Self-adaptive spot welding correction system based on visual inspection

Abstract

The invention discloses a self-adaptive spot welding correction system based on visual inspection. The self-adaptive spot welding correction system comprises the steps that an actual welding area image after a workpiece is welded is obtained through a shooting module; according to actual welding area image information of the actual welding area image, image extraction is conducted on the actual welding area image, and an actual welding point image of a welding point in the workpiece is obtained; the actual welding point pixel information of the actual welding point image is compared with the standard welding point pixel information, and the welding quality of the welding points is determined. According to the method, the shooting module is used for shooting the actual welding area image of the welding point after the workpiece is welded, then the image is extracted to obtain the actual welding point image, and the actual welding point pixel information of the welding point can be compared with the standard welding point pixel information of the standard welding point after each time of welding; and errors caused by comparison between the welding points and the standard welding points through naked eyes when the welding quality is determined manually are reduced, and the accuracy of determining the welding quality is improved.

Description

Technical Field

[0001] The present application belongs to the field of workpiece detection, and in particular to an adaptive spot welding correction system based on visual detection. Background Art

[0002] Spot welding technology is an extremely important part of the modern industrial manufacturing process of aircraft engines. Spot welding usually refers to a welding method that uses a cylindrical electrode to form a weld on the contact surface of two overlapping workpieces. During spot welding, the contact surfaces of the two overlapping workpieces are first squeezed, and then the current is turned on. Under the action of resistance heat, the two overlapping workpieces are melted, combined, and cooled to form.

[0003] At present, spot welding technology is mainly divided into manual spot welding and mechanical spot welding. Manual spot welding is mainly used in some small electronic equipment, and mechanical spot welding mainly uses spot welding equipment to control the movement of the workpiece and the welding gun head so that the spot welding end corresponds to the spot welding area. However, after these two types of spot welding are completed, there may be abnormal welding quality such as misalignment and warping, so it is necessary to use inspectors to check whether the welding quality of the workpiece after welding is normal.

[0004] At present, the detection of workpiece welding points in China is mainly focused on detecting the position coordinates of the welding points to determine whether the welding quality of the welding points is qualified. Among them, the patent with publication number CN104535587A proposes a PCBA solder joint detection method based on machine vision, which determines the position and quality of the solder joints through image acquisition and analysis, and specifically includes the following steps: S1, preset detection parameters, the detection parameters include one-to-one corresponding solder joint standard coordinates and solder joint standard parameters; S2, take a picture of the PCBA to be detected to obtain a PCBA image; S3, analyze the PCBA image, extract the coordinates and surface parameters of the solder joint to be detected; S4, compare the coordinates of the detected solder joint with the standard coordinates of the solder joint to determine whether the solder joint position is correct; S5, according to the solder joint coordinates and the standard coordinates of the solder joint, compare the solder joint surface parameters with the solder joint standard parameters to determine whether the solder joint quality is qualified.

[0005] The above patent determines whether the welding quality of the welding point is qualified by analyzing the position coordinates of the welding point from the image, and the judgment of the welding point position depends on the accurate matching of the coordinates. If the positioning accuracy is not high enough, it may lead to misjudgment, so there is a certain problem of inaccurate welding quality judgment. Summary of the invention

[0006] The embodiment of the present application provides an adaptive spot welding correction system based on visual detection, which improves the accuracy of workpiece welding quality detection.

[0007] According to a first aspect of the present application, an embodiment of the present application provides an adaptive spot welding correction system based on visual detection, which may include:

[0008] Base, on which the welded workpiece is placed;

[0009] A mounting bracket, the mounting bracket is mounted on the base;

[0010] A shooting module is connected to the mounting bracket, and is used to shoot the workpiece after welding placed on the base to obtain an image of the actual welding area of ​​the workpiece after welding;

[0011] The control module is communicatively connected with the shooting module and is used for receiving an actual welding area image sent by the shooting module; performing image extraction on the actual welding area image according to actual welding area image information of the actual welding area image to obtain an actual welding point image of the welding point in the workpiece; and comparing the actual welding point pixel information of the actual welding point image with the standard welding point pixel information to determine the welding quality of the welding point.

[0012] Optionally, the institution also includes:

[0013] The positioning assembly comprises a plurality of positioning clamps, the positioning clamps comprise a mounting portion and a clamping portion which are movably connected, the mounting portion is mounted on a base, and the plurality of clamping portions are arranged relatively to each other for clamping a workpiece.

[0014] The driving device is installed on the base and connected with each clamping part, and is used to drive each clamping part to move so as to make each clamping part approach or move away from each other.

[0015] Optionally, the institution also includes:

[0016] Welding assembly, the welding assembly includes an electric welder and a welding gun;

[0017] The electric welder is connected to a welding gun, and the electric welder is installed on a base;

[0018] The welding gun is mounted on the mounting bracket and is used to weld the workpiece.

[0019] According to a second aspect of the present application, there is provided an adaptive spot welding correction method based on visual detection, which is applied to the control module of any one of the first aspects and may include:

[0020] Receiving the actual welding area image sent by the camera module;

[0021] According to the actual welding area image information of the actual welding area image, image extraction is performed on the actual welding area image to obtain an actual welding point image of the welding point in the workpiece;

[0022] The actual welding point pixel information of the actual welding point image is compared with the standard welding point pixel information to determine the welding quality of the welding point, wherein the standard welding point pixel information is information extracted from the standard welding area image of the standard welding point.

