distribution area data; performing cutting experiment parameter setting on the laser cutting machine according to the predicted energy distribution area data to generate cutting experiment parameter data;

[0117] Step S32: performing a three-dimensional cutting trajectory simulation on the laser cutting machine according to the cutting experiment parameter data to obtain three-dimensional simulated cutting data; performing a simulated cutting experiment on the three-dimensional simulated cutting data to obtain simulated cutting experiment data; performing a laser energy distribution experiment analysis on the simulated cutting experiment data to obtain laser energy distribution experiment data;

[0118] Step S33: cross-comparing the laser energy distribution experimental data with the predicted laser energy distribution data to obtain energy distribution difference data; performing cutting parameter sensitivity analysis on the energy distribution difference data to obtain cutting parameter sensitivity data; performing cutting optimization analysis on the cutting parameter sensitivity data to generate cutting parameter optimization data;

[0119] Step S34: performing speed anomaly detection on the cutting parameter optimization data to generate cutting speed anomaly data; dynamically adjusting the speed of the laser cutting machine according to the cutting speed anomaly data to obtain cutting speed adjustment data; performing power anomaly identification on the cutting parameter optimization data to generate cutting power anomaly data; dynamically adjusting the power of the laser cutting machine according to the cutting power anomaly data to obtain cutting power adjustment data;

[0120] Step S35: Integrate the cutting speed adjustment data and the cutting power adjustment data to obtain speed and power adjustment data.

[0121] In an embodiment of the present invention, the trajectory of the movement of the cutting head is recorded by high-speed camera technology, and an edge detection algorithm (such as the Canny algorithm) is applied using image processing software to identify and quantify edge irregularities; further, the predicted laser energy distribution data is identified for energy distribution regions using region recognition technology to obtain predicted energy distribution region data; based on the predicted energy distribution region data, a machine learning algorithm, such as a support vector machine (SVM), is used to set cutting experiment parameters for a laser cutting machine to generate cutting experiment parameter data; computer-aided design (CAD) software is used to simulate the cutting experiment parameter data in three dimensions to obtain three-dimensional simulated cutting data; a virtual cutting tool in the simulation software is used to perform a simulated cutting experiment on the three-dimensional simulated cutting data to obtain simulated cutting experiment data; combined with the simulated cutting experiment data, a statistical analysis method, such as variance analysis, is used to analyze the laser energy distribution experiment situation to obtain laser energy distribution experiment data. Using data analysis techniques, such as cross-comparison analysis, to cross-comparison the laser energy distribution experimental data with the predicted laser energy distribution data, so as to obtain energy distribution difference data; based on the energy distribution difference data, sensitivity analysis techniques, such as Monte Carlo simulation, are applied to perform sensitivity analysis on cutting parameters to obtain cutting parameter sensitivity data; using optimization algorithms, such as genetic algorithms, cutting optimization analysis is performed on cutting parameter sensitivity data to generate cutting parameter optimization data. Using anomaly detection algorithms, such as Z-score algorithms, speed anomaly detection is performed on cutting parameter optimization data to generate cutting speed anomaly data; based on cutting speed anomaly data, adaptive control technology is used to dynamically adjust the speed of the laser cutting machine to obtain cutting speed adjustment data; using a power monitoring system to collect cutting power data, and using anomaly recognition techniques, such as neural networks, to perform power anomaly recognition on cutting parameter optimization data to generate cutting power anomaly data; based on cutting power anomaly data, adaptive control technology is used to dynamically adjust the power of the laser cutting machine to obtain cutting power adjustment data; integrating cutting speed adjustment data and cutting power adjustment data to obtain speed and power adjustment data.

