Vehicle body adhesive tape detection method

Abstract

The invention relates to the technical field of adhesive tape detection, in particular to a vehicle body adhesive tape detection method, which comprises the following steps of: acquiring an image of a white vehicle body which is not sprayed with adhesive, and stroking a weld joint in the image to obtain a weld joint line; selecting a plurality of feature points in the weld stroke image; obtaining the coordinate position of the regional contour of each section of rubber strip in the image, obtaining a plurality of rubber edge point groups and coordinates thereof, and obtaining a rubber strip contour image; fitting a weld line in the weld line stroke image in the rubber strip contour image to obtain a plurality of weld points corresponding to the plurality of rubber edge point groups and coordinates thereof; if the distance between the coordinate of the current glue edge point group and the coordinate of the corresponding welding seam point is within an offset error range, the glue edge point group is considered to be qualified, otherwise, the glue edge point group is considered to be undetermined; and for the area with continuous n glue edge point groups which are detected to be undetermined, determining that the gluing is poor. The spraying state of the vehicle body adhesive tape can be detected based on the welding seam, and the adhesive tape detection efficiency can be improved.

Description

Technical Field

[0001] This invention relates to the technical field of rubber strip detection, and more specifically, to a method for detecting rubber strips on vehicle bodies. Background Technology

[0002] Sealant is typically applied to the weld seams of vehicle components such as wheel hubs, passenger compartments, trunks, engine hoods, trunk lids, front and rear doors, and roof panels. This enhances the sealing, waterproofing, and dustproofing of these components. Currently, most sealant application on vehicle bodies is done using painting robots. However, during the application process, issues such as nozzle clogging and visual abnormalities can occur, resulting in the applied sealant strips not completely covering the weld seams. Furthermore, defects such as broken sealant or perforations can occur due to temperature variations and sealant quality. Existing methods for inspecting the sealant strip condition mostly rely on direct visual inspection of the sealant-covered vehicle body parts. However, since the weld seams are obscured by the sealant strips, it's difficult to assess the sealant application based on the weld seam orientation. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of existing technologies that make it difficult to detect the coating status of rubber strips based on the direction of the weld, and to provide a method for detecting rubber strips on a car body that can detect the coating status of rubber strips based on the weld, thereby improving the efficiency of rubber strip detection.

[0004] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows: A method for detecting vehicle body rubber strips is provided, comprising the following steps: S1. Obtain an image of the un-adhesive-coated white body, trace the weld seams in the image to obtain weld seam lines, and obtain a weld seam traced image; S2. Select several feature points in the weld outline image; S3. Obtain an image of the glued white body, use the feature points selected in step S2 to correct the image, then obtain the coordinate position of the region contour of each glue strip in the image, obtain multiple glue edge point groups and their coordinates, and obtain the glue strip contour image. S4. Using the feature points selected in step S2, the weld line in the weld outline image is fitted to the adhesive strip contour image to obtain multiple weld points and their coordinates corresponding to multiple adhesive edge point groups; S5. Check point by point along the weld line: If the distance between the coordinates of the current glue edge point group and the coordinates of the corresponding weld point are within the offset error range, the glue edge point group is considered qualified; otherwise, it is considered pending. For an area with n consecutive glue edge point groups that are considered pending, it is considered to be a poor glue application area.

[0005] This invention discloses a method for detecting adhesive strips on a car body. The method obtains the weld line by outlining the actual position of the weld on the car body in an image of the un-adhesive-coated white body. Then, by fitting the weld outline image to the adhesive strip contour image, the distance between the weld line and the edge of the adhesive strip region contour is obtained as the detection target. The method assesses the adhesive strip coating quality by measuring the width of the adhesive strip covering the weld, thereby reducing missed detections. Furthermore, this invention, by setting an offset error range and considering areas with n consecutive undetermined adhesive edge point groups as poorly coated areas, can be adapted to actual adhesive strip detection application scenarios, reducing unnecessary judgments of coating defects and improving adhesive strip detection efficiency.

[0006] Further, step S1 includes the following steps: S11. Select the un-applied white body and collect multiple images of a local area of ​​the un-applied white body; wherein the total imaging range of the multiple images covers the entire un-applied white body, and the weld seam in each image is in an intact state; S12. The weld seam in each image obtained in step S11 is outlined to obtain the weld seam line, and multiple weld seam outlined images are obtained accordingly.

