Hybrid common edge analysis method and system for nesting layout based on lens laser cutting

Abstract

The present invention relates to the field of laser cutting technology, and in particular to a nesting typesetting mixed common edge analysis method and system based on lens laser cutting. The method comprises the following steps: obtaining a laser cutting preparatory data set; performing data preprocessing on the laser cutting preparatory data set to generate a laser cutting preprocessing data set; performing geometric feature-material property correlation analysis on the laser cutting preprocessing data set to generate laser cutting geometry-material correlation data; constructing an intelligent common edge analysis model based on the laser cutting geometry-material correlation data to generate a laser cutting common edge preliminary analysis model; therefore, the present invention solves the problems of repeated cutting paths, material waste and low cutting efficiency in the traditional laser cutting process by introducing intelligent common edge analysis and optimization strategies, thereby improving the efficiency and accuracy of laser cutting operations.

Description

Technical Field

[0001] The present invention relates to the field of laser cutting technology, and in particular to a nesting layout mixed common edge analysis method and system based on lens laser cutting. Background Art

[0002] In the current lens laser cutting technology, the planning of the cutting path is usually based on simple geometric analysis and preset parameters. However, due to the complexity of lens materials, these traditional methods are difficult to effectively avoid the thermal expansion effect and stress concentration of the materials, resulting in difficulty in controlling the precision during the cutting process. In addition, traditional methods often lack sufficient adaptability to lenses of different materials (such as optical glass, polymer lenses, etc.) and different thicknesses. In addition, the traditional cutting algorithm lacks a detailed analysis of the characteristics of the lens material, and fails to comprehensively consider factors such as beam penetration, heat distribution, and thickness uniformity during cutting, thereby affecting the cutting efficiency and the quality of the final product. The special geometric shape of the lens also brings difficulties to the traditional nesting layout and common edge analysis. The lens often requires complex edge cutting and precise angle adjustment, and the traditional laser cutting path planning technology often cannot effectively adapt to the changes in the lens shape, and is prone to problems such as excessive edge melting or uneven cutting. Especially in the production process of multiple lenses, the traditional nesting layout method does not take into account the common edge effect between lenses and the optimization of the cutting path, which often leads to unnecessary material waste and extended cutting time. In addition, since lens cutting operations usually require high-precision optical testing and real-time feedback to ensure that the cutting quality meets the requirements, existing technologies also have defects in real-time evaluation and automatic adjustment. Traditional laser cutting evaluation methods mostly rely on manual monitoring and post-data processing, lacking real-time monitoring and feedback adjustment during the cutting process, resulting in the inability to perform immediate optimization during the cutting process, and it is difficult to cope with quality fluctuations and external environmental changes that may occur during lens cutting. Summary of the invention

[0003] Based on this, it is necessary to provide a hybrid common edge analysis method and system for nesting layout based on lens laser cutting to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a nesting layout mixed common edge analysis method based on lens laser cutting is provided, the method comprising the following steps: Step S1: Acquire a laser cutting preparation data set; perform data preprocessing on the laser cutting preparation data set to generate a laser cutting preprocessing data set; perform geometric feature-material property correlation analysis on the laser cutting preprocessing data set to generate laser cutting geometry-material correlation data; Step S2: constructing an intelligent common edge analysis model based on laser cutting geometry-material association data to generate a preliminary common edge analysis model for laser cutting; Step S3: Perform global optimization of nesting layout based on the preliminary analysis model of laser cutting co-edge, and generate a global optimization model for laser cutting; perform local co-edge analysis on the global optimization model for laser cutting, and generate an intelligent co-edge analysis model for laser cutting; Step S4: Evaluate based on the intelligent common edge analysis model of laser cutting to generate laser cutting evaluation data; generate an evaluation report for the laser cutting evaluation data, thereby completing the nesting and typesetting mixed common edge analysis operation based on lens laser cutting.

[0005] The beneficial effect of the present invention is that the efficiency and accuracy of the laser cutting process are significantly improved by performing intelligent common edge analysis, global optimization of nesting layout and local analysis on the laser cutting process. First, by obtaining the laser cutting preparation data set and preprocessing it, the quality and consistency of the data can be ensured, which lays the foundation for the subsequent correlation analysis of geometric features and material properties. When performing deep correlation analysis between geometric features and material properties, a more accurate cutting parameter prediction model can be generated by analyzing the reaction characteristics of different materials in the laser cutting process (such as thermal expansion coefficient, hardness, thickness uniformity, etc.), thereby achieving better control and optimization in the cutting process. Then, based on this correlation data, an intelligent common edge analysis model is constructed, so that multiple parts can share the cutting path, reducing the movement time and unnecessary pauses of the cutting head, thereby improving the overall efficiency and accuracy of the cutting process. Subsequently, the nesting layout is globally optimized based on the preliminary common edge analysis model, and the optimization algorithm (such as genetic algorithm, particle swarm optimization, etc.) is used to ensure the maximum utilization of the material, and the cutting path is optimized through local analysis, so that the resource consumption in the cutting process is minimized, and the cutting quality is further improved. Finally, the cutting effect is evaluated based on the intelligent common edge analysis model, and a detailed evaluation data report is generated, which can provide reliable feedback information for the subsequent production process. Overall, the present invention greatly improves the efficiency, material utilization rate and quality of the final product in the cutting process by accurately controlling and optimizing the laser cutting process from the data level. Therefore, the present invention solves the problems of repeated cutting paths, material waste and low cutting efficiency in the traditional laser cutting process by introducing intelligent common edge analysis and optimization strategies, thereby improving the efficiency and accuracy of laser cutting operations.

[0006] Preferably, step S1 comprises the following steps: Step S11: Acquire laser cutting preparation data set; Step S12: performing data preprocessing on the laser cutting preparation data set to generate a laser cutting preprocessing data set; Step S13: extracting data from the laser cutting preprocessing data set to generate laser cutting extraction data; performing geometric feature-material property correlation analysis on the laser cutting extraction data to generate laser cutting geometry-material correlation data.

[0007] The present invention obtains the laser cutting preparatory data set, ensuring that various basic data required for the cutting process (such as the geometric dimensions of the lens, material properties and cutting parameters, etc.) can fully and accurately reflect the actual cutting environment. Data preprocessing is performed through the data set, eliminating noise and inconsistency in the data, and solving the inaccurate cutting results caused by data quality problems. In the data preprocessing process, through standardization, normalization and other technical means, data from different sources and formats can be unified, which is convenient for subsequent analysis and processing. Then, by extracting the preprocessed data, laser cutting extraction data is generated, providing a targeted key data set for further analysis. In this process, data extraction not only converts complex input data into effective and operational information, but also filters out irrelevant variables, thereby improving the efficiency and accuracy of data analysis. Most importantly, by performing correlation analysis between geometric features and material properties on the extracted data, the intrinsic relationship between the geometric properties of the material and its laser cutting behavior can be effectively revealed, and laser cutting geometry-material correlation data can be generated. These correlation data are crucial for optimizing cutting parameters, improving cutting quality and efficiency, and can provide strong support for subsequent cutting path planning and intelligent control. Through this series of data processing steps, the present invention improves the intelligence of decision-making in the laser cutting process on the basis of ensuring the high quality and availability of data, and realizes the precise matching and optimization between material properties and geometric features, thereby effectively reducing errors in the cutting process and improving cutting efficiency and finished product quality.

[0008] Preferably, step S12 comprises the following steps: Step S121: normalizing the laser cutting preparation data set to generate laser cutting normalized data; Step S122: performing data cleaning according to the laser cutting normalized data, and removing abnormal data to generate laser cutting cleaning data; Step S123: performing data standardization processing on the laser cutting cleaning data to generate a laser cutting preprocessing data set, wherein the laser cutting preprocessing data set includes a laser cutting geometry preprocessing data set and a laser cutting material property preprocessing data set.

[0009] The present invention ensures that data of different scales and units can be compared and analyzed under the same standard through data set normalization operation. Various input variables in the laser cutting preparation data set, such as geometric dimensions, material properties and laser cutting parameters, often have different dimensions or ranges. Through normalization processing, these differences can be eliminated to avoid excessive impact of certain variables on subsequent analysis due to excessively large or small dimensions, so that all data are processed at the same scale, ensuring the fairness and consistency of data analysis. Next, in the data cleaning process, abnormal data (such as measurement errors, invalid values ​​or input errors) in the laser cutting preparation data set are eliminated to ensure that the analysis process will not be disturbed by irrelevant data. By removing these abnormal data, the influence of data deviation on subsequent analysis results is avoided, and the quality and accuracy of the data set are improved. After data cleaning, the data set is further normalized by standardization processing, and the generated laser cutting preprocessing data set can be processed and analyzed under a unified scale and standard. The standardized data set includes a geometric preprocessing data set and a material property preprocessing data set, which respectively normalizes the geometric features and material properties of the lens, providing reliable basic data for the subsequent geometric feature-material property correlation analysis. This series of data processing steps greatly improves the quality and consistency of the data, making subsequent analysis and modeling more accurate and efficient. Through precise data cleaning, standardization and normalization, the data set can provide more reliable support for the optimization of the laser cutting process and provide high-quality input data for model construction.

