Complex workpiece detection method and related device
By combining the empty stage station and the MP unit station with robot and multi-angle camera, computer vision and machine learning algorithms are used to conduct all-round detection of complex workpieces, solving the problems of low detection efficiency and missed detection in the existing technology, and realizing the Efficient defect detection.
Patent Information
- Application Number
- CN202411435174.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-15
- Publication Date
- 2024-11-15
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing complex workpiece detection methods cannot effectively detect multiple faces and multiple angles of the workpiece, resulting in low defect detection efficiency and missed inspections in sampling inspection.
Using an empty stage station and an MP station combined with a robot, image acquisition and defect detection are carried out through cameras of different angles, and process defect detection is carried out by integrating computer vision algorithms and machine learning algorithms to achieve complex workpieces All-round inspection.
The defect detection efficiency of complex workpieces is improved, the inspection coverage of all workpieces is ensured, the risk of missed inspection is reduced, and the site station occupation is avoided through high-speed flying shooting technology, which improves the detection efficiency.
Smart Images

Figure CN118961736A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent manufacturing technology, and in particular to a complex workpiece detection method and related devices. Background Art
[0002] In the inspection of some complex workpieces, such as some complex workpieces produced by automobile stamping (such as fenders, left and right side panels, engine hood inner panels, etc.), the existing inspection method is generally carried out through simple visual inspection or sampling inspection. Therefore, in simple visual inspection, it is impossible to perform visual inspection on multiple faces and multiple angles of complex workpieces, so that some defects in the workpiece products cannot be discovered in time, resulting in low defect detection efficiency; or in sampling inspection, it is impossible to inspect all workpiece products, and there may be some possibilities of missed inspections. Summary of the invention
[0003] The purpose of the present invention is to overcome the deficiencies of the prior art. The present invention provides a method and related devices for detecting complex workpieces, so as to realize process-based defect detection of complex workpieces and improve defect detection efficiency.
[0004] In order to solve the above technical problems, an embodiment of the present invention provides a method for detecting complex workpieces, which is applied to an empty stage station, a robot and an MP station, wherein the robot is used to transfer the workpiece to be detected on the empty stage station to the conveyor belt where the MP station is located; the method comprises: The empty stage station receives the ADC workpiece program number, and obtains the workpiece number corresponding to the workpiece to be detected based on the ADC workpiece program number; The first pan-tilt platform on the empty stage station performs image acquisition processing on the front of the workpiece to be inspected placed on the empty stage station based on the workpiece number to obtain a first inspection image set of the workpiece to be inspected, and a plurality of camera devices at different angles are arranged above the first pan-tilt platform; Performing defect detection processing on the workpiece to be inspected based on the inspection images in the first inspection image set, and controlling the robot to transfer the workpiece to be inspected to the conveyor belt according to the first defect detection result; When the workpiece arrival sensor on the conveyor belt senses the workpiece to be detected, the second pan-tilt platform corresponding to the MP part station is triggered to perform image acquisition and processing on the remaining surfaces of the workpiece to be detected except the front surface, so as to obtain a second detection image set of the workpiece to be detected, and a plurality of camera devices with different angles are arranged above and on both sides of the second pan-tilt platform; Based on the detection images in the second detection image set, defect detection processing is performed on the workpiece to be detected to obtain a second defect detection result.
[0005] Optionally, the empty stage station receives an ADC workpiece program number, and obtains a workpiece number corresponding to the workpiece to be inspected based on the ADC workpiece program number, including: The empty stage station receives the ADC workpiece program number based on user input; The empty stage station parses the ADC workpiece program number to obtain the workpiece number of the workpiece to be detected corresponding to the ADC workpiece program number.
[0006] Optionally, the first pan / tilt stage on the empty stage station performs image acquisition processing on the front side of the workpiece to be inspected placed on the empty stage station based on the workpiece number to obtain a first inspection image set of the workpiece to be inspected, including: The empty stage station adjusts the angles of multiple camera devices arranged on the first pan-tilt head based on the workpiece number to form multiple camera devices with adjusted angles; Based on the workpiece number, focus adjustment processing is performed on lenses in the multiple camera devices after the angles are adjusted to obtain the multiple camera devices adjusted on the first pan / tilt platform; After the workpiece to be inspected enters the empty stage workstation, the multiple camera devices adjusted on the first pan-tilt platform are controlled to perform image acquisition and processing on the front side of the workpiece to be inspected, and the images acquired by the multiple camera devices are placed in a collection to obtain a first inspection image set of the workpiece to be inspected.
[0007] Optionally, performing missing detection processing on the workpiece to be inspected based on the inspection images in the first inspection image set includes: The detection images in the first detection image set are subjected to defect detection processing on the workpiece to be detected by utilizing a fusion method of a computer vision algorithm and a machine learning algorithm.
[0008] Optionally, controlling the robot to transfer the workpiece to be inspected to the conveyor belt according to the first defect detection result includes: When there is a defect detection image in the first defect detection result, the empty stage station is controlled to perform abnormal shutdown processing, and the workpiece to be detected on the empty stage station is processed manually; When there is no defect detection image in the first defect detection result, the first defect detection result is visualized and displayed on a designated display screen, and at the same time, the robot is controlled to transfer the workpiece to be inspected to the conveyor belt, with the workpiece to be inspected on the conveyor belt with the reverse side facing up.