[0007] Further, in step S2, at least three hole locations are selected as feature points in the weld outline image.

[0008] Further, step S3 includes the following steps: S31. Acquire multiple images of local locations of the glued body-in-white during transport; wherein the total imaging range of the multiple images covers the entire glued body-in-white, and the glue strip in each image is in an intact state; S32. Using the feature points selected in step S2, correct the multiple images in step S31, and then establish a spatial coordinate system for each image. S33. Use the adhesive strip recognition model to recognize multiple images from step S32 to obtain the region contour of each segment of adhesive strip in the image; S34. Using the adhesive strip cutting model, the region contour of each adhesive strip is cut at the millimeter level. Multiple adhesive edge points and their coordinates are obtained through the intersection of the cutting line and the region contour. Then, the adhesive edge points obtained by cutting through the same cutting line are grouped into an adhesive edge point group, and the adhesive strip contour image is obtained.

[0009] Furthermore, in step S4, the weld point is the intersection of the weld line and the cutting line after image fitting.

[0010] Further, in step S5, the offset error range includes a one-sided offset error range; if the distance between the coordinates of the glue edge point in the current glue edge point group and the coordinates of the corresponding weld point are both within the one-sided offset error range, then the glue edge point group is considered qualified; otherwise, it is considered pending. For an area with n consecutive glue edge point groups that are considered pending, then the area is considered a poor glue application area. The left endpoint of the one-sided offset error range is 3mm, and 5≤n≤15.

[0011] Furthermore, the vehicle body adhesive strip detection method also includes step S6: for areas with poor adhesive application, obtain the adhesive strip corresponding to the area, and adjust the preset adhesive application parameters associated with the adhesive application trajectory corresponding to the adhesive strip.

[0012] Further, step S6 includes the following steps: S61. Assign a brush number to each section of the adhesive application trajectory, so that the preset adhesive application parameters associated with each section of the adhesive application trajectory have a corresponding brush number, and so that each adhesive strip also has a corresponding brush number for each section of the adhesive application trajectory. S62. For areas with poor adhesive application, retrieve the brush number corresponding to the adhesive strip in that area, and then adjust the preset adhesive application parameters under that brush number; wherein, the preset adhesive application parameters include adhesive flow rate and pre-pressure.

[0013] Further, in step S5, the offset error range includes a two-sided offset error range; wherein, the poor adhesive application area includes: For a region with n consecutive glue edge point groups that are to be determined, and the sum of the distances between the coordinates of each glue edge point group and the coordinates of the corresponding weld point is greater than the range of double-sided offset error, it is considered to belong to a wide glue diameter defect area. For a group of n consecutive glue edge points that are to be determined, and the sum of the distances between the coordinates of each glue edge point group and the coordinates of the corresponding weld point is less than the range of the double-sided offset error, it is considered to belong to the narrow glue diameter defect area. In step S62, for the wide-diameter defect area, the adjustment is made by reducing the glue flow rate or pre-pressure by 5%; for the narrow-diameter defect area, the adjustment is made by increasing the glue flow rate or pre-pressure by 5%.

[0014] Furthermore, in step S5, for defects that do not belong to either the wide-diameter defect area or the narrow-diameter defect area, the glue strip identification model is used for defect identification; in step S62, for defects identified as perforation areas, the glue flow rate or pre-pressure is increased by 10%; for defects identified as glue breakage or forking areas, the glue gun nozzle flushing function is activated.

