Vehicle body gluing quality detection system and detection method

Abstract

The invention provides a vehicle body gluing quality detection system and detection method, and relates to the technical field of vehicle gluing detection, and the system comprises a vehicle body positioning module which is used for detecting the type of a to-be-detected vehicle and the real-time coordinate of the to-be-detected vehicle in a vehicle body gluing quality detection station when the to-be-detected vehicle enters the vehicle body gluing quality detection station, adjusting the shooting position of each detection robot according to the vehicle type, the real-time coordinate and a pre-stored reference coordinate; the quality detection module is connected with the vehicle body positioning module and is used for collecting adhesive tape images of a plurality of adhesive coating positions of the vehicle to be detected through the detection robots after the detection robots are adjusted, then identifying adhesive tapes in the adhesive tape images respectively, teaching corresponding standard inspection lines in the adhesive tape images, and sending the standard inspection lines to the vehicle body positioning module; and performing gluing quality detection on the corresponding adhesive tape according to each standard inspection line, and recording each corresponding detection result. The beneficial effects are that full automation is realized, the detection camera position of the machine detector is adjusted according to the vehicle type, and the detection error is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile glue coating detection, and in particular to a vehicle body glue coating quality detection system and detection method. Background Art

[0002] With the application of robot gluing in automatic automobile production lines, in order to ensure the quality of gluing, a quantitative gluing device is used to control the amount of glue output. However, if the glue gun nozzle is crooked and the glue output from the glue gun is not applied to the workpiece, it will cause a gluing quality accident, which will directly affect the quality of the car and there is a possibility of car leakage, noise, etc.

[0003] In the automatic production line of vehicle manufacturing, some gluing areas are unattended, and the traditional manual visual inspection method is slow and prone to errors.

[0004] It is necessary to provide a detection system that can quickly and accurately detect the glue coating quality of a vehicle that has been glued, so as to realize automatic, fast and accurate vehicle body glue coating quality detection. Summary of the invention

[0005] In view of the problems existing in the prior art, the present invention provides a vehicle body glue coating quality detection system, which is applied in a vehicle body glue coating quality detection station. The vehicle body quality detection station is associated with a plurality of detection robots, including:

[0006] A vehicle body positioning module, used to detect the vehicle model of the vehicle to be inspected and its real-time coordinates in the vehicle body glue quality inspection station when the vehicle to be inspected enters the vehicle body glue quality inspection station, and adjust the shooting position of each inspection robot according to the vehicle model, the real-time coordinates and the pre-stored reference coordinates;

[0007] The quality inspection module is connected to the vehicle body positioning module and is used to collect images of rubber strips at multiple gluing positions of the vehicle to be inspected through each of the inspection robots after the inspection robots are adjusted, and then respectively identify the rubber strips in each of the rubber strip images, and teach the corresponding standard inspection lines in each of the rubber strip images, and then respectively perform glue coating quality inspections on the corresponding rubber strips according to each of the standard inspection lines and record the corresponding inspection results.

[0008] Preferably, a fixed camera is pre-installed in the vehicle body glue coating quality inspection station, and the vehicle body positioning module includes:

[0009] A first detection unit is used to obtain a body code of the vehicle to be detected by the fixed camera to determine the vehicle type, and then photograph the vehicle to be detected by the fixed camera to obtain a body image;

[0010] a second detection unit, connected to the first detection unit, for identifying vehicle body feature points in the vehicle body image, and then performing coordinate system transformation to obtain spatial coordinates of the vehicle body feature points in a spatial coordinate system, and using the spatial coordinates as the real-time coordinates of the vehicle to be detected;

[0011] A storage unit, used to store the reference coordinates corresponding to each of the vehicle models, and a plurality of associated shooting points;

[0012] An adjustment unit is respectively connected to the first detection unit, the second detection unit and the storage unit, and is used to obtain an offset according to the real-time coordinates and the reference coordinates corresponding to the vehicle model, and then control each of the detection robots to move to the corresponding shooting point, and adjust the shooting position of each of the detection robots according to the offset.

