An adaptive focal length adjusting method of an ultra-precision high-power laser cutting device

Abstract

The application relates to the technical field of industrial control, and provides a self-adaptive focal length adjusting method of an ultra-precise high-power laser cutting device.The method comprises the following steps: monitoring and acquiring the thickness and attribute information of a first layer of material; performing focal length analysis on the laser cutting device according to the thickness and attribute information, and outputting a first layer cutting focal length; performing one-time laser cutting on the composite material according to the first layer focal length, and monitoring first layer cutting edge data; performing secondary focal length compensation analysis according to the edge data, outputting a compensation coefficient, correcting a second layer focal length, and outputting an optimized focal length; performing secondary cutting on the composite material according to the optimized focal length, and iteratively correcting the focal length and controlling the cutting until the tail layer cutting is completed.The application solves the technical problems of unstable cutting focal length and insufficient cutting precision caused by the thickness and attribute differences of the material in the process of cutting the multi-layer composite material by using the laser cutting device in the industrial control, and achieves the technical effect of improving the precision and efficiency of the laser cutting process in the industrial control.

Description

Technical Field

[0001] This application relates to the field of industrial control technology, specifically to an adaptive focal length adjustment method for ultra-precision high-power laser cutting equipment. Background Technology

[0002] High-power laser cutting equipment is an advanced device that uses a high-power laser beam for cutting and processing, and is widely used for precision cutting of various materials such as metals, composite materials, ceramics, and plastics. However, when processing multi-layer composite materials, traditional high-power laser cutting equipment struggles to ensure consistency in the cut surfaces of each layer due to differences in thickness, variations in thermophysical properties, and the heat accumulation effect during processing. This leads to process defects such as fluctuating edge quality and an expanded heat-affected zone. Particularly in the processing of carbon fiber reinforced composite materials and titanium alloy laminates, the differences in the reflectivity and absorptivity of the materials to lasers can reach orders of magnitude. Existing industrial control methods lack real-time sensing and dynamic adjustment capabilities, often requiring manual intervention to adjust parameters, which severely restricts production efficiency and product qualification rates. Summary of the Invention

[0003] This application provides an adaptive focal length adjustment method for ultra-precision high-power laser cutting equipment, aiming to solve the technical problems of unstable cutting focal length and insufficient cutting accuracy caused by differences in material thickness and properties during the cutting of multi-layer composite materials in industrial control. The method aims to improve the accuracy and efficiency of the laser cutting process in industrial control by means of adaptive focal length adjustment, and ensure that the cutting quality of each layer of material is stable and meets the precision requirements.

[0004] This application provides an adaptive focal length adjustment method for an ultra-precision high-power laser cutting equipment. The method includes: monitoring and acquiring the material thickness and material property information of the first layer of a multilayer composite material; performing a cutting focal length analysis on the current laser cutting equipment based on the material thickness and material property information, and outputting the first layer cutting focal length; performing a laser cut on the multilayer composite material according to the first layer cutting focal length, and monitoring and acquiring the first layer cutting edge state data; performing a secondary cutting focal length compensation analysis based on the first layer cutting edge state data, outputting a secondary cutting compensation coefficient, correcting the second layer cutting focal length, and outputting an optimized second layer cutting focal length; performing a secondary laser cut on the multilayer composite material according to the optimized second layer cutting focal length, and iteratively performing cutting focal length correction and cutting control until the tail layer cutting operation is completed.

[0005] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0006] The aforementioned adaptive focal length adjustment method for ultra-precision high-power laser cutting equipment first collects relevant data by monitoring the thickness and properties of the first layer in a multi-layer composite material. Then, based on this data, the focal length of the current laser cutting equipment is analyzed to determine the suitable focal length for the first layer cutting, and this focal length is output. After obtaining the first-layer cutting focal length, the equipment performs the first laser cut according to this focal length, and the cutting effect is evaluated by monitoring the state data of the first-layer cutting edge. Subsequently, based on these edge state data, a secondary focal length compensation analysis is performed to obtain a compensation coefficient used to adjust the second-layer cutting focal length. Through this compensation analysis, the second-layer cutting focal length can be corrected to obtain an optimized second-layer cutting focal length. The optimized focal length is applied to the laser cutting of the second layer, and further iterative optimization of the focal length is performed based on the cutting effect. This process continues until the cutting operations of all layers are completed, thereby ensuring the cutting accuracy and quality of the entire multi-layer composite material.

[0007] The above description is merely an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 This is a flowchart illustrating an adaptive focal length adjustment method for an ultra-precision high-power laser cutting device in one embodiment.