[0010] Preferably, step S13 includes the following steps: Step S131: extracting the size features of the laser cutting geometric preprocessing data set to generate laser cutting size feature data; performing geometric shape analysis on the laser cutting size feature data to generate laser cutting geometric shape data; establishing a three-dimensional image based on the laser cutting geometric shape data to generate a laser cutting three-dimensional image; Step S132: performing lens shape feature analysis on the laser-cut three-dimensional image to generate laser-cut lens shape data; performing lens edge tilt angle detection on the laser-cut lens shape data to generate laser-cut lens edge tilt angle data; performing cutting angle detection on the laser-cut lens shape data to generate laser cutting angle data; performing plane angle calculation on the laser-cut lens edge tilt angle data and the laser cutting angle data to generate laser cutting geometric feature extraction data; Step S133: performing thermal expansion coefficient influence detection on the laser cutting material characteristic preprocessing data set to generate laser cutting thermal expansion coefficient data; performing beam penetration analysis on the laser cutting thermal expansion coefficient data to generate laser cutting beam penetration data; performing thickness uniformity measurement on the laser cutting beam penetration data to generate laser cutting material characteristic extraction data; Step S134: perform L1 regularization on the laser cutting geometric feature extraction data and the laser cutting material feature extraction data to generate laser cutting feature regularization data; create a geometric feature-material characteristic feature matrix for the laser cutting feature regularization data to generate a laser cutting geometric feature-material characteristic feature matrix; perform geometric feature-material characteristic correlation analysis on the laser cutting geometric feature-material characteristic feature matrix to generate laser cutting geometry-material correlation data.

[0011] The present invention generates laser cutting size feature data by extracting size features, which provides basic information for subsequent geometric shape analysis. Through further geometric shape analysis, laser cutting geometric shape data is generated, which provides accurate shape information for the establishment of subsequent three-dimensional images, thereby making the geometric model of the lens visualized, which is convenient for subsequent processing and optimization. Next, the lens shape feature analysis is performed based on the generated three-dimensional image, and the shape features are further refined, especially the detection of the inclination angle and cutting angle of the edge. These data are helpful to evaluate the geometric errors occurring in the cutting process and provide necessary information for the subsequent cutting path optimization. Through the calculation of the plane angle, the inclination angle and cutting angle data of the lens edge are integrated to generate laser cutting geometric feature extraction data, which provides essential support for the precise control of laser cutting and ensures the accuracy of the geometric shape during the cutting process. On the other hand, the laser cutting material properties are detected, including the thermal expansion coefficient and the beam penetration analysis. These material properties are crucial to the thermal impact and cutting quality during the cutting process. Through the thickness uniformity measurement, the laser cutting material feature data is further extracted, which provides a quantitative basis for evaluating the thermal deformation of the material during the cutting process. Finally, L1 regularization technology was used to normalize the geometric and material feature data of laser cutting, reducing the interference of redundant features and ensuring the simplicity and effectiveness of the data. Subsequently, a geometric feature-material feature matrix was created, and the intrinsic relationship between geometric features and material properties was revealed through correlation analysis, thus providing strong support for precise parameter setting and path optimization during laser cutting. Through this series of data extraction, standardization and correlation analysis, it is ensured that each link of the cutting process can be coordinated with each other, laying a solid foundation for improving the accuracy and efficiency of laser cutting.

[0012] Preferably, step S2 comprises the following steps: Step S21: obtaining laser cutting parameter data; Step S22: constructing a three-dimensional model using the laser cutting geometry-material association data to generate a laser cutting three-dimensional solid model; Step S23: constructing an algorithm model for the laser cutting three-dimensional model using the laser cutting parameter data to generate a preliminary analysis model for laser cutting common edges.

[0013] The present invention provides a key control basis for the entire cutting process through the acquired laser cutting parameter data, including parameters such as laser power, cutting speed, beam diameter, focal position, etc., which have a direct impact on cutting quality, efficiency and stability. By using the laser cutting geometry-material association data to construct a three-dimensional model, the geometric shape of the cutting object and its interaction with the material properties can be intuitively displayed. The generation of the three-dimensional model not only helps to simulate and predict the thermal deformation, stress distribution and cutting effect in the cutting process, but also provides a morphological basis for subsequent path planning and optimization, so that the cutting operation can be more accurate and efficient. Further, by combining the laser cutting parameter data with the three-dimensional model, an algorithm model is constructed, so that multiple key factors in the laser cutting process (such as cutting angle, material thermal response, edge quality, etc.) can be uniformly described and optimized through a mathematical model. In the generated common edge preliminary analysis model, through a comprehensive analysis of the cutting path, material reaction and cutting process, decision support can be provided for subsequent path optimization and cutting parameter adjustment, thereby effectively reducing errors and waste in cutting, improving cutting efficiency and ensuring the consistency and high precision of finished product quality. Overall, this series of data processing and modeling steps achieves precise control and intelligent optimization of the cutting process by taking into account all aspects from geometric features, material properties to cutting parameters, ensuring the efficiency, precision and stability of laser cutting operations.

[0014] Preferably, step S23 includes the following steps: Step S231: performing geometric overlap analysis on the laser cutting three-dimensional model to generate laser cutting shared boundary data; Step S232: performing cutting path planning on the laser cutting shared boundary data to generate laser cutting path data; Step S233: specifying focus-speed cutting parameters for the laser cutting path data to generate cutting parameter data; constructing an algorithm model based on the cutting parameter data and the laser cutting path data to generate a preliminary analysis model for laser cutting common edge.

[0015] The present invention can accurately identify the shared boundaries between different cutting areas by performing geometric overlap analysis on the laser cutting three-dimensional model. This process not only effectively integrates the data of each cutting area, but also provides a key data basis for subsequent cutting path planning. The shared boundary data reflects the relationship between different areas and the geometric shape of the boundary junction during the laser cutting process, which is of great significance for optimizing cutting efficiency and improving material utilization. By performing cutting path planning on the shared boundary data, laser cutting path data is generated to ensure the efficiency of the cutting process. Through path optimization, the laser cutting equipment can more reasonably select the cutting route, thereby reducing unnecessary movement and cutting times, improving overall operating efficiency, and effectively reducing material waste. In addition, the accuracy of path planning also plays a vital role in the final cutting quality, avoiding cutting errors caused by improper path selection. Cutting parameter data is generated by specifying the focus-speed cutting parameters of the cutting path data. These parameters not only affect the cutting quality, but also are related to the thermal response and mechanical stress of the material during the cutting process. By accurately specifying the focus position and cutting speed, fine control of the cutting process can be achieved, avoiding problems such as uneven cutting and thermal deformation caused by improper parameters. Finally, through the algorithm model built based on cutting parameter data and path data, a preliminary analysis model for laser cutting common edge was generated. This model integrates all key cutting factors, including path planning, parameter settings, and geometric features, thereby providing comprehensive optimization and decision support for the subsequent cutting process. Through this series of optimization steps, each link in the laser cutting process is precisely controlled, ensuring the efficiency, stability, and high quality of the cutting operation.

[0016] Preferably, step S3 comprises the following steps: Step S31: performing global optimization of nesting layout based on the preliminary analysis model of laser cutting common edge, and generating global optimization data for laser cutting; Step S32: Performing model nesting integer linear programming on the laser cutting global optimization data to generate a laser cutting global optimization model; Step S33: Perform local co-edge analysis on the laser cutting global optimization model to generate an intelligent co-edge analysis model for laser cutting.