[0009] Optionally, when the workpiece arrival sensor on the conveyor belt senses the workpiece to be detected, the second pan / tilt platform corresponding to the MP part station is triggered to perform image acquisition and processing on the remaining surfaces of the workpiece to be detected except the front surface, so as to obtain a second detection image set of the workpiece to be detected, including: When the workpiece in-place sensor on the conveyor belt detects that the workpiece to be detected is in place, a workpiece in-place signal is generated. The workpiece positioning encoder clears the recorded pulse data and recounts according to the workpiece in-place signal to form updated pulse data; When the updated pulse data in the workpiece positioning encoder is consistent with the pulse data triggered by the current workpiece monitoring point, the second pan-tilt head corresponding to the MP part workstation is triggered to perform image acquisition and processing on the remaining surfaces of the workpiece to be inspected except the front side, so as to obtain a second detection image set of the workpiece to be inspected.
[0010] Optionally, before triggering the second pan / tilt platform corresponding to the MP part station to perform image acquisition processing on the remaining surfaces of the workpiece to be inspected except the front surface, the method further includes: The MP section station adjusts the angles of multiple camera devices on the second pan-tilt head and the focal length of the lens in each camera device based on the workpiece number.
[0011] In addition, an embodiment of the present invention further provides a complex workpiece detection device, which is applied to an empty stage station, a robot and an MP station, wherein the robot is used to transfer the workpiece to be detected on the empty stage station to the conveyor belt where the MP station is located; the device comprises: An acquisition module: used for the empty stage station to receive the ADC workpiece program number, and to obtain the workpiece number corresponding to the workpiece to be detected based on the ADC workpiece program number; A first image acquisition module: a first pan-tilt platform on the empty stage station is used to perform image acquisition processing on the front of the workpiece to be inspected placed on the empty stage station based on the workpiece number to obtain a first inspection image set of the workpiece to be inspected, wherein a plurality of camera devices at different angles are arranged above the first pan-tilt platform; A first defect detection module: used for performing defect detection processing on the workpiece to be detected based on the detection images in the first detection image set, and controlling the robot to transfer the workpiece to be detected to the conveyor belt according to the first defect detection result; The second image acquisition module is used to trigger the second pan-tilt platform corresponding to the MP part station to perform image acquisition processing on the remaining surfaces of the workpiece to be detected except the front surface when the workpiece arrival sensor on the conveyor belt senses the workpiece to be detected, so as to obtain a second detection image set of the workpiece to be detected. A plurality of camera devices with different angles are arranged above and on both sides of the second pan-tilt platform; The second defect detection module is used to perform defect detection processing on the workpiece to be detected based on the detection images in the second detection image set to obtain a second defect detection result.
[0012] In addition, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the detection method as described in any one of the above is implemented.
[0013] In addition, an embodiment of the present invention further provides an electronic device, the electronic device comprising: one or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to: execute the detection method according to any one of the above.
[0014] In an embodiment of the present invention, the empty stage station requires the workpiece number corresponding to the workpiece to be inspected; then, according to the workpiece number, the first pan-tilt control is used to perform image acquisition and processing on the front side of the workpiece to be inspected at the empty stage station to obtain a first detection image set; then, according to the detection image in the first detection image set, defect detection processing is performed on the workpiece to be inspected, and according to the first defect detection result, the robot is controlled to transfer the workpiece to be inspected to the conveyor belt; on the conveyor belt, the second pan-tilt corresponding to the MP station is used to perform image acquisition and processing on the remaining sides of the workpiece to be inspected except the front side to obtain a second detection image set; finally, according to the detection image in the second detection image set, defect detection processing is performed on the workpiece to be inspected to obtain a second defect detection result; process-based defect detection of complex workpieces is realized, and defect detection efficiency is improved; and high-speed flying shooting is adopted at the MP station, so as not to occupy the on-site workstation beat and improve detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0016] Figure 1 is a schematic flow chart of a complex workpiece detection method in an embodiment of the present invention; Figure 2 Schematic diagram of the structure of a complex workpiece detection device in an embodiment of the present invention; Figure 3 is a schematic diagram of the structure of an electronic device in an embodiment of the present invention; Figure 4 It is a schematic diagram of movement on the workstation during complex workpiece inspection in this embodiment. DETAILED DESCRIPTION
[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0018] For example, see Figure 1 , Figure 1 It is a schematic flow chart of a method for detecting a complex workpiece in an embodiment of the present invention.
[0019] like Figure 1 As shown, a method for inspecting complex workpieces is applied to an empty stage station, a robot and an MP station, wherein the robot is used to transfer the workpiece to be inspected on the empty stage station to the conveyor belt where the MP station is located; In the specific implementation of the present invention, Figure 4 As shown, the workstation consists of an empty stage station, a robot and multiple MP station stations; the robot is used to transfer the workpiece to be inspected on the empty stage station to the conveyor belt where the MP station is located; the complex workpiece will move on the conveyor belt, and then the second gimbal on the MP station will perform high-speed flying shooting, so that high-speed visual inspection can be achieved without occupying the on-site workstation cycle.