[0015] Compared with the prior art, the beneficial effects of the present invention are: This invention discloses a method for detecting adhesive strips on a car body. The method obtains the weld line by outlining the actual position of the weld on the car body in an image of the un-adhesive-coated white body. Then, by fitting the weld outline image to the adhesive strip contour image, the distance between the weld line and the edge of the adhesive strip region contour is obtained as the detection target. The method assesses the adhesive strip coating quality by measuring the width of the adhesive strip covering the weld, thereby reducing missed detections. Furthermore, this invention, by setting an offset error range and considering areas with n consecutive undetermined adhesive edge point groups as poorly coated areas, can be adapted to actual adhesive strip detection application scenarios, reducing unnecessary judgments of coating defects and improving adhesive strip detection efficiency. Attached Figure Description

[0016] Figure 1 This is a flowchart of a method for detecting vehicle body rubber strips according to the present invention; Figure 2 This is a schematic diagram of the image fitting in step S4 of the vehicle body rubber strip detection method of the present invention; Figure 3 This is a schematic diagram of the brush number in step S62 of the vehicle body rubber strip detection method of the present invention. Detailed Implementation

[0017] The present invention will be further described below with reference to specific embodiments. The accompanying drawings are for illustrative purposes only, representing schematic diagrams rather than actual physical objects, and should not be construed as limiting the scope of this patent. To better illustrate the embodiments of the present invention, some components in the drawings may be omitted, enlarged, or reduced, and do not represent the actual dimensions of the product. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0018] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present patent. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0019] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0020] It should be noted that the terms "comprising" and "having" and any variations thereof in the specification, claims and accompanying drawings of this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such process, method, product or device.

[0021] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0022] Example 1 like Figure 1 The following is a first embodiment of a method for detecting vehicle body rubber strips according to the present invention, which includes the following steps: S1. Obtain an image of the un-adhesive-coated white body, trace the weld seams in the image to obtain weld seam lines, and obtain a weld seam traced image; S2. Select several feature points in the weld outline image; S3. Obtain an image of the glued white body, use the feature points selected in step S2 to correct the image, then obtain the coordinate position of the region contour of each glue strip in the image, obtain multiple glue edge point groups and their coordinates, and obtain the glue strip contour image. S4. Using the feature points selected in step S2, fit the weld line in the weld outline image to the adhesive strip contour image to obtain multiple weld points and their coordinates corresponding to multiple adhesive edge point groups. S5. Check point by point along the weld line: If the distance between the coordinates of the current glue edge point group and the coordinates of the corresponding weld point are within the offset error range, the glue edge point group is considered qualified; otherwise, it is considered pending. For an area with n consecutive glue edge point groups that are considered pending, it is considered to be a poor glue application area.

[0023] This invention obtains the weld line by outlining the actual position of the weld on the body of the un-adhesive-coated white car body image. Then, by fitting the weld outline image with the adhesive strip contour image, the distance between the weld line and the edge of the adhesive strip area contour is obtained as the detection object. The width of the adhesive strip covering the weld is used to judge the adhesive strip coating quality, which can reduce missed detections. Furthermore, by setting an offset error range and considering areas with n consecutive adhesive edge point groups as poor adhesive application areas, this invention can be adapted to actual adhesive strip inspection application scenarios, reducing unnecessary judgment of adhesive defects and improving adhesive strip inspection efficiency.

[0024] Example 2 This embodiment is a second embodiment of a method for detecting vehicle body rubber strips. This embodiment is similar to the first embodiment, except that step S1 in this embodiment includes the following steps: S11. Select the un-adhesive-coated white body and collect multiple images of a local area of ​​the un-adhesive-coated white body; wherein the total imaging range of the multiple images covers the entire un-adhesive-coated white body, and the weld seam in each image is in an intact state; wherein the weld seam in each image is in an intact state means that the position of the weld seam in the image is kept at a certain distance from the edge of the image, specifically, the distance can be set to 10cm. S12. The weld seam in each image obtained in step S11 is outlined to obtain the weld seam line, and multiple weld seam outline images are obtained accordingly. In this embodiment, the weld seam can be detected and outlined by YOLO model, or the weld seam can be outlined by drawing software.

[0025] In this embodiment, in step S2, at least three hole positions are selected as feature points in the weld outline image; preferably, the hole positions are round holes.