[0010] Figure 2 This is a schematic diagram illustrating the process of obtaining material thickness and material property information using an adaptive focal length adjustment method for an ultra-precision high-power laser cutting device in one embodiment. Detailed Implementation

[0011] This application provides an adaptive focal length adjustment method for ultra-precision high-power laser cutting equipment. This method addresses the technical problems of unstable cutting focal length and insufficient cutting accuracy caused by differences in material thickness and properties during the cutting of multi-layer composite materials in industrial control. The goal is to improve the accuracy and efficiency of the laser cutting process in industrial control through adaptive focal length adjustment, ensuring stable cutting quality of each layer of material and meeting precision requirements.

[0012] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0013] It should be noted that the terms “comprising” and “having”, and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to such process, method, product, or device.

[0014] Examples, such as Figure 1 As shown, this application provides an adaptive focal length adjustment method for ultra-precision high-power laser cutting equipment, the method comprising:

[0015] Monitoring and acquiring information on the material thickness and properties of the first layer in a multilayer composite material.

[0016] In this embodiment, laser ranging technology is used to obtain the thickness of the first layer in a multilayer composite material. Simultaneously, the material's property information, such as absorptivity, reflectivity, and thermal conductivity, is also acquired. These properties are crucial for optimizing the subsequent laser cutting process. By obtaining this thickness and property data, necessary foundational information can be provided for subsequent laser cutting focal length analysis and compensation.

[0017] Furthermore, such as Figure 2 As shown, this application provides methods for monitoring and acquiring the material thickness and material property information of the first layer material in a multilayer composite material, including:

[0018] Laser ranging technology is used to monitor and obtain the material thickness of the first layer in a multilayer composite material; the material property information of the first layer is obtained, wherein the material property information includes at least absorptivity, reflectivity, thermal conductivity, melting point and coefficient of thermal expansion.

[0019] Preferably, laser ranging technology is first used to emit a laser beam onto the surface of the multilayer composite material using a laser sensor, and the reflected laser beam is received by the sensor. The time difference between emission and reception of the laser beam is then measured to calculate the material thickness data of the first layer. Typically, the laser rangefinder can adjust its focus to focus only on the surface of the first layer, thus avoiding the measurement of the thickness of other layers. Subsequently, material property information of the first layer is obtained from the material's technical manual, including but not limited to absorptivity, reflectivity, thermal conductivity, melting point, and coefficient of thermal expansion. Among these, absorptivity refers to the proportion of light energy absorbed by the material to the incident light energy, which determines the efficiency of energy conversion into heat energy during laser cutting; reflectivity refers to the proportion of light energy reflected from the material surface to the incident light energy, affecting energy transfer during laser cutting; thermal conductivity refers to the material's ability to transfer heat; materials with high thermal conductivity dissipate heat more quickly, affecting the temperature distribution during laser cutting; melting point refers to the temperature at which the material changes from a solid to a liquid state, affecting the melting behavior of the material during cutting; and the coefficient of thermal expansion refers to the rate of dimensional change of the material with temperature changes, determining the degree of deformation of the material during heating. In summary, by obtaining the thickness of the first layer of material and its key properties, necessary data support can be provided for subsequent laser cutting processes.

[0020] Based on the material thickness and material property information, the cutting focal length of the current laser cutting equipment is analyzed, and the first-layer cutting focal length is output.

[0021] In one embodiment, after obtaining the material thickness and material property information of the first layer material, this data is input into a pre-built cutting focal length analysis model for cutting focal length analysis. The cutting focal length analysis model combines the material thickness, absorptivity, reflectivity and other properties, and uses the learned mapping relationship to calculate the first layer cutting focal length suitable for the current material, which is used to control the laser cutting head to automatically adjust the focal length, thereby ensuring the accuracy and efficiency of the first layer cutting.

[0022] Furthermore, this application provides a method for analyzing the cutting focal length of a current laser cutting device based on the material thickness and material property information, and outputting the first-layer cutting focal length, including:

[0023] Using the current laser cutting equipment as the equipment retrieval constraint, historical laser cutting records of similar equipment are obtained. Based on the historical laser cutting records, sample material thickness sets and sample material attribute datasets are collected, and the average historical cutting focal length of different sample material thicknesses and different sample material attribute data under the cutting standard is statistically analyzed and set as the sample cutting focal length, thus obtaining a sample cutting focal length set. A cutting focal length analysis model is constructed using a deep neural network, and the sample material thickness set and sample material attribute dataset are used as inputs, while the sample cutting focal length set is used as supervision to train the cutting focal length analysis model, obtaining a cutting focal length analysis model that meets the preset convergence conditions. Using the cutting focal length analysis model, the cutting focal length of the current laser cutting equipment is analyzed based on the material thickness and material attribute information, and the first-layer cutting focal length is output.

