Laser welding monitoring system and monitoring method

Abstract

According to the laser welding monitoring system, the material type and welding information of the to-be-machined workpiece are determined through the workpiece determining strategy, and corresponding welding data are indexed in a welding database to be set as welding parameters according to the material type and welding position information of the to-be-machined workpiece; the pre-welding device is driven to weld the pre-welded workpiece to the surface of a workpiece to be machined; an image, collected by a visual camera, of a pre-welding point is obtained to serve as a pre-welding image, the pre-welding image comprises images generated when different tensile forces act on a pre-welding workpiece, and the pre-welding image is analyzed according to a welding seam change strategy to obtain welding seam defect changes of the pre-welding point under the different acting forces; a welding quality value is obtained according to the welding seam defect change of the welding point and the tensile strength through a tensile value calculation formula, the welding quality is judged according to welding quality parameters, and if the welding quality is lower than a threshold value, a parameter adjusting command is output; and a parameter adjusting command is obtained, and the welding parameters are adjusted.

Description

Technical Field

[0001] The present invention relates to the technical field of laser welding, and more specifically, to a laser welding monitoring system and a monitoring method. Background Art

[0002] Laser welding is an efficient and precise welding method that uses a laser beam with a high energy density as a heat source; during the laser welding process, two groups of workpieces to be processed can be connected. During the welding process, due to factors such as the material of the workpieces to be processed and the welding position, the welding effect can be affected, and during the welding process, welding parameters such as current, voltage, and welding speed will all affect the welding quality; current welding technologies directly detect the weld seams after welding. For some large workpieces to be processed, when there are unqualified welded products, timely treatment cannot be carried out. Summary of the Invention

[0003] Aiming at the deficiencies of the existing technology, the purpose of the present invention is to provide a laser welding monitoring system and a monitoring method to overcome the above-mentioned defects in the existing technology.

[0004] To achieve the above purpose, the present invention provides the following technical solutions:

[0005] A laser welding monitoring system includes

[0006] A pre-welding device, the pre-welding device includes a manipulator, a pre-welding workpiece is clamped on the manipulator, and a tensile sensor is arranged on the manipulator,

[0007] A welding information acquisition module; using a workpiece determination strategy to determine the material type and welding information of the workpiece to be processed, and indexing the corresponding welding data in the welding database as welding parameters according to the material type and welding position information of the workpiece to be processed;

[0008] A pre-welding module: driving the pre-welding device to weld the pre-welding workpiece on the surface of the workpiece to be processed;

[0009] A welding detection module: obtaining an image of the pre-welding point collected by a vision camera as a pre-welding image, the pre-welding image includes images of different tensile forces acting on the pre-welding workpiece, analyzing the weld defect changes of the pre-welding point under different acting forces according to the weld change strategy, obtaining a welding quality value by calculating the weld defect changes and the tensile strength of the welding point through a tensile value calculation formula, judging the welding quality according to the welding quality parameters, and if the welding quality is lower than the threshold, outputting a parameter adjustment command, otherwise outputting a normal welding command;

[0010] A welding parameter adjustment module, used to obtain a parameter adjustment command and adjust the welding parameters.

[0011] Preferably, for the weld seam change strategy, a pre-welding image is analyzed by a target detection model to obtain a pre-welding weld seam area. When the pre-welding weld seam area changes, the pre-welding area is calculated through vertex pixels to obtain weld seam change defects, and weld seam defect data is obtained through a defect calculation formula. The weld seam change defects include defect size, defect type, and defect quantity.

[0012] Preferably, the defect calculation formula is configured as:

[0013]

[0014] where D represents weld seam defect data, N represents the quantity of weld seam defects, w i represents the size weight of the i-th weld seam defect, S i represents the size of the i-th weld seam defect, A i represents the area of the region where the i-th weld seam defect is located, v i represents the type weight of the i-th weld seam defect, C i represents the type of the i-th weld seam defect, T i represents the temperature of the region where the i-th weld seam defect is located.

[0015] Preferably, the tensile value calculation formula is configured as:

[0016]

[0017] where Q is the welding quality value, S(t) represents the tensile strength at time t, D(t) represents the weld seam defect data at time t, and λ is a decay factor used to adjust the weights of data at different time points.