[0013] Preferably, a detection camera is provided at the end of the arm of the detection robot, and each detection robot stores the initial position of the corresponding detection camera in the robot coordinate system with itself as the coordinate origin, and the adjustment unit includes:

[0014] A first adjustment subunit, configured to obtain the offset according to the real-time coordinates and the reference coordinates corresponding to the vehicle type;

[0015] a second adjustment subunit, connected to the first adjustment subunit, and configured to obtain the robot coordinates of each of the detection robots in the spatial coordinate system according to the installation position of the fixed camera and the installation position of each of the detection robots, and then control each of the detection robots to move to the corresponding shooting point;

[0016] The third adjustment subunit is connected to the second adjustment subunit and is used to obtain the camera position of each detection camera in the spatial coordinate system according to the coordinates of each robot and the corresponding initial position, and then adjust the position of each camera according to the offset to adjust the shooting position of the corresponding detection robot.

[0017] Preferably, the glue coating quality detection includes glue strip gray value detection, glue strip width detection and glue strip offset detection, and the quality detection module includes:

[0018] A teaching unit, used for collecting a plurality of rubber strip images of the vehicle to be inspected by each of the inspection robots after the inspection robots are adjusted, then identifying the rubber strip in each of the teaching images for each of the rubber strip images, then generating the corresponding standard inspection line in the rubber strip image according to an externally input instruction, then selecting a plurality of inspection points on the standard inspection line at preset intervals to obtain a teaching image;

[0019] The detection unit is connected to the teaching unit and is used to perform glue strip gray value detection, glue strip width detection and glue strip offset detection on each inspection point in each teaching image and record the corresponding detection results.

[0020] Preferably, the detection result includes a grayscale detection result, a width detection result, and an offset detection result, and the detection unit includes:

[0021] A first detection subunit is used to generate a corresponding detection frame for each of the inspection points, and when it is determined that the grayscale value pixels of the rubber strip in the detection frame are greater than a preset grayscale threshold, the grayscale is unqualified as the grayscale detection result; when it is determined that the grayscale value pixels in the detection frame are not greater than the grayscale threshold, the grayscale is qualified as the grayscale detection result;

[0022] A second detection subunit is used for, for each of the inspection points, when it is determined that the width of the rubber strip at the inspection point in the length direction perpendicular to the inspection line is within a preset width range, to take the width as qualified as the width detection result, and when it is determined that the width of the corresponding rubber strip in the length direction perpendicular to the inspection line is not within the width range, to take the width as unqualified as the width detection result;

[0023] The third detection subunit is used to calculate the distance between the center point of the rubber strip at the checkpoint and the checkpoint for each of the checkpoints, and when it is judged that the distance is not greater than a preset offset threshold, take the position as qualified as the offset detection result; and when it is judged that the distance is greater than the offset threshold, take the position as unqualified as the offset detection result.

[0024] Preferably, it also includes:

[0025] A display module is connected to the quality inspection module and is used to display each of the inspection results to the staff and to prompt the staff when the inspection result indicates that the glue coating quality is unqualified.

[0026] The present invention also provides a vehicle body glue coating quality detection method, which is applied to the above-mentioned vehicle body glue coating quality detection system, and the vehicle body glue coating quality detection method comprises:

[0027] Step S1, the body glue quality detection system detects the model of the vehicle to be detected and the real-time coordinates in the body glue quality detection station when the vehicle to be detected enters the body glue quality detection station, and adjusts the shooting position of each detection robot according to the model, the real-time coordinates and the pre-stored reference coordinates;

[0028] Step S2, the vehicle body glue coating quality inspection system collects the rubber strip images of multiple glue coating positions of the vehicle to be inspected through each of the inspection robots and then respectively identifies the rubber strips in each of the rubber strip images, and shows the corresponding standard inspection lines in each of the rubber strip images, and then performs glue coating quality inspection on the corresponding rubber strips according to each of the standard inspection lines and records the corresponding inspection results.

[0029] Preferably, the vehicle body glue coating quality inspection station is pre-installed with a fixed camera, and also stores the reference coordinates corresponding to each vehicle model and multiple associated shooting points; then step S1 includes:

[0030] Step S11, the vehicle body glue coating quality detection system acquires the vehicle body code of the vehicle to be detected by the fixed camera to determine the vehicle model, and then photographs the vehicle to be detected by the fixed camera to obtain a vehicle body image;

[0031] Step S12, the vehicle body glue quality detection system identifies the vehicle body feature points in the vehicle body image, then performs coordinate system transformation to obtain the spatial coordinates of the vehicle body feature points in the spatial coordinate system, and uses the spatial coordinates as the real-time coordinates of the vehicle to be detected;

[0032] In step S13, the vehicle body glue coating quality detection system obtains an offset according to the real-time coordinates and the reference coordinates corresponding to the vehicle model, and then controls each of the detection robots to move to the corresponding shooting point, and adjusts the shooting position of each of the detection robots according to the offset.