[0024] Preferably, the process begins by using the current laser cutting equipment as the equipment retrieval constraint. Historical laser cutting records for similar equipment are extracted from a historical database. These records include focal length settings and material properties under different materials and cutting conditions. Based on the acquired historical laser cutting records, relevant sample material thickness sets and sample material property datasets are extracted. These datasets contain the thickness and properties (such as absorptivity and reflectivity) of different materials. The average historical cutting focal length under each material condition is statistically calculated according to the cutting standard. These averages are set as sample cutting focal lengths, forming a sample cutting focal length set. After obtaining the sample dataset, a cutting focal length analysis model is constructed using a deep neural network, including input layers, hidden layers, and output layers. The weights of the cutting focal length analysis model are initialized using random numbers and other methods. The sample dataset is then input into the initialized cutting focal length analysis model for forward propagation. The model is passed layer by layer through the input layer, hidden layer, and output layer to calculate the predicted result, including the cutting focal length. Subsequently, the mean squared error loss function is used to calculate the loss value between the predicted result and the sample cutting focal length. The gradient of the loss with respect to the weights of each layer is calculated layer by layer through backpropagation. The Adam optimizer is then used to optimize the model parameters, adjusting the weights to minimize the loss function value. This process is repeated until the maximum number of iterations is reached or the loss function converges. After training, the model performance is tested using sample data not used for training to evaluate the model's accuracy in the cutting focal length prediction task. If the accuracy meets expectations, the current cutting focal length analysis model is output; otherwise, hyperparameters such as the learning rate and the number of training batches are adjusted to further improve the predictive performance of the cutting focal length analysis model. Once training is complete, the current material thickness and material property information are input into the cutting focal length analysis model to perform cutting focal length analysis on the current laser cutting equipment. The model outputs a suitable cutting focal length for the first layer of material. This focal length is used to adjust the laser cutting head to ensure accuracy and efficiency during the cutting process, thereby improving the precision and efficiency of the laser cutting process, reducing manual intervention, and increasing the automation level of industrial control.

[0025] The multilayer composite material is laser-cut once according to the first layer cutting focal length, and the state data of the first layer cutting edge is monitored and acquired.

[0026] In one embodiment, based on the calculated focal length for the first layer cut, the laser cutting equipment performs the first laser cut on the multilayer composite material at this focal length. During the cutting process, the laser beam is focused on the first layer of the material and processed according to the set cutting conditions to ensure precise cutting of the first layer. During the first layer cut, an infrared thermal imager and a vision sensor are used to simultaneously monitor the edge state of the cutting area, acquiring data on the first layer's cutting edge state, including the distribution of the heat-affected zone, the amount of slag, and the number of pores. This data helps assess the cutting quality and determine whether the focal length needs adjustment, so that subsequent cutting operations can be more precise.

[0027] Furthermore, this application provides methods for monitoring and acquiring the state data of the first-layer cutting edge, including:

[0028] The temperature distribution of the first-layer cutting area is monitored using an infrared thermal imager to obtain the distribution of the heat-affected zone, which includes its shape and size. Images of the first-layer cutting area are acquired using a visual sensor, and the number of slag and pores is obtained based on the image recognition of the cutting area. A convolutional neural network is used to identify and extract the features of slag and pores. The distribution of the heat-affected zone, the number of slag, and the number of pores are used as the state data of the first-layer cutting edge.

[0029] Preferably, during the first-layer laser cutting process, an infrared thermal imager performs real-time temperature imaging of the cutting area. By sensing the temperature distribution at different locations, the heat-affected zone (HAZ) caused by high temperatures around the material after cutting can be determined. In the thermal image output by the infrared thermal imager, different temperature areas are represented by different colors or grayscale changes. Through binarization processing, areas in the thermal image with temperatures greater than or equal to a temperature threshold are marked as 1 or white, representing the HAZ; areas with temperatures less than the threshold are marked as "0" or black, representing the non-HAZ. Subsequently, the contour of the HAZ in the binary image is extracted using edge detection algorithms (such as Canny edge detection, Sobel operator, or contour detection methods). These edge detection algorithms detect and delineate the edges of the HAZ by recognizing changes in grayscale or color in the image, thus obtaining the shape of the HAZ. After extracting the contour, a region filling algorithm is used to fill the pixels inside the HAZ, generating a complete HAZ. Then, by counting the number of pixels within the HAZ, the area of ​​the HAZ is calculated. Simultaneously, a vision sensor (such as an industrial camera) acquires high-resolution images of the area after the first layer of cutting is completed. These images include potential defect features at the cutting edge, such as slag accumulation and porosity. The acquired cutting images are then input into a convolutional neural network (CNN) model. This CNN is pre-trained using the same training method as described above, iteratively performing forward propagation, loss calculation, backpropagation, and parameter optimization. Based on its learned knowledge, the CNN automatically identifies and marks slag and porosity, and counts the number of slag and pores. Finally, the shape and size of the heat-affected zone, the amount of slag, and the number of pores are integrated into a complete set of first-layer cutting edge state data. This data serves as a crucial basis for subsequent cutting focal length compensation analysis, used to evaluate the current cutting quality and guide the optimization of cutting parameters for subsequent layers. This ensures that subsequent cutting processes are dynamically adjusted based on the actual cutting effect, thereby improving overall cutting accuracy and stability.

