Automatic deslagging control method and system for laser cutting

Abstract

The invention relates to an automatic deslagging control method for laser cutting. The method comprises the following steps: acquiring basic data of metal to be cut; inputting the metal basic data into a preset working data matching model to match corresponding laser working parameters; detecting the falling condition of the metal slag when the metal slag falls into the collecting tank to generate metal slag falling data; a first slag removal strategy is generated according to the metal slag falling data, and a first slag removal control instruction is generated according to the first slag removal strategy and used for conducting slag removal during laser cutting; detecting whether the metal slag on the surface of the collecting tank has a residue condition or not, generating metal slag residue data, and generating a slag removal adjustment instruction if the metal slag has the residue condition; and generating a collecting tank surface slag removal strategy according to the metal slag residue data, and generating a second slag removal control instruction according to the collecting tank surface slag removal strategy to remove the metal slag remaining on the surface of the collecting tank. The laser cutting slag removal device has the effect of improving the slag removal efficiency in laser cutting.

Description

Technical Field

[0001] The present invention relates to the technical field of laser cutting, and in particular to an automatic slag removal control method and system for laser cutting. Background Art

[0002] Laser cutting technology is widely used in the metal industry, with advantages such as high precision, high efficiency and non-contact. Laser cutting uses a high-energy (high-temperature) laser beam to melt, gasify and evaporate metal materials to achieve a fast and precise cutting process. However, in the metal cutting process, the generation of metal slag has become a common problem.

[0003] Metal slag is composed of oxides, residual impurities and melted metal particles of metal materials during the laser cutting process. At present, the removal of metal slag mainly relies on manual operation, such as using physical methods such as scrapers, wire brushes or high-pressure airflow for removal. However, this manual slag removal method requires a lot of manpower and time, and has low efficiency. Manual operation is easily affected by the operator's technical level and fatigue, and it is difficult to ensure consistent slag removal quality, which reduces the slag removal efficiency in laser cutting. Therefore, it needs to be improved. Summary of the invention

[0004] In order to improve the slag removal efficiency in laser cutting, the present application provides an automatic slag removal control method and system for laser cutting.

[0005] In the first aspect, the above-mentioned invention objective of the present application is achieved through the following technical solutions: An automatic slag removal control method for laser cutting, the method comprising the steps of: Acquire basic data of metal to be cut, wherein the basic data includes metal type and metal shape; Inputting the metal basic data into a preset working data matching model to match corresponding laser working parameters; Detecting the falling condition of the metal slag when it falls into the collecting tank to generate metal slag falling data, wherein the falling data includes the falling rate, the falling position and the shape of the metal slag; Generating a first slag removal strategy according to the metal slag falling data, wherein the slag removal strategy includes a slag removal method, a slag removal start time and an interval, and generating a first slag removal control instruction according to the first slag removal strategy for performing slag removal during laser cutting; Detect whether there is any residual metal slag on the surface of the collecting tank and generate residual metal slag data. If there is any residual metal slag, generate a slag removal adjustment instruction; A slag removal strategy for the surface of the collecting tank is generated according to the metal slag residual data, and a second slag removal control instruction is generated according to the slag removal strategy for the surface of the collecting tank to remove the metal slag remaining on the surface of the collecting tank.

[0006] By adopting the above technical scheme, the first slag removal strategy and control instructions are generated according to the metal slag falling data, and the metal slag generated in the cutting process is removed in time to prevent its influence on the cutting quality and equipment performance. Compared with the existing manual removal of metal slag in laser cutting, this scheme improves the timeliness and intelligence of metal slag removal, improves the slag removal efficiency in laser cutting, and reduces labor costs. By detecting the residual metal slag and generating slag removal adjustment instructions, the problem of metal slag residue is discovered and dealt with in time to ensure the continuity and quality of the cutting process, and the metal slag on the surface of the collecting trough is cleaned in time to avoid excessive metal residue adhering to the surface of the collecting trough and making it difficult to clean, thereby improving the environmental cleanliness during laser cutting and improving the quality of laser cutting.

[0007] In a preferred example, the present application may be further configured as follows: before the step of inputting the metal basic data into a preset working data matching model to match the corresponding laser working parameters, the step includes: Acquire historical laser working parameters and historical metal basic data, and form a mapping relationship between each of the laser working parameters and the metal basic data to construct a working database; Obtaining the cutting efficiency corresponding to the laser working parameters and inputting it into the working database, and establishing a mapping relationship between the cutting efficiency and the laser working parameters in the working database; The working data matching model matches corresponding laser working parameters according to expected cutting efficiency based on the working database.

[0008] By adopting the above technical solution, historical laser working parameters and metal basic data are collected and organized to build a working database, which provides a reference and basis for subsequent working data matching, improves the accuracy and efficiency of parameter matching, establishes a mapping relationship between laser working parameters and cutting efficiency and stores it in the working database, understands the cutting efficiency under different parameter settings, and provides a basis for subsequent working data matching and efficiency optimization. Through the working data matching model, the corresponding laser working parameters can be quickly and accurately matched according to the expected cutting efficiency, improves cutting efficiency and quality, reduces the time and cost of parameter adjustment, and improves the working efficiency of laser cutting.

