Control strategy optimization method for laser cutting machine

Abstract

The invention discloses a control strategy optimization method for a laser cutting machine, and relates to the technical field of laser cutting, and the method comprises the following steps: obtaining cutting design information of a target laser cutting machine and a workpiece by constructing an operation data space of the laser cutting machine; and performing matching retrieval on the operation data, and establishing an operation data memory bank. Performing equivalent region segmentation on the workpiece based on the cutting design information to obtain an equivalent cutting region set; and performing control strategy analysis, and determining a control strategy parameter set. And the control strategy parameter set is used for conducting cutting feedback detection on the laser cutting machine, and a sensing feedback data stream is obtained. And optimization analysis is conducted on the control strategy parameter set, an optimized control strategy parameter set is determined, and strategy optimization control is conducted on the laser cutting machine. The technical problem that an existing laser cutting machine is unstable in cutting quality under different workpieces and cutting conditions is solved, and the technical effects that the control strategy optimization accuracy is improved, and the cutting quality is kept stable are achieved.

Description

Technical Field

[0001] The present application relates to the field of laser cutting technology, and in particular to a control strategy optimization method for a laser cutting machine. Background Art

[0002] As an efficient and precise cutting method in modern manufacturing, laser cutting technology is widely used in many fields such as metal processing, electronic manufacturing, automobile manufacturing, aerospace, and art design. However, with the continuous increase in industrial production needs, traditional laser cutting machines face many technical challenges in control strategies. Existing control methods usually rely on preset parameters and lack the ability to dynamically adapt to different workpiece characteristics and real-time cutting conditions, resulting in low cutting efficiency and unstable cutting quality. This limits the application effect and production efficiency of laser cutting technology in complex and diversified cutting tasks.

[0003] In the current related technologies, there is a technical problem that the cutting quality of laser cutting machines is unstable under different workpieces and cutting conditions. Summary of the invention

[0004] The present application solves the technical problem of unstable cutting quality of existing laser cutting machines under different workpieces and cutting conditions by providing a control strategy optimization method for a laser cutting machine.

[0005] This application provides a control strategy optimization method for a laser cutting machine, including: The laser cutting machine operation data space is constructed by data mining technology, and the cutting design information of the target laser cutting machine and the target workpiece is obtained; the laser cutting machine operation data space is matched and retrieved according to the attribute information of the target laser cutting machine, and the target laser cutting machine operation data memory is obtained; the target workpiece is segmented into equivalent areas based on the cutting design information to obtain a workpiece equivalent cutting area set; the target laser cutting machine operation data memory is used to perform control strategy analysis on the workpiece equivalent cutting area set in turn to determine the equivalent cutting area control strategy parameter set; based on the equivalent cutting area control strategy parameter set, the target laser cutting machine is controlled to perform cutting feedback detection on the target workpiece to obtain a cutting area perception feedback data stream; based on the cutting area perception feedback data stream, the equivalent cutting area control strategy parameter set is integrated and optimized to determine the cutting machine optimization control strategy parameter set, and the target laser cutting machine is strategy optimized through the cutting machine optimization control strategy parameter set.

[0006] The control strategy optimization method for a laser cutting machine proposed in this application is to first construct the operation data space of the laser cutting machine through data mining technology to obtain the cutting design information of the target laser cutting machine and the workpiece. The operation data is matched and retrieved according to the attribute information of the laser cutting machine, and an operation data memory is established. The workpiece is segmented into equivalent regions based on the cutting design information to obtain a set of equivalent cutting regions. The control strategy is analyzed on the equivalent cutting region using the operation data memory to determine the control strategy parameter set. The laser cutting machine is subjected to cutting feedback detection using the control strategy parameter set to obtain the perception feedback data stream. The control strategy parameter set is optimized and analyzed based on the feedback data stream to determine the optimized control strategy parameter set, and strategy optimization control is implemented on the laser cutting machine, thereby achieving the technical effect of improving the accuracy of control strategy optimization and maintaining stable cutting quality when facing different types of workpieces and diverse cutting conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0008] Figure 1 A flow chart of a control strategy optimization method for a laser cutting machine provided in an embodiment of the present application; Figure 2 A schematic diagram of the process of acquiring an operating data memory library for a control strategy optimization method for a laser cutting machine provided in an embodiment of the present application. DETAILED DESCRIPTION

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0010] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0011] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0012] The present application embodiment provides a control strategy optimization method for a laser cutting machine, such as Figure 1 As shown, the method includes: Step S100, construct the laser cutting machine operation data space through data mining technology, and obtain the cutting design information of the target laser cutting machine and the target workpiece. Specifically, using data mining technology, collect multi-dimensional data such as laser power output, cutting speed, focal position, cutting gas flow rate, etc. from the operation records of laser cutting machines under many different models, manufacturers and cutting task scenarios, and construct the laser cutting machine operation data space after sorting, classification and structured processing; obtain the type, structural specifications, power level and other attribute information of the target laser cutting machine, as well as the material, shape, size and expected cutting quality standard of the target workpiece. The former is helpful for the subsequent accurate matching and screening of relevant data in the data space, and the latter serves as the key target basis for the optimization of the control strategy, laying the foundation for the entire laser cutting control strategy optimization process.

[0013] Step S200, matching and searching the laser cutting machine operation data space according to the attribute information of the target laser cutting machine, and obtaining the target laser cutting machine operation data memory library. Specifically, the attribute information such as the type, structural specifications, and power level of the target laser cutting machine is standardized and converted into quantifiable numerical values ​​or range descriptions, so as to construct a multi-dimensional index system. In the laser cutting machine operation data space, starting from the top level according to the index system, the data set is first filtered by type, and then the range is further narrowed by the structural specification index, and finally the power level index is accurately matched, so as to accurately filter out the data subset that highly matches the target laser cutting machine attributes, integrate and organize them, and generate the target laser cutting machine operation data memory library after classification and association processing and quality assessment screening. This memory library, as its tailor-made experience treasure house, can provide important basis and reference for subsequent cutting control strategy analysis.