[0122] Preferably, step S4 comprises the following steps:

[0123] Step S41: performing application implementation processing on the speed and power adjustment data to obtain application implementation adjustment data; performing a secondary cutting operation on the laser cutting machine according to the application implementation adjustment data to generate secondary cutting data;

[0124] Step S42: Compare the secondary cutting data with the first cutting data to obtain cutting comparison data;

[0125] Step S43: performing variability analysis on the cutting comparison data to obtain cutting variability data; performing material adaptability evaluation on the cutting variability data to obtain material adaptability evaluation data; performing material thickness cutting parameter analysis on the material adaptability evaluation data to obtain material thickness cutting parameters; predicting the optimal cutting parameters of the material thickness for the laser cutting machine according to the material thickness cutting parameters to obtain cutting parameter prediction data;

[0126] Step S44: performing intelligent adjustment control on the laser cutting machine according to the cutting parameter prediction data to generate intelligent adjustment control data;

[0127] Step S45: Control the laser cutting machine according to the intelligently adjusted control data to generate a laser cutting control solution.

[0128] In the embodiment of the present invention, the design drawings and material parameters of the workpiece to be cut are input through the software interface of the laser cutting machine control system, and the system will automatically calculate the required cutting parameters such as power and speed; then, the laser cutting machine is started, and according to the preset cutting path, the X and Y axis servo motors of the machine will drive the laser head to move to the starting position; next, the laser emits a high-power laser beam, focuses on the surface of the material through the focusing lens, and starts cutting according to the design drawings; during the cutting process, the control system monitors the cutting quality in real time and obtains the application implementation adjustment data; according to the application implementation adjustment data, the laser cutting machine is subjected to a secondary cutting operation to generate secondary cutting data. After the laser cutting machine completes the cutting, the system will record the cutting data, including the cutting path, speed and power, etc.; then, the secondary cutting data is compared with the first cutting data to determine the deviation in the cutting process. Statistical methods, such as standard deviation analysis, are used to perform variability analysis on the cutting comparison data to evaluate the consistency of the cutting process; then, the material adaptability is evaluated based on the cutting variability data, specifically including the analysis of the material's characteristics of absorbing laser energy; further, based on the material characteristics and cutting variability data, material thickness cutting parameter analysis is performed to determine the optimal cutting parameters, thereby obtaining the material thickness cutting parameters. Adaptive control algorithms are used to intelligently adjust and control the laser cutting machine based on the cutting parameter prediction data, specifically including adjusting the laser output power, changing the cutting speed, or optimizing the beam focusing characteristics; real-time monitoring systems and precision motion control systems are used to control the laser cutting machine based on the intelligent adjustment control data, and a laser cutting control plan is generated, including setting parameters such as the cutting path, speed, and power of the laser cutting.

[0129] Preferably, step S42 includes the following steps:

[0130] Step S421: performing multi-parameter parallel analysis on the secondary cutting data to obtain secondary cutting parallel data, wherein the secondary cutting parallel data includes secondary cutting speed data, secondary cutting power data and secondary cutting quality data;

[0131] Step S422: performing feature alignment processing on the first cutting data to generate cutting feature alignment data, wherein the cutting feature alignment data includes cutting speed feature alignment data, cutting power feature alignment data and cutting quality feature alignment data;

[0132] Step S423: Synchronously compare the secondary cutting speed data with the cutting speed feature alignment data to obtain cutting speed comparison data; perform performance matching on the secondary cutting power data with the cutting power feature alignment data to obtain cutting power comparison data; perform quality comparison on the secondary cutting quality data with the cutting quality feature alignment data to obtain cutting quality comparison data;

[0133] Step S424: Integrate the cutting speed comparison data, the cutting power comparison data and the cutting quality comparison data to obtain cutting comparison data.

[0134] In an embodiment of the present invention, a multi-parameter parallel analysis is performed on the secondary cutting data, and the secondary cutting data is divided into multiple subsets using data parallel technology, and multi-parameter parallel processing is performed on multiple computing nodes to finally obtain secondary cutting parallel data. The first cutting data is feature aligned to generate cutting feature alignment data; in this step, a multimodal large model technology, such as a visual encoder and a visual text feature alignment technology, is used to process the first cutting data; specifically, feature recognition is performed on the first cutting data, and the visual encoder is used to map the features to the same dimension as the text features to generate cutting speed feature alignment, cutting power feature alignment, and cutting quality feature alignment data. The secondary cutting speed data is synchronously compared with the cutting speed feature alignment data to obtain the cutting speed comparison data; the secondary cutting power data is efficiency matched with the cutting power feature alignment data to obtain the cutting power comparison data; the secondary cutting quality data is quality compared with the cutting quality feature alignment data to obtain the cutting quality comparison data; in this specific step, data integration technology is used to integrate and compare the cutting data from different sources, and data parallel technology is used to process the data in parallel on multiple computing nodes to ensure the synchronization and consistency of the data; in addition, multimodal ultra-detailed interpretation technology is used, such as the ALBEF model, to improve the accuracy of the multimodal characterization of the data; data integration technology is used to integrate the cutting speed comparison data, cutting power comparison data and cutting quality comparison data to obtain the cutting comparison data.

