Welding defect detection method and device, electronic equipment and storage medium

Abstract

The invention provides a welding defect detection method and device, electronic equipment and a storage medium, and the method comprises the steps: calculating a welding defect value according to a numerical relationship between an intersection point abscissa and a central point abscissa, a difference value between the intersection point abscissa and a central point abscissa extreme value, and a numerical relationship between the central point abscissa and the central point abscissa extreme value; the current welding deviation defect in the welding process is detected; and according to the current welding wire dry elongation change rate, the current weld penetration defect in the welding process is detected. Through the current welding wire dry elongation change rate in the welding process, the abscissa of the intersection point of the weld bead area contour and the weld pool area contour in the current welding image, the abscissa of the center point of the welding gun and the extreme value of the abscissa of the center point of the welding gun in the welding image in the current swing period, the welding defects can be detected in the welding process; the waste of welding resources is reduced, and the detection efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of welding technology, and in particular to a welding defect detection method, device, electronic equipment and storage medium. Background Art

[0002] The welding process is a relatively complex physical change process, and there are many unpredictable welding defects in the welding process.

[0003] Traditional welding defect detection methods generally detect welding quality through post-weld testing, such as RT testing, UT testing, mechanical properties testing, etc. However, post-weld testing cannot change the fact that welding defects already exist, and the remedy is to re-weld after the defects are found. Traditional detection methods are time-consuming and damage the welding process, resulting in a waste of welding resources and low detection efficiency. Summary of the invention

[0004] In view of this, the purpose of the present application is to provide a welding defect detection method, device, electronic device and storage medium, which can detect welding defects during the welding process, reduce the waste of welding resources and improve the detection efficiency.

[0005] In a first aspect, an embodiment of the present application provides a method for detecting welding defects, the method comprising:

[0006] Obtain the current wire dry extension change rate during the welding process, the horizontal coordinate of the intersection of the weld bead area contour and the molten pool area contour in the current welding image, the horizontal coordinate of the center point of the welding gun in the current welding image, and the extreme value of the horizontal coordinate of the center point of the welding gun in the current swing cycle; the horizontal coordinate of the center point of the welding gun is determined based on the position of the weld wire area contour in the current welding image; the weld bead area contour, the molten pool area contour and the weld wire area contour are obtained by inputting the current welding image into the regional segmentation model to segment the molten pool area, the weld bead area and the welding wire area;

[0007] According to the numerical relationship between the abscissa of the intersection point and the abscissa of the center point, and the numerical relationship between the extreme values ​​of the abscissa of the intersection point and the abscissa of the center point, the current welding deviation defect in the welding process is detected;

[0008] According to the current wire extension change rate, the current weld penetration defect in the welding process is detected.

[0009] In a possible implementation manner, the intersection abscissa includes a first intersection abscissa and a second intersection abscissa; and according to a numerical relationship between the intersection abscissa and the center point abscissa, and a numerical relationship between the intersection abscissa and the extreme value of the center point abscissa, detecting a current weld deviation defect in the welding process includes:

[0010] If the abscissa of the center point is less than or equal to the abscissa of the first intersection point or greater than the abscissa of the second intersection point, the current swing amplitude defect in the welding process is detected according to the difference between the abscissa of the intersection point and the extreme value of the abscissa of the center point;

[0011] According to the numerical relationship between the abscissa of the intersection point and the extreme value of the abscissa of the center point, the defect of the current swing center position in the welding process is detected.

[0012] In a possible implementation manner, the extreme value of the horizontal coordinate of the center point includes a maximum value of the horizontal coordinate of the center point and a minimum value of the horizontal coordinate of the center point; and detecting the current swing amplitude defect in the welding process according to the difference between the horizontal coordinate of the intersection point and the extreme value of the horizontal coordinate of the center point includes:

[0013] If the value obtained by subtracting the minimum value of the abscissa of the center point from the abscissa of the first intersection point is greater than the preset pixel deviation threshold and the value obtained by subtracting the maximum value of the abscissa of the center point from the abscissa of the second intersection point is greater than the preset pixel deviation threshold, the current swing amplitude in the welding process is too small;

[0014] If the value obtained by subtracting the minimum value of the horizontal coordinate of the center point from the horizontal coordinate of the first intersection point is less than or equal to the preset pixel deviation threshold or the value obtained by subtracting the maximum value of the horizontal coordinate of the center point from the horizontal coordinate of the second intersection point is less than or equal to the preset pixel deviation threshold, then determine whether the value obtained by subtracting the minimum value of the horizontal coordinate of the center point from the horizontal coordinate of the first intersection point is greater than the preset pixel deviation threshold, and whether the value obtained by subtracting the maximum value of the horizontal coordinate of the center point from the horizontal coordinate of the second intersection point is greater than the preset pixel deviation threshold;

[0015] If the value obtained by subtracting the minimum value of the abscissa of the center point from the abscissa of the first intersection is greater than the preset pixel deviation threshold, and the value obtained by subtracting the maximum value of the abscissa of the center point from the abscissa of the second intersection is greater than the preset pixel deviation threshold, the current swing amplitude in the welding process is too large.