[0018] Preferably, a heat transfer tester and a heat conduction device are connected to the workpiece to be processed. A heat conduction data set is stored in the welding database, and the heat conduction data set corresponds to metal materials one by one. The workpiece determination strategy includes

[0019] a heat conduction detection step of using the heat conduction device to adjust the temperature of the workpiece to be processed and detecting and obtaining the thermal conductivity of the material through a heat conduction instrument;

[0020] a material determination step of indexing the corresponding metal material as the material type in the welding database according to the thermal conductivity.

[0021] Preferably, the workpiece determination strategy includes

[0022] Welding position determination steps: Obtain the image of the workpiece to be processed captured by the vision sensor as the welding image, analyze the relative positions of two groups of workpieces to be processed according to the target detection model, and determine the welding position information, where the welding position information includes the intersection position, butt joint position, T-joint position, corner joint position, etc.

[0023] Preferably, a de-welding device is also provided on the pre-welding device, and the de-welding device is used to heat the welding points on the pre-welded workpiece and then de-weld.

[0024] Preferably, a welding verification module is further included. The welding verification module uses the image of the two groups of workpieces after welding as the image to be analyzed, obtains the weld area through the feature extraction strategy, analyzes the temperature field distribution of the weld area, and identifies the temperature abnormal area. If there is no temperature abnormal area, the welding is qualified; otherwise, it is judged that the welding is unqualified, and the weld defect features are extracted according to the image processing algorithm, and the weld defect type is output according to the matching of the weld defect features.

[0025] Preferably, a defect processing sub-module is also provided in the welding verification module. The defect processing sub-module is used to obtain the weld defect type and generate a repair welding command or an abnormal instruction according to the weld defect type.

[0026] A laser welding monitoring method includes

[0027] Welding information acquisition steps: Use the workpiece determination strategy to determine the material type and welding information of the workpiece to be processed, and index the corresponding welding data in the welding database as welding parameters according to the material type and welding position information of the workpiece to be processed;

[0028] Pre-welding step: Drive the pre-welding device to weld the pre-welded workpiece on the surface of the workpiece to be processed;

[0029] Welding detection steps: Obtain the image of the pre-welding point collected by the vision camera as the pre-welding image. The pre-welding image includes images of different tensile forces acting on the pre-welded workpiece. Analyze the weld defect changes of the pre-welding point under different forces according to the weld change strategy, and obtain the welding quality value by calculating the tensile value of the weld defect change of the welding point and the tensile strength. Judge the welding quality according to the welding quality parameters. If the welding quality is lower than the threshold, output a parameter adjustment command; otherwise, output a normal welding command;

[0030] Welding parameter adjustment steps, used to obtain the parameter adjustment command and adjust the welding parameters.

[0031] Advantages of the present invention: By using a pre-welding device, welding can be performed on the surface to be processed. With the use of a welding device, pre-detection of welding parameters can be carried out, and rapid adjustment of welding parameters can be achieved, improving the accuracy and quality of welding. At the same time, the pre-welded workpiece can be quickly de-welded without affecting the normal use of the workpiece to be processed; by using heat conduction detection and image detection, the material type and welding position information of the workpiece to be processed can be quickly obtained, and corresponding welding parameters can be retrieved and set according to the material information and welding position information, improving the welding quality; and through tensile testing, the quality of the pre-welded part can be detected, and the welding quality can be evaluated by detecting the changes in the weld seam and the corresponding weld defects under different tensile forces, and the weld seam parameters can be adjusted according to the welding quality, thereby further improving the welding quality.

