Laser cutting control method, device, equipment and storage medium for rock slabs

Abstract

The present invention relates to the field of laser cutting control, and in particular to a laser cutting control method, device, equipment and storage medium for rock slabs. The method comprises the following steps: obtaining a laser cutting reflection signal based on an optical fiber detector; digitally processing the laser cutting reflection signal, and performing light intensity distribution fitting to construct a light intensity distribution diagram; performing light distribution topological structure analysis on the light intensity distribution diagram to construct a real-time cutting morphology point cloud model; performing real-time morphology deviation comparison on the real-time cutting morphology point cloud model based on a preset theoretical rock slab cutting morphology, thereby obtaining morphology deviation parameters; obtaining real-time operating state parameters of a laser cutter; performing cutting deviation compensation calculation on the real-time operating state parameters of the laser cutter based on the morphology deviation parameters, obtaining a dynamic cutting control strategy, and continuously monitoring the response data of the laser cutting correction process. The present invention realizes efficient and precise laser cutting control, and effectively reduces laser cutting deviations.

Description

Technical Field

[0001] The present invention relates to the field of laser cutting control technology, and in particular to a laser cutting control method, device, equipment and storage medium for rock slabs. Background Art

[0002] With the rapid development of the construction and decoration industries, rock slabs, as an important building material, are widely used in many fields such as floors, walls, countertops, etc. The traditional rock slab cutting method mainly relies on mechanical cutting technology. Although the cutting effect is relatively stable, there are many limitations in cutting accuracy, material waste and production efficiency. In recent years, laser cutting technology has gradually become the preferred solution for rock slab processing due to its high precision, low heat-affected zone and flexibility. Laser cutting technology focuses a high-energy laser beam on the surface of the rock slab, quickly heats the material to a molten state and evaporates it, thereby achieving cutting. This technology can not only achieve the cutting of complex shapes, but also reduce the thermal deformation of the material during the cutting process. However, in actual applications, the laser cutting process is affected by many factors, such as laser power, cutting speed, focal length and material properties, resulting in fluctuations in the accuracy and quality of the cut shape.

[0003] During long-term cutting operations, the cutting effect of the rock plate may be affected by component wear, load changes, and external environmental conditions (such as temperature, humidity, etc.). These factors will not only lead to deviations in the cutting morphology, but may also cause abnormalities in the cutting process, such as edge cracking, uneven cutting depth, etc., which will in turn affect the overall quality and production efficiency of the product.

[0004] Traditional rock slab laser cutting control methods usually rely on empirical rules and manual adjustments. This method is often difficult to maintain consistent cutting quality when faced with large production volumes and complex processes. In addition, the lack of real-time monitoring and feedback mechanisms makes it impossible to adjust cutting parameters in a timely manner during the production process, resulting in low efficiency and material waste. There are often problems such as the cutting effect is not as good as expected and the cutting accuracy is not high. Therefore, in order to meet the above challenges, an intelligent rock slab laser cutting control method is urgently needed. Summary of the invention

[0005] In order to solve the above-mentioned technical problems, the present invention proposes a laser cutting control method, device, equipment and storage medium for rock slabs to solve at least one of the above-mentioned technical problems.

[0006] To achieve the above object, the present invention provides a laser cutting control method for a rock plate, comprising the following steps:

[0007] Step S1: obtaining a laser cutting reflection signal based on a fiber optic detector; digitizing the laser cutting reflection signal, performing light intensity distribution fitting, and constructing a light intensity distribution diagram;

[0008] Step S2: performing light distribution topological structure analysis on the light intensity distribution map, reconstructing the cutting morphology point cloud, and building a real-time cutting morphology point cloud model;

[0009] Step S3: Based on the preset theoretical slab cutting morphology, the real-time cutting morphology point cloud model is compared with the real-time morphology deviation, and then the regional deviation is calculated to obtain the morphology deviation parameter;

[0010] Step S4: obtaining the real-time operating state parameters of the laser cutter; performing cutting deviation compensation calculation on the real-time operating state parameters of the laser cutter based on the morphology deviation parameters, obtaining a dynamic cutting control strategy, and continuously monitoring the response data of the laser cutting correction process;

[0011] Step S5: analyzing the cutting morphology time series change of the real-time cutting morphology point cloud model according to the laser cutting correction process response data, predicting the final cutting morphology evolution, and constructing a rock plate cutting morphology prediction model;

[0012] Step S6: Based on the rock slab cutting morphology prediction model, the dynamic cutting control strategy is adjusted in advance parameters to construct an advance cutting control strategy to perform laser cutting control operations.

[0013] The present invention also provides a laser cutting control device for rock slabs, comprising:

[0014] The light intensity distribution module obtains the laser cutting reflection signal based on the optical fiber detector; digitally processes the laser cutting reflection signal, performs light intensity distribution fitting, and constructs a light intensity distribution diagram;

[0015] The shape reconstruction module analyzes the light distribution topology of the light intensity distribution map, reconstructs the cutting shape point cloud, and builds a real-time cutting shape point cloud model;

[0016] The shape deviation module compares the real-time cutting shape point cloud model with the preset theoretical rock plate cutting shape, and then calculates the regional deviation to obtain the shape deviation parameters;

[0017] The cutting deviation compensation module obtains the real-time operating status parameters of the laser cutter; based on the morphology deviation parameters, the cutting deviation compensation calculation is performed on the real-time operating status parameters of the laser cutter to obtain the dynamic cutting control strategy, and the response data of the laser cutting correction process is continuously monitored;

[0018] A shape evolution prediction module analyzes the cutting shape time series changes of the real-time cutting shape point cloud model according to the response data of the laser cutting correction process, and predicts the final cutting shape evolution to build a rock plate cutting shape prediction model;

[0019] The advanced control module performs advanced parameter control on the dynamic cutting control strategy based on the rock slab cutting morphology prediction model, and constructs an advanced cutting control strategy to perform laser cutting control operations.

[0020] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the laser cutting control method of the rock slab described in any one of the above items are implemented.

[0021] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the laser cutting control method for rock slabs described in any one of the above items are implemented.