[0016] In a possible implementation, the numerical relationship between the abscissa of the intersection point and the extreme value of the abscissa of the center point is used to detect the defect of the current swing center position during the welding process, including:

[0017] Calculate the intermediate horizontal coordinate between the maximum value of the horizontal coordinate of the center point and the minimum value of the horizontal coordinate of the center point to obtain the first intermediate horizontal coordinate;

[0018] Calculate the middle horizontal coordinate between the first intersection point horizontal coordinate and the second intersection point horizontal coordinate to obtain a second middle horizontal coordinate;

[0019] If the first intermediate horizontal coordinate is greater than the second intermediate horizontal coordinate, it is determined whether the value obtained by subtracting the second intermediate horizontal coordinate from the first intermediate horizontal coordinate is less than the preset pixel deviation threshold; if the value obtained by subtracting the second intermediate horizontal coordinate from the first intermediate horizontal coordinate is greater than or equal to the preset pixel deviation threshold, the current swing center position is biased to the right during the welding process;

[0020] If the first intermediate horizontal coordinate is less than or equal to the second intermediate horizontal coordinate, it is determined whether the value obtained by subtracting the first intermediate horizontal coordinate from the second intermediate horizontal coordinate is less than the preset pixel deviation threshold; if the value obtained by subtracting the first intermediate horizontal coordinate from the second intermediate horizontal coordinate is greater than or equal to the preset pixel deviation threshold, the current swing center position during the welding process is biased to the left.

[0021] In a possible implementation, detecting a current weld penetration defect in a welding process according to a current welding wire dry extension change rate includes:

[0022] If the current welding wire dry extension length change rate is greater than the preset welding wire dry extension length change rate, the current weld penetration probability in the welding process is determined according to the current welding wire dry extension length change rate.

[0023] In a possible implementation manner, the welding defect detection method further includes:

[0024] Determine the tangent point between the minimum bounding box of the molten pool area contour and the molten pool area contour;

[0025] The current flatness during welding is detected based on the tangent point.

[0026] In a possible implementation manner, the tangent points include a first tangent point A, a second tangent point B, and a third tangent point C; and detecting the current flatness during the welding process according to the tangent points includes:

[0027] The current flatness during the welding process is determined based on the angle difference between 180° and the angle value corresponding to ∠ACB.

[0028] In a second aspect, an embodiment of the present application further provides a welding defect detection device, the device comprising:

[0029] An acquisition module is used to acquire the current wire dry extension change rate during welding, the horizontal coordinate of the intersection of the weld bead area contour and the molten pool area contour in the current welding image, the horizontal coordinate of the center point of the welding gun in the current welding image, and the extreme value of the horizontal coordinate of the center point of the welding gun in the current swing cycle; the horizontal coordinate of the center point of the welding gun is determined based on the position of the weld wire area contour in the current welding image; the weld bead area contour, the molten pool area contour and the weld wire area contour are obtained by inputting the current welding image into the area segmentation model to segment the molten pool area, the weld bead area and the welding wire area;

[0030] A detection module, used for detecting the current welding deviation defect in the welding process according to the numerical relationship between the horizontal coordinate of the intersection point and the horizontal coordinate of the center point, and the numerical relationship between the extreme values ​​of the horizontal coordinate of the intersection point and the horizontal coordinate of the center point;

[0031] The detection module is also used to detect the current weld penetration defect in the welding process according to the current welding wire dry extension change rate.

[0032] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the storage medium communicate through the bus, and the processor executes the machine-readable instructions to perform the steps of any welding defect detection method as described in the first aspect.

[0033] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the welding defect detection method as described in any one of the first aspects are executed.

[0034] The embodiment of the present application provides a method, device, electronic device and storage medium for detecting welding defects, the method comprising: detecting the current welding deviation defect in the welding process according to the numerical relationship between the horizontal coordinate of the intersection and the horizontal coordinate of the center point, the difference between the horizontal coordinate of the intersection and the extreme value of the horizontal coordinate of the center point, and the numerical relationship between the horizontal coordinate of the center point and the extreme value of the horizontal coordinate of the center point; detecting the current welding penetration defect in the welding process according to the current welding wire dry extension change rate. The present application can detect welding defects in the welding process through the current welding wire dry extension change rate in the welding process, the horizontal coordinate of the intersection of the weld area contour and the molten pool area contour in the current welding image, the horizontal coordinate of the center point of the welding gun, and the extreme value of the horizontal coordinate of the center point of the welding gun in the welding image within the current swing cycle, thereby reducing the waste of welding resources and improving the detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 A flow chart of a welding defect detection method provided in an embodiment of the present application is shown;

[0037] Figure 2 A schematic diagram of the segmentation process of the region segmentation model provided in an embodiment of the present application is shown;

[0038] Figure 3 A schematic diagram of a segmented welding image provided by an embodiment of the present application is shown;

[0039] Figure 4 A schematic structural diagram of a welding defect detection device provided in an embodiment of the present application is shown;

[0040] Figure 5A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0041] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0042] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0043] In order to enable those skilled in the art to use the content of this application, the following implementation is provided in conjunction with a specific application scenario "the field of welding technology". For those skilled in the art, the general principles defined herein can be applied to other embodiments and application scenarios without departing from the spirit and scope of this application. Although this application is mainly described around the "field of welding technology", it should be understood that this is only an exemplary embodiment.