[0009] In a preferred example, the present application can be further configured as follows: in the step of detecting the falling condition of the metal slag when it falls into the collection tank to generate the metal slag falling data, the steps are as follows: Acquire a metal slag drop image in a preset unit area to extract the metal slag drop quantity characteristics, drop point characteristics and metal slag shape characteristics in the unit area; Constructing a three-dimensional model of the metal slag based on the falling quantity characteristics, falling point characteristics and metal slag shape characteristics of the metal slag; Calculating the falling rate of the metal slag based on the change of the three-dimensional model of the metal slag; The metal slag dropping data is generated based on the metal slag three-dimensional model and the dropping rate of the metal slag.

[0010] By adopting the above technical scheme, continuous three-dimensional models of metal slag are compared, the changes in the position and shape of the metal slag are calculated, and the falling rate of the metal slag is derived in combination with the time information. The average falling speed of the metal slag is calculated according to the position change and time interval of the metal slag. By calculating the falling rate of the metal slag, the movement law and falling speed of the metal slag are calculated. By generating the metal slag falling data, the falling situation of the metal slag is quantitatively recorded, providing accurate reference and basis for subsequent slag removal control and data analysis.

[0011] In a preferred example, the present application can be further configured as follows: in the step of generating a first slag removal strategy according to the metal slag falling data, the slag removal strategy includes a slag removal method, a slag removal start time and an interval, and generating a first slag removal control instruction according to the first slag removal strategy for slag removal during laser cutting, the steps include the following: Analyze the distribution of metal slag in the falling process according to the falling point characteristics in the metal slag three-dimensional model to determine the slag removal location; Analyze the metal slag falling strength according to the metal slag falling quantity characteristics and the metal slag shape characteristics in the metal slag three-dimensional model to determine the slag removal strength; A first slag removal strategy is generated based on the slag removal location and the slag removal intensity, wherein the working range of the slag removal machine is determined according to the slag removal location, the type of the slag removal machine is determined according to the slag removal intensity, and the start-up time and interval of the slag removal machine are determined according to the drop rate of the metal slag.

[0012] By adopting the above technical scheme, the appropriate slag removal intensity is determined according to the actual situation, excessive or insufficient slag removal operations are avoided, the slag removal effect and work quality are improved, and a reasonable slag removal plan is formulated according to the slag removal site, slag removal intensity and metal slag falling rate to improve the slag removal efficiency and work stability and reduce the interference of metal slag on the cutting process.

[0013] In a preferred example, the present application can be further configured as follows: in the step of detecting whether there is residual metal slag on the surface of the collecting tank and generating metal slag residual data, the steps are as follows: Acquire image data of the surface of the collecting tank, and record historical image data of the surface of the collecting tank based on a timestamp to build a collection tank surface image database; Analyzing whether there is any unremoved metal slag residue on the surface of the collecting tank based on the collecting tank surface image database, and generating a first judgment result; Acquire airflow data on the surface of the collecting tank, detect whether the airflow data is abnormal, and generate a second judgment result; A metal slag residue report is generated based on the first judgment result and the second judgment result, and metal slag residue data is generated based on the metal slag residue report.

[0014] By adopting the above technical solution, the image database of the collecting tank surface is analyzed to identify and determine whether there is any metal slag residue that has not been removed, and a first judgment result is generated based on the analysis result, that is, it is determined whether there is any metal slag residue on the collecting tank surface. Through the analysis of the image database, automatic detection and judgment of the metal slag residue can be achieved, which improves the accuracy and efficiency of detection, reduces the need for manual intervention, and determines whether the airflow on the collecting tank surface is normal. By monitoring and analyzing the airflow data, abnormal airflow on the collecting tank surface can be discovered in time, which provides additional basis for judging the metal slag residue and improves the automatic monitoring capability of the system.

[0015] In a preferred example, the present application may be further configured as follows: after the step of generating a metal slag residue report based on the first judgment result and the second judgment result, and generating metal slag residue data based on the metal slag residue report, the following steps are included: Extracting the metal slag residue point characteristics and metal slag residue quantity characteristics in the metal slag residue report; Constructing a slag removal optimization database according to the metal slag residual point characteristics and the metal slag quantity characteristics; The residual point characteristics and the amount of metal slag in the slag removal optimization database are respectively associated with the first slag removal strategy, and a preset slag removal optimization model analyzes the slag removal optimization database based on a machine self-learning algorithm to generate a compensation slag removal strategy, wherein the compensation slag removal strategy is used to optimize the first slag removal strategy; The first slag removal strategy is optimized based on the compensatory slag removal strategy to generate a modified first slag removal strategy, and the modified first slag removal strategy is mapped with the slag removal site and the slag removal intensity corresponding to the first slag removal strategy. The modified first slag removal strategy is used to optimize the slag removal effect corresponding to the slag removal site and the slag removal intensity to reduce metal slag residue.

[0016] By adopting the above technical solution, the slag removal optimization database is analyzed using a machine self-learning algorithm to generate a compensatory slag removal strategy. The compensatory slag removal strategy can optimize the first slag removal strategy according to different situations of residual points and the amount of metal slag, thereby improving the removal effect of metal slag during the falling process and reducing the residue of metal slag caused by insufficient removal.

[0017] In a preferred example, the present application can be further configured as follows: the machine self-learning algorithm is a random forest self-learning algorithm.

