A method and system for tracking weld seam of welded pipe laser welding

Abstract

The present invention relates to the technical field of laser welding, and provides a method and system for tracking the weld seam of laser welding of welded pipes, the method comprising: obtaining the allowable deviation parameters of the weld seam of the welded pipe; obtaining the total number of visual calibration images according to the allowable deviation parameters of the weld seam of the welded pipe, the preset weld delay tracking time, the accuracy of the calibration plate, and the predicted environmental parameters; visually calibrating the camera; and tracking the weld seam of the welded pipe based on the camera after visual calibration. The present invention takes into account the allowable deviation parameters of the weld seam of the welded pipe, the preset weld delay tracking time, the accuracy of the calibration plate, and the predicted environmental parameters, and can set the number of calibration images required for camera calibration based on different welded pipe types or welding requirements and the weld tracking accuracy required in the actual application of laser welding weld tracking of welded pipes, so as to balance the weld tracking accuracy with the time and computing resources required for camera calibration, and has good flexibility and a wide range of applications.

Description

Technical Field

[0001] The present invention relates to the technical field of laser welding, and in particular to a method and system for tracking weld seams in laser welding of welded pipes. Background Art

[0002] Welded steel pipes, also known as welded pipes, are steel pipes made by welding steel plates or strips after curling and forming. In recent years, with the development and maturity of visual image processing technology, people have increasingly used visual sensors to obtain images of laser welded welds in actual welded pipe laser welding applications, and track and monitor the welds based on the weld images to ensure the quality of welded pipe welds. Since the calibration accuracy of the camera has a crucial impact on the quality of visual tracking, it is generally necessary to visually calibrate the camera before using visual sensors to track and monitor welded pipe welds to determine the internal and external parameters of the camera.

[0003] In order to improve the camera calibration accuracy, the number of calibration images can be increased to calibrate the camera. Increasing the number of calibration images means that more image processing time and computing resources are required. In the actual application of weld seam tracking in laser welding of welded pipes, different weld pipe types or welding requirements often correspond to different weld seam tracking accuracy and quality.

[0004] The Chinese invention patent with announcement number CN107649802B discloses a laser vision weld tracking system and calibration method, which calibrates the camera to better achieve weld tracking. When calibrating the camera, the number of calibration images required for camera calibration is not set according to the weld tracking accuracy requirements, and the weld tracking accuracy and the time and computing resources required for camera calibration are not well balanced, which needs to be improved. Summary of the invention

[0005] Based on this, in order to solve the problems existing in the prior art, the present invention provides a weld seam tracking method and system for laser welding of welded pipes, which obtains the total number of visual calibration images based on the allowable deviation parameters of the weld seam of the welded pipe, the preset weld seam delay tracking time, the calibration plate accuracy and the predicted environmental parameters, and collects multiple calibration plate images of different angles and positions according to the total number of visual calibration images to perform visual calibration on the camera, comprehensively considers multiple different factors to set the number of calibration images required for camera calibration, can well balance the weld seam tracking accuracy and the time and computing resources required for camera calibration, and can better realize the tracking of the weld seam of laser welding of welded pipes. The specific technical scheme is as follows:

[0006] A method for tracking weld seams during laser welding of a welded pipe comprises the following steps:

[0007] Obtaining a target welded pipe type, and obtaining a weld seam allowable deviation parameter of the welded pipe according to the target welded pipe type;

[0008] Obtaining the accuracy of the calibration plate, the preset weld delay tracking time, and the predicted environmental parameters during the laser welding process, and obtaining the total number of visual calibration images according to the weld allowable deviation parameter of the welded pipe, the preset weld delay tracking time, the accuracy of the calibration plate, and the predicted environmental parameters;

[0009] Collecting a plurality of calibration plate images at different angles and positions according to the total number of visual calibration images, and performing visual calibration on the camera according to the calibration plate images;

[0010] The camera after visual calibration collects the weld seam image of the welded pipe, and tracks the weld seam of the welded pipe according to the weld seam image of the welded pipe.

[0011] The weld seam tracking method for laser welding of welded pipes obtains the calibration plate accuracy, preset weld seam delay tracking time and predicted environmental parameters during the laser welding process, obtains the total number of visual calibration images according to the weld seam allowable deviation parameter of the weld seam, the preset weld seam delay tracking time, the calibration plate accuracy and the predicted environmental parameters, and collects multiple calibration plate images at different angles and positions according to the total number of visual calibration images to perform visual calibration on the camera. The method takes into account the weld seam allowable deviation parameter of the weld seam, the preset weld seam delay tracking time, the calibration plate accuracy and the predicted environmental parameters, and can set the number of calibration images required for camera calibration based on different weld pipe types or welding requirements and the weld seam tracking accuracy required in the actual application of weld seam tracking for laser welding of welded pipes, so as to balance the weld seam tracking accuracy with the time and computing resources required for camera calibration. The method has good flexibility and a wide range of applications.

[0012] Preferably, the weld seam tracking method for laser welding of welded pipe further comprises the following steps:

[0013] According to the collected weld seam images of the welded pipe, multi-dimensional weld seam defect information of the welded pipe is obtained;

[0014] Based on the multi-dimensional welded pipe weld defect information, obtaining a welded pipe weld quality index;

[0015] A laser welding parameter constraint model is constructed, and the laser welding parameters are corrected according to the weld quality index of the welded pipe and the laser welding parameter constraint model.

[0016] Preferably, the weld seam tracking method for laser welding of welded pipe further comprises the following steps:

[0017] Based on the corrected laser welding parameters, laser repair welding is performed on the defective parts of the weld seam of the welded pipe;

[0018] Obtain the weld quality index of the welded pipe at the weld defective part after laser repair welding;

[0019] Determine whether the weld quality index of the welded pipe is greater than a preset quality index threshold. If not, laser repair welding is performed on the defective weld of the welded pipe again until the weld quality index of the welded pipe at the defective weld of the welded pipe is greater than the preset quality index threshold.

[0020] Preferably, according to the formula Get the total number of visual calibration images;

[0021] in, represents the rounding function, , , Indicates the preset calibration image cardinality, represents a natural constant, Indicates the accuracy of the calibration plate, represents the intermediate variable, Indicates the preset weld delay tracking time. represents the environmental correction factor, , They represent the deviation parameter adjustment coefficient and the tracking time adjustment coefficient respectively. The total number of dimensions representing the allowable deviation parameters of the weld seam of the welded pipe. Indicates The allowable deviation parameter value of the weld seam of the welded pipe in each dimension, The total number of dimensions representing the predicted environmental parameters that are greater than the preset environmental parameter threshold. Indicates The predicted environmental parameter values ​​of dimensions that are greater than the preset environmental parameter thresholds, Representation and The corresponding preset environmental parameter thresholds, Representation and The corresponding environmental parameter adjustment coefficient.