[0020] The method comprises: S11: The empty stage station receives the ADC workpiece program number, and obtains the workpiece number corresponding to the workpiece to be detected based on the ADC workpiece program number; In the specific implementation process of the present invention, the empty stage station receives the ADC workpiece program number, and obtains the workpiece number corresponding to the workpiece to be inspected based on the ADC workpiece program number, including: the empty stage station receives the ADC workpiece program number based on user input; the empty stage station parses the ADC workpiece program number to obtain the workpiece number of the workpiece to be inspected corresponding to the ADC workpiece program number.
[0021] Specifically, the empty stage station needs to receive the ADC workpiece program number through user input, and the ADC workpiece program number contains the workpiece number; then the empty stage station will parse the ADC workpiece program number to obtain the workpiece number of the workpiece to be inspected corresponding to the ADC workpiece program number; the workpiece number is used to determine the model or type of the workpiece to be inspected that needs to be inspected currently, so as to facilitate the subsequent adjustment of the corresponding camera device angle and the focal length of the lens in the camera device by the corresponding pan-tilt stage on the empty stage station and the MP station.
[0022] S12: the first pan-tilt platform on the empty stage station performs image acquisition processing on the front side of the workpiece to be inspected placed on the empty stage station based on the workpiece number to obtain a first inspection image set of the workpiece to be inspected, wherein a plurality of camera devices at different angles are arranged above the first pan-tilt platform; In the specific implementation process of the present invention, the first pan-tilt platform on the empty stage station performs image acquisition and processing on the front side of the workpiece to be inspected placed on the empty stage station based on the workpiece number to obtain a first detection image set of the workpiece to be inspected, including: the empty stage station adjusts the angles of multiple camera devices arranged on the first pan-tilt platform based on the workpiece number to form multiple camera devices after the angles are adjusted; based on the workpiece number, performs focal length adjustment processing on the lenses in the multiple camera devices after the angles are adjusted to obtain the multiple camera devices adjusted on the first pan-tilt platform; after the workpiece to be inspected enters the empty stage station, controls the multiple camera devices adjusted on the first pan-tilt platform to perform image acquisition and processing on the front side of the workpiece to be inspected, and places the images acquired by the multiple camera devices into a set to obtain a first detection image set of the workpiece to be inspected.
[0023] Specifically, after obtaining the workpiece number corresponding to the workpiece to be inspected at the empty stage station, the type of the workpiece to be inspected is indexed through the workpiece number, that is, the angle that needs to be adjusted for the camera device on the first pan-tilt platform on the empty stage station and the focal length that needs to be adjusted for the lens in the camera are indexed through the type of the workpiece to be inspected; then, according to the angles that need to be adjusted corresponding to the multiple camera devices on the first pan-tilt platform, the corresponding angle adjustment is performed on each camera device on the first pan-tilt platform to form multiple camera devices after the angle adjustment; the focal length adjustment processing is performed according to the focal length that needs to be adjusted for each lens in the multiple camera devices on the first pan-tilt platform, and finally the multiple camera devices on the first pan-tilt platform after adjustment are obtained. equipment; finally, after the workpiece to be inspected enters the empty platform station, the multiple camera devices adjusted on the first pan-tilt platform are controlled to perform image acquisition and processing on the front of the workpiece to be inspected, and the images acquired by the multiple camera devices are placed in a collection to obtain a first detection image set of the workpiece to be inspected; the camera device on the first pan-tilt platform has 2 adjustment axes, which will be conducive to inspection, maintenance and replacement, and has a high degree of freedom and can adjust different angles, so as to ensure that each camera device has sufficient shooting angles, and a high-brightness surface light source is arranged on the first pan-tilt platform, and the lens in each camera device is connected with an aviation joint, and the zoom lens design can set the corresponding focal length according to needs.
[0024] S13: performing defect detection processing on the workpiece to be inspected based on the detection images in the first detection image set, and controlling the robot to transfer the workpiece to be inspected to the conveyor belt according to the first defect detection result; In the specific implementation process of the present invention, the defect detection processing of the workpiece to be inspected based on the detection images in the first detection image set includes: performing defect detection processing on the workpiece to be inspected based on the detection images in the first detection image set by using a fusion of computer vision algorithm and machine learning algorithm.
[0025] Furthermore, the controlling the robot to transfer the workpiece to be inspected to the conveyor belt according to the first defect detection result includes: when there is a defect detection image in the first defect detection result, controlling the empty stage workstation to perform abnormal shutdown processing, and manually processing the workpiece to be inspected on the empty stage workstation; when there is no defect detection image in the first defect detection result, visually displaying the first defect detection result on a designated display screen, and controlling the robot to transfer the workpiece to be inspected to the conveyor belt, and the posture of the workpiece to be inspected on the conveyor belt is with the reverse side facing up.
[0026] Specifically, for the defect detection processing of the inspection image, the present embodiment adopts a fusion method of computer vision algorithm and machine learning algorithm, that is, the inspection images in the first inspection image set are subjected to defect detection processing on the workpiece to be inspected by utilizing the fusion method of computer vision algorithm and machine learning algorithm to obtain the first defect detection result.
[0027] After obtaining the first defect detection result, when there is a defect detection image in the first defect detection result, it is necessary to control the empty stage station to perform abnormal shutdown processing, and manually process the workpiece to be inspected on the empty stage station; the processing of the defective workpiece to be inspected here is manual re-inspection and when there is an abnormality in the re-inspection, control the entry into the defective workpiece storage area; when there is no defect detection image in the first defect detection result, the first defect detection result is visualized and processed on the designated display screen, and at the same time, the robot is controlled to transfer the workpiece to be inspected to the conveyor belt, and the posture of the workpiece to be inspected on the conveyor belt is with the back side facing up; this will achieve the control of the workpiece to be inspected to enter the next inspection process.