[0018] By adopting the above technical solutions, the random forest self-learning algorithm can reduce the overfitting problem of a single decision tree and improve the overall prediction accuracy by combining multiple decision trees. It can handle high-dimensional data and large-scale data sets and has a lower generalization error. The random forest has good robustness to missing values ​​and outliers. It can automatically handle missing values, and during the training process, since each decision tree is built based on random samples and features, it has less impact on outliers. The random forest can evaluate the importance of features by calculating the frequency and importance of each feature in the decision tree. Since each decision tree in the random forest can be built independently, it can be easily parallelized, which makes the training and prediction speed of the random forest on large-scale data sets faster. When constructing each decision tree, the random forest reduces the risk of overfitting by randomly selecting samples and features.

[0019] In the second aspect, the above invention objective of the present application is achieved through the following technical solutions: An automatic slag removal control device for laser cutting, the device comprising: a metal basic data acquisition module, used to acquire the basic data of the metal to be cut, the basic data of the metal including the metal type and the metal shape; A working data matching module, used for inputting the metal basic data into a preset working data matching model to match corresponding laser working parameters; A metal slag drop detection module, used to detect the drop of the metal slag when it falls into the collection tank, so as to generate metal slag drop data, wherein the drop data includes the metal slag drop rate, drop position and metal slag shape; A first slag removal strategy generating module, used to generate a first slag removal strategy according to the metal slag falling data, wherein the slag removal strategy includes a slag removal method, a slag removal start time and an interval, and to generate a first slag removal control instruction according to the first slag removal strategy for slag removal during laser cutting; A metal slag residue data generation module is used to detect whether there is metal slag residue on the surface of the collecting tank and generate metal slag residue data. If there is residue, a slag removal adjustment instruction is generated; The collecting tank surface slag removal strategy generation module is used to generate a collecting tank surface slag removal strategy according to the metal slag residual data, and generate a second slag removal control instruction according to the collecting tank surface slag removal strategy for removing the metal slag remaining on the collecting tank surface.

[0020] By adopting the above technical scheme, the first slag removal strategy and control instructions are generated according to the metal slag falling data, and the metal slag generated in the cutting process is removed in time to prevent its influence on the cutting quality and equipment performance. Compared with the existing manual removal of metal slag in laser cutting, this scheme improves the timeliness and intelligence of metal slag removal, improves the slag removal efficiency in laser cutting, and reduces labor costs. By detecting the residual metal slag and generating slag removal adjustment instructions, the problem of metal slag residue is discovered and dealt with in time to ensure the continuity and quality of the cutting process, and the metal slag on the surface of the collecting trough is cleaned in time to avoid excessive metal residue adhering to the surface of the collecting trough and making it difficult to clean, thereby improving the environmental cleanliness during laser cutting and improving the quality of laser cutting.

[0021] On the third aspect, the above-mentioned purpose of the present application is achieved through the following technical solutions: An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned automatic slag removal control method for laser cutting when executing the computer program.

[0022] Fourthly, the above-mentioned purpose of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned automatic slag removal control method for laser cutting are implemented.

[0023] In summary, the present application includes at least one of the following beneficial technical effects: 1. Generate the first slag removal strategy and control instructions according to the metal slag falling data, and remove the metal slag generated in the cutting process in time to prevent it from affecting the cutting quality and equipment performance. Compared with the existing manual removal of metal slag in laser cutting, this solution improves the timeliness and intelligence of metal slag removal, improves the slag removal efficiency in laser cutting, and reduces labor costs. By detecting the residual metal slag and generating slag removal adjustment instructions, the problem of metal slag residue is discovered and handled in time to ensure the continuity and quality of the cutting process. The metal slag on the surface of the collection tank is cleaned in time to avoid excessive metal residue adhering to the surface of the collection tank and making it difficult to clean, thereby improving the environmental cleanliness during laser cutting and improving the quality of laser cutting. 2. Collect and organize historical laser working parameters and metal basic data to build a working database, provide reference and basis for subsequent working data matching, improve the accuracy and efficiency of parameter matching, establish a mapping relationship between laser working parameters and cutting efficiency and store them in the working database, understand the cutting efficiency under different parameter settings, and provide a basis for subsequent working data matching and efficiency optimization. Through the working data matching model, the corresponding laser working parameters can be quickly and accurately matched according to the expected cutting efficiency, improve cutting efficiency and quality, reduce the time and cost of parameter adjustment, and improve the working efficiency of laser cutting; 3. Compare the continuous three-dimensional models of metal slag, calculate the change in the position and shape of the metal slag, and combine the time information to deduce the drop rate of the metal slag. According to the position change and time interval of the metal slag, calculate the average drop speed of the metal slag. By calculating the drop rate of the metal slag, calculate the movement law and drop speed of the metal slag. By generating the metal slag drop data, quantitatively record the drop of the metal slag, and provide accurate reference and basis for subsequent slag removal control and data analysis; 4. Use machine self-learning algorithm to analyze the slag removal optimization database to generate a compensatory slag removal strategy. The compensatory slag removal strategy can optimize the first slag removal strategy according to the different situations of residual points and the amount of metal slag, improve the removal effect of metal slag in the falling process, and reduce the residual metal slag caused by insufficient removal. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a flowchart of the steps of an automatic slag removal control method for laser cutting in one embodiment of the present application; Figure 2 This is a principle block diagram of an automatic slag removal control device for laser cutting in one embodiment of the present application; Figure 3 It is a schematic diagram of an electronic device in an embodiment of the present application.