[0044] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0045] A welding defect detection method provided in an embodiment of the present application is described in detail below.

[0046] Reference Figure 1 As shown, it is a flow chart of a welding defect detection method provided in an embodiment of the present application. The specific execution process of the welding defect detection method is as follows:

[0047] S101, obtaining the current wire elongation change rate during the welding process, the horizontal coordinate of the intersection of the weld bead area contour and the molten pool area contour in the current welding image, the horizontal coordinate of the center point of the welding gun, and the extreme value of the horizontal coordinate of the center point of the welding gun in the current swing cycle; the weld bead area contour, the molten pool area contour and the welding wire area contour are obtained by inputting the current welding image into the regional segmentation model to segment the molten pool area, the weld bead area and the welding wire area.

[0048] S102, detecting the current welding deviation defect in the welding process according to the numerical relationship between the horizontal coordinates of the intersection points and the horizontal coordinates of the center points, and the numerical relationship between the extreme values ​​of the horizontal coordinates of the intersection points and the horizontal coordinates of the center points.

[0049] S103, detecting the current weld penetration defect in the welding process according to the current welding wire dry extension change rate.

[0050] The embodiment of the present application provides a method for detecting welding defects, which includes: obtaining the current welding wire dry extension change rate during the welding process, the horizontal coordinate of the intersection of the weld bead area contour and the molten pool area contour in the current welding image, the horizontal coordinate of the center point of the welding gun, and the extreme value of the horizontal coordinate of the center point of the welding gun in the welding image within the current swing cycle; according to the numerical relationship between the horizontal coordinate of the intersection and the horizontal coordinate of the center point, the difference between the horizontal coordinate of the intersection and the extreme value of the horizontal coordinate of the center point, and the numerical relationship between the horizontal coordinate of the center point and the extreme value of the horizontal coordinate of the center point; according to the current welding wire dry extension change rate, the current welding penetration defect in the welding process is detected. The present application can detect welding defects in the welding process through the current welding wire dry extension change rate during the welding process, the horizontal coordinate of the intersection of the weld bead area contour and the molten pool area contour in the current welding image, the horizontal coordinate of the center point of the welding gun, and the extreme value of the horizontal coordinate of the center point of the welding gun in the welding image within the current swing cycle, thereby reducing the waste of welding resources and improving the detection efficiency.

[0051] The following is a description of the exemplary steps of the present application embodiment:

[0052] S101, obtaining the current wire elongation change rate during the welding process, the horizontal coordinate of the intersection of the weld bead area contour and the molten pool area contour in the current welding image, the horizontal coordinate of the center point of the welding gun in the current welding image, and the extreme value of the horizontal coordinate of the center point of the welding gun in the current swing cycle; the weld bead area contour, the molten pool area contour and the welding wire area contour are obtained by inputting the current welding image into the regional segmentation model to segment the molten pool area, the weld bead area and the welding wire area.

[0053] In the implementation mode of the present application, the current welding image is acquired in real time during the welding process; the welding image is input into the regional segmentation model to segment the molten pool area, the weld bead area and the welding wire area, and the molten pool area contour, the weld bead area contour and the welding wire area contour in the current welding image are obtained; Figure 2 The figure is a schematic diagram of the segmentation process of the region segmentation model provided in the embodiment of the present application; wherein the region segmentation model is a deep learning model. It includes an encoder and a decoder; Rate represents the learning rate, which is a hyperparameter. Figure 3 As shown, it is a schematic diagram of the segmented welding image provided in an embodiment of the present application; the part shaped like an "arm" in the figure is the weld bead area, the part shaped like a "fist" in the figure is the molten pool area, and the part shaped like a "finger" in the figure is the welding wire area.

[0054] Among them, the molten pool refers to the part of the base material that is melted into a pool due to the heat of the welding arc; the weld is the weld formed during the metal welding process, which is the basic unit in the welding process; the welding wire is a metal wire welding material used as filler metal or as a conductor at the same time.

[0055] Further, the horizontal coordinate of the intersection of the weld area contour and the molten pool area contour refers to the horizontal coordinate of the intersection of the left groove and the right groove in the weld area contour with the bottom of the molten pool area contour respectively; specifically, determine the linear equation corresponding to the left groove and the linear equation corresponding to the right groove in the weld area contour; determine the intersection of the linear equation corresponding to the left groove and the bottom of the molten pool area contour to obtain the first intersection; the intersection of the linear equation corresponding to the right groove and the bottom of the molten pool area contour to obtain the second intersection; the horizontal coordinate of the first intersection is called the first intersection horizontal coordinate, and the horizontal coordinate of the second intersection is called the second intersection horizontal coordinate. It should be noted that the horizontal coordinate of the first intersection is smaller than the horizontal coordinate of the second intersection. Due to the shooting angle, the area with a larger vertical coordinate in the molten pool area contour in the welding image is closer to the actual bottom of the molten pool area contour.

[0056] Among them, the groove refers to the groove of a certain geometric shape processed and assembled at the part to be welded of the weldment. The groove is the premise and basis for the formation of the weld bead, and the weld bead is filled and connected on the basis of the groove.