[0135] Preferably, step S44 includes the following steps:

[0136] Step S441: performing material property analysis on the cutting parameter prediction data to obtain cutting material data; correlating the material thickness with the cutting parameters on the cutting material data to obtain cutting material correlation data;

[0137] Step S442: performing adaptive logic control on the laser cutting machine according to the cutting material related data to obtain adaptive logic control data;

[0138] Step S443: performing real-time dynamic cutting adjustment on the adaptive logic control data to obtain dynamic cutting adjustment data; performing multi-dimensional synchronous control on the laser cutting machine according to the dynamic cutting adjustment data to obtain multi-dimensional synchronous control data;

[0139] Step S444: performing multi-objective optimization on the multi-dimensional synchronous control data to obtain multi-objective optimization control data; performing real-time performance monitoring on the laser cutting machine according to the multi-objective optimization control data to obtain real-time performance feedback data;

[0140] Step S445: Perform intelligent feedback correction and regulation on the laser cutting machine according to the real-time performance feedback data to generate intelligent adjustment control data.

[0141] In an embodiment of the present invention, material analysis techniques, such as X-ray diffraction (XRD) and scanning electron microscopy (SEM), are used to perform material property analysis on cutting parameter prediction data to determine the microstructure and chemical composition of the material, and obtain cutting material data; then, data association technology, such as response surface methodology, is used to perform association analysis between material thickness and cutting parameters to obtain cutting material associated data; the laser cutting machine is adaptively logically controlled based on the cutting material associated data; specifically, an intelligent control system, such as the CutBox Pro platform, is used, and focus position compensation is performed in real time through the BeamTec function to obtain adaptive logic control data; the adaptive logic control data can automatically adjust the cutting parameters according to real-time feedback to adapt to different material properties and thickness changes. Adopting advanced monitoring technology, such as PierceTec, to make real-time dynamic cutting adjustments to the adaptive logic control data, specifically monitor and control the cutting process, and obtain dynamic cutting adjustment data; performing multi-dimensional synchronous control of the laser cutting machine according to the dynamic cutting adjustment data, including synchronous control of the cutting speed, power and precise control of the focus position, to obtain multi-dimensional synchronous control data; adopting multi-objective optimization algorithm, such as NSGA-II, to perform multi-objective optimization on the multi-dimensional synchronous control data, specifically considering multiple optimization objectives at the same time, such as cutting speed, quality and efficiency, to obtain multi-objective optimization control data; using feedback technology, the laser cutting machine is intelligently feedback corrected and controlled according to the real-time performance feedback data, thereby generating intelligent adjustment control data to achieve higher production efficiency and more stable cutting quality.

[0142] In this specification, a laser cutting device is provided, including a control system for executing the above-mentioned control method of the laser cutting device, the control system including:

[0143] The cutting path recognition module is used to collect data from the laser cutting machine to obtain laser cutting machine data; extract the cutting head moving speed data from the laser cutting machine data to obtain the cutting head moving speed data; perform power calculation on the cutting head moving speed data to obtain laser power data; perform spatial modeling based on the cutting head moving speed data and the laser power data to generate a three-dimensional model of the laser cutting machine; perform cutting path recognition on the three-dimensional model of the laser cutting machine to generate cutting path data;