[0017] The present invention generates laser cutting global optimization data by performing nesting layout global optimization on the laser cutting common edge preliminary analysis model. This step utilizes the data of geometric features, material properties and path planning in the laser cutting process to achieve global optimization, ensuring that each cutting area and material plate can maximize the use of existing materials, reducing blank areas and cutting waste. This optimization not only improves material utilization, but also reduces invalid movement in the cutting process, and improves the efficiency of the entire operation. Secondly, a laser cutting global optimization model is generated by performing model nesting integer linear programming on the laser cutting global optimization data. Through the integer linear programming algorithm, the cutting path and material distribution are optimized, so that the various parameters in the cutting process such as position, angle and path can be optimally matched, thereby further improving the cutting efficiency and reducing energy consumption. The core of this step is to accurately describe the relationship between material layout and cutting path through a mathematical model, so that the optimal solution can be found under multiple constraints, significantly improving the intelligent level of the cutting system. Finally, by performing local co-edge analysis on the laser cutting global optimization model, an intelligent co-edge analysis model for laser cutting is generated. The model further optimizes the local details of the cutting process, especially for fine-tuning the cutting path close to the edge and complex shape areas, ensuring the consistency and high precision of the cutting quality. Local analysis helps to reduce cutting defects caused by path errors, while improving the accuracy and consistency of cutting. Through this series of optimization steps, comprehensive improvements have been achieved from the global to the local level, ensuring the efficiency, precision and stability of the laser cutting process.

[0018] Preferably, step S33 includes the following steps: Step S331: performing path planning simulation on the laser cutting global optimization model to generate laser cutting path planning simulation data; performing shortest path generation tree optimization on the laser cutting path planning simulation data to generate a laser cutting optimization tree path; Step S332: performing local material scanning on the global optimization model for laser cutting to generate local material data for laser cutting; re-optimizing the material utilization rate of the local material data for laser cutting to generate re-optimized material data for laser cutting; Step S333: Draw a two-dimensional optimization graph of cutting speed and power for the global optimization model of laser cutting to generate a two-dimensional optimization graph of local speed and power for laser cutting; create a speed-power matrix based on the two-dimensional optimization graph of local speed and power for laser cutting, determine the best speed-power combination, and generate data of the best combination of laser cutting speed and power; Step S334: Based on the laser cutting optimization tree path, the laser cutting material re-optimization data and the laser cutting speed-power optimal combination data, the laser cutting global optimization model is subjected to local co-edge analysis to generate an intelligent laser cutting co-edge analysis model.

[0019] The present invention generates laser cutting path planning simulation data by performing path planning simulation on the global optimization model of laser cutting. The path planning simulation data provides an important basis for further optimizing the cutting path, and can accurately predict and evaluate the advantages and disadvantages of different path schemes. Next, the shortest path generation tree optimization process further optimizes the path selection through the shortest path algorithm, and generates a laser cutting optimization tree path. The optimized tree path ensures the optimality of the path during the laser cutting process, reduces unnecessary path redundancy, thereby improving cutting efficiency and reducing energy consumption. Subsequently, by performing local material scanning on the global optimization model of laser cutting, local material data for laser cutting is generated, and then the material utilization rate of these data is re-optimized to generate laser cutting material re-optimization data. This step ensures the optimal utilization of materials through careful local scanning and optimization adjustment, effectively reduces waste, and improves the economy and resource utilization efficiency in the production process. The material re-optimization data further optimizes the material configuration in the entire cutting process, so that the cutting operation can maximize the benefits. Next, by drawing a two-dimensional optimization diagram of cutting speed-power for the global optimization model of laser cutting, a two-dimensional optimization diagram of local speed-power for laser cutting was generated, and based on this, a speed-power matrix was created, and finally the optimal speed-power combination was determined. This optimization diagram and matrix provide a precise basis for adjusting the speed and power during the cutting process, so that each parameter in the cutting process can operate in the best state, avoiding problems such as uneven cutting or excessive loss due to unreasonable parameter settings. Finally, by integrating the laser cutting optimization tree path, material re-optimization data and speed-power optimal combination data, the global optimization model was analyzed locally for co-edge, and an intelligent co-edge analysis model for laser cutting was generated. This model integrates data from multiple aspects such as path optimization, material utilization, speed and power adjustment, further improving the accuracy and intelligence of the laser cutting process, and ensuring the consistency and high precision of the cutting quality.

[0020] Preferably, step S4 comprises the following steps: Step S41: acquiring real-time laser cutting data; Step S42: performing laser cutting operation based on the laser cutting intelligent common edge analysis model to generate laser cutting model data; evaluating the real-time laser cutting data and the laser cutting model data to generate laser cutting evaluation data; Step S43: generating an evaluation report for the laser cutting evaluation data, thereby completing the nesting, layout and mixed common edge analysis operation based on lens laser cutting.

[0021] The present invention obtains real-time laser cutting data, which includes key parameters such as laser power, speed, focal position, cutting path, etc. during the cutting process. By collecting these data in real time, each link can be accurately monitored during the laser cutting process, providing a solid foundation for subsequent model optimization. Next, the operation is performed based on the intelligent common edge analysis model of laser cutting, and laser cutting model data is generated. Through the application of the model, the system can simulate and optimize the cutting process, and adjust the cutting path and parameters in real time in combination with real-time data to ensure that each cutting operation is performed in the optimal state. In this process, the generated laser cutting model data not only reflects the dynamic changes of the cutting process, but also provides detailed data support for subsequent evaluation. The real-time laser cutting data and the laser cutting model data are also evaluated to generate laser cutting evaluation data. By comparing and analyzing the real-time data with the simulation data, the system can identify potential cutting errors, path deviations, and fluctuations in cutting quality, providing accurate feedback for subsequent optimization. This process ensures that the cutting operation is always in a closed loop of feedback regulation, reduces the need for human intervention, and further improves the automation level of cutting. Finally, an evaluation report is generated based on the laser cutting evaluation data to ensure the transparency and traceability of the entire laser cutting operation process. The evaluation report not only summarizes the key parameters and performance data of the cutting process, but also analyzes the potential optimization space, providing data support for the optimization and improvement of subsequent operations.

[0022] In this specification, a nesting layout mixed common edge analysis system based on lens laser cutting is provided, which is used to execute the above-mentioned nesting layout mixed common edge analysis method based on lens laser cutting. The nesting layout mixed common edge analysis system based on lens laser cutting includes: The data processing module is used to obtain a laser cutting preparatory data set; perform data preprocessing on the laser cutting preparatory data set to generate a laser cutting preprocessing data set; perform geometric feature-material property correlation analysis on the laser cutting preprocessing data set to generate laser cutting geometry-material correlation data; The common edge analysis model building module is used to build an intelligent common edge analysis model based on the laser cutting geometry-material correlation data to generate a preliminary common edge analysis model for laser cutting; The optimization and local analysis module is used to perform global optimization of nesting layout based on the preliminary analysis model of laser cutting co-edge, and generate a global optimization model for laser cutting; perform local co-edge analysis on the global optimization model for laser cutting, and generate an intelligent co-edge analysis model for laser cutting; The evaluation and report generation module is used to evaluate based on the intelligent common edge analysis model of laser cutting and generate laser cutting evaluation data; generate an evaluation report for the laser cutting evaluation data, thereby completing the nesting and typesetting mixed common edge analysis operation based on lens laser cutting.

[0023] The beneficial effects of the present invention are that by acquiring a laser cutting preparation data set and performing data preprocessing, the standardization of input data is improved, data noise and redundant information are reduced, the stability and accuracy of data processing are improved, and a geometric feature-material property correlation analysis is performed on the laser cutting preprocessing data set, the precise adaptability of laser cutting parameters is improved, the cutting quality and material utilization rate are improved, an intelligent common edge analysis model is constructed based on the laser cutting geometry-material correlation data, the common edge adaptation ability between different lens geometric shapes is improved, the material layout compactness and resource utilization rate are improved, and material waste is reduced. Based on the laser cutting common edge preliminary analysis model, a global nesting layout is performed Optimize, improve the rationality of the overall cutting plan, reduce cutting path redundancy, improve laser cutting efficiency, conduct local common edge analysis on the global optimization model of laser cutting, optimize the local common edge path, reduce the cumulative effect of the heat affected zone, improve the quality of the cutting edge, and reduce the loss of material due to thermal deformation. Evaluate based on the intelligent common edge analysis model of laser cutting to improve the stability and applicability of the nesting layout plan, ensure the reliability of the cutting plan under different production conditions, generate an evaluation report for the laser cutting evaluation data, provide accurate common edge layout optimization suggestions for the production process, improve the visualization and controllability of production management, and improve production efficiency and quality control. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic diagram of the steps of a hybrid common edge analysis method for nesting layout based on lens laser cutting; Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart; Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG. Figure 4 for Figure 1 Detailed implementation steps of step S4 in FIG. The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0025] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0026] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0027] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0028] To achieve this, please refer to Figures 1 to 4 , a nesting layout mixed common edge analysis method based on lens laser cutting, the method comprises the following steps: Step S1: Acquire a laser cutting preparation data set; perform data preprocessing on the laser cutting preparation data set to generate a laser cutting preprocessing data set; perform geometric feature-material property correlation analysis on the laser cutting preprocessing data set to generate laser cutting geometry-material correlation data; Step S2: constructing an intelligent common edge analysis model based on laser cutting geometry-material association data to generate a preliminary common edge analysis model for laser cutting; Step S3: Perform global optimization of nesting layout based on the preliminary analysis model of laser cutting co-edge, and generate a global optimization model for laser cutting; perform local co-edge analysis on the global optimization model for laser cutting, and generate an intelligent co-edge analysis model for laser cutting; Step S4: Evaluate based on the intelligent common edge analysis model of laser cutting to generate laser cutting evaluation data; generate an evaluation report for the laser cutting evaluation data, thereby completing the nesting and typesetting mixed common edge analysis operation based on lens laser cutting.

