Fusion method, system and equipment based on laser tracking and arc tracking

Abstract

The invention relates to the field of pipeline welding, in particular to a fusion method, system and equipment based on laser tracking and arc tracking. Acquiring laser tracking data and arc tracking data; a weld center line is extracted through a preset method, and weld feature points are extracted based on a preset weld geometric model; detecting a local extreme value in the arc tracking data, speculating the position deviation direction of the welding gun by using the local extreme value, calculating an extreme value difference value in the arc tracking data by using a preset integral method, and estimating the offset of the welding gun by using the extreme value difference value; the welding gun track is determined by utilizing the welding seam feature points extracted by the preset welding seam geometric model, the position deviation direction of the welding gun and the offset of the welding gun for welding guidance, accurate welding gun position estimation can be provided, the precision and stability of the welding process are improved, and the method is suitable for complex pipeline all-position welding operation.

Description

Technical Field

[0001] The present application relates to the field of pipeline welding, and in particular to a fusion method, system and equipment based on laser tracking and arc tracking. Background Art

[0002] In the field of pipeline welding, ensuring the quality of welds is of vital importance, and accurate positioning and tracking of welds are key links in achieving this goal.

[0003] Traditional weld tracking methods mainly rely on arc tracking, among which the current tracking method based on Hall sensors is more commonly used. Its principle is to use Hall sensors to detect the changes in the magnetic field generated by the current when the arc is working, and convert it into an electrical signal to transmit to the control system. The system infers the arc stability and weld deviation by analyzing the fluctuations in the current signal, and then adjusts the position of the welding equipment to keep the arc in the center of the weld. However, this method has many problems. On the one hand, its accuracy depends on the current fluctuation. When the arc is stable or the change amplitude is small, it is difficult to capture the tiny arc deviation, and the tracking accuracy is limited. On the other hand, it cannot directly obtain the spatial characteristics of the weld. When the weld shape is complex, the groove is irregular, and the workpiece surface is uneven, it is difficult to accurately track the arc, which easily causes the welding gun to deviate from the weld center. In addition, the entire arc tracking system is complex to debug, the current signal is easily interfered by external noise, and requires complex algorithm processing. In addition, for specific workpiece materials, such as high conductivity or special coating materials, its adaptability is poor.

[0004] As an emerging technology, active vision weld tracking technology using structured light projects structured light onto the welding surface and uses a camera to capture the deformation of the light bar to track the weld position. Compared with arc tracking, it can directly obtain geometric information of the weld surface, such as height, width, groove shape, etc., with higher accuracy and robustness, and is suitable for complex welds. However, this technology also faces challenges. It is sensitive to lighting and environmental conditions. Strong light or welding smoke can affect the deformation and reflection of the light bar, reducing the quality of image acquisition. At the same time, there are requirements for the flatness and reflectivity of the workpiece surface. Rough or low reflectivity surfaces can affect the projection effect of the light bar and tracking accuracy. Moreover, the system is complex, requires high-precision cameras and image processing algorithms, has high requirements for computing resources, and in specific welding environments, tracking information may be lost or errors may increase due to spatial occlusion or welding posture problems.

[0005] At present, laser tracking and arc tracking are often used independently in existing technologies, and their advantages have not yet been fully utilized for joint perception and spatial fusion. This also provides a research direction for the further development of pipeline welding weld tracking technology. Summary of the invention

[0006] In view of this, the purpose of the present invention is to provide a fusion method, system and equipment based on laser tracking and arc tracking to solve the technical problems existing in the prior art.

[0007] According to a first aspect of an embodiment of the present invention, a fusion method based on laser tracking and arc tracking is provided, the method comprising:

[0008] Obtain laser tracking data and arc tracking data;

[0009] Using the laser tracking data, obtaining first picture information;

[0010] Utilizing the first image information, extracting the weld centerline by a preset method, and extracting weld feature points based on a preset weld geometry model;

[0011] Detecting local extreme values ​​in the arc tracking data, inferring the position deviation direction of the welding gun using the local extreme values, calculating the extreme value difference in the arc tracking data using a preset integration method, and estimating the offset of the welding gun using the extreme value difference;

[0012] The laser tracking data, the arc tracking data, the weld feature points extracted by the preset weld geometry model, the position deviation direction of the welding gun, and the offset of the welding gun are integrated to determine the welding gun trajectory for welding guidance.