[0033] Preferably, a detection camera is provided at the end of the arm of the detection robot, and each detection robot stores the initial position of the corresponding detection camera in the robot coordinate system with itself as the coordinate origin, then step S13 comprises:

[0034] Step S131, the vehicle body glue coating quality detection system then processes the real-time coordinates and the reference coordinates corresponding to the vehicle model to obtain the offset;

[0035] Step S132, the vehicle body glue coating quality detection system obtains the robot coordinates of each detection robot in the space coordinate system according to the installation position of the fixed camera and the installation position of each detection robot, and then controls each detection robot to move to the corresponding shooting point;

[0036] In step S133, the vehicle body glue coating quality detection system obtains the camera position of each detection camera in the spatial coordinate system according to the coordinates of each robot and the corresponding initial position, and then adjusts the position of each camera according to the offset to adjust the shooting position of the corresponding detection robot.

[0037] Preferably, the glue coating quality detection includes glue strip gray value detection, glue strip width detection and glue strip offset detection, and the step S2 includes:

[0038] Step S21, the vehicle body glue coating quality inspection system collects multiple rubber strip images of the vehicle to be inspected through each of the inspection robots, identifies the rubber strip in each of the rubber strip images, and then generates the corresponding standard inspection line in the rubber strip image according to an external input instruction, and then selects multiple inspection points on the standard inspection line at preset intervals to obtain a teaching image;

[0039] Step S22, the vehicle body glue coating quality detection system performs glue strip gray value detection, glue strip width detection and glue strip offset detection on each inspection point in each teaching image and records the corresponding detection results.

[0040] The above technical solution has the following advantages or beneficial effects: by providing a body glue quality inspection station that is inspected by a robot, the glue quality of the vehicle after the gluing is inspected, full automation is achieved, and the inspection results are fast and accurate. The position of the inspection camera of the robot detector is adjusted according to different vehicle models, which can ensure that the rubber strip in the inspection image maintains the same position in the collected picture during each inspection, thereby reducing the inspection error. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a structural schematic diagram of a vehicle body glue coating quality inspection station in a preferred embodiment of the present invention;

[0042] Figure 2 The figure is a flow chart of a method for detecting the quality of glue coating on a vehicle body in a preferred embodiment of the present invention;

[0043] Figure 3 A schematic diagram of a sub-process of step S1 in a preferred embodiment of the present invention;

[0044] Figure 4 Schematic diagram of a sub-flow chart of step S13 in a preferred embodiment of the present invention;

[0045] Figure 5 This is a schematic diagram of a sub-process of step S2 in a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0046] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. The present invention is not limited to this embodiment, and other embodiments may also fall within the scope of the present invention as long as they conform to the gist of the present invention.

[0047] In a preferred embodiment of the present invention, based on the above problems existing in the prior art, a vehicle body glue coating quality detection system is provided, which is applied to a vehicle body glue coating quality detection station. The vehicle body quality detection station is associated with multiple detection robots, such as Figure 1 As shown, including:

[0048] The vehicle body positioning module 1 is used to detect the vehicle model of the vehicle to be inspected and the real-time coordinates in the vehicle body glue quality inspection station when the vehicle to be inspected enters the vehicle body glue quality inspection station, and adjust the shooting position of each inspection robot according to the vehicle model, real-time coordinates and pre-stored reference coordinates;

[0049] The quality inspection module 2 is connected to the vehicle body positioning module 1, and is used to collect images of rubber strips at multiple gluing positions of the vehicle to be inspected through each inspection robot after the inspection robot is adjusted, and then identify the rubber strips in each rubber strip image respectively, and teach the corresponding standard inspection line in each rubber strip image, and then perform glue coating quality inspection on the corresponding rubber strips according to each standard inspection line and record the corresponding inspection results.

[0050] In a preferred embodiment of the present invention, a fixed camera is pre-installed in the vehicle body glue quality inspection station. Figure 1 As shown, the vehicle body positioning module 1 includes:

[0051] The first detection unit 11 is used to obtain the body code of the vehicle to be detected by a fixed camera to determine the vehicle model, and then photograph the vehicle to be detected by the fixed camera to obtain a body image;

[0052] The second detection unit 12 is connected to the first detection unit 11 and is used to identify the body feature points in the body image, and then perform coordinate system transformation to obtain the spatial coordinates of the body feature points in the spatial coordinate system, and use the spatial coordinates as the real-time coordinates of the vehicle to be detected;

[0053] The storage unit 13 is used to store the reference coordinates corresponding to each vehicle type and the associated multiple shooting points;

[0054] The adjustment unit 14 is respectively connected to the first detection unit 11, the second detection unit 12 and the storage unit 13, and is used to obtain an offset according to the real-time coordinates and the reference coordinates corresponding to the vehicle model, and then control each detection robot to move to the corresponding shooting point, and adjust the shooting position of each detection robot according to the offset.