[0032] Using a welding verification module, the images of two groups of workpieces to be processed after welding are detected, the welding quality is evaluated, whether there are welding defects is judged, the type of weld defect is judged, and targeted adjustments are made according to the type of weld defect to improve the welding success rate. Brief Description of the Drawings

[0033] Figure 1 is the control flow chart of the present invention. Detailed Embodiments

[0034] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0035] It should be noted that when a component is referred to as being "fixed to" another component, it can be directly on the other component or there may also be an intermediate component. When a component is considered to be "connected" to another component, it can be directly connected to the other component or there may be an intermediate component at the same time. When a component is considered to be "disposed on" another component, it can be directly disposed on the other component or there may be an intermediate component at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs. The terms used in the specification of this invention are only for the purpose of describing specific embodiments, and are not intended to limit the invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0037] The following further details the embodiments of the present invention in conjunction with the accompanying drawings:

[0038] A laser welding monitoring system includes

[0039] A pre-welding device, which includes a manipulator. A pre-welding workpiece is clamped on the manipulator, and a tensile sensor is arranged on the manipulator. The pre-welding device is arranged on the laser welding device. By using the pre-welding device, the pre-welding workpiece is clamped to facilitate the clamping and welding between the pre-welding workpiece and the workpiece to be processed, and pre-welding detection is realized. And a tensile sensor is arranged on the manipulator. After pre-welding is completed, the pre-welding workpiece is pulled by the manipulator to realize the detection of welding strength. And by using the tensile sensor, the tensile strength acting on the pre-welding workpiece is monitored in real time to facilitate the detection of pre-welding strength and improve the welding quality.

[0040] A welding information acquisition module; using a workpiece determination strategy to determine the material type and welding information of the workpiece to be processed, and indexing the corresponding welding data in the welding database as welding parameters according to the material type and welding position information of the workpiece to be processed; using the heat conduction detection in the workpiece strategy to determine the material type of the workpiece to be processed, and determining the welding position of the workpiece to be processed through image processing technology. According to the material type and welding position information of the workpiece to be processed, appropriate welding parameters are retrieved and set in the welding database, and the welding parameters include welding current, voltage, welding speed, welding material, etc.;

[0041] A heat transfer tester and a heat conduction device are connected to the workpiece to be processed. A heat conduction data set is stored in the welding database, and the heat conduction data set corresponds to metal materials one by one. The heat transfer tester and the heat conduction device are connected to the workpiece to be processed. The workpiece determination strategy includes

[0042] A heat conduction detection step, using the heat conduction device to adjust the temperature of the workpiece to be processed, and detecting and obtaining the heat conductivity of the material through the heat conduction instrument. The temperature of the workpiece to be processed is adjusted by the heat conduction device, which includes two processes: heating and cooling. The heating process is used to increase the temperature of the workpiece to reach the temperature range required for heat conduction testing, and the cooling process is used to observe the heat conduction characteristics of the workpiece during the temperature reduction process. During the temperature adjustment process, the heat conductivity of the workpiece to be processed is monitored and recorded in real time by the heat conduction instrument;

[0043] Material determination step: Index the corresponding metal material in the welding database as the material type according to the thermal conductivity; compare the measured thermal conductivity with the thermal conductivity dataset in the welding database. In the welding database, the metal material type corresponds to the thermal conductivity data. Perform a matching analysis on the measured thermal conductivity and the data in the welding database according to the algorithm to find the metal material type with the highest matching degree with the measured value.

[0044] The workpiece determination strategy includes

[0045] Welding position determination step: Obtain the image of the workpiece to be processed captured by the vision sensor as the welding image. Analyze the relative positions of two groups of workpieces to be processed based on the target detection model and determine the welding position information. The welding position information includes the intersection position, butt joint position, T-joint position, corner joint position, etc.; Use the vision sensor to capture the image of the workpiece to be processed. The image includes the complete shape, size, and possible welding area of the workpiece to be processed. Analyze the welding image using the target detection model. Based on the deep learning neural network, it can identify the key features of the image and output the relative position information of two groups of workpieces to be processed, including position coordinates, size, and shape features. Determine the welding position information according to the analysis results of the target detection model. The welding position information includes the intersection position, butt joint position, T-joint position, and intersection joint position; The intersection position is where two groups of workpieces to be processed intersect and overlap; The butt joint position is where two groups of workpieces to be processed are arranged opposite to each other and butt joint; The T-joint position is the position relationship where the end face of one workpiece to be processed forms a right angle or an approximate right angle with the surface of another workpiece to be processed; The corner joint position is the joint position where two groups of workpieces to be processed form a certain angle.