[0013] Further, the obtaining of laser tracking data includes:

[0014] Use a preset structured light sensor to project laser stripes of a specific pattern onto the surface of the object to be measured to obtain a stripe image;

[0015] The reflected fringe image is captured using a preset high-speed camera.

[0016] Further, the using the laser tracking data to obtain the first picture information includes:

[0017] Using median filtering method and Gaussian filtering method to remove the influence of ambient light and stray light in the fringe image;

[0018] A histogram equalization image enhancement algorithm is used to enhance the stripe contrast in the stripe image and the image clarity of the stripe image to obtain first picture information.

[0019] Furthermore, the extracting the weld centerline by a preset method using the first image information includes:

[0020] Using an edge detection algorithm to identify the position and contour of the laser stripes in the first image information, and to segment the area to distinguish the weld from the background area;

[0021] The center line is determined by least square curve fitting of the extracted laser stripe profile, and the continuity of the center line is optimized by morphological operation.

[0022] Furthermore, the extraction of weld feature points based on a preset weld geometry model includes:

[0023] Use prior knowledge of welding process to build weld geometry model, and use polynomial or ellipse mathematics to describe groove type, width, and angle parameters;

[0024] The constructed weld geometry model is used to extract key feature points of the weld through a feature extraction algorithm.

[0025] Further, the obtaining of arc tracking data includes:

[0026] The welding current signal is collected by using a Hall current sensor or a current transformer, and the arc voltage signal is collected by using a voltage transformer or a Hall voltage sensor;

[0027] The welding current signal and the arc voltage signal are respectively converted into digital forms by using a preset digital acquisition card to obtain a first welding current digital signal and a first arc voltage digital signal.

[0028] Furthermore, the method further comprises:

[0029] A low-pass filter is used to remove high-frequency noise in the first welding current digital signal and the first arc voltage digital signal, and a median filter is used to remove pulse interference in the first welding current digital signal and the first arc voltage digital signal.

[0030] Further, the fusion of the laser tracking data, the arc tracking data, and the weld feature points extracted by the preset weld geometry model, the position deviation direction of the welding gun, and the offset of the welding gun to determine the welding gun trajectory for welding guidance includes:

[0031] Using known calibration parameters, the laser tracking data and arc tracking data are uniformly converted into the same spatial coordinate system for data fusion, and the welding gun position is optimized using a Kalman filter algorithm;

[0032] And the welding gun trajectory is determined by utilizing the real-time feedback of the position deviation direction of the welding gun and the offset of the welding gun extracted by the preset welding gun geometric model for welding guidance.

[0033] According to a second aspect of an embodiment of the present invention, a fusion system based on laser tracking and arc tracking is provided, which is applied to any of the above-mentioned fusion methods based on laser tracking and arc tracking, and the system comprises:

[0034] An acquisition module, used for acquiring laser tracking data and arc tracking data;

[0035] A first processing module, used to obtain first image information using the laser tracking data;

[0036] A second processing module is used to extract the weld centerline by a preset method using the first image information, and to extract weld feature points based on a preset weld geometry model;

[0037] a third processing module, configured to detect a local extreme value in the arc tracking data, infer a position deviation direction of the welding gun using the local extreme value, calculate an extreme value difference in the arc tracking data using a preset integral method, and estimate an offset of the welding gun using the extreme value difference;

[0038] The fourth processing module is used to fuse the laser tracking data, the arc tracking data, and the weld feature points extracted by the preset weld geometry model, the position deviation direction of the welding gun, and the offset of the welding gun to determine the welding gun trajectory for welding guidance.

[0039] According to a third aspect of an embodiment of the present invention, a fusion device based on laser tracking and arc tracking is provided, the device comprising:

[0040] a memory having an executable program stored therein;

[0041] A processor is used to execute the executable program in the memory to implement the steps of any one of the above methods.

[0042] The technical solution provided by the embodiments of the present invention may have the following beneficial effects:

[0043] It is understandable that the technical solution provided by the present invention uses a structured light vision sensor to obtain the spatial feature information of the weld, and combines the arc sensor to provide real-time feedback on the welding gun position, forming a spatial fusion perception system to achieve accurate positioning of the weld and real-time correction of the welding gun position. The technical solution of this application helps to provide accurate welding gun position estimation, improve the accuracy and stability of the welding process, and is suitable for complex pipeline full-position welding operations, solving the problems of insufficient accuracy and real-time feedback lag in traditional methods.