[0022] The beneficial effects of the present invention are as follows: by acquiring the reflected signal through the optical fiber detector, the real-time monitoring and data collection of the laser cutting process are realized. Digital processing of the reflected signal and fitting of the light intensity distribution are helpful to understand the light intensity distribution during the cutting process and provide data support for subsequent analysis. Constructing a light intensity distribution diagram can intuitively display the light intensity distribution of the cutting area and help operators understand the optical characteristics of the cutting area. Light distribution topological structure analysis and point cloud reconstruction are helpful to establish a real-time cutting morphology point cloud model and provide basic data for subsequent morphology deviation comparison. By comparing and calculating the deviation of the real-time morphology point cloud model, the deviation of the cutting morphology can be monitored in real time and the cutting control strategy can be adjusted in time. After obtaining the morphology deviation parameters, the cutting quality can be evaluated and controlled to improve the cutting accuracy and efficiency. Through the cutting deviation compensation calculation and dynamic control strategy, the cutting deviation compensation of the real-time operating state parameters of the laser cutter can be realized to improve the cutting accuracy. Continuously monitor the response data of the laser cutting correction process to ensure the stability and accuracy of the cutting process. By analyzing and predicting the time series changes of the cutting morphology, it can help predict the evolution trend of the slab cutting morphology and make cutting preparations and adjustments in advance. Building a prediction model can improve cutting efficiency and accuracy, reduce waste and adjustment time in cutting. Advanced parameter control based on the prediction model can achieve more accurate cutting control, reduce morphological deviation, and improve cutting quality. Building an advanced cutting control strategy can achieve automated adjustment and improve cutting efficiency and quality consistency. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of the steps of a laser cutting control method for a rock plate according to the present invention;

[0024] Figure 2 Detailed implementation flow chart of step S1;

[0025] Figure 3 Detailed implementation flow chart of step S2;

[0026] Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0027] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0028] The present application example provides a laser cutting control method, device, equipment and storage medium for rock slabs. The execution subjects of the laser cutting control method, device, equipment and storage medium for rock slabs include but are not limited to: mechanical equipment, data processing platform, cloud server node, network upload equipment, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio image management system, an information management system, and a cloud data management system.

[0029] See also Figures 1 to 4 The present invention provides a laser cutting control method for a rock plate, and the laser cutting control method for a rock plate comprises the following steps:

[0030] Step S1: obtaining a laser cutting reflection signal based on a fiber optic detector; digitizing the laser cutting reflection signal, performing light intensity distribution fitting, and constructing a light intensity distribution diagram;

[0031] Step S2: performing light distribution topological structure analysis on the light intensity distribution map, reconstructing the cutting morphology point cloud, and building a real-time cutting morphology point cloud model;

[0032] Step S3: Based on the preset theoretical slab cutting morphology, the real-time cutting morphology point cloud model is compared with the real-time morphology deviation, and then the regional deviation is calculated to obtain the morphology deviation parameter;

[0033] Step S4: obtaining the real-time operating state parameters of the laser cutter; performing cutting deviation compensation calculation on the real-time operating state parameters of the laser cutter based on the morphology deviation parameters, obtaining a dynamic cutting control strategy, and continuously monitoring the response data of the laser cutting correction process;

[0034] Step S5: analyzing the cutting morphology time series change of the real-time cutting morphology point cloud model according to the laser cutting correction process response data, predicting the final cutting morphology evolution, and constructing a rock plate cutting morphology prediction model;

[0035] Step S6: Based on the rock slab cutting morphology prediction model, the dynamic cutting control strategy is adjusted in advance parameters to construct an advance cutting control strategy to perform laser cutting control operations.

[0036] The beneficial effects of the present invention are specifically as follows: obtaining reflected signals through optical fiber detectors to achieve real-time monitoring and data collection of the laser cutting process; digital processing of reflected signals and fitting of light intensity distribution are helpful to understand the light intensity distribution during the cutting process and provide data support for subsequent analysis; constructing a light intensity distribution diagram can intuitively display the light intensity distribution of the cutting area and help operators understand the optical characteristics of the cutting area; light distribution topological structure analysis and point cloud reconstruction are helpful to establish a real-time cutting morphology point cloud model and provide basic data for subsequent morphology deviation comparison; by comparing and calculating the deviation of the real-time morphology point cloud model, the deviation of the cutting morphology can be monitored in real time, the cutting control strategy can be adjusted in time, and after obtaining the morphology deviation parameters, the cutting quality can be evaluated and Control, improve cutting accuracy and efficiency, through cutting deviation compensation calculation and dynamic control strategy, it can realize cutting deviation compensation for the real-time operating status parameters of the laser cutter, improve cutting accuracy, continuously monitor the response data of the laser cutting correction process, and ensure the stability and accuracy of the cutting process. Through the analysis and prediction of the time series changes of the cutting morphology, it can help predict the evolution trend of the rock slab cutting morphology, make cutting preparations and adjustments in advance, and build a prediction model to improve cutting efficiency and accuracy, reduce waste and adjustment time in cutting, and adjust the parameters in advance based on the prediction model, which can achieve more accurate cutting control, reduce morphology deviation, and improve cutting quality. Building an advanced cutting control strategy can realize automatic adjustment and improve cutting efficiency and quality consistency.