[0022] Preferably, based on the multi-dimensional welded pipe weld defect information, a specific method for obtaining a welded pipe weld quality index comprises the following steps:

[0023] Constructing a weld defect grade detection model, and obtaining the weld defect grade of each dimension of the welded pipe according to the weld defect grade detection model;

[0024] According to the weld defect level of each dimension of the welded pipe, the weld quality index of the welded pipe is obtained. ;

[0025] in, The total number of dimensions representing the multi-dimensional welded pipe weld defect information, Indicates The weld defect level of welded pipe in three dimensions.

[0026] Preferably, the specific method for tracking the weld seam of the welded pipe according to the weld seam image of the welded pipe comprises the following steps:

[0027] Acquire the real-time position information and movement trend of the weld seam of the weld pipe according to the weld seam image of the weld pipe;

[0028] The position of the welding gun is adjusted according to the real-time position information, the movement trend and the preset weld path trajectory, so that the actual weld path trajectory is consistent with the preset weld path trajectory, thereby realizing tracking and monitoring of the weld of the welded pipe.

[0029] A weld seam tracking system for laser welding of welded pipes, used to implement the weld seam tracking method for laser welding of welded pipes, comprising:

[0030] A parameter acquisition module is used to acquire the target welded pipe type, acquire the weld seam allowable deviation parameter of the welded pipe according to the target welded pipe type, acquire the calibration plate accuracy, preset weld seam delay tracking time and predicted environmental parameters during laser welding;

[0031] The total number of images acquisition module is used to acquire the total number of visual calibration images according to the allowable deviation parameter of the weld seam of the welded pipe, the preset weld seam delay tracking time, the accuracy of the calibration plate and the predicted environmental parameters;

[0032] A visual calibration module, used to collect a plurality of calibration plate images at different angles and positions according to the total number of visual calibration images, and perform visual calibration on the camera according to the calibration plate images;

[0033] The weld tracking module is used to collect the weld image of the welded pipe based on the visually calibrated camera, and track the weld of the welded pipe according to the weld image.

[0034] Preferably, the welded pipe laser welding weld tracking system further comprises:

[0035] A defect information acquisition module is used to acquire multi-dimensional welded pipe weld defect information based on the collected welded pipe weld image;

[0036] A quality index acquisition module, used to acquire the weld quality index of the welded pipe based on the multi-dimensional weld defect information of the welded pipe;

[0037] Constraint model building module, used to build laser welding parameter constraint model;

[0038] The welding parameter correction module is used to correct the laser welding parameters according to the weld quality index of the welded pipe and the laser welding parameter constraint model.

[0039] Preferably, the welded pipe laser welding weld tracking system further comprises:

[0040] The control module is used to control the laser action to perform laser repair welding on the defective part of the weld seam of the welded pipe based on the corrected laser welding parameters, and to determine whether the weld seam quality index of the welded pipe is greater than a preset quality index threshold. If not, the laser action is controlled again to perform laser repair welding on the defective part of the weld seam of the welded pipe until the weld seam quality index of the defective part of the weld seam of the welded pipe is greater than the preset quality index threshold. If so, it is determined that the repair welding of the defective part of the weld seam of the welded pipe is completed, and the current step is exited to perform other operations in the next step.

[0041] Preferably, the image total number acquisition module is based on the formula Get the total number of visual calibration images;

[0042] in, represents the rounding function, , , Indicates the preset calibration image cardinality, represents a natural constant, Indicates the accuracy of the calibration plate, represents the intermediate variable, Indicates the preset weld delay tracking time. represents the environmental correction factor, , They represent the deviation parameter adjustment coefficient and the tracking time adjustment coefficient respectively. The total number of dimensions representing the allowable deviation parameters of the weld seam of the welded pipe. Indicates The allowable deviation parameter value of the weld seam of the welded pipe in each dimension, The total number of dimensions representing the predicted environmental parameters that are greater than the preset environmental parameter threshold. Indicates The predicted environmental parameter values ​​of dimensions that are greater than the preset environmental parameter thresholds, Representation and The corresponding preset environmental parameter thresholds, Representation and The corresponding environmental parameter adjustment coefficient.

[0043] Preferably, the constraint model building module builds a laser welding parameter constraint model according to the target welded pipe type and the performance parameters of the laser, and the laser welding parameters include laser power, laser power density, welding speed and defocus amount. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The present invention can be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily drawn to scale, but the emphasis is placed on illustrating the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0045] Figure 1 It is a schematic diagram of the overall process of a weld seam tracking method for laser welding of a welded pipe in one embodiment of the present invention;

[0046] Figure 2 FIG. 1 is a schematic diagram of a process of tracking a weld seam of a welded pipe laser welding according to another embodiment of the present invention. Figure 1 ;

[0047] Figure 3 It is a flow chart of a specific method for obtaining a weld quality index of a welded pipe in one embodiment of the present invention;

[0048] Figure 4 FIG. 1 is a schematic diagram of a process of tracking a weld seam of a welded pipe laser welding according to another embodiment of the present invention. Figure 2 ;

[0049] Figure 5 It is a schematic diagram of the structural relationship between the laser, welding pipe and blowing device in one embodiment of the present invention.

[0050] Description of reference numerals:

[0051] 1. Laser; 2. Air blowing device; 3. Welded pipe. DETAILED DESCRIPTION

[0052] 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 its embodiments. It should be understood that the specific implementation methods described herein are only used to explain the present invention and do not limit the protection scope of the present invention.

[0053] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only and do not represent the only implementation method.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0055] The “first” and “second” mentioned in the present invention do not represent specific quantities and orders, but are merely used to distinguish names.

[0056] Before describing the embodiments of the present invention, a brief introduction to the prior art is given first.

[0057] With the continuous development of robotics technology, visual tracking has become an indispensable part of many robotic applications. Camera calibration is the first step to achieve visual tracking. It can obtain the internal and external parameters of the camera by shooting the pattern on the calibration plate, including the focal length, distortion coefficient, optical center position, etc. of the camera, to ensure the accuracy of the collected image and thus ensure the quality of visual tracking.