[0044] More specifically, 1. Improve weld tracking accuracy: Through the fusion of laser and arc tracking, weld features can be accurately captured, especially when the weld groove is complex or irregular, weld identification is more accurate.

[0045] 2. Real-time feedback of welding gun position: Arc tracking provides real-time feedback during the welding process, and combined with the information prediction of laser tracking, the spatial position of the welding gun can be effectively corrected.

[0046] 3. Enhance the adaptability to the welding environment: By using known calibration parameters, the signals of laser tracking and arc tracking are uniformly converted into the same spatial coordinate system for fusion. In this process, the Kalman filter algorithm is widely used to optimize the welding gun position estimation. The laser geometric information and the real-time feedback of the arc are combined to obtain a stable and accurate welding gun trajectory. The fusion algorithm can handle interference factors such as spatter and strong light during the welding process to ensure the stability and reliability of weld tracking.

[0047] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0049] Figure 1 is a schematic diagram of steps of a fusion method based on laser tracking and arc tracking according to an exemplary embodiment;

[0050] Figure 2 is a schematic diagram of weld tracking based on a fusion method of laser tracking and arc tracking according to an exemplary embodiment;

[0051] Figure 3 is a schematic diagram showing the composition of a fusion x system based on laser tracking and arc tracking according to an exemplary embodiment;

[0052] Figure 4 is a schematic diagram showing the composition of a fusion device based on laser tracking and arc tracking according to an exemplary embodiment;

[0053] Figure 5 The figure is a flow chart of laser tracking and welding seam centerline solution according to an exemplary embodiment. DETAILED DESCRIPTION

[0054] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0055] Embodiment 1

[0056] See also Figure 1 as well as Figure 2 , Figure 1The present invention is a schematic diagram of a fusion method based on laser tracking and arc tracking according to an exemplary embodiment, wherein the method comprises:

[0057] S1. Obtain laser tracking data and arc tracking data;

[0058] S2. Using the laser tracking data, obtaining first image information;

[0059] S3. Using the first image information, extracting the weld centerline by a preset method, and extracting weld feature points based on a preset weld geometry model;

[0060] S4. Detecting the local extreme value in the arc tracking data, using the local extreme value to infer the position deviation direction of the welding gun and using a preset integral method to calculate the extreme value difference in the arc tracking data, and using the extreme value difference to estimate the offset of the welding gun;

[0061] S5. Fusion of the laser tracking data, arc tracking data, and weld feature points extracted using the preset weld geometry model, the position deviation direction of the welding gun, and the offset of the welding gun to determine the welding gun trajectory for welding guidance.

[0062] In a specific implementation, as described in step S1, obtaining laser tracking data includes:

[0063] Use a preset structured light sensor to project laser stripes of a specific pattern onto the surface of the object to be measured to obtain a stripe image;

[0064] The reflected fringe image is captured using a preset high-speed camera.

[0065] In specific implementations, the structured light sensor projects laser stripes of a known pattern onto the weld surface. The spacing, width, and angle of the stripes are precisely adjusted according to the shape of the welded workpiece to ensure clear projection and reflection.

[0066] The high-speed camera captures the reflected fringe image, and the relative position of the camera and the structured light projector is calibrated and optimized to make the fringe reflection image accurately match the workpiece surface.

[0067] Further, the using the laser tracking data to obtain the first picture information includes:

[0068] Using median filtering method and Gaussian filtering method to remove the influence of ambient light and stray light in the fringe image;

[0069] A histogram equalization image enhancement algorithm is used to enhance the stripe contrast in the stripe image and the image clarity of the stripe image to obtain first picture information.

[0070] More specifically, denoising methods such as median filtering and Gaussian filtering are used to remove the influence of ambient light and stray light.

[0071] Image enhancement algorithms such as histogram equalization are used to enhance fringe contrast and improve image clarity, ensuring that weld geometry information can be accurately extracted in complex environments.