[0028] S14: When the workpiece arrival sensor on the conveyor belt senses the workpiece to be detected, the second pan-tilt platform corresponding to the MP part station is triggered to perform image acquisition and processing on the remaining surfaces of the workpiece to be detected except the front surface, so as to obtain a second detection image set of the workpiece to be detected, wherein a plurality of camera devices with different angles are arranged above and on both sides of the second pan-tilt platform; In the specific implementation process of the present invention, when the workpiece in-place sensor on the conveyor belt senses the workpiece to be detected, the second pan-tilt stage corresponding to the MP part workstation is triggered to perform image acquisition and processing on the remaining surfaces of the workpiece to be detected except the front side, and a second detection image set of the workpiece to be detected is obtained, including: when the workpiece in-place sensor on the conveyor belt detects that the workpiece to be detected is in place, a workpiece in-place signal is generated, and the workpiece positioning encoder clears and recounts the recorded pulse data according to the workpiece in-place signal to form updated pulse data; when the updated pulse data in the workpiece positioning encoder is consistent with the pulse data triggered by the current workpiece monitoring point, the second pan-tilt stage corresponding to the MP part workstation is triggered to perform image acquisition and processing on the remaining surfaces of the workpiece to be detected except the front side, and a second detection image set of the workpiece to be detected is obtained.
[0029] Furthermore, before triggering the second pan-tilt stage corresponding to the MP part workstation to perform image acquisition and processing on the remaining surfaces of the workpiece to be inspected except the front side, it also includes: the MP part workstation adjusts the angles of multiple camera devices on the second pan-tilt stage and the focal length of the lens in each camera device based on the workpiece number.
[0030] Specifically, before the second gimbal on the MP workstation performs image acquisition, the multiple camera devices on the second gimbal also need to be adjusted; similarly, the multiple camera devices on the second gimbal have two adjustable degrees of freedom, which can ensure that the camera device can be adjusted to the optimal image acquisition angle when acquiring images for different workpieces to be inspected, and has strong compatibility with different workpiece sizes and optimal shooting angles; that is, the MP workstation will adjust the angles of the multiple camera devices on the second gimbal and the focal length of the lens in each camera device according to the workpiece number.
[0031] A workpiece in-place sensor is arranged on the conveyor belt, and real-time detection of workpieces is performed on the conveyor belt through the workpiece in-place sensor. When it is detected that the workpiece to be detected is in place, a workpiece in-place signal is generated; then the workpiece positioning encoder will clear the recorded pulse data and recount according to the workpiece in-place signal to form updated pulse data; finally, when the updated pulse data in the workpiece positioning encoder is consistent with the pulse data triggered by the current workpiece monitoring point, the second pan-tilt head corresponding to the MP workstation is triggered to perform image acquisition processing on the remaining surfaces of the workpiece to be inspected except the front side. The image acquisition processing here is high-speed flying processing, which will not need to occupy the on-site workstation beat, thereby obtaining the second detection image set of the workpiece to be inspected.
[0032] S15: performing defect detection processing on the workpiece to be inspected based on the inspection images in the second inspection image set to obtain a second defect detection result.
[0033] In the specific implementation process of the present invention, after the second detection image set is collected, the defect detection of the workpiece to be inspected is performed on each detection image in the second detection image set in the same way as the fusion of computer vision algorithm and machine learning algorithm; the final second defect detection result is obtained; at the same time, when there is an abnormality in the second defect detection result, it is necessary to control the corresponding MP part workstation to stop and notify manual intervention; when there is no abnormality in the second defect detection result, the inspection result is visualized and displayed on the designated display screen.
[0034] In an embodiment of the present invention, the empty stage station requires the workpiece number corresponding to the workpiece to be inspected; then, according to the workpiece number, the first pan-tilt control is used to perform image acquisition and processing on the front side of the workpiece to be inspected at the empty stage station to obtain a first detection image set; then, according to the detection image in the first detection image set, defect detection processing is performed on the workpiece to be inspected, and according to the first defect detection result, the robot is controlled to transfer the workpiece to be inspected to the conveyor belt; on the conveyor belt, the second pan-tilt corresponding to the MP station is used to perform image acquisition and processing on the remaining sides of the workpiece to be inspected except the front side to obtain a second detection image set; finally, according to the detection image in the second detection image set, defect detection processing is performed on the workpiece to be inspected to obtain a second defect detection result; process-based defect detection of complex workpieces is realized, and defect detection efficiency is improved; and high-speed flying shooting is adopted at the MP station, so as not to occupy the on-site workstation beat and improve detection efficiency.
[0035] For example 2, please refer to Figure 2 , Figure 2 It is a schematic diagram of the structural composition of a complex workpiece detection device in an embodiment of the present invention.
[0036] like Figure 2 As shown, a complex workpiece inspection device is applied to an empty stage station, a robot and an MP station, wherein the robot is used to transfer the workpiece to be inspected on the empty stage station to the conveyor belt where the MP station is located; In the specific implementation of the present invention, Figure 4 As shown, the workstation consists of an empty stage station, a robot and multiple MP station stations; the robot is used to transfer the workpiece to be inspected on the empty stage station to the conveyor belt where the MP station is located; the complex workpiece will move on the conveyor belt, and then the second gimbal on the MP station will perform high-speed flying shooting, so that high-speed visual inspection can be achieved without occupying the on-site workstation cycle.