[0057] Furthermore, the horizontal coordinate of the center point of the welding gun in the current welding image refers to the horizontal coordinate of the center point of the welding gun, which is determined based on the contour of the welding wire area in the current welding image; specifically, the horizontal coordinate of the center point of the welding gun in the current welding image is determined based on the correspondence between the welding wire position and the welding gun position and the position of the welding wire area contour in the current welding image.

[0058] Furthermore, the extreme values ​​of the horizontal coordinates of the center point of the welding gun in the current swing cycle include a maximum value of the horizontal coordinates of the center point and a minimum value of the horizontal coordinates of the center point; specifically, one swing cycle contains multiple welding images; the maximum value of the horizontal coordinates of the center point of the welding gun in all welding images in the current swing cycle is determined as the maximum value of the horizontal coordinates of the center point; the minimum value of the horizontal coordinates of the center point of the welding gun in all welding images in the current swing cycle is determined as the minimum value of the horizontal coordinates of the center point.

[0059] The oscillation period in the welding process refers to the distance that the welding tool moves forward in one oscillation period, that is, the distance that the welding tool coordinates move forward in one oscillation period.

[0060] S102, detecting the current welding deviation defect in the welding process according to the numerical relationship between the horizontal coordinates of the intersection points and the horizontal coordinates of the center points, and the numerical relationship between the extreme values ​​of the horizontal coordinates of the intersection points and the horizontal coordinates of the center points.

[0061] In the implementation manner of the present application, a weld deviation defect is a type of welding defect, which refers to the phenomenon that the weld deviates from the predetermined position or direction during the formation process and is not completely aligned with the parent material or the path required by the design. Weld deviation defects include swing defects and swing center position defects. Swing defects and swing center position defects are factors that cause weld deviation defects. Swing defects refer to abnormalities in the amplitude of the swing, and swing center position defects refer to abnormalities in the center position of the swing.

[0062] Specifically, the current welding deviation defect in the welding process is detected through the following steps:

[0063] Step 1: Determine whether the horizontal coordinate of the center point is greater than the horizontal coordinate of the first intersection point and less than the horizontal coordinate of the second intersection point.

[0064] Step 2: If the horizontal coordinate of the center point is less than or equal to the horizontal coordinate of the first intersection point or greater than the horizontal coordinate of the second intersection point, the current swing defect in the welding process is detected according to the difference between the horizontal coordinate of the intersection point and the extreme value of the horizontal coordinate of the center point.

[0065] In an embodiment of the present application, if the horizontal coordinate of the center point is less than or equal to the horizontal coordinate of the first intersection point or greater than the horizontal coordinate of the second intersection point, it indicates that a welding offset defect may exist, and further detection is performed to determine whether the welding offset defect is caused by an amplitude defect; the swing amplitude defect includes a large swing amplitude and a small swing amplitude.

[0066] Here, the current swing defect during welding is detected through the following steps:

[0067] (1) If the value obtained by subtracting the minimum value of the horizontal coordinate of the center point from the horizontal coordinate of the first intersection point is greater than the preset pixel deviation threshold and the value obtained by subtracting the maximum value of the horizontal coordinate of the center point from the horizontal coordinate of the second intersection point is greater than the preset pixel deviation threshold, the current swing amplitude in the welding process is too small.

[0068] (2) If the value obtained by subtracting the horizontal coordinate of the first intersection from the minimum value of the horizontal coordinate of the center point is less than or equal to the preset pixel deviation threshold or the value obtained by subtracting the horizontal coordinate of the second intersection from the maximum value of the horizontal coordinate of the center point is less than or equal to the preset pixel deviation threshold, then determine whether the value obtained by subtracting the horizontal coordinate of the first intersection from the minimum value of the horizontal coordinate of the center point is greater than the preset pixel deviation threshold, and whether the value obtained by subtracting the horizontal coordinate of the second intersection from the maximum value of the horizontal coordinate of the center point is greater than the preset pixel deviation threshold.

[0069] (3) If the value obtained by subtracting the minimum value of the horizontal coordinate of the center point from the horizontal coordinate of the first intersection is greater than the preset pixel deviation threshold, and the value obtained by subtracting the maximum value of the horizontal coordinate of the center point from the horizontal coordinate of the second intersection is greater than the preset pixel deviation threshold, then the current swing amplitude in the welding process is too large.

[0070] (4) If the value obtained by subtracting the minimum value of the horizontal coordinate of the center point from the horizontal coordinate of the first intersection point is less than or equal to the preset pixel deviation threshold, or the value obtained by subtracting the maximum value of the horizontal coordinate of the center point from the horizontal coordinate of the second intersection point is less than or equal to the preset pixel deviation threshold, there is no swing defect in the welding process.

[0071] Step three: Detect the defect of the current swing center position during the welding process according to the numerical relationship between the horizontal coordinate of the intersection point and the extreme value of the horizontal coordinate of the center point.

[0072] In the embodiment of the present application, if the horizontal coordinate of the center point is less than or equal to the horizontal coordinate of the first intersection point or greater than the horizontal coordinate of the second intersection point, it indicates that there may be a welding deviation defect, and further detection is performed to determine whether the welding deviation defect is caused by a swing center position defect. The swing center position defect includes a swing center deviation to the left and a swing center deviation to the right.