[0030] Based on the first-layer cutting edge state data, a secondary cutting focal length compensation analysis is performed, and a secondary cutting compensation coefficient is output to correct the second-layer cutting focal length and output an optimized second-layer cutting focal length.

[0031] In one embodiment, the cutting quality is first analyzed based on the edge status data of the first layer. Specifically, the shape and size of the monitored heat-affected zone, the amount of slag, and the number of pores are input into the focal length compensation analysis model to assess whether there is a deviation in the current cut and output a secondary cutting compensation coefficient. This compensation coefficient reflects the degree and direction of the current focal length deviation, such as needing to slightly increase or decrease the focal length to improve the accuracy of the next layer's cut. Subsequently, based on the secondary cutting compensation coefficient calculated for the first layer, the focal length of the second layer cut, determined based on the material thickness and material property information of the second layer material, is corrected to generate an optimized second-layer cutting focal length. Finally, the laser cutting equipment uses this optimized second-layer cutting focal length to perform the next cutting operation on the multi-layer composite material, thereby continuously optimizing the cutting quality during each layer's cutting process and ensuring that the overall cutting effect meets ultra-precision requirements.

[0032] Furthermore, this application provides a secondary cutting focal length compensation analysis based on the first-layer cutting edge state data, outputting secondary cutting compensation coefficients, including:

[0033] Based on historical laser cutting records, a set of information distributions of the heat-affected zone (HAZ), a set of information on the quantity of molten slag, and a set of information on the quantity of pores were collected. The material cutting deviation range under different HAZ distributions, molten slag quantities, and pore quantities was statistically analyzed and set as the sample cutting compensation coefficients, resulting in a set of sample cutting compensation coefficients. Using the aforementioned set of information distributions of the HAZ, molten slag quantities, pore quantities, and cutting compensation coefficients, a deep neural network was trained to construct a focal length compensation analysis model. The first-layer cutting edge state data was input into the focal length compensation analysis model, and the secondary cutting compensation coefficients were output.

[0034] Optionally, based on historical laser cutting records extracted from a historical database, a set of sample heat-affected zone information distribution, a set of sample slag quantity, and a set of sample porosity quantity are collected. These sample data will serve as input features for subsequent analysis and model training. For each sample data, the difference between the corresponding cutting result and the expected result is obtained, i.e., the material cutting deviation amplitude. This material cutting deviation amplitude is used to define the sample cutting compensation coefficient, representing the amount of adjustment required for the focal length. By adding these sample cutting compensation coefficients to a set, a sample cutting compensation coefficient set is obtained for model training. Subsequently, the collected sample data (heat-affected zone information, slag quantity, porosity quantity, etc.) and the corresponding sample cutting compensation coefficients are used as input data to train a deep neural network. The network learns the relationship between different sample features and focal length compensation, gradually adjusting its internal parameters, and finally constructs an analytical model that can accurately predict the focal length compensation coefficient, i.e., the focal length compensation analysis model. After the focal length compensation analysis model is trained, it is used to analyze the edge state data of the first layer of cutting. Edge state data (such as heat-affected zone, slag quantity, and porosity) obtained during the actual cutting process are input into a trained model. The model then outputs a secondary cutting compensation coefficient based on this data. This coefficient indicates how to adjust the laser cutting focal length to achieve a more precise cutting effect for the current cutting state. Through this process, the deep neural network can effectively learn focal length compensation patterns from historical data and apply them to the actual cutting process, thereby achieving continuous optimization of cutting accuracy.

[0035] Furthermore, this application provides a method for training a deep neural network and constructing a focal length compensation analysis model using the sample heat-affected zone information distribution set, the sample slag quantity set, the sample porosity quantity set, and the sample cutting compensation coefficient set, including:

[0036] The sample heat-affected zone information distribution set, sample slag quantity set, sample pore quantity set, and sample cutting compensation coefficient set are used as training data and divided into P equal parts to obtain P sample datasets, where P is an integer greater than 5. The deep neural network is trained and tested using the P sample datasets until the network converges, resulting in P focal length compensation analysis units, which are then combined to construct a focal length compensation analysis model.