[0037] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a laser cutting control method for a rock plate of the present invention. In this example, the steps of the laser cutting control method for a rock plate include:

[0038] Step S1: obtaining a laser cutting reflection signal based on a fiber optic detector; digitizing the laser cutting reflection signal, performing light intensity distribution fitting, and constructing a light intensity distribution diagram;

[0039] In this embodiment, a suitable position is selected in the laser cutting system to install the fiber optic detector, usually near the laser cutting head, to ensure that the reflected signal can be accurately received and that the detector position will not be interfered by cutting smoke or other substances to ensure signal quality. The laser cutting machine is started according to the operating procedures, and the cutting parameters (such as power, speed, focal length, etc.) are set to irradiate the laser beam on the material to be cut. The cutting process is monitored to ensure that the laser beam works normally and starts to generate reflected signals. The fiber optic detector converts the signal reflected from the surface of the material into an electrical signal. This process usually involves a photoelectric detector (such as a photodiode or a photomultiplier tube), which can convert optical signals into electrical signals. The intensity and time series data of the reflected signal are recorded through a data acquisition system (such as an oscilloscope or a data acquisition card). These data will be used for subsequent digital processing. The electrical signal is preprocessed, including noise removal, filtering and amplification, to improve the quality of the signal. Digital signal processing (DSP) technology, such as a low-pass filter or a moving average method, can be used to convert the preprocessed analog signal into a digital signal. An analog-to-digital converter (ADC) is usually used for conversion. This process can convert the amplitude of the analog signal into a corresponding digital value to facilitate subsequent analysis. A suitable light intensity distribution fitting method is selected, such as Gaussian fitting, Bessel function fitting or polynomial fitting. The fitting method should be selected according to the characteristics of the reflected signal. A fitting algorithm (such as the least squares method) is used to fit the digitized signal to obtain a mathematical model of the light intensity distribution. According to the fitting results, a visualization tool (such as Matplotlib or MATLAB) is used to draw a light intensity distribution diagram. This diagram can intuitively display the light intensity distribution at different locations.

[0040] Step S2: performing light distribution topological structure analysis on the light intensity distribution map, reconstructing the cutting morphology point cloud, and building a real-time cutting morphology point cloud model;

[0041] In this embodiment, before performing the light distribution topological structure analysis, ensure that the data of the light intensity distribution map is clear and noise-free, use filtering technology (such as Gaussian filtering) to remove possible noise to improve the quality of the data, convert the light intensity distribution data into a format suitable for analysis, usually in the form of a matrix or array, so as to perform subsequent topological analysis, select a suitable topological analysis method, such as a gradient-based edge detection algorithm (such as the Sobel algorithm) or a connectivity-based method (such as morphological analysis), to extract the structural features of the light intensity distribution map, calculate the gradient of the light intensity distribution map to identify the edges of light intensity changes, extract the main contours and features of the light intensity distribution map based on the calculated gradient, and these features will serve as the basis for subsequent point cloud reconstruction, use the extracted light intensity distribution features to convert them into point cloud data, each point in the point cloud can be represented as (x, y, z), where z is the light intensity value or other related parameters (such as cutting depth), apply a point cloud reconstruction algorithm (such as Delaunay triangulation or Poisson triangulation) Reconstruction) converts the light intensity distribution characteristics into a three-dimensional point cloud model. These algorithms can effectively generate surface structures and integrate the generated point cloud data into a real-time cutting morphology point cloud model to ensure that the model can reflect the real-time status of the current cutting process. A dynamic update mechanism is designed to receive new light intensity distribution data in real time and update the point cloud model. This can be achieved by periodically collecting and reconstructing data. The reconstructed point cloud model is visualized using a visualization library (such as PCL, Open3D or MATLAB) for analysis and evaluation, allowing users to interact with the point cloud model, such as rotating, zooming and switching perspectives, in order to better understand the cutting morphology and quality. By analyzing the generated point cloud model, the cutting quality and morphological characteristics are evaluated, which can include the uniformity of the cutting depth, the smoothness of the edge, etc., providing a basis for improving the cutting process. According to the analysis results of the cutting morphology, the recommended parameter adjustments are fed back to the laser cutting system to provide data support for subsequent cutting optimization.

[0042] Step S3: Based on the preset theoretical slab cutting morphology, the real-time cutting morphology point cloud model is compared with the real-time morphology deviation, and then the regional deviation is calculated to obtain the morphology deviation parameter;

[0043] In this embodiment, a preset theoretical rock slab cutting morphology model is obtained from the design stage. This model is usually a three-dimensional model under ideal conditions, which defines the cutting depth, edge shape and other geometric features. To ensure that the data format of the theoretical model is consistent with that of the real-time cutting morphology point cloud model, it is usually converted into a unified point cloud format (such as PLY or OBJ), and the current cutting morphology point cloud model is obtained from the laser cutting system in real time. The model should include the depth and shape data measured in real time during the cutting process. The real-time point cloud data is preprocessed, including denoising, filtering outliers and smoothing, to improve the accuracy of subsequent analysis. The point cloud registration technology (such as the ICP algorithm) is used to align the real-time cutting morphology point cloud model with the preset theoretical model. The ICP (Iterative Closest Point) algorithm achieves the alignment by minimizing the distance between the two groups of point clouds. After the registration is completed, the deviation of each point is calculated, and the entire cutting area is divided into multiple small areas. Usually based on the gridding method, a uniform grid or an adaptive grid based on cutting features can be used. The point deviation in each area is statistically analyzed, and the average deviation and variance of each area are calculated. The calculation results of the regional deviation are integrated to generate the overall morphology deviation parameters, which can include maximum deviation, minimum deviation, average deviation and standard deviation. The calculated morphology deviation parameters are stored in the database, and a corresponding report is generated for subsequent analysis and optimization. According to the calculated morphology deviation parameters, feedback is provided to the laser cutting control system, and it is recommended to adjust the cutting parameters (such as power, speed, etc.) to improve the cutting effect. A continuous monitoring mechanism is established to track the changes in the cutting morphology in real time, and the deviation calculation is continuously updated according to the new data to ensure the cutting quality.

