A manufacturing equipment monitoring method and system based on artificial intelligence

Abstract

The present invention is applicable to the field of laser welding technology, and provides a manufacturing equipment monitoring method and system based on artificial intelligence, the method comprising: when the target laser welding equipment performs welding operation on the target workpiece, obtaining real-time monitoring data of the surface of the target workpiece and a preset complex path numerical control model. The present invention combines the real-time monitoring data with the preset complex path numerical control model to accurately optimize the air pressure of the target workpiece, thereby significantly improving the stability and welding quality of the laser welding process. The scheme can dynamically calculate the minimum reasonable output air pressure value for each area through accurate analysis of the complex path values ​​and reflectivity values ​​of the initial welding area and each designated welding area, thereby ensuring that the airflow, heat and molten pool stability during the welding process reach the optimal state.

Description

Technical Field

[0001] The present invention belongs to the technical field of laser welding, and in particular relates to a manufacturing equipment monitoring method and system based on artificial intelligence. Background Art

[0002] At present, laser welding technology has been widely used in various industrial fields, especially in precision manufacturing and the production of high-demand workpieces. Laser welding equipment connects materials through precise laser beam energy, and has the advantages of fast welding speed and small heat-affected zone. In laser welding technology, one of the main functions of auxiliary gas is to remove slag and impurities to ensure the cleanliness and welding quality of the welding area. During laser welding, due to the high temperature, slag, oxides and other impurities are easily generated on the surface of the workpiece and around the molten pool. These residues will affect the uniformity of welding, the strength and appearance of the weld. In order to ensure the quality of welding, auxiliary gas must be used to effectively remove these residues to prevent them from having adverse effects on the molten pool during welding. Common auxiliary gases such as argon, nitrogen or carbon dioxide can provide appropriate airflow to blow away slag and bubbles and prevent them from reattaching to the welding area, thereby ensuring the stability of welding and the uniformity of the molten pool.

[0003] However, in many current laser welding equipment, the output and pressure of the auxiliary gas are usually fixed or set based on experience, lacking precise control for different welding areas. This "one-size-fits-all" gas regulation method is often difficult to adapt to the changing needs of complex workpiece surface features, and is prone to excessive or insufficient gas, which in turn affects the welding effect. Excessive gas not only wastes energy, but may also cause excessive gas dispersion, affecting the heat distribution and molten pool stability in the welding area. Insufficient gas may result in the failure to effectively remove residues, leading to problems such as unstable molten pool and welding defects. The gas regulation method in the prior art does not fully consider the specific complexity and reflectivity differences of each welding area, and lacks refined gas pressure optimization adjustment. Summary of the invention

[0004] The purpose of the present invention is to provide a manufacturing equipment monitoring method and system based on artificial intelligence, aiming to solve the problems raised in the background technology.

[0005] The present invention is implemented as follows: a manufacturing equipment monitoring method based on artificial intelligence, the method comprising:

[0006] When the target laser welding equipment performs welding operation on the target workpiece, real-time monitoring data of the surface of the target workpiece and a preset complex path numerical comparison model are obtained;

[0007] Combining the real-time monitoring data with the complex path numerical control model, determine the welding area that the target laser welding equipment contacts for the first time and that meets the specified range of the complex path numerical value, and mark the welding area as the initial welding area;

[0008] Conduct dynamic gas pressure optimization analysis on the initial welding area, and determine the lowest reasonable output gas pressure value of the auxiliary gas output in the initial welding area in combination with real-time monitoring data;

[0009] Acquire the surface image of the subsequent welding area of ​​the target workpiece along the preset welding path, identify the designated welding area that meets the specified range of the complex path value according to the complex path value comparison model, and determine the specific complex path value of the initial welding area and each designated welding area;

[0010] Taking the initial welding area as the initial point, obtaining the reflectivity values ​​of the initial welding area and the designated welding area of ​​the target workpiece along the preset welding path;

[0011] The lowest reasonable output pressure value corresponding to each designated welding area is calculated by combining the deviation degree of the complex path value of each designated welding area and the deviation degree of the reflectivity value between the initial welding area.

[0012] As a further limitation of the technical solution of the embodiment of the present invention, the preset complex path numerical control model refers to a refined mapping benchmark of the association between the surface image of the target workpiece and the path complexity, wherein the surface image of each area of ​​the target workpiece is assigned a specific complex path numerical value by analyzing the geometric features of curvature change, turning density, line segment length change and surface texture complexity;

[0013] The division of different areas is based on the variation of complex path values. Only when the difference in complex path values ​​between adjacent areas exceeds a preset threshold, they are defined as independent areas.

[0014] The complex path numerical designation range refers to a specific numerical interval used to screen the target workpiece surface area. Only the target workpiece surface area that meets the complex path numerical designation range will be determined as a welding area with a demand for dynamic gas pressure adjustment.

[0015] As a further limitation of the technical solution of the embodiment of the present invention, the steps of determining the welding area that the target laser welding equipment contacts for the first time and meets the specified range of the complex path value by combining the real-time monitoring data and the complex path value comparison model, and marking the welding area as the initial welding area include:

[0016] Intelligently analyze real-time monitoring data and intermittently capture the surface image of the target workpiece in the real-time monitoring video;

[0017] Input each intercepted target workpiece surface image into the complex path numerical comparison model, match the corresponding designated complex path value in the complex path numerical comparison model, and determine whether the designated complex path value falls within the designated range of the complex path value;

[0018] When the complex path value of a target workpiece surface image meets the specified range of the complex path value, the welding area corresponding to the target workpiece surface image is determined to be the welding area that the target laser welding equipment first contacts and meets the specified range of the complex path value, and it is calibrated as the initial welding area.

[0019] As a further limitation of the technical solution of the embodiment of the present invention, the steps of performing dynamic gas pressure optimization analysis on the initial welding area and determining the minimum reasonable output gas pressure value of the auxiliary gas output in the initial welding area in combination with real-time monitoring data include:

[0020] In the initial welding area, gradually increase the output pressure of the auxiliary gas, and observe the slag cleaning situation in the initial welding area in real time in combination with real-time monitoring data;

[0021] When the output gas pressure reaches a certain value and the slag is sufficiently cleaned, the specific value is determined to be the lowest reasonable output gas pressure value of the auxiliary gas output in the initial welding area.

[0022] As a further limitation of the technical solution of the embodiment of the present invention, the step of calculating the minimum reasonable output pressure value corresponding to each designated welding area in combination with the deviation degree of the complex path value and the deviation degree of the reflectivity value between each designated welding area and the initial welding area includes:

[0023] Quantifying the degree of deviation of the complex path value of each designated welding area relative to the initial welding area to obtain a complex path deviation value;

[0024] quantifying the degree of deviation of the reflectivity value of each designated welding area relative to the initial welding area to obtain a reflectivity deviation value;

[0025] The preset reasonable air pressure value calculation formula is called up, and the corresponding minimum reasonable output air pressure value is calculated by combining the complex path deviation value and reflectivity deviation value of each specified welding area.