[0023] Optionally, according to the actual welding area image information of the actual welding area image, image extraction is performed on the actual welding area image to obtain an actual welding point image of the welding point in the workpiece, including:

[0024] De-noising the image of the actual welding area to obtain a pixel image of the actual welding area;

[0025] The brightness value of each pixel in the actual welding area pixel image is weighted averaged to obtain the actual welding area grayscale image;

[0026] According to the edge features of the standard welding area grayscale image, the actual welding point image is extracted from the actual welding area grayscale image.

[0027] Optionally, according to the edge features of the standard welding area grayscale image, the actual welding point image is extracted from the actual welding area grayscale image, including:

[0028] Perform edge detection on the grayscale image of the actual welding area to obtain an edge feature image of the actual welding area;

[0029] According to the edge features of the standard welding area grayscale image, feature matching is performed on the actual welding area edge feature image to determine the image position of each edge feature in the actual welding area edge feature image, wherein each edge feature includes a welding point;

[0030] According to the image position of the welding point in each edge feature, the actual welding point image is extracted from the edge feature image of the actual welding area.

[0031] Optionally, before performing feature matching on the actual welding area edge feature image according to the edge features of the standard welding area grayscale image to determine the image position of each feature in the actual welding area edge feature image, the method further comprises:

[0032] According to the current environment information, determining the current gradient threshold corresponding to the current environment information from the corresponding relationship between the preset environment information and the preset gradient threshold;

[0033] According to the relationship between the actual gradient value of the grayscale image of the actual welding area and the current gradient threshold, the grayscale image of the actual welding area is converted to obtain the edge feature image of the actual welding area.

[0034] Optionally, the actual welding point pixel information includes: an actual grayscale value, and the standard welding point pixel information includes: a standard grayscale value;

[0035] Compare the actual welding point pixel information of the actual welding point image with the standard welding point pixel information to determine the welding quality of the welding point, including:

[0036] Determine the difference between the actual gray value and the standard gray value as the actual gray value difference;

[0037] When the actual gray value difference is greater than the gray value difference threshold, it is determined that the welding quality of the welding point is warping.

[0038] Optionally, the actual welding point pixel information includes: the actual number of pixels of the welding point, and the standard welding point pixel information includes: the standard number of pixels of the welding point;

[0039] Compare the actual welding point pixel information of the actual welding point image with the standard welding point pixel information to determine the welding quality of the welding point, including:

[0040] Determine the difference between the actual number of pixels of the welding point and the standard number of pixels of the welding point as the difference in the number of pixels of the welding point;

[0041] When the pixel quantity difference of the welding point is greater than the pixel quantity difference threshold, it is determined that the welding quality of the welding point is misaligned.

[0042] Optionally, before comparing the actual welding point pixel information of the actual welding point image with the standard welding point pixel information to determine the welding quality of the welding point, the method further includes:

[0043] Acquire a standard welding area image of a standard workpiece after welding through a shooting module;

[0044] According to the standard welding area image information of the standard welding area image, image extraction is performed on the standard welding area image to obtain a standard welding point image of the standard welding point in the workpiece;

[0045] The standard welding point pixel information is extracted from the standard welding point image.

[0046] According to a third aspect of the present application, an embodiment of the present application provides an adaptive spot welding correction device based on visual detection, which includes: a processor and a memory storing computer program instructions;

[0047] When the processor executes the computer program instructions, it implements the adaptive spot welding correction method based on visual inspection as described in any one of the first aspects.

[0048] According to the fourth aspect of the present application, an embodiment of the present application provides a computer storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the adaptive spot welding correction method based on visual inspection of any one of the first aspects is implemented.

[0049] According to the fifth aspect of the present application, an embodiment of the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes any one of the adaptive spot welding correction methods based on visual inspection in the first aspect.

[0050] The technical solution provided by the embodiments of the present application brings at least the following beneficial effects:

[0051] The embodiments of the present application provide an adaptive spot welding correction method, device, equipment and computer storage medium based on visual detection, which obtains the actual welding area image of the welding point of the workpiece after welding through a shooting module, and then uses the actual welding area image information of the actual welding area to perform image extraction on the actual welding area image, and extracts the actual welding point image related to the welding point from it, and then uses the standard welding point image of the standard welding point to compare with the actual welding point image, so as to compare the image difference of the two welding points, and then determine the welding quality of the welding point; based on this, after each welding, the actual welding point pixel information of the welding point can be compared with the standard welding point pixel information of the standard welding point, which reduces the error of comparing the welding point with the standard welding point by the naked eye when manually determining the welding quality, and improves the accuracy of welding quality determination.

[0052] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute an improper limitation on the present application.

[0054] Figure 1 is a flow chart of an adaptive spot welding correction method based on visual inspection according to an exemplary embodiment;

[0055] Figure 2 is a structural schematic diagram of an adaptive spot welding correction system based on visual detection according to an exemplary embodiment;

[0056] Figure 3 It is a structural block diagram of an adaptive spot welding correction device based on visual detection according to an exemplary embodiment.