[0044] Step S4: obtaining the real-time operating state parameters of the laser cutter; performing cutting deviation compensation calculation on the real-time operating state parameters of the laser cutter based on the morphology deviation parameters, obtaining a dynamic cutting control strategy, and continuously monitoring the response data of the laser cutting correction process;

[0045] In this embodiment, the real-time operating state parameters that need to be monitored are determined, such as laser power, cutting speed, focal length, cutting depth and feed rate. A data acquisition system (such as a PLC or embedded controller) is used to collect these parameters in real time. These systems can ensure the real-time and accuracy of the data through sensors and feedback mechanisms. The collected operating state parameters are recorded in a database for subsequent analysis and processing. This can use a timestamp to record the changes in each parameter to achieve time series analysis. According to the morphology deviation parameters calculated in the previous step, a compensation calculation model is established. The model will adjust the operating state parameters of the laser cutter according to the real-time morphology deviation. Select a suitable compensation algorithm, such as a proportional-integral-differential (PID) control algorithm or a fuzzy control algorithm. These algorithms can dynamically adjust the parameters of laser cutting according to the deviation. Generate a dynamic cutting control strategy based on the results of the compensation calculation. The strategy should include the adjusted laser power, cutting speed and other relevant parameters. The dynamic cutting control strategy is applied to the laser cutter in real time to ensure that the cutting process can be adjusted in time according to the deviation. Establish a real-time monitoring system to continuously track the operating state and cutting effect of the laser cutter. This system should be able to provide real-time feedback on any abnormal conditions in the cutting process. The monitored correction process response data is recorded and analyzed in real time to ensure that any deviations or problems in the cutting process can be quickly identified. A feedback mechanism is established to compare the real-time monitoring data with the preset ideal cutting effect, identify deviations and make corresponding adjustments. Based on the feedback information, the operating parameters of the laser cutter are dynamically adjusted. This can be achieved through an automatic control system, so that the cutting process can be adaptively adjusted.

[0046] Step S5: analyzing the cutting morphology time series change of the real-time cutting morphology point cloud model according to the laser cutting correction process response data, predicting the final cutting morphology evolution, and constructing a rock plate cutting morphology prediction model;

[0047] In this embodiment, response data of the correction process are obtained from the laser cutting system. These data include real-time cutting morphology changes, cutting parameters, and any external factors that may affect the cutting effect. The collected data are stored in a database for subsequent analysis. The data should include a timestamp for time series analysis. The real-time cutting morphology point cloud model is preprocessed, including denoising, smoothing, and alignment to ensure the consistency of the point cloud model in the time series. A suitable time series analysis method is selected, such as an autoregressive moving average (ARMA) model or a long short-term memory (LSTM) neural network. These methods can effectively capture trends and periodic changes in time series data. The selected time series analysis model is trained using the collected cutting morphology point cloud data. The relationship between different time points should be taken into account during the training process, and the model parameters should be optimized to improve the prediction accuracy. Based on the trained time series analysis model, the future cutting morphology is predicted to evolve. By inputting the latest correction process response data, the model can generate a point cloud prediction of the cutting morphology at future moments. The evolution prediction results are integrated into a complete rock slab cutting morphology prediction model. The model should be able to output the changing trend of the cutting morphology, including cutting depth, shape and edge features. The accuracy of the prediction model can be verified by comparing the prediction results with the actual cutting effect. This process can be carried out using methods such as cross-validation. Select appropriate data visualization tools (such as Matplotlib, Open3D or Paraview) to visualize the results of the prediction model, draw a three-dimensional graph of the cutting morphology evolution, and use different colors or transparency to represent the cutting morphology changes at different time points to help users intuitively understand the dynamic changes of the cutting process.

[0048] Step S6: Based on the rock slab cutting morphology prediction model, the dynamic cutting control strategy is adjusted in advance parameters to construct an advance cutting control strategy to perform laser cutting control operations.

[0049] In this embodiment, the output of the rock slab cutting morphology prediction model is reviewed, including the depth, edge features and other key parameters of the future cutting morphology. These outputs will provide basic data for advanced parameter control, identify the changing trend of the cutting morphology, and evaluate the law of morphology change under different cutting conditions, such as the cutting effect at different powers or speeds. According to the output of the prediction model, a dynamic cutting control strategy framework is constructed. The framework should include adjustment mechanisms for parameters such as laser power, cutting speed, and focal length, and parameter adjustment rules are formulated. For example, when the prediction model shows that the cutting depth is insufficient, increase the laser power; when the cutting edge is not smooth, adjust the cutting speed, and select a suitable advanced control algorithm, such as feedforward control or predictive control (Model Predictive Control, MPC). MPC can optimize the current control strategy based on the analysis of future states, embed the advanced control algorithm into the cutting control system, and ensure that the cutting parameters are dynamically adjusted according to the output of the prediction model. The dynamic cutting control strategy and The advanced parameter control mechanism is applied to laser cutting operations to ensure that the laser cutter can adjust parameters according to real-time feedback and predictions during operation. During the cutting process, the operating status of the laser cutter is continuously monitored, and the cutting parameters are adjusted in real time to cope with changes in the actual cutting process. This can be achieved through a closed-loop control system. After the cutting operation is completed, the effect of the advanced cutting control strategy is evaluated, the cutting quality, efficiency and consistency are analyzed, and the differences between the actual cutting results and the predicted results are compared to identify potential problems. According to the evaluation results, the advanced cutting control strategy is adjusted and optimized. For example, if the adjustment of certain parameters fails to achieve the expected effect, it is necessary to re-evaluate the prediction model and adjustment rules, collect the result data of the cutting operation through the feedback mechanism, and analyze the changes in cutting quality and efficiency. These data will provide a basis for future model updates and strategy optimization. The rock slab cutting morphology prediction model and the advanced cutting control strategy are regularly updated to adapt to new cutting conditions and material properties to ensure that the system can maintain optimal performance in various environments.

[0050] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0051] Step S11: Detect the rock plate cutting process in real time based on the optical fiber detector to obtain the laser cutting reflection signal;

[0052] Step S12: digitally processing the laser cutting reflection signal to obtain laser cutting light data;

[0053] Step S13: calculating the light signal intensity of the laser cutting light data, thereby obtaining the cutting light reflection intensity data;

[0054] Step S14: performing light intensity distribution fitting on the cutting light reflection intensity data to construct a light intensity distribution graph.