[0026] As a further limitation of the technical solution of the embodiment of the present invention, the preset reasonable air pressure value calculation formula is: ;

[0027] Where P n Refers to the lowest reasonable output pressure value corresponding to the nth specified welding area, C n Refers to the specific complex path value of the nth specified welding area, C initRefers to the specific complex path value of the initial welding area, R n Refers to the reflectivity value of the nth specified welding area, R init Refers to the reflectivity value of the initial welding area, w path refers to the weight of the complex path numerical deviation, w reflect Refers to the weight of the reflectivity numerical deviation, P init Refers to the lowest reasonable output gas pressure value in the initial welding area. Refers to the complex path deviation value, Refers to the reflectivity deviation value.

[0028] A manufacturing equipment monitoring system based on artificial intelligence, the system comprises: a data acquisition module, an initial welding area calibration module, a first output air pressure value generation module, an image analysis module, a reflectivity value acquisition module and a second output air pressure value generation module, wherein:

[0029] A data acquisition module, used to acquire real-time monitoring data of the surface of the target workpiece and a preset complex path numerical comparison model when the target laser welding equipment performs welding operation on the target workpiece;

[0030] The preset complex path numerical control model refers to a refined mapping benchmark of the association between the target workpiece surface image and the path complexity, in which the surface image of each area of ​​the target workpiece is assigned a specific complex path value by analyzing the geometric characteristics of curvature change, turning density, line segment length change and surface texture complexity;

[0031] The division of different areas is based on the variation of complex path values. Only when the difference in complex path values ​​between adjacent areas exceeds a preset threshold, they are defined as independent areas.

[0032] An initial welding area calibration module is used to determine the welding area that the target laser welding equipment contacts for the first time and that meets the specified range of the complex path value by combining the real-time monitoring data and the complex path value comparison model, and calibrate the welding area as the initial welding area;

[0033] The complex path numerical value specified range refers to a specific numerical interval used to screen the target workpiece surface area. Only the target workpiece surface area that meets the complex path numerical value specified range will be determined as the welding area with the demand for dynamic gas pressure adjustment;

[0034] The first output gas pressure value generating module is used to perform dynamic gas pressure optimization analysis on the initial welding area, and determine the lowest reasonable output gas pressure value of the auxiliary gas output in the initial welding area in combination with the real-time monitoring data;

[0035] An image analysis module is used to obtain the surface image of the subsequent welding area of ​​the target workpiece along the preset welding path, and identify the designated welding area that meets the specified range of the complex path value according to the complex path value comparison model, and determine the specific complex path value of the initial welding area and each designated welding area;

[0036] A reflectivity value acquisition module is used to acquire reflectivity values ​​of the initial welding area and the designated welding area of ​​the target workpiece along a preset welding path with the initial welding area as the initial point;

[0037] The second output pressure value generating module is used to calculate the minimum reasonable output pressure value corresponding to each designated welding area by combining the deviation degree of the complex path value and the deviation degree of the reflectivity value between each designated welding area and the initial welding area.

[0038] As a further limitation of the technical solution of the embodiment of the present invention, the initial welding area calibration module specifically includes:

[0039] An image acquisition unit is used to intelligently analyze real-time monitoring data and intermittently capture the surface image of the target workpiece in the real-time monitoring video;

[0040] The model parsing unit is used to input each intercepted target workpiece surface image into the complex path numerical comparison model, match the corresponding designated complex path numerical value in the complex path numerical comparison model, and determine whether the designated complex path numerical value falls within the designated range of the complex path numerical value;

[0041] The initial welding area calibration unit is used to determine that the welding area corresponding to a target workpiece surface image is the welding area that the target laser welding equipment contacts for the first time and meets the specified range of complex path values, and calibrate it as the initial welding area when the complex path value of a target workpiece surface image meets the specified range of complex path values.

[0042] As a further limitation of the technical solution of the embodiment of the present invention, the first output air pressure value generating module specifically includes:

[0043] Dynamic gas pressure analysis unit, used to gradually increase the output pressure of auxiliary gas in the initial welding area, and observe the slag cleaning situation in the initial welding area in real time in combination with real-time monitoring data;

[0044] The first output gas pressure value generating unit is used to determine that when the output gas pressure value reaches a certain value and the slag is sufficiently cleaned, the certain value is the lowest reasonable output gas pressure value of the auxiliary gas output in the initial welding area.

[0045] As a further limitation of the technical solution of the embodiment of the present invention, the second output air pressure value generating module specifically includes:

[0046] A complex path deviation value generating unit is used to quantify the degree of deviation of the complex path value of each designated welding area relative to the initial welding area to obtain a complex path deviation value;

[0047] A reflectivity deviation value generating unit, used for quantifying the deviation degree of the reflectivity value of each designated welding area relative to the initial welding area to obtain a reflectivity deviation value;

[0048] The second output pressure value generating unit is used to call a preset reasonable pressure value calculation formula, and calculate the corresponding minimum reasonable output pressure value in combination with the complex path deviation value and the reflectivity deviation value of each designated welding area;

[0049] The preset reasonable air pressure value calculation formula is: ;

[0050] Where P n Refers to the lowest reasonable output pressure value corresponding to the nth specified welding area, C n Refers to the specific complex path value of the nth specified welding area, C init Refers to the specific complex path value of the initial welding area, R n Refers to the reflectivity value of the nth specified welding area, R init Refers to the reflectivity value of the initial welding area, w path refers to the weight of the complex path numerical deviation, w reflect Refers to the weight of the reflectivity numerical deviation, P init Refers to the lowest reasonable output gas pressure value in the initial welding area. Refers to the complex path deviation value, Refers to the reflectivity deviation value.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] By combining real-time monitoring data with a preset complex path numerical control model, the target workpiece is accurately adjusted for gas pressure optimization, significantly improving the stability and quality of the laser welding process. This solution can dynamically calculate the lowest reasonable output gas pressure value for each area through accurate analysis of the complex path values ​​and reflectivity values ​​of the initial welding area and each specified welding area, thereby ensuring that the airflow, heat and molten pool stability during the welding process are in the best state.

[0053] The greatest benefit of this technology is its predictability and accuracy. By analyzing the workpiece surface in detail before welding and dividing the welding area according to the complex path numerical control model, it is ensured that during the actual welding process, the gas pressure adjustment can be personalized according to the complexity and reflection characteristics of different areas. Especially in the gas pressure optimization analysis of the initial welding area and the gas pressure adjustment process of the subsequent areas, the output gas pressure can be adjusted in real time and dynamically, thereby avoiding unnecessary waste of gas pressure and achieving energy saving. In addition, the gas pressure optimization for each designated welding area makes the welding quality more stable, reduces welding defects caused by inappropriate gas pressure, and further improves production efficiency and product consistency.