[0046] Pre-welding module: Drive the pre-welding device to weld the pre-welding workpiece on the surface of the workpiece to be processed. After the workpiece to be processed is installed, use the pre-welding module to send a drive command and drive the pre-welding device to weld the pre-welding workpiece on the workpiece to be processed to achieve pre-welding;

[0047] Welding detection module: obtain the image of the pre-welding point collected by the visual camera as the pre-welding image, which includes images of different tensile forces acting on the pre-welding workpiece. According to the weld change strategy, the pre-welding image analysis obtains the weld defect change of the pre-welding point under different forces, and the weld defect change of the welding point and the tensile strength are calculated by the tensile value formula to obtain the welding quality value. The welding quality is judged according to the welding quality parameters. If the welding quality is lower than the threshold, the parameter adjustment command is output, otherwise the normal welding command is output; the image of the pre-welding point is collected by the visual camera, and the pre-welding image includes the image of the welding point under different tensile forces, and the pre-welding image is respectively Perform analysis, identify parameters such as weld shape, length, width, etc. according to the weld change strategy, and observe the changes of these parameters under different tensile forces. On the basis of weld change analysis, detect whether there is a cutting line in the weld, such as a crack, etc., associate the weld defect change of the welding point with the tensile strength through the stretching calculation formula, and calculate the welding conscience. The welding quality value is used to evaluate the quality of welding. A threshold is preset in the welding detection module. When the welding quality value is lower than the threshold, the parameter adjustment command is output to adjust the welding parameters and improve the welding quality. If the welding quality meets the standard, the normal welding command is output to continue the welding operation.

[0048] Weld change strategy, the pre-welding image is analyzed through the target detection model to obtain the pre-welding weld area. When the pre-welding weld area changes, the pre-welding area is calculated through the item point pixel calculation to obtain the weld change defect, and the weld defect data is obtained through the defect calculation formula. The weld change defect includes defect size, defect type and defect quantity; Yu Xun is used to obtain the target detection model, and the target detection model is used to accurately analyze the pre-welding image. The model can accurately identify and extract the weld area, and continuously monitor the identified weld area to observe the changes under different tensile forces. The detection design compares multiple image frames to detect slight changes in the weld area. When the weld area changes, the item point pixel calculation is used to quantify the change. According to the item point pixel calculation results, it is a century-old weld change defect, and the defect calculation formula is used to obtain similar data of weld defects, including defect size, cut-in line type and quantity.

[0049] The defect calculation formula is configured as:

[0050]

[0051] Where D represents the weld defect data, N represents the number of weld defects, and w i represents the size weight of the i-th weld defect, S i represents the size of the ith weld defect, A i represents the area where the ith weld defect is located, v iRepresents the type weight of the i-th weld defect, C i Represents the type of the i-th weld defect, T i Represents the temperature of the area where the i-th weld defect is located, and the weld defect data is collected and obtained using the defect calculation formula.

[0052] The tensile value calculation formula is configured as:

[0053]

[0054] Where Q is the welding quality value, S(t) represents the tensile strength at time t, D(t) represents the weld defect data at time t, and λ is a decay factor used to adjust the weights of data at different time points.

[0055] The welding parameter adjustment module is used to obtain the parameter adjustment command and adjust the welding parameters to achieve the best welding effect.

[0056] The pre-welding device is also provided with a de-welding device, which is used to heat and de-weld the welding points on the pre-welded workpiece; the pre-welded points are heated using heat energy to make the weld metal reach the melting point, and the pre-welded workpiece is separated from the workpiece to be processed, facilitating the recycling of the pre-welded workpiece without affecting the normal use of the workpiece to be processed.