[0055] In this embodiment, a laser cutting device is used. The laser cutting device has a laser cutting head. A fiber optic detector is embedded under the laser cutting head. Ensure that the fiber optic detector is correctly installed and connected to the laser cutting device. The optical fiber should be able to effectively receive the signal reflected during the laser cutting process. Configure the parameters of the fiber optic detector, such as sampling rate, sensitivity, etc., to ensure that the details of the laser cutting reflection signal can be captured. Start the laser cutting device and ensure that the cutting process proceeds normally. The fiber optic detector detects the laser signal reflected during the laser cutting process in real time. The detector converts the captured signal into an electrical signal, records the intensity and time information of the reflected signal, digitally samples the original signal, and converts the analog signal into a digital signal. This process can be performed using an analog-to-digital converter (ADC). Apply digital filtering technology (such as a low-pass filter) to remove high-frequency noise to improve the quality and accuracy of the signal. Calculate the intensity of the optical signal, which is usually expressed by the amplitude or power of the signal, using the formula Where I is light intensity, P is power, and A is the laser cutting receiving area. The calculated light signal intensity data is recorded in the data table to form the cutting light reflection intensity data. According to the characteristics of the light intensity distribution, a suitable fitting model (such as Gaussian distribution, Poisson distribution, etc.) is selected to fit and analyze the light intensity data. The light intensity data is fitted using data analysis tools (such as MATLAB, Python's SciPy library, etc.), the fitting parameters are calculated, the fitting results are visualized, and a light intensity distribution diagram is drawn to show the spatial distribution characteristics of the light intensity during the cutting process. The characteristics of the light intensity distribution diagram are analyzed to identify the changing trend of the light intensity and the possible cutting effect, which serves as the basis for subsequent optimization of the cutting process.

[0056] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0057] Step S21: identifying laser reflection points one by one on the light intensity distribution map, and extracting all laser cutting reflection feature points;

[0058] Step S22: performing light distribution topological structure analysis on all laser cutting reflection feature points to obtain an initial rock plate topological structure;

[0059] Step S23: performing non-uniform light scattering analysis on the light intensity distribution diagram to generate laser cutting light scattering data;

[0060] Step S24: performing local light scattering structure correction on the initial rock plate topology structure according to the laser cutting light scattering data to obtain a local corrected rock plate topology structure;

[0061] Step S25: reconstruct the cutting morphology point cloud of the locally corrected rock slab topology structure and construct a real-time cutting morphology point cloud model.

[0062] In this embodiment, a recognition threshold is set according to the characteristics of the light intensity distribution map to distinguish between laser reflection points and background noise, and a suitable image processing algorithm is selected, such as edge detection (Canny edge detection) or threshold segmentation (Otsu method), to automatically identify reflection points. The light intensity distribution map is processed using the selected algorithm, and the laser reflection points are identified one by one, and their coordinate information is extracted. The coordinates and intensity values ​​of all identified laser cutting reflection feature points are recorded in a data table for subsequent analysis. The topological structure of the initial rock slab is constructed based on the data of the feature points using Delaunay triangulation or other topological analysis methods, and key features in the topological model, such as unevenness, cutting depth, etc., are identified to obtain complete structural information of the initial rock slab, and a suitable light scattering method is selected. Analytical models, such as Mie scattering or Rayleigh scattering model, are adapted to the interaction between laser and rock surface. According to the light intensity distribution and laser incident angle, the intensity and distribution of light scattering are calculated to generate laser cutting light scattering data. The influence of light scattering data on the initial rock slab topological structure is analyzed to determine the local area that needs to be corrected. According to the analysis results, the initial rock slab topological structure is adjusted, and appropriate algorithms (such as interpolation or smoothing technology) are applied for local correction to obtain the locally corrected rock slab topological structure. The corrected data is recorded for subsequent processing, and a suitable point cloud reconstruction algorithm is selected, such as Poisson reconstruction, triangular mesh reconstruction, etc., to generate a cutting morphology point cloud model. The corrected topological structure data is input into the reconstruction algorithm to generate a three-dimensional point cloud model of the cutting morphology.

[0063] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0064] Step S31: performing real-time shape deviation comparison on the real-time cutting shape point cloud model based on the preset theoretical rock plate cutting shape, and marking the deviation area;

[0065] Step S32: performing region cutting processing on the real-time cutting morphology point cloud model based on the deviation region to extract the morphology model of the morphology deviation region;

[0066] Step S33: performing regional deviation calculation on the morphology deviation regional morphology model, thereby obtaining morphology deviation parameters.

[0067] In this embodiment, the preset theoretical model is aligned with the real-time cutting morphology point cloud model using point cloud registration technology (such as ICP algorithm, IterativeClosestPoint) to ensure that the two are compared in the same coordinate system. After alignment, the morphology deviation between the two is calculated point by point, and the deviation = real-time cutting point - theoretical cutting point, and the calculated deviation value is stored in the data structure. According to the actual application, a deviation threshold (such as ± 0.5mm) is set to determine which areas are considered to be deviation areas. For points whose deviation values ​​exceed the set threshold, they are marked as deviation areas, and these areas are displayed visually (for example, highlighted with different colors). The morphology model of the deviation area is extracted using a point cloud cutting algorithm (such as KD-Tree or RANSAC). Selecting a suitable algorithm can improve processing speed and accuracy. According to the extracted deviation area points, a new point cloud model is generated, which only contains data from these deviation areas. The deviation parameters are calculated for each point in the deviation area, and the mean, variance and maximum value of the deviation value are statistically calculated to form the deviation parameters. The calculation results are organized into reports for easy analysis and decision-making.

[0068] In this embodiment, step S4 includes the following steps:

[0069] Step S41: obtaining real-time operating status parameters of the laser cutter;

[0070] Step S42: Calculating the laser cutting power based on the real-time operating state parameters of the laser cutter to obtain the laser cutting power characteristics;

[0071] Step S43: performing laser scanning speed identification on the real-time operating state parameters of the laser cutter to extract the laser scanning speed parameters;

[0072] Step S44: performing cutting deviation compensation calculation on the laser scanning speed parameter and the laser cutting power characteristic based on the morphology deviation parameter to obtain a cutting deviation compensation value;

[0073] Step S45: Dynamically correct and regulate the laser cutter according to the cutting deviation compensation value, thereby obtaining a dynamic cutting control strategy, and continuously monitor the response data of the laser cutting correction process.