[0026] In this embodiment, step S3 includes the following steps: S31. Acquire multiple images of local locations of the glued body-in-white during transport; wherein the total imaging range of the multiple images covers the entire glued body-in-white, and the glue strip in each image is in an intact state; S32. Using the feature points selected in step S2, correct the multiple images in step S31, and then establish a spatial coordinate system for each image. S33. Use the adhesive strip recognition model to recognize multiple images from step S32 to obtain the region contour of each segment of adhesive strip in the image; specifically, the existing adhesive strip recognition YOLO model can be used as the adhesive strip recognition model; S34. Using the adhesive strip cutting model, the region contour of each adhesive strip is cut at the millimeter level. Multiple adhesive edge points and their coordinates are obtained through the intersection of the cutting lines and the region contour. Then, the adhesive edge points obtained through the same cutting line are grouped into an adhesive edge point group, resulting in the adhesive strip contour image. Specifically, after cutting at the millimeter level using the adhesive strip cutting model, a cutting line is obtained every millimeter along the extension direction of each adhesive strip region contour. Two adhesive edge points can be obtained on the same cutting line, corresponding to the left and right sides of the adhesive strip edge, respectively. These two adhesive edge points form an adhesive edge point group. It should be noted that if more than two adhesive edge points are obtained on the same cutting line, it will be considered an anomaly and an alarm will be triggered.

[0027] In this embodiment, in step S4, the feature points selected in step S2 are used to fit the weld line in the weld outline image to the adhesive strip contour image. After fitting, the intersection of the weld line and the cutting line is obtained as the weld point, and each group of adhesive edge points can obtain the corresponding weld point through the same cutting line, such as... Figure 2 As shown, the coordinates of the weld points can be obtained. It should be noted that if two adhesive edge points on the same cutting line are located on the same side of the weld line, it will be considered an anomaly and an alarm will be triggered.

[0028] In this embodiment, in step S5, the offset error range includes the unilateral offset error range. It should be noted that the unilateral offset error range refers to the allowable offset error range of the distance between the left or right edge of the adhesive strip and the weld position; that is, the allowable offset error range of the distance between the coordinates of one adhesive edge point and the coordinates of the weld point on the same cutting line. If the distances between the coordinates of the adhesive edge points and the corresponding weld point coordinates in the current adhesive edge point group are all within the unilateral offset error range, then the adhesive edge point group is considered qualified; otherwise, it is considered pending. For any n consecutive detections that are pending... The area of ​​the glue edge point group is considered a poor glue application area and an alarm is triggered. The left endpoint of the single-sided offset error range is 3mm, and the right endpoint can be set according to the actual scenario requirements. Preferably, the right endpoint value can be set to 10mm. In this embodiment, 5≤n≤15. By setting the area of ​​n consecutive glue edge point groups that are detected as undetermined as poor glue application areas, it can be adapted to the actual glue strip detection application scenario, reduce unnecessary judgment of glue application defects, avoid excessively frequent alarms, and improve glue strip detection efficiency.

[0029] It should be further explained that in step S5, the specific values ​​in the single-sided offset error range can be set to different ranges on the left and right sides according to actual usage requirements. Also, different ranges can be set in areas with different weld seam orientation shapes on the body white according to actual usage requirements. That is, for the local rubber strip spraying area on the body white, it is not required that the center line of the rubber strip coincide with the weld as much as possible. Specifically, the offset error range can be adjusted according to the orientation shape of the weld seam, with the specific values ​​of the offset error range on the left and right sides of the rubber strip edge respectively. The weld seam orientation shapes that need to be adjusted include: weld seams with arc segments, weld seams with broken line segments, and weld seams with at least two intersection points within a certain area.

[0030] Example 3 This embodiment is a third embodiment of a vehicle body adhesive strip detection method. This embodiment is similar to embodiment one or two, except that in this embodiment, the vehicle body adhesive strip detection method further includes step S6: for areas with poor adhesive application, obtain the adhesive strip corresponding to the area, and adjust the preset adhesive application parameters associated with the adhesive application trajectory corresponding to the adhesive strip.

[0031] Step S6 includes the following steps: S61. Number each segment of the adhesive application trajectory generated by the coating robot with a brush number, so that the preset adhesive application parameters associated with each segment of the adhesive application trajectory have a corresponding brush number, and so that each adhesive strip also has a corresponding brush number corresponding to each segment of the adhesive application trajectory. S62. For areas with poor adhesive application, retrieve the brush number corresponding to the adhesive strip in that area, and then adjust the preset adhesive application parameters under that brush number; wherein, the preset adhesive application parameters include adhesive flow rate and pre-pressure.

