A machine vision-based hose defect detection apparatus

Abstract

The application provides a kind of rubber pipe defect detection equipment based on machine vision, comprising: image acquisition device, clamping device and control device;Image acquisition device includes: drive part and image acquisition part, drive part is connected with image acquisition part, for controlling the distance between the position of image acquisition part and different size rubber pipe constant;Clamping device includes transverse guide roller adjusting mechanism, longitudinal guide roller adjusting mechanism and multiple guide rollers;Guide roller is used to clamp rubber pipe;Transverse guide roller adjusting mechanism and longitudinal guide roller adjusting mechanism are connected with guide roller, for controlling the distance between guide roller, clamping different size rubber pipe, while controlling the movement of rubber pipe.The application realizes the accurate capture of rubber pipe image information through image acquisition device, controls the position of rubber pipe through clamping device, realizes self-adaptive clamping, accurate positioning and continuous movement of rubber pipe, and improves detection accuracy.

Description

Technical Field

[0001] This application relates to the field of hose manufacturing technology, and more specifically, to a hose defect detection device based on machine vision. Background Technology

[0002] During the production of rubber hoses, instability in the manufacturing process can lead to defects such as deformation, dead material, foreign objects, wrinkles, joint defects, and printing defects. These defects not only affect the aesthetics of the hoses but also their safety and durability. The various defects in rubber hoses have created a huge market demand for defect detection. Manual inspection is greatly affected by subjective factors and suffers from drawbacks such as slow speed, high cost, and low accuracy. Studies show that manual inspection can only detect about 85% of defects, with a detection speed not exceeding 15m / min, and visual fatigue easily leads to missed or false detections. To reduce costs and improve productivity, companies urgently need automated hose inspection equipment based on machine vision.

[0003] Chinese patent CN 215572692U describes a machine vision-based device for inspecting the appearance of cooling pipes. However, it cannot automatically adjust the camera's shooting distance based on the outer diameter of the cooling pipe. In practical use, it can only simultaneously capture images of the cooling pipe from three directions.

[0004] It can be seen that the main drawbacks of the existing computer vision image processing and analysis technology for classifying and identifying rubber tubes are: (1) the camera position needs to be adjusted manually frequently, which is difficult to adapt to industrial production scenarios; (2) there are few shooting angles, which cannot detect defects at various angles of the rubber tube. Summary of the Invention

[0005] In view of one of the defects in the prior art, the purpose of this application is to provide a hose defect detection device based on machine vision.

[0006] A first aspect of this application provides a machine vision-based hose defect detection device, comprising: An image acquisition device for acquiring images of rubber hoses includes a driving unit and an image acquisition unit. The driving unit is connected to the image acquisition unit. Under the drive of the driving unit, the image acquisition unit always maintains the same set shooting distance with rubber hoses of different models. A clamping device adapted to different hoses is provided for clamping the hoses and allowing the hoses to move while clamped, and works in conjunction with the image acquisition device to acquire images of the hoses; the clamping device includes a guide roller adjustment mechanism and multiple guide rollers, the guide rollers being used to clamp the hoses; the guide roller adjustment mechanism is connected to the guide rollers and adjusts the lateral and / or longitudinal distance between adjacent guide rollers to accommodate different hoses.

[0007] Optionally, the image acquisition device further includes a fixing part for supporting the image acquisition device and the clamping device; The fixing part includes a support plate and a fixing seat, the fixing seat is connected to the support plate, and the support plate is fixed at the detection position by the fixing seat; The image acquisition device and the clamping device are mounted on the support plate.

[0008] Optionally, the image acquisition unit includes: a cylindrical light source, a camera, and a lens; One end of the columnar light source is fixed on the support plate, and the lens is mounted on the camera and is evenly spaced around the circumference of the columnar light source. The cylindrical light source has a placement hole at its center, through which the tube passes. The tube can be photographed through the placement hole by the lens and the camera, capturing image information of the tube from multiple directions.