[0037] The device comprises: Acquisition module 21: used for the empty stage station to receive the ADC workpiece program number, and obtain the workpiece number corresponding to the workpiece to be detected based on the ADC workpiece program number; In the specific implementation process of the present invention, the empty stage station receives the ADC workpiece program number, and obtains the workpiece number corresponding to the workpiece to be inspected based on the ADC workpiece program number, including: the empty stage station receives the ADC workpiece program number based on user input; the empty stage station parses the ADC workpiece program number to obtain the workpiece number of the workpiece to be inspected corresponding to the ADC workpiece program number.
[0038] Specifically, the empty stage station needs to receive the ADC workpiece program number through user input, and the ADC workpiece program number contains the workpiece number; then the empty stage station will parse the ADC workpiece program number to obtain the workpiece number of the workpiece to be inspected corresponding to the ADC workpiece program number; the workpiece number is used to determine the model or type of the workpiece to be inspected that needs to be inspected currently, so as to facilitate the subsequent adjustment of the corresponding camera device angle and the focal length of the lens in the camera device by the corresponding pan-tilt stage on the empty stage station and the MP station.
[0039] The first image acquisition module 22 is used for the first pan-tilt platform on the empty stage station to perform image acquisition processing on the front of the workpiece to be detected placed on the empty stage station based on the workpiece number to obtain a first detection image set of the workpiece to be detected, and a plurality of camera devices with different angles are arranged above the first pan-tilt platform; In the specific implementation process of the present invention, the first pan-tilt platform on the empty stage station performs image acquisition and processing on the front side of the workpiece to be inspected placed on the empty stage station based on the workpiece number to obtain a first detection image set of the workpiece to be inspected, including: the empty stage station adjusts the angles of multiple camera devices arranged on the first pan-tilt platform based on the workpiece number to form multiple camera devices after the angles are adjusted; based on the workpiece number, performs focal length adjustment processing on the lenses in the multiple camera devices after the angles are adjusted to obtain the multiple camera devices adjusted on the first pan-tilt platform; after the workpiece to be inspected enters the empty stage station, controls the multiple camera devices adjusted on the first pan-tilt platform to perform image acquisition and processing on the front side of the workpiece to be inspected, and places the images acquired by the multiple camera devices into a set to obtain a first detection image set of the workpiece to be inspected.
[0040] Specifically, after obtaining the workpiece number corresponding to the workpiece to be inspected at the empty stage station, the type of the workpiece to be inspected is indexed through the workpiece number, that is, the angle that needs to be adjusted for the camera device on the first pan-tilt platform on the empty stage station and the focal length that needs to be adjusted for the lens in the camera are indexed through the type of the workpiece to be inspected; then, according to the angles that need to be adjusted corresponding to the multiple camera devices on the first pan-tilt platform, the corresponding angle adjustment is performed on each camera device on the first pan-tilt platform to form multiple camera devices after the angle adjustment; the focal length adjustment processing is performed according to the focal length that needs to be adjusted for each lens in the multiple camera devices on the first pan-tilt platform, and finally the multiple camera devices on the first pan-tilt platform after adjustment are obtained. equipment; finally, after the workpiece to be inspected enters the empty platform station, the multiple camera devices adjusted on the first pan-tilt platform are controlled to perform image acquisition and processing on the front of the workpiece to be inspected, and the images acquired by the multiple camera devices are placed in a collection to obtain a first detection image set of the workpiece to be inspected; the camera device on the first pan-tilt platform has 2 adjustment axes, which will be conducive to inspection, maintenance and replacement, and has a high degree of freedom and can adjust different angles, so as to ensure that each camera device has sufficient shooting angles, and a high-brightness surface light source is arranged on the first pan-tilt platform, and the lens in each camera device is connected with an aviation joint, and the zoom lens design can set the corresponding focal length according to needs.
[0041] The first defect detection module 23 is used to perform defect detection processing on the workpiece to be detected based on the detection images in the first detection image set, and control the robot to transfer the workpiece to be detected to the conveyor belt according to the first defect detection result; In the specific implementation process of the present invention, the defect detection processing of the workpiece to be inspected based on the detection images in the first detection image set includes: performing defect detection processing on the workpiece to be inspected based on the detection images in the first detection image set by fusing computer vision algorithm with machine learning algorithm.
[0042] Furthermore, the controlling the robot to transfer the workpiece to be inspected to the conveyor belt according to the first defect detection result includes: when there is a defect detection image in the first defect detection result, controlling the empty stage workstation to perform abnormal shutdown processing, and manually processing the workpiece to be inspected on the empty stage workstation; when there is no defect detection image in the first defect detection result, visually displaying the first defect detection result on a designated display screen, and controlling the robot to transfer the workpiece to be inspected to the conveyor belt, and the posture of the workpiece to be inspected on the conveyor belt is with the reverse side facing up.
[0043] Specifically, for the defect detection processing of the inspection image, the present embodiment adopts a fusion method of computer vision algorithm and machine learning algorithm, that is, the inspection images in the first inspection image set are subjected to defect detection processing on the workpiece to be inspected by utilizing the fusion method of computer vision algorithm and machine learning algorithm to obtain the first defect detection result.