[0144] The laser energy distribution prediction module is used to extract the first cutting data of the laser cutting machine data to obtain the first cutting data; evaluate the cutting edge smoothness of the first cutting data to obtain edge smoothness data; fine-tune the cutting path data according to the edge smoothness data to obtain the cutting head movement trajectory; predict the laser energy distribution of the cutting path data according to the cutting head movement trajectory and the laser power data to obtain the predicted laser energy distribution data;

[0145] The cutting speed and power adjustment module is used to perform a simulated cutting experiment on the laser cutting machine by predicting the laser energy distribution data to obtain simulated cutting experiment data; perform cutting optimization analysis on the simulated cutting experiment data and the predicted laser energy distribution data to generate cutting parameter optimization data; perform dynamic speed and power adjustment on the laser cutting machine according to the cutting parameter optimization data to generate speed and power adjustment data;

[0146] The laser cutting intelligent adjustment control module is used to perform a secondary cutting operation on the laser cutting machine according to the speed and power adjustment data to generate secondary cutting data; compare the secondary cutting data with the first cutting data to obtain cutting comparison data; predict the optimal cutting parameters of the material thickness of the laser cutting machine according to the cutting comparison data to obtain cutting parameter prediction data; perform intelligent adjustment control on the laser cutting machine based on the cutting parameter prediction data to generate intelligent adjustment control data; perform cutting control on the laser cutting machine according to the intelligent adjustment control data to generate a laser cutting control plan.

[0147] The present invention collects data of the laser cutting machine through the cutting path identification module, ensures a comprehensive understanding of the laser cutting machine, and provides an accurate basis for subsequent analysis; extracts the cutting head movement speed data and performs power calculation, can accurately obtain the laser power data, and provides key parameters for subsequent cutting path planning; based on the cutting head movement speed data and laser power data, the three-dimensional model of the laser cutting machine generated by spatial modeling provides an intuitive visual three-dimensional model for the identification and optimization of the cutting path; the cutting path data generated by the cutting path identification provides clear guidance for the cutting operation of the laser cutting machine, ensuring the accuracy and efficiency of the cutting process. After the first cutting data is extracted by the laser energy distribution prediction module, the smoothness of the cutting edge is evaluated, and the key indicators reflecting the quality of the first cutting can be accurately identified; the cutting path data is fine-tuned according to the edge smoothness data, and the cutting head movement trajectory is optimized, thereby improving the cutting quality; combined with the cutting head movement trajectory and laser power data, the cutting path data is predicted for laser energy distribution, and the predicted laser energy distribution data obtained provides an important reference basis for subsequent simulation cutting experiments. Through the cutting speed and power adjustment module, simulated cutting experiments are carried out according to the predicted laser energy distribution data. The obtained simulated cutting experiment data clarifies the verification parameters of the subsequent cutting operation experiment; the simulated cutting experiment data is compared and analyzed with the predicted laser energy distribution data to provide adjustment guidance for the operation of the laser cutting machine; the laser cutting machine is dynamically adjusted in speed and power according to the cutting parameter optimization data to ensure the stability of the cutting process and the consistency of the cutting quality. Through the laser cutting intelligent adjustment control module, secondary cutting operations are carried out according to the speed and power adjustment data, and the generated secondary cutting data provide actual data support for the comparative analysis of the cutting effect; by comparing the secondary cutting data with the first cutting data, the obtained cutting comparison data can intuitively reflect the effect of the cutting parameter adjustment; according to the cutting comparison data, the optimal cutting parameters of the material thickness of the laser cutting machine are predicted, and parameter prediction is provided for the cutting of different material thicknesses; intelligent adjustment and control are carried out according to the cutting parameter prediction data, realizing the automation and intelligent operation of the laser cutting machine, improving the cutting efficiency and quality, while reducing the complexity of the operation, and finally generating a laser cutting control solution, providing a comprehensive technical solution for the precise cutting of the laser cutting machine. Therefore, the present invention realizes adaptive laser cutting control for different materials and thicknesses through Internet of Things technology, data mapping technology, data analysis technology and intelligent control technology, thereby improving the quality and efficiency of cutting.