[0009] Optionally, the cylindrical light source has a plurality of detection holes on its peripheral wall, which are evenly spaced around the peripheral wall of the cylindrical light source. The inner wall of the columnar light source is coated with a white coating to reflect internal light. The lens can be inserted into the detection hole to take pictures of the tubing, and the number of the lens and the camera is the same as the number of detection holes.

[0010] Optionally, the drive unit is movably disposed on the support plate; The drive unit includes a servo module, a scale, and a scale indicator; The scale is mounted on the support plate, and the scale value indicator is movable on the scale to adjust the position of the servo module during installation. The servo module is fixed on the support plate, the camera is mounted on the servo module, and the servo module controls the position of the camera; The number of the servo module, the scale, the scale indicator, and the camera are the same.

[0011] Optionally, the drive unit further includes a fixing plate and a transition plate; The camera is mounted on the fixed plate, the fixed plate is connected to the transition plate, and the transition plate is mounted on the servo module; When the position of the camera needs to be changed, the servo module drives the transition plate to move, and the transition plate drives the camera to move, adjusting the position of the camera so that the shooting distance between the camera and the lens and the tube is constant.

[0012] Optionally, the shooting distance between the camera and the lens can be adjusted within 100-400mm depending on the outer diameter of the tubing.

[0013] Optionally, the clamping device further includes a base plate, and the guide roller adjustment mechanism includes a transverse guide roller adjustment mechanism and a longitudinal guide roller adjustment mechanism, which are disposed on the base plate; The plurality of guide rollers include multiple sets of transverse guide rollers and longitudinal guide rollers arranged along the length of the hose. The transverse guide rollers are connected to the transverse guide roller adjustment mechanism, and the longitudinal guide rollers are connected to the longitudinal guide roller adjustment mechanism. In each set of transverse guide rollers and longitudinal guide rollers, there are two transverse guide rollers and two longitudinal guide rollers. The transverse guide roller adjustment mechanism adjusts the distance between the two transverse guide rollers, and the longitudinal guide roller adjustment mechanism adjusts the distance between the two longitudinal guide rollers. The space formed between the two transverse guide rollers and the two longitudinal guide rollers is used to clamp the rubber tube.

[0014] Optionally, the transverse guide roller adjustment mechanism includes a transverse servo motor, and the longitudinal guide roller adjustment mechanism includes a longitudinal servo motor; The transverse servo motor drives the transverse guide roller to move, and the longitudinal servo motor controls the longitudinal guide roller to move.

[0015] Optionally, it also includes a control device, which is connected to the image acquisition device; The control device includes a model acquisition mechanism and a detection mechanism; The model acquisition mechanism is connected to the image acquisition device and the clamping device respectively, and is used to acquire the model of the hose and adjust the position of the image acquisition unit and the position of the guide roller according to the model of the hose. The detection mechanism is connected to the image acquisition device and is used to detect defects in the rubber tube in the image information acquired by the image acquisition device.

[0016] This application provides a machine vision-based hose defect detection device, which combines a machine vision-based image acquisition device and a clamping device. Through an adjustable drive unit maintaining a constant distance between the image acquisition unit and hoses of different sizes, it achieves precise capture of hose image information. The clamping device, a transverse guide roller adjustment mechanism, a longitudinal guide roller adjustment mechanism, and multiple guide rollers control the hose's position, size adaptation, and movement. This allows for adaptation to hoses of different sizes, achieving self-adaptive clamping, precise positioning, and continuous movement. This improves detection accuracy, adaptability to different hose models, and overall production efficiency, while reducing reliance on manual labor and detection costs.

[0017] Other technical effects resulting from the additional features will be further illustrated in the corresponding embodiments. Attached Figure Description

[0018] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is an assembly structure diagram of a machine vision-based hose defect detection device according to an exemplary embodiment; Figure 2 This is a structural diagram of an image acquisition device for a machine vision-based hose defect detection equipment, according to an exemplary embodiment. Figure 3 This is a structural diagram of a clamping device for a machine vision-based hose defect detection device, according to an exemplary embodiment. Figure 4 This is a structural diagram of a transverse guide roller mechanism according to an exemplary embodiment; Figure 5 This is a structural diagram of a longitudinal guide roller mechanism according to an exemplary embodiment.