[0014] In one possible implementation, Figure 2 As shown, the laser cutting machine operation data space is matched and retrieved according to the attribute information of the target laser cutting machine to obtain the target laser cutting machine operation data memory library, and step S200 further includes step S210, obtaining the laser cutting machine attribute factor information, and the laser cutting machine attribute factor information includes the cutting machine type, structural specifications, power level and cutting material. Specifically, the attribute factor information related to the laser cutting machine is collected. For the type of cutting machine, it is clear whether it belongs to a carbon dioxide laser cutting machine, a fiber laser cutting machine, a disc laser cutting machine or other specific types, because different types of laser generators have different working principles and have a significant impact on the cutting process. For example, a fiber laser cutting machine has higher energy conversion efficiency and beam quality when cutting metal materials, while a carbon dioxide laser cutting machine has unique advantages in cutting certain non-metallic materials. In terms of structural specifications, accurately measuring the size of the workbench, including the specific values ​​of length, width, and height, determines the maximum size range of the workpiece that can be processed; determining the travel range of the cutting head, which directly affects the cutting ability of workpieces of different heights or depths; understanding the accuracy of the mechanical transmission system. A high-precision transmission system can achieve more precise cutting positioning. For example, when cutting tiny parts or workpieces with extremely high cutting edge accuracy, transmission accuracy is crucial. Power level information is also indispensable. Determine whether low power (such as a few hundred watts) is suitable for fine cutting of thin materials, medium power (several thousand watts) can cope with the cutting of general thickness materials, or high power (tens of thousands of watts) is used for cutting and processing thick and hard materials. Record the types of materials that the laser cutting machine is good at cutting, such as whether it is mainly for metal materials (such as steel, aluminum, copper, etc.), or focuses on non-metallic materials (such as plastics, wood, ceramics, etc.), or has a certain cutting ability for multiple materials. This information will provide a basic basis for subsequent data processing.

[0015] Step S220, classify and encode the laser cutting machine operation data space according to the laser cutting machine attribute factor information to obtain the cutting machine attribute code set. Specifically, classify and encode the laser cutting machine operation data space according to the acquired laser cutting machine attribute factor information. For the type of cutting machine, set specific coding rules, such as the carbon dioxide laser cutting machine is coded as "C02", the fiber laser cutting machine is coded as "Fiber", etc., so that different types of cutting machines are clearly distinguished in data classification. For structural specifications, information such as workbench size, cutting head stroke and mechanical transmission accuracy are converted into digital codes. For example, different intervals are divided according to the length and width of the workbench, and each interval is assigned a specific coding number; the cutting head stroke is coded according to different length ranges; and the mechanical transmission accuracy is set according to the size of its error value. The power level is also coded as "L", "M", "H", etc. according to low, medium and high power. The cutting material is coded according to the type of material, such as metal material is coded as "M", non-metallic material is coded as "N", and multiple materials are coded as "B". Through encoding, the multi-dimensional attribute information of each laser cutting machine is converted into a unified coding format, thereby obtaining a cutting machine attribute coding set, so that each laser cutting machine operation data in the data space can be quickly classified and retrieved according to its corresponding coding.

[0016] Step S230, clustering and dividing the laser cutting machine operation data space based on the cutting machine attribute coding set to obtain a laser cutting machine operation clustering data set. Specifically, clustering and dividing the laser cutting machine operation data space based on the generated cutting machine attribute coding set. Using a clustering algorithm, based on attribute coding, the laser cutting machine operation data with similar attribute coding are clustered together. For example, all laser cutting machine operation data with type coding as "Fiber", power level coding as "M", cutting material coding as "M" and structural specification coding in a similar interval are classified into one category. A laser cutting machine operation clustering data set is obtained, and the data in each cluster has a high similarity, reflecting the operation rules and characteristics of the laser cutting machine under similar attribute conditions. Clustering helps to reduce the scope and complexity of data search, improve the efficiency and accuracy of data retrieval, and lay the foundation for subsequent accurate data matching for the target laser cutting machine.

[0017] Step S240, according to the attribute information of the target laser cutting machine and the laser cutting machine operation clustering data set, attribute matching retrieval is performed to obtain the target laser cutting machine operation data memory library. Specifically, according to the attribute information of the target laser cutting machine and the laser cutting machine operation clustering data set, attribute matching retrieval is performed. After the attribute information such as the type, structural specification, power level and cutting material of the target laser cutting machine is converted into corresponding codes, matching search is performed in the laser cutting machine operation clustering data set. Starting from each cluster in the clustering data set, the encoding of the target laser cutting machine is compared with the encoding attributes of the data in the cluster in turn. For example, if the target laser cutting machine is a fiber laser cutting machine, medium power, cutting metal materials and the structural specifications are within a specific range, it is first searched in the cluster with the type of "Fiber", the power level of "M", and the cutting material of "M", and further compared whether the structural specification coding matches. Through accurate attribute matching retrieval, the data that best matches the attributes of the target laser cutting machine is screened out from the clustering data set, and the data is integrated to obtain the target laser cutting machine operation data memory library. The memory library contains the operating data of other laser cutting machines with similar properties to the target laser cutting machine, such as the optimal power setting, cutting speed, focus position and other parameter information when cutting specific materials. It can provide valuable reference and reference for the target laser cutting machine when handling different cutting tasks, and help optimize its cutting control strategy and improve cutting quality and efficiency.

[0018] Step S300, based on the cutting design information, the target workpiece is segmented into equivalent regions to obtain a workpiece equivalent cutting region set. Specifically, the cutting design information of the target workpiece is analyzed, covering the geometric shape, size requirements and material properties, etc., and segmentation indicators such as geometric shape category, size range, material type, etc. are accurately extracted. A three-dimensional model of the target workpiece is constructed using computer-aided design or special modeling tools. The three-dimensional model is spatially segmented and marked according to the segmentation indicators. Parts with the same or similar geometric shape, size range, and material type are divided into regions and assigned corresponding labels to form a workpiece indicator segmentation region set and a regional segmentation indicator label set. Finally, the workpiece indicator segmentation region set is clustered and integrated according to the regional segmentation indicator label set, and regions with the same or similar labels are gathered together, thereby determining a workpiece equivalent cutting region set, in which each region has similar cutting characteristic requirements, which is conducive to the formulation of subsequent cutting control strategies.

[0019] In a possible implementation, the target workpiece is segmented into equivalent regions based on the cutting design information to obtain a set of equivalent cutting regions of the workpiece. Step S300 further includes step S310, performing three-dimensional modeling based on the cutting design information to establish a three-dimensional model of the target workpiece. Specifically, three-dimensional modeling is performed based on the obtained cutting design information of the target workpiece. The cutting design information contains detailed dimension data of the workpiece, such as length, width, height, and specific shape and size descriptions of each part, and the data becomes the basic framework data for building a three-dimensional model. In terms of shape, if the workpiece is a complex mechanical part, its contour is composed of multiple curved surfaces, planes, and various transition shapes. When modeling, it is necessary to accurately construct the corresponding geometric shape entity based on these shape information using professional three-dimensional modeling software (such as CAD software). For example, if the workpiece has an arc-shaped surface, the arc-shaped surface must be accurately drawn by defining parameters such as the center of the circle, radius, starting angle, and end angle during the modeling process. At the same time, the internal structure information of the workpiece is analyzed. If there are internal features such as holes and grooves, they must also be realistically reflected in the three-dimensional model to determine their position, shape, and size. Through comprehensive integration and precise drawing of cutting design information, a three-dimensional model of the target workpiece is established. The model will present the overall picture of the workpiece in an intuitive three-dimensional form, providing a visual basis for subsequent segmentation operations.