[0148] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0149] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A control method for a laser cutting device, characterized in that: The following steps are involved: Step S1: Collect data of the laser cutting machine to obtain laser cutting machine data; extract cutting head moving speed data of the laser cutting machine data to obtain cutting head moving speed data; perform power calculation on the cutting head moving speed data to obtain laser power data; perform spatial modeling based on the cutting head moving speed data and the laser power data to generate a three-dimensional model of the laser cutting machine; perform cutting path recognition on the three-dimensional model of the laser cutting machine to generate cutting path data; Step S2: extracting the first cutting data of the laser cutting machine data to obtain the first cutting data; evaluating the cutting edge smoothness of the first cutting data to obtain edge smoothness data; fine-tuning the cutting path data according to the edge smoothness data to obtain the cutting head movement trajectory; predicting the laser energy distribution of the cutting path data according to the cutting head movement trajectory and the laser power data to obtain predicted laser energy distribution data; Step S3: performing a simulated cutting experiment on the laser cutting machine by predicting the laser energy distribution data to obtain simulated cutting experiment data; performing cutting optimization analysis on the simulated cutting experiment data and the predicted laser energy distribution data to generate cutting parameter optimization data; dynamically adjusting the speed and power of the laser cutting machine according to the cutting parameter optimization data to generate speed and power adjustment data; Step S4: Perform a secondary cutting operation on the laser cutting machine according to the speed and power adjustment data to generate secondary cutting data; compare the secondary cutting data with the first cutting data to obtain cutting comparison data; predict the optimal cutting parameters of the material thickness for the laser cutting machine according to the cutting comparison data to obtain cutting parameter prediction data; perform intelligent adjustment and control on the laser cutting machine based on the cutting parameter prediction data to generate intelligent adjustment control data; perform cutting control on the laser cutting machine according to the intelligent adjustment control data to generate a laser cutting control plan.

2. The control method of the laser cutting device according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: collecting data of the laser cutting machine to obtain laser cutting machine data; performing speed feature recognition on the laser cutting machine data to obtain laser cutting machine speed features; performing cutting head moving speed extraction on the laser cutting machine speed features to obtain cutting head moving speed data; Step S12: Accumulate the cutting head movement speed data to obtain the cutting head speed accumulation data; perform displacement analysis on the cutting head speed accumulation data to obtain the cutting head movement displacement data; perform differential processing on the cutting head movement displacement data to obtain the cutting head speed change rate data; perform power calculation on the cutting head movement speed data according to the cutting head speed change rate data to obtain the laser power data; Step S13: performing cutting space association on the cutting head movement speed data and the laser power data to generate space parameter association data; performing geometric analysis on the laser cutting machine data through the space parameter association data to obtain the laser cutting machine geometry data; performing three-dimensional model construction based on the space parameter association data and the laser cutting machine geometry data to generate a three-dimensional model of the laser cutting machine; Step S14: performing cutting area analysis on the three-dimensional model of the laser cutting machine to obtain cutting area data; performing cutting path recognition on the cutting area data to generate cutting path data.

3. The control method of the laser cutting device according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: extracting cutting conditions from laser cutting machine data to obtain laser cutting data; identifying timestamps from laser cutting data to obtain cutting timestamp data; determining first cutting of laser cutting data according to cutting timestamp data to obtain first cutting data; Step S22: performing edge feature recognition on the first cutting data to obtain first edge feature data; performing cutting contour geometry analysis on the first edge feature data to obtain cutting contour geometry data; performing surface gloss recognition on the cutting contour geometry data to obtain contour surface gloss data; performing smoothness evaluation on the contour surface gloss data to obtain edge smoothness data; Step S23: fine-tuning the cutting path data according to the edge smoothness data to obtain the cutting head movement trajectory; Step S24: predicting the laser energy distribution of the cutting path data according to the cutting head movement trajectory and the laser power data to obtain predicted laser energy distribution data.