[0025] Figure Number: 1. Metal basic data acquisition module; 2. Working data matching module; 3. Metal slag drop detection module; 4. First slag removal strategy generation module; 5. Metal slag residual data generation module; 6. Collection tank surface slag removal strategy generation module. DETAILED DESCRIPTION

[0026] The present application is further described in detail below in conjunction with the accompanying drawings.

[0027] In one embodiment, stainless steel is used as the metal to be cut. Figure 1 As shown, the present application discloses an automatic slag removal control method for laser cutting, which specifically includes the following steps: S10: Acquire basic data of the metal to be cut, wherein the basic data includes metal type and metal shape; Specifically, in the embodiment of the present application, the data of the stainless steel plate to be cut is obtained, including the stainless steel material type (such as 304, 316, etc.) and the plate shape (such as rectangular, circular, etc.), length and width. By obtaining the basic metal data, the characteristics and shape of the metal to be cut are understood, which provides a basis for subsequent work data matching and slag removal control.

[0028] S20: inputting the metal basic data into a preset working data matching model to match corresponding laser working parameters; Specifically, the metal basic data of the stainless steel plate is input into the working data matching model. The model matches the appropriate working parameters such as laser power, laser frequency and cutting speed according to different stainless steel material types and plate shapes. Through the working data matching model, the optimal laser working parameters are automatically determined according to the metal basic data to improve cutting efficiency and quality.

[0029] S30: detecting the falling condition of the metal slag when it falls into the collecting tank to generate metal slag falling data, wherein the falling data includes the falling rate, the falling position and the shape of the metal slag; Specifically, sensors and image recognition technology are used to detect the metal slag falling into the collection tank during the cutting process, and data such as the rate, position and shape of the metal slag falling are recorded to understand the generation and falling rules of the metal slag, providing a basis for subsequent slag removal operations.

[0030] S40: generating a first slag removal strategy according to the metal slag falling data, wherein the slag removal strategy includes a slag removal method, a slag removal start time and an interval, and generating a first slag removal control instruction according to the first slag removal strategy for slag removal during laser cutting; Specifically, by generating the first slag removal strategy and control instructions according to the metal slag falling data, the metal slag generated during the cutting process can be removed in time to prevent its impact on the cutting quality and equipment performance. Compared with the existing manual removal of metal slag in laser cutting, this solution improves the timeliness and intelligence of metal slag removal, improves the slag removal efficiency in laser cutting, and reduces labor costs.

[0031] S50: Detect whether there is any metal slag remaining on the surface of the collecting tank and generate metal slag residual data. If there is any metal slag remaining, generate a slag removal adjustment instruction; S60: generating a slag removal strategy on the surface of the collecting tank according to the metal slag residual data, and generating a second slag removal control instruction according to the slag removal strategy on the surface of the collecting tank for removing the metal slag remaining on the surface of the collecting tank.

[0032] Specifically, sensors and image recognition technology are used to detect whether there is any residual metal slag on the surface of the collection tank. If there is any residual metal slag, a slag removal adjustment instruction for the surface of the collection tank is generated to adjust the slag removal strategy or parameters. By detecting the residual metal slag and generating the slag removal adjustment instruction, the problem of residual metal slag can be discovered and handled in a timely manner to ensure the continuity and quality of the cutting process, and the metal slag on the surface of the collection tank can be cleaned in a timely manner to avoid excessive metal residue adhering to the surface of the collection tank and making it difficult to clean, thereby improving the environmental cleanliness during laser cutting and improving the quality of laser cutting.

[0033] Before the step S20: inputting the metal basic data into a preset working data matching model to match corresponding laser working parameters, the following steps are included: S201: Acquire historical laser working parameters and historical metal basic data, and form a mapping relationship between each of the laser working parameters and the metal basic data to construct a working database; Specifically, the working parameters and metal basic data of the laser cutting machines used in the past period of time are collected, such as laser power, laser frequency, cutting speed, stainless steel material type and plate shape, etc. These historical data are classified and sorted according to different laser working parameters and metal basic data to form a working database. By building a working database, historical laser working parameters and metal basic data can be collected and sorted to provide reference and basis for subsequent working data matching, thereby improving the accuracy and efficiency of parameter matching.

[0034] S202: Obtaining the cutting efficiency corresponding to the laser working parameter and inputting it into the working database, and constructing a mapping relationship between the cutting efficiency and the laser working parameter in the working database; Specifically, according to historical data and experimental tests, the cutting efficiency data under different laser working parameters are obtained. In the embodiment of the present application, for example, the cutting efficiency is 90% when the cutting speed is 100 mm / s, and the cutting efficiency is 85% when the cutting speed is 200 mm / s, that is, in the embodiment of the present application, the cutting speed is negatively correlated with the cutting efficiency. A mapping relationship is established between these cutting efficiency data and the corresponding laser working parameters, and stored in the working database. By establishing a mapping relationship between the laser working parameters and the cutting efficiency and storing them in the working database, the cutting efficiency under different parameter settings can be understood, providing a basis for subsequent working data matching and efficiency optimization.

[0035] S203: The working data matching model matches corresponding laser working parameters according to expected cutting efficiency based on the working database.

[0036] Specifically, based on the constructed working database, a working data matching model is developed using a machine learning algorithm or a rule-based reasoning method. The model receives the expected cutting efficiency as input, and matches the laser working parameters suitable for achieving the expected cutting efficiency according to the mapping relationship in the working database.