[0044] After obtaining the first defect detection result, when there is a defect detection image in the first defect detection result, it is necessary to control the empty stage station to perform abnormal shutdown processing, and manually process the workpiece to be inspected on the empty stage station; the processing of the defective workpiece to be inspected here is manual re-inspection and when there is an abnormality in the re-inspection, control the entry into the defective workpiece storage area; when there is no defect detection image in the first defect detection result, the first defect detection result is visualized and processed on the designated display screen, and at the same time, the robot is controlled to transfer the workpiece to be inspected to the conveyor belt, and the posture of the workpiece to be inspected on the conveyor belt is with the back side facing up; this will achieve the control of the workpiece to be inspected to enter the next inspection process.
[0045] The second image acquisition module 24 is used to trigger the second pan-tilt platform corresponding to the MP part station to perform image acquisition processing on the remaining surfaces of the workpiece to be detected except the front surface when the workpiece arrival sensor on the conveyor belt senses the workpiece to be detected, so as to obtain a second detection image set of the workpiece to be detected. A plurality of camera devices with different angles are arranged above and on both sides of the second pan-tilt platform; In the specific implementation process of the present invention, when the workpiece in-place sensor on the conveyor belt senses the workpiece to be detected, the second pan-tilt stage corresponding to the MP part workstation is triggered to perform image acquisition and processing on the remaining surfaces of the workpiece to be detected except the front side, and a second detection image set of the workpiece to be detected is obtained, including: when the workpiece in-place sensor on the conveyor belt detects that the workpiece to be detected is in place, a workpiece in-place signal is generated, and the workpiece positioning encoder clears and recounts the recorded pulse data according to the workpiece in-place signal to form updated pulse data; when the updated pulse data in the workpiece positioning encoder is consistent with the pulse data triggered by the current workpiece monitoring point, the second pan-tilt stage corresponding to the MP part workstation is triggered to perform image acquisition and processing on the remaining surfaces of the workpiece to be detected except the front side, and a second detection image set of the workpiece to be detected is obtained.
[0046] Furthermore, before triggering the second pan-tilt stage corresponding to the MP part workstation to perform image acquisition and processing on the remaining surfaces of the workpiece to be inspected except the front side, it also includes: the MP part workstation adjusts the angles of multiple camera devices on the second pan-tilt stage and the focal length of the lens in each camera device based on the workpiece number.
[0047] Specifically, before the second gimbal on the MP workstation performs image acquisition, the multiple camera devices on the second gimbal also need to be adjusted; similarly, the multiple camera devices on the second gimbal have two adjustable degrees of freedom, which can ensure that the camera device can be adjusted to the optimal image acquisition angle when acquiring images for different workpieces to be inspected, and has strong compatibility with different workpiece sizes and optimal shooting angles; that is, the MP workstation will adjust the angles of the multiple camera devices on the second gimbal and the focal length of the lens in each camera device according to the workpiece number.
[0048] A workpiece in-place sensor is arranged on the conveyor belt, and real-time detection of workpieces is performed on the conveyor belt through the workpiece in-place sensor. When it is detected that the workpiece to be detected is in place, a workpiece in-place signal is generated; then the workpiece positioning encoder will clear the recorded pulse data and recount according to the workpiece in-place signal to form updated pulse data; finally, when the updated pulse data in the workpiece positioning encoder is consistent with the pulse data triggered by the current workpiece monitoring point, the second pan-tilt head corresponding to the MP workstation is triggered to perform image acquisition processing on the remaining surfaces of the workpiece to be inspected except the front side. The image acquisition processing here is high-speed flying processing, which will not need to occupy the on-site workstation beat, thereby obtaining the second detection image set of the workpiece to be inspected.
[0049] The second defect detection module 25 is used to perform defect detection processing on the workpiece to be detected based on the detection images in the second detection image set to obtain a second defect detection result.
[0050] In the specific implementation process of the present invention, after the second detection image set is collected, the defect detection of the workpiece to be inspected is performed on each detection image in the second detection image set in the same way as the fusion of computer vision algorithm and machine learning algorithm; the final second defect detection result is obtained; at the same time, when there is an abnormality in the second defect detection result, it is necessary to control the corresponding MP part workstation to stop and notify manual intervention; when there is no abnormality in the second defect detection result, the inspection result is visualized and displayed on the designated display screen.
[0051] In an embodiment of the present invention, the empty stage station requires the workpiece number corresponding to the workpiece to be inspected; then, according to the workpiece number, the first pan-tilt control is used to perform image acquisition and processing on the front side of the workpiece to be inspected at the empty stage station to obtain a first detection image set; then, according to the detection image in the first detection image set, defect detection processing is performed on the workpiece to be inspected, and according to the first defect detection result, the robot is controlled to transfer the workpiece to be inspected to the conveyor belt; on the conveyor belt, the second pan-tilt corresponding to the MP station is used to perform image acquisition and processing on the remaining sides of the workpiece to be inspected except the front side to obtain a second detection image set; finally, according to the detection image in the second detection image set, defect detection processing is performed on the workpiece to be inspected to obtain a second defect detection result; process-based defect detection of complex workpieces is realized, and defect detection efficiency is improved; and high-speed flying shooting is adopted at the MP station, so as not to occupy the on-site workstation beat and improve detection efficiency.