[0054] The present invention has great industrial application value, especially in the field of precision manufacturing with high requirements on welding quality, and can greatly improve the welding accuracy of workpieces, reduce gas consumption, and improve production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A flowchart of a method provided by an embodiment of the present invention;

[0056] Figure 2 A flow chart of calibrating an initial welding area in a method provided in an embodiment of the present invention;

[0057] Figure 3 A flow chart of determining the lowest reasonable output gas pressure value of the auxiliary gas output in the initial welding area in the method provided by an embodiment of the present invention;

[0058] Figure 4 A flow chart of the lowest reasonable output gas pressure value of the auxiliary gas output in the specified welding area in the method provided in the embodiment of the present invention;

[0059] Figure 5 An application architecture diagram of a system provided for an embodiment of the present invention;

[0060] Figure 6 A structural block diagram of an initial welding area calibration module in a system provided by an embodiment of the present invention;

[0061] Figure 7 A structural block diagram of a first output air pressure value generating module in a system provided by an embodiment of the present invention;

[0062] Figure 8 This is a structural block diagram of a second output air pressure value generating module in a system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0064] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0065] Specifically, a manufacturing equipment monitoring method based on artificial intelligence, the method specifically comprises the following steps:

[0066] Step S100, when the target laser welding equipment performs welding operation on the target workpiece, real-time monitoring data of the surface of the target workpiece and a preset complex path numerical comparison model are obtained.

[0067] The preset complex path numerical control model refers to a refined mapping benchmark of the association between the target workpiece surface image and the path complexity, in which the surface image of each area of ​​the target workpiece is assigned a specific complex path value by analyzing the geometric characteristics of curvature change, turning density, line segment length change and surface texture complexity;

[0068] The division of different areas is based on the variation of complex path values. Only when the difference in complex path values ​​of adjacent areas exceeds a preset threshold, they are defined as independent areas.

[0069] In the embodiment of the present invention, the target laser welding equipment uses relatively costly gases, such as high-purity gases such as argon or helium, which play an important role in the welding process, protecting the welding area from oxidation and effectively improving the welding quality and stability. Since the cost of these gases is relatively high, reasonable gas pressure regulation and optimization are of extremely important economic significance.

[0070] In actual operation, real-time monitoring data of the target workpiece surface is obtained through an intelligent sensor system. The system includes high-resolution cameras, infrared sensors, and spectral analysis devices, which can capture the surface status of the target workpiece in real time, such as surface temperature, reflectivity, geometry, and dynamic changes in the molten pool. Through these devices, the surface image of each time point and each area during the welding process can be accurately captured and input into the system for further analysis. Combined with these real-time data, a detailed image of the surface status of the target workpiece can be generated, providing the original input for the subsequent complex path numerical comparison model.

[0071] The preset complex path numerical control model is a refined mapping benchmark based on the association between the target workpiece surface image and the path complexity. In this model, the surface image of each area of ​​the target workpiece will obtain the corresponding complex path value through a comprehensive analysis of its geometric features. Specifically, by analyzing factors such as the curvature change, turning density, line segment length change and surface texture complexity of each area on the workpiece surface, the geometric features of each area can be quantified and a specific complex path value can be assigned to it. These values ​​not only reflect the shape complexity of the regional surface, but are also closely related to factors such as airflow and temperature distribution during the welding process, and can provide an accurate basis for air pressure adjustment. This process uses advanced computer vision technology, image processing algorithms and geometric modeling methods, combined with deep learning models to efficiently analyze the workpiece surface, thereby achieving accurate calculation of complex path values.

[0072] The division of different areas is determined based on the variation of the complex path values. Specifically, only when the difference in complex path values ​​of adjacent areas exceeds a preset threshold, they are defined as independent areas. This division method helps to refine the gas pressure regulation of the welding area, so that each area can obtain accurate gas pressure optimization according to its geometric complexity, and ensure that each area can obtain appropriate gas protection and cleaning effects during the welding process, avoiding excessive or insufficient gas pressure regulation from having adverse effects on welding quality.

[0073] Furthermore, the manufacturing equipment monitoring method based on artificial intelligence also includes the following steps:

[0074] Step S200, combining the real-time monitoring data and the complex path numerical control model to determine the welding area that the target laser welding equipment contacts for the first time and that meets the specified range of the complex path numerical value, and calibrating the welding area as the initial welding area.

[0075] Specifically, Figure 2 A flow chart for calibrating the initial weld area is shown.

[0076] Among them, combining the real-time monitoring data and the complex path numerical control model to determine the welding area that the target laser welding equipment contacts for the first time and meets the specified range of the complex path numerical value, and marking the welding area as the initial welding area specifically includes the following steps:

[0077] Step S201, intelligently analyzing real-time monitoring data, and periodically capturing the surface image of the target workpiece in the real-time monitoring video;

[0078] Step S202, inputting each intercepted target workpiece surface image into the complex path numerical comparison model, matching the corresponding designated complex path numerical value in the complex path numerical comparison model, and determining whether the designated complex path numerical value falls within the designated range of the complex path numerical value;

[0079] Step S203, when the complex path value of a target workpiece surface image meets the specified range of the complex path value, determine that the welding area corresponding to the target workpiece surface image is the welding area that the target laser welding equipment first contacts and meets the specified range of the complex path value, and calibrate it as the initial welding area.

[0080] The complex path numerical designation range refers to a specific numerical interval used to screen the target workpiece surface area. Only the target workpiece surface area that meets the complex path numerical designation range will be determined as a welding area with a demand for dynamic gas pressure adjustment.

[0081] In an embodiment of the present invention, during the welding process, the target laser welding device continuously captures the target workpiece surface images through the real-time monitoring system, and these images are then input into the complex path numerical comparison model for analysis. In this model, each workpiece surface area corresponds to a specific complex path value according to its geometric characteristics, texture complexity and other factors. These complex path values ​​can effectively reflect the geometric complexity of the area and the gas pressure regulation requirements required for welding.

[0082] Each time a new workpiece surface image is acquired, the device will use a matching algorithm to search for the complex path value corresponding to the image in the complex path value comparison model. Then, the system will determine whether the complex path value is within the preset complex path value specified range. If the complex path value corresponding to the image meets the specified range, it indicates that the area has the need to adapt to the dynamic adjustment of air pressure. At this time, the area will be determined as the welding area that the target laser welding equipment contacts for the first time, and will be marked as the initial welding area, entering the subsequent air pressure adjustment process.

[0083] The significance of the specified range of complex path values ​​is that it is an effective screening tool for the geometric complexity of the target workpiece surface area. Only when the complex path value is within this range does it mean that the gas pressure in this area needs to be optimized and adjusted to ensure welding quality and avoid excessive gas consumption. If the complex path value exceeds the specified range, it means that the geometric complexity of the area is high, and a higher auxiliary gas pressure is usually required to ensure a good welding effect; if it is below this range, it means that the area is relatively flat, and usually only a lower gas pressure is required to meet the welding requirements.

[0084] Furthermore, the manufacturing equipment monitoring method based on artificial intelligence also includes the following steps:

[0085] Step S300, performing dynamic gas pressure optimization analysis on the initial welding area, and determining the lowest reasonable output gas pressure value of the auxiliary gas output in the initial welding area in combination with real-time monitoring data.

[0086] Specifically, Figure 3 A flow chart is shown for determining the lowest reasonable output gas pressure value for assist gas output in the initial weld zone.