[0037] Through the working data matching model, the corresponding laser working parameters can be quickly and accurately matched according to the expected cutting efficiency, thereby improving the cutting efficiency and quality, reducing the time and cost of parameter adjustment, and improving the working efficiency of laser cutting.

[0038] In the step of S30: detecting the falling condition of the metal slag when it falls into the collecting tank to generate the metal slag falling data, the following steps are included: S31: acquiring a metal slag falling image in a preset unit area to extract the metal slag falling quantity characteristics, falling point characteristics and metal slag shape characteristics in the unit area; Specifically, in the embodiment of the present application, a high-speed camera or a video camera is used to continuously shoot a preset unit area to obtain an image sequence of metal slag falling. The number of metal slag falling, the falling points and the shape characteristics of the metal slag in the image are extracted through image processing and computer vision technology.

[0039] By acquiring the metal slag falling image and extracting relevant features, the metal slag falling situation can be quantitatively described, providing a data basis for subsequent analysis and modeling.

[0040] S32: constructing a three-dimensional model of the metal slag based on the falling quantity characteristics, falling point characteristics and metal slag shape characteristics of the metal slag; Specifically, according to the acquired metal slag falling images and feature data, a three-dimensional reconstruction technology or a point cloud processing algorithm is used to construct a three-dimensional model of the metal slag. The model includes information such as the shape, size, and position of the metal slag. By constructing a three-dimensional model of the metal slag, the spatial distribution and morphological characteristics of the metal slag can be more accurately described.

[0041] S33: calculating the falling rate of the metal slag based on the change of the three-dimensional model of the metal slag; Specifically, in the embodiment of the present application, by comparing the continuous three-dimensional models of the metal slag, the change in the position and shape of the metal slag is calculated, and the drop rate of the metal slag is derived by combining the time information. According to the position change and time interval of the metal slag, the average falling speed of the metal slag is calculated, and by calculating the drop rate of the metal slag, the movement law and drop speed of the metal slag are calculated.

[0042] S34: Generate metal slag dropping data based on the metal slag three-dimensional model and the metal slag dropping rate.

[0043] According to the three-dimensional model and drop rate of the metal slag, the metal slag drop data is generated, including the drop position, drop time and drop shape of the metal slag. These data can be stored in the database or exported as a file.

[0044] By generating metal slag falling data, the metal slag falling situation is quantitatively recorded, providing accurate reference and basis for subsequent slag removal control and data analysis.

[0045] In S40: generating a first slag removal strategy according to the metal slag falling data, the slag removal strategy including a slag removal method, a slag removal start time and an interval, and generating a first slag removal control instruction according to the first slag removal strategy for slag removal during laser cutting, including the following steps: S41: Analyze the distribution of the metal slag in the falling process according to the falling point characteristics in the metal slag three-dimensional model to determine the slag removal location; By analyzing the drop point characteristics in the 3D model of the metal slag, the metal slag in the dropping process can be identified. According to the distribution and drop characteristics of the metal slag, the appropriate slag removal site, that is, the location where slag removal is required, is determined.

[0046] By analyzing the characteristics of the falling points of metal slag, the location where slag removal is required can be accurately determined, avoiding ineffective slag removal operations in the entire working area, improving slag removal efficiency and saving resources.

[0047] S42: analyzing the metal slag falling strength according to the metal slag falling quantity characteristics and the metal slag shape characteristics in the metal slag three-dimensional model to determine the slag removal strength; Specifically, the falling strength of the metal slag is analyzed according to the falling quantity characteristics and the shape characteristics of the metal slag in the three-dimensional model of the metal slag. For example, according to the quantity and shape characteristics of the metal slag, the density and distribution of the metal slag are evaluated to determine the strength of the slag removal.

[0048] By analyzing the falling strength of metal slag, the appropriate slag removal strength can be determined according to the actual situation, avoiding excessive or insufficient slag removal operations, and improving the slag removal effect and work quality.

[0049] S43: Generate a first slag removal strategy based on the slag removal site and the slag removal intensity, wherein the working range of the slag removal machine is determined according to the slag removal site, the type of the slag removal machine is determined according to the slag removal intensity, and the start-up time and interval of the slag removal machine are determined according to the drop rate of the metal slag.

[0050] Specifically, based on the determined slag removal site and slag removal intensity, a first slag removal strategy is generated. The working range of the slag removal machine is determined according to the slag removal site, that is, the area that the slag removal machine needs to cover. The type of the slag removal machine is determined according to the slag removal intensity. In the embodiment of the present application, an appropriate slag removal nozzle or brush is selected based on the slag removal site and the slag removal intensity. The start-up time and interval of the slag removal machine are determined according to the drop rate of the metal slag to ensure timely removal of the metal slag and maintain work efficiency.

[0051] It is further explained that by generating the first slag removal strategy, a reasonable slag removal plan can be formulated according to the slag removal site, slag removal intensity and metal slag falling rate, thereby improving the slag removal efficiency and working stability and reducing the interference of metal slag on the cutting process.