[0029] The beneficial effect of the present invention is that the efficiency and accuracy of the laser cutting process are significantly improved by performing intelligent common edge analysis, global optimization of nesting layout and local analysis on the laser cutting process. First, by obtaining the laser cutting preparation data set and preprocessing it, the quality and consistency of the data can be ensured, which lays the foundation for the subsequent correlation analysis of geometric features and material properties. When performing deep correlation analysis between geometric features and material properties, a more accurate cutting parameter prediction model can be generated by analyzing the reaction characteristics of different materials in the laser cutting process (such as thermal expansion coefficient, hardness, thickness uniformity, etc.), thereby achieving better control and optimization in the cutting process. Then, based on this correlation data, an intelligent common edge analysis model is constructed, so that multiple parts can share the cutting path, reducing the movement time and unnecessary pauses of the cutting head, thereby improving the overall efficiency and accuracy of the cutting process. Subsequently, the nesting layout is globally optimized based on the preliminary common edge analysis model, and the optimization algorithm (such as genetic algorithm, particle swarm optimization, etc.) is used to ensure the maximum utilization of the material, and the cutting path is optimized through local analysis, so that the resource consumption in the cutting process is minimized, and the cutting quality is further improved. Finally, the cutting effect is evaluated based on the intelligent common edge analysis model, and a detailed evaluation data report is generated, which can provide reliable feedback information for the subsequent production process. Overall, the present invention greatly improves the efficiency, material utilization rate and quality of the final product in the cutting process by accurately controlling and optimizing the laser cutting process from the data level. Therefore, the present invention solves the problems of repeated cutting paths, material waste and low cutting efficiency in the traditional laser cutting process by introducing intelligent common edge analysis and optimization strategies, thereby improving the efficiency and accuracy of laser cutting operations.

[0030] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a schematic diagram of the steps of a hybrid common edge analysis method for nesting layout based on lens laser cutting of the present invention. In this example, the hybrid common edge analysis method for nesting layout based on lens laser cutting includes the following steps: Step S1: Acquire a laser cutting preparation data set; perform data preprocessing on the laser cutting preparation data set to generate a laser cutting preprocessing data set; perform geometric feature-material property correlation analysis on the laser cutting preprocessing data set to generate laser cutting geometry-material correlation data; In the embodiment of the present invention, obtaining the laser cutting preparatory data set is the starting point of the entire processing flow. First, it is necessary to collect various data types related to the laser cutting process, including geometric data (such as size, shape, cutting path, etc.), material property data (such as thermal expansion coefficient, hardness, thickness uniformity, etc.), and operating parameter data during the laser cutting process (such as laser power, cutting speed, focus position, etc.). These data are usually obtained through high-precision sensors, the control system of the laser cutting machine, and external measuring equipment. The acquired data set needs to go through a series of preprocessing steps to ensure data quality. Specifically, the data preprocessing process includes conventional data cleaning operations such as data normalization, removal of outliers, and filling of missing values ​​to ensure that all data are subsequently processed at the same scale and reduce the impact of noise and inconsistency on model accuracy. In addition, it is also necessary to standardize the data from different data sources to ensure that all input data are consistent, thereby improving the reliability and comparability of subsequent data analysis. Through this process, the generated laser cutting preprocessing data set contains various information obtained after cleaning, normalization and standardization from the original data. These data sets then provide a basis for the association analysis between geometric features and material properties. In the geometric feature-material property correlation analysis, data mining techniques such as statistical analysis and regression analysis are used to explore the mutual influence relationship between different geometric features and material properties, and these correlation relationships are quantified through mathematical models. In particular, through technical means such as feature selection and dimensionality reduction, features that have a significant impact on cutting performance can be extracted from complex multidimensional data to generate geometric feature-material property correlation data.

[0031] Step S2: constructing an intelligent common edge analysis model based on laser cutting geometry-material association data to generate a preliminary common edge analysis model for laser cutting; In the embodiment of the present invention, the core technical means of the process of constructing an intelligent common edge analysis model based on laser cutting geometry-material association data is to use advanced data analysis and machine learning methods to predict and optimize the cutting path and cutting effect by modeling the complex association relationship between geometric features and material properties. First, the association data between geometric features and material properties obtained in step S1 provides key data input for subsequent model construction. These association data reveal the relationship between different geometric features and material properties through statistical methods including regression analysis, cluster analysis, principal component analysis (PCA), etc., such as the influence between cutting angle and material thickness, the interaction between cutting paths of different shapes and thermal expansion coefficients, etc. On the basis of these data, an intelligent analysis method is used to construct a common edge analysis model. The core goal of common edge analysis is to optimize the cutting path so that the cutting paths between adjacent areas can share the cutting edge, thereby reducing energy consumption during cutting, improving material utilization, and reducing cutting time. In this process, the support vector machine (SVM), neural network (NN) or deep learning model in machine learning is first used to train historical data to establish a prediction model between the cutting path and material properties. Specifically, geometric features and material properties are considered as input features. The model learns the influence of various geometric shapes and different material properties on cutting effects (such as cutting accuracy, cutting time, etc.), and then derives the optimal strategy for common edge cutting. In addition, the generation of common edge analysis models can be further refined through optimization algorithms (such as genetic algorithms, particle swarm optimization, etc.). These optimization algorithms continuously adjust cutting parameters such as cutting path, laser power, speed, etc. through iterative calculations, and finally generate cutting path configuration and common edge strategy with optimal performance.

[0032] Step S3: Perform global optimization of nesting layout based on the preliminary analysis model of laser cutting co-edge, and generate a global optimization model for laser cutting; perform local co-edge analysis on the global optimization model for laser cutting, and generate an intelligent co-edge analysis model for laser cutting; In the embodiment of the present invention, the core technical means for global optimization of nesting layout based on the preliminary analysis model of laser cutting common edge is a multi-stage optimization process combining data-driven global optimization and local analysis. First, the construction of the global optimization model depends on the common edge data and related features extracted from the preliminary analysis model of laser cutting common edge. By deeply mining these data, advanced optimization algorithms such as integer linear programming (ILP), mixed integer linear programming (MILP) or genetic algorithm (GA) are used to achieve the global optimization goal of nesting layout. Specifically, the data contains the geometric features, material properties and the correlation relationship of the cutting path of each cutting component, which are used to construct the optimal match between the cutting path and the material configuration. The optimization algorithm formulates the global optimal nesting layout plan by minimizing the total length of the cutting path, maximizing the material utilization rate, and considering multiple goals such as cutting time and energy consumption. In the global optimization process, all cutting tasks are firstly planned overall, resources are reasonably allocated, and components of different materials and geometric shapes are optimally arranged. At this stage, the common edge sharing between different components is optimized on a large scale to reduce unnecessary duplication of cutting paths, thereby improving cutting efficiency and reducing cutting energy consumption. By establishing a comprehensive evaluation model, different nesting schemes can be simulated, their actual effects can be evaluated, and the optimization direction can be continuously adjusted according to the evaluation results, and finally a global optimization model for laser cutting can be generated. After completing the global optimization, the local analysis of common edge is further carried out, the purpose is to fine-tune the cutting path by further optimizing the local area to ensure that the optimal effect can be achieved in the local cutting process. Local analysis usually adopts methods such as dynamic programming algorithm (DP) and particle swarm optimization (PSO) to further improve cutting accuracy, material utilization and production efficiency by refining the cutting path of a specific area. Local analysis not only focuses on the shortest cutting path, but also considers the influence of material properties and geometric shapes of specific areas on the cutting effect. Finally, through the combination of global optimization and local optimization, the generated intelligent common edge analysis model for laser cutting can adaptively make the best decision in complex cutting tasks, optimize the cutting path, reduce material waste and improve cutting efficiency.

[0033] Step S4: Evaluate based on the intelligent common edge analysis model of laser cutting to generate laser cutting evaluation data; generate an evaluation report for the laser cutting evaluation data, thereby completing the nesting and typesetting mixed common edge analysis operation based on lens laser cutting.