[0073] Here, the current swing center position defect during welding is detected through the following steps:

[0074] (1) Calculate the intermediate horizontal coordinate between the maximum horizontal coordinate of the center point and the minimum horizontal coordinate of the center point to obtain the first intermediate horizontal coordinate.

[0075] (2) Calculate the intermediate horizontal coordinate between the horizontal coordinate of the first intersection point and the horizontal coordinate of the second intersection point to obtain the second intermediate horizontal coordinate.

[0076] (3) If the first intermediate horizontal coordinate is greater than the second intermediate horizontal coordinate, determine whether the value obtained by subtracting the second intermediate horizontal coordinate from the first intermediate horizontal coordinate is less than a preset pixel deviation threshold; if the value obtained by subtracting the second intermediate horizontal coordinate from the first intermediate horizontal coordinate is greater than or equal to the preset pixel deviation threshold, the current swing center position is biased to the right during the welding process.

[0077] (4) If the value obtained by subtracting the second intermediate horizontal coordinate from the first intermediate horizontal coordinate is less than the preset pixel deviation threshold, the current swing center position during the welding process is appropriate.

[0078] (5) If the first intermediate horizontal coordinate is less than or equal to the second intermediate horizontal coordinate, determine whether the value obtained by subtracting the first intermediate horizontal coordinate from the second intermediate horizontal coordinate is less than a preset pixel deviation threshold; if the value obtained by subtracting the first intermediate horizontal coordinate from the second intermediate horizontal coordinate is greater than or equal to the preset pixel deviation threshold, the current swing center position is biased to the left during the welding process.

[0079] (6) If the value obtained by subtracting the first intermediate horizontal coordinate from the second intermediate horizontal coordinate is less than the preset pixel deviation threshold, the current swing center position during the welding process is appropriate.

[0080] Step 4: If the horizontal coordinate of the center point is greater than the horizontal coordinate of the first intersection point and less than the horizontal coordinate of the second intersection point, there is no welding deviation defect in the welding process.

[0081] S103, detecting the current weld penetration defect in the welding process according to the current welding wire dry extension change rate.

[0082] In the implementation mode of the present application, welding defects also include weld-through defects, which refer to the phenomenon that the product substrate is perforated due to excessive current during the welding process. The wire extension refers to the distance from the end of the conductive nozzle to the workpiece. This distance is crucial to the welding process because it directly affects the quality and efficiency of welding. If the current wire extension change rate is greater than the preset wire extension change rate, the current weld-through probability during the welding process is determined according to the current wire extension change rate. The larger the value corresponding to the current wire extension change rate, the greater the current weld-through probability.

[0083] Among them, the wire extension length is determined based on the wire area profile.

[0084] Specifically, the current wire extension change rate is obtained through the following steps:

[0085] Step 1: Obtain the target welding wire dry extension length corresponding to the latest welding images of the first preset frame number in the welding process.

[0086] Optionally, the target welding wire stick-out length may be filtered to obtain a final target welding wire stick-out length.

[0087] Step 2: Divide all target welding wire extension lengths into multiple target welding wire extension length sets in chronological order; the number of target welding wire extension lengths in each target welding wire extension length set is equal to the second preset frame number; the first preset frame number is an integer multiple of the second preset frame number.

[0088] Step 3: Calculate the target wire extension length average value and acquisition time average value corresponding to each target wire extension length set.

[0089] For example, the target welding wire elongation set U includes target welding wire elongation 1 and target welding wire elongation 2; the value corresponding to the target welding wire elongation 1 is d1, and the value corresponding to the target welding wire elongation 2 is d2; the time corresponding to the target welding wire elongation 1 is t1, and the time corresponding to the target welding wire elongation 2 is t2; then the average value of the target welding wire elongation corresponding to the target welding wire elongation set U is (d1+d2) / 2; the average value of the acquisition time corresponding to the target welding wire elongation set U is (t1+t2) / 2.

[0090] Step 4. For every two target welding wire extension length sets, divide "the absolute value of the difference between the target welding wire extension length average value corresponding to the second target welding wire extension length set and the target welding wire extension length average value corresponding to the first target welding wire extension length set" by "the absolute value of the difference between the acquisition time average value corresponding to the second target welding wire extension length set and the acquisition time average value corresponding to the first target welding wire extension length set" to obtain the current initial welding wire extension length change rate; wherein, the acquisition time average value corresponding to the second target welding wire extension length set is less than the acquisition time average value corresponding to the first target welding wire extension length set.

[0091] For example, the average acquisition time corresponding to the first target welding wire extension length set is t3, the average acquisition time corresponding to the second target welding wire extension length set is t4, the target welding wire extension length average value corresponding to the first target welding wire extension length set is d3, and the target welding wire extension length average value corresponding to the second target welding wire extension length set is d4; then the current initial welding wire extension length change rate is (d4-d3) / (t4-t3).

[0092] Step 5: Determine the current target welding wire dry extension length change rate as the average value or weighted sum value of all current initial welding wire dry extension length change rates.

[0093] Furthermore, the embodiments of the present application can also detect the flatness of welding, including: determining the intersection point between the minimum circumscribed frame of the molten pool area contour and the molten pool area contour; and detecting the current flatness during the welding process based on the intersection point.