[0052] In the step S50: detecting whether there is residual metal slag on the surface of the collecting tank and generating metal slag residual data, the following steps are included: S51: Acquire image data of the surface of the collecting tank, and record historical image data of the surface of the collecting tank based on a timestamp to construct a collection tank surface image database; Specifically, a camera or sensor is used to obtain image data of the collection tank surface, and these data are associated with a timestamp to record historical image data of the collection tank surface. These data can be integrated into a database for subsequent analysis and comparison. By building a collection tank surface image database, the historical record and tracking of the collection tank surface status can be achieved.

[0053] S52: analyzing whether there is any metal slag residue on the surface of the collecting tank that has not been removed based on the collecting tank surface image database, and generating a first judgment result; Specifically, the image database of the surface of the collecting tank is analyzed by using image processing algorithms and machine learning technology to identify and determine whether there is any metal slag residue that has not been removed. A first judgment result is generated based on the analysis result, that is, whether there is any metal slag residue on the surface of the collecting tank. Through the analysis of the image database, automatic detection and judgment of the metal slag residue can be achieved, which improves the accuracy and efficiency of detection and reduces the need for manual intervention.

[0054] S53: Acquire airflow data on the surface of the collecting tank, detect whether the airflow data is abnormal, and generate a second judgment result; The airflow data on the surface of the collection tank is obtained by using an airflow sensor or other airflow detection equipment, and the data is analyzed to detect whether there are abnormal conditions, such as airflow blockage or abnormal flow. A second judgment result is generated based on the analysis result, that is, whether the airflow condition on the surface of the collection tank is normal. By monitoring and analyzing the airflow data, the abnormal airflow condition on the surface of the collection tank can be discovered in time, which provides an additional basis for judging the metal slag residue and improves the automatic monitoring capability of the system.

[0055] S54: generating a metal slag residue report based on the first judgment result and the second judgment result, and generating metal slag residue data based on the metal slag residue report; Specifically, a metal slag residue report is generated based on the first and second judgment results, and the report includes information such as the location, quantity, shape, and abnormal airflow of the metal slag residue. Based on the report, metal slag residue data is generated and stored in a database or exported as a file. By generating metal slag residue reports and data, a comprehensive record and analysis of metal slag residue conditions is achieved, providing an important basis for subsequent slag removal control and system optimization.

[0056] After the step of S54: generating a metal slag residue report based on the first judgment result and the second judgment result, and generating metal slag residue data based on the metal slag residue report, the following steps are included: S541: extracting the metal slag residue point characteristics and the metal slag residue quantity characteristics in the metal slag residue report; Specifically, the positional features of the metal slag residue are extracted from the metal slag residue report, such as the coordinate position and shape description of the slag residue points. At the same time, the quantity features of the metal slag residue are extracted, including the quantity and distribution of the slag residue. By extracting the positional features and quantity features of the metal slag residue, the metal slag residue situation is quantitatively described, providing an accurate data basis for subsequent slag removal optimization.

[0057] S542: constructing a slag removal optimization database according to the metal slag residual point characteristics and the metal slag quantity characteristics; Specifically, the residual positional features and quantity features of metal slag are used to construct a slag removal optimization database, and these features are used as key fields of the database and stored in association with other relevant data.

[0058] S543: Associating the residual point feature and the amount of metal slag in the slag removal optimization database with the first slag removal strategy respectively, and a preset slag removal optimization model analyzes the slag removal optimization database based on a machine self-learning algorithm to generate a compensation slag removal strategy, wherein the compensation slag removal strategy is used to optimize the first slag removal strategy; Specifically, the residual point characteristics and the amount of metal slag in the slag removal optimization database are associated with the first slag removal strategy, and the slag removal optimization database is analyzed using a machine self-learning algorithm to generate a compensatory slag removal strategy. The compensatory slag removal strategy can optimize the first slag removal strategy according to different situations of residual points and the amount of metal slag, thereby improving the removal effect of metal slag during the falling process and reducing the residue of metal slag caused by insufficient removal.

[0059] The machine self-learning algorithm uses the random forest self-learning algorithm. By combining multiple decision trees, the random forest can reduce the overfitting problem of a single decision tree and improve the overall prediction accuracy. It can handle high-dimensional data and large-scale data sets with low generalization error; the random forest has good robustness to missing values ​​and outliers. It can automatically handle missing values, and during the training process, since each decision tree is built based on random samples and features, it has less impact on outliers; the random forest can evaluate the importance of features by calculating the frequency and importance of each feature in the decision tree; since each decision tree in the random forest can be built independently, it can be easily parallelized. This makes the training and prediction of random forests on large-scale data sets faster; when constructing each decision tree, the random forest reduces the risk of overfitting by randomly selecting samples and features.

[0060] By generating a compensatory slag removal strategy, the first slag removal strategy can be optimized according to the actual metal slag residue situation to improve the accuracy and efficiency of slag removal.

[0061] S544: Optimize the first slag removal strategy based on the compensation slag removal strategy to generate a modified first slag removal strategy, and map the modified first slag removal strategy to the slag removal site and the slag removal intensity corresponding to the first slag removal strategy, wherein the modified first slag removal strategy is used to optimize the slag removal effect corresponding to the slag removal site and the slag removal intensity, thereby reducing metal slag residue Specifically, the first slag removal strategy is optimized based on the compensation slag removal strategy to generate a revised first slag removal strategy. The slag removal sites and slag removal strengths corresponding to the revised first slag removal strategy and the original first slag removal strategy are mapped to optimize the slag removal effect corresponding to the slag removal sites and slag removal strengths, thereby reducing metal slag residue. By revising the first slag removal strategy, the settings of the slag removal sites and slag removal strengths can be optimized according to the guidance of the compensation slag removal strategy, the occurrence of metal slag residues can be reduced, and the slag removal effect and system stability can be improved.