[0058] Factors such as calibration plate accuracy, the number and quality of calibration images, and environmental parameters will affect the accuracy of camera calibration. In other words, the accuracy of camera calibration has a crucial impact on the quality of visual tracking. In order to improve the accuracy of camera calibration, the camera can be calibrated by selecting a calibration plate with higher accuracy or increasing the number of calibration images. In this process, the impact of environmental factors on camera calibration can also be taken into account. However, increasing the number of calibration images means that more image processing time and computing resources such as computer memory are required. If the number of calibration images is too small, the accuracy of camera calibration will be reduced. In the actual application of weld seam tracking of welded pipe laser welding, different weld pipe types or welding requirements often have different corresponding weld seam tracking qualities. This makes it possible to determine the number of calibration images according to actual conditions, so as to balance the weld seam tracking accuracy and the time and computing resources required for camera calibration on the basis of meeting the weld seam tracking accuracy and quality requirements in actual applications, thereby improving the flexibility and intelligence of weld seam tracking, and improving the overall quality and efficiency of weld seam tracking.

[0059] In order to determine the number of calibration images according to the actual situation, so as to balance the weld tracking accuracy and the time and computing resources required for camera calibration on the basis of meeting the weld tracking accuracy quality requirements in actual applications, such as Figure 1 As shown, the present invention provides a weld seam tracking method for laser welding of a welded pipe, comprising the following steps:

[0060] S1, obtaining a target welded pipe type, and obtaining a weld seam allowable deviation parameter of the welded pipe according to the target welded pipe type.

[0061] Welded pipes can be classified in many ways according to different classification standards, mainly including classification by manufacturing method, purpose, standard and material. According to the manufacturing method, the target welded pipe types include but are not limited to long welded pipes, spiral welded pipes and straight seam welded pipes. According to the material, the target welded pipe types include carbon welded pipes, stainless steel welded pipes and alloy welded pipes.

[0062] For different types of target welded pipes, the corresponding welded pipe weld allowable deviation parameters are also different. The welded pipe weld allowable deviation parameters here include length allowable deviation, width allowable deviation and height allowable deviation. The allowable deviation can be understood as the maximum allowable difference range between the actual measured value and the preset expected value.

[0063] The specific method for obtaining the allowable deviation parameters of the weld seam of the welded pipe according to the target welded pipe type includes: obtaining different target welded pipe types and the allowable deviation parameters of the weld seam of the welded pipe corresponding to different types of target welded pipes in advance, and constructing a mapping relationship according to different target welded pipe types and the corresponding allowable deviation parameters of the weld seam of the welded pipe, and then obtaining the allowable deviation parameters of the weld seam of the welded pipe according to the constructed mapping relationship and the specific target welded pipe type.

[0064] S2, obtaining the calibration plate accuracy, the preset weld delay tracking time and the predicted environmental parameters during the laser welding process, and obtaining the total number of visual calibration images according to the weld allowable deviation parameter of the welded pipe, the preset weld delay tracking time, the calibration plate accuracy and the predicted environmental parameters.

[0065] The allowable deviation parameter of the weld seam of the welded pipe is related to the accuracy of camera calibration. When the allowable deviation parameter of the weld seam of the welded pipe is large, the accuracy requirement of camera calibration can be appropriately reduced; on the contrary, if the allowable deviation parameter of the weld seam of the welded pipe is small, the accuracy of camera calibration needs to be improved accordingly. The accuracy of the calibration plate will also affect the accuracy of camera calibration. Under certain camera calibration accuracy, the higher the accuracy of the calibration plate, the fewer the number of corresponding visual calibration images required, and the lower the accuracy of the calibration plate, the more visual calibration images are required.

[0066] In addition, the preset weld delay tracking time is also related to the accuracy of camera calibration. During the welding process of the weld pipe, a certain amount of smoke and arc light will be generated. The shorter the preset weld delay tracking time, the more likely the image quality collected by the camera will be affected by smoke and arc light and reduced. In other words, on the basis that the quality of the camera calibration image may be affected by smoke and arc light and reduced, if the quality of the weld pipe weld tracking is to be maintained, it is necessary to appropriately collect more camera calibration images from different angles. Therefore, the shorter the preset weld delay tracking time, the more it is necessary to improve the accuracy of camera calibration to ensure the accuracy and reliability of the weld pipe weld tracking.

[0067] As for environmental parameters, especially the environmental parameters in the process of capturing weld seam images with the camera to track the weld seam of the weld pipe, they will also affect the accuracy of camera calibration. Since the environmental parameters in the process of welding the weld pipe are often different from those in the process of not welding the weld pipe, sometimes they may differ greatly, such as ambient temperature and light intensity. When acquiring the total number of visual calibration images, this embodiment takes into account the predicted environmental parameters instead of the environmental parameters in the process of not welding the weld pipe, which is more in line with the actual situation in the process of laser welding of the weld pipe, and can avoid the reduction of camera calibration accuracy due to fluctuations in environmental parameters. As for the predicted environmental parameters, they can be obtained by finite element simulation, or based on the actual environmental parameters in the laser welding process of a limited number of different types of target weld pipes in the past, such as taking the weighted average of the historical environmental parameters as the predicted environmental parameters.

[0068] By obtaining the total number of visual calibration images according to the allowable deviation parameter of the welded pipe weld, the preset weld delay tracking time, the accuracy of the calibration plate and the predicted environmental parameters, it is possible to take into account factors of different dimensions that affect the accuracy of camera calibration, so as to better determine the number of calibration images according to actual conditions, and balance the weld tracking accuracy with the time and computing resources required for camera calibration on the basis of meeting the weld tracking accuracy quality requirements in actual applications, so as to avoid the problem of reducing the welded pipe weld tracking quality due to insufficient camera calibration images, failing to meet the actual welded pipe weld tracking quality requirements, or consuming more image processing time and computing resources such as computer memory due to too many camera calibration images, thereby reducing the overall efficiency of weld tracking.

[0069] Preferably, in step S2, according to the formula Get the total number of visual calibration images;

[0070] in, represents the rounding function, , , Indicates the preset calibration image cardinality, represents a natural constant, Indicates the accuracy of the calibration plate, It represents the intermediate variable, which can be understood as the average value of the allowable deviation parameter value of the weld seam of the multi-dimensional welded pipe. Indicates the preset weld delay tracking time. represents the environmental correction factor, , They represent the deviation parameter adjustment coefficient and the tracking time adjustment coefficient respectively. The total number of dimensions representing the allowable deviation parameters of the weld seam of the welded pipe. Indicates The allowable deviation parameter value of the weld seam of the welded pipe in each dimension, The total number of dimensions representing the predicted environmental parameters that are greater than the preset environmental parameter threshold. Indicates The predicted environmental parameter values ​​of dimensions that are greater than the preset environmental parameter thresholds, Representation and The corresponding preset environmental parameter thresholds, Representation and The corresponding environmental parameter adjustment coefficient.

[0071] Here, the accuracy of the calibration plate is related to the allowable deviation value of the weld seam of the welded pipe. Under the condition of preset calibration image base, environmental correction factor and preset weld delay tracking time, the total number of visual calibration images is It is proportional to the ratio between the accuracy of the calibration plate and the average value of the allowable deviation parameter value of the multi-dimensional welded pipe weld.