[0057] Legend:

[0058] 200-adaptive spot welding correction system based on visual detection; 210-base; 220-mounting bracket; 230-shooting module; 240-control module; 250-positioning assembly; 251-positioning clamp; 251a-mounting part; 251b-clamping part; 260-driving device; 270-welding assembly; 271-electric welder; 272-welding gun. DETAILED DESCRIPTION

[0059] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0060] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0061] As described in the background technology, the welding quality of the welding point is judged by analyzing the position coordinates of the welding point from the image, and the judgment of the welding point position depends on the accurate matching of the coordinates. If the positioning accuracy is not high enough, it may lead to misjudgment, so there is a certain problem of inaccurate welding quality judgment.

[0062] Based on this, the present application provides an adaptive spot welding correction system based on visual detection. The following first introduces the adaptive spot welding correction method based on visual detection provided in the embodiment of the present application.

[0063] Embodiment 1;

[0064] Figure 1 FIG. 1 is a flow chart of an adaptive spot welding correction method based on visual inspection provided by an embodiment of the present application. Figure 1 As shown, the method can be applied to a control module, which may include the following steps:

[0065] S101, receiving an actual welding area image sent by a camera module;

[0066] S102, performing image extraction on the actual welding area image according to the actual welding area image information of the actual welding area image to obtain an actual welding point image of the welding point in the workpiece;

[0067] S103, comparing the actual welding point pixel information of the actual welding point image with the standard welding point pixel information to determine the welding quality of the welding point.

[0068] Based on the above embodiment, the actual welding area image of the welding point of the workpiece after welding is obtained by the shooting module, and then the actual welding area image information of the actual welding area is used to perform image extraction on the actual welding area image, and the actual welding point image related to the welding point is extracted therefrom, and then the standard welding point image of the standard welding point is used to compare with the actual welding point image, so as to compare the image difference of the two welding points, and then determine the welding quality of the welding point; based on this, after each welding, the actual welding point pixel information of the welding point can be compared with the standard welding point pixel information of the standard welding point, thereby reducing the error of comparing the welding point and the standard welding point by the naked eye when manually determining the welding quality, and improving the accuracy of welding quality determination.

[0069] In the above step S101, after the workpiece is welded by the welding gun, a series of welding points are formed on the workpiece, and the area on the workpiece related to the welding points is the welding area. The welding area on the workpiece can be photographed by the shooting module, so that the actual welding area image of the workpiece after welding can be obtained from the shooting module.

[0070] As an example, the shooting module may include a camera, an image sensor, etc.; more specifically, the shooting module is a CMOS (Complementary Metal-Oxide-Semiconductor) imaging sensor.

[0071] In the above step S102, since the actual welding area image captured by the shooting module includes not only the welding point but also other areas of the workpiece around the welding point, and the image information of other areas of the workpiece does not affect the determination of the welding quality of the workpiece, and the actual welding area image information displayed by the welding point and other areas of the workpiece in the actual welding area image is different, therefore, according to the actual welding area image information of the actual welding area image, the actual welding point image related to the welding point can be extracted from the actual welding area image.

[0072] As an example, the actual welding area image information includes: pixel values ​​of pixels in the actual welding area image, brightness values ​​of the actual welding area image, color temperature of the actual welding area image, and other information.

[0073] In the above S103, the image information of the actual welding point in the actual welding point image is compared with the image information of the standard welding point to determine whether there are errors in the image information of the actual welding point and the image information of the standard welding point. If there are no errors, it means that the welding point is consistent with the standard welding point, the welding point is normal, and the welding quality meets the welding requirements. Otherwise, there are differences, which means that the welding point is abnormal, that is, the welding quality cannot meet the welding requirements.

[0074] Before the above S103, the method may further include:

[0075] Acquiring a standard welding area image of the standard workpiece after welding by means of the shooting module;

[0076] According to the standard welding area image information of the standard welding area image, image extraction is performed on the standard welding area image to obtain a standard welding point image of the standard welding point in the workpiece;

[0077] The standard welding point pixel information is extracted from the standard welding point image.

[0078] It should be noted that the standard welding point pixel information is the information of the pixel points in the standard welding point image, and the standard welding point image is obtained by taking a picture of the standard welding point on the workpiece by a camera, and obtaining a standard welding area image, and performing image processing in the same manner as above. The standard welding point refers to a welding point whose welding quality meets the welding requirements and can be used as a standard part. The standard welding point pixel information can be stored in a storage, and the control module can directly obtain the standard welding point pixel information from the storage.

[0079] Embodiment 2;

[0080] Based on Example 1, this embodiment further provides another implementation of the adaptive spot welding correction method based on visual detection in order to improve the accuracy of extracting the actual welding point image from the actual welding area image.

[0081] Specifically, the above S102 may also include:

[0082] S1021, performing denoising processing on the actual welding area image to obtain a pixel image of the actual welding area;

[0083] S1022, performing weighted average processing on the brightness value of each pixel point in the actual welding area pixel image to obtain a grayscale image of the actual welding area;

[0084] S1023, extracting an actual welding point image from the actual welding area grayscale image according to the edge features of the standard welding area grayscale image.