[0019] In the diagram: 1. Support plate; 2. Fixing base; 3. Servo module; 4. Columnar light source; 5. Fixing plate; 6. Transition plate; 7. Camera; 8. Lens; 9. Scale; 10. Scale indicator; 11. Base plate; 12. Transverse guide roller adjustment mechanism; 13. Longitudinal guide roller adjustment mechanism; 14. Guide roller; 15. Transverse servo motor; 16. Longitudinal servo motor; 17. First reducer; 18. First coupling; 19. First bearing; 20. Second reducer; 21. Second coupling; 22. Second bearing; 100. Image acquisition device; 101. Drive unit; 102. Image acquisition unit; 103. Fixing unit; 200. Clamping device; 201. Guide roller adjustment mechanism; 202. Transverse guide roller; 203. Longitudinal guide roller; 300. Placement hole; 400. Detection hole; 500. Control device. Detailed Implementation

[0020] The present application will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present application, but do not limit the present application in any way. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application, and these all fall within the protection scope of the present application. Parts not described in detail in the following embodiments can be implemented using existing technology.

[0021] In the description of the embodiments of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0022] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature.

[0023] In the description of the embodiments in this application, "multiple" means two or more, unless otherwise explicitly specified. In this application, unless otherwise explicitly specified and limited, the terms "installed," "connected," "linked," "fixed," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0024] The terms "comprising" and "having," and any variations thereof, in the embodiments of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such processes, methods, products, or devices.

[0025] In existing technologies, the method of classifying and identifying rubber hoses using computer vision image processing and analysis technology requires frequent manual adjustment of the camera position, making it difficult to adapt to industrial production scenarios; the limited shooting angles also prevent the detection of defects at various angles of the rubber hose. To address these issues, this application provides a machine vision-based rubber hose defect detection device to solve these problems.

[0026] Reference Figure 1 As shown in one embodiment of this application, a machine vision-based hose defect detection device includes: an image acquisition device 100 for acquiring images of hoses 600 and a clamping device 200 adapted to different hoses 600.

[0027] The image acquisition device 100 includes a driving unit 101 and an image acquisition unit 102. The driving unit 101 is connected to the image acquisition unit 102. Under the drive of the driving unit 101, the image acquisition unit 102 always maintains the same set shooting distance with different types of tubing 600. The clamping device 200 is used to clamp the hose 600, and the hose 600 can move in the clamped state. It works with the image acquisition device 100 to realize image acquisition of the hose 600. The clamping device 200 includes a guide roller adjustment mechanism 201 and a plurality of guide rollers 14. The guide rollers 14 are used to clamp the hose 600. The guide roller adjustment mechanism 201 is connected to the guide rollers 14 and adjusts the lateral and / or longitudinal distance between adjacent guide rollers 14 to accommodate different hoses 600.

[0028] Specifically, in the operation of the machine vision-based hose defect detection equipment, the drive unit 101 of the image acquisition device 100 first adjusts the position of the image acquisition unit 102 according to the different sizes of hoses 600, ensuring a constant distance between it and the hose 600. Then, the image acquisition unit 102 takes pictures of the hose 600 to acquire image information. Simultaneously, the guide roller adjustment mechanism 201 of the clamping device 200 operates, controlling the distance between the multiple guide rollers 14 connected to it to clamp hoses 600 of different sizes and control the movement of the hoses 600 during the detection process. Finally, during detection, the control device 500 on the detection equipment cooperates with the image acquisition device 100 to receive the acquired image information and perform defect detection on the hose 600 accordingly.

[0029] Among them, the multiple guide rollers 14 move symmetrically according to the center of the light source. Regardless of the outer diameter of the different models of rubber tubes 600, the center point of the guide rollers 14 is always at the center of the light source of the image acquisition unit 102.