[0094] In an embodiment of the present application, the intersection points include a first intersection point A, a second intersection point B and a third intersection point C; the vertical coordinate of the third intersection point C is smaller than that of the first intersection point A and the second intersection point B; it should be noted that, due to the shooting angle, the area with a smaller vertical coordinate within the outline of the molten pool area in the welding image is closer to the actual top of the molten pool area outline.

[0095] Specifically, the current flatness during the welding process is determined according to the angle difference between 180° and the angle value corresponding to ∠ACB; the larger the angle difference, the worse the flatness; the smaller the angle difference, the better the flatness. Or the current flatness during the welding process is determined according to the curvature of the curve between the first tangent point A and the second tangent point B in the contour of the molten pool area; the larger the curvature, the worse the flatness; the smaller the curvature, the better the flatness.

[0096] Furthermore, the embodiments of the present application can also detect the current molten pool stability during the welding process, including: obtaining the collective features of the molten pool area contour in the current welding image (such as the length and width of the molten pool, aspect ratio, circumference, area, back drag angle, etc.), and determining the current molten pool stability during the welding process.

[0097] Based on the same inventive concept, the embodiment of the present application also provides a welding defect detection device corresponding to the welding defect detection method. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned welding defect detection method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0098] Reference Figure 4 FIG. 1 is a schematic diagram of a welding defect detection device provided in an embodiment of the present application, and the welding defect detection device includes:

[0099] The acquisition module 401 is used to acquire the current wire dry extension change rate during the welding process, the horizontal coordinate of the intersection of the weld bead area contour and the molten pool area contour in the current welding image, the horizontal coordinate of the center point of the welding gun in the current welding image, and the extreme value of the horizontal coordinate of the center point of the welding gun in the current swing cycle; the horizontal coordinate of the center point of the welding gun is determined based on the position of the weld wire area contour in the current welding image; the weld bead area contour, the molten pool area contour and the weld wire area contour are obtained by inputting the current welding image into the regional segmentation model to segment the molten pool area, the weld bead area and the welding wire area;

[0100] A detection module 402, for detecting a current weld deviation defect in the welding process according to a numerical relationship between the horizontal coordinates of the intersection points and the horizontal coordinates of the center points, and a numerical relationship between the extreme values ​​of the horizontal coordinates of the intersection points and the horizontal coordinates of the center points;

[0101] The detection module 402 is also used to detect the current weld penetration defect in the welding process according to the current welding wire dry extension change rate.

[0102] In one possible implementation, the intersection horizontal coordinate includes a first intersection horizontal coordinate and a second intersection horizontal coordinate; the detection module 402 is specifically used to detect the current swing amplitude defect in the welding process according to the difference between the intersection horizontal coordinate and the extreme value of the center point horizontal coordinate if the center point horizontal coordinate is less than or equal to the first intersection horizontal coordinate or greater than the second intersection horizontal coordinate; and detect the current swing center position defect in the welding process according to the numerical relationship between the intersection horizontal coordinate and the extreme value of the center point horizontal coordinate.

[0103] In a possible implementation, the detection module 402 is specifically used to determine whether the value obtained by subtracting the minimum value of the horizontal coordinate of the center point from the horizontal coordinate of the first intersection is greater than a preset pixel deviation threshold and the value obtained by subtracting the maximum value of the horizontal coordinate of the center point from the horizontal coordinate of the second intersection is greater than the preset pixel deviation threshold, then the current swing amplitude during the welding process is too small; if the value obtained by subtracting the minimum value of the horizontal coordinate of the center point from the horizontal coordinate of the first intersection is less than or equal to the preset pixel deviation threshold or the value obtained by subtracting the maximum value of the horizontal coordinate of the center point from the horizontal coordinate of the second intersection is less than or equal to the preset pixel deviation threshold, then determine whether the value obtained by subtracting the minimum value of the horizontal coordinate of the center point from the horizontal coordinate of the first intersection is greater than the preset pixel deviation threshold, and whether the value obtained by subtracting the maximum value of the horizontal coordinate of the center point from the horizontal coordinate of the second intersection is greater than the preset pixel deviation threshold; if the value obtained by subtracting the minimum value of the horizontal coordinate of the center point from the horizontal coordinate of the first intersection is greater than the preset pixel deviation threshold, and the value obtained by subtracting the maximum value of the horizontal coordinate of the center point from the horizontal coordinate of the second intersection is greater than the preset pixel deviation threshold, then the current swing amplitude during the welding process is too large.