[0085] Based on the above embodiment, by performing denoising processing on the actual welding area image, the obtained pixel image of the actual image welding area is made clearer, which is convenient for subsequent analysis. Then, the color image is converted into a grayscale image, and the color information can be removed, and only the brightness information is retained, thereby simplifying the image content and facilitating subsequent feature extraction and defect identification. The weighted average processing may include steps such as contrast enhancement to make the grayscale difference of the welding area more obvious, which helps to more accurately identify welding defects. The edge features of the standard welding area grayscale image are extracted to ensure that the extracted welding point image has consistent features with the standard image, thereby improving the detection accuracy.

[0086] In the above S1021, for each pixel point in the actual welding area image, the pixel value in its neighborhood is taken with the pixel as the center. These pixel values ​​are multiplied by the weights of the corresponding positions of the Gaussian template, and then summed to obtain new pixel values. For the pixel points at the edge of the image, one or more layers of pixel points with zero pixel values ​​can be added to the surroundings (upper, lower, left, and right) of the pixel points at the edge of the image and then weighted multiplied, so that each pixel point in the actual welding area image can be normalized, and the pixel values ​​of each pixel point are all unified into one interval, thereby reducing the impact caused by the abnormal data scale of the pixel value, making the pixel values ​​in the actual welding area pixel image more unified.

[0087] As an example, a Gaussian filter may be used to perform filtering operations to achieve denoising of the actual welding area image.

[0088] Among them, the Gaussian filter is based on the Gaussian function, and its formula is:

[0089]

[0090] Where σ is the standard deviation and determines the smoothness of the filter.

[0091] In the above S1022, each pixel point is usually composed of three components, which respectively represent the brightness values ​​of the three colors red (R), green (G), and blue (B). Each brightness value corresponds to a weight value. By weighted averaging the brightness values ​​of the pixels in the actual welding area pixel image, the color of the pixel point can be converted to gray. The above conversion is performed on each pixel in the actual welding area pixel image, thereby realizing the conversion of the actual welding area pixel image into a gray actual welding area grayscale image.

[0092] As an example, the specific formula is as follows:

[0093] Gray=0.299×R+0.587×G+0.114×B

[0094] Among them, R represents the red brightness, G represents the green brightness, and B represents the blue brightness.

[0095] In the above S1023, edge feature detection is performed on the grayscale image of the actual welding area by using an image edge detection algorithm, so that each edge feature can be highlighted from the actual welding area image, and then compared with the edge features of the standard welding area grayscale image, and the image related to the welding point is extracted from the features displayed in the actual welding area image, that is, the actual welding point image is obtained.

[0096] Specifically, the standard welding area grayscale image is obtained by photographing a standard welding workpiece with normal welding points on the workpiece, photographing the welding points of the workpiece as a standard template, and then performing image processing using the above method to obtain a grayscale image, namely, the standard welding area grayscale image. In the standard welding area grayscale image, each edge feature is clearly known.

[0097] More specifically, a neural network model is trained by using a large number of preset welding area grayscale images and preset welding point images as training sets until a trained neural network model is obtained, and then the actual welding area grayscale image is input into the trained neural network model, so that the actual welding point image can be extracted from the actual welding area grayscale image.

[0098] As an example, edge features may include welds, protrusions on a workpiece, depressions on a workpiece, and the like.

[0099] In one embodiment, in order to more accurately extract welding points from the grayscale image of the standard welding area, the present application also provides another implementation of the adaptive spot welding correction method based on visual detection.

[0100] Specifically, the above S1023 may also include:

[0101] S10231, performing edge detection on the grayscale image of the actual welding area to obtain an edge feature image of the actual welding area;

[0102] S10232, performing feature matching on the edge feature image of the actual welding area according to the edge features of the standard welding area grayscale image, and determining the image position of each edge feature in the edge feature image of the actual welding area, wherein each edge feature includes a welding point;

[0103] S10233, extracting the actual welding point image from the edge feature image of the actual welding area according to the image position of the welding point in each edge feature.

[0104] Based on the above embodiment, by performing edge detection on the grayscale image of the standard welding area, the edge features of the welding area can be accurately identified. These edge features usually correspond to key parts such as welds and welding points, and are the basis for subsequent feature matching and welding point extraction; by using the edge features of the grayscale image of the standard welding area, feature matching is performed on the edge feature image of the actual welding area, and various features in the actual welding area, including the position of the welding point, can be further confirmed. This improves the accuracy of extracting the actual welding point image related to the welding point.

[0105] In the above S10231, an edge detection algorithm is used to perform edge detection on the grayscale image of the actual welding area according to the image gradient of the grayscale image of the actual welding area to obtain an edge feature image of the actual welding area.

[0106] Image gradient refers to the direction and size of the fastest changing pixel value in the grayscale image of the actual welding area. The amplitude and direction of the gradient are obtained by calculating the first-order derivative of the grayscale image of the actual welding area in the horizontal and vertical directions. After obtaining the amplitude and direction of the gradient, for each pixel in the grayscale image of the actual welding area, we check the adjacent pixels in the gradient direction. If the gradient amplitude of the pixel is not the local maximum in the gradient direction, it is suppressed (i.e. set to 0), otherwise the pixel is retained. In this way, some unnecessary edge points can be removed, making the edges of each feature in the standard welding area grayscale image clearer.