[0030] In the above embodiments of this application, the driving unit 101 in the image acquisition device 100 ensures a constant distance between the image acquisition unit 102 and the hose 600, thereby achieving stable and clear image quality and avoiding the impact of image problems on the detection results. The guide roller adjustment mechanism 201 of the clamping device 200 can flexibly adapt to hoses 600 of different sizes, precisely control their position and movement, and improve the comprehensiveness and accuracy of the detection. It realizes an automated detection process, improves detection efficiency, reduces manual labor intensity and human error, and enhances the quality and reliability of hose 600 defect detection.

[0031] In some specific embodiments of this application, the image acquisition device 100 also includes a fixing part 103 for supporting the image acquisition device 100 and the clamping device 200.

[0032] The fixing part 103 includes a support plate 1 and a fixing seat 2. The fixing seat 2 is connected to the support plate 1, and the support plate 1 is fixed at the detection position by the fixing seat 2. The image acquisition device 100 and the clamping device 200 are disposed on the support plate 1.

[0033] In the above embodiments of this application, a fixing part 103 structure is constructed for the image acquisition device 100. First, the fixing base 2 is stably connected to the support plate 1. The support plate 1 is precisely fixed at the detection position by the fixing base 2. Then, the image acquisition device 100 and the clamping device 200 are orderly arranged and installed on the support plate 1 to realize the support and positioning of the image acquisition device 100 and the clamping device 200, reduce the acquisition error caused by device shaking or position displacement, and improve the quality and accuracy of image acquisition.

[0034] In some specific embodiments of this application, the image acquisition unit 102 includes: a columnar light source 4, a camera 7, and a lens 8.

[0035] One end of the columnar light source 4 is fixed on the support plate 1, and the lens 8 is mounted on the camera 7 and is evenly spaced around the circumference of the columnar light source 4.

[0036] The cylindrical light source 4 has a placement hole 300 through its center. The tube 600 can pass through the placement hole 300 and be photographed by the lens 8 and camera 7 to collect image information of the tube 600 from multiple directions.

[0037] It should be noted that the placement hole 300 is 55mm in size, and tubing 600 smaller than 40mm can be inserted. The size of the placement hole 300 in this application can be changed according to the size of the tubing 600, and is not limited to a fixed size.

[0038] Specifically, when constructing the image acquisition unit 102, one end of the cylindrical light source 4 is first securely fixed to the wall. Next, the lens 8 is mounted on the camera 7, and the camera 7 with the lens 8 mounted is arranged around the circumference of the cylindrical light source 4 at even intervals. Then, a placement hole 300 is set in the center of the cylindrical light source 4, allowing the tube 600 to pass smoothly through the placement hole 300. Then, the lens 8 and camera 7 are used to take pictures of the tube 600 inside the cylindrical light source 4, acquiring image information of the tube 600 from multiple directions.

[0039] In the above embodiments of this application, by fixing one end of the columnar light source 4 to the wall, stable information acquisition is achieved; the lens 8 is evenly spaced around the columnar light source 4 to observe the tube 600 from multiple angles. With the placement hole 300 on the other end face of the columnar light source 4, the tube 600 is accurately placed in a position that can be photographed from multiple angles, so that the camera 7 and the lens 8 can comprehensively acquire image information of the tube 600 from multiple directions, improving the integrity and accuracy of image acquisition.

[0040] In some specific embodiments of this application, a plurality of detection holes 400 are provided on the peripheral wall of the columnar light source 4, which are evenly spaced around the peripheral wall of the columnar light source 4; the inner wall of the columnar light source 4 is coated with a white coating for reflecting internal light.

[0041] Among them, the lens 8 can be inserted into the detection hole 400 to take pictures of the tube 600, and the number of lenses 8 and cameras 7 is the same as the number of detection holes 400.

[0042] It should be noted that there are 9 detection holes 400. In this application, if there is an even number of cameras 7, the alignment camera 7 will be captured. If there are fewer than 9 cameras 7, some defects will not be captured clearly from a certain angle. If there are too many cameras 7, the system processing speed will be slow and computing resources will be wasted. In practice, 9 cameras 7 is the optimal number.