[0037] Optionally, the heat-affected zone information distribution set, slag quantity set, porosity quantity set, and cutting compensation coefficient set of the samples are used as training data and equally divided to obtain P sample datasets. Each sample dataset contains a portion of the sample data and can be used for model training or testing, ensuring fairness and data diversity in the training process. Here, P is an integer greater than 5, which can be set according to actual needs. Subsequently, a portion of the P datasets (e.g., the first subset) is used as training data, and the remaining subsets are used as test data, input into the deep neural network for training. The training process is the same as described above. After training, the test data is used to evaluate the performance of the trained model and calculate the model's prediction accuracy. In this way, the training and testing processes are continuously alternated to ensure that each set of data is used for training and testing, avoiding overfitting or underfitting problems. After all tests are passed, P focal length compensation analysis units are generated. Each analysis unit is based on a different data subset and training results and can independently perform focal length compensation analysis. Finally, the P focal length compensation analysis units are combined to form a complete focal length compensation analysis model. This model integrates all the knowledge acquired during training and can output accurate focal length compensation coefficients based on the actual first-layer cutting edge state data. This combination method can improve the robustness and accuracy of the model, avoid the limitations that may exist in a single model, and thus optimize the laser cutting quality.

[0038] Furthermore, this application provides a method for inputting the first-layer cutting edge state data into the focal length compensation analysis model and outputting secondary cutting compensation coefficients, including:

[0039] Calculate the ratios of the heat-affected zone information distribution, slag quantity, and porosity quantity to the historical maximum heat-affected zone information distribution, historical maximum slag quantity, and historical maximum porosity quantity, and then weight them to determine the cutting deviation scale coefficient. Multiply the cutting deviation scale coefficient by P and round it to obtain the number of units selected, K. Randomly select K focal length compensation analysis units from the P focal length compensation analysis units in the focal length compensation analysis model to perform compensation analysis on the first-layer cutting edge state data, output K compensation coefficients, and calculate the average value to obtain the secondary cutting compensation coefficient.

[0040] Optionally, the distribution of heat-affected zone (HAZ), the amount of molten slag, and the number of pores in the first-layer cutting edge state data are calculated as ratios to the maximum HAZ distribution, maximum molten slag amount, and maximum number of pores in historical data. For example, the current HAZ area is compared to the historical maximum HAZ area, the current molten slag amount is compared to the historical maximum molten slag amount, and the current number of pores is compared to the historical maximum number of pores, yielding three ratios. These ratios are then weighted and summed according to preset weights (which can be set based on historical experience or experimental data) to obtain a cutting deviation scale coefficient. This coefficient is then multiplied by the sample subset size P and rounded up to obtain the number of selected units K. Next, K units are randomly selected from the P trained focal length compensation analysis units. Each unit independently outputs a focal length compensation coefficient based on the input first-layer cutting edge state data. Finally, the average of the compensation coefficients output by these K compensation units is calculated to obtain the final secondary cutting compensation coefficient, which is used for subsequent correction and optimization of the second-layer cutting focal length. In summary, by dynamically adjusting the number of analysis units based on actual cutting deviations, the focal length compensation intensity can be flexibly adjusted according to the actual cutting effect of the first layer, making the compensation results both accurate and adaptable, and significantly improving the industrial control precision and reliability in the cutting process of multi-layer composite materials.

[0041] Furthermore, this application provides a method for correcting the focal length of the two-layer cutting and outputting an optimized focal length for the two-layer cutting, including:

[0042] The material thickness and material property information of the second layer in the multilayer composite material are monitored and obtained, and the cutting focal length of the second layer is determined by analysis; the secondary cutting compensation coefficient is subtracted from 1 to obtain the secondary correction coefficient; the cutting focal length of the second layer is corrected according to the secondary correction coefficient, and the optimized cutting focal length of the second layer is output.

[0043] Preferably, after the first layer of cutting is completed, the laser cutting equipment uses laser ranging technology to measure the thickness of the exposed second layer of material. Simultaneously, it collects the material's properties, including parameters such as absorptivity, reflectivity, thermal conductivity, melting point, and coefficient of thermal expansion. Then, the monitored thickness and properties of the second layer are input into the cutting focal length analysis model, outputting a preliminary second-layer cutting focal length. This focal length is calculated solely based on the material's inherent characteristics and does not yet consider the actual errors exposed during the first layer cutting. Next, a secondary correction coefficient is obtained by subtracting the secondary cutting compensation coefficient from 1. This coefficient reflects the degree of fine-tuning of the preliminary second-layer focal length. A large compensation coefficient indicates significant deviation in the first layer, requiring more adjustment to the second-layer focal length; a small coefficient requires only minor adjustment. Finally, the preliminary second-layer cutting focal length is multiplied by the secondary correction coefficient to obtain the final optimized second-layer cutting focal length. This optimized focal length better reflects the actual cutting situation, considering not only the inherent characteristics of the second layer material but also the error trends exposed during the first layer cutting, thus achieving more precise cutting control. Finally, the laser cutting equipment continued to perform the second layer laser cutting operation on the multi-layer composite material according to this optimized two-layer cutting focal length, laying a good foundation for the cutting accuracy of subsequent layers.