[0072] Furthermore, the extracting the weld centerline by a preset method using the first image information includes:

[0073] Using an edge detection algorithm to identify the position and contour of the laser stripes in the first image information, and to segment the area to distinguish the weld from the background area;

[0074] The center line is determined by least square curve fitting of the extracted laser stripe profile, and the continuity of the center line is optimized by morphological operation.

[0075] In specific implementation, edge detection is performed on the image to identify the position of the laser stripes, and regional segmentation is performed to distinguish the weld from the background area.

[0076] The center line of the extracted stripe profile is determined by least square curve fitting. For welds of different shapes (such as V-shaped and U-shaped grooves), adaptive curve fitting is used to ensure accuracy.

[0077] Morphological operations (dilation and erosion) are used to optimize the continuity of the center line to make it smooth and meet the actual welding requirements. Based on this, geometric features such as weld width and groove angle are calculated to provide a reference for welding gun control.

[0078] For specific implementation, please refer to Figure 2 The center line of the weld can be obtained through each frame of the image, and the position of the welding gun can be obtained. By using the pre-scan method, the position information of the entire weld can be obtained, and the predetermined trajectory of the entire welding gun can be obtained.

[0079] Furthermore, the extraction of weld feature points based on a preset weld geometry model includes:

[0080] Use prior knowledge of welding process to build weld geometry model, and use polynomial or ellipse mathematical method to describe groove type, width, angle parameters;

[0081] The constructed weld geometry model is used to extract key feature points of the weld through a feature extraction algorithm.

[0082] It should be noted that the weld geometry model is constructed based on the prior knowledge of the welding process, and the parameters such as groove type, width, angle, etc. are described by mathematical methods such as polynomials or ellipses, and the model parameters are dynamically adjusted with the welding conditions.

[0083] The key feature points of the weld (such as the starting point, end point, center point of the weld, etc.) are extracted through the feature extraction algorithm. Accurate feature point extraction helps to monitor and adjust the welding gun position in real time to ensure high welding precision.

[0084] For specific implementation, please refer to Figure 5 , when detecting and locating a specific shape (such as a groove), the following steps are mainly performed:

[0085] 1. Get the original image (fringe image);

[0086] 2. Perform Gaussian blur operation on the original image to reduce image noise.

[0087] 3. Adaptive threshold binarization: Perform adaptive threshold binarization on the Gaussian blurred image to convert the image into a binary image.

[0088] 4. Skeleton refinement: Perform skeleton refinement on the binarized image to extract the skeleton structure in the image.

[0089] 5. Hough line detection: Perform Hough line detection in the image after skeleton refinement to find the straight lines in the image.

[0090] 6. Classify according to the slope of the straight line (K). If the absolute value of the slope of the straight line is less than tan(5), proceed to the next step of "fitting the horizontal line outside the groove";

[0091] If the slope of the straight line is greater than or less than tan(60), perform “bevel fitting”.

[0092] 7. Solve the intersection point and get the two ends of the groove: find the intersection point through the fitting straight line, and then get the two ends of the groove.

[0093] 8. Calculate the position of the center of the groove based on the positions of the two ends of the groove.

[0094] In a specific implementation, the step of obtaining arc tracking data includes:

[0095] The welding current signal is collected by using a Hall current sensor or a current transformer, and the arc voltage signal is collected by using a voltage transformer or a Hall voltage sensor;

[0096] The welding current signal and the arc voltage signal are respectively converted into digital forms by using a preset digital acquisition card to obtain a first welding current digital signal and a first arc voltage digital signal.

[0097] Furthermore, the method further comprises:

[0098] A low-pass filter is used to remove high-frequency noise in the first welding current digital signal and the first arc voltage digital signal, and a median filter is used to remove pulse interference in the first welding current digital signal and the first arc voltage digital signal.

[0099] In the specific implementation, the welding current signal is collected by using a Hall sensor or a current transformer. Since the current fluctuation is closely related to the welding gun offset, monitoring the current change can assist in determining the welding gun position. At the same time, the change of the arc voltage signal can also provide support for the adjustment of the welding gun position. Afterwards, the collected current and voltage signals are converted into digital form using a data acquisition card to facilitate subsequent processing and analysis. Furthermore, a low-pass filter is used to remove high-frequency noise, and a median filter is used to remove pulse interference to ensure the smoothness and effectiveness of the signal, thereby ensuring the accuracy of the arc signal and providing a reliable data basis for subsequent arc tracking.