[0034] In an embodiment of the present invention, the evaluation process relies on various data generated in the laser cutting intelligent common edge analysis model, including information such as cutting path, material utilization, cutting speed and power combination, common edge sharing degree, etc. These data can fully reflect the efficiency and effect of the laser cutting operation. Therefore, the first step of the evaluation is to input these data into a multi-dimensional evaluation framework, which usually adopts an evaluation model based on multi-objective optimization, such as weighted scoring method, analytic hierarchy process (AHP) or data envelopment analysis (DEA). The evaluation framework comprehensively considers multiple key indicators such as cutting accuracy, material utilization, production efficiency, energy consumption, etc., and quantitatively evaluates the overall performance of the cutting process through preset evaluation criteria. In the evaluation process, the data of each dimension of the laser cutting intelligent common edge analysis model are firstly counted and analyzed, including the optimization degree of the cutting path, the reduction of material waste, the improvement of cutting quality, etc., which are all key indicators of the evaluation. For each cutting task, the evaluation system generates real-time evaluation data by comparing with the standard value or the historical best value. These evaluation data include but are not limited to cutting efficiency, energy efficiency, error range, material loss, etc. The real-time tracking and comparison of these indicators provide data support for subsequent optimization. Next, an evaluation report is generated through further analysis of the evaluation data. The generation of the report relies on an in-depth interpretation of the evaluation results and data visualization techniques, such as pivot tables, heat maps, line charts, etc., to help users clearly understand the actual performance of the cutting operation. The evaluation report not only contains numerical analysis of various optimization indicators, but also includes improvement suggestions for specific problems. For example, if there are long invalid gaps in certain cutting paths, the report will prompt this problem and recommend optimization solutions. At the same time, the report can also compare multiple optimization solutions based on different operating conditions to help operators make more reasonable decisions. In the end, this evaluation and report generation process completed the mixed common edge analysis operation based on lens laser cutting.

[0035] Preferably, step S1 comprises the following steps: Step S11: Acquire laser cutting preparation data set; Step S12: performing data preprocessing on the laser cutting preparation data set to generate a laser cutting preprocessing data set; Step S13: extracting data from the laser cutting preprocessing data set to generate laser cutting extraction data; performing geometric feature-material property correlation analysis on the laser cutting extraction data to generate laser cutting geometry-material correlation data.

[0036] In an embodiment of the present invention, the process of obtaining a laser cutting preparation data set requires collecting basic data related to the cutting task from multiple sources, including but not limited to the geometric size, shape, material properties (such as thermal expansion coefficient, hardness, etc.) of the lens and parameters of the laser cutting equipment (such as laser power, cutting speed, etc.). The acquired data often has multidimensional characteristics and includes raw data and potential noise or missing values, so it needs to go through a rigorous data preprocessing process. The laser cutting preparation data set is preprocessed mainly by technical means such as standardization, denoising and filling missing values ​​to ensure that the data quality meets the requirements of subsequent processing. Data preprocessing generally includes operations such as cleaning and normalization of the raw data (for example, linear transformation to a uniform scale), outlier detection and correction. These steps help to eliminate noise caused by measurement errors or external interference, and make various data features consistent in numerical range, reducing deviations in subsequent modeling processes. In the data processing process, cluster analysis and data interpolation methods (such as KNN interpolation, Lagrange interpolation, etc.) are used to fill missing data or reduce dimensions through principal component analysis (PCA) to retain important information in the data and reduce unnecessary complexity. The data extraction stage extracts key features related to cutting quality, efficiency, etc. from the processed preliminary data set. Common geometric features include cutting path, lens shape, edge quality, etc., while material properties include physical properties of materials (such as hardness, thermal expansion coefficient) and thickness uniformity of materials. By extracting these features, valuable information can be provided for subsequent analysis models. Geometric feature-material property association analysis mainly analyzes the influence of different geometric forms and material properties on laser cutting performance by establishing a mathematical model. This step usually uses regression analysis, statistical analysis, machine learning algorithms and other methods to explore the potential relationship between geometric features and material properties. For example, algorithms such as support vector machines (SVM), decision trees or random forests are used to model the data and extract the key factors affecting the quality and efficiency of laser cutting. Through this process, the generated "geometric feature-material property association data" can provide important decision-making basis for the subsequent optimization of the laser cutting process. The results of data association analysis are usually presented in the form of a feature matrix, in which each column represents a variable related to the cutting process and each row represents the characteristic value of a sample. These data provide a basis for further optimization of laser cutting parameters and path planning.

[0037] Preferably, step S12 comprises the following steps: Step S121: normalizing the laser cutting preparation data set to generate laser cutting normalized data; Step S122: performing data cleaning according to the laser cutting normalized data, and removing abnormal data to generate laser cutting cleaning data; Step S123: performing data standardization processing on the laser cutting cleaning data to generate a laser cutting preprocessing data set, wherein the laser cutting preprocessing data set includes a laser cutting geometry preprocessing data set and a laser cutting material property preprocessing data set.

[0038] In the embodiment of the present invention, the technical means of the laser cutting data preprocessing method are mainly concentrated on the processing of the laser cutting preparatory data set, including data normalization, data cleaning, standardization processing and other links, aiming to improve data quality, remove noise and make the data suitable for subsequent analysis and modeling. From the data level, the implementation steps of these technical means are firstly to perform a unified scale conversion by normalizing the laser cutting preparatory data set to ensure that different feature data have the same numerical range and standard. This process usually adopts a linear normalization method, such as minimum-maximum normalization, to compress the value of each feature to the interval [0,1] or [-1,1] to avoid some features from causing undue influence on the subsequent analysis process due to large values. In addition, if the preparatory data set contains non-numerical data or high-dimensional composite data, encoding conversion or dimensionality reduction processing is also required to ensure the consistency of the data during the processing process and simplify the difficulty of subsequent analysis. The main task of data cleaning is to eliminate abnormal data and process missing values. There are outliers in the laser cutting preparatory data set caused by sensor errors, external interference or data transmission problems. If these abnormal data are not processed, they will have a negative impact on the training results of the model. Therefore, the data cleaning process is usually combined with statistical methods or machine learning algorithms, such as outlier detection based on the Z-score method, identification and elimination of outliers using the box plot method, or identification of noise points through clustering algorithms. In addition, if there are missing values ​​in the data set, interpolation methods (such as mean interpolation, KNN interpolation, or regression interpolation, etc.) are often used to fill in the missing data to ensure the integrity of the data so as not to affect the subsequent standardization and analysis process. The main purpose of data standardization is to further unify the scale of the cleaned data to eliminate the dimensional differences between data features, so that different features can participate in modeling and analysis under the same standards. Standardization methods include Z-score standardization, which usually subtracts the mean of the data and divides it by the standard deviation so that the data distribution of each feature has zero mean and unit variance, which can eliminate the impact of scale differences of different features. Standardized data is particularly important for subsequent modeling work, especially when using machine learning or optimization algorithms, to ensure that each feature has a relatively fair weight during the training process. After the standardization process is completed, the data will be divided into two categories: geometric property data and material property data, which will be used for subsequent geometric feature analysis and material property analysis respectively.

[0039] Preferably, step S13 includes the following steps: Step S131: extracting the size features of the laser cutting geometric preprocessing data set to generate laser cutting size feature data; performing geometric shape analysis on the laser cutting size feature data to generate laser cutting geometric shape data; establishing a three-dimensional image based on the laser cutting geometric shape data to generate a laser cutting three-dimensional image; Step S132: performing lens shape feature analysis on the laser-cut three-dimensional image to generate laser-cut lens shape data; performing lens edge tilt angle detection on the laser-cut lens shape data to generate laser-cut lens edge tilt angle data; performing cutting angle detection on the laser-cut lens shape data to generate laser cutting angle data; performing plane angle calculation on the laser-cut lens edge tilt angle data and the laser cutting angle data to generate laser cutting geometric feature extraction data; Step S133: performing thermal expansion coefficient influence detection on the laser cutting material characteristic preprocessing data set to generate laser cutting thermal expansion coefficient data; performing beam penetration analysis on the laser cutting thermal expansion coefficient data to generate laser cutting beam penetration data; performing thickness uniformity measurement on the laser cutting beam penetration data to generate laser cutting material characteristic extraction data; Step S134: perform L1 regularization on the laser cutting geometric feature extraction data and the laser cutting material feature extraction data to generate laser cutting feature regularization data; create a geometric feature-material characteristic feature matrix for the laser cutting feature regularization data to generate a laser cutting geometric feature-material characteristic feature matrix; perform geometric feature-material characteristic correlation analysis on the laser cutting geometric feature-material characteristic feature matrix to generate laser cutting geometry-material correlation data.