[0104] In one possible implementation, the detection module 402 is specifically used to calculate the intermediate horizontal coordinate between the maximum horizontal coordinate of the center point and the minimum horizontal coordinate of the center point to obtain a first intermediate horizontal coordinate; calculate the intermediate horizontal coordinate between the horizontal coordinate of the first intersection point and the horizontal coordinate of the second intersection point to obtain a second intermediate horizontal coordinate; if the first intermediate horizontal coordinate is greater than the second intermediate horizontal coordinate, determine whether the value obtained by subtracting the second intermediate horizontal coordinate from the first intermediate horizontal coordinate is less than a preset pixel deviation threshold; if the value obtained by subtracting the second intermediate horizontal coordinate from the first intermediate horizontal coordinate is greater than or equal to the preset pixel deviation threshold, the current swing center position during the welding process is biased to the right; if the first intermediate horizontal coordinate is less than or equal to the second intermediate horizontal coordinate, determine whether the value obtained by subtracting the first intermediate horizontal coordinate from the second intermediate horizontal coordinate is less than the preset pixel deviation threshold; if the value obtained by subtracting the first intermediate horizontal coordinate from the second intermediate horizontal coordinate is greater than or equal to the preset pixel deviation threshold, the current swing center position during the welding process is biased to the left.

[0105] In a possible implementation, the detection module 402 is specifically used to determine the current weld penetration probability during the welding process according to the current welding wire dry extension change rate if the current welding wire dry extension change rate is greater than the preset welding wire dry extension change rate.

[0106] In a possible implementation, the detection module 402 is further configured to:

[0107] Determine the tangent point between the minimum bounding box of the molten pool area contour and the molten pool area contour;

[0108] The current flatness during welding is detected based on the tangent point.

[0109] In a possible implementation, the tangent points include a first tangent point A, a second tangent point B and a third tangent point C; the detection module 402 is specifically used to determine the current flatness during the welding process based on the angle difference between 180° and the angle value corresponding to ∠ACB.

[0110] The embodiment of the present application provides a welding defect detection device, which includes: an acquisition module 401, which is used to acquire the current welding wire dry extension change rate during the welding process, the horizontal coordinate of the intersection of the weld area contour and the molten pool area contour in the current welding image, the horizontal coordinate of the center point of the welding gun in the current welding image, and the extreme value of the horizontal coordinate of the center point of the welding gun in the current swing cycle; the horizontal coordinate of the center point of the welding gun is determined based on the position of the welding wire area contour in the current welding image; the detection module 402 is used to detect the current welding deviation defect during the welding process according to the numerical relationship between the horizontal coordinate of the intersection and the horizontal coordinate of the center point, and the numerical relationship between the horizontal coordinate of the intersection and the extreme value of the horizontal coordinate of the center point; the detection module 402 is also used to detect the current welding penetration defect during the welding process according to the current welding wire dry extension change rate. The present application can detect welding defects during the welding process through the current welding wire dry extension change rate during the welding process, the horizontal coordinate of the intersection of the weld area contour and the molten pool area contour in the current welding image, the horizontal coordinate of the center point of the welding gun, and the extreme value of the horizontal coordinate of the center point of the welding gun in the welding image in the current swing cycle, thereby reducing the waste of welding resources and improving the detection efficiency.

[0111] like Figure 5 As shown, an electronic device 500 provided in an embodiment of the present application includes: a processor 501, a memory 502 and a bus, the memory 502 stores machine-readable instructions executable by the processor 501, when the electronic device is running, the processor 501 communicates with the memory 502 through the bus, and the processor 501 executes the machine-readable instructions to perform the steps of the above-mentioned welding defect detection method.

[0112] Specifically, the memory 502 and the processor 501 can be general-purpose memories and processors, which are not specifically limited here. When the processor 501 runs the computer program stored in the memory 502, the welding defect detection method can be executed.

[0113] Corresponding to the above-mentioned welding defect detection method, an embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned welding defect detection method are executed.

[0114] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in this application. In the several embodiments provided in this application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0115] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0116] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0117] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the information processing method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.

[0118] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for detecting welding defects, characterized in that: The method comprises: Obtaining the current wire dry extension change rate during the welding process, the horizontal coordinate of the intersection of the weld bead area contour and the molten pool area contour in the current welding image, the horizontal coordinate of the center point of the welding gun in the current welding image, and the extreme value of the horizontal coordinate of the center point of the welding gun in the current swing cycle; the horizontal coordinate of the center point of the welding gun is determined based on the position of the weld wire area contour in the current welding image; the weld bead area contour, the molten pool area contour and the weld wire area contour are obtained by inputting the current welding image into a regional segmentation model to segment the molten pool area, the weld bead area and the welding wire area in the current welding image; Detecting a current welding deviation defect in the welding process according to a numerical relationship between the abscissa of the intersection point and the abscissa of the center point and a numerical relationship between the abscissa of the intersection point and an extreme value of the abscissa of the center point; According to the current welding wire dry extension change rate, a current weld penetration defect in the welding process is detected.

2. The method for detecting welding defects according to claim 1, characterized in that: The intersection abscissa includes a first intersection abscissa and a second intersection abscissa; and detecting the current welding deviation defect in the welding process according to the numerical relationship between the intersection abscissa and the center point abscissa and the numerical relationship between the intersection abscissa and the extreme value of the center point abscissa includes: If the abscissa of the center point is less than or equal to the abscissa of the first intersection point or greater than the abscissa of the second intersection point, detecting the current swing amplitude defect in the welding process according to the difference between the abscissa of the intersection point and the extreme value of the abscissa of the center point; According to the numerical relationship between the horizontal coordinate of the intersection point and the extreme value of the horizontal coordinate of the center point, the defect of the current swing center position in the welding process is detected.