[0100] In specific implementation, as described in step S4, by detecting the local extreme value points in the arc signal and analyzing the change rules between the extreme value points, the deviation direction between the welding gun and the weld can be inferred. For example, when the extreme value points of the current signal change abnormally, it may mean that the welding gun deviates from the center of the weld. By analyzing these changes, it can be determined whether the welding gun is offset to the left or right.

[0101] Furthermore, the integration method is used to calculate the extreme value difference in the arc signal, so as to more accurately estimate the offset of the welding gun. This accurate offset information is crucial for the welding robot to adjust the welding gun position in real time, so that the welding gun can be more accurately aligned with the weld to ensure the welding quality. Through the welding gun position feedback obtained by arc tracking feature extraction, the welding robot can correct the position of the welding gun in time to ensure the stability and accuracy of the welding process.

[0102] Further, the fusion of the laser tracking data, the arc tracking data, and the weld feature points extracted by the preset weld geometry model, the position deviation direction of the welding gun, and the offset of the welding gun to determine the welding gun trajectory for welding guidance includes:

[0103] Using known calibration parameters, the laser tracking data and arc tracking data are uniformly converted into the same spatial coordinate system for data fusion, and the welding gun position is optimized using a Kalman filter algorithm;

[0104] And the welding gun trajectory is determined by utilizing the real-time feedback of the position deviation direction of the welding gun and the offset of the welding gun extracted by the preset welding gun geometric model for welding guidance.

[0105] It should be noted that, using known calibration parameters, the signals of laser tracking and arc tracking are uniformly converted into the same spatial coordinate system for fusion. In this process, the Kalman filter algorithm is widely used to optimize the welding gun position estimation, and the laser geometric information and real-time arc feedback are combined to obtain a stable and accurate welding gun trajectory.

[0106] The real-time feedback system transmits the welding gun deviation information to the welding robot control system and uses the PID control algorithm for automatic adjustment to ensure that the welding gun always follows the center of the weld throughout the welding process, thereby ensuring the stability and accuracy of the welding quality.

[0107] In specific implementation, by providing accurate welding gun position estimation, the accuracy and stability of the welding process are improved. It is suitable for complex pipeline all-position welding operations and solves the problems of insufficient accuracy and real-time feedback lag of traditional methods.

[0108] It should be noted that in addition to the combination of laser tracking and arc tracking, alternative solutions also include the introduction of other sensors, such as monitoring the temperature distribution of the weld through thermal imaging sensors, or using the arc sound generated by welding to obtain the welding gun position information, and integrating it with the existing laser and arc tracking information to achieve further optimization of weld tracking.

[0109] See also Figure 3 , Figure 3 The present invention is a schematic diagram showing the composition of a fusion system based on laser tracking and arc tracking according to an exemplary embodiment, wherein the system comprises:

[0110] An acquisition module 30, used for acquiring laser tracking data and arc tracking data;

[0111] A first processing module 31 is used to obtain first image information using the laser tracking data;

[0112] A second processing module 32 is used to extract the weld centerline by a preset method using the first image information, and to extract weld feature points based on a preset weld geometric model;

[0113] A third processing module 33 is used to detect local extreme values ​​in the arc tracking data, infer the position deviation direction of the welding gun using the local extreme values, calculate the extreme value difference in the arc tracking data using a preset integration method, and estimate the offset of the welding gun using the extreme value difference;

[0114] The fourth processing module 34 is used to fuse the laser tracking data, the arc tracking data, and the weld feature points extracted by the preset weld geometry model, the position deviation direction of the welding gun, and the offset of the welding gun to determine the welding gun trajectory for welding guidance.

[0115] See also Figure 4 , Figure 4 The present invention is a schematic diagram showing the composition of a fusion device based on laser tracking and arc tracking according to an exemplary embodiment, wherein the device comprises:

[0116] A memory 41 on which an executable program is stored;

[0117] The processor 42 is used to execute the executable program in the memory 41 to implement the steps of any one of the above methods.