[0062] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0063] In one embodiment, an automatic slag removal control device for laser cutting is provided, and the automatic slag removal control device for laser cutting corresponds one-to-one with an automatic slag removal control method for laser cutting in the above embodiment. Figure 2 As shown, the automatic slag removal control device for laser cutting comprises: A metal basic data acquisition module 1 is used to acquire the basic data of the metal to be cut, wherein the basic data of the metal includes the metal type and the metal shape; A working data matching module 2, used for inputting the metal basic data into a preset working data matching model to match corresponding laser working parameters; The metal slag drop detection module 3 is used to detect the drop of the metal slag when it falls into the collection tank to generate metal slag drop data, wherein the drop data includes the metal slag drop rate, drop position and metal slag shape; A first slag removal strategy generating module 4 is used to generate a first slag removal strategy according to the metal slag falling data, wherein the slag removal strategy includes a slag removal method, a slag removal start time and an interval, and to generate a first slag removal control instruction according to the first slag removal strategy for slag removal during laser cutting; The metal slag residual data generating module 5 is used to detect whether there is any metal slag residual on the surface of the collecting tank and generate metal slag residual data, and if there is any metal slag residual, generate a slag removal adjustment instruction; The collecting tank surface slag removal strategy generating module 6 is used to generate a collecting tank surface slag removal strategy according to the metal slag residual data, and to generate a second slag removal control instruction according to the collecting tank surface slag removal strategy for removing the metal slag remaining on the collecting tank surface.

[0064] For the specific definition of an automatic slag removal control device for laser cutting, please refer to the definition of an automatic slag removal control method for laser cutting mentioned above, which will not be repeated here. Each module in the above-mentioned automatic slag removal control device for laser cutting can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0065] In one embodiment, an electronic device is provided. The electronic device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The electronic device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store a database. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an automatic slag removal control method for laser cutting is implemented.

[0066] In one embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Acquire basic data of metal to be cut, wherein the basic data includes metal type and metal shape; Inputting the metal basic data into a preset working data matching model to match corresponding laser working parameters; Detecting the falling condition of the metal slag when it falls into the collecting tank to generate metal slag falling data, wherein the falling data includes the falling rate, the falling position and the shape of the metal slag; Generating a first slag removal strategy according to the metal slag falling data, wherein the slag removal strategy includes a slag removal method, a slag removal start time and an interval, and generating a first slag removal control instruction according to the first slag removal strategy for performing slag removal during laser cutting; Detect whether there is any residual metal slag on the surface of the collecting tank and generate residual metal slag data. If there is any residual metal slag, generate a slag removal adjustment instruction; A slag removal strategy for the surface of the collecting tank is generated according to the metal slag residual data, and a second slag removal control instruction is generated according to the slag removal strategy for the surface of the collecting tank to remove the metal slag remaining on the surface of the collecting tank.

[0067] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Acquire basic data of metal to be cut, wherein the basic data includes metal type and metal shape; Inputting the metal basic data into a preset working data matching model to match corresponding laser working parameters; Detecting the falling condition of the metal slag when it falls into the collecting tank to generate metal slag falling data, wherein the falling data includes the falling rate, the falling position and the shape of the metal slag; Generating a first slag removal strategy according to the metal slag falling data, wherein the slag removal strategy includes a slag removal method, a slag removal start time and an interval, and generating a first slag removal control instruction according to the first slag removal strategy for performing slag removal during laser cutting; Detect whether there is any residual metal slag on the surface of the collecting tank and generate residual metal slag data. If there is any residual metal slag, generate a slag removal adjustment instruction; A slag removal strategy for the surface of the collecting tank is generated according to the metal slag residual data, and a second slag removal control instruction is generated according to the slag removal strategy for the surface of the collecting tank to remove the metal slag remaining on the surface of the collecting tank.

[0068] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0069] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0070] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An automatic slag removal control method for laser cutting, characterized in that: The method comprises the following steps: obtaining basic data of metal to be cut, wherein the basic data of the metal comprises the type of metal and the shape of the metal; Inputting the metal basic data into a preset working data matching model to match corresponding laser working parameters; Detecting the falling condition of the metal slag when it falls into the collecting tank to generate metal slag falling data, wherein the falling data includes the falling rate, the falling position and the shape of the metal slag; Generating a first slag removal strategy according to the metal slag falling data, wherein the slag removal strategy includes a slag removal method, a slag removal start time and an interval, and generating a first slag removal control instruction according to the first slag removal strategy for performing slag removal during laser cutting; Detect whether there is any residual metal slag on the surface of the collecting tank and generate residual metal slag data. If there is any residual metal slag, generate a slag removal adjustment instruction; A slag removal strategy for the surface of the collecting tank is generated according to the metal slag residual data, and a second slag removal control instruction is generated according to the slag removal strategy for the surface of the collecting tank to remove the metal slag remaining on the surface of the collecting tank.