[0057] It also includes a welding verification module. The welding verification module uses the images after welding of two groups of workpieces to be processed as the images to be analyzed. The weld area is obtained through the feature extraction strategy, and the temperature field distribution of the weld area is analyzed to identify the temperature abnormal area. If there is no temperature abnormal area, the welding is qualified; otherwise, it is judged that the welding is unqualified. The weld defect features are extracted according to the image processing algorithm, and the weld defect types are output according to the matching of the weld defect features. The images after welding are collected as the images to be analyzed. The images to be analyzed contain the complete information of the weld area. Using the feature extraction strategy, the weld area is extracted from the images to be analyzed, and the temperature field of the weld area is analyzed. Whether there is a temperature abnormal area is detected. By comparing the weld area, it is judged whether there is a temperature abnormal area. According to the analysis result of the temperature field, it is judged whether the welding is qualified. If there is no temperature abnormal area, the welding is qualified; if there is a temperature abnormal area, the welding is unqualified. For the unqualified welding images, the weld defect features are extracted using the image processing algorithm. The weld defect features include cracks, lack of fusion, pores, etc. The extracted weld defect features are matched with the preset weld defect types, and according to the matching result, the weld defect types are output, and the next instruction for welding is given according to the weld defect types.

[0058] When there is a temperature anomaly area in the image to be analyzed and the temperature of this area is significantly different from the temperature of the surrounding welds, it is a crack defect. The crack may appear as a thin black line, with fine tips at both ends and the blackness gradually disappearing. When there is an irregular temperature anomaly area in the image to be analyzed, which appears around the midpoint between the center and the edge of the weld and has a relatively wide line, it is lack of fusion. When there are small circular or nearly circular low-temperature areas in the image, they are pores, and the size, shape, and distribution of the pores can all be identified through temperature differences, etc.

[0059] A defect processing sub-module is also set in the welding verification module. The defect processing sub-module is used to obtain the type of weld defect and generate a repair welding command or an abnormal instruction according to the type of weld defect. Using the defect sub-module, analyze the welding defect to determine whether the weld defect can be repaired. When the identified defect types are pores, lack of fusion, etc., the weld can be welded again to make up for it. If there are irreparable defects such as cracks, etc., then mark the product and use other means for processing.

[0060] A laser welding monitoring method, characterized by including

[0061] A welding information acquisition step; using a workpiece determination strategy to determine the material type and welding information of the workpiece to be processed, and indexing the corresponding welding data in the welding database as welding parameters according to the material type and welding position information of the workpiece to be processed;

[0062] A pre-welding step: driving a pre-welding device to weld a pre-welding workpiece on the surface of the workpiece to be processed;

[0063] A welding detection step: obtaining the image of the pre-welding point collected by a vision camera as a pre-welding image. The pre-welding image includes images of different tensile forces acting on the pre-welding workpiece. Analyze the change of the weld defect at the pre-welding point under different acting forces according to the weld change strategy, and obtain the welding quality value by calculating the tensile value of the change of the weld defect at the welding point and the tensile strength. Judge the welding quality according to the welding quality parameters. If the welding quality is lower than the threshold, output a parameter adjustment command, otherwise output a normal welding command;

[0064] A welding parameter adjustment step, used to obtain a parameter adjustment command and adjust the welding parameters.

[0065] The above are only the preferred embodiments of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions falling within the concept of the present invention belong to the protection scope of the present invention. It should be noted that for those of ordinary skill in the art in this technical field, several improvements and refinements made without departing from the principle of the present invention should also be regarded as the protection scope of the present invention..

Claims

1. A laser welding monitoring system, characterized in that, including a pre-welding device, the pre-welding device includes a manipulator, a pre-welding workpiece is clamped on the manipulator, and a tensile sensor is arranged on the manipulator, a welding information acquisition module; determining the material type and welding information of the workpiece to be processed by using a workpiece determination strategy, and indexing the corresponding welding data in the welding database as welding parameters according to the material type and welding position information of the workpiece to be processed; a pre-welding module: driving the pre-welding device to weld the pre-welding workpiece on the surface of the workpiece to be processed; a welding detection module: obtaining an image of the pre-welding point collected by a vision camera as a pre-welding image, the pre-welding image includes images of different tensile forces acting on the pre-welding workpiece, analyzing the pre-welding image according to a weld change strategy to obtain the weld defect change of the pre-welding point under different acting forces, obtaining a welding quality value by using the weld defect change of the welding point and the tensile strength through a tensile value calculation formula, judging the welding quality according to the welding quality parameter, if the welding quality is lower than the threshold, outputting a parameter adjustment command, otherwise outputting a normal welding command; a welding parameter adjustment module, configured to obtain a parameter adjustment command and adjust the welding parameters.