[0032] This invention uses a different brush number for each segment of the glue application trajectory and outputs different brush number sequences to the glue spraying control system via a universal output signal from the coating robot. This enables the binding of different preset glue application parameters for each segment of the glue application trajectory and allows for rapid identification of the brush number corresponding to poorly applied glue strips. Figure 3 By setting different adhesive flow rates and pre-pressure, the adhesive strip spraying can be adjusted. It should be noted that the preset adhesive parameters may also include the dispensing speed.

[0033] Example 4 This embodiment is the fourth embodiment of a method for detecting vehicle body rubber strips. This embodiment is similar to any of the embodiments one to three, except that in this embodiment, in step S5, the offset error range includes a bilateral offset error range. The bilateral offset error range refers to the offset error range of the sum of the distance between the left rubber strip edge position and the weld position and the distance between the right rubber strip edge position and the weld position. That is, it refers to the offset error range of the sum of the distances between the coordinates of the two rubber edge points and the corresponding weld point coordinates. It should be noted that the bilateral offset error range can also be considered to be equal to the sum of the magnitudes of the two unilateral offset error ranges.

[0034] In this embodiment, in step S5, the areas with poor adhesive application include: For a region with n consecutive glue edge point groups that are to be determined, and the sum of the distances between the coordinates of each glue edge point group and the coordinates of the corresponding weld point is greater than the range of double-sided offset error, it is considered to belong to a wide glue diameter defect area. For a group of n consecutive glue edge points that are to be determined, and the sum of the distances between the coordinates of each glue edge point group and the coordinates of the corresponding weld point is less than the range of the double-sided offset error, it is considered to belong to the narrow glue diameter defect area. For defects that do not fall into either the wide-diameter or narrow-diameter defect area, a glue strip identification model is used for defect identification; specifically, the existing glue strip identification YOLO model can be selected.

[0035] In this embodiment, in step S62: For areas with poor performance due to wide rubber diameter, adjustments can be made by reducing the rubber flow rate or pre-pressure by 5%. For areas with poor performance due to narrow rubber diameter, adjustments can be made by increasing the rubber flow rate by 5% or by adjusting the pre-pressure. For areas identified as perforated, adjustments are made by increasing the rubber flow rate or pre-pressure by 10%. For areas identified as broken or forked glue lines, activate the glue gun nozzle flushing function.

[0036] Specifically, in step S62, after each adjustment by decreasing or increasing the adhesive flow rate, or each adjustment by decreasing or increasing the pre-pressure, the coated adhesive strip is inspected to check whether the distance between the coordinates of the adhesive edge point group and the corresponding weld point coordinates is within the double-sided offset error range. If it is within the double-sided offset error range, the preset adhesive coating parameters are adjusted; if it is still not within the double-sided offset error range, the adhesive flow rate is further decreased or increased, or the pre-pressure is further decreased or increased.

[0037] In the specific implementation of the above embodiments, the technical features can be combined in any non-contradictory way. For the sake of brevity, not all possible combinations of the above technical features are described. However, as long as the combination of these technical features is not contradictory, it should be considered to be within the scope of this specification.

[0038] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the implementation of the present invention. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively describe all embodiments here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A method for detecting vehicle body rubber strips, characterized in that, Includes the following steps: S1. Obtain an image of the un-adhesive-coated white body, trace the weld seams in the image to obtain weld seam lines, and obtain a weld seam traced image; S2. Select several feature points in the weld outline image; S3. Obtain an image of the glued white body, use the feature points selected in step S2 to correct the image, then obtain the coordinate position of the region contour of each glue strip in the image, obtain multiple glue edge point groups and their coordinates, and obtain the glue strip contour image. S4. Using the feature points selected in step S2, the weld line in the weld outline image is fitted to the adhesive strip contour image to obtain multiple weld points and their coordinates corresponding to multiple adhesive edge point groups; S5. Check point by point along the weld line: If the distance between the coordinates of the current glue edge point group and the coordinates of the corresponding weld point are within the offset error range, the glue edge point group is considered qualified; otherwise, it is considered pending. For an area with n consecutive glue edge point groups that are considered pending, it is considered to be a poor glue application area.