[0055] Specifically, in this embodiment, the system is applied in a car body gluing inspection station, in which a fixed camera is fixed and associated with a plurality of movable inspection robots (in this embodiment, a six-axis robot of FANUC is preferably used), the fixed camera is used to take pictures of the car body, and obtain the car body code in the image to determine which car model is currently entering the station, because different car models have different frame sizes and gluing positions, so the reference coordinates of various car models in the inspection station and the corresponding shooting points are pre-stored in the inspection station, each shooting point corresponds to a gluing position of the car body, and each inspection robot needs to move to the corresponding shooting point to take pictures of the gluing position on the car body to detect the quality of the rubber strip; however, due to When a vehicle enters the inspection station, there will inevitably be a certain offset from the reference position, so it is necessary to use a fixed camera to take a picture of the vehicle body and identify the feature points of the vehicle body to obtain the coordinate position in the image coordinate system. When the fixed camera is set, the spatial coordinates of the fixed camera in the inspection station under the spatial coordinate system have been saved. Then, through the coordinate system transformation, the spatial coordinates of the feature points of the vehicle body in the spatial coordinate system are obtained as the real-time position of the vehicle in the inspection station. At this time, the offset between the real-time position and the reference position of the vehicle can be calculated, and the shooting position of the inspection robot can be further adjusted to ensure that when shooting the gluing position of vehicles of the same model, the position of the rubber strip in the image remains consistent to improve the accuracy of the inspection.

[0056] In a preferred embodiment of the present invention, a detection camera is provided at the end of the arm of the detection robot, and each detection robot stores the initial position of the corresponding detection camera in the robot coordinate system with the detection robot itself as the coordinate origin. Figure 1 As shown, the adjustment unit 14 includes:

[0057] The first adjustment subunit 141 is used to obtain an offset according to the real-time coordinates and the reference coordinates corresponding to the vehicle model;

[0058] The second adjustment subunit 142 is connected to the first adjustment subunit 141 and is used to obtain the robot coordinates of each detection robot in the space coordinate system according to the installation position of the fixed camera and the installation position of each detection robot, and then control each detection robot to move to a corresponding shooting point;

[0059] The third adjustment subunit 143 is connected to the second adjustment subunit 142, and is used to obtain the camera position of each detection camera in the spatial coordinate system according to the coordinates of each robot and the corresponding initial position, and then adjust the position of each camera according to the offset to adjust the shooting position of the corresponding detection robot.

[0060] Specifically, in this embodiment, the offset between the real-time position and the reference position of the vehicle is obtained by the aforementioned method. Since the reference position and the shooting point of the gluing position corresponding to each vehicle model are different, it is necessary to control each detection robot to move to the corresponding shooting point to shoot the gluing position. Before controlling the movement of the detection robot, it is necessary to first know the coordinate position of each detection robot in the detection station. The positional relationship between the fixed camera and the installation position of each detection robot can be obtained through the visual calibration program, thereby obtaining the transformation relationship between the spatial coordinate system and the robot coordinates (the coordinate system established by each detection robot with itself as the coordinate origin); a detection camera is set at the end of the robot arm of each detection robot, and each detection camera is used to shoot and detect the corresponding gluing position on the vehicle body; however, due to the offset between the real-time position and the reference position of the vehicle, the area of ​​the image obtained by shooting the gluing position of the same vehicle model cannot be guaranteed to be completely consistent, which leads to errors in the detection, so the position of the detection camera needs to be adjusted;

[0061] First, each inspection robot has known its own position in the inspection station through the visual calibration program, and then established the corresponding robot coordinate system with itself as the coordinate origin. The position of the inspection camera installed at the end of its arm in its own robot coordinate system is obtained through the hand-eye calibration program to determine the position of its own inspection camera in the entire inspection station. Before starting the inspection, the inspection camera will be in the preset default initial position. Then, the initial position of each inspection camera will be further adjusted according to the offset obtained above to ensure that the same area can be covered when shooting the corresponding gluing position, ensuring that each shooting and inspection can be consistent to improve accuracy.