[0072] In the actual application of laser welding seam tracking of welded pipes, it is found that under certain conditions of preset calibration image base, environmental correction factor and preset weld delay tracking time and on the basis of meeting the weld tracking accuracy quality requirements in actual applications, the higher the calibration plate accuracy, the greater the average value of the multi-dimensional welded pipe weld allowable deviation parameter value, and the total number of visual calibration images can be reduced accordingly; if the calibration plate accuracy is reduced, the average value of the multi-dimensional welded pipe weld allowable deviation parameter value is reduced, and the total number of visual calibration images can be increased accordingly. This maximum reduction or increase in the total number of visual calibration images is consistent with It shows a strong positive correlation. Therefore, by associating the calibration plate accuracy with the allowable deviation value of the weld seam of the welded pipe, a more appropriate total number of calibration images that conforms to the actual situation can be obtained. On the basis of meeting the weld seam tracking accuracy quality requirements in actual applications, the weld seam tracking accuracy and the time and computing resources required for camera calibration are balanced to avoid the problem of reducing the weld seam tracking quality of the welded pipe due to insufficient camera calibration images, not meeting the actual weld seam tracking quality requirements, or consuming more image processing time and computing resources such as computer memory due to too many camera calibration images, reducing the overall efficiency of weld seam tracking.

[0073] Specifically, the preset calibration image cardinality range is 5-8, and the deviation parameter adjustment coefficient and the tracking time adjustment coefficient are 0.61 and 0.26 respectively. When calculating the total number of visual calibration images according to the formula, the variables in the formula can be dimensionless. For other formulas of the present invention, dimensionless processing can also be performed when calculating the variables as needed.

[0074] S3, collecting a plurality of calibration plate images at different angles and positions according to the total number of the visual calibration images, and performing visual calibration on the camera according to the calibration plate images.

[0075] Specifically, the estimated values ​​of the camera's internal and external parameters are obtained based on the collected real-time calibration plate image, and the estimated values ​​of the internal and external parameters are iteratively optimized through an optimization iterative method to obtain the optimal internal and external parameters, thereby completing the camera's visual calibration.

[0076] Since calibrating a camera based on a visual calibration image is a conventional technique in the art, it will not be described in detail here.

[0077] S4, collecting a weld seam image of the welded pipe based on the visually calibrated camera, and tracking the weld seam of the welded pipe according to the weld seam image of the welded pipe.

[0078] Specifically, the weld seam image of the welded pipe is first processed and analyzed to identify and extract the position and shape of the weld seam, and then the motion trajectory and speed of the weld seam are calculated according to the change of the weld seam position in the continuous weld seam image frame, and finally, according to the real-time position information and motion trend of the weld seam, combined with the preset weld seam path trajectory, the position where the welding gun should move next is predicted, so as to adjust the position of the welding gun in time, so that the actual weld seam path trajectory is consistent with the preset weld seam path trajectory, and the tracking and monitoring of the weld seam of the welded pipe is realized. Since tracking and monitoring the weld seam of the welded pipe according to the weld seam image of the welded pipe belongs to the conventional technical means in this field, it will not be repeated here.

[0079] By collecting images of weld seams of welded pipes based on visually calibrated cameras and balancing the weld seam tracking accuracy with the time and computing resources required for camera calibration, the tracking and monitoring of weld seams of laser welded pipes can be better achieved, so that the quality of weld seams of laser welded pipes can meet the specific needs of customers, improve the flexibility and comprehensive performance of laser welding of welded pipes, and have a wide range of applications.

[0080] In summary, the weld seam tracking method for laser welding of welded pipes obtains the calibration plate accuracy, the preset weld seam delay tracking time and the predicted environmental parameters during the laser welding process, obtains the total number of visual calibration images according to the weld seam allowable deviation parameters of the weld seam, the preset weld seam delay tracking time, the calibration plate accuracy and the predicted environmental parameters, and collects multiple calibration plate images at different angles and positions according to the total number of visual calibration images to perform visual calibration on the camera. The method takes into account the weld seam allowable deviation parameters of the weld seam, the preset weld seam delay tracking time, the calibration plate accuracy and the predicted environmental parameters, and can be based on For different weld pipe types or welding requirements, the number of calibration images required for camera calibration is set according to the weld seam tracking accuracy required in the actual application of weld pipe laser welding weld seam tracking, and the weld seam tracking accuracy is balanced with the time and computing resources required for camera calibration. This can avoid the problem of reducing the weld seam tracking quality of weld pipes due to insufficient camera calibration images, failing to meet the actual weld seam tracking quality requirements, or consuming more image processing time and computing resources such as computer memory due to too many camera calibration images, thereby reducing the overall efficiency of weld seam tracking. It has good flexibility and a wide range of applications.

[0081] As a preferred technical solution, Figure 2 As shown, the weld seam tracking method for laser welding of welded pipes also includes the following steps:

[0082] S5, obtaining multi-dimensional weld seam defect information of the weld pipe according to the collected weld seam image of the weld pipe.

[0083] Specifically, the multi-dimensional welded pipe weld defect information includes but is not limited to sand holes, pores, cracks, collapse, insufficient welding depth, undercut and spatter. The specific method for obtaining multi-dimensional welded pipe weld defect information based on the welded pipe weld image includes: performing image processing on the welded pipe weld image, extracting the contour shape, gray value, gradient value or gradient direction of the area of ​​interest based on the edge detection extraction algorithm, and identifying specific defect information.

[0084] Since the identification of weld defect information of welded pipes based on image recognition technology is a conventional technical means in this field, it will not be described in detail here.

[0085] S6, obtaining a weld quality index of the weld based on the multi-dimensional weld defect information of the weld.

[0086] Preferably, in step S6, Figure 3 As shown, based on the multi-dimensional welded pipe weld defect information, a specific method for obtaining a welded pipe weld quality index comprises the following steps:

[0087] S61, constructing a weld defect level detection model, and obtaining the weld defect level of each dimension of the welded pipe according to the weld defect level detection model; the weld defect level detection model includes a plurality of weld defect level detection functions of welded pipes in different dimensions.

[0088] Specifically, the weld defect level detection function of the welded pipe ,in, Indicates the weld defect level of welded pipe. Indicates the defect level adjustment coefficient, which can be set by technicians; It represents the characteristic value of weld defects of welded pipes, which can be extracted based on the weld defect information of welded pipes and characterize the size of weld defects of welded pipes; It indicates the preset welded pipe weld defect characteristic threshold, which is set by the technicians. The welded pipe weld defect grade indicates the severity of the welded pipe weld defect. The larger the grade, the more serious the welded pipe weld defect.