[0020] Step S320, extract the segmentation index of the workpiece cutting application information, and obtain the workpiece segmentation index set, which includes geometric shape, cutting size and material properties. Specifically, after establishing the three-dimensional model of the target workpiece, the workpiece cutting application information is analyzed to extract the segmentation index. From the perspective of geometric shape, the shape characteristics of the workpiece as a whole and each part are identified to determine whether it belongs to a simple geometric shape (such as a circle, square, triangle, etc.) or a complex combination shape or a special-shaped structure. For example, for a workpiece composed of multiple cylinders and cuboids, the shape category of each component must be clearly defined. In terms of cutting size, in addition to the overall length, width and height, it is also necessary to pay attention to the relative size relationship between the parts and the thickness information of different parts. For example, for a plate-shaped workpiece with different thin and thick areas, the thickness values ​​of the thin area and the thick area and the position distribution in the entire workpiece should be recorded. Material properties are one of the key indicators. It is necessary to understand whether the workpiece material is metal (such as steel, aluminum, copper, etc.) or non-metal (such as plastic, wood, ceramic, etc.). If it is a metal material, further analyze its hardness, melting point, thermal conductivity and other performance parameters. For example, alloy steel workpieces with higher hardness are more difficult to cut and require higher energy cutting methods; while aluminum materials with lower melting points require precise control of laser energy during cutting to prevent over-melting. Through analysis, a set of workpiece segmentation indicators including geometric shape, cutting size and material properties are obtained, which will serve as an important basis for dividing the workpiece area.

[0021] Step S330, based on the workpiece segmentation index set, the target workpiece three-dimensional model is spatially segmented and marked in sequence to obtain a workpiece index segmentation region set and a region segmentation index label set. Specifically, based on the extracted workpiece segmentation index set, the target workpiece three-dimensional model is spatially segmented and marked. Starting from the geometric shape index, regions with the same or similar geometric shapes are marked. For example, all circular parts are marked as one category, and square parts are marked as another category. In terms of cutting size, regions with the same thickness or similar thickness within a certain error range are uniformly marked, and their size ranges are indicated. For example, regions with a thickness between 3 and 5 mm are marked as a group, and their thickness ranges are recorded. For material performance indicators, regions with the same material and similar performance are classified as the same mark. For example, all regions with steel materials and hardness within a certain range are marked together. The target workpiece three-dimensional model is spatially segmented and marked in sequence to obtain multiple marked regions, which constitute a workpiece index segmentation region set, and each region corresponds to a specific region segmentation index label, which records the region's geometric shape, cutting size, material performance and other information to form a region segmentation index label set.

[0022] Step S340, clustering and integrating the workpiece index segmentation region set according to the region segmentation index label set to obtain the workpiece equivalent cutting region set. Specifically, clustering and integrating the workpiece index segmentation region set according to the region segmentation index label set. Clustering regions with the same or similar region segmentation index labels together to form a workpiece equivalent cutting region set. For example, all regions marked as circular, with a thickness of 2 to 3 mm and made of aluminum will be integrated into an equivalent cutting region. In the clustering and integration process, some boundary region processing will be involved. For those regions with similar but not completely identical indicators, it is determined whether to merge them into a certain equivalent cutting region according to the requirements of the actual cutting process and the degree of influence on the cutting effect. Through the clustering and integration operation, each region in the workpiece equivalent cutting region set obtained has relatively similar cutting characteristic requirements. When formulating the cutting control strategy in the future, each equivalent cutting region can be considered uniformly, which reduces the complexity of the control strategy and improves the efficiency and accuracy of strategy formulation, thereby laying the foundation for realizing efficient and accurate laser cutting operations.

[0023] Step S400, using the target laser cutting machine operation data memory library to sequentially perform control strategy analysis on the workpiece equivalent cutting region set, and determine the equivalent cutting region control strategy parameter set. Specifically, extract data from the target laser cutting machine operation data memory library, for the first region in the workpiece equivalent cutting region set, according to its geometric shape, cutting size and material properties and other characteristics, search the memory library for the operation data of similar regions and compare and match, then disassemble the workpiece cutting control target, build the workpiece cutting effect fitness function with indicators such as cutting accuracy and speed, then analyze the regional cutting characteristics and build a strategy analysis algorithm list, select a suitable algorithm according to the characteristic information to determine the equivalent region control strategy algorithm set, then determine the equivalent region cutting strategy parameter threshold according to the data memory library, use the fitness function to preliminarily search and evaluate to obtain the preliminary strategy parameter fitness, finally use the algorithm set and the preliminary fitness to iteratively optimize the threshold to meet the preset conditions to determine the current region equivalent cutting region control strategy parameter set, and then repeat the operation for the remaining regions until the parameter sets of all regions are determined.

[0024] In a possible implementation, the target laser cutting machine operation data memory is used to sequentially perform control strategy analysis on the workpiece equivalent cutting area set, and the equivalent cutting area control strategy parameter set is determined. Step S400 further includes step S410, disassembling and analyzing the workpiece cutting control target, obtaining the workpiece cutting evaluation index set, and fitting and constructing the workpiece cutting effect fitness function based on the workpiece cutting evaluation index set. Specifically, the workpiece cutting control target is disassembled and analyzed. The cutting control target is multi-dimensional, covering aspects such as cutting accuracy, cutting speed, cutting surface roughness, and the size of the heat affected zone during the cutting process. For example, in the cutting of precision parts in the aerospace field, the cutting accuracy requirements are extremely high, and need to be accurate to the micron level to ensure the assembly accuracy and performance of the parts; while in the cutting of some building decoration materials, the cutting speed may be more critical because a large amount of material needs to be processed quickly. Through detailed analysis of different aspects, a workpiece cutting evaluation index set is obtained. Based on the index set, a mathematical modeling method is used to fit and construct a workpiece cutting effect fitness function. The function takes indicators such as cutting accuracy, speed, roughness and heat-affected zone as variables, and sets different weights to reflect the relative importance of each indicator in the overall cutting effect. For example, for high-precision part cutting, the weight of cutting accuracy may be set higher, while for rough processing scenarios with relatively low surface quality requirements, the weight of cutting speed can be appropriately increased. The constructed fitness function can quantitatively evaluate the cutting effect under different control strategies, providing a clear evaluation standard for subsequent strategy parameter optimization.