[0062] In a preferred embodiment of the present invention, the glue coating quality detection includes the detection of the gray value of the glue strip, the detection of the width of the glue strip and the detection of the offset of the glue strip. Figure 1 As shown, the quality detection module 2 includes:

[0063] The teaching unit 21 is used to collect multiple rubber strip images of the vehicle to be inspected through each inspection robot after the inspection robot is adjusted, and then for each rubber strip image, identify the rubber strip in each teaching image, and then generate a corresponding standard inspection line in the rubber strip image according to an external input instruction, and then select multiple inspection points on the standard inspection line at a preset interval to obtain a teaching image;

[0064] The detection unit 22 is connected to the teaching unit 21 and is used to perform glue strip gray value detection, glue strip width detection and glue strip offset detection on each inspection point in each teaching image and record the corresponding detection results.

[0065] Specifically, in this embodiment, after the inspection robot reaches the designated shooting point and adjusts the position of the inspection camera, it controls the inspection camera to take pictures, and selects the corresponding visual program to perform quality inspection on the rubber strip in the image;

[0066] First, the inspection line needs to be taught for the captured rubber strip image. The rubber strip in the rubber strip image is first identified, and then the staff selects the starting point and end point of the inspection line in the current rubber strip image through the display screen and connects them (the inspection line is a straight line, a broken line or a curve and needs to be selected by the staff. There may be multiple rubber strips and corresponding inspection lines on the same rubber strip image). The inspection lines of the rubber strip image corresponding to the same gluing position of the same vehicle model are the same. Then the detection system selects multiple inspection points on the detection line with the same spacing. The detection program installed in the detection system performs rubber strip grayscale value detection, rubber strip width detection and rubber strip offset detection on each inspection point and records the corresponding detection results.

[0067] In a preferred embodiment of the present invention, the detection result includes a grayscale detection result, a width detection result, and an offset detection result. Figure 1 As shown, the detection unit 22 includes:

[0068] The first detection subunit 221 is used to generate a corresponding detection frame for each inspection point, and when it is determined that the gray value pixel of the rubber strip in the detection frame is greater than a preset gray value threshold, the gray value is unqualified as the gray value detection result; when it is determined that the gray value pixel in the detection frame is not greater than the gray value threshold, the gray value is qualified as the gray value detection result;

[0069] The second detection subunit 222 is used for, for each inspection point, when it is judged that the width of the rubber strip at the inspection point in the length direction perpendicular to the inspection line is within a preset width range, to take the width as a qualified width detection result; and when it is judged that the width of the corresponding rubber strip in the length direction perpendicular to the inspection line is not within the width range, to take the width as an unqualified width detection result;

[0070] The third detection subunit 223 is used to calculate the distance between the center point of the rubber strip at the checkpoint and the checkpoint for each checkpoint, and when it is judged that the distance is not greater than a preset offset threshold, the position is qualified as the offset detection result; and when it is judged that the distance is greater than the offset threshold, the position is unqualified as the offset detection result.

[0071] Specifically, in this embodiment, the glue coating quality detection is performed based on the checkpoints generated in the above steps, and whether the checkpoint is qualified is determined by judging whether the pixel grayscale value distribution, the width of the glue strip, and the center position of the glue strip near the checkpoint in the glue strip image are within the set threshold range; when the number of unqualified checkpoints is less than the set threshold, the glue strip at that location is determined to be qualified; when all the glue strips in the image are qualified, the glue coating quality detection result of the glue strip image is determined to be qualified;

[0072] For the gray value detection of the rubber strip, a rectangular detection frame with a fixed relative position of each inspection point needs to be set to determine the pixel gray value distribution of the rubber strip image within each detection frame. When the gray value pixel ratio in the detection frame is higher than the threshold, the inspection point is judged to be unqualified, otherwise it is qualified.

[0073] For the rubber strip width detection, the rubber strip width perpendicular to the length direction of the inspection line at the inspection point is measured with the inspection point as the center. The rubber strip width range is matched to the model based on the edge. When the rubber strip width is too wide or too narrow, it is judged as unqualified.