[0089] The welded pipe weld defect grade detection function based on multiple different dimensions Constructing a weld defect grade detection model can quickly obtain the weld defect grade of each dimension of the welded pipe.

[0090] S62, according to the weld defect level of each dimension of the welded pipe, obtain the weld quality index of the welded pipe ;in, The total number of dimensions representing the multi-dimensional welded pipe weld defect information, Indicates The weld defect level of welded pipe in three dimensions.

[0091] Here, according to the weld defect level of each dimension of the welded pipe, obtaining the weld quality index of the welded pipe can be understood as obtaining the weld defect level of each dimension of the welded pipe weld area of ​​the preset length or area, and obtaining the weld quality index of the welded pipe according to the weld defect level of each dimension. From the formula It can be seen that the larger the sum of the weld defect levels of the welded pipe in multiple dimensions, the more serious the overall defects, and the smaller the corresponding weld quality index of the welded pipe, that is, the worse the weld quality of the welded pipe.

[0092] Compared with the prior art that only judges the weld quality based on a single dimension of welded pipe weld defect information, the present invention obtains the weld quality index of the weld by the weld defect level of each dimension of the weld, which can more comprehensively reflect the weld quality of the weld and provide a clearer reference for technical personnel so that the weld defect area of ​​the weld can be processed accordingly.

[0093] S7, constructing a laser welding parameter constraint model, and correcting the laser welding parameters according to the weld quality index of the welded pipe and the laser welding parameter constraint model.

[0094] The laser welding parameter constraint model is used to limit laser welding parameters, including but not limited to upper and lower limits of parameters and change rates.

[0095] Generally speaking, the quality of welded pipe welds can be optimized by adjusting laser welding parameters. Laser welding speed is one of the important factors affecting the quality of welded pipe welds. Too fast welding speed will lead to unstable molten pool, reduce the width of fusion zone, make weld surface rough and uneven, and easily cause defects such as sand holes, V-shaped fish scales and small or even no weld excess height; while too slow welding speed will lead to the spread of overheated area, which is also prone to defects such as sand holes.

[0096] Correcting the laser welding parameters according to the weld pipe weld quality index and the laser welding parameter constraint model can be understood as improving the weld pipe weld quality by timely and real-time adjustment of laser welding parameters such as laser welding speed, laser power, shielding gas and defocus amount.

[0097] Preferably, a laser welding parameter constraint model can be constructed according to the target welded pipe type and the performance parameters of the laser. The laser welding parameters include but are not limited to laser power , laser power density , welding speed and defocus .

[0098] Specifically, the laser welding parameter constraint model is expressed as ;in, , , , They represent the preset minimum laser power, the preset minimum laser power density, the preset minimum welding speed and the preset minimum defocus amount, respectively. , , , They respectively represent the preset maximum laser power, the preset maximum laser power density, the preset maximum welding speed and the preset maximum defocus amount.

[0099] The laser welding parameters are corrected according to the weld pipe weld quality index and the laser welding parameter constraint model in detail as follows: based on the laser welding parameter constraint model, the laser welding parameters are corrected according to the weld pipe weld quality index.

[0100] Furthermore, the laser welding parameter optimization function is constructed .

[0101] Represents looking for a set of laser welding parameters , maximize the weld quality index of the welded pipe. Specifically, the variable laser power , laser power density , welding speed and defocus As the independent variable, the weld quality index of the welded pipe is used as the dependent variable. Through finite element simulation or iterative optimization method, the weld quality index of the welded pipe is maximized to obtain the optimal laser welding parameter set. . In obtaining the optimal laser welding parameter set After that, according to the optimal laser welding parameter set Correct the laser welding parameters so that the current laser welding parameters are consistent with the optimal laser welding parameter combination. Matches and satisfies the laser welding parameter constraint model.

[0102] In this way, the optimal laser welding parameter set is obtained by constructing the laser welding parameter optimization function. And correct the laser welding parameters so that the current laser welding parameters are consistent with the optimal laser welding parameter combination. Matching can improve the response speed of laser welding of welded pipes, timely and dynamically correct and optimize laser welding parameters, reduce laser welding defects of welded pipes, and improve its overall welding quality.

[0103] As a preferred technical solution, Figure 4 As shown, the weld seam tracking method for laser welding of welded pipes also includes the following steps:

[0104] S8, based on the corrected laser welding parameters, laser repair welding is performed on the defective parts of the weld seam of the welded pipe.

[0105] S9, obtaining the weld quality index of the welded pipe at the weld defective position after laser repair welding.

[0106] S10, judging whether the weld quality index of the welded pipe is greater than a preset quality index threshold, if not, performing laser repair welding on the defective weld of the welded pipe again until the weld quality index of the defective weld of the welded pipe is greater than the preset quality index threshold.

[0107] The preset quality index threshold can be set by a technician. By laser repair welding the defective part, the weld quality of the laser welded pipe can be improved as a whole, and the performance of the welded pipe after laser welding can be guaranteed.

[0108] The present invention also provides a weld seam tracking system for laser welding of welded pipes, which is used to implement the weld seam tracking method for laser welding of welded pipes, and comprises a parameter acquisition module, an image total acquisition module, a visual calibration module and a weld seam tracking module.

[0109] The parameter acquisition module is used to obtain the target weld pipe type, obtain the weld pipe weld allowable deviation parameters according to the target weld pipe type, obtain the calibration plate accuracy, the preset weld delay tracking time and the predicted environmental parameters during laser welding; the total number of images acquisition module is used to obtain the total number of visual calibration images according to the weld pipe weld allowable deviation parameters, the preset weld delay tracking time, the calibration plate accuracy and the predicted environmental parameters.

[0110] For different types of target welded pipes, the corresponding welded pipe weld allowable deviation parameters are also different. The welded pipe weld allowable deviation parameters here include length allowable deviation, width allowable deviation and height allowable deviation. The allowable deviation can be understood as the maximum allowable difference range between the actual measured value and the preset expected value.

[0111] Of course, the corresponding laser welding parameters will be different for different types of target welded pipes. For example, for 0.5-2.0mm stainless steel welded pipes, the laser power is generally between 800-1350W, the scanning width is between 0.2-0.3MM, the penetration depth is between 0.15-0.2MM, and the focus position is between -0.1MM-0.0MM. For 1.0-2.0mm aluminum alloy welded pipes, the recommended laser power is 1200-1500W, the scanning width is 0.3-0.4mm, the penetration depth is 0.2-0.3mm, and the focus position needs to be just right. If welding 0.5mm carbon steel welded pipes, the laser power should be 900-1100W, the scanning width is 0.2-0.3mm, the penetration depth range is 0.1-0.15mm, and the focus position is fine-tuned to -0.05mm. When welding 0.5mm galvanized welded pipe, the recommended laser power is 700-900W, the scanning width is 0.15-0.25mm, and the penetration depth is between 0.05-0.1mm.