[0074] In this embodiment, ensure that the data interface of the laser cutter (such as RS-232, USB, Ethernet, etc.) is connected to the data acquisition system. Use data acquisition software (such as LabVIEW, MATLAB) to read the status parameters from the laser cutter in real time, and record the timestamp and parameter value. According to the working characteristics of the laser cutter, calculate the laser cutting power, P = V × I, where P is the laser power, V is the laser voltage, and I is the laser current. Record the calculated laser cutting power characteristics in the data table, monitor the movement of the laser head in real time, obtain the scanning speed through an encoder or speed sensor, or calculate the speed based on the cutting path and time: Where v is the scanning speed, d is the cutting path length, and t is the time taken. According to the morphological deviation and the characteristics of laser power and scanning speed, linear regression or other compensation models are used to calculate the compensation value, and the parameters of the laser cutter are adjusted according to the cutting deviation compensation value, including: Adjusting the laser power: adjusting the power output according to the compensation value. Adjusting the scanning speed: adjusting the moving speed of the cutting head according to the compensation value. Send the adjusted parameters to the laser cutter in real time for dynamic cutting correction. During the correction process, the state parameters of the laser cutter are monitored in real time, and the response data, including actual cutting depth, power, speed, etc., are recorded. A feedback mechanism is established to continuously adjust the compensation strategy based on real-time monitoring data to ensure the quality and efficiency of the cutting process.

[0075] Specific implementation sample code:

[0076] importrandom

[0077] importtime

[0078] classLaserCutter:

[0079] def __init__(self):

[0080] self.power = 0 # laser power

[0081] self.speed=0#scanning speed

[0082] self.depth=0#cutting depth

[0083] def read_status(self):

[0084] #Simulate to obtain real-time status parameters

[0085] self.power = random.uniform(100, 500) #Simulated power range (W)

[0086] self.speed = random.uniform(1, 10) #Simulation speed range (m / s)

[0087] self.depth=random.uniform(0.1, 2.0)#Simulate cutting depth (mm) return{'power':self.power,'speed':self.speed,'depth':self.depth}laser_cutter=LaserCutter()

[0088] #Get parameters in real time

[0089] whileTrue:

[0090] status=laser_cutter.read_status()

[0091] print(f"Real-time status parameter:{status}")

[0092] time.sleep(1)#Get the status once per second

[0093] Laser cutting power calculation:

[0094] defcalculate_laser_power(voltage, current):

[0095] returnvoltage*current#power calculation formula

[0096] #Example: Simulating Voltage and Current

[0097] voltage = random.uniform(10, 100) # voltage (V)

[0098] current = random.uniform(1,5) #current (A)

[0099] power=calculate_laser_power(voltage,current)

[0100] print(f"Calculated laser power:{power:.2f}W")

[0101] Laser scanning speed identification:

[0102] defcalculate_scanning_speed(distance, time):

[0103] returndistance / time#Speed ​​calculation formula

[0104] #Example: Simulating distance and time

[0105] distance=5.0#cutting path length (m)

[0106] time_taken=2.0#Time taken (s)

[0107] scanning_speed=calculate_scanning_speed(distance,time_taken)print(f"Laser scanning speed:{scanning_speed:.2f}m / s")

[0108] Cutting deviation compensation calculation:

[0109] defcalculate_compensation(deviation, power, speed):

[0110] k1, k2, k3 = 0.5, 0.3, 0.2 # Assumed model coefficients

[0111] compensation_value=k1*deviation+k2*power+k3*speed

[0112] returncompensation_value

[0113] #Example: Simulate deviation value

[0114] deviation=0.3#Deviation value(mm)

[0115] compensation_value=calculate_compensation(deviation, power, scanning_speed)

[0116] print(f"Cutting deviation compensation value:{compensation_value:.2f}")

[0117] Dynamic cutting correction control:

[0118] classDynamicControl:

[0119] def __init__(self):

[0120] self.laser_cutter=LaserCutter()

[0121] defadjust_parameters(self, compensation_value):

[0122] #Simulate and adjust the laser cutter parameters

[0123] self.laser_cutter.power+=compensation_value*0.1#Adjust power according to compensation value

[0124] self.laser_cutter.speed+=compensation_value*0.05#Adjust speed according to compensation value

[0125] print(f"Dynamically adjusted laser power: {self.laser_cutter.power:.2f}W")

[0126] print(f"Dynamically adjusted scanning speed: {self.laser_cutter.speed:.2f}m / s")

[0127] #Instantiate dynamic control

[0128] dynamic_control=DynamicControl()

[0129] #Dynamic adjustment based on compensation value

[0130] dynamic_control.adjust_parameters(compensation_value)

[0131] #Continuously monitor the laser cutting correction process response data

[0132] whileTrue:

[0133] current_status=dynamic_control.laser_cutter.read_status()

[0134] print(f"Current laser cutter status:{current_status}")

[0135] time.sleep(1)#Monitor once per second

[0136] In this embodiment, step S5 includes the following steps:

[0137] Step S51: dividing the laser cutting correction process response data into multiple time points to obtain correction process response data at multiple time points;

[0138] Step S52: analyzing the cutting morphology time series changes of the correction process response data at multiple time points to generate the rock plate cutting morphology change data;

[0139] Step S53: performing a rock slab morphology trend evolution analysis on the rock slab cutting morphology change data, thereby obtaining a rock slab morphology trend evolution law;

[0140] Step S54: According to the evolution law of the rock slab morphology trend, the final cutting morphology evolution prediction is performed on the real-time cutting morphology point cloud model to construct a rock slab cutting morphology prediction model.

[0141] In this embodiment, the time point to be analyzed is determined, and it may be selected by uniform intervals or specific event triggering. Use a programming language (such as Python) to split the response data by time point to form a data set of multiple time periods. For example, use the groupby method of the pandas library. Analyze the changes in cutting morphology at different time points, and use statistical analysis methods (such as variance analysis, regression analysis) to identify trends and patterns. Calculate the change in cutting depth at each time point to generate rock slab cutting morphology change data. This can be done by calculating the difference between adjacent time points. According to the extracted rock slab cutting morphology change data, pay attention to the changes in parameters such as cutting depth, power and speed. Apply time series analysis methods (such as ARIMA model, moving average, exponential smoothing) to analyze the change data and identify the law of morphology evolution. Extract the evolution trend of the rock slab morphology based on the analysis results, such as the trend of increasing or decreasing cutting depth. Use the trend law extracted in the previous step to establish a prediction model (such as a linear regression model, a machine learning model, etc.) to predict future cutting morphology. Use a data visualization library (such as Matplotlib or Seaborn) to show the changing trend of the actual cutting depth and the predicted depth.