[0074] For the rubber strip offset detection, the coordinates of the center points of the rubber strip edges on both sides based on the edge pair model matching are calculated, and the distance between the center points and the check points at that location is used as the rubber strip offset at that location. When the rubber strip offset is greater than the set threshold, it is judged as unqualified, otherwise it is qualified;

[0075] The quality inspection visual program information in the inspection system (including inspection lines, inspection points, inspection items and judgment thresholds, etc.), the inspection results of each inspection and the name of the collected image file are automatically written into the inspection log for record keeping.

[0076] In a preferred embodiment of the present invention, Figure 1 As shown, it also includes:

[0077] The display module 3 is connected to the quality inspection module 2 and is used to display various inspection results to the staff and to remind the staff when the inspection results indicate that the glue coating quality is unqualified.

[0078] Specifically, in this embodiment, various test results are displayed to each staff member through a display screen, and when the test result indicates that the glue coating quality test is unqualified, the unqualified area in the corresponding glue strip image is displayed to prompt the staff member that recoating is required.

[0079] The present invention also provides a vehicle body glue coating quality detection method, which is applied to the above vehicle body glue coating quality detection system, such as Figure 2 As shown, the vehicle body glue quality detection method includes:

[0080] Step S1, the body glue quality inspection system detects the model of the vehicle to be inspected and the real-time coordinates in the body glue quality inspection station when the vehicle to be inspected enters, and adjusts the shooting position of each inspection robot according to the model, real-time coordinates and pre-stored reference coordinates;

[0081] Step S2, the vehicle body glue quality inspection system collects the images of the rubber strips at multiple glue coating positions of the vehicle to be inspected through each inspection robot, and then identifies the rubber strips in each rubber strip image respectively, and shows the corresponding standard inspection line in each rubber strip image, and then performs glue coating quality inspection on the corresponding rubber strips according to each standard inspection line and records the corresponding inspection results.

[0082] In a preferred embodiment of the present invention, a fixed camera is pre-installed in the vehicle body glue quality inspection station, and the reference coordinates corresponding to each vehicle model and the associated multiple shooting points are stored; Figure 3 As shown, step S1 includes:

[0083] Step S11, the body glue quality inspection system acquires the body code of the vehicle to be inspected by a fixed camera to determine the vehicle model, and then photographs the vehicle to be inspected by the fixed camera to obtain a body image;

[0084] Step S12, the body glue quality detection system identifies the body feature points in the body image, and then performs coordinate system transformation to obtain the spatial coordinates of the body feature points in the spatial coordinate system, and uses the spatial coordinates as the real-time coordinates of the vehicle to be detected;

[0085] In step S13, the vehicle body glue coating quality detection system obtains an offset according to the real-time coordinates and the reference coordinates corresponding to the vehicle model, and then controls each detection robot to move to the corresponding shooting point, and adjusts the shooting position of each detection robot according to the offset.

[0086] In a preferred embodiment of the present invention, a detection camera is provided at the end of the arm of the detection robot, and each detection robot stores the initial position of the corresponding detection camera in the robot coordinate system with itself as the coordinate origin. Figure 4 As shown, step S13 includes:

[0087] Step S131, the body glue quality detection system then processes the real-time coordinates and the reference coordinates corresponding to the vehicle model to obtain the offset;

[0088] Step S132, the vehicle body glue coating quality inspection system obtains the robot coordinates of each inspection robot in the space coordinate system according to the installation position of the fixed camera and the installation position of each inspection robot, and then controls each inspection robot to move to the corresponding shooting point;

[0089] In step S133, the vehicle body glue coating quality inspection system obtains the camera position of each inspection camera in the space coordinate system according to the coordinates of each robot and the corresponding initial position, and then adjusts the position of each camera according to the offset to adjust the shooting position of the corresponding inspection robot.

[0090] In a preferred embodiment of the present invention, the glue coating quality detection includes the detection of the gray value of the glue strip, the detection of the width of the glue strip and the detection of the offset of the glue strip. Figure 5 As shown, step S2 includes:

[0091] Step S21, the vehicle body glue quality inspection system collects multiple rubber strip images of the vehicle to be inspected through each inspection robot, identifies the rubber strip in each rubber strip image, and then generates a corresponding standard inspection line in the rubber strip image according to an external input instruction, and then selects multiple inspection points on the standard inspection line at preset intervals to obtain a teaching image;

[0092] Step S22, the vehicle body glue coating quality detection system performs glue strip gray value detection, glue strip width detection and glue strip offset detection on each inspection point in each teaching image and records the corresponding detection results.