[0118] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0119] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0120] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0121] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0122] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0123] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0124] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0125] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0126] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A fusion method based on laser tracking and arc tracking, characterized in that: The method comprises: Obtain laser tracking data and arc tracking data; Using the laser tracking data, obtaining first picture information; Utilizing the first image information, extracting the weld centerline by a preset method, and extracting weld feature points based on a preset weld geometry model; Detecting local extreme values ​​in the arc tracking data, inferring the position deviation direction of the welding gun using the local extreme values, calculating the extreme value difference in the arc tracking data using a preset integration method, and estimating the offset of the welding gun using the extreme value difference; The laser tracking data, the arc tracking data, the weld feature points extracted by the preset weld geometry model, the position deviation direction of the welding gun, and the offset of the welding gun are integrated to determine the welding gun trajectory for welding guidance.

2. The method according to claim 1, characterized in that The step of acquiring laser tracking data comprises: Use a preset structured light sensor to project laser stripes of a specific pattern onto the surface of the object to be measured to obtain a stripe image; The reflected fringe image is captured using a preset high-speed camera.

3. The method according to claim 2, characterized in that The step of obtaining first image information by using the laser tracking data includes: Using median filtering method and Gaussian filtering method to remove the influence of ambient light and stray light in the fringe image; A histogram equalization image enhancement algorithm is used to enhance the stripe contrast in the stripe image and the image clarity of the stripe image to obtain first picture information.

4. The method according to claim 1, characterized in that: The method of extracting the weld centerline by using the first image information through a preset method includes: Using an edge detection algorithm to identify the position and contour of the laser stripes in the first image information, and to segment the area to distinguish the weld from the background area; The center line is determined by least square curve fitting of the extracted laser stripe profile, and the continuity of the center line is optimized by morphological operation.

5. The method according to claim 1, characterized in that The method of extracting weld feature points based on a preset weld geometry model includes: Use prior knowledge of welding process to build weld geometry model, and use polynomial or ellipse mathematical method to describe groove type, width, angle parameters; The constructed weld geometry model is used to extract key feature points of the weld through a feature extraction algorithm.

6. The method according to claim 1, characterized in that The obtaining of arc tracking data comprises: The welding current signal is collected by using a Hall current sensor or a current transformer, and the arc voltage signal is collected by using a voltage transformer or a Hall voltage sensor; The welding current signal and the arc voltage signal are respectively converted into digital forms by using a preset digital acquisition card to obtain a first welding current digital signal and a first arc voltage digital signal.

7. The method according to claim 6, characterized in that The method further comprises: A low-pass filter is used to remove high-frequency noise in the first welding current digital signal and the first arc voltage digital signal, and a median filter is used to remove pulse interference in the first welding current digital signal and the first arc voltage digital signal.

8. The method according to claim 1, characterized in that The fusing of the laser tracking data, the arc tracking data, and the weld feature points extracted by the preset weld geometry model, the position deviation direction of the welding gun, and the offset of the welding gun to determine the welding gun trajectory for welding guidance includes: Using known calibration parameters, the laser tracking data and arc tracking data are uniformly converted into the same spatial coordinate system for data fusion, and the welding gun position is optimized using a Kalman filter algorithm; And the welding gun trajectory is determined by utilizing the real-time feedback of the position deviation direction of the welding gun and the offset of the welding gun extracted by the preset welding gun geometric model for welding guidance.

9. A fusion system based on laser tracking and arc tracking, applied to the fusion method based on laser tracking and arc tracking as claimed in any one of claims 1 to 8, characterized in that: The system comprises: An acquisition module, used for acquiring laser tracking data and arc tracking data; A first processing module, used to obtain first image information using the laser tracking data; A second processing module is used to extract the weld centerline by a preset method using the first image information, and to extract weld feature points based on a preset weld geometry model; a third processing module, configured to detect a local extreme value in the arc tracking data, infer a position deviation direction of the welding gun using the local extreme value, calculate an extreme value difference in the arc tracking data using a preset integral method, and estimate an offset of the welding gun using the extreme value difference; The fourth processing module is used to fuse the laser tracking data, the arc tracking data, and the weld feature points extracted by the preset weld geometry model, the position deviation direction of the welding gun, and the offset of the welding gun to determine the welding gun trajectory for welding guidance.

10. Fusion equipment based on laser tracking and arc tracking, characterized in that: The device comprises: A memory having an executable program stored therein; A processor, configured to execute the executable program in the memory to implement the steps of the method according to any one of claims 1 to 8.

Images