[0112] The specific method for obtaining the allowable deviation parameters of the weld seam of the welded pipe according to the target welded pipe type includes: obtaining different target welded pipe types and the allowable deviation parameters of the weld seam of the welded pipe corresponding to different types of target welded pipes in advance, and constructing a mapping relationship according to different target welded pipe types and the corresponding allowable deviation parameters of the weld seam of the welded pipe, and then obtaining the allowable deviation parameters of the weld seam of the welded pipe according to the constructed mapping relationship and the specific target welded pipe type.

[0113] Preferably, the image total number acquisition module is based on the formula Get the total number of visual calibration images;

[0114] in, represents the rounding function, , , Indicates the preset calibration image cardinality, represents a natural constant, Indicates the accuracy of the calibration plate, represents the intermediate variable, Indicates the preset weld delay tracking time. represents the environmental correction factor, , They represent the deviation parameter adjustment coefficient and the tracking time adjustment coefficient respectively. The total number of dimensions representing the allowable deviation parameters of the weld seam of the welded pipe. Indicates The allowable deviation parameter value of the weld seam of the welded pipe in each dimension, The total number of dimensions representing the predicted environmental parameters that are greater than the preset environmental parameter threshold. Indicates The predicted environmental parameter values ​​of dimensions that are greater than the preset environmental parameter thresholds, Representation and The corresponding preset environmental parameter thresholds, Representation and The corresponding environmental parameter adjustment coefficient.

[0115] The preset weld delay tracking time is between 0.1S and 0.5S, and the specific value can be set by the technician based on experience.

[0116] Preferably, the specific method for obtaining the preset weld delay tracking time includes: first setting a standard weld delay tracking time, such as 0.2 seconds or 0.3 seconds, etc., and a grayscale pixel threshold, and after completing camera calibration, obtaining a plurality of weld pipe weld images within the standard weld delay tracking time at the first welding point, i.e., the starting point of the laser welding weld of the weld pipe, and then processing the plurality of weld pipe weld images, respectively obtaining the grayscale pixel value of the smoke arc area in each weld pipe weld image, and obtaining the time difference between the acquisition time of the first weld pipe weld image and the acquisition time of a weld pipe weld image whose grayscale pixel value is less than the grayscale pixel threshold according to the grayscale pixel value of the smoke arc area in each weld pipe weld image. This time difference can be understood as the time required from the generation of smoke arc at the welding point to the reduction and dissipation of the smoke arc to an acceptable range (that is, the grayscale pixel value of the smoke arc area is less than the grayscale pixel threshold); when obtaining the time difference Finally, the average value of the allowable deviation parameter value of the multi-dimensional welded pipe weld and the standard weld delay tracking time are combined to obtain a better preset weld delay tracking time.

[0117] Specifically, based on the standard weld delay tracking time If the average value of the allowable deviation is small or the time difference is small, the standard weld delay tracking time can be shortened accordingly. To obtain the preset weld delay tracking time, improve the response speed of laser welding parameter correction, ensure the quality of welded pipe welds, and avoid defects such as sand holes and cracks in welds due to untimely correction of laser welding parameters. At the same time, it can also avoid the problem that the preset weld delay tracking time is too long, which causes the inability to track the weld in time and adjust the welding gun position, resulting in the actual weld path trajectory being inconsistent with or differing greatly from the preset weld path trajectory. If the allowable deviation average value is large or the time difference is large, the standard weld delay tracking time can be increased accordingly. To obtain the preset weld delay tracking time, minimize the impact of smoke and arc light on image acquisition, ensure the quality of the acquired weld pipe weld image, and meet the actual weld pipe weld tracking quality requirements (which can be understood as the weld pipe weld path trajectory quality requirements) and weld pipe weld quality requirements.

[0118] More specifically, preset weld delay tracking time ;in, , These are the delay tracking time adjustment weights set by technical personnel.

[0119] In this way, combined with the time difference , the average value of the allowable deviation and the standard weld delay tracking time can obtain a better preset weld delay tracking time, balance the quality of the collected weld pipe weld images and the timeliness and response speed of weld pipe weld tracking, and ensure the overall quality of the weld pipe weld.

[0120] Here, the accuracy of the calibration plate is related to the allowable deviation value of the weld seam of the welded pipe. Under the condition of preset calibration image base, environmental correction factor and preset weld delay tracking time, the total number of visual calibration images is It is proportional to the ratio between the accuracy of the calibration plate and the average value of the allowable deviation parameter value of the multi-dimensional welded pipe weld.

[0121] In the actual application of laser welding seam tracking of welded pipes, it is found that under certain conditions of preset calibration image base, environmental correction factor and preset weld delay tracking time and on the basis of meeting the weld tracking accuracy quality requirements in actual applications, the higher the calibration plate accuracy, the greater the average value of the multi-dimensional welded pipe weld allowable deviation parameter value, and the total number of visual calibration images can be reduced accordingly; if the calibration plate accuracy is reduced, the average value of the multi-dimensional welded pipe weld allowable deviation parameter value is reduced, and the total number of visual calibration images can be increased accordingly. This maximum reduction or increase in the total number of visual calibration images is consistent with It shows a strong positive correlation.

[0122] Therefore, by associating the accuracy of the calibration plate with the allowable deviation value of the weld seam of the welded pipe, a more appropriate total number of calibration images that conforms to the actual situation can be obtained. On the basis of meeting the weld seam tracking accuracy quality requirements in actual applications, the weld seam tracking accuracy and the time and computing resources required for camera calibration are balanced to avoid the problem of reducing the weld seam tracking quality of the welded pipe due to insufficient camera calibration images, failing to meet the actual weld seam tracking quality requirements, or consuming more image processing time and computing resources such as computer memory due to too many camera calibration images, thereby reducing the overall efficiency of weld seam tracking.

[0123] The visual calibration module is used to collect multiple calibration plate images of different angles and positions according to the total number of visual calibration images, and visually calibrate the camera according to the calibration plate images. The weld tracking module is used to collect weld images of welded pipes based on the visually calibrated camera, and track the welds of the welded pipes according to the weld images of the welds.

[0124] Since there are interference factors such as arc light and smoke around the weld point of the laser welding of the welded pipe, it will reduce the image quality of the welded pipe weld, thereby reducing the accuracy of the welded pipe weld trajectory acquisition. By setting the preset weld delay tracking time and using the calibrated camera to delay the acquisition of the weld image of the current weld point, the influence of the arc light and smoke of the weld point on the weld image acquisition of the welded pipe can be avoided, and a clearer and higher quality welded pipe weld image can be obtained, thereby improving the accuracy of the welded pipe weld trajectory acquisition.