[0093] The above are only preferred embodiments of the present invention, and are not intended to limit the implementation methods and protection scope of the present invention. Those skilled in the art should be aware that all solutions obtained by equivalent substitutions and obvious changes made using the contents of this specification and illustrations should be included in the protection scope of the present invention.

Claims

1. A vehicle body glue coating quality detection system, characterized in that: Applied in the body glue quality inspection station, the body quality inspection station is associated with multiple inspection robots, including: A vehicle body positioning module, used to detect the vehicle model of the vehicle to be inspected and its real-time coordinates in the vehicle body glue quality inspection station when the vehicle to be inspected enters the vehicle body glue quality inspection station, and adjust the shooting position of each inspection robot according to the vehicle model, the real-time coordinates and the pre-stored reference coordinates; The quality inspection module is connected to the vehicle body positioning module and is used to collect images of rubber strips at multiple gluing positions of the vehicle to be inspected through each of the inspection robots after the inspection robots are adjusted, and then respectively identify the rubber strips in each of the rubber strip images, and teach the corresponding standard inspection lines in each of the rubber strip images, and then respectively perform gluing quality inspections on the corresponding rubber strips according to each of the standard inspection lines and record the corresponding inspection results.

2. The vehicle body glue coating quality detection system according to claim 1 is characterized in that: The body glue quality inspection station is pre-installed with a fixed camera, and the body positioning module includes: A first detection unit is used to obtain a body code of the vehicle to be detected by the fixed camera to determine the vehicle type, and then photograph the vehicle to be detected by the fixed camera to obtain a body image; a second detection unit, connected to the first detection unit, for identifying vehicle body feature points in the vehicle body image, and then performing coordinate system transformation to obtain spatial coordinates of the vehicle body feature points in a spatial coordinate system, and using the spatial coordinates as the real-time coordinates of the vehicle to be detected; A storage unit, used to store the reference coordinates corresponding to each of the vehicle models, and a plurality of associated shooting points; An adjustment unit is respectively connected to the first detection unit, the second detection unit and the storage unit, and is used to obtain an offset according to the real-time coordinates and the reference coordinates corresponding to the vehicle model, and then control each of the detection robots to move to the corresponding shooting point, and adjust the shooting position of each of the detection robots according to the offset.

3. The vehicle body glue coating quality detection system according to claim 2 is characterized in that: The detection robot is provided with a detection camera at the end of its arm, and each detection robot stores the initial position of the corresponding detection camera in the robot coordinate system with itself as the coordinate origin. The adjustment unit includes: A first adjustment subunit, configured to obtain the offset according to the real-time coordinates and the reference coordinates corresponding to the vehicle type; a second adjustment subunit, connected to the first adjustment subunit, and configured to obtain the robot coordinates of each of the detection robots in the spatial coordinate system according to the installation position of the fixed camera and the installation position of each of the detection robots, and then control each of the detection robots to move to the corresponding shooting point; The third adjustment subunit is connected to the second adjustment subunit and is used to obtain the camera position of each detection camera in the spatial coordinate system according to the coordinates of each robot and the corresponding initial position, and then adjust the position of each camera according to the offset to adjust the shooting position of the corresponding detection robot.

4. The vehicle body glue coating quality detection system according to claim 1 is characterized in that: The glue coating quality detection includes glue strip gray value detection, glue strip width detection and glue strip offset detection, and the quality detection module includes: A teaching unit, used for collecting a plurality of rubber strip images of the vehicle to be inspected by each of the inspection robots after the inspection robots are adjusted, then identifying the rubber strip in each of the teaching images for each of the rubber strip images, then generating the corresponding standard inspection line in the rubber strip image according to an externally input instruction, then selecting a plurality of inspection points on the standard inspection line at preset intervals to obtain a teaching image; The detection unit is connected to the teaching unit and is used to perform glue strip gray value detection, glue strip width detection and glue strip offset detection on each inspection point in each teaching image and record the corresponding detection results.