[0087] The following steps are specifically included in the process of performing dynamic gas pressure optimization analysis on the initial welding area and determining the lowest reasonable output gas pressure value of the auxiliary gas output in the initial welding area in combination with real-time monitoring data:

[0088] Step S301, in the initial welding area, gradually increasing the output pressure of the auxiliary gas, and combining the real-time monitoring data to observe the slag cleaning situation in the initial welding area in real time;

[0089] Step S302, when the output gas pressure value reaches a certain value and the slag is sufficiently cleaned, the certain value is determined as the lowest reasonable output gas pressure value of the auxiliary gas output in the initial welding area.

[0090] In the embodiment of the present invention, when the initial welding area is determined, the system will first lower the output pressure of the auxiliary gas to a preset lower value. Then, the pressure value is gradually increased through the control system of the target laser welding equipment. This gradual increase process is to ensure that there is no over-purging in the initial stage, and gradually optimize the pressure during the actual welding process to achieve the best slag cleaning effect.

[0091] As the gas pressure gradually increases, the system observes the slag removal in the initial weld area through real-time monitoring data. Specifically, a high-resolution camera or other sensor device is used to monitor the slag status in the weld area, and an image processing algorithm is used to analyze the slag removal effect in real time. When the gas pressure reaches a certain set value, the system automatically evaluates the slag removal. If the slag is fully removed, the system records the gas pressure value at this time and determines that this pressure value is the lowest reasonable output gas pressure value for the initial weld area.

[0092] In this process, existing real-time monitoring technology and image processing technology are used. The former captures and transmits the surface status of the target workpiece through camera equipment, while the latter processes images through algorithms to accurately analyze the slag removal situation. The dynamic adjustment of air pressure relies on a precise air pressure control system, which can automatically adjust the air pressure value according to real-time monitoring data to ensure that the welding task is completed at the appropriate air pressure. In this way, the whole process can not only optimize the welding quality, but also avoid gas waste, improve efficiency and reduce costs.

[0093] Furthermore, the manufacturing equipment monitoring method based on artificial intelligence also includes the following steps:

[0094] Step S400, along the preset welding path, a surface image of a subsequent welding area of ​​the target workpiece is obtained, and a designated welding area that meets the specified range of complex path values ​​is identified according to the complex path value comparison model, and a specific complex path value of the initial welding area and each designated welding area is determined;

[0095] Step S500, taking the initial welding area as the initial point, obtaining reflectivity values ​​of the initial welding area and the designated welding area of ​​the target workpiece along a preset welding path.

[0096] In the embodiment of the present invention, in the welding path presetting stage, the surface information of the target workpiece is first obtained by digital means (such as CAD model or scanning technology), and these data provide accurate workpiece geometry and feature description of each area for subsequent welding operations. On this basis, the surface image of the target workpiece is further analyzed to facilitate the allocation of appropriate complex path values ​​to each area.

[0097] Specifically, during this process, the surface image of each area of ​​the target workpiece is input into the complex path numerical comparison model for comparative analysis. The model acts as a refined mapping benchmark, automatically assigning a corresponding complex path value to each area by identifying and comparing geometric features in the image (such as curvature, surface turning point density, and texture complexity). The model can directly find the corresponding value of each area in the complex path numerical comparison model by matching the regional image with the defined complex path numerical library.

[0098] The complex path numerical comparison model accurately maps the relationship between the workpiece surface image and the path complexity. Therefore, the surface image of each area of ​​the target workpiece will correspond to its corresponding complex path value. In this way, through simple image comparison, the system can quickly identify the complex path value of each area and make accurate judgments for subsequent welding path planning and gas pressure adjustment.

[0099] In further operation, the system will also obtain the reflectivity value of each specified welding area through the spectral analysis device. The reflectivity value reflects the reflective properties of the welding surface and is usually obtained through laser reflectivity measurement technology. Along the preset welding path, the laser welding equipment will measure the reflectivity changes of each welding area according to the real-time monitoring data and compare these reflectivity values ​​with the initial welding area. In this process, the combination of real-time monitoring technology, laser reflectivity detection, and data processing algorithms ensures that the surface condition of each welding area can be accurately monitored and analyzed.

[0100] These processes apply existing image processing technology, laser welding equipment control systems, and real-time data acquisition and feedback mechanisms to ensure the accuracy and stability of welding operations by combining various sensor data for dynamic adjustments.

[0101] Furthermore, the manufacturing equipment monitoring method based on artificial intelligence also includes the following steps:

[0102] Step S600, combining the degree of deviation of the complex path value and the degree of deviation of the reflectivity value of each designated welding area with that of the initial welding area, calculates the lowest reasonable output pressure value corresponding to each designated welding area.

[0103] Specifically, Figure 4 A flow chart showing the lowest reasonable output gas pressure values ​​for assist gas output for a given weld zone.

[0104] The calculation of the lowest reasonable output pressure value corresponding to each designated welding area by combining the deviation degree of the complex path value and the deviation degree of the reflectivity value between each designated welding area and the initial welding area specifically includes the following steps:

[0105] Step S601, quantifying the degree of deviation of the complex path value of each designated welding area relative to the initial welding area to obtain a complex path deviation value;

[0106] Step S602, quantifying the deviation degree of the reflectivity value of each designated welding area relative to the initial welding area to obtain a reflectivity deviation value;

[0107] Step S603, calling a preset reasonable air pressure value calculation formula, combining the complex path deviation value and the reflectivity deviation value of each designated welding area, and calculating the corresponding minimum reasonable output air pressure value.

[0108] The preset reasonable air pressure value calculation formula is: ;

[0109] Where P n Refers to the lowest reasonable output pressure value corresponding to the nth specified welding area, C n Refers to the specific complex path value of the nth specified welding area, C init Refers to the specific complex path value of the initial welding area, R n Refers to the reflectivity value of the nth specified welding area, R init Refers to the reflectivity value of the initial welding area, w path refers to the weight of the complex path numerical deviation, w reflect Refers to the weight of the reflectivity numerical deviation, P init Refers to the lowest reasonable output gas pressure value in the initial welding area. Refers to the complex path deviation value, Refers to the reflectivity deviation value.

[0110] In the embodiment of the present invention, the degree of deviation of the complex path value of each designated welding area relative to the initial welding area is quantified to obtain the complex path deviation value; the degree of deviation of the reflectivity value of each designated welding area relative to the initial welding area is quantified to obtain the reflectivity deviation value. These two steps are to quantify the relative complexity and surface characteristics of each designated welding area, and further adjust the output pressure value of the auxiliary gas according to these characteristics, so as to ensure the welding quality.

[0111] The deviation of the complex path value mainly reflects the geometric complexity of the welding area. The complex path value is usually related to the geometric characteristics of the workpiece surface such as curvature change, turn density, texture complexity, etc. These characteristics directly affect the interaction between the laser beam and the workpiece surface, thereby affecting the heat transfer and molten pool formation during the welding process. By quantifying the deviation of the complex path value, the complexity of the target area can be evaluated, and the gas pressure output can be adjusted according to the complexity to ensure that the appropriate gas pressure support is obtained in different complex areas.

[0112] The reflectivity value reflects the reflection of the laser on the workpiece surface. Too high or too low reflectivity will affect the absorption efficiency of the laser. Therefore, the change of reflectivity is another important factor affecting the welding effect. By calculating the deviation of reflectivity, we can further understand the demand for gas pressure regulation due to the change of surface characteristics in the welding area, so as to make adjustments and optimize the gas pressure output.