[0107] In the above S10232, the edge features of the standard welding area grayscale image are known and preset, so the standard welding area grayscale image can be used as a template to compare the edge features with the actual welding area edge feature image, so as to determine the position of each edge feature in the actual welding area edge feature image.

[0108] In the above S10233, after determining the position of each edge feature in the edge feature image of the actual welding area, the position of the edge feature related to the welding point is found from each edge feature, that is, the position of the welding point is determined from multiple edge features.

[0109] The other features, working principles and beneficial effects of this embodiment are consistent with those of Embodiment 1.

[0110] Embodiment 3;

[0111] Based on Example 2, this embodiment further provides another implementation of the adaptive spot welding correction method based on visual detection in order to further improve the accuracy of the edge feature image of the actual welding area.

[0112] Specifically, before the above S10232, the method may further include:

[0113] S10234, determining, according to the current environment information, a current gradient threshold corresponding to the current environment information from a correspondence between preset environment information and preset gradient thresholds;

[0114] S10235, performing image conversion on the grayscale image of the actual welding area according to the relationship between the actual gradient value of the grayscale image of the actual welding area and the current gradient threshold, to obtain an edge feature image of the actual welding area.

[0115] Based on the above embodiment, by selecting a current gradient threshold suitable for the current environment according to the current environmental information, and then performing image conversion according to the magnitude relationship between the current gradient threshold and the actual gradient value of the pixel point in the grayscale image of the actual welding area, a binary image of the actual welding area is obtained, thereby edge detection is performed from the binary image of the actual welding area to obtain an edge feature image of the actual welding area. Based on this, by combining the current environmental information to determine the current gradient threshold corresponding to the current environmental information before performing image conversion, the interference of environmental factors on the shooting module during the image shooting process is reduced, and the accuracy of obtaining the edge feature image of the actual welding area is improved.

[0116] In the above S10234, the environmental information includes brightness and light intensity. In the process of capturing images of the actual welding area, the environmental information will affect factors such as exposure and brightness of the captured image, resulting in different image gradient values. Therefore, it is necessary to balance the impact of the environmental information during image processing.

[0117] Based on a large number of experiments and data statistical analysis, the corresponding relationship between the preset environmental information and the preset gradient threshold can be obtained, and the current gradient threshold corresponding to the current environmental information can be found according to the current environmental information.

[0118] As an example, current environment information may be acquired through sensors; wherein the sensors may include brightness sensors, light intensity sensors, and the like.

[0119] In the above S10235, for pixels whose actual gradient value in the grayscale image of the actual welding area is less than the current gradient threshold, it can be considered that an abnormality such as overexposure occurred during the image capture process; otherwise, it is considered that an abnormality such as excessive brightness occurred during the image capture process. Therefore, compensation needs to be performed during the image conversion process before it can be converted into an accurate binary image of the actual welding area.

[0120] Specifically, the current gradient threshold refers to a gradient interval. For each pixel in the grayscale image of the actual welding area, if its actual gradient value is greater than the current gradient threshold (gradient interval), it is marked as a strong edge point; if its gradient value is between the current gradient threshold (gradient interval), it is marked as a weak edge point; if its gradient value is less than the current gradient threshold (gradient interval), it is suppressed (i.e., set to 0). Then, we traverse all weak edge points, and if they are connected to strong edge points, they are retained as edge points, otherwise they are suppressed. Through the above steps, we get a grayscale image of the actual welding area containing edge information. The pixel points in this grayscale image of the actual welding area have only two possible values: 0 or 255 (or other values ​​representing black and white colors), where 0 represents a non-edge point and 255 represents an edge point. In this way, we get a binary image of the actual welding area containing edge information, that is, an edge feature image of the actual welding area.

[0121] Other features, working principles and beneficial effects of this embodiment are consistent with those of Embodiment 1 and Embodiment 2.

[0122] Embodiment 4;

[0123] This embodiment further illustrates the above S103 based on the embodiment 1.

[0124] Optionally, in one embodiment, the actual welding point pixel information includes: an actual grayscale value, and the standard welding point pixel information includes: a standard grayscale value;

[0125] The above S103 may include:

[0126] S1031, determining the difference between the actual gray value and the standard gray value as the actual gray value difference;

[0127] S1032: When the actual gray value difference is greater than the gray value difference threshold, determine that the welding quality of the welding point is warping.

[0128] In the above S1031, the difference between the actual grayscale value and the standard grayscale value is calculated to obtain the actual grayscale value difference in the form of the actual grayscale value difference.

[0129] In the above S1032, the grayscale value is an important parameter in image analysis, which reflects the brightness or darkness of different areas in the image. Therefore, the type of abnormality can be determined by comparing the actual grayscale value difference with the grayscale value difference threshold. Specifically, when the actual grayscale value difference is greater than the grayscale value difference threshold, it is determined that the welding quality of the welding point is warping.