[0025] Step S420, performing cutting characteristic analysis on the equivalent cutting region set of the workpiece, and obtaining an equivalent region cutting characteristic information set. Specifically, performing cutting characteristic analysis on the equivalent cutting region set of the workpiece. For each equivalent cutting region, studying its material characteristics, including the type of material (metal or non-metal), the physical properties of the material (such as hardness, melting point, thermal conductivity, etc.). For example, for high-hardness metal materials, such as tungsten alloy, it is difficult to cut, requiring higher laser energy and slower cutting speed; while for low-melting point materials, such as tin, the laser energy needs to be precisely controlled during the cutting process to prevent excessive melting. At the same time, the influence of the geometric shape of the analysis area on the cutting is analyzed. For example, when cutting a circular area, the laser head needs to move in a circular motion, which puts forward special requirements for the planning of the cutting trajectory and the dynamic adjustment of the cutting speed; complex polygonal areas need to consider the cutting strategy at the corners to avoid incomplete cutting or overburning. The size of the analysis area, the larger area may need to adjust the laser spot size and power distribution to ensure uniform cutting quality of the entire area. Through analysis, the equivalent area cutting characteristic information set is obtained to provide a basis for selecting a suitable control strategy algorithm.

[0026] Step S430, construct a strategy analysis algorithm list, and perform matching analysis and selection on the equivalent region cutting characteristic information set based on the strategy analysis algorithm list to determine the equivalent region control strategy algorithm set. Specifically, a strategy analysis algorithm list is constructed, and the list contains a variety of algorithms suitable for laser cutting control strategy analysis, such as genetic algorithm, particle swarm optimization algorithm, simulated annealing algorithm, etc. These algorithms have their own characteristics. The genetic algorithm has a strong global search capability and can find the optimal solution in a large parameter space, but the computational complexity is relatively high; the particle swarm optimization algorithm has a fast convergence speed and is suitable for situations where there is a certain understanding of the parameter variation range; the simulated annealing algorithm performs well when dealing with problems with multiple local optimal solutions. Based on the strategy analysis algorithm list, the equivalent region cutting characteristic information set is matched and analyzed and selected. For example, if the equivalent region is a region with a complex shape, variable material properties and extremely high cutting accuracy requirements, then the genetic algorithm may be a more appropriate choice because it can comprehensively search for the optimal cutting strategy parameters in a complex parameter space; while for a region with a relatively simple shape, relatively stable material properties and high cutting speed requirements, the particle swarm optimization algorithm can quickly determine the appropriate parameter combination. Through matching analysis, the equivalent region control strategy algorithm set is determined to ensure that the most suitable algorithm can be used to optimize the strategy parameters for different equivalent cutting regions.

[0027] Step S440, using the equivalent area control strategy algorithm set and the workpiece cutting effect fitness function, based on the target laser cutting machine operation data memory library, respectively, the workpiece equivalent cutting area set is optimized for strategy parameters, and the equivalent cutting area control strategy parameter set is determined. Specifically, using the equivalent area control strategy algorithm set and the workpiece cutting effect fitness function, based on the target laser cutting machine operation data memory library, respectively, the workpiece equivalent cutting area set is optimized for strategy parameters. From the target laser cutting machine operation data memory library, historical cutting data similar to the current equivalent cutting area is extracted, and the threshold of the equivalent area cutting strategy parameter is determined based on the data, that is, the approximate value range of parameters such as laser power, cutting speed, focus position, and auxiliary gas flow rate is determined. For example, for an equivalent cutting area of ​​a certain material and shape, the data in the memory library shows that the laser power may be between 800 and 1200 watts and the cutting speed may be between 1 and 3 meters per minute. The range is used as the initial strategy parameter search range. Then, the workpiece cutting effect fitness function is used to perform a preliminary search and evaluation within the threshold of the equivalent area cutting strategy parameter. Several groups of parameter combinations are selected and substituted into the fitness function to calculate their function values ​​to obtain the fitness of the equivalent area preliminary strategy parameters, so as to understand the advantages and disadvantages of these initial parameter combinations. Finally, the equivalent area control strategy algorithm set and the equivalent area preliminary strategy parameter fitness are used to iteratively evaluate and optimize the equivalent area cutting strategy parameter threshold. During the iteration process, the algorithm continuously adjusts the parameter combination according to the value of the fitness function, gradually narrowing the search range until the preset iteration conditions are met, such as reaching the predetermined number of iterations, the fitness function value converges to a certain accuracy, or finding a parameter combination that meets the specific cutting effect requirements, etc., to determine the equivalent cutting area control strategy parameter set, and obtain the optimal control strategy parameter combination for each equivalent cutting area, so as to achieve efficient and accurate laser cutting.

[0028] In a possible implementation, the equivalent area control strategy algorithm set and the workpiece cutting effect fitness function are used, and the strategy parameters of the workpiece equivalent cutting area set are optimized based on the target laser cutting machine operation data memory library, and the equivalent cutting area control strategy parameter set is determined. Step S440 further includes step S441, based on the target laser cutting machine operation data memory library, the strategy parameters of the workpiece equivalent cutting area set are analyzed, and the equivalent area cutting strategy parameter threshold is obtained. Specifically, the target laser cutting machine operation data memory library is analyzed. For each area in the workpiece equivalent cutting area set, the historical cutting task data similar to it in the memory library is sorted. The data covers various control strategy parameters used in the past when cutting similar geometric shapes, the same or similar materials, and workpieces of similar cutting sizes, such as the setting range of laser power, the value range of cutting speed, the adjustment range of focus position, and the size of auxiliary gas flow. By analyzing and summarizing the data, a more reasonable equivalent area cutting strategy parameter threshold for the current equivalent cutting area is determined. For example, if the current workpiece equivalent cutting area is a stainless steel circular area with a thickness of 6 mm, the task data of previous cutting of similar stainless steel circular areas with a thickness between 5 and 7 mm is extracted from the memory bank. After statistical analysis, it is concluded that the laser power may be more appropriate between 1200 and 1500 watts, and the cutting speed is approximately in the range of 1.5 to 2.5 meters per minute. The cutting strategy parameter threshold of this area is preliminarily determined, providing a well-founded parameter range limitation for subsequent search and evaluation.