[0113] The Complex Path Deviation value is calculated by dividing the difference between the Complex Path value of the specified weld area and the Complex Path value of the initial weld area by the Complex Path value of the initial weld area. This method reflects the change in geometric complexity of each specified weld area relative to the initial weld area. A higher Complex Path value difference means a more difficult weld and the gas pressure needs to be increased accordingly to ensure a good weld quality.

[0114] The reflectivity deviation value is calculated by subtracting the reflectivity value of the specified weld area from the reflectivity value of the initial weld area, divided by the reflectivity value of the initial weld area. This method measures the effect of changes in reflectivity on the gas pressure output. If the reflectivity of the specified area is lower, it means that the laser absorption effect is stronger in this area, and lower gas pressure may be required; conversely, when the reflectivity is higher, higher gas pressure may be required to ensure adequate gas coverage and slag removal.

[0115] For example, according to the calculation formula of reasonable gas pressure value, assuming that the complex path value of the initial welding area is 150 and the reflectivity value is 0.8, the minimum reasonable output gas pressure value of the initial welding area is 4 bar; assuming that the complex path value of the first specified welding area is 130 and the reflectivity value is 0.75.

[0116] First, calculate the complex path deviation value: (complex path value of the specified welding area - complex path value of the initial welding area) / complex path value of the initial welding area = (130-150) / 150 = -0.1333.

[0117] Next, the reflectivity deviation value is calculated: (initial weld area reflectivity value - designated weld area reflectivity value) / initial weld area reflectivity value = (0.8-0.75) / 0.8 = 0.0625.

[0118] Next, calculate according to the formula: First, multiply the complex path deviation value by its weight. The complex path deviation value is -0.1333, and the weight is 0.7, so: -0.1333×0.7=-0.0933.

[0119] Then, multiply the reflectivity deviation value by its weight. The reflectivity deviation value is 0.0625 and the weight is 0.3, so: 0.0625×0.3=0.01875.

[0120] Next, add these two values ​​and add 1, which is -0.0933+0.01875+1=0.92545.

[0121] Finally, multiply this sum by the lowest reasonable output pressure value P in the initial welding area. init (4 bar in this example): 0.92545×4=3.7018 bar.

[0122] Therefore, this calculation shows that the lowest reasonable output pressure value for the specified welding area is 3.7 bar. This result shows that after considering the complex path and reflectivity characteristics of this area, the gas pressure output needs to be slightly reduced to ensure gas conservation while maintaining welding quality.

[0123] In summary, this technical solution can accurately calculate the gas pressure requirements of each designated welding area before welding by pre-setting a complex path numerical control model and combining the geometric features of the target workpiece surface (such as curvature, texture complexity, etc.) and reflectivity data. This process relies on in-depth analysis of the target workpiece surface image and the preset welding path, thus providing a scientific basis for subsequent gas pressure adjustment. In actual operation, the complex path value and reflectivity of the workpiece are first calculated, and then the gas output pressure is adjusted according to the degree of deviation and the preset calculation formula. This preset intelligent control strategy avoids the uncertainty caused by relying on real-time feedback to adjust the gas pressure during the welding process.

[0124] The surface image of the target workpiece is acquired and analyzed in advance, and the gas pressure is optimized according to the complex path numerical control model, providing accurate parameter support for the welding operation. This not only improves the gas use efficiency during the welding process, but also effectively avoids unnecessary waste and achieves energy conservation and emission reduction. Under complex welding paths and different workpiece surface characteristics, the lowest reasonable gas pressure value can be accurately calculated for each area to ensure the stability of the molten pool and the uniform distribution of heat during the welding process, thereby improving the welding quality.

[0125] In addition, the preset nature of the entire process greatly enhances the controllability of welding operations and ensures the improvement of welding quality and efficiency. Through precise gas pressure regulation, the stability and reliability of the welding process are guaranteed, while avoiding welding defects or quality fluctuations that may be caused by untimely real-time adjustment. This intelligent preset control strategy not only effectively reduces energy consumption, but also saves gas costs, helping companies to reduce production costs while improving production efficiency. Therefore, this technical solution not only improves the quality, efficiency and controllability of welding operations, but also makes positive contributions to environmental protection and resource conservation.

[0126] Furthermore, Figure 5 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0127] Among them, in another preferred embodiment provided by the present invention, a manufacturing equipment monitoring system based on artificial intelligence includes:

[0128] The data acquisition module 100 is used to acquire real-time monitoring data of the surface of the target workpiece and a preset complex path numerical comparison model when the target laser welding equipment performs welding operation on the target workpiece;

[0129] The preset complex path numerical control model refers to a refined mapping benchmark of the association between the target workpiece surface image and the path complexity, in which the surface image of each area of ​​the target workpiece is assigned a specific complex path value by analyzing the geometric characteristics of curvature change, turning density, line segment length change and surface texture complexity;

[0130] The division of different areas is based on the variation of complex path values. Only when the difference in complex path values ​​of adjacent areas exceeds a preset threshold, they are defined as independent areas.

[0131] In the embodiment of the present invention, the target laser welding equipment uses relatively costly gases, such as high-purity gases such as argon or helium, which play an important role in the welding process, protecting the welding area from oxidation and effectively improving the welding quality and stability. Since the cost of these gases is relatively high, reasonable gas pressure regulation and optimization are of extremely important economic significance.

[0132] In actual operation, real-time monitoring data of the target workpiece surface is obtained through an intelligent sensor system. The system includes high-resolution cameras, infrared sensors, and spectral analysis devices, which can capture the surface status of the target workpiece in real time, such as surface temperature, reflectivity, geometry, and dynamic changes in the molten pool. Through these devices, the surface image of each time point and each area during the welding process can be accurately captured and input into the system for further analysis. Combined with these real-time data, a detailed image of the surface status of the target workpiece can be generated, providing the original input for the subsequent complex path numerical comparison model.

[0133] The preset complex path numerical control model is a refined mapping benchmark based on the association between the target workpiece surface image and the path complexity. In this model, the surface image of each area of ​​the target workpiece will obtain the corresponding complex path value through a comprehensive analysis of its geometric features. Specifically, by analyzing factors such as the curvature change, turning density, line segment length change and surface texture complexity of each area on the workpiece surface, the geometric features of each area can be quantified and a specific complex path value can be assigned to it. These values ​​not only reflect the shape complexity of the regional surface, but are also closely related to factors such as airflow and temperature distribution during the welding process, and can provide an accurate basis for air pressure adjustment. This process uses advanced computer vision technology, image processing algorithms and geometric modeling methods, combined with deep learning models to efficiently analyze the workpiece surface, thereby achieving accurate calculation of complex path values.

[0134] The division of different areas is determined based on the variation of the complex path values. Specifically, only when the difference in complex path values ​​of adjacent areas exceeds a preset threshold, they are defined as independent areas. This division method helps to refine the gas pressure regulation of the welding area, so that each area can obtain accurate gas pressure optimization according to its geometric complexity, and ensure that each area can obtain appropriate gas protection and cleaning effects during the welding process, avoiding excessive or insufficient gas pressure regulation from having adverse effects on welding quality.