[0040] In the embodiment of the present invention, the laser cutting dimension feature data is generated by extracting the dimension feature of the laser cutting geometric preprocessing data set. This process relies on morphological analysis and geometric operations. By calculating the dimensions of various objects in the data set (such as length, width, thickness, etc.) and converting them into numerical features, it is intended to provide a basis for subsequent geometric shape analysis. When performing geometric shape analysis on the dimension feature data, the shape features of the laser cutting object are extracted based on edge detection, contour extraction and other technologies, thereby generating geometric shape data, which is then used for subsequent three-dimensional image establishment. The generation of three-dimensional images usually uses spatial interpolation and grid reconstruction technology in computer graphics to construct an accurate three-dimensional model using the spatial relationship in the geometric shape data. The three-dimensional image is further analyzed for the shape feature of the lens, and the geometric characteristics of the lens are identified by algorithms such as feature point extraction and shape matching. Then, the tilt angle detection algorithm is used to accurately measure the edge of the lens, and the plane angle is calculated by the plane geometry method, thereby generating laser cutting geometric feature extraction data. The laser cutting material property preprocessing data set processes multiple important steps. First, the thermal expansion coefficient influence detection technology is used to evaluate the thermal deformation of the material under different temperature conditions to generate thermal expansion coefficient data. Next, beam penetration analysis is performed. This process generates beam penetration data by calculating the penetration depth and absorption rate of the laser beam in the material, which is crucial for subsequent cutting paths and power adjustments. In addition, the thickness of the material is detected through thickness uniformity measurement to ensure consistency and accuracy during the cutting process, and finally generate material feature data. The geometric feature data and material property data are processed by L1 regularization. The L1 regularization method is usually used for feature selection and sparse processing. By constraining the data, some redundant or unimportant features are compressed to zero during the optimization process, retaining the most representative features. This process effectively removes noise from the data and improves the effectiveness and interpretability of the features. Next, the regularized data is used to create a geometric feature-material property feature matrix. This matrix not only summarizes the geometric and material property data, but also provides a mathematical basis for subsequent correlation analysis. In the last step, the geometric feature-material property correlation analysis reveals the relationship between geometric shape and material properties, further optimizes the parameter allocation of the cutting process, and generates laser cutting geometry-material correlation data, providing strong data support for accurate laser cutting path planning and optimization.

[0041] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: Step S21: obtaining laser cutting parameter data; Step S22: constructing a three-dimensional model using the laser cutting geometry-material association data to generate a laser cutting three-dimensional solid model; Step S23: constructing an algorithm model for the laser cutting three-dimensional model using the laser cutting parameter data to generate a preliminary analysis model for laser cutting common edges.

[0042] In an embodiment of the present invention, the process of obtaining laser cutting parameter data generally includes collecting various key parameters in the cutting process, including laser power, cutting speed, focal length, spot size, laser wavelength, etc. These parameters are often monitored in real time by sensors and stored by data acquisition systems to provide necessary data support for subsequent model construction. The technical means of this step include real-time data acquisition and timing analysis, which can collect accurate cutting parameter data according to different cutting conditions to ensure that the key physical properties of the actual cutting environment can be accurately reflected during the three-dimensional model construction process. The process of using laser cutting geometry-material association data to build a three-dimensional model adopts modeling technology based on computer-aided design (CAD) and computer graphics. By combining and analyzing geometric features (such as object size, shape, contour, etc.) and material properties (such as material density, hardness, thermal conductivity, etc.) data, a three-dimensional stereoscopic model integrating geometric information and material properties can be generated. This process usually uses methods such as spatial transformation and geometric interpolation to map the two-dimensional features in the data set to three-dimensional space, and generates a fine three-dimensional model through three-dimensional modeling technology (such as voxel modeling, grid modeling, etc.). The associated data of geometric features and material properties plays a key role here, ensuring that the generated three-dimensional model accurately reflects the physical and material properties of the cutting object, especially the material response and deformation under different cutting parameters. The algorithm model of the three-dimensional model is constructed based on the laser cutting parameter data to generate a preliminary analysis model of laser cutting common edge. This process relies on a variety of algorithms and optimization techniques, mainly including path planning based on geometric shapes and cutting parameters, common edge optimization, and optimal connection algorithms between adjacent cutting surfaces. In this process, cutting parameters (such as laser power, speed, etc.) directly affect the generation and optimization of the cutting path. Therefore, the algorithm model must not only consider the matching of geometric shapes, but also comprehensively consider factors such as thermal effects and mechanical effects in the cutting process, and then generate an optimization plan for the cutting path.

[0043] Preferably, step S23 includes the following steps: Step S231: performing geometric overlap analysis on the laser cutting three-dimensional model to generate laser cutting shared boundary data; Step S232: performing cutting path planning on the laser cutting shared boundary data to generate laser cutting path data; Step S233: specifying focus-speed cutting parameters for the laser cutting path data to generate cutting parameter data; constructing an algorithm model based on the cutting parameter data and the laser cutting path data to generate a preliminary analysis model for laser cutting common edge.

[0044] In the embodiment of the present invention, the core technical means for geometric overlap analysis of laser cutting three-dimensional stereo models is geometric matching and spatial overlap analysis algorithm. This process first identifies the shared boundaries of multiple cutting areas by performing accurate geometric overlap analysis on the three-dimensional model of the laser cutting object. This operation usually relies on efficient spatial data structures (such as octrees, BVH trees, etc.), which can quickly find and determine the overlapping boundaries between models. The shared boundary data generated after the geometric overlap analysis further provides key reference information for cutting path planning, ensuring seamless connection of the cutting path and maximization of material utilization. When planning the cutting path based on the shared boundary data of laser cutting, the path optimization algorithm and the shortest path algorithm in graph theory are used. These algorithms plan efficient cutting paths by considering the geometric characteristics of the cutting object, the cutting order, and the characteristics of the material (such as thickness, density, etc.). The path planning algorithm also needs to take into account physical factors such as thermal effects and stress changes that occur during the cutting process, as well as the minimization of path intersections, to reduce equipment pauses and reverse cutting. Heuristic algorithms (such as A* algorithms, Dijkstra algorithms, etc.) are usually used to optimize the cutting path to minimize energy consumption and improve cutting efficiency. The technical means of specifying the focus-speed cutting parameters based on the laser cutting path data is used to optimize the laser cutting parameters and paths in both directions. The effect of laser cutting is highly dependent on the setting of parameters such as the position of the laser beam focus, cutting speed, and power. In this process, the selection of the focus-speed cutting parameters depends on the thermal conductivity characteristics of the actual material and the complexity of the cutting path, ensuring that each cutting segment can be cut with the optimal laser power and speed. These cutting parameters are determined by multidimensional data analysis and optimization algorithms, and dynamically adjusted based on the data model of the laser cutting path to ensure the balance between cutting quality and efficiency. Finally, the preliminary analysis model of laser cutting common edge is further generated by constructing an algorithm model based on cutting parameter data and path data. This technical means combines the aforementioned geometric overlap analysis and path planning data, and further verifies and optimizes the cutting path and parameter settings by establishing a mathematical model and simulation system to ensure that the generated preliminary analysis model meets the actual cutting requirements. The main technologies used in this process include numerical optimization algorithms, simulated annealing algorithms, and genetic algorithms. Through the integration of these technologies, the optimal solution can be found in complex cutting scenarios.

[0045] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes: Step S31: performing global optimization of nesting layout based on the preliminary analysis model of laser cutting common edge, and generating global optimization data for laser cutting; Step S32: Performing model nesting integer linear programming on the laser cutting global optimization data to generate a laser cutting global optimization model; Step S33: Perform local co-edge analysis on the laser cutting global optimization model to generate an intelligent co-edge analysis model for laser cutting.