[0044] The multi-layer composite material is subjected to secondary laser cutting according to the optimized two-layer cutting focal length, and the cutting focal length is iteratively corrected and the cutting control is performed until the tail layer cutting operation is completed.

[0045] In one embodiment, after obtaining the optimized two-layer cutting focal length, the laser cutting equipment performs a second-layer laser cutting operation on the multilayer composite material according to the focal length parameter. During the cutting process, the equipment continues to monitor the cutting edge status of the second layer in real time, including the distribution of the heat-affected zone, the amount of slag, and the number of pores, to evaluate the current cutting quality. Based on the cutting monitoring data of the second layer, a focal length compensation analysis is performed again, outputting a new compensation coefficient, and the focal length required for the next layer cutting is corrected and optimized accordingly. Subsequently, the next layer cutting is performed according to the optimized focal length parameter. After each layer cutting is completed, the iterative process of focal length correction and cutting control optimization is repeated. This dynamic iterative adjustment of the cutting focal length continues until the last layer of the multilayer composite material is cut, ensuring that the cutting effect of each layer of material is in the optimal state, thereby achieving high precision and high consistency in the overall cutting operation and effectively meeting the processing requirements of ultra-precision industrial control.

[0046] Furthermore, this application provides iterative methods for cutting focal length correction and cutting control until the tail layer cutting operation is completed, including:

[0047] Iteratively perform cutting focal length correction and cutting control until the tail layer of the multilayer composite material is reached, and analyze to obtain the optimized tail layer cutting focal length; monitor and obtain the cutting deviation sequence during the multilayer cutting process, where the cutting deviation is the deviation between the actual cutting state and the expected cutting state after cutting according to the optimized cutting focal length; perform secondary optimization of the optimized tail layer cutting focal length based on the cutting deviation sequence to obtain the optimal tail layer cutting focal length, and perform the tail layer cutting operation.

[0048] Preferably, after each layer of material is cut, the focal length is corrected based on the actual cutting effect of that layer (edge ​​state data such as heat-affected zone, slag, and porosity), and the optimized cutting focal length for the next layer is output. The equipment continues laser cutting the next layer based on the corrected focal length, while maintaining real-time monitoring and continuously iterating to adjust the cutting focal length and control the cutting operation. This iterative optimization continues until the last layer of multi-layer composite material is cut. When the last layer is reached, based on the thickness and property information of the last layer material and the previous cutting experience, a preliminary optimized cutting focal length for the last layer is analyzed and output. This focal length is obtained based on conventional optimization, but in order to further improve the cutting quality of the last layer, it needs to be corrected a second time by incorporating deviation information from the actual cutting process. Specifically, during the entire multi-layer material cutting process, the cutting deviation after each layer cutting operation is continuously recorded, forming a set of cutting deviation sequences. The cutting deviation is the difference between the actual cutting state (such as cutting line width and cutting edge integrity) and the expected standard state after cutting according to the optimized focal length. Subsequently, based on the collected cutting deviation sequence, the deviation change trend is fitted in two-dimensional space to plot the cutting deviation curve. This curve is then analyzed to predict the potential cutting deviation in the tail layer if the initial optimized focal length is applied directly. Following this, based on the predicted deviation, the optimized tail layer focal length is adjusted a second time—that is, fine-tuned based on the initial optimized value—to obtain a more precise optimal tail layer cutting focal length. Finally, the laser cutting equipment uses the second-optimized optimal tail layer cutting focal length to complete the precise cutting of the tail layer material, ensuring that the cutting edge quality, dimensional accuracy, and overall process consistency meet the highest standards. In summary, this entire process, by combining material characteristics, real-time monitoring data, historical deviation trends, and intelligent analysis, achieves ultra-high precision, multi-level adaptive laser cutting industrial control, effectively improving the quality of the final product.

[0049] Furthermore, this application provides a secondary optimization of the optimized tail layer cutting focal length based on the cutting deviation sequence, including:

[0050] In a two-dimensional space, the cutting deviation sequence is fitted according to the cutting order to generate a cutting deviation curve, and the predicted tail layer cutting deviation is obtained by analyzing the cutting deviation curve; the optimized tail layer cutting focal length is then optimized a second time according to the predicted tail layer cutting deviation.