[0135] Furthermore, the artificial intelligence-based manufacturing equipment monitoring system also includes:

[0136] The initial welding area calibration module 200 is used to determine the welding area that the target laser welding equipment contacts for the first time and meets the specified range of the complex path value by combining the real-time monitoring data and the complex path value control model, and calibrate the welding area as the initial welding area.

[0137] The complex path numerical designation range refers to a specific numerical interval used to screen the target workpiece surface area. Only the target workpiece surface area that meets the complex path numerical designation range will be determined as a welding area with a demand for dynamic gas pressure adjustment.

[0138] Specifically, Figure 6 The structure block diagram of the initial welding area calibration module 200 in the system provided by the embodiment of the present invention is shown.

[0139] Among them, in the preferred embodiment provided by the present invention, the initial welding area calibration module 200 specifically includes:

[0140] An image acquisition unit 201 is used to intelligently analyze real-time monitoring data and intermittently capture the surface image of the target workpiece in the real-time monitoring video;

[0141] The model parsing unit 202 is used to input each intercepted target workpiece surface image into the complex path numerical comparison model, match the corresponding designated complex path numerical value in the complex path numerical comparison model, and determine whether the designated complex path numerical value falls within the designated range of the complex path numerical value;

[0142] The initial welding area calibration unit 203 is used to determine that the welding area corresponding to a target workpiece surface image is the welding area that the target laser welding equipment first contacts and meets the specified range of complex path values ​​when the complex path value of a target workpiece surface image meets the specified range of complex path values, and calibrate it as the initial welding area.

[0143] In an embodiment of the present invention, during the welding process, the target laser welding device continuously captures the target workpiece surface images through the real-time monitoring system, and these images are then input into the complex path numerical comparison model for analysis. In this model, each workpiece surface area corresponds to a specific complex path value according to its geometric characteristics, texture complexity and other factors. These complex path values ​​can effectively reflect the geometric complexity of the area and the gas pressure regulation requirements required for welding.

[0144] Each time a new workpiece surface image is acquired, the device will use a matching algorithm to search for the complex path value corresponding to the image in the complex path value comparison model. Then, the system will determine whether the complex path value is within the preset complex path value specified range. If the complex path value corresponding to the image meets the specified range, it indicates that the area has the need to adapt to the dynamic adjustment of air pressure. At this time, the area will be determined as the welding area that the target laser welding equipment contacts for the first time, and will be marked as the initial welding area, entering the subsequent air pressure adjustment process.

[0145] The significance of the specified range of complex path values ​​is that it is an effective screening tool for the geometric complexity of the target workpiece surface area. Only when the complex path value is within this range does it mean that the gas pressure in this area needs to be optimized and adjusted to ensure welding quality and avoid excessive gas consumption. If the complex path value exceeds the specified range, it means that the geometric complexity of the area is high, and a higher auxiliary gas pressure is usually required to ensure a good welding effect; if it is below this range, it means that the area is relatively flat, and usually only a lower gas pressure is required to meet the welding requirements.

[0146] Furthermore, the artificial intelligence-based manufacturing equipment monitoring system also includes:

[0147] The first output gas pressure value generating module 300 is used to perform dynamic gas pressure optimization analysis on the initial welding area, and determine the lowest reasonable output gas pressure value of the auxiliary gas output in the initial welding area in combination with the real-time monitoring data.

[0148] Specifically, Figure 7 It shows a structural block diagram of the first output air pressure value generating module 300 in the system provided by an embodiment of the present invention.

[0149] In a preferred embodiment of the present invention, the first output air pressure value generating module 300 specifically includes:

[0150] The dynamic gas pressure analysis unit 301 is used to gradually increase the output gas pressure of the auxiliary gas in the initial welding area, and observe the slag cleaning situation in the initial welding area in real time in combination with the real-time monitoring data;

[0151] The first output gas pressure value generating unit 302 is used to determine that when the output gas pressure value reaches a certain value and the slag is sufficiently cleaned, the certain value is the lowest reasonable output gas pressure value of the auxiliary gas output in the initial welding area.

[0152] In the embodiment of the present invention, when the initial welding area is determined, the system will first lower the output pressure of the auxiliary gas to a preset lower value. Then, the pressure value is gradually increased through the control system of the target laser welding equipment. This gradual increase process is to ensure that there is no over-purging in the initial stage, and gradually optimize the pressure during the actual welding process to achieve the best slag cleaning effect.

[0153] As the gas pressure gradually increases, the system observes the slag removal in the initial weld area through real-time monitoring data. Specifically, a high-resolution camera or other sensor device is used to monitor the slag status in the weld area, and an image processing algorithm is used to analyze the slag removal effect in real time. When the gas pressure reaches a certain set value, the system automatically evaluates the slag removal. If the slag is fully removed, the system records the gas pressure value at this time and determines that this pressure value is the lowest reasonable output gas pressure value for the initial weld area.

[0154] In this process, existing real-time monitoring technology and image processing technology are used. The former captures and transmits the surface status of the target workpiece through camera equipment, while the latter processes images through algorithms to accurately analyze the slag removal situation. The dynamic adjustment of air pressure relies on a precise air pressure control system, which can automatically adjust the air pressure value according to real-time monitoring data to ensure that the welding task is completed at the appropriate air pressure. In this way, the whole process can not only optimize the welding quality, but also avoid gas waste, improve efficiency and reduce costs.

[0155] Furthermore, the artificial intelligence-based manufacturing equipment monitoring system also includes:

[0156] The image analysis module 400 is used to obtain the surface image of the subsequent welding area of ​​the target workpiece along the preset welding path, and identify the designated welding area that meets the specified range of the complex path value according to the complex path value comparison model, and determine the specific complex path value of the initial welding area and each designated welding area;

[0157] The reflectivity value acquisition module 500 is used to acquire the reflectivity values ​​of the initial welding area and the designated welding area of ​​the target workpiece along a preset welding path with the initial welding area as the initial point.

[0158] In the embodiment of the present invention, in the welding path presetting stage, the surface information of the target workpiece is first obtained by digital means (such as CAD model or scanning technology), and these data provide accurate workpiece geometry and feature description of each area for subsequent welding operations. On this basis, the surface image of the target workpiece is further analyzed to facilitate the allocation of appropriate complex path values ​​to each area.

[0159] Specifically, during this process, the surface image of each area of ​​the target workpiece is input into the complex path numerical comparison model for comparative analysis. The model acts as a refined mapping benchmark, automatically assigning a corresponding complex path value to each area by identifying and comparing geometric features in the image (such as curvature, surface turning point density, and texture complexity). The model can directly find the corresponding value of each area in the complex path numerical comparison model by matching the regional image with the defined complex path numerical library.

[0160] The complex path numerical comparison model accurately maps the relationship between the workpiece surface image and the path complexity. Therefore, the surface image of each area of ​​the target workpiece will correspond to its corresponding complex path value. In this way, through simple image comparison, the system can quickly identify the complex path value of each area and make accurate judgments for subsequent welding path planning and gas pressure adjustment.