[0052] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the detection method of any one of the above embodiments is implemented. The computer-readable storage medium includes, but is not limited to, any type of disk (including floppy disk, hard disk, optical disk, CD-ROM, and magneto-optical disk), ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (EraSable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic card or optical card. That is, the storage device includes any medium that stores or transmits information in a readable form by a device (for example, a computer, a mobile phone), which can be a read-only memory, a disk or an optical disk, etc.
[0053] An embodiment of the present invention further provides a computer application program, which runs on a computer and is used to execute the detection method of any one of the above embodiments.
[0054] also, Figure 3 It is a schematic diagram of the structure of an electronic device in an embodiment of the present invention.
[0055] The embodiment of the present invention further provides an electronic device, such as Figure 3 The electronic device includes a processor 302, a memory 303, an input unit 304, a display unit 305 and other devices. Those skilled in the art will understand that Figure 3The electronic device structure device shown does not constitute a limitation on all devices, and may include more or fewer components than shown, or combine certain components. The memory 303 can be used to store the application 301 and various functional modules, and the processor 302 runs the application 301 stored in the memory 303, thereby executing various functional applications and data processing of the device. The memory can be an internal memory or an external memory, or include both internal and external memories. The internal memory may include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, or a random access memory. The external memory may include a hard disk, a floppy disk, a ZIP disk, a U disk, a magnetic tape, etc. The memory disclosed in the present invention includes but is not limited to these types of memories. The memory disclosed in the present invention is only used as an example and not as a limitation.
[0056] The input unit 304 is used to receive the input of signals and keywords input by the user. The input unit 304 may include a touch panel and other input devices. The touch panel can collect the touch operations of the user on or near it, and drive the corresponding connection device according to a pre-set program; other input devices may include but are not limited to one or more of a physical keyboard, function keys (such as playback control keys, switch keys, etc.), a trackball, a mouse, a joystick, etc. The display unit 305 can be used to display the information input by the user or the information provided to the user and various menus of the terminal device. The display unit 305 can be in the form of a liquid crystal display, an organic light emitting diode, etc. The processor 302 is the control center of the terminal device, which uses various interfaces and lines to connect various parts of the entire device, and executes various functions and processes data by running or executing software programs and / or modules stored in the memory 303, and calling data stored in the memory.
[0057] As an embodiment, the electronic device includes: one or more processors 302, a memory 303, and one or more applications 301, wherein the one or more applications 301 are stored in the memory 303 and are configured to be executed by the one or more processors 302, and the one or more applications 301 are configured to execute the detection method in any one of the above-mentioned embodiments.
[0058] In an embodiment of the present invention, the empty stage station requires the workpiece number corresponding to the workpiece to be inspected; then, according to the workpiece number, the first pan-tilt control is used to perform image acquisition and processing on the front side of the workpiece to be inspected at the empty stage station to obtain a first detection image set; then, according to the detection image in the first detection image set, defect detection processing is performed on the workpiece to be inspected, and according to the first defect detection result, the robot is controlled to transfer the workpiece to be inspected to the conveyor belt; on the conveyor belt, the second pan-tilt corresponding to the MP station is used to perform image acquisition and processing on the remaining sides of the workpiece to be inspected except the front side to obtain a second detection image set; finally, according to the detection image in the second detection image set, defect detection processing is performed on the workpiece to be inspected to obtain a second defect detection result; process-based defect detection of complex workpieces is realized, and defect detection efficiency is improved; and high-speed flying shooting is adopted at the MP station, so as not to occupy the on-site workstation beat and improve detection efficiency.
[0059] In addition, the above is a detailed introduction to a complex workpiece detection method and related devices provided in an embodiment of the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.
Claims
1. A method for detecting complex workpieces, characterized in that: Applied to an empty stage station, a robot and an MP station, the robot is used to transfer the workpiece to be inspected on the empty stage station to the conveyor belt where the MP station is located; the method comprises: The empty stage station receives the ADC workpiece program number, and obtains the workpiece number corresponding to the workpiece to be detected based on the ADC workpiece program number; The first pan-tilt platform on the empty stage station performs image acquisition processing on the front of the workpiece to be inspected placed on the empty stage station based on the workpiece number to obtain a first inspection image set of the workpiece to be inspected, and a plurality of camera devices at different angles are arranged above the first pan-tilt platform; Performing defect detection processing on the workpiece to be inspected based on the inspection images in the first inspection image set, and controlling the robot to transfer the workpiece to be inspected to the conveyor belt according to the first defect detection result; When the workpiece arrival sensor on the conveyor belt senses the workpiece to be detected, the second pan-tilt platform corresponding to the MP part station is triggered to perform image acquisition and processing on the remaining surfaces of the workpiece to be detected except the front surface, so as to obtain a second detection image set of the workpiece to be detected, and a plurality of camera devices with different angles are arranged above and on both sides of the second pan-tilt platform; Based on the detection images in the second detection image set, defect detection processing is performed on the workpiece to be detected to obtain a second defect detection result.
2. The detection method according to claim 1, characterized in that: The empty stage station receives the ADC workpiece program number, and obtains the workpiece number corresponding to the workpiece to be detected based on the ADC workpiece program number, including: The empty stage station receives the ADC workpiece program number based on user input; The empty stage station parses the ADC workpiece program number to obtain the workpiece number of the workpiece to be detected corresponding to the ADC workpiece program number.