[0051] Optionally, the cutting deviation sequence recorded throughout the multi-layer cutting process is compiled, with each deviation point corresponding to one cutting operation. Then, in two-dimensional space, with the cutting sequence as the x-axis and the cutting deviation value as the y-axis, these deviation data points are fitted. The fitting can employ multinomial regression, spline interpolation, or other suitable curve fitting methods to generate a smooth cutting deviation curve that reflects the overall trend of deviation changes during the cutting process. By analyzing the fitting, a cutting deviation curve is obtained. By inputting the next cutting sequence into the curve fitting function corresponding to this cutting deviation curve, the predicted cutting deviation value for the next cutting sequence is calculated, i.e., the possible cutting deviation value of the tail layer. This predicted tail layer cutting deviation reflects the magnitude of the cutting error that may occur in the tail layer material under the current cutting state, serving as an important basis for whether to further adjust the focal length. Next, based on the predicted tail-layer cutting deviation, it is determined whether the focal length needs correction. If the predicted deviation exceeds a set threshold, a secondary fine-tuning of the optimized tail-layer focal length is required. At this point, the focal length is appropriately increased or decreased according to the sign and magnitude of the predicted deviation to offset its impact. For example, the focal length can be corrected according to a linear or proportional relationship, with the adjustment magnitude proportional to the predicted deviation. Through this secondary optimization process, an optimal tail-layer cutting focal length that better meets actual cutting requirements is obtained. Finally, this focal length parameter is used for the tail-layer laser cutting operation, thereby maximizing the dimensional accuracy and edge quality of the tail-layer cutting. In summary, this process, by introducing the fitting and prediction of historical deviation trends, identifies and compensates for potential errors in advance, greatly improving the stability and accuracy of multi-layer composite material cutting in the tail-layer operation stage, meeting the high standards of ultra-precision cutting processes in the industrial control field.

[0052] In summary, the embodiments of this application have at least the following technical effects:

[0053] This application embodiment first monitors and acquires the material thickness and material property information of the first layer in a multilayer composite material. Then, based on the material thickness and material property information, it analyzes the cutting focal length of the current laser cutting equipment and outputs the first-layer cutting focal length. Next, it performs a first laser cut on the multilayer composite material according to the first-layer cutting focal length, and monitors and acquires the first-layer cutting edge state data. Then, based on the first-layer cutting edge state data, it performs a second cutting focal length compensation analysis, outputs a second cutting compensation coefficient, corrects the second-layer cutting focal length, and outputs an optimized second-layer cutting focal length. Finally, it performs a second laser cut on the multilayer composite material according to the optimized second-layer cutting focal length, iteratively correcting the cutting focal length and controlling the cutting until the last layer cutting operation is completed. These technical effects collectively solve the technical problems of unstable cutting focal length and insufficient cutting accuracy caused by differences in material thickness and properties during the cutting of multilayer composite materials in industrial control laser cutting equipment. It achieves the technical effect of improving the accuracy and efficiency of the laser cutting process in industrial control through an adaptive focal length adjustment method, ensuring stable cutting quality of each layer of material and meeting precision requirements.

[0054] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0055] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0056] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. An adaptive focal length adjustment method for ultra-precision high-power laser cutting equipment, characterized in that, The methods include: Monitoring and acquiring information on the material thickness and properties of the first layer in multilayer composite materials; Based on the material thickness and material property information, the cutting focal length of the current laser cutting equipment is analyzed, and the first-layer cutting focal length is output. The multilayer composite material is laser-cut once according to the first layer cutting focal length, and the state data of the first layer cutting edge is monitored and acquired. Based on the first-layer cutting edge state data, a second-layer cutting focal length compensation analysis is performed, and a second-layer cutting compensation coefficient is output to correct the second-layer cutting focal length and output an optimized second-layer cutting focal length. The multi-layer composite material is subjected to secondary laser cutting according to the optimized two-layer cutting focal length, and the cutting focal length is iteratively corrected and the cutting control is performed until the tail layer cutting operation is completed. The process of correcting the focal length of the two-layer cutting and outputting an optimized focal length for the two-layer cutting includes: Monitoring and acquiring material thickness and material property information of the second layer in a multi-layer composite material, and analyzing and determining the cutting focal length of the second layer; Subtract the secondary cutting compensation coefficient from 1 to obtain the secondary correction coefficient; The second-layer cutting focal length is corrected according to the second-level correction coefficient, and the optimized second-layer cutting focal length is output. The iteration performs cutting focal length correction and cutting control until the tail layer cutting operation is completed, including: Iteratively perform cutting focal length correction and cutting control until the tail layer material of the multilayer composite material is reached, and analyze to obtain the optimized tail layer cutting focal length; The cutting deviation sequence during the multi-layer cutting process is monitored and obtained. The cutting deviation is the deviation between the actual cutting state and the expected cutting state after cutting according to the optimized cutting focal length. The optimal tail layer cutting focal length is further optimized based on the cutting deviation sequence to obtain the optimal tail layer cutting focal length, and then the tail layer cutting operation is performed. The step of performing secondary optimization of the tail layer cutting focal length based on the cutting deviation sequence includes: In a two-dimensional space, the cutting deviation sequence is fitted according to the cutting order to generate a cutting deviation curve, and the predicted tail layer cutting deviation is obtained by analyzing the cutting deviation curve. The optimized tail layer cutting focal length is further optimized based on the predicted tail layer cutting deviation.