[0043] In the above embodiments of this application, multiple (a total of 9) detection holes 400 are evenly spaced on the periphery of the columnar light source 4 to achieve the integrity and accuracy of image acquisition; while the white coating on the inner wall can effectively reflect the internal light, enhance the uniformity of the light source inside the columnar light source 4, make the surface of the tube 600 more evenly illuminated, reduce the shooting error caused by uneven light, further improve the quality of the acquired image, and ensure the accuracy and reliability of the detection.

[0044] In some specific embodiments of this application, the drive unit 101 is movably mounted on the support plate 1. The drive unit 101 includes a servo module 3, a scale 9, and a scale indicator 10.

[0045] A scale 9 is mounted on the support plate 1, and a scale indicator 10 is movable on the scale 9 for adjusting the position of the servo module 3 during installation. The servo module 3 is fixed on the support plate 1, and the camera 7 is mounted on the servo module 3. The servo module 3 controls the position of the camera 7.

[0046] The number of servo modules 3, scales 9, and scale indicators 10 is the same as that of cameras 7.

[0047] Specifically, the scale 9 is first fixedly installed on the support plate 1, and then the scale indicator 10 is installed on the scale 9, allowing the scale indicator 10 to move flexibly on the scale 9. At the same time, when installing the servo module 3, the installation position of the servo module 3 on the support plate 1 is adjusted according to the position information of the scale indicator 10 on the scale 9. Meanwhile, the camera 7 is installed on the servo module 3. Since the number of servo modules 3, scale 9, scale indicator 10 and camera 7 is the same, each servo module 3 corresponds to one camera 7, one set of scale 9 and scale indicator 10, and the position of the corresponding camera 7 is precisely controlled by the servo module 3.

[0048] In the above embodiments of this application, the scale 9 cooperates with the movable scale indicator 10 to provide a precise position reference for adjusting the installation position of the servo module 3, so that the servo module 3 can be installed in a suitable position and the accuracy of the initial position of the camera 7 can be guaranteed. The servo module 3 can control the position of the camera 7. Combined with the matching setting of the number, each camera 7 can move independently and accurately under the drive of the corresponding servo module 3, meet the needs of different shooting positions, improve the flexibility and accuracy of image acquisition, and improve the performance and reliability of the entire system.

[0049] In some specific embodiments of this application, the drive unit 101 also includes a fixing plate 5 and a transition plate 6.

[0050] Camera 7 is mounted on fixed plate 5, which is connected to transition plate 6. Transition plate 6 is mounted on servo module 3.

[0051] When the position of camera 7 needs to be changed, servo module 3 drives transition plate 6 to move, transition plate 6 drives camera 7 to move, adjusts the position of camera 7, and keeps the shooting distance between camera 7, lens 8 and tube 600 constant.

[0052] In the above embodiments of this application, by setting a fixed plate 5 and a transition plate 6, the camera 7 is indirectly connected to the servo module 3. When there is a need to adjust the position of the camera 7 in actual use, the servo module 3 starts to operate and drives the transition plate 6 to move. Since the fixed plate 5 is connected to the transition plate 6, the transition plate 6 will drive the camera 7 on the fixed plate 5 to move together, thereby adjusting the position of the camera 7, making the adjustment of the position of the camera 7 more flexible and stable. The servo module 3 drives the transition plate 6 to move the camera 7, which can accurately control the displacement of the camera 7, ensure that the shooting distance between the camera 7 and the lens 8 and the tube 600 is constant, avoid image blurring and distortion caused by distance changes, and improve the quality and consistency of image acquisition.

[0053] In some specific embodiments of this application, the shooting distance between the camera 7 and the lens 8 is adjusted within 100-400mm depending on the outer diameter of the tubing 600.

[0054] In some specific embodiments of this application, the clamping device 200 further includes a base plate 11, and the guide roller adjustment mechanism 201 includes a transverse guide roller adjustment mechanism 12 and a longitudinal guide roller adjustment mechanism 13, which are disposed on the base plate 11; the plurality of guide rollers 14 include a plurality of transverse guide rollers 202 and longitudinal guide rollers 203 disposed along the length direction of the hose 600.