5. The vehicle body glue coating quality detection system according to claim 4 is characterized in that: The detection result includes a grayscale detection result, a width detection result, and an offset detection result, and the detection unit includes: A first detection subunit is used to generate a corresponding detection frame for each of the inspection points, and when it is determined that the grayscale value pixels of the rubber strip in the detection frame are greater than a preset grayscale threshold, the grayscale is unqualified as the grayscale detection result; when it is determined that the grayscale value pixels in the detection frame are not greater than the grayscale threshold, the grayscale is qualified as the grayscale detection result; A second detection subunit is used for, for each of the inspection points, when it is determined that the width of the rubber strip at the inspection point in the length direction perpendicular to the inspection line is within a preset width range, to take the width as qualified as the width detection result, and when it is determined that the width of the corresponding rubber strip in the length direction perpendicular to the inspection line is not within the width range, to take the width as unqualified as the width detection result; The third detection subunit is used to calculate the distance between the center point of the rubber strip at the checkpoint and the checkpoint for each of the checkpoints, and when it is judged that the distance is not greater than a preset offset threshold, take the position as qualified as the offset detection result; and when it is judged that the distance is greater than the offset threshold, take the position as unqualified as the offset detection result.

6. The vehicle body glue coating quality detection system according to claim 1 is characterized in that: Also includes: A display module is connected to the quality inspection module and is used to display each of the inspection results to the staff and to prompt the staff when the inspection result indicates that the glue coating quality is unqualified.

7. A method for detecting the quality of glue coating on a vehicle body, characterized in that: Applied to the vehicle body glue coating quality detection system as claimed in any one of claims 1 to 6, the vehicle body glue coating quality detection method comprises: Step S1, the body glue quality detection system detects the model of the vehicle to be detected and the real-time coordinates in the body glue quality detection station when the vehicle to be detected enters the body glue quality detection station, and adjusts the shooting position of each detection robot according to the model, the real-time coordinates and the pre-stored reference coordinates; Step S2, the vehicle body glue coating quality inspection system collects the rubber strip images of multiple glue coating positions of the vehicle to be inspected through each of the inspection robots and then respectively identifies the rubber strips in each of the rubber strip images, and shows the corresponding standard inspection lines in each of the rubber strip images, and then performs glue coating quality inspection on the corresponding rubber strips according to each of the standard inspection lines and records the corresponding inspection results.

8. The method for detecting the quality of vehicle body glue coating according to claim 7, characterized in that: The vehicle body glue coating quality inspection station is pre-installed with a fixed camera, and also stores the reference coordinates corresponding to each vehicle model and multiple associated shooting points; then the step S1 includes: Step S11, the vehicle body glue coating quality detection system acquires the vehicle body code of the vehicle to be detected by the fixed camera to determine the vehicle model, and then photographs the vehicle to be detected by the fixed camera to obtain a vehicle body image; Step S12, the vehicle body glue quality detection system identifies the vehicle body feature points in the vehicle body image, then performs coordinate system transformation to obtain the spatial coordinates of the vehicle body feature points in the spatial coordinate system, and uses the spatial coordinates as the real-time coordinates of the vehicle to be detected; In step S13, the vehicle body glue coating quality detection system obtains an offset according to the real-time coordinates and the reference coordinates corresponding to the vehicle model, and then controls each of the detection robots to move to the corresponding shooting point, and adjusts the shooting position of each of the detection robots according to the offset.

9. The vehicle body glue coating quality detection method according to claim 8, characterized in that: The detection robot is provided with a detection camera at the end of its arm, and each detection robot stores the initial position of the corresponding detection camera in the robot coordinate system with itself as the coordinate origin. Then, step S13 includes: Step S131, the vehicle body glue coating quality detection system then processes the real-time coordinates and the reference coordinates corresponding to the vehicle model to obtain the offset; Step S132, the vehicle body glue coating quality detection system obtains the robot coordinates of each detection robot in the space coordinate system according to the installation position of the fixed camera and the installation position of each detection robot, and then controls each detection robot to move to the corresponding shooting point; In step S133, the vehicle body glue coating quality detection system obtains the camera position of each detection camera in the spatial coordinate system according to the coordinates of each robot and the corresponding initial position, and then adjusts the position of each camera according to the offset to adjust the shooting position of the corresponding detection robot.

10. The vehicle body glue coating quality detection method according to claim 7, characterized in that: The glue coating quality detection includes glue strip gray value detection, glue strip width detection and glue strip offset detection, and the step S2 includes: Step S21, the vehicle body glue coating quality inspection system collects multiple rubber strip images of the vehicle to be inspected through each of the inspection robots, identifies the rubber strip in each of the rubber strip images, and then generates the corresponding standard inspection line in the rubber strip image according to an external input instruction, and then selects multiple inspection points on the standard inspection line at preset intervals to obtain a teaching image; Step S22, the vehicle body glue coating quality detection system performs glue strip gray value detection, glue strip width detection and glue strip offset detection on each inspection point in each teaching image and records the corresponding detection results.

Images