2. The adaptive focal length adjustment method for an ultra-precision high-power laser cutting equipment according to claim 1, characterized in that, Monitoring and acquiring material thickness and material property information of the first layer in a multilayer composite material, including: Laser ranging technology is used to monitor and obtain the material thickness of the first layer in a multilayer composite material. Obtain the material property information of the first layer material, wherein the material property information includes at least absorptivity, reflectivity, thermal conductivity, melting point, and coefficient of thermal expansion.

3. The adaptive focal length adjustment method for an ultra-precision high-power laser cutting equipment according to claim 1, characterized in that, Based on the material thickness and material property information, the current laser cutting equipment is analyzed for cutting focal length, and the first-layer cutting focal length is output, including: Using the current laser cutting equipment as the equipment search constraint, retrieve historical laser cutting records of similar equipment; Based on the historical laser cutting records, a sample material thickness set and a sample material attribute set are collected, and the average historical cutting focal length of different sample material thicknesses and different sample material attribute data under the cutting standard is statistically analyzed and set as the sample cutting focal length to obtain the sample cutting focal length set. A cutting focal length analysis model is constructed using a deep neural network. The sample material thickness set and sample material attribute set are used as inputs, and the sample cutting focal length set is used as supervision to train the cutting focal length analysis model, thereby obtaining a cutting focal length analysis model that satisfies the preset convergence condition. Using the cutting focal length analysis model, the cutting focal length of the current laser cutting equipment is analyzed based on the material thickness and material property information, and the first-layer cutting focal length is output.

4. The adaptive focal length adjustment method for an ultra-precision high-power laser cutting equipment according to claim 1, characterized in that, Monitoring and acquiring the status data of the first-layer cutting edge, including: Infrared thermal imagers were used to monitor the temperature distribution in the first-floor cutting area and obtain the distribution of the heat-affected zone, which included both shape and size. The first-layer cutting area is imaged using a visual sensor. The number of slag and pores is obtained by image recognition of the cutting area. Convolutional neural networks are used to identify and extract the features of slag and pores. The distribution of the heat-affected zone, the amount of slag, and the number of pores are used as the first-layer cutting edge status data.

5. The adaptive focal length adjustment method for an ultra-precision high-power laser cutting equipment according to claim 4, characterized in that, Based on the first-layer cutting edge state data, a secondary cutting focal length compensation analysis is performed, and secondary cutting compensation coefficients are output, including: Based on historical laser cutting records, collect the distribution set of heat-affected zone information, the number set of molten slag, and the number set of pores in the sample; The material cutting deviation range under the statistical distribution of heat-affected zone information, sample slag quantity, and sample porosity quantity of different samples is set as the sample cutting compensation coefficient, and the sample cutting compensation coefficient set is obtained. Using the sample heat-affected zone information distribution set, sample slag quantity set, sample pore quantity set, and sample cutting compensation coefficient set, a deep neural network is trained to construct a focal length compensation analysis model; The first-layer cutting edge state data is input into the focal length compensation analysis model, and the secondary cutting compensation coefficient is output.

6. The adaptive focal length adjustment method for an ultra-precision high-power laser cutting equipment according to claim 5, characterized in that, Using the sample heat-affected zone information distribution set, sample slag quantity set, sample porosity quantity set, and sample cutting compensation coefficient set, a deep neural network is trained to construct a focal length compensation analysis model, including: The sample heat-affected zone information distribution set, sample slag quantity set, sample porosity quantity set, and sample cutting compensation coefficient set are used as training data and divided into P equal parts to obtain P sample datasets, where P is an integer greater than 5. Using the P sample datasets, the deep neural network is trained and tested until the network converges, resulting in P focal length compensation analysis units, which are then combined to construct a focal length compensation analysis model.

7. The adaptive focal length adjustment method for an ultra-precision high-power laser cutting equipment according to claim 6, characterized in that, The first-layer cutting edge state data is input into the focal length compensation analysis model, and the secondary cutting compensation coefficients are output, including: Calculate the ratios of the heat-affected zone information distribution, slag quantity, and porosity quantity to the historical maximum heat-affected zone information distribution, historical maximum slag quantity, and historical maximum porosity quantity, and then use the weighted average to determine the cutting deviation scale coefficient. The number of units selected, K, is obtained by multiplying the cutting deviation scale coefficient by P and rounding it down. K focal length compensation analysis units are randomly selected from the P focal length compensation analysis units in the focal length compensation analysis model to perform compensation analysis on the first layer cutting edge state data, outputting K compensation coefficients. The average value is used to calculate the secondary cutting compensation coefficient.

Images