[0055] The transverse guide roller 202 is connected to the transverse guide roller adjustment mechanism 12, and the distance of the transverse guide roller 202 is adjusted by the transverse guide roller adjustment mechanism 12; the longitudinal guide roller 203 is connected to the longitudinal guide roller adjustment mechanism 13, and the distance of the longitudinal guide roller adjustment mechanism 13 is adjusted by the longitudinal guide roller adjustment mechanism 13.

[0056] In each set of transverse guide rollers 202 and longitudinal guide rollers 203, there are two transverse guide rollers 202 and two longitudinal guide rollers 203; the transverse guide roller adjustment mechanism 12 adjusts the distance between the two transverse guide rollers 202; the longitudinal guide roller adjustment mechanism 13 adjusts the distance between the two longitudinal guide rollers 203, and the space formed between the two transverse guide rollers 202 and the two longitudinal guide rollers 203 is used to clamp the rubber tube 600.

[0057] It should be noted that the transverse guide roller 202 and the longitudinal guide roller 203 are divided into two sections. The threads of the transverse guide roller 202 and the longitudinal guide roller 203 are opposite, so adjacent guide rollers 14 move symmetrically regardless of rotation. Example of movement: The initial position of guide roller 14 is 0mm. The center point of the two sets of guide rollers 14 is at the center of the light source. The system receives a signal: the outer diameter of the hose 600 is 30mm, and each guide roller 14 is offset outward by 15mm. A square space with a side length of 30mm is left, i.e., the clamping part, for clamping hoses 600 of different sizes.

[0058] In the above embodiments of this application, the clamping device 200 uses a base plate 11 as a support, on which a transverse guide roller adjustment mechanism 12 and a longitudinal guide roller adjustment mechanism 13 are provided. Multiple sets of guide rollers are arranged along the length of the hose 600, each set including two transverse guide rollers 202 and two longitudinal guide rollers 203. The transverse guide rollers 202 are connected to the transverse guide roller adjustment mechanism 12, and the longitudinal guide rollers 203 are connected to the longitudinal guide roller adjustment mechanism 13. These two adjustment mechanisms can adjust the distance between the two transverse guide rollers 202 and the two longitudinal guide rollers 203 within the same set, thereby clamping the hose 600 using the space enclosed by the two transverse guide rollers 202 and the two longitudinal guide rollers 203. The guide roller spacing can be flexibly adjusted according to different sizes of hoses 600, increasing adaptability to different hose sizes. Combined with a multi-directional stable clamping method, it avoids the hose 600 from shifting or swaying during movement, improving stability and reliability, thus achieving stable clamping of hoses 600 of different specifications.

[0059] In some specific embodiments of this application, the transverse guide roller adjustment mechanism 12 includes a transverse servo motor 15, and the longitudinal guide roller adjustment mechanism 13 includes a longitudinal servo motor 16; the transverse servo motor 15 drives the transverse guide roller 202 to move, and the longitudinal servo motor 16 controls the longitudinal guide roller 203 to move.

[0060] Specifically, the support plate 1 is provided with a fixing base 2 to fix the support plate 1. The servo module 3 and the columnar light source 4 are fixed on the support plate 1. The camera 7 and its lens 8 are combined together by the fixing plate 5 and the fixing transition plate 6. The scale 9 and the scale indicator 10 are used for debugging the servo module 3 during the installation process.

[0061] Reference Figure 3 As shown, there is a base plate 11 and a transverse guide roller adjustment mechanism 12 and a longitudinal guide roller adjustment mechanism 13 fixed on the base plate 11. The transverse guide roller adjustment mechanism 12 and the longitudinal guide roller adjustment mechanism 13 are driven by a transverse servo motor 15 and a longitudinal servo motor 16 to adjust the distance between the guide rollers 14.

[0062] Reference Figure 4 As shown, the transverse guide roller adjustment mechanism 12 also includes a first reducer 17, a first coupling 18, and a first bearing 19; the output end of the transverse servo motor 15 is connected to the first reducer 17, the output end of the first reducer 17 is connected to the first coupling 18, and there is a connecting rod between the first reducer 15 and the first bearing 19 for mounting the transverse guide roller 202, and the transverse guide roller 202 is moved by rotating the connecting rod.