[0029] Step S442, using the workpiece cutting effect fitness function to perform a preliminary search and evaluation within the threshold of the equivalent area cutting strategy parameter, and obtain the fitness of the equivalent area preliminary strategy parameter. Specifically, after determining the threshold of the equivalent area cutting strategy parameter, use the pre-constructed workpiece cutting effect fitness function to carry out a preliminary search and evaluation within the threshold range. Substitute different parameter combinations within the threshold range into the fitness function in turn for calculation. For example, within the threshold range of the above-mentioned laser power and cutting speed, select multiple groups of different power and speed combinations, such as (1200 watts, 1.5 meters / minute), (1300 watts, 2 meters / minute), etc., and substitute the combination into the fitness function with cutting accuracy, cutting surface roughness, cutting speed, and heat-affected zone as variables. Through the calculation of the fitness function, the fitness of the equivalent area preliminary strategy parameter corresponding to each group of parameter combinations is obtained. The fitness value intuitively reflects the degree of pros and cons of the group of parameter combinations in achieving the cutting goal. For example, a high fitness value is obtained after a set of parameter combinations are substituted, indicating that under this parameter setting, the cutting accuracy is high, the cutting surface roughness is low, the cutting speed is fast, and the heat-affected zone is small. Otherwise, it means that this parameter combination is insufficient in some cutting effect indicators, thus providing initial evaluation information and screening basis for further iterative optimization.

[0030] Step S443, adopt the equivalent region control strategy algorithm set and the equivalent region preliminary strategy parameter fitness, iteratively evaluate and optimize the equivalent region cutting strategy parameter threshold, until the preset iteration condition is met, and the equivalent cutting region control strategy parameter set is determined. Specifically, adopt the previously selected equivalent region control strategy algorithm set and the obtained equivalent region preliminary strategy parameter fitness, iteratively evaluate and optimize the equivalent region cutting strategy parameter threshold. Taking the genetic algorithm as an example, a plurality of parameter combinations randomly generated within the threshold range are used as the initial population, each parameter combination is regarded as an individual, and its fitness value is used as the fitness evaluation index of the individual. According to the selection, crossover and mutation operation rules of the genetic algorithm, individuals with higher fitness are selected in each generation of population to perform crossover and mutation operations to generate a new population. The individuals in the new population are substituted into the fitness function again to calculate the fitness value, and the cycle is iterated. In the iterative process, the best fitness value in each generation of population is continuously compared with the preset iteration condition. The preset iteration conditions include reaching a predetermined number of iterations, such as 100 iterations; or the fitness function value converges to a certain accuracy, such as the change in the best fitness value of the population for 10 consecutive generations is less than 0.01. When the preset iteration conditions are met, the best parameter combination in the population is the determined equivalent cutting area control strategy parameter set. The final parameter set can optimize the cutting effect in the current equivalent cutting area cutting task, and maximize the cutting speed, reduce the roughness of the cutting surface and reduce the heat affected zone while ensuring the cutting accuracy, thereby providing reliable control strategy parameter support for efficient and accurate laser cutting operations.

[0031] Step S500, based on the equivalent cutting area control strategy parameter set, the target laser cutting machine is controlled to perform cutting feedback detection on the target workpiece to obtain a cutting area perception feedback data stream. Specifically, according to the equivalent cutting area control strategy parameter set, the laser power, cutting head movement speed, focus position and auxiliary gas flow rate of the target laser cutting machine are accurately set and then the cutting is started. During cutting, feedback detection is performed with the help of the power sensor installed on the laser generator, the speed and position sensor of the cutting head, the temperature and image sensor near the cutting area, etc. The power sensor at the laser generator monitors the actual power output value and deviation, the speed sensor of the cutting head captures speed fluctuations, the position sensor tracks the position deviation, the temperature sensor monitors the cutting temperature change, and the image sensor captures the real-time image of the cutting surface. These laser power, cutting head status, cutting area environment and other information are integrated according to a specific time series and data format to obtain a cutting area perception feedback data stream.

[0032] Step S600, based on the cutting area perception feedback data stream, the equivalent cutting area control strategy parameter set is integrated and optimized, the cutting machine optimization control strategy parameter set is determined, and the target laser cutting machine is optimized and controlled by the cutting machine optimization control strategy parameter set. Specifically, the cutting area perception feedback data stream is preprocessed, and the data noise, missing and abnormal values ​​are processed and standardized by filtering algorithms, image enhancement and other means, and key features such as temperature features and image features are extracted; the equivalent area strategy parameter optimization target set is determined based on feature analysis, and multiple target constraints are set by analyzing the cutting surface roughness, heat affected zone and cutting efficiency; then, the equivalent cutting area control strategy parameter set is analyzed according to the optimization target, and multiple equivalent area optimization strategy parameter sets are generated by random mutation and other methods according to the optimization direction; finally, the idea of ​​ensemble learning is used to evaluate the performance of each parameter set with indicators such as cutting surface roughness, and the optimal parameter set is determined as the cutting machine optimization control strategy parameter set by integrated methods such as weighted average, which is applied to the target laser cutting machine to achieve strategy optimization control and continuous cycle optimization.

[0033] In a possible implementation, based on the cutting area perception feedback data stream, the equivalent cutting area control strategy parameter set is integrated and optimized, the cutting machine optimization control strategy parameter set is determined, and the target laser cutting machine is strategically optimized and controlled by the cutting machine optimization control strategy parameter set. Step S600 further includes step S610, preprocessing and optimizing the cutting area perception feedback data stream, and determining the equivalent area strategy parameter optimization target set. Specifically, preprocessing is performed on the cutting area perception feedback data stream. Since there may be many problems with the data collected by the sensor, such as the laser power sensor data may generate noise due to electromagnetic interference, the cutting surface image captured by the image sensor may be blurred or unevenly illuminated, and the position sensor data may have a slight drift. Therefore, multi-source data processing technology is used for preprocessing. For noise data, a filtering algorithm, such as a low-pass filter, is used to remove high-frequency noise to make the data curve smoother, so as to accurately obtain the true change trend of the laser power. For image data, image enhancement processing is performed, and key features such as the texture and edge of the cutting surface are highlighted by adjusting parameters such as contrast and brightness, so as to more accurately analyze information such as the roughness of the cutting surface. After completing data cleaning and sorting, perform optimization target analysis. Analyze the various data features in the cutting area perception feedback data stream. If the cutting surface roughness data shows that the current cutting surface is relatively rough and exceeds the expected quality standard, then reducing the cutting surface roughness is set as an important optimization goal; if the temperature data shows that the temperature of the heat-affected zone is too high during the cutting process, which may affect the material properties and dimensional accuracy of the workpiece, then reducing the heat-affected zone becomes one of the key optimization directions. At the same time, considering the importance of cutting efficiency to production, we cannot simply pursue the optimization of a certain indicator while ignoring the overall efficiency. For example, while ensuring that the cutting surface roughness is reduced by a certain proportion, the reduction in cutting speed must be controlled within a reasonable range. This will determine the optimization target set of the equivalent area strategy parameters and provide clear direction guidance for subsequent parameter optimization.