4. The control method of the laser cutting device according to claim 3, characterized in that: Step S23 includes the following steps: Step S231: performing geometric irregularity analysis on the edge smoothness data to obtain edge geometric irregularity data; performing feature mapping on the edge smoothness data according to the edge geometric irregularity data to generate edge smoothness feature data; Step S232: Compare the edge smoothness feature data with the preset edge smoothness data to obtain edge deviation data; perform compensation calculation on the edge deviation data to obtain edge deviation compensation data; determine the cutting compensation path parameters on the edge deviation compensation data to obtain path adjustment parameter data; Step S233: performing point-by-point correction processing on the cutting path data according to the path adjustment parameter data to obtain point-by-point corrected path data; performing continuity analysis on the point-by-point corrected path data to obtain cutting path continuity data; Step S234: fine-tuning the cutting head moving speed and direction of the cutting path data according to the cutting path continuity data to obtain cutting head fine-tuning data; Step S235: monitoring the cutting head movement trajectory of the cutting path data according to the cutting head fine-tuning data to obtain the cutting head movement trajectory.

5. The control method of the laser cutting device according to claim 3, characterized in that: Step S24 includes the following steps: Step S241: performing time series analysis on the cutting head movement trajectory to obtain trajectory time series data; decomposing the trajectory time series data into small segments to obtain trajectory segmentation data; Step S242: performing trajectory behavior pattern recognition on the trajectory segmentation data to obtain trajectory behavior pattern data; performing energy demand analysis on the laser power data according to the trajectory behavior pattern data to obtain cutting energy demand data; Step S243: performing laser energy distribution calculation on the cutting energy demand data to obtain laser energy distribution data; performing energy distribution prediction on the cutting path data according to the laser energy distribution data to generate energy prediction distribution data; Step S244: Analyze the cutting effect of the energy prediction distribution data on the active material to obtain active material energy data; predict the laser energy distribution of the cutting path data based on the active material energy data to obtain predicted laser energy distribution data.

6. The control method of the laser cutting device according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing energy distribution area identification on the predicted laser energy distribution data to obtain predicted energy distribution area data; performing cutting experiment parameter setting on the laser cutting machine according to the predicted energy distribution area data to generate cutting experiment parameter data; Step S32: performing a three-dimensional cutting trajectory simulation on the laser cutting machine according to the cutting experiment parameter data to obtain three-dimensional simulated cutting data; performing a simulated cutting experiment on the three-dimensional simulated cutting data to obtain simulated cutting experiment data; performing a laser energy distribution experiment analysis on the simulated cutting experiment data to obtain laser energy distribution experiment data; Step S33: cross-comparing the laser energy distribution experimental data with the predicted laser energy distribution data to obtain energy distribution difference data; performing cutting parameter sensitivity analysis on the energy distribution difference data to obtain cutting parameter sensitivity data; performing cutting optimization analysis on the cutting parameter sensitivity data to generate cutting parameter optimization data; Step S34: performing speed anomaly detection on the cutting parameter optimization data to generate cutting speed anomaly data; dynamically adjusting the speed of the laser cutting machine according to the cutting speed anomaly data to obtain cutting speed adjustment data; performing power anomaly identification on the cutting parameter optimization data to generate cutting power anomaly data; dynamically adjusting the power of the laser cutting machine according to the cutting power anomaly data to obtain cutting power adjustment data; Step S35: Integrate the cutting speed adjustment data and the cutting power adjustment data to obtain speed and power adjustment data.

7. The control method of the laser cutting device according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing application implementation processing on the speed and power adjustment data to obtain application implementation adjustment data; performing a secondary cutting operation on the laser cutting machine according to the application implementation adjustment data to generate secondary cutting data; Step S42: Compare the secondary cutting data with the first cutting data to obtain cutting comparison data; Step S43: performing variability analysis on the cutting comparison data to obtain cutting variability data; performing material adaptability evaluation on the cutting variability data to obtain material adaptability evaluation data; performing material thickness cutting parameter analysis on the material adaptability evaluation data to obtain material thickness cutting parameters; predicting the optimal cutting parameters of the material thickness for the laser cutting machine according to the material thickness cutting parameters to obtain cutting parameter prediction data; Step S44: performing intelligent adjustment control on the laser cutting machine according to the cutting parameter prediction data to generate intelligent adjustment control data; Step S45: Control the laser cutting machine according to the intelligently adjusted control data to generate a laser cutting control solution.