[0161] In further operation, the system will also obtain the reflectivity value of each specified welding area through the spectral analysis device. The reflectivity value reflects the reflective properties of the welding surface and is usually obtained through laser reflectivity measurement technology. Along the preset welding path, the laser welding equipment will measure the reflectivity changes of each welding area according to the real-time monitoring data and compare these reflectivity values ​​with the initial welding area. In this process, the combination of real-time monitoring technology, laser reflectivity detection, and data processing algorithms ensures that the surface condition of each welding area can be accurately monitored and analyzed.

[0162] Furthermore, the artificial intelligence-based manufacturing equipment monitoring system also includes:

[0163] The second output pressure value generating module 600 is used to calculate the minimum reasonable output pressure value corresponding to each designated welding area by combining the deviation degree of the complex path value and the deviation degree of the reflectivity value between each designated welding area and the initial welding area.

[0164] Specifically, Figure 8 It shows a structural block diagram of the second output air pressure value generating module 600 in the system provided by an embodiment of the present invention.

[0165] In a preferred embodiment of the present invention, the second output air pressure value generating module 600 specifically includes:

[0166] A complex path deviation value generating unit 601 is used to quantify the degree of deviation of the complex path value of each designated welding area relative to the initial welding area to obtain a complex path deviation value;

[0167] A reflectivity deviation value generating unit 602 is used to quantify the deviation degree of the reflectivity value of each designated welding area relative to the initial welding area to obtain a reflectivity deviation value;

[0168] The second output pressure value generating unit 603 is used to retrieve a preset reasonable pressure value calculation formula, and calculate the corresponding minimum reasonable output pressure value in combination with the complex path deviation value and the reflectivity deviation value of each designated welding area;

[0169] The preset reasonable air pressure value calculation formula is: ;

[0170] Where P n Refers to the lowest reasonable output pressure value corresponding to the nth specified welding area, C n Refers to the specific complex path value of the nth specified welding area, C init Refers to the specific complex path value of the initial welding area, R n Refers to the reflectivity value of the nth specified welding area, R init Refers to the reflectivity value of the initial welding area, w path refers to the weight of the complex path numerical deviation, w reflect Refers to the weight of the reflectivity numerical deviation, P init Refers to the lowest reasonable output gas pressure value in the initial welding area. Refers to the complex path deviation value, Refers to the reflectivity deviation value.

[0171] In the embodiment of the present invention, the degree of deviation of the complex path value of each designated welding area relative to the initial welding area is quantified to obtain the complex path deviation value; the degree of deviation of the reflectivity value of each designated welding area relative to the initial welding area is quantified to obtain the reflectivity deviation value. These two steps are to quantify the relative complexity and surface characteristics of each designated welding area, and further adjust the output pressure value of the auxiliary gas according to these characteristics, so as to ensure the welding quality.

[0172] The deviation of the complex path value mainly reflects the geometric complexity of the welding area. The complex path value is usually related to the geometric characteristics of the workpiece surface such as curvature change, turn density, texture complexity, etc. These characteristics directly affect the interaction between the laser beam and the workpiece surface, thereby affecting the heat transfer and molten pool formation during the welding process. By quantifying the deviation of the complex path value, the complexity of the target area can be evaluated, and the gas pressure output can be adjusted according to the complexity to ensure that the appropriate gas pressure support is obtained in different complex areas.

[0173] The reflectivity value reflects the reflection of the laser on the workpiece surface. Too high or too low reflectivity will affect the absorption efficiency of the laser. Therefore, the change of reflectivity is another important factor affecting the welding effect. By calculating the deviation of reflectivity, we can further understand the demand for gas pressure regulation due to the change of surface characteristics in the welding area, so as to make adjustments and optimize the gas pressure output.

[0174] The Complex Path Deviation value is calculated by dividing the difference between the Complex Path value of the specified weld area and the Complex Path value of the initial weld area by the Complex Path value of the initial weld area. This method reflects the change in geometric complexity of each specified weld area relative to the initial weld area. A higher Complex Path value difference means a more difficult weld and the gas pressure needs to be increased accordingly to ensure a good weld quality.

[0175] The reflectivity deviation value is calculated by subtracting the reflectivity value of the specified weld area from the reflectivity value of the initial weld area, divided by the reflectivity value of the initial weld area. This method measures the effect of changes in reflectivity on the gas pressure output. If the reflectivity of the specified area is lower, it means that the laser absorption effect is stronger in this area, and lower gas pressure may be required; conversely, when the reflectivity is higher, higher gas pressure may be required to ensure adequate gas coverage and slag removal.

[0176] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0177] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0178] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0179] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A manufacturing equipment monitoring method based on artificial intelligence, characterized in that: The method comprises: When the target laser welding equipment performs welding operation on the target workpiece, real-time monitoring data of the surface of the target workpiece and a preset complex path numerical comparison model are obtained; Combining the real-time monitoring data with the complex path numerical control model, determine the welding area that the target laser welding equipment contacts for the first time and that meets the specified range of the complex path numerical value, and mark the welding area as the initial welding area; Perform dynamic gas pressure optimization analysis on the initial welding area, and determine the lowest reasonable output gas pressure value of the auxiliary gas output in the initial welding area in combination with real-time monitoring data; Acquire the surface image of the subsequent welding area of ​​the target workpiece along the preset welding path, identify the designated welding area that meets the specified range of the complex path value according to the complex path value comparison model, and determine the specific complex path value of the initial welding area and each designated welding area; Taking the initial welding area as the initial point, obtaining the reflectivity values ​​of the initial welding area and the designated welding area of ​​the target workpiece along the preset welding path; The lowest reasonable output pressure value corresponding to each designated welding area is calculated by combining the deviation degree of the complex path value of each designated welding area and the deviation degree of the reflectivity value between the initial welding area.

2. The manufacturing equipment monitoring method based on artificial intelligence according to claim 1 is characterized in that: The preset complex path numerical control model refers to a refined mapping benchmark of the association between the target workpiece surface image and the path complexity, in which the surface image of each area of ​​the target workpiece is assigned a specific complex path value by analyzing the geometric characteristics of curvature change, turning density, line segment length change and surface texture complexity; The division of different areas is based on the variation of complex path values. Only when the difference in complex path values ​​between adjacent areas exceeds a preset threshold, they are defined as independent areas. The complex path numerical designation range refers to a specific numerical interval used to screen the target workpiece surface area. Only the target workpiece surface area that meets the complex path numerical designation range will be determined as a welding area with a demand for dynamic gas pressure adjustment.

3. The manufacturing equipment monitoring method based on artificial intelligence according to claim 2 is characterized in that: The steps of combining the real-time monitoring data and the complex path numerical control model to determine the welding area that the target laser welding equipment contacts for the first time and that meets the specified range of the complex path numerical value, and marking the welding area as the initial welding area include: Intelligently analyze real-time monitoring data and intermittently capture the surface image of the target workpiece in the real-time monitoring video; Input each intercepted target workpiece surface image into the complex path numerical comparison model, match the corresponding designated complex path value in the complex path numerical comparison model, and determine whether the designated complex path value falls within the designated range of the complex path value; When the complex path value of a target workpiece surface image meets the specified range of the complex path value, the welding area corresponding to the target workpiece surface image is determined to be the welding area that the target laser welding equipment first contacts and meets the specified range of the complex path value, and it is calibrated as the initial welding area.