[0046] In the embodiment of the present invention, the core technical means of "global optimization of nesting layout based on the preliminary analysis model of laser cutting common edge" is to optimize the overall layout of the cutting area through a data-driven optimization algorithm. This process usually uses a heuristic optimization algorithm (such as a genetic algorithm, a simulated annealing algorithm or a particle swarm optimization, etc.) to efficiently solve the problem of maximizing material utilization. The goal of global optimization is to ensure that each component in the cutting area can be arranged with minimal material waste, optimize the overall cutting process, reduce waste and improve cutting efficiency. This optimization process adjusts the cutting path and relative position of each component based on the boundary data in the preliminary analysis model of laser cutting common edge, thereby achieving global optimization. The technical means of "model nesting integer linear programming for laser cutting global optimization data" is to use the integer linear programming (ILP) method in mathematical optimization to further refine the global optimization results. This method transforms the cutting layout problem into a mathematical problem of linear constraints by constructing a mathematical model, ensuring that the optimization of nesting layout is achieved under the premise of satisfying certain physical constraints (such as cutting path, machine performance, material thickness, etc.). Specifically, the integer linear programming method can minimize material waste by setting a suitable objective function. Constraints include material size, shape restrictions, and machine processing capabilities. By solving this linear programming problem, a set of optimal cutting solutions can be generated to provide data support for subsequent cutting operations. "Performing local co-edge analysis on the global optimization model of laser cutting and generating an intelligent co-edge analysis model for laser cutting" further refines and locally optimizes the cutting path after global optimization. This process mainly uses data analysis and intelligent algorithms, relying on machine learning or deep learning models, to perform local intelligent analysis of the co-edge area within the cutting area. The local co-edge analysis usually uses the previously generated global optimization data to optimize the intersection points, shared boundaries, and cutting order of each cutting path, with the aim of further reducing the reverse path during the cutting process, improving material utilization, and reducing thermal effects and stress changes during cutting.

[0047] Preferably, step S33 includes the following steps: Step S331: performing path planning simulation on the laser cutting global optimization model to generate laser cutting path planning simulation data; performing shortest path generation tree optimization on the laser cutting path planning simulation data to generate a laser cutting optimization tree path; Step S332: performing local material scanning on the global optimization model for laser cutting to generate local material data for laser cutting; re-optimizing the material utilization rate of the local material data for laser cutting to generate re-optimized material data for laser cutting; Step S333: Draw a two-dimensional optimization graph of cutting speed and power for the global optimization model of laser cutting to generate a two-dimensional optimization graph of local speed and power for laser cutting; create a speed-power matrix based on the two-dimensional optimization graph of local speed and power for laser cutting, determine the best speed-power combination, and generate data of the best combination of laser cutting speed and power; Step S334: Based on the laser cutting optimization tree path, the laser cutting material re-optimization data and the laser cutting speed-power optimal combination data, the laser cutting global optimization model is subjected to local co-edge analysis to generate an intelligent laser cutting co-edge analysis model.

[0048] In the embodiment of the present invention, the technical means of "simulating the path planning of the global optimization model of laser cutting and generating the simulation data of the path planning of laser cutting" is mainly to simulate the cutting path by using the path planning algorithm. At this time, the algorithm generates a preliminary cutting path planning data set by comprehensive analysis of the geometric shape of the cutting area, material properties and other data. On this basis, the path is further optimized by the shortest path generation tree optimization (such as Dijkstra algorithm or A* algorithm) to ensure that the cutting path reduces the reverse path and idle path of the machine movement under the premise of minimizing the time cost and energy consumption, thereby generating the laser cutting optimization tree path. This process uses the shortest path algorithm in graph theory to solve the optimal problem of path selection in the cutting process by optimizing the path generation tree. The technical means of "scanning the local material of the global optimization model of laser cutting and generating the local material data of laser cutting" is to scan the materials in the local area in detail based on the scanning technology and sensor data to obtain the actual characteristic data of the materials. These data include the thickness, density, hardness, etc. of the material, and local material data are generated by comparing with the global optimization model. Next, through material utilization re-optimization (such as linear programming or simulated annealing algorithms), the cutting path and material arrangement are further adjusted and optimized according to the scanning data and optimization model to generate laser cutting material re-optimization data. This optimization process can further improve the utilization of materials and reduce waste on the basis of ensuring cutting accuracy. The technical means of "drawing a two-dimensional optimization diagram of cutting speed-power for the global optimization model of laser cutting and generating a two-dimensional optimization diagram of local speed-power for laser cutting" is based on the balance between energy consumption and cutting quality in the cutting process. Through experimental data and theoretical models, a two-dimensional optimization diagram between cutting speed and power is drawn. The optimization diagram shows the best combination of speed and power under different cutting conditions. Based on this diagram, a speed-power matrix is ​​created, and the optimal speed-power combination is determined by an optimization algorithm (such as gradient descent method or genetic algorithm) to generate the best combination data of laser cutting speed-power. This process helps to improve cutting efficiency while avoiding the problem of material ablation or incomplete cutting due to too high or too low power settings. The technical means of "local analysis of common edge of laser cutting global optimization model based on laser cutting optimization tree path, laser cutting material re-optimization data and laser cutting speed-power optimal combination data" is to integrate the optimized path, material data and speed-power data, and conduct local analysis of common edge in the cutting process through intelligent algorithms (such as deep learning or fuzzy logic algorithms). This analysis not only considers the efficiency of path optimization, but also combines the comprehensive influence of material properties and energy consumption to generate an intelligent common edge analysis model for laser cutting. The model can adaptively adjust the cutting strategy to maximize material utilization, improve cutting speed, and ensure the stability of cutting quality.

[0049] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes: Step S41: acquiring real-time laser cutting data; Step S42: performing laser cutting operation based on the laser cutting intelligent common edge analysis model to generate laser cutting model data; evaluating the real-time laser cutting data and the laser cutting model data to generate laser cutting evaluation data; Step S43: generating an evaluation report for the laser cutting evaluation data, thereby completing the nesting, layout and mixed common edge analysis operation based on lens laser cutting.

[0050] In the embodiment of the present invention, "obtaining real-time laser cutting data" relies on sensors and monitoring equipment to collect multi-dimensional data in the cutting process in real time, including laser power, cutting speed, temperature, material changes, etc. These data are transmitted to the computing platform through the data acquisition system to form a real-time laser cutting data set. The accurate acquisition of these data provides a basis for subsequent analysis and ensures the timeliness and accuracy of the data. Then, in step S42, laser cutting model data is generated through the operation based on the "intelligent common edge analysis model for laser cutting". In this process, the intelligent common edge analysis model uses a data model based on the combination of laser cutting geometric features and material properties, and automatically generates a set of theoretically optimal cutting paths and process parameters through a comprehensive evaluation of cutting paths, common edge analysis and material properties. Using the output of the model, laser cutting model data that interacts with real-time data can be generated. These data include specific values ​​of various parameters in the cutting process, such as speed, power, focus position, etc. Next, the real-time laser cutting data and the laser cutting model data are evaluated, and laser cutting evaluation data is generated. This process is to evaluate the deviation between the actual cutting effect and the expected effect through comparative analysis between real-time data and theoretical models. Specifically, the evaluation data includes the actual performance indicators in the cutting process, such as cutting quality, material utilization, processing accuracy, etc., and the differences between them and the model prediction values, and the error correction is performed through intelligent algorithms to further optimize the operation process. Report generation is performed on the laser cutting evaluation data. Based on these evaluation data, the system generates a detailed evaluation report through certain algorithms (such as data mining, machine learning, etc.).

[0051] In this specification, a nesting layout mixed common edge analysis system based on lens laser cutting is provided, which is used to execute the above-mentioned nesting layout mixed common edge analysis method based on lens laser cutting. The nesting layout mixed common edge analysis system based on lens laser cutting: The data processing module is used to obtain a laser cutting preparatory data set; perform data preprocessing on the laser cutting preparatory data set to generate a laser cutting preprocessing data set; perform geometric feature-material property correlation analysis on the laser cutting preprocessing data set to generate laser cutting geometry-material correlation data; The common edge analysis model building module is used to build an intelligent common edge analysis model based on the laser cutting geometry-material correlation data to generate a preliminary common edge analysis model for laser cutting; The optimization and local analysis module is used to perform global optimization of nesting layout based on the preliminary analysis model of laser cutting co-edge, and generate a global optimization model for laser cutting; perform local co-edge analysis on the global optimization model for laser cutting, and generate an intelligent co-edge analysis model for laser cutting; The evaluation and report generation module is used to evaluate based on the intelligent common edge analysis model of laser cutting and generate laser cutting evaluation data; generate an evaluation report for the laser cutting evaluation data, thereby completing the nesting and typesetting mixed common edge analysis operation based on lens laser cutting.