8. The control method of the laser cutting device according to claim 7, characterized in that: Step S42 includes the following steps: Step S421: performing multi-parameter parallel analysis on the secondary cutting data to obtain secondary cutting parallel data, wherein the secondary cutting parallel data includes secondary cutting speed data, secondary cutting power data and secondary cutting quality data; Step S422: performing feature alignment processing on the first cutting data to generate cutting feature alignment data, wherein the cutting feature alignment data includes cutting speed feature alignment data, cutting power feature alignment data and cutting quality feature alignment data; Step S423: Synchronously compare the secondary cutting speed data with the cutting speed feature alignment data to obtain cutting speed comparison data; perform performance matching on the secondary cutting power data with the cutting power feature alignment data to obtain cutting power comparison data; perform quality comparison on the secondary cutting quality data with the cutting quality feature alignment data to obtain cutting quality comparison data; Step S424: Integrate the cutting speed comparison data, the cutting power comparison data and the cutting quality comparison data to obtain cutting comparison data.

9. The control method of the laser cutting device according to claim 7, characterized in that: Step S44 includes the following steps: Step S441: performing material property analysis on the cutting parameter prediction data to obtain cutting material data; correlating the material thickness with the cutting parameters on the cutting material data to obtain cutting material correlation data; Step S442: performing adaptive logic control on the laser cutting machine according to the cutting material related data to obtain adaptive logic control data; Step S443: performing real-time dynamic cutting adjustment on the adaptive logic control data to obtain dynamic cutting adjustment data; performing multi-dimensional synchronous control on the laser cutting machine according to the dynamic cutting adjustment data to obtain multi-dimensional synchronous control data; Step S444: performing multi-objective optimization on the multi-dimensional synchronous control data to obtain multi-objective optimization control data; performing real-time performance monitoring on the laser cutting machine according to the multi-objective optimization control data to obtain real-time performance feedback data; Step S445: Perform intelligent feedback correction and regulation on the laser cutting machine according to the real-time performance feedback data to generate intelligent adjustment control data.

10. A laser cutting device, characterized in that: A control system is included, wherein the control system is used to execute the control method of the laser cutting device according to claim 1, and the control system includes: The cutting path recognition module is used to collect data from the laser cutting machine to obtain laser cutting machine data; extract the cutting head moving speed data from the laser cutting machine data to obtain the cutting head moving speed data; perform power calculation on the cutting head moving speed data to obtain laser power data; perform spatial modeling based on the cutting head moving speed data and the laser power data to generate a three-dimensional model of the laser cutting machine; perform cutting path recognition on the three-dimensional model of the laser cutting machine to generate cutting path data; The laser energy distribution prediction module is used to extract the first cutting data of the laser cutting machine data to obtain the first cutting data; evaluate the cutting edge smoothness of the first cutting data to obtain edge smoothness data; fine-tune the cutting path data according to the edge smoothness data to obtain the cutting head movement trajectory; predict the laser energy distribution of the cutting path data according to the cutting head movement trajectory and the laser power data to obtain the predicted laser energy distribution data; The cutting speed and power adjustment module is used to perform a simulated cutting experiment on the laser cutting machine by predicting the laser energy distribution data to obtain simulated cutting experiment data; perform cutting optimization analysis on the simulated cutting experiment data and the predicted laser energy distribution data to generate cutting parameter optimization data; perform dynamic speed and power adjustment on the laser cutting machine according to the cutting parameter optimization data to generate speed and power adjustment data; The laser cutting intelligent adjustment control module is used to perform a secondary cutting operation on the laser cutting machine according to the speed and power adjustment data to generate secondary cutting data; compare the secondary cutting data with the first cutting data to obtain cutting comparison data; predict the optimal cutting parameters of the material thickness of the laser cutting machine according to the cutting comparison data to obtain cutting parameter prediction data; perform intelligent adjustment control on the laser cutting machine based on the cutting parameter prediction data to generate intelligent adjustment control data; perform cutting control on the laser cutting machine according to the intelligent adjustment control data to generate a laser cutting control plan.

Images