2. The automatic slag removal control method for laser cutting according to claim 1, characterized in that: Before the step of inputting the metal basic data into the preset working data matching model to match the corresponding laser working parameters, the following steps are included: Acquire historical laser working parameters and historical metal basic data, and form a mapping relationship between each of the laser working parameters and the metal basic data to construct a working database; Obtaining the cutting efficiency corresponding to the laser working parameters and inputting it into the working database, and establishing a mapping relationship between the cutting efficiency and the laser working parameters in the working database; The working data matching model matches corresponding laser working parameters according to expected cutting efficiency based on the working database.

3. The automatic slag removal control method for laser cutting according to claim 1, characterized in that: The step of detecting the falling condition of the metal slag when it falls into the collecting tank to generate the metal slag falling data includes the following steps: Acquire a metal slag drop image in a preset unit area to extract the metal slag drop quantity characteristics, drop point characteristics and metal slag shape characteristics in the unit area; Constructing a three-dimensional model of the metal slag based on the falling quantity characteristics, falling point characteristics and metal slag shape characteristics of the metal slag; Calculating the falling rate of the metal slag based on the change of the three-dimensional model of the metal slag; The metal slag dropping data is generated based on the metal slag three-dimensional model and the dropping rate of the metal slag.

4. The automatic slag removal control method for laser cutting according to claim 3, characterized in that: In the step of generating a first slag removal strategy according to the metal slag falling data, the slag removal strategy includes a slag removal method, a slag removal start time and an interval, and generating a first slag removal control instruction according to the first slag removal strategy for slag removal during laser cutting, the steps include the following: Analyze the distribution of metal slag in the falling process according to the falling point characteristics in the metal slag three-dimensional model to determine the slag removal location; Analyze the metal slag falling strength according to the metal slag falling quantity characteristics and the metal slag shape characteristics in the metal slag three-dimensional model to determine the slag removal strength; A first slag removal strategy is generated based on the slag removal location and the slag removal intensity, wherein the working range of the slag removal machine is determined according to the slag removal location, the type of the slag removal machine is determined according to the slag removal intensity, and the start-up time and interval of the slag removal machine are determined according to the drop rate of the metal slag.

5. The automatic slag removal control method for laser cutting according to claim 4, characterized in that: In the step of detecting whether there is residual metal slag on the surface of the collecting tank and generating metal slag residual data, the following steps are included: Acquire image data of the surface of the collecting tank, and record historical image data of the surface of the collecting tank based on a timestamp to build a collection tank surface image database; Analyzing whether there is any unremoved metal slag residue on the surface of the collecting tank based on the collecting tank surface image database, and generating a first judgment result; Acquire airflow data on the surface of the collecting tank, detect whether the airflow data is abnormal, and generate a second judgment result; A metal slag residue report is generated based on the first judgment result and the second judgment result, and metal slag residue data is generated based on the metal slag residue report.

6. The automatic slag removal control method for laser cutting according to claim 5, characterized in that: After the step of generating a metal slag residue report based on the first judgment result and the second judgment result, and generating metal slag residue data based on the metal slag residue report, the following steps are included: Extracting the metal slag residue point characteristics and metal slag residue quantity characteristics in the metal slag residue report; Constructing a slag removal optimization database according to the metal slag residual point characteristics and the metal slag quantity characteristics; The residual point characteristics and the amount of metal slag in the slag removal optimization database are respectively associated with the first slag removal strategy, and a preset slag removal optimization model analyzes the slag removal optimization database based on a machine self-learning algorithm to generate a compensation slag removal strategy, wherein the compensation slag removal strategy is used to optimize the first slag removal strategy; The first slag removal strategy is optimized based on the compensatory slag removal strategy to generate a modified first slag removal strategy, and the modified first slag removal strategy is mapped with the slag removal site and the slag removal intensity corresponding to the first slag removal strategy. The modified first slag removal strategy is used to optimize the slag removal effect corresponding to the slag removal site and the slag removal intensity to reduce metal slag residue.

7. The automatic slag removal control method for laser cutting according to claim 6, characterized in that: The machine self-learning algorithm is a random forest self-learning algorithm.

8. An automatic slag removal control device for laser cutting, applied to an automatic slag removal control method for laser cutting as claimed in any one of claims 1 to 7, characterized in that: It comprises a metal basic data acquisition module (1) for acquiring the basic data of the metal to be cut, wherein the basic data of the metal includes the metal type and the metal shape; A working data matching module (2), used for inputting the metal basic data into a preset working data matching model to match corresponding laser working parameters; A metal slag drop detection module (3) is used to detect the drop of the metal slag when it drops into the collection tank, so as to generate metal slag drop data, wherein the drop data includes the metal slag drop rate, drop position and metal slag shape; A first slag removal strategy generating module (4) is used to generate a first slag removal strategy according to the metal slag falling data, wherein the slag removal strategy includes a slag removal method, a slag removal start time and an interval, and to generate a first slag removal control instruction according to the first slag removal strategy for slag removal during laser cutting; A metal slag residue data generation module (5) is used to detect whether there is any metal slag residue on the surface of the collection tank and generate metal slag residue data, and if there is any metal slag residue, generate a slag removal adjustment instruction; The collecting tank surface slag removal strategy generation module (6) is used to generate a collecting tank surface slag removal strategy according to the metal slag residual data, and to generate a second slag removal control instruction according to the collecting tank surface slag removal strategy for removing the metal slag remaining on the collecting tank surface.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the automatic slag removal control method for laser cutting as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of an automatic slag removal control method for laser cutting as claimed in any one of claims 1 to 7 are implemented.

Images