[0052] The beneficial effects of the present invention are that by acquiring a laser cutting preparation data set and performing data preprocessing, the standardization of input data is improved, data noise and redundant information are reduced, the stability and accuracy of data processing are improved, and a geometric feature-material property correlation analysis is performed on the laser cutting preprocessing data set, the precise adaptability of laser cutting parameters is improved, the cutting quality and material utilization rate are improved, an intelligent common edge analysis model is constructed based on the laser cutting geometry-material correlation data, the common edge adaptation ability between different lens geometric shapes is improved, the material layout compactness and resource utilization rate are improved, and material waste is reduced. Based on the laser cutting common edge preliminary analysis model, a global nesting layout is performed Optimize, improve the rationality of the overall cutting plan, reduce cutting path redundancy, improve laser cutting efficiency, conduct local common edge analysis on the global optimization model of laser cutting, optimize the local common edge path, reduce the cumulative effect of the heat affected zone, improve the quality of the cutting edge, and reduce the loss of material due to thermal deformation. Evaluate based on the intelligent common edge analysis model of laser cutting to improve the stability and applicability of the nesting layout plan, ensure the reliability of the cutting plan under different production conditions, generate an evaluation report for the laser cutting evaluation data, provide accurate common edge layout optimization suggestions for the production process, improve the visualization and controllability of production management, and improve production efficiency and quality control.

[0053] 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.

[0054] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A nesting layout mixed common edge analysis method based on lens laser cutting, characterized in that: The following steps are involved: Step S1: Acquire laser cutting preparation data set; Performing data preprocessing on the laser cutting preparation data set to generate a laser cutting preprocessing data set; performing geometric feature-material property correlation analysis on the laser cutting preprocessing data set to generate laser cutting geometry-material correlation data; Step S2: constructing an intelligent common edge analysis model based on laser cutting geometry-material association data to generate a preliminary common edge analysis model for laser cutting; Step S3: Perform global optimization of nesting layout based on the preliminary analysis model of laser cutting co-edge, and generate a global optimization model for laser cutting; perform local co-edge analysis on the global optimization model for laser cutting, and generate an intelligent co-edge analysis model for laser cutting; Step S4: Evaluate based on the intelligent common edge analysis model of laser cutting to generate laser cutting evaluation data; generate an evaluation report for the laser cutting evaluation data, thereby completing the nesting and typesetting mixed common edge analysis operation based on lens laser cutting.

2. The nesting layout mixed common edge analysis method based on lens laser cutting according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Acquire laser cutting preparation data set; Step S12: performing data preprocessing on the laser cutting preparation data set to generate a laser cutting preprocessing data set; Step S13: extracting data from the laser cutting preprocessing data set to generate laser cutting extraction data; performing geometric feature-material property correlation analysis on the laser cutting extraction data to generate laser cutting geometry-material correlation data.

3. The nesting layout mixed common edge analysis method based on lens laser cutting according to claim 2 is characterized in that: Step S12 includes the following steps: Step S121: normalizing the laser cutting preparation data set to generate laser cutting normalized data; Step S122: performing data cleaning according to the laser cutting normalized data, and removing abnormal data to generate laser cutting cleaning data; Step S123: performing data standardization processing on the laser cutting cleaning data to generate a laser cutting preprocessing data set, wherein the laser cutting preprocessing data set includes a laser cutting geometry preprocessing data set and a laser cutting material property preprocessing data set.

4. The nesting layout mixed common edge analysis method based on lens laser cutting according to claim 2 is characterized in that: Step S13 includes the following steps: Step S131: extracting the size features of the laser cutting geometric preprocessing data set to generate laser cutting size feature data; performing geometric shape analysis on the laser cutting size feature data to generate laser cutting geometric shape data; establishing a three-dimensional image based on the laser cutting geometric shape data to generate a laser cutting three-dimensional image; Step S132: performing lens shape feature analysis on the laser-cut three-dimensional image to generate laser-cut lens shape data; performing lens edge tilt angle detection on the laser-cut lens shape data to generate laser-cut lens edge tilt angle data; performing cutting angle detection on the laser-cut lens shape data to generate laser cutting angle data; performing plane angle calculation on the laser-cut lens edge tilt angle data and the laser cutting angle data to generate laser cutting geometric feature extraction data; Step S133: performing thermal expansion coefficient influence detection on the laser cutting material characteristic preprocessing data set to generate laser cutting thermal expansion coefficient data; performing beam penetration analysis on the laser cutting thermal expansion coefficient data to generate laser cutting beam penetration data; performing thickness uniformity measurement on the laser cutting beam penetration data to generate laser cutting material characteristic extraction data; Step S134: perform L1 regularization on the laser cutting geometric feature extraction data and the laser cutting material feature extraction data to generate laser cutting feature regularization data; create a geometric feature-material characteristic feature matrix for the laser cutting feature regularization data to generate a laser cutting geometric feature-material characteristic feature matrix; perform geometric feature-material characteristic correlation analysis on the laser cutting geometric feature-material characteristic feature matrix to generate laser cutting geometry-material correlation data.

5. The nesting layout mixed common edge analysis method based on lens laser cutting according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: obtaining laser cutting parameter data; Step S22: constructing a three-dimensional model using laser cutting geometry-material association data to generate a laser cutting three-dimensional solid model; Step S23: constructing an algorithm model for the laser cutting three-dimensional model using the laser cutting parameter data to generate a preliminary analysis model for laser cutting common edges.

6. The nesting layout mixed common edge analysis method based on lens laser cutting according to claim 5 is characterized in that: Step S23 includes the following steps: Step S231: performing geometric overlap analysis on the laser cutting three-dimensional model to generate laser cutting shared boundary data; Step S232: performing cutting path planning on the laser cutting shared boundary data to generate laser cutting path data; Step S233: specifying focus-speed cutting parameters for the laser cutting path data to generate cutting parameter data; constructing an algorithm model based on the cutting parameter data and the laser cutting path data to generate a preliminary analysis model for laser cutting common edge.

7. The nesting layout mixed common edge analysis method based on lens laser cutting according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: performing global optimization of nesting layout based on the preliminary analysis model of laser cutting common edge, and generating global optimization data for laser cutting; Step S32: Performing model nesting integer linear programming on the laser cutting global optimization data to generate a laser cutting global optimization model; Step S33: Perform local co-edge analysis on the laser cutting global optimization model to generate an intelligent co-edge analysis model for laser cutting.

8. The nesting layout mixed common edge analysis method based on lens laser cutting according to claim 7 is characterized in that: Step S33 includes the following steps: Step S331: performing path planning simulation on the laser cutting global optimization model to generate laser cutting path planning simulation data; performing shortest path generation tree optimization on the laser cutting path planning simulation data to generate a laser cutting optimization tree path; Step S332: performing local material scanning on the global optimization model for laser cutting to generate local material data for laser cutting; re-optimizing the material utilization rate of the local material data for laser cutting to generate re-optimized material data for laser cutting; Step S333: Draw a two-dimensional optimization graph of cutting speed and power for the global optimization model of laser cutting to generate a two-dimensional optimization graph of local speed and power for laser cutting; create a speed-power matrix based on the two-dimensional optimization graph of local speed and power for laser cutting, determine the best speed-power combination, and generate data of the best combination of laser cutting speed and power; Step S334: Based on the laser cutting optimization tree path, the laser cutting material re-optimization data and the laser cutting speed-power optimal combination data, the laser cutting global optimization model is subjected to local co-edge analysis to generate an intelligent laser cutting co-edge analysis model.

9. The nesting layout mixed common edge analysis method based on lens laser cutting according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: acquiring real-time laser cutting data; Step S42: performing laser cutting operation based on the laser cutting intelligent common edge analysis model to generate laser cutting model data; evaluating the real-time laser cutting data and the laser cutting model data to generate laser cutting evaluation data; Step S43: generating an evaluation report for the laser cutting evaluation data, thereby completing the nesting, layout and mixed common edge analysis operation based on lens laser cutting.

10. A nesting layout mixed common edge analysis system based on lens laser cutting, characterized in that: Used to execute the nesting layout mixed common edge analysis method based on lens laser cutting as claimed in claim 1, the nesting layout mixed common edge analysis system based on lens laser cutting comprises: The data processing module is used to obtain a laser cutting preparatory data set; perform data preprocessing on the laser cutting preparatory data set to generate a laser cutting preprocessing data set; perform geometric feature-material property correlation analysis on the laser cutting preprocessing data set to generate laser cutting geometry-material correlation data; The common edge analysis model building module is used to build an intelligent common edge analysis model based on the laser cutting geometry-material correlation data to generate a preliminary common edge analysis model for laser cutting; The optimization and local analysis module is used to perform global optimization of nesting layout based on the preliminary analysis model of laser cutting co-edge, and generate a global optimization model for laser cutting; perform local co-edge analysis on the global optimization model for laser cutting, and generate an intelligent co-edge analysis model for laser cutting; The evaluation and report generation module is used to evaluate based on the intelligent common edge analysis model of laser cutting and generate laser cutting evaluation data; generate an evaluation report for the laser cutting evaluation data, thereby completing the nesting and typesetting mixed common edge analysis operation based on lens laser cutting.

Images