[0034] Step S620, based on the equivalent area strategy parameter optimization target set, the equivalent cutting area control strategy parameter set is optimized and analyzed to obtain the equivalent area strategy parameter optimization rule set. Specifically, based on the determined equivalent area strategy parameter optimization target set, the equivalent cutting area control strategy parameter set is optimized and analyzed. Analyze the intrinsic connection between the current control strategy parameters and the optimization target. For example, if the roughness of the cutting surface is to be reduced, it is necessary to study the synergistic relationship between the laser power and the cutting speed. Under normal circumstances, appropriately reducing the cutting speed and fine-tuning the laser power can make the laser energy act more evenly on the cutting surface, thereby improving the roughness. At the same time, the focal position also has an important influence on the cutting effect. If the focal position is inaccurate, the energy distribution of the cutting surface will be uneven, which will affect the roughness and cutting accuracy. Through the correlation analysis between the parameters and the optimization target, the adjustment direction and approximate adjustment range of each parameter are determined, so as to obtain the equivalent area strategy parameter optimization rule set. For example, if the optimization goal is to reduce the roughness of the cutting surface and reduce the heat-affected zone, the rule set may stipulate specific adjustment rules such as reducing the laser power by 5% to 10% on the original basis, reducing the cutting speed by 10% to 15%, and fine-tuning the focus position upward by 0.5 to 1 mm, etc., to provide a basis for subsequent variation optimization.

[0035] Step S630, according to the equivalent area strategy parameter optimization rule set, the equivalent cutting area control strategy parameter set is mutated and optimized to obtain multiple equivalent area optimization strategy parameter sets. Specifically, according to the equivalent area strategy parameter optimization rule set, the equivalent cutting area control strategy parameter set is mutated and optimized. A variety of mutation methods are used to generate multiple equivalent area optimization strategy parameter sets. For example, using a random mutation method, on the laser power parameter, with the original parameter value as the center, several mutation values ​​are randomly generated according to the range set by the optimization rule set. For example, if the original laser power is 1500 watts, the mutation value can be randomly selected between 1350 and 1425 watts according to the rule set; for the cutting speed parameter, random mutation is also performed within the specified range. At the same time, a gradient-based mutation method can also be used to mutate according to the gradient direction of the optimization objective function, so that the mutated parameters are more likely to move towards the optimization target. Through these mutation operations, the various parameters in the original equivalent cutting area control strategy parameter set are changed in a diversified manner, and combined to form multiple equivalent area optimization strategy parameter sets. For example, one equivalent area optimization strategy parameter set may be laser power 1380 watts, cutting speed 1.8 m / min, and focal position 5.2 mm, and another may be laser power 1400 watts, cutting speed 1.7 m / min, and focal position 5.3 mm, etc., providing a rich set of candidate parameters for subsequent integrated optimization analysis.

[0036] Step S640, performing integrated optimization analysis on the multiple equivalent area optimization strategy parameter sets to determine the cutting machine optimization control strategy parameter set. Specifically, performing integrated optimization analysis on multiple equivalent area optimization strategy parameter sets. Using an integrated learning method, the parameter set is regarded as multiple different models or decision schemes. First, for each equivalent area optimization strategy parameter set, the data in the cutting area perception feedback data stream is used to perform performance evaluation. Using indicators such as cutting surface roughness, heat affected zone size, and cutting speed as evaluation criteria, the scores of each parameter set on these indicators are calculated. For example, for a parameter set, by simulating its effect in the cutting process, it is calculated that the cutting surface roughness is 5 microns, the heat affected zone area is 2 square millimeters, and the cutting speed is 2 meters / minute. According to the pre-set weights and evaluation formulas, its comprehensive score is obtained. Then, an integrated method, such as a weighted average method, is used to assign different weights according to the performance scores of each parameter set, and the multiple parameter sets are integrated. Alternatively, a voting method is used. When there are differences in the decisions of multiple parameter sets on certain indicators, the final parameter values ​​are determined by majority vote. Through the integrated optimization analysis method, the optimal parameter set is determined, that is, the cutting machine optimization control strategy parameter set. The final parameter set can achieve precise control of the target laser cutting machine on the basis of meeting multiple target optimization requirements, improve cutting quality, efficiency and stability, and provide a better control strategy for laser cutting operations.

[0037] In a possible implementation, the multiple equivalent area optimization strategy parameter sets are integrated and optimized to determine the cutting machine optimization control strategy parameter set. Step S640 further includes step S641, using the workpiece cutting effect fitness function to evaluate the fitness of the multiple equivalent area optimization strategy parameter sets to obtain the fitness of multiple equivalent area strategy parameters. Specifically, the fitness function of the workpiece cutting effect constructed in advance is used to evaluate the fitness of multiple equivalent area optimization strategy parameter sets. The fitness function uses key indicators such as cutting accuracy, cutting speed, cutting surface roughness, and the size of the heat affected zone during the cutting process as variables. For each equivalent area optimization strategy parameter set, the parameters therein, such as laser power, cutting speed, focal position, etc., are substituted into the fitness function for calculation. For example, if an equivalent area optimization strategy parameter set sets the laser power to 1200 watts, the cutting speed to 2 meters / minute, and the focal position to 3 mm, after the parameters are substituted into the fitness function, the function will analyze the cutting accuracy, cutting surface roughness, and heat affected zone size under the parameter combination, and calculate a fitness value according to the set weight. By performing such calculations on multiple equivalent region optimization strategy parameter sets in turn, the fitness of multiple equivalent region strategy parameters is obtained. The fitness value intuitively reflects the pros and cons of each parameter set in achieving the ideal cutting effect. The higher the fitness value, the closer the parameter set is to the expected target in terms of comprehensive cutting effect.