[0125] In summary, the weld tracking system for laser welding of welded pipes obtains the calibration plate accuracy, the preset weld delay tracking time and the predicted environmental parameters during the laser welding process, obtains the total number of visual calibration images according to the weld allowable deviation parameters of the welded pipe, the preset weld delay tracking time, the calibration plate accuracy and the predicted environmental parameters, and collects multiple calibration plate images at different angles and positions according to the total number of visual calibration images to perform visual calibration on the camera. It takes into account the factors such as the weld allowable deviation parameters of the welded pipe, the preset weld delay tracking time, the calibration plate accuracy and the predicted environmental parameters, and can be based on For different weld pipe types or welding requirements, the number of calibration images required for camera calibration is set according to the weld seam tracking accuracy required in the actual application of weld pipe laser welding weld seam tracking, and the weld seam tracking accuracy is balanced with the time and computing resources required for camera calibration. This can avoid the problem of reducing the weld seam tracking quality of weld pipes due to insufficient camera calibration images, failing to meet the actual weld seam tracking quality requirements, or consuming more image processing time and computing resources such as computer memory due to too many camera calibration images, thereby reducing the overall efficiency of weld seam tracking. It has good flexibility and a wide range of applications.

[0126] As a preferred technical solution, the weld seam tracking system for laser welding of welded pipes also includes a defect information acquisition module, a quality index acquisition module, a constraint model construction module and a welding parameter correction module.

[0127] The defect information acquisition module is used to obtain multi-dimensional welded pipe weld defect information based on the collected welded pipe weld image; the quality index acquisition module is used to obtain the welded pipe weld quality index based on the multi-dimensional welded pipe weld defect information. ;in, The total number of dimensions representing the multi-dimensional welded pipe weld defect information, Indicates The weld defect level of welded pipe in three dimensions.

[0128] Here, according to the weld defect level of each dimension of the welded pipe, obtaining the weld quality index of the welded pipe can be understood as obtaining the weld defect level of each dimension of the welded pipe weld area of ​​the preset length or area, and obtaining the weld quality index of the welded pipe according to the weld defect level of each dimension. From the formula It can be seen that the larger the sum of the weld defect levels of the welded pipe in multiple dimensions, the more serious the overall defects, and the smaller the corresponding weld quality index of the welded pipe, that is, the worse the weld quality of the welded pipe.

[0129] Compared with the prior art that only judges the weld quality based on a single dimension of welded pipe weld defect information, the present invention obtains the weld quality index of the weld by the weld defect level of each dimension of the weld, which can more comprehensively reflect the weld quality of the weld and provide a clearer reference for technical personnel so that the weld defect area of ​​the weld can be processed accordingly.

[0130] The constraint model building module is used to build a laser welding parameter constraint model; the welding parameter correction module is used to correct the laser welding parameters according to the weld quality index of the welded pipe and the laser welding parameter constraint model.

[0131] Since a preset weld delay tracking time is set, the influence of arc smoke from welding spots on the weld image acquisition of welded pipes can be avoided to obtain clearer and higher quality weld images of welded pipes. In addition to improving the accuracy of weld trajectory acquisition of welded pipes, the accuracy of weld quality index can also be improved, so as to more accurately correct laser welding parameters and optimize the overall quality of welded pipes.

[0132] The constraint model building module builds a laser welding parameter constraint model according to the target welded pipe type and the performance parameters of the laser, wherein the laser welding parameters include laser power, laser power density, welding speed and defocus amount.

[0133] Preferably, the laser welding parameter constraint model is expressed as ;in, , , , They represent the preset minimum laser power, the preset minimum laser power density, the preset minimum welding speed and the preset minimum defocus amount, respectively. , , , They respectively represent the preset maximum laser power, the preset maximum laser power density, the preset maximum welding speed and the preset maximum defocus amount.

[0134] The preset minimum laser power, the preset minimum laser power density, the preset minimum welding speed, the preset minimum defocus, the preset maximum laser power, the preset maximum laser power density, the preset maximum welding speed and the preset maximum defocus can all be set by the technicians according to the type of welded pipe and in combination with production experience. For example, in one case, for stainless steel, carbon steel and aluminum alloy welded pipes with a thickness of 0.5-2.0 mm, the preset welding speed range can be 50-80 mm / s, and for stainless steel, carbon steel and aluminum alloy welded pipes with a thickness of 2.0-5.0 mm, the preset welding speed range can be 30-50 mm / s.

[0135] After correcting the laser welding parameters, laser welding is performed on the welded pipe area to be welded based on the corrected laser welding parameters and the preset weld path trajectory. In practical applications, after laser welding of 2.0MM stainless steel welded pipes based on the welded pipe laser welding weld tracking system, the weld is overall flat and uniform without obvious unevenness, and the width of the weld remains relatively consistent over the entire weld length, and there are no obvious cracks, sand holes, pores and other defects on the weld surface. The overall quality of the stainless steel welded pipe laser welding weld is excellent.

[0136] The weld quality index of the welded pipe and the laser welding parameter constraint model can timely and dynamically correct and optimize the laser welding parameters, thereby improving the response speed of the welded pipe laser welding, reducing the defects of the welded pipe laser welding, and improving the overall welding quality.

[0137] Preferably, the weld seam tracking system for welded pipe laser welding further includes a control module.

[0138] The control module is used to control the laser to perform laser repair welding on the defective part of the weld seam of the welded pipe based on the corrected laser welding parameters, and to determine whether the weld seam quality index of the welded pipe is greater than the preset quality index threshold. If not, the laser 1 is controlled again to perform laser repair welding on the defective part of the weld seam of the welded pipe until the weld seam quality index of the defective part of the weld seam of the welded pipe is greater than the preset quality index threshold.

[0139] like Figure 5 As shown, the laser 1 can be perpendicular to the weld, that is, perpendicular to the section of the welding point of the welded pipe 3, or at a certain inclination angle to the section, for example, the inclination angle is set between 30 degrees forward and 30 degrees backward; the welded pipe laser welding weld tracking system also includes a blowing device 2 for blowing protective gas to the side of the welding area.

[0140] The preset quality index threshold can be set by a technician. By laser repair welding the defective part, the weld quality of the laser welded pipe can be improved as a whole, and the performance of the welded pipe after laser welding can be guaranteed.

[0141] 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.

[0142] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. 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, and these 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.