[0130] Edge warping refers to the phenomenon that the metal sheets on both sides of the weld warp upward during the welding process.

[0131] Optionally, for welding points with warped edges, the welding points of the workpieces are heated while external force is applied through a clamp tool to further correct the deformation. After the correction is completed, a cooling treatment is performed to ensure that the correction effect is stable. After cooling, the clamp is released. Finally, the welding parts before and after correction are checked and compared again through an industrial computer to ensure that the deformation has been effectively corrected and the welding quality meets the requirements.

[0132] The other features, working principles and beneficial effects of this embodiment are consistent with those of Embodiment 1.

[0133] Embodiment 5;

[0134] This embodiment further illustrates the above S103 based on the embodiment 1.

[0135] Optionally, in one embodiment, the actual welding point pixel information includes: the actual number of pixels of the welding point, and the standard welding point pixel information includes: the standard number of pixels of the welding point;

[0136] The above S103 may include:

[0137] S1033, determining the difference between the actual number of pixels of the welding point and the standard number of pixels of the welding point as the welding point pixel number difference;

[0138] S1034: When the pixel quantity difference of the welding point is greater than the pixel quantity difference threshold, determine that the welding quality of the welding point is misalignment.

[0139] In the above S1033, the actual number of pixels of the welding points related to the welding points in the actual welding point image is counted, and the standard number of pixels of the welding points related to the welding points in the standard welding point image is obtained, and then the difference between the actual number of pixels of the welding points and the standard number of pixels of the welding points is calculated to obtain the difference in the number of pixels of the welding points.

[0140] In the above S1034, the image size of the actual welding area image and the standard welding area image size are certain, so the size of the area related to the welding point is also the same. In the area related to the welding point, if the number of actual pixels is greater than the normal standard pixel number by more than the pixel number difference threshold, it means that there is misalignment and overlap in the welded part of the welding point. Therefore, when the difference in the number of pixels of the welding point is greater than the pixel number difference threshold, the welding quality of the welding point is misaligned.

[0141] Misalignment refers to the misalignment of the weldment in both height and length during the welding process, resulting in discontinuity or offset of the weld.

[0142] Optionally, in the case of misalignment of welding quality, the misalignment problem can be solved by repositioning the workpiece or adjusting the position of the welding equipment to ensure that the welding point is in line with the position required by the design. In the case of small misalignment, compensating welding materials can be used to fill the misaligned part so that the weld meets the design requirements. In the case of large misalignment, the misaligned weld is removed by grinding or cutting, and then re-welding is performed to achieve post-welding repair and correction. After the correction is completed, a cooling treatment is performed to ensure that the correction effect is stable. After cooling, the clamp is released, and the welding parts before and after correction are checked and compared again by the industrial computer to ensure that the misalignment has been effectively corrected and the welding quality meets the requirements.

[0143] In one embodiment, when an adaptive spot welding correction system based on visual inspection detects that the welding quality of the workpiece at the welding point is of different abnormal types such as warping or misalignment, different signals can be sent to the welding correction equipment, and a calibration plate of known size and position can be used to calibrate the shooting module, receive the internal and external parameters of the shooting module, extract the image coordinates of the weld point through an image processing algorithm, and use the calibration parameters to convert the image coordinates into world coordinates, so as to determine the actual coordinates of the weld point on the workpiece based on the world coordinates, so that the welding correction mechanism can correct the weld point of the workpiece.

[0144] In other embodiments, when the adaptive spot welding correction system based on visual inspection detects that the welding quality of the workpiece at the welding point is of different abnormal types such as warping or misalignment, different prompt signals can be sent according to different welding qualities to inform the staff of the welding quality of the welding point, so that the workers can use different correction methods according to different welding qualities.

[0145] Optionally, the prompt signal may include but is not limited to light, sound and other signals.

[0146] The other features, working principles and beneficial effects of this embodiment are the same as those of Embodiment 1.

[0147] Embodiment 6;

[0148] Based on the same inventive concept, this embodiment further provides an adaptive spot welding correction system 200 based on visual detection on the basis of embodiment 1, as shown in FIG. Figure 2 As shown, it includes:

[0149] A base 210, on which the welded workpiece is placed;

[0150] A mounting bracket 220, wherein the mounting bracket 220 is mounted on the base 210;

[0151] A photographing module 230, which is connected to the mounting bracket 220 and is used to photograph the workpiece placed on the base 210 after welding, and obtain an image of the actual welding area of ​​the workpiece after welding;

[0152] The control module 240 is communicatively connected with the shooting module 230, and is used to receive the actual welding area image sent by the shooting module 230; according to the actual welding area image information of the actual welding area image, the image extraction is performed on the actual welding area image to obtain the actual welding point image of the welding point in the workpiece; the actual welding point pixel information of the actual welding point image is compared with the standard welding point pixel information to determine the welding quality of the welding point.

[0153] Optionally, the workpiece is placed on the base 210, and the photographing device is installed on the base 210 via the mounting bracket 220. The workpiece placed on the base 210 can be photographed, thereby obtaining an actual welding area image of the workpiece after welding. Since the photographing device is installed on the mounting bracket 220, and the mounting bracket 220 is installed on the base 210, the photographing device can always maintain the same position to photograph the workpiece, so that the actual welding area image taken by the welding photographing device, the actual welding area image and / or the original workpiece image have consistent internal and external parameters, so that when the control module 240 executes the above method embodiment method, the welding quality obtained is more accurate.