2. The method for detecting vehicle body rubber strips according to claim 1, characterized in that, Step S1 includes the following steps: S11. Select the un-applied white body and collect multiple images of a local area of ​​the un-applied white body; wherein the total imaging range of the multiple images covers the entire un-applied white body, and the weld seam in each image is in an intact state; S12. The weld seam in each image obtained in step S11 is outlined to obtain the weld seam line, and multiple weld seam outlined images are obtained accordingly.

3. The method for detecting vehicle body rubber strips according to claim 1, characterized in that, In step S2, at least three hole locations are selected as feature points in the weld outline image.

4. The method for detecting vehicle body rubber strips according to claim 1, characterized in that, Step S3 includes the following steps: S31. Acquire multiple images of local locations of the glued body-in-white during transport; wherein the total imaging range of the multiple images covers the entire glued body-in-white, and the glue strip in each image is in an intact state; S32. Using the feature points selected in step S2, correct the multiple images in step S31, and then establish a spatial coordinate system for each image. S33. Use the adhesive strip recognition model to recognize multiple images from step S32 to obtain the region contour of each segment of adhesive strip in the image; S34. Using the adhesive strip cutting model, the region contour of each adhesive strip is cut at the millimeter level. Multiple adhesive edge points and their coordinates are obtained through the intersection of the cutting line and the region contour. Then, the adhesive edge points obtained by cutting through the same cutting line are grouped into an adhesive edge point group, and the adhesive strip contour image is obtained.

5. The method for detecting vehicle body rubber strips according to claim 4, characterized in that, In step S4, the weld point is the intersection of the weld line and the cutting line after image fitting.

6. The method for detecting vehicle body rubber strips according to claim 4, characterized in that, In step S5, the offset error range includes a unilateral offset error range; If the distance between the coordinates of the glue edge points and the corresponding weld point coordinates in the current glue edge point group is within the range of the one-sided offset error, then the glue edge point group is considered qualified; otherwise, it is considered pending. For an area with n consecutive glue edge point groups that are considered pending, the area is considered to be a poor glue application area. The left endpoint of the one-sided offset error range is 3mm, and 5≤n≤15.

7. The method for detecting vehicle body rubber strips according to any one of claims 1 to 6, characterized in that, It also includes step S6: for areas with poor adhesive application, obtain the adhesive strip corresponding to the area, and adjust the preset adhesive application parameters associated with the adhesive application trajectory corresponding to the adhesive strip.

8. The method for detecting vehicle body rubber strips according to claim 7, characterized in that, Step S6 includes the following steps: S61. Assign a brush number to each section of the adhesive application trajectory, so that the preset adhesive application parameters associated with each section of the adhesive application trajectory have a corresponding brush number, and so that each adhesive strip also has a corresponding brush number for each section of the adhesive application trajectory. S62. For areas with poor adhesive application, retrieve the brush number corresponding to the adhesive strip in that area, and then adjust the preset adhesive application parameters under that brush number; wherein, the preset adhesive application parameters include adhesive flow rate and pre-pressure.

9. The method for detecting vehicle body rubber strips according to claim 8, characterized in that, In step S5, the offset error range includes a two-sided offset error range; wherein, the poor adhesive application area includes: For a region with n consecutive glue edge point groups that are to be determined, and the sum of the distances between the coordinates of each glue edge point group and the coordinates of the corresponding weld point is greater than the range of double-sided offset error, it is considered to belong to a wide glue diameter defect area. For a group of n consecutive glue edge points that are to be determined, and the sum of the distances between the coordinates of each glue edge point group and the coordinates of the corresponding weld point is less than the range of the double-sided offset error, it is considered to belong to the narrow glue diameter defect area. In step S62, for the wide-diameter defect area, the adjustment is made by reducing the glue flow rate or pre-pressure by 5%; for the narrow-diameter defect area, the adjustment is made by increasing the glue flow rate or pre-pressure by 5%.

10. The method for detecting vehicle body rubber strips according to claim 9, characterized in that, In step S5, for defects that do not belong to either the wide-diameter defect area or the narrow-diameter defect area, the adhesive strip identification model is used for defect identification. In step S62, for areas identified as perforated, the flow rate or pre-pressure of the adhesive is increased by 10%; for areas identified as areas of adhesive breakage or bifurcation, the nozzle flushing function of the glue gun is activated.

Images