4. The manufacturing equipment monitoring method based on artificial intelligence according to claim 1 is characterized in that: The steps of performing dynamic gas pressure optimization analysis on the initial welding area and determining the lowest reasonable output gas pressure value of the auxiliary gas output in the initial welding area in combination with real-time monitoring data include: In the initial welding area, gradually increase the output pressure of the auxiliary gas, and observe the slag cleaning situation in the initial welding area in real time in combination with real-time monitoring data; When the output gas pressure reaches a certain value and the slag is sufficiently cleaned, the specific value is determined to be the lowest reasonable output gas pressure value of the auxiliary gas output in the initial welding area.

5. The manufacturing equipment monitoring method based on artificial intelligence according to claim 2 is characterized in that: The steps of calculating the lowest reasonable output pressure value corresponding to each designated welding area by combining the deviation degree of the complex path value of each designated welding area and the deviation degree of the reflectivity value between each designated welding area and the initial welding area include: Quantifying the degree of deviation of the complex path value of each designated welding area relative to the initial welding area to obtain a complex path deviation value; quantifying the degree of deviation of the reflectivity value of each designated welding area relative to the initial welding area to obtain a reflectivity deviation value; The preset reasonable air pressure value calculation formula is called up, and the corresponding minimum reasonable output air pressure value is calculated by combining the complex path deviation value and reflectivity deviation value of each specified welding area.

6. The manufacturing equipment monitoring method based on artificial intelligence according to claim 5 is characterized in that: The preset reasonable air pressure value calculation formula is: ; Where P n Refers to the lowest reasonable output pressure value corresponding to the nth specified welding area, C n Refers to the specific complex path value of the nth specified welding area, C init Refers to the specific complex path value of the initial welding area, R n Refers to the reflectivity value of the nth specified welding area, R init Refers to the reflectivity value of the initial welding area, w path refers to the weight of the complex path numerical deviation, w reflect Refers to the weight of the reflectivity numerical deviation, P init Refers to the lowest reasonable output gas pressure value in the initial welding area. Refers to the complex path deviation value, Refers to the reflectivity deviation value.

7. A manufacturing equipment monitoring system based on artificial intelligence, characterized in that: The system comprises: a data acquisition module, an initial welding area calibration module, a first output air pressure value generation module, an image analysis module, a reflectivity value acquisition module and a second output air pressure value generation module, wherein: A data acquisition module, used to acquire real-time monitoring data of the surface of the target workpiece and a preset complex path numerical comparison model when the target laser welding equipment performs welding operation on the target workpiece; The preset complex path numerical control model refers to a refined mapping benchmark of the association between the target workpiece surface image and the path complexity, in which the surface image of each area of ​​the target workpiece is assigned a specific complex path value by analyzing the geometric characteristics of curvature change, turning density, line segment length change and surface texture complexity; The division of different areas is based on the variation of complex path values. Only when the difference in complex path values ​​between adjacent areas exceeds a preset threshold, they are defined as independent areas. An initial welding area calibration module is used to determine the welding area that the target laser welding equipment contacts for the first time and that meets the specified range of the complex path value by combining the real-time monitoring data and the complex path value comparison model, and calibrate the welding area as the initial welding area; The complex path numerical value specified range refers to a specific numerical interval used to screen the target workpiece surface area. Only the target workpiece surface area that meets the complex path numerical value specified range will be determined as the welding area with the demand for dynamic gas pressure adjustment; The first output gas pressure value generating module is used to perform dynamic gas pressure optimization analysis on the initial welding area, and determine the lowest reasonable output gas pressure value of the auxiliary gas output in the initial welding area in combination with the real-time monitoring data; An image analysis module is used to obtain the surface image of the subsequent welding area of ​​the target workpiece along the preset welding path, and identify the designated welding area that meets the specified range of the complex path value according to the complex path value comparison model, and determine the specific complex path value of the initial welding area and each designated welding area; A reflectivity value acquisition module is used to acquire reflectivity values ​​of the initial welding area and the designated welding area of ​​the target workpiece along a preset welding path with the initial welding area as the initial point; The second output pressure value generating module is used to calculate the minimum reasonable output pressure value corresponding to each designated welding area by combining the deviation degree of the complex path value and the deviation degree of the reflectivity value between each designated welding area and the initial welding area.

8. The artificial intelligence-based manufacturing equipment monitoring system according to claim 7 is characterized in that: The initial welding area calibration module specifically includes: An image acquisition unit is used to intelligently analyze real-time monitoring data and intermittently capture the surface image of the target workpiece in the real-time monitoring video; The model parsing unit is used to input each intercepted target workpiece surface image into the complex path numerical comparison model, match the corresponding designated complex path numerical value in the complex path numerical comparison model, and determine whether the designated complex path numerical value falls within the designated range of the complex path numerical value; The initial welding area calibration unit is used to determine that the welding area corresponding to a target workpiece surface image is the welding area that the target laser welding equipment contacts for the first time and meets the specified range of complex path values, and calibrate it as the initial welding area when the complex path value of a target workpiece surface image meets the specified range of complex path values.

9. The artificial intelligence-based manufacturing equipment monitoring system according to claim 8, characterized in that: The first output air pressure value generating module specifically includes: Dynamic gas pressure analysis unit, used to gradually increase the output pressure of auxiliary gas in the initial welding area, and observe the slag cleaning situation in the initial welding area in real time in combination with real-time monitoring data; The first output gas pressure value generating unit is used to determine that when the output gas pressure value reaches a certain value and the slag is sufficiently cleaned, the certain value is the lowest reasonable output gas pressure value of the auxiliary gas output in the initial welding area.

10. The artificial intelligence-based manufacturing equipment monitoring system according to claim 9, characterized in that: The second output air pressure value generating module specifically includes: A complex path deviation value generating unit is used to quantify the degree of deviation of the complex path value of each designated welding area relative to the initial welding area to obtain a complex path deviation value; A reflectivity deviation value generating unit, used for quantifying the deviation degree of the reflectivity value of each designated welding area relative to the initial welding area to obtain a reflectivity deviation value; The second output pressure value generating unit is used to call a preset reasonable pressure value calculation formula, and calculate the corresponding minimum reasonable output pressure value in combination with the complex path deviation value and the reflectivity deviation value of each designated welding area; The preset reasonable air pressure value calculation formula is: ; Where P n Refers to the lowest reasonable output pressure value corresponding to the nth specified welding area, C n Refers to the specific complex path value of the nth specified welding area, C init Refers to the specific complex path value of the initial welding area, R n Refers to the reflectivity value of the nth specified welding area, R init Refers to the reflectivity value of the initial welding area, w path refers to the weight of the complex path numerical deviation, w reflect Refers to the weight of the reflectivity numerical deviation, P init Refers to the lowest reasonable output gas pressure value in the initial welding area. Refers to the complex path deviation value, Refers to the reflectivity deviation value.

Images