[0154] Optionally, the photographing device can also photograph the original workpiece image before welding, and send the original workpiece image to the control module 240, so that the control module 240 determines the welding quality of the workpiece by comparing the difference between the actual welding area image and the original workpiece image.

[0155] In one embodiment, the adaptive spot welding correction system 200 based on visual inspection further includes:

[0156] The positioning assembly 250 includes a plurality of positioning clamps 251 . The positioning clamps 251 include a movably connected mounting portion 251 a and a clamping portion 251 b . The mounting portion 251 is mounted on the base 210 . The plurality of clamping portions 251 b are arranged relatively to each other for clamping a workpiece.

[0157] Specifically, by setting up multiple positioning clamps, the mounting portion 251a of the positioning clamp is installed on the base 210, and the clamping portion 251b clamps the workpiece placed on the base 210, so that during the process of the shooting device shooting the workpiece, the shooting module 230 and the workpiece can remain relatively still, thereby obtaining a more stable and clear image.

[0158] In one embodiment, the adaptive spot welding correction system 200 based on visual inspection further includes:

[0159] The driving device 260 is installed on the base 210 and is connected to each clamping portion 252 to drive each clamping portion 252 to move so that each clamping portion 252 moves closer to or farther from each other.

[0160] Specifically, by providing a driving device 260 and utilizing the driving device 260 to drive the clamping portion 252 to move, the clamping portion 252 can clamp workpieces of different sizes and shapes, thereby improving the applicability of the positioning clamp in clamping the workpiece.

[0161] In one embodiment, the adaptive spot welding correction system 200 based on visual inspection further includes:

[0162] A welding assembly 270, the welding assembly 270 includes an electric welder 271 and a welding gun 272;

[0163] The electric welder 271 is connected to the welding gun 272, and the electric welder 271 is installed on the base 210;

[0164] The welding gun 272 is mounted on the mounting bracket 220 and is used for welding workpieces.

[0165] Specifically, by setting a welding assembly 270 on the adaptive spot welding correction system 200 based on visual detection, the adaptive spot welding correction structure based on visual detection can correct the workpiece by using an electric welder 271 and a welding gun 272 after determining the welding quality of the workpiece through the control module 240, thereby improving the applicability of the adaptive spot welding correction system 200 based on visual detection.

[0166] More specifically, the welding gun includes a cathode welding gun and an anode welding gun.

[0167] In embodiment 6, the control module 240 can implement Figure 1 The various processes implemented in Example 1 can achieve the same technical effects, and will not be described here to avoid repetition.

[0168] Figure 3 A schematic diagram of the hardware structure of an adaptive spot welding correction device based on visual detection provided by an embodiment of the present invention is shown.

[0169] The adaptive spot welding correction device based on vision detection may include a processor 301 and a memory 302 storing computer program instructions.

[0170] Specifically, the processor 301 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiment of the present invention.

[0171] The memory 302 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 302 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 302 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 302 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 32 is a non-volatile solid-state memory.

[0172] In certain embodiments, the memory 302 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage media device, an optical storage media device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, typically, the memory 302 includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors 301), it is operable to perform the operations described with reference to the method according to an aspect of the present application.

[0173] The processor 301 reads and executes the computer program instructions stored in the memory 302 to implement any one of the adaptive spot welding correction methods based on visual detection in the above embodiments.

[0174] In one example, the adaptive spot welding correction device based on visual detection may further include a communication interface 303 and a bus 304. As shown in the figure, the processor 301, the memory 302, and the communication interface 303 are connected through the bus 304 and communicate with each other.

[0175] The communication interface 303 is mainly used to implement the communication between the modules, devices, units and / or equipment in the embodiment of the present invention.

[0176] The bus 304 includes hardware, software or both. For example, but not limitation, the bus 304 may include an accelerated graphics port (AGP) or other graphics bus, an enhanced industry standard architecture (EISA) bus, a front-side bus (FSB), a hypertransport (HT) interconnect, an industry standard architecture (ISA) bus, a wireless bandwidth interconnect, a low pin count (LPC) bus, a memory bus, a microchannel architecture (MCA) bus, a peripheral control interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a serial advanced technology attachment (SATA) bus, a video electronics standard association local (VLB) bus or other suitable bus or a combination of two or more of these. Where appropriate, the bus 304 may include one or more buses 304. Although the present application embodiment describes and shows a specific bus 304, the present application considers any suitable bus 304 or interconnection.

[0177] The adaptive spot welding correction device based on visual detection can be based on the current adaptive spot welding correction method based on visual detection, thereby realizing the combination of Figure 1 , 2 An adaptive spot welding correction method and control module based on visual inspection are described.

[0178] In addition, the embodiment of the present application also provides a computer program product, including computer program instructions, and when the computer program product is executed by the processor 301, the steps and corresponding contents of the aforementioned method embodiment can be implemented.