3. The detection method according to claim 1, characterized in that: The first pan / tilt stage on the empty stage station performs image acquisition processing on the front side of the workpiece to be inspected placed on the empty stage station based on the workpiece number to obtain a first inspection image set of the workpiece to be inspected, including: The empty stage station adjusts the angles of multiple camera devices arranged on the first pan-tilt head based on the workpiece number to form multiple camera devices with adjusted angles; Based on the workpiece number, focus adjustment processing is performed on lenses in the multiple camera devices after the angles are adjusted to obtain the multiple camera devices adjusted on the first pan / tilt platform; After the workpiece to be inspected enters the empty stage workstation, the multiple camera devices adjusted on the first pan-tilt platform are controlled to perform image acquisition and processing on the front side of the workpiece to be inspected, and the images acquired by the multiple camera devices are placed in a collection to obtain a first inspection image set of the workpiece to be inspected.
4. The detection method according to claim 1, characterized in that: The performing missing detection processing on the workpiece to be detected based on the detection images in the first detection image set includes: The detection images in the first detection image set are subjected to defect detection processing on the workpiece to be detected by utilizing a fusion method of a computer vision algorithm and a machine learning algorithm.
5. The detection method according to claim 1, characterized in that: The controlling the robot to transfer the workpiece to be inspected to the conveyor belt according to the first defect detection result comprises: When there is a defect detection image in the first defect detection result, the empty stage station is controlled to perform abnormal shutdown processing, and the workpiece to be detected on the empty stage station is processed manually; When there is no defect detection image in the first defect detection result, the first defect detection result is visualized and displayed on a designated display screen, and at the same time, the robot is controlled to transfer the workpiece to be inspected to the conveyor belt, with the workpiece to be inspected on the conveyor belt with the reverse side facing up.
6. The detection method according to claim 1, characterized in that: When the workpiece arrival sensor on the conveyor belt senses the workpiece to be detected, the second pan / tilt platform corresponding to the MP part station is triggered to perform image acquisition and processing on the remaining surfaces of the workpiece to be detected except the front surface, so as to obtain a second detection image set of the workpiece to be detected, including: When the workpiece in-place sensor on the conveyor belt detects that the workpiece to be detected is in-place, a workpiece in-place signal is generated; The workpiece positioning encoder clears the recorded pulse data and recounts according to the workpiece in-place signal to form updated pulse data; When the updated pulse data in the workpiece positioning encoder is consistent with the pulse data triggered by the current workpiece monitoring point, the second pan-tilt head corresponding to the MP part workstation is triggered to perform image acquisition and processing on the remaining surfaces of the workpiece to be inspected except the front side, so as to obtain a second detection image set of the workpiece to be inspected.
7. The detection method according to claim 1, characterized in that: Before triggering the second pan / tilt platform corresponding to the MP part station to perform image acquisition processing on the remaining surfaces of the workpiece to be inspected except the front surface, the method further includes: The MP section station adjusts the angles of multiple camera devices on the second pan-tilt head and the focal length of the lens in each camera device based on the workpiece number.
8. A complex workpiece detection device, characterized in that: Applicable to an empty stage station, a robot and an MP station, the robot is used to transfer the workpiece to be inspected on the empty stage station to the conveyor belt where the MP station is located; the device includes: An acquisition module: used for the empty stage station to receive the ADC workpiece program number, and to obtain the workpiece number corresponding to the workpiece to be detected based on the ADC workpiece program number; A first image acquisition module: a first pan-tilt platform on the empty stage station is used to perform image acquisition processing on the front of the workpiece to be inspected placed on the empty stage station based on the workpiece number to obtain a first inspection image set of the workpiece to be inspected, wherein a plurality of camera devices at different angles are arranged above the first pan-tilt platform; A first defect detection module: used for performing defect detection processing on the workpiece to be detected based on the detection images in the first detection image set, and controlling the robot to transfer the workpiece to be detected to the conveyor belt according to the first defect detection result; The second image acquisition module is used to trigger the second pan-tilt platform corresponding to the MP part station to perform image acquisition processing on the remaining surfaces of the workpiece to be detected except the front surface when the workpiece arrival sensor on the conveyor belt senses the workpiece to be detected, so as to obtain a second detection image set of the workpiece to be detected. A plurality of camera devices with different angles are arranged above and on both sides of the second pan-tilt platform; The second defect detection module is used to perform defect detection processing on the workpiece to be detected based on the detection images in the second detection image set to obtain a second defect detection result.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the detection method as described in any one of claims 1 to 7 is implemented.
10. An electronic device, characterized in that: The electronic device comprises: one or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to: execute the detection method according to any one of claims 1 to 7.
Citation Information
Patent Citations
Workpiece three-dimensional defect detection method, device and system and storage medium
CN115713479A
Visual inspection system, control method and device thereof and storage medium
CN118425045A
Visual quality inspection method and device of workpiece, visual quality inspection equipment, system and medium
CN118671073A
Lithium battery appearance defect detection system based on machine vision
CN216622191U
Workpiece appearance defect detection equipment
CN218331189U
Cited By
Method for detecting colloid integrity in 3D gluing and related device
CN119722583A
A method and related device for detecting colloid integrity in 3D coating
CN119722583B