[0038] Step S642, based on the fitness of the multiple equivalent area strategy parameters, the multiple equivalent area optimization strategy parameter sets are optimized to determine the equivalent area optimization strategy parameter set. Specifically, based on the obtained fitness of the multiple equivalent area strategy parameters, multiple equivalent area optimization strategy parameter sets are optimized. The fitness values ​​of each parameter set are sorted, and some parameter sets with higher fitness values ​​are selected. For example, if there are 10 equivalent area optimization strategy parameter sets, after fitness evaluation, it is found that the fitness values ​​of 3 of the parameter sets are significantly higher than those of other parameter sets. In the optimization process, not only the fitness value is considered, but also the characteristics of each parameter set need to be comprehensively analyzed. For example, although a parameter set has a high fitness value, the laser power it requires may be very close to the maximum power limit of the laser cutting machine, which may cause great pressure on the equipment in practical applications. At this time, it is necessary to carefully consider whether to select the parameter set. Through comprehensive analysis and comparison, one or several relatively optimal equivalent area optimization strategy parameter sets are determined, and the parameter set has certain feasibility and stability while ensuring a good cutting effect.

[0039] Step S643, performing an integrated impact analysis on the equivalent region optimization strategy parameter set to obtain a cutting machine optimization control strategy parameter set. Specifically, performing an integrated impact analysis on the optimal equivalent region optimization strategy parameter set. Considering that in the actual laser cutting process, each equivalent cutting region is not completely independent, and there is a relationship of mutual influence between them. For example, the cutting order of adjacent regions, the heat conduction during the cutting process, etc. will have an impact on the overall cutting effect. By simulating the interaction of different equivalent region optimization strategy parameter sets in the entire workpiece cutting process, the integrated impact is analyzed. For example, when a region is cut quickly with a higher power, it may have a thermal impact on the material properties of the adjacent region, thereby affecting the cutting quality of the adjacent region. According to the integrated impact analysis, the optimal parameter set is further adjusted and optimized. For example, the cutting power of a certain region is appropriately reduced to reduce the thermal impact on the adjacent region, and the cutting speed of other regions is adjusted to compensate for the loss of overall cutting efficiency. After integrated impact analysis and optimization, the cutting machine optimization control strategy parameter set is finally determined. The parameter set can achieve optimal control of the entire target laser cutting machine on the basis of analyzing the mutual influence of each equivalent cutting region, so as to achieve the best cutting effect and the highest production efficiency.

[0040] In a possible implementation, an integrated impact analysis is performed on the equivalent area optimization strategy parameter set to obtain a cutting machine optimization control strategy parameter set, and step S643 further includes step S6431, respectively performing cutting impact analysis on each cutting area in the equivalent cutting area set of the workpiece to obtain cutting area impact level information. Specifically, cutting impact analysis is performed on each cutting area in the equivalent cutting area set of the workpiece. Since each area of ​​the workpiece does not exist in isolation during the cutting process, there are various forms of mutual influence between them. For example, in terms of cutting depth, when the cutting depth of an area is large, the stress distribution inside the workpiece may be changed, thereby affecting the cutting stability of the adjacent area. If a deep area is cut first, the material in the surrounding area may be deformed, resulting in difficulty in accurately controlling the cutting path in the subsequent cutting area. From the perspective of the cutting path, if the cutting paths of adjacent areas have intersecting or connecting parts, the cutting accuracy and edge quality of the first cutting area will affect the connection effect of the cutting starting point and cutting edge of the subsequent area. Through a comprehensive analysis of factors such as cutting depth and cutting path, the degree of influence of each area on other areas is determined, thereby obtaining cutting area impact level information. For example, in an area located in the center of a workpiece with a complex structure, any slight change in the cutting process may produce a chain reaction on multiple surrounding areas, so the impact level of this area is higher; while in an area located at the edge with a simple shape, the impact range is relatively small and the impact level is lower.

[0041] Step S6432, based on the cutting area impact level information, cutting correlation impact analysis is performed to determine the cutting area correlation impact factor set. Specifically, based on the cutting area impact level information, cutting correlation impact analysis is performed. The mutual correlations between areas of different impact levels are sorted out in detail to determine the cutting area correlation impact factor set. For example, for the high impact level area, the heat, vibration and material deformation generated during cutting are the main correlation impact factors. When the high impact level area is cut, a large amount of heat released may be conducted to the adjacent low impact level area, changing the physical properties of the material in the low level area, such as reducing the hardness of the material, thereby affecting its cutting difficulty and cutting effect. Vibration may also be transmitted through the structure of the workpiece, interfering with the cutting accuracy of the adjacent area. For the low impact level area, its own cutting parameter adjustment may have little effect on the high impact level area, but the cumulative effect of multiple low impact level areas cannot be ignored. For example, the change of the cutting order of multiple low impact level areas may change the stress distribution of the entire workpiece, thereby indirectly affecting the cutting quality of the high impact level area. By analyzing and summarizing the associated influencing factors, a set of associated influencing factors of the cutting area is constructed, providing a basis for the subsequent weighted integrated analysis.

[0042] Step S6433, based on the set of influencing factors associated with the cutting area, the equivalent area optimization strategy parameter set is subjected to an impact weighted integrated analysis to obtain the cutting machine optimization control strategy parameter set. Specifically, the equivalent area optimization strategy parameter set is subjected to an impact weighted integrated analysis based on the set of influencing factors associated with the cutting area to obtain the cutting machine optimization control strategy parameter set. For each equivalent area optimization strategy parameter set, the importance weights of each parameter under the influence of different cutting area associations are analyzed. For example, for the laser power parameter, if a certain area is greatly affected by the heat conduction of the adjacent high-impact level area, then in the parameter set of the area, the weight of the laser power needs to be adjusted according to the degree of thermal influence. If the thermal influence may cause excessive melting of the material, the weight of the laser power needs to be appropriately reduced to avoid a decrease in cutting quality. Similarly, for the cutting speed parameter, if a certain area is greatly affected by vibration and the cutting speed needs to be reduced to improve the cutting accuracy, the weight of the cutting speed parameter will also change accordingly. By adjusting the weights and integrating the analysis of each parameter under different association influences, the overall cutting effect of the equivalent cutting area set of the entire workpiece is comprehensively analyzed, and finally the optimization control strategy parameter set suitable for the entire laser cutting machine is determined. The parameter set can achieve precise control of the target laser cutting machine on the basis of fully considering the mutual influence between regions, improve the cutting quality and efficiency, and ensure that the cutting process of the entire workpiece reaches the optimal state.

[0043] The embodiment of the present application uses data mining technology to construct the operation data space of the laser cutting machine to obtain the cutting design information of the target laser cutting machine and the workpiece. The operation data is matched and retrieved according to the attribute information of the laser cutting machine, and an operation data memory is established. The workpiece is segmented into equivalent areas based on the cutting design information to obtain an equivalent cutting area set. The control strategy analysis of the equivalent cutting area is performed using the operation data memory to determine the control strategy parameter set. The laser cutting machine is subjected to cutting feedback detection using the control strategy parameter set to obtain the perception feedback data stream. The control strategy parameter set is optimized and analyzed based on the feedback data stream to determine the optimized control strategy parameter set, and the strategy optimization control is implemented on the laser cutting machine, thereby achieving the technical effect of improving the control strategy optimization accuracy and maintaining stable cutting quality when facing different types of workpieces and diverse cutting conditions.