[0142] In this embodiment, step S6 includes the following steps:

[0143] Step S61: performing a similarity evaluation on the rock slab cutting morphology prediction model based on a preset theoretical rock slab cutting morphology, thereby obtaining a similarity evaluation value;

[0144] Step S62: fine-tuning and optimizing the cutting parameters according to the similarity evaluation value to generate fine-tuning cutting parameters;

[0145] Step S63: Perform advanced parameter adjustment on the dynamic cutting control strategy according to the fine-tuning cutting parameters, and construct an advanced cutting control strategy to execute the laser cutting control operation.

[0146] In this embodiment, a preset theoretical rock slab cutting morphology model is obtained from the theoretical design stage, which is usually in the form of a three-dimensional model, including cutting depth, edge shape and other key features. A cutting morphology prediction model generated based on actual cutting conditions is obtained from the real-time monitoring system. The model can be generated by machine learning algorithms, sensor data and historical cutting data. Feature extraction is performed on the theoretical model and the prediction model to extract key parameters, such as cutting depth, edge profile, roughness, etc. This can be achieved by calculating geometric features or using image processing algorithms (such as edge detection). A suitable similarity evaluation method is used, such as cosine similarity, Euclidean distance or structural similarity index (SSIM). These methods can quantify the difference between the theoretical model and the prediction model. The extracted feature data is input into the selected similarity evaluation algorithm to calculate the similarity evaluation value. A similarity threshold is set according to the historical data and cutting standards, usually between 0 and 1. If the similarity evaluation value is lower than the threshold, parameter fine-tuning is required, and a suitable optimization algorithm is selected, such as a genetic algorithm. , particle swarm optimization or Bayesian optimization. These algorithms can find the best cutting parameter configuration in a certain search space and define the optimization objective function, which is usually to improve the similarity evaluation value. Under the framework of the optimization algorithm, by adjusting the cutting parameters (such as laser power, cutting speed, focal length, etc.), the similarity evaluation value is repeatedly calculated until the best parameter combination is found. According to the fine-tuned cutting parameters, a dynamic cutting control strategy is designed. This strategy should be able to respond to changes in real time during the cutting process and adjust according to the real-time monitoring data to ensure that the laser cutter is equipped with a real-time monitoring system that can continuously monitor parameters such as cutting depth, power, speed, and feed the data back to the control system in real time. Based on the fine-tuned cutting parameters, the control system issues instructions to the laser cutter to adjust parameters such as laser power and cutting speed. For example, if the cutting depth is detected to be insufficient, the system can increase the laser power or adjust the cutting speed in real time. During the cutting process, a feedback mechanism is set to compare the real-time monitoring data with the preset target, and continuously adjust the parameters in the cutting process to ensure the cutting effect.

[0147] In a rock slab cutting operation, the preset theoretical rock slab cutting morphology showed an ideal cutting depth of 10 mm and a smooth edge contour. However, in the actual cutting process, the cutting morphology prediction model generated based on real-time monitoring data showed that the cutting depth was only 8 mm and the edge was obviously rough. Through similarity evaluation, the system calculated that the similarity value between the current cutting effect and the theoretical model was 0.75, which was lower than the set threshold of 0.85. At this time, the system will start fine-tuning and optimizing the cutting parameters, adjusting the laser power from 150W to 180W, and reducing the cutting speed to avoid overheating and material damage.

[0148] After fine-tuning, the system re-evaluated the similarity, and the results showed that the similarity increased to 0.88, which was in line with expectations. Finally, based on these fine-tuning parameters, the system constructed an advanced cutting control strategy to control the laser cutter in real time to ensure that in the subsequent cutting process, it can continue to maintain the ideal cutting effect and ultimately achieve high-quality rock slab cutting operations. This method not only improves the cutting efficiency, but also reduces material waste, achieving a dual improvement in economic benefits and cutting quality.

[0149] The present invention also provides a laser cutting control device for rock slabs, comprising:

[0150] The light intensity distribution module obtains the laser cutting reflection signal based on the optical fiber detector; digitally processes the laser cutting reflection signal, performs light intensity distribution fitting, and constructs a light intensity distribution diagram;

[0151] The shape reconstruction module analyzes the light distribution topology of the light intensity distribution map, reconstructs the cutting shape point cloud, and builds a real-time cutting shape point cloud model;

[0152] The shape deviation module compares the real-time cutting shape point cloud model with the preset theoretical rock plate cutting shape, and then calculates the regional deviation to obtain the shape deviation parameters;

[0153] The cutting deviation compensation module obtains the real-time operating status parameters of the laser cutter; based on the morphology deviation parameters, the cutting deviation compensation calculation is performed on the real-time operating status parameters of the laser cutter to obtain the dynamic cutting control strategy, and the response data of the laser cutting correction process is continuously monitored;

[0154] A shape evolution prediction module analyzes the cutting shape time series changes of the real-time cutting shape point cloud model according to the response data of the laser cutting correction process, and predicts the final cutting shape evolution to build a rock plate cutting shape prediction model;

[0155] The advanced control module performs advanced parameter control on the dynamic cutting control strategy based on the rock slab cutting morphology prediction model, and constructs an advanced cutting control strategy to perform laser cutting control operations.

[0156] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the laser cutting control method of the rock slab described in any one of the above items are implemented.

[0157] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the laser cutting control method for rock slabs described in any one of the above items are implemented.

[0158] Those skilled in the art clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0159] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it is stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or partly or all or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media for storing program codes such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0160] 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.