[0179] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0180] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0181] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0182] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, or a processor of other programmable adaptive spot welding correction systems based on visual detection to produce a machine so that these instructions executed by the processor of the computer or other programmable adaptive spot welding correction systems based on visual detection enable the implementation of the functions / actions specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0183] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. An adaptive spot welding correction system based on visual inspection, characterized in that: The system comprises: a base on which the welded workpiece is placed; A mounting bracket, the mounting bracket being mounted on the base; A shooting module, the shooting module is connected to the mounting bracket and is used to shoot the workpiece placed on the base to obtain an image of an actual welding area of ​​the workpiece after welding; A control module is communicatively connected with the shooting module, and is used for receiving an actual welding area image sent by the shooting module; performing image extraction on the actual welding area image according to actual welding area image information of the actual welding area image to obtain an actual welding point image of the welding point in the workpiece; and comparing the actual welding point pixel information of the actual welding point image with the standard welding point pixel information to determine the welding quality of the welding point.

2. The system according to claim 1, characterized in that The system further comprises: The positioning assembly comprises a plurality of positioning clamps, wherein the positioning clamps comprise a mounting portion and a clamping portion which are movably connected, the mounting portion is mounted on the base, and the plurality of clamping portions are arranged relatively to each other for clamping the workpiece. A driving device is installed on the base, and the driving device is connected to each of the clamping parts, and is used to drive each of the clamping parts to move so that each of the clamping parts moves closer to or farther away from each other.

3. The system according to claim 1, characterized in that The system further comprises: A welding assembly, the welding assembly comprising an electric welder and a welding gun; The electric welder is connected to the welding gun, and the electric welder is installed on the base; The welding gun is mounted on the mounting bracket and is used for welding the workpiece.

4. An adaptive spot welding correction method based on visual inspection, characterized in that: The method is applied to a control module according to any one of claims 1 to 3, and comprises: Receiving the actual welding area image sent by the shooting module; According to the actual welding area image information of the actual welding area image, image extraction is performed on the actual welding area image to obtain an actual welding point image of the welding point in the workpiece; The actual welding point pixel information of the actual welding point image is compared with the standard welding point pixel information to determine the welding quality of the welding point.

5. The method according to claim 4, characterized in that The step of performing image extraction on the actual welding area image according to the actual welding area image information of the actual welding area image to obtain an actual welding point image of the welding point in the workpiece includes: De-noising the actual welding area image to obtain an actual welding area pixel image; Performing weighted average processing on the brightness value of each pixel in the actual welding area pixel image to obtain a grayscale image of the actual welding area; The actual welding point image is extracted from the actual welding area grayscale image according to the edge features of the standard welding area grayscale image.

6. The method according to claim 5, characterized in that The step of extracting the actual welding point image from the actual welding area grayscale image according to the edge features of the standard welding area grayscale image comprises: Performing edge detection on the grayscale image of the actual welding area to obtain an edge feature image of the actual welding area; According to the edge features of the standard welding area grayscale image, feature matching is performed on the actual welding area edge feature image to determine the image position of each edge feature in the actual welding area edge feature image, each edge feature including the welding point; According to the image position of the welding point in each edge feature, the actual welding point image is extracted from the actual welding area edge feature image.

7. The method according to claim 6, characterized in that Before performing feature matching on the actual welding area edge feature image according to the edge features of the standard welding area grayscale image to determine the image position of each feature in the actual welding area edge feature image, the method further includes: According to the current environment information, determining a current gradient threshold corresponding to the current environment information from a correspondence between preset environment information and preset gradient thresholds; According to the magnitude relationship between the actual gradient value of the actual welding area grayscale image and the current gradient threshold, the actual welding area grayscale image is converted to obtain an actual welding area edge feature image.

8. The method according to claim 4, characterized in that The actual welding point pixel information includes: actual grayscale value, and the standard welding point pixel information includes: standard grayscale value; The comparing the actual welding point pixel information of the actual welding point image with the standard welding point pixel information to determine the welding quality of the welding point includes: Determine the difference between the actual gray value and the standard gray value as the actual gray value difference; When the actual gray value difference is greater than the gray value difference threshold, it is determined that the welding quality of the welding point is warping.

9. The method according to claim 4, characterized in that The actual welding point pixel information includes: the actual number of pixels of the welding point, and the standard welding point pixel information includes: the standard number of pixels of the welding point; The comparing the actual welding point pixel information of the actual welding point image with the standard welding point pixel information to determine the welding quality of the welding point includes: Determine the difference between the actual number of pixels of the welding point and the standard number of pixels of the welding point as the welding point pixel number difference; When the pixel quantity difference of the welding point is greater than the pixel quantity difference threshold, it is determined that the welding quality of the welding point is misalignment.

10. The method according to any one of claims 4 to 9, characterized in that Before comparing the actual welding point pixel information of the actual welding point image with the standard welding point pixel information to determine the welding quality of the welding point, the method further includes: Acquiring a standard welding area image of the standard workpiece after welding by means of the shooting module; According to the standard welding area image information of the standard welding area image, image extraction is performed on the standard welding area image to obtain a standard welding point image of the standard welding point in the workpiece; The standard welding point pixel information is extracted from the standard welding point image.

Images