Claims

1. A weld seam tracking method for laser welding of welded pipes, characterized in that: The weld seam tracking method for laser welding of welded pipe comprises the following steps: Obtaining a target welded pipe type, and obtaining a weld seam allowable deviation parameter of the welded pipe according to the target welded pipe type; Obtaining the accuracy of the calibration plate, the preset weld delay tracking time, and the predicted environmental parameters during the laser welding process, and obtaining the total number of visual calibration images according to the weld allowable deviation parameter of the welded pipe, the preset weld delay tracking time, the accuracy of the calibration plate, and the predicted environmental parameters; Collecting a plurality of calibration plate images at different angles and positions according to the total number of visual calibration images, and performing visual calibration on the camera according to the calibration plate images; The camera collects the weld seam image of the welded pipe based on the visual calibration, and tracks the weld seam of the welded pipe according to the weld seam image of the welded pipe; The weld seam tracking method for laser welding of welded pipe also includes the following steps: According to the collected weld seam images of the welded pipe, multi-dimensional weld seam defect information of the welded pipe is obtained; Based on the multi-dimensional welded pipe weld defect information, obtaining a welded pipe weld quality index; Constructing a laser welding parameter constraint model, and correcting the laser welding parameters according to the weld quality index of the welded pipe and the laser welding parameter constraint model; Based on the corrected laser welding parameters, laser repair welding is performed on the defective parts of the weld seam of the welded pipe; Obtain the weld quality index of the welded pipe at the weld defective part after laser repair welding; Determine whether the weld quality index of the welded pipe is greater than a preset quality index threshold. If not, laser repair welding is performed on the defective weld of the welded pipe again until the weld quality index of the welded pipe at the defective weld of the welded pipe is greater than the preset quality index threshold.

2. A weld seam tracking method for laser welding of welded pipes as claimed in claim 1, characterized in that , according to the formula Get the total number of visual calibration images; Among them, [] represents the rounding function, PictureBasic represents the preset calibration image base, e represents the natural constant, Cc represents the calibration plate accuracy, μ represents the intermediate variable, T represents the preset weld delay tracking time, C represents the environmental correction factor, λ1 and λ2 represent the deviation parameter adjustment coefficient and the tracking time adjustment coefficient respectively, n represents the total number of dimensions of the allowable deviation parameter of the weld seam of the welded pipe, Dev i represents the allowable deviation parameter value of the weld seam of the welded pipe in the i-th dimension, m represents the total number of dimensions of the predicted environmental parameters that are greater than the preset environmental parameter threshold, PEP i Indicates the predicted environmental parameter value of the i-th dimension that is greater than the preset environmental parameter threshold, SEP i Representation and PEP i The corresponding preset environmental parameter threshold, α i Representation and PEP i The corresponding environmental parameter adjustment coefficient.

3. A weld seam tracking method for laser welding of welded pipes as claimed in claim 2, characterized in that Based on the multi-dimensional welded pipe weld defect information, a specific method for obtaining a welded pipe weld quality index includes the following steps: Constructing a weld defect grade detection model, and obtaining the weld defect grade of each dimension of the welded pipe according to the weld defect grade detection model; According to the weld defect level of each dimension of the welded pipe, the weld quality index of the welded pipe is obtained. Among them, k represents the total number of dimensions of multi-dimensional welded pipe weld defect information, ck i Represents the weld defect level of the welded pipe in the i-th dimension.

4. A weld seam tracking method for laser welding of welded pipes as claimed in claim 3, characterized in that The specific method for tracking the weld seam of the welded pipe according to the weld seam image of the welded pipe comprises the following steps: Acquire the real-time position information and movement trend of the weld seam of the weld pipe according to the weld seam image of the weld pipe; The position of the welding gun is adjusted according to the real-time position information, the movement trend and the preset weld path trajectory, so that the actual weld path trajectory is consistent with the preset weld path trajectory, thereby realizing tracking and monitoring of the weld of the welded pipe.

5. A weld seam tracking system for laser welding of welded pipes, used to implement the weld seam tracking method for laser welding of welded pipes as claimed in any one of claims 1 to 4, characterized in that: The welded pipe laser welding weld tracking system comprises: A parameter acquisition module is used to acquire the target welded pipe type, acquire the weld seam allowable deviation parameter of the welded pipe according to the target welded pipe type, acquire the calibration plate accuracy, preset weld seam delay tracking time and predicted environmental parameters during laser welding; The total number of images acquisition module is used to acquire the total number of visual calibration images according to the allowable deviation parameter of the weld seam of the welded pipe, the preset weld seam delay tracking time, the accuracy of the calibration plate and the predicted environmental parameters; A visual calibration module, used to collect a plurality of calibration plate images at different angles and positions according to the total number of visual calibration images, and perform visual calibration on the camera according to the calibration plate images; A weld tracking module, used to collect a weld image of a welded pipe based on a visually calibrated camera, and track the weld image of the welded pipe according to the weld image; The welded pipe laser welding weld tracking system also includes: A defect information acquisition module is used to acquire multi-dimensional welded pipe weld defect information based on the collected welded pipe weld image; A quality index acquisition module, used to acquire a weld quality index of the welded pipe based on the multi-dimensional weld defect information of the welded pipe; Constraint model building module, used to build laser welding parameter constraint model; A welding parameter correction module, used to correct the laser welding parameters according to the weld quality index of the welded pipe and the laser welding parameter constraint model; The control module is used to control the laser action to perform laser repair welding on the defective part of the weld seam of the welded pipe based on the corrected laser welding parameters, and to determine whether the weld seam quality index of the welded pipe is greater than a preset quality index threshold value. If not, the laser action is controlled again to perform laser repair welding on the defective part of the weld seam of the welded pipe until the weld seam quality index of the defective part of the weld seam of the welded pipe is greater than the preset quality index threshold value.

6. A weld seam tracking system for laser welding of welded pipes as claimed in claim 5, characterized in that: The total number of images is obtained according to the formula Get the total number of visual calibration images; Among them, [] represents the rounding function, PictureBasic represents the preset calibration image base, e represents the natural constant, Cc represents the calibration plate accuracy, μ represents the intermediate variable, T represents the preset weld delay tracking time, C represents the environmental correction factor, λ1 and λ2 represent the deviation parameter adjustment coefficient and the tracking time adjustment coefficient respectively, n represents the total number of dimensions of the allowable deviation parameter of the weld seam of the welded pipe, Dev i represents the allowable deviation parameter value of the weld seam of the welded pipe in the i-th dimension, m represents the total number of dimensions of the predicted environmental parameters that are greater than the preset environmental parameter threshold, PEP i Indicates the predicted environmental parameter value of the i-th dimension that is greater than the preset environmental parameter threshold, SEP i Representation and PEP i The corresponding preset environmental parameter threshold, α i Representation and PEP i The corresponding environmental parameter adjustment coefficient.

Images