[0044] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A control strategy optimization method for a laser cutting machine, characterized in that: The method comprises: The laser cutting machine operation data space is constructed through data mining technology, and the cutting design information of the target laser cutting machine and the target workpiece is obtained; According to the attribute information of the target laser cutting machine, the operation data space of the laser cutting machine is matched and searched to obtain the operation data memory library of the target laser cutting machine; Performing equivalent region segmentation on the target workpiece based on the cutting design information to obtain a workpiece equivalent cutting region set; Using the target laser cutting machine operation data memory library to sequentially perform control strategy analysis on the workpiece equivalent cutting area set, and determine the equivalent cutting area control strategy parameter set; Based on the equivalent cutting area control strategy parameter set, the target laser cutting machine is controlled to perform cutting feedback detection on the target workpiece to obtain a cutting area perception feedback data stream; Based on the cutting area perception feedback data stream, the equivalent cutting area control strategy parameter set is integrated and optimized to determine the cutting machine optimization control strategy parameter set, and the target laser cutting machine is strategically optimized and controlled through the cutting machine optimization control strategy parameter set.

2. The control strategy optimization method for a laser cutting machine according to claim 1, characterized in that: The step of obtaining a target laser cutting machine operation data memory library comprises: Acquire attribute factor information of the laser cutting machine, wherein the attribute factor information of the laser cutting machine includes the type of cutting machine, structural specifications, power level, and cutting material; According to the attribute factor information of the laser cutting machine, attribute classification encoding is performed on the operation data space of the laser cutting machine to obtain a cutting machine attribute encoding set; Clustering and dividing the laser cutting machine operation data space based on the cutting machine attribute coding set to obtain a laser cutting machine operation clustering data set; According to the attribute information of the target laser cutting machine and the laser cutting machine operation clustering data set, attribute matching retrieval is performed to obtain a target laser cutting machine operation data memory library.

3. The control strategy optimization method for a laser cutting machine according to claim 1, characterized in that: The step of obtaining a workpiece equivalent cutting region set comprises: Perform three-dimensional modeling based on the cutting design information to establish a three-dimensional model of the target workpiece; Extracting segmentation indexes from the workpiece cutting application information to obtain a workpiece segmentation index set, wherein the workpiece segmentation index set includes geometric shape, cutting size, and material properties; Based on the workpiece segmentation index set, the target workpiece three-dimensional model is sequentially spatially segmented and marked to obtain a workpiece index segmentation region set and a region segmentation index label set; The workpiece index segmentation region set is clustered and integrated according to the region segmentation index label set to obtain the workpiece equivalent cutting region set.

4. The control strategy optimization method for a laser cutting machine according to claim 1, characterized in that: The step of determining the equivalent cutting area control strategy parameter set includes: Disassembling and analyzing the workpiece cutting control target to obtain a workpiece cutting evaluation index set, and fitting and constructing a workpiece cutting effect fitness function based on the workpiece cutting evaluation index set; Performing cutting characteristic analysis on the workpiece equivalent cutting region set to obtain an equivalent region cutting characteristic information set; Constructing a strategy analysis algorithm list, and performing matching analysis and selection on the equivalent region cutting characteristic information set based on the strategy analysis algorithm list to determine the equivalent region control strategy algorithm set; The equivalent area control strategy algorithm set and the workpiece cutting effect fitness function are adopted, and the strategy parameters of the workpiece equivalent cutting area set are optimized based on the target laser cutting machine operation data memory library to determine the equivalent cutting area control strategy parameter set.

5. The control strategy optimization method for a laser cutting machine according to claim 4, characterized in that: The step of determining the equivalent cutting area control strategy parameter set includes: Based on the target laser cutting machine operation data memory library, the strategy parameters of the workpiece equivalent cutting area set are respectively analyzed to obtain the equivalent area cutting strategy parameter threshold; Using the workpiece cutting effect fitness function to perform a preliminary search and evaluation within the equivalent region cutting strategy parameter threshold, to obtain the equivalent region preliminary strategy parameter fitness; The equivalent region control strategy algorithm set and the fitness of the equivalent region preliminary strategy parameters are used to iteratively evaluate and optimize the equivalent region cutting strategy parameter threshold until the preset iteration condition is met, thereby determining the equivalent cutting region control strategy parameter set.

6. The control strategy optimization method for a laser cutting machine according to claim 5, characterized in that: The step of determining the cutting machine optimization control strategy parameter set comprises: Preprocessing and optimizing the target data stream of the sensing feedback of the cutting area to determine an optimization target set of equivalent area strategy parameters; Based on the equivalent area strategy parameter optimization target set, the equivalent cutting area control strategy parameter set is optimized and analyzed to obtain an equivalent area strategy parameter optimization rule set; Performing variation optimization on the equivalent cutting region control strategy parameter set according to the equivalent region strategy parameter optimization rule set to obtain a plurality of equivalent region optimization strategy parameter sets; An integrated optimization analysis is performed on the multiple equivalent region optimization strategy parameter sets to determine a cutting machine optimization control strategy parameter set.

7. The control strategy optimization method for a laser cutting machine according to claim 6, characterized in that: The step of determining the cutting machine optimization control strategy parameter set comprises: Using the workpiece cutting effect fitness function to evaluate the fitness of the multiple equivalent region optimization strategy parameter sets, and obtain the fitness of multiple equivalent region strategy parameters; Optimizing the multiple equivalent area optimization strategy parameter sets based on the fitness of the multiple equivalent area strategy parameters to determine the equivalent area optimization strategy parameter set; An integrated impact analysis is performed on the equivalent region optimization strategy parameter set to obtain a cutting machine optimization control strategy parameter set.

8. The control strategy optimization method for a laser cutting machine according to claim 7, characterized in that: The obtaining of the cutting machine optimization control strategy parameter set comprises: Performing cutting impact analysis on each cutting area in the equivalent cutting area set of the workpiece to obtain cutting area impact level information; Perform cutting-related impact analysis based on the cutting-area impact level information to determine a set of cutting-area-related impact factors; Based on the cutting area associated influencing factor set, an impact weighted integrated analysis is performed on the equivalent area optimization strategy parameter set to obtain the cutting machine optimization control strategy parameter set.

Images