[0063] Reference Figure 5 As shown, the longitudinal guide roller adjustment mechanism 13 also includes a second reducer 20, a second coupling 21, and a second bearing 22; the output end of the longitudinal servo motor 16 is connected to the second reducer 20, the output end of the second reducer 20 is connected to the second coupling 21, and there is a connecting rod between the longitudinal guide roller 203 and the second bearing 22, which drives the longitudinal guide roller 203 to move by rotating the connecting rod.

[0064] In some specific embodiments of this application, the detection device further includes a control device 500, which is connected to the image acquisition device 100 and the clamping device 200. The control device 500 includes a model acquisition mechanism and a detection mechanism.

[0065] The model acquisition mechanism is connected to the image acquisition device 100 and the clamping device 200 respectively, and is used to acquire the model of the hose 600. The position of the image acquisition unit 102 and the position of the guide roller are adjusted according to the model of the hose 600. The detection mechanism is connected to the image acquisition device 100 and is used to detect defects in the hose 600 in the image information acquired by the image acquisition device 100.

[0066] In this embodiment, the model acquisition mechanism obtains the model information of the hose 600. The control device 500, using this model information, sends signals to the servo module 3 and the guide roller adjustment mechanism 201. The servo module 3 adjusts the position of the camera 7 based on the outer diameter of the hose 600 in the signal, maintaining a constant shooting distance. The guide roller adjustment mechanism 201 drives the transverse guide roller adjustment mechanism 12 and the longitudinal guide roller adjustment mechanism 13 via the transverse servo motor 15 and the longitudinal servo motor 16, ensuring that the spacing between the guide rollers 14 is slightly larger than the outer diameter of the hose 600.

[0067] During the operation of the testing device, the hose 600 passes through the placement hole 300 in the center of the cylindrical light source 4 and is pulled by the winding machine at the end of the production line. The cylindrical light source 4 flashes, and the camera 7 takes a picture of the hose 600. The control device 500 stores the correspondence between the hose 600 model number and the hose 600 outer diameter. The model number can be obtained by scanning the QR code on the hose 600 label or by manually entering the hose 600 model number. Camera 7 is mounted on servo module 3. Servo module 3 receives the model information of hose 600 and adjusts the shooting distance of camera 7 according to the hose 600 model. Simultaneously, clamping device 200 receives the hose 600 model information. Guide roller 14 is mounted on guide roller adjustment mechanism 201. Clamping device 200 is controlled by a PLC. Based on the hose 600 model information, the PLC receives a movement signal from guide roller adjustment mechanism 201 and adjusts guide roller 14 to control the position of hose 600. The movement distance of guide roller 14 is the change in hose 600 radius: r2 - r1. r1 is the radius of hose 600 detected in the previous test, and r2 is the current radius of hose 600, thus automatically adjusting the shooting distance and hose 600 position. When the detection system detects a defect in hose 600 in the image, it sends a stop signal to the traction machine. The specific method for detecting hose 600 defects uses existing technology and is not an innovation of this application.

[0068] The preferred features in the above embodiments can be used individually in any embodiment, or in any combination thereof, provided they do not conflict with each other. Furthermore, parts not described in detail in the embodiments can be implemented using existing technologies.

[0069] The foregoing has described some specific embodiments of this application. It should be understood that this application is not limited to the specific embodiments described above, and those skilled in the art can make various modifications or variations within the scope of the claims, which do not affect the substantive content of this application. The above-described preferred features can be used in any combination without conflict.

Claims

1. A machine vision-based hose defect detection device, characterized in that, include: An image acquisition device for acquiring images of rubber hoses includes a driving unit and an image acquisition unit. The driving unit is connected to the image acquisition unit. Under the drive of the driving unit, the image acquisition unit always maintains the same set shooting distance with rubber hoses of different models. A clamping device adapted to different hoses is provided for clamping the hoses and allowing the hoses to move while clamped, and works in conjunction with the image acquisition device to acquire images of the hoses; the clamping device includes a guide roller