[0161] The above 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 will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A laser cutting control method for rock slabs, characterized in that: The following steps are involved: Step S1: obtaining a laser cutting reflection signal based on a fiber optic detector; digitizing the laser cutting reflection signal, performing light intensity distribution fitting, and constructing a light intensity distribution diagram; Step S2: performing light distribution topological structure analysis on the light intensity distribution map, reconstructing the cutting morphology point cloud, and building a real-time cutting morphology point cloud model; Step S3: Based on the preset theoretical slab cutting morphology, the real-time cutting morphology point cloud model is compared with the real-time morphology deviation, and then the regional deviation is calculated to obtain the morphology deviation parameter; Step S4: obtaining the real-time operating state parameters of the laser cutter; performing cutting deviation compensation calculation on the real-time operating state parameters of the laser cutter based on the morphology deviation parameters, obtaining a dynamic cutting control strategy, and continuously monitoring the response data of the laser cutting correction process; Step S5: analyzing the cutting morphology time series change of the real-time cutting morphology point cloud model according to the laser cutting correction process response data, predicting the final cutting morphology evolution, and constructing a rock plate cutting morphology prediction model; Step S6: Based on the rock plate cutting morphology prediction model, the dynamic cutting control strategy is controlled by advanced parameters, and an advanced cutting control strategy is constructed to perform laser cutting control operations; The specific steps of step S4 are: Step S41: obtaining real-time operating status parameters of the laser cutter; Step S42: Calculating the laser cutting power based on the real-time operating state parameters of the laser cutter to obtain the laser cutting power characteristics; Step S43: performing laser scanning speed identification on the real-time operating state parameters of the laser cutter to extract the laser scanning speed parameters; Step S44: performing cutting deviation compensation calculation on the laser scanning speed parameter and the laser cutting power characteristic based on the morphology deviation parameter to obtain a cutting deviation compensation value; Step S45: dynamically adjusting and correcting the laser cutter according to the cutting deviation compensation value, thereby obtaining a dynamic cutting control strategy, and continuously monitoring the response data of the laser cutting correction process; The specific steps of step S6 are: Step S61: performing a similarity evaluation on the rock slab cutting morphology prediction model based on a preset theoretical rock slab cutting morphology, thereby obtaining a similarity evaluation value; Step S62: fine-tuning and optimizing the cutting parameters according to the similarity evaluation value to generate fine-tuning cutting parameters; Step S63: Perform advanced parameter adjustment on the dynamic cutting control strategy according to the fine-tuning cutting parameters, and construct an advanced cutting control strategy to execute the laser cutting control operation.

2. The laser cutting control method of rock plate according to claim 1 is characterized in that: The specific steps of step S1 are: Step S11: Detect the rock plate cutting process in real time based on the optical fiber detector to obtain the laser cutting reflection signal; Step S12: digitally processing the laser cutting reflection signal to obtain laser cutting light data; Step S13: calculating the light signal intensity of the laser cutting light data, thereby obtaining the cutting light reflection intensity data; Step S14: performing light intensity distribution fitting on the cutting light reflection intensity data to construct a light intensity distribution graph.

3. The laser cutting control method of rock plate according to claim 1 is characterized in that: The specific steps of step S2 are: Step S21: identifying laser reflection points one by one on the light intensity distribution map, and extracting all laser cutting reflection feature points; Step S22: performing light distribution topological structure analysis on all laser cutting reflection feature points to obtain an initial rock plate topological structure; Step S23: performing non-uniform light scattering analysis on the light intensity distribution diagram to generate laser cutting light scattering data; Step S24: performing local light scattering structure correction on the initial rock plate topology structure according to the laser cutting light scattering data to obtain a local corrected rock plate topology structure; Step S25: reconstruct the cutting morphology point cloud of the locally corrected rock slab topology structure and construct a real-time cutting morphology point cloud model.

4. The laser cutting control method of rock plate according to claim 1 is characterized in that: The specific steps of step S3 are: Step S31: performing real-time shape deviation comparison on the real-time cutting shape point cloud model based on the preset theoretical rock plate cutting shape, and marking the deviation area; Step S32: performing region cutting processing on the real-time cutting morphology point cloud model based on the deviation region to extract the morphology model of the morphology deviation region; Step S33: performing regional deviation calculation on the morphology deviation regional morphology model, thereby obtaining morphology deviation parameters.

5. The laser cutting control method of rock plate according to claim 1 is characterized in that: The specific steps of step S5 are: Step S51: dividing the laser cutting correction process response data into multiple time points to obtain correction process response data at multiple time points; Step S52: analyzing the cutting morphology time series changes of the correction process response data at multiple time points to generate the rock plate cutting morphology change data; Step S53: performing a rock slab morphology trend evolution analysis on the rock slab cutting morphology change data, thereby obtaining a rock slab morphology trend evolution law; Step S54: According to the evolution law of the rock slab morphology trend, the final cutting morphology evolution prediction is performed on the real-time cutting morphology point cloud model to construct a rock slab cutting morphology prediction model.

6. A laser cutting control device for rock slabs, characterized in that: A laser cutting control method for executing the rock plate according to claim 1, comprising: The light intensity distribution module obtains the laser cutting reflection signal based on the optical fiber detector; digitally processes the laser cutting reflection signal, performs light intensity distribution fitting, and constructs a light intensity distribution diagram; The shape reconstruction module analyzes the light distribution topology of the light intensity distribution map, reconstructs the cutting shape point cloud, and builds a real-time cutting shape point cloud model; The shape deviation module compares the real-time cutting shape point cloud model with the preset theoretical rock plate cutting shape, and then calculates the regional deviation to obtain the shape deviation parameters; The cutting deviation compensation module obtains the real-time operating status parameters of the laser cutter; based on the morphology deviation parameters, the cutting deviation compensation calculation is performed on the real-time operating status parameters of the laser cutter to obtain the dynamic cutting control strategy, and the response data of the laser cutting correction process is continuously monitored; A shape evolution prediction module analyzes the cutting shape time series changes of the real-time cutting shape point cloud model according to the response data of the laser cutting correction process, and predicts the final cutting shape evolution to build a rock plate cutting shape prediction model; The advanced control module performs advanced parameter control on the dynamic cutting control strategy based on the rock slab cutting morphology prediction model, and constructs an advanced cutting control strategy to perform laser cutting control operations.

7. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the laser cutting control method of the rock slab described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the laser cutting control method for rock slabs described in any one of claims 1 to 5 are implemented.

Images