3. The method for detecting welding defects according to claim 2, characterized in that: The extreme value of the horizontal coordinate of the center point includes a maximum value of the horizontal coordinate of the center point and a minimum value of the horizontal coordinate of the center point; and detecting the current swing amplitude defect in the welding process according to the difference between the horizontal coordinate of the intersection point and the extreme value of the horizontal coordinate of the center point includes: If the value obtained by subtracting the minimum value of the horizontal coordinate of the center point from the horizontal coordinate of the first intersection point is greater than the preset pixel deviation threshold and the value obtained by subtracting the maximum value of the horizontal coordinate of the center point from the horizontal coordinate of the second intersection point is greater than the preset pixel deviation threshold, then the current swing amplitude in the welding process is too small; If the value obtained by subtracting the minimum value of the horizontal coordinate of the center point from the horizontal coordinate of the first intersection point is less than or equal to the preset pixel deviation threshold or the value obtained by subtracting the maximum value of the horizontal coordinate of the center point from the horizontal coordinate of the second intersection point is less than or equal to the preset pixel deviation threshold, then determine whether the value obtained by subtracting the minimum value of the horizontal coordinate of the center point from the horizontal coordinate of the first intersection point is greater than the preset pixel deviation threshold, and whether the value obtained by subtracting the maximum value of the horizontal coordinate of the center point from the horizontal coordinate of the second intersection point is greater than the preset pixel deviation threshold; If the value obtained by subtracting the minimum value of the horizontal coordinate of the center point from the first intersection point is greater than the preset pixel deviation threshold, and the value obtained by subtracting the maximum value of the horizontal coordinate of the center point from the horizontal coordinate of the second intersection point is greater than the preset pixel deviation threshold, then the current swing amplitude in the welding process is too large.

4. The method for detecting welding defects according to claim 3, characterized in that: The numerical relationship between the abscissa of the intersection point and the extreme value of the abscissa of the center point is used to detect the defect of the current swing center position during the welding process, including: Calculate the intermediate horizontal coordinate between the maximum value of the horizontal coordinate of the center point and the minimum value of the horizontal coordinate of the center point to obtain a first intermediate horizontal coordinate; Calculate the middle horizontal coordinate between the first intersection horizontal coordinate and the second intersection horizontal coordinate to obtain a second middle horizontal coordinate; If the first intermediate horizontal coordinate is greater than the second intermediate horizontal coordinate, it is determined whether a value obtained by subtracting the second intermediate horizontal coordinate from the first intermediate horizontal coordinate is less than the preset pixel deviation threshold; if a value obtained by subtracting the second intermediate horizontal coordinate from the first intermediate horizontal coordinate is greater than or equal to the preset pixel deviation threshold, the current swing center position in the welding process is biased to the right; If the first intermediate horizontal coordinate is less than or equal to the second intermediate horizontal coordinate, it is determined whether the value obtained by subtracting the first intermediate horizontal coordinate from the second intermediate horizontal coordinate is less than the preset pixel deviation threshold; if the value obtained by subtracting the first intermediate horizontal coordinate from the second intermediate horizontal coordinate is greater than or equal to the preset pixel deviation threshold, the current swing center position during the welding process is biased to the left.

5. The method for detecting welding defects according to claim 1, characterized in that: The detecting the current weld penetration defect in the welding process according to the current welding wire dry extension change rate comprises: If the current welding wire dry extension change rate is greater than the preset welding wire dry extension change rate, the current weld penetration probability in the welding process is determined according to the current welding wire dry extension change rate.

6. The method for detecting welding defects according to any one of claims 1 to 5, characterized in that: The welding defect detection method further includes: Determine the tangent point between the minimum bounding box of the molten pool area contour and the molten pool area contour; The current flatness during the welding process is detected according to the tangent point.

7. The method for detecting welding defects according to claim 6, characterized in that: The tangent points include a first tangent point A, a second tangent point B, and a third tangent point C; and detecting the current flatness during the welding process according to the tangent points includes: The current flatness during the welding process is determined according to the angle difference between 180° and the angle value corresponding to ∠ACB.

8. A welding defect detection device, characterized in that: The device comprises: An acquisition module, used for acquiring the current welding wire dry extension change rate during welding, the horizontal coordinate of the intersection of the weld bead area contour and the molten pool area contour in the current welding image, the horizontal coordinate of the center point of the welding gun in the current welding image, and the extreme value of the horizontal coordinate of the center point of the welding gun in the current swing cycle; the horizontal coordinate of the center point of the welding gun is determined based on the position of the weld wire area contour in the current welding image; the weld bead area contour, the molten pool area contour and the weld wire area contour are obtained by inputting the current welding image into a regional segmentation model to segment the molten pool area, the weld bead area and the welding wire area; A detection module, used for detecting a current welding deviation defect in the welding process according to a numerical relationship between the horizontal coordinate of the intersection point and the horizontal coordinate of the center point, and a numerical relationship between the horizontal coordinate of the intersection point and an extreme value of the horizontal coordinate of the center point; The detection module is also used to detect the current weld penetration defect in the welding process according to the current welding wire dry extension change rate.

9. An electronic device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the welding defect detection method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the welding defect detection method according to any one of claims 1 to 7 are executed.

Images