2. The laser welding monitoring system according to claim 1, wherein For the weld change strategy, analyzing the pre-welding image through a target detection model to obtain the pre-welding weld area, when the pre-welding weld area changes, calculating the weld change defect of the pre-welding area through vertex pixels, and obtaining weld defect data through a defect calculation formula, the weld change defect includes defect size, defect type and defect quantity.

3. The laser welding monitoring system according to claim 2, characterized in that, The defect calculation formula is configured as: Among them, D represents the weld defect data, N represents the number of weld defects, w i represents the size weight of the i-th weld defect, S i represents the size of the i-th weld defect, A i represents the area of the region where the i-th weld defect is located, v i represents the type weight of the i-th weld defect, C i represents the type of the i-th weld defect, T i represents the temperature of the region where the i-th weld defect is located.

4. The laser welding monitoring system according to claim 1, wherein The tensile value calculation formula is configured as: Where Q is the welding quality value, S(t) represents the tensile strength at time t, D(t) represents the weld defect data at time t, and λ is a decay factor used to adjust the weights of data at different time points.

5. A laser welding monitoring system according to claim 1, characterized in that, A heat transfer tester and a heat conduction device are connected to the workpiece to be processed, a heat conduction data set is stored in the welding database, the heat conduction data set corresponds to metal materials one by one, and the workpiece determination strategy includes a heat conduction detection step, using the heat conduction device to adjust the temperature of the workpiece to be processed, and detecting and obtaining the heat conductivity of the material through a heat conduction instrument; a material determination step, indexing the corresponding metal material in the welding database as the material type according to the heat conductivity.

6. The laser welding monitoring system according to claim 1, characterized in that, The workpiece determination strategy includes a welding position determination step, obtaining an image of the workpiece to be processed captured by a vision sensor as a welding image, analyzing the relative positions of two groups of workpieces to be processed through a target detection model, and determining welding position information, the welding position information includes intersection position, butt joint position, T-joint position, corner joint position, etc.

7. A laser welding monitoring system according to claim 1, wherein, A de-welding device is further arranged on the pre-welding device, and the de-welding device is used to heat the welding point on the pre-welding workpiece and then de-weld it.

8. A laser welding monitoring system according to claim 1, wherein, It further includes a welding verification module, which uses the image of two sets of workpieces to be processed after welding as the image to be analyzed, obtains the weld area through a feature extraction strategy, analyzes the temperature field distribution of the weld area, identifies the temperature abnormal area. If there is no temperature abnormal area, the welding is qualified; otherwise, it is judged that the welding is unqualified, and the weld defect features are extracted according to the image processing algorithm, and the weld defect type is output according to the matching of the weld defect features.

9. The laser welding monitoring system according to claim 8, characterized in that, A defect processing sub-module is further set in the welding verification module, and the defect processing sub-module is used to obtain the weld defect type and generate a repair welding command or an abnormal instruction according to the weld defect type.

10. A laser welding monitoring method, characterized in that, including Welding information acquisition step: Use the workpiece determination strategy to determine the material type and welding information of the workpiece to be processed, and index the corresponding welding data in the welding database as welding parameters according to the material type and welding position information of the workpiece to be processed; Pre-welding step: Drive the pre-welding device to weld the pre-welding workpiece on the surface of the workpiece to be processed; Welding detection step: Obtain the image of the pre-welding point collected by the vision camera as the pre-welding image. The pre-welding image includes the images of different tensile forces acting on the pre-welding workpiece. According to the weld change strategy, analyze the weld defect changes of the pre-welding point under different forces from the pre-welding image, obtain the welding quality value by calculating the weld defect changes of the welding point and the tensile strength through the tensile value calculation formula, and judge the welding quality according to the welding quality parameters. If the welding quality is lower than the threshold, output a parameter adjustment command; otherwise, output a normal welding command; Welding parameter adjustment step, used to obtain the parameter adjustment command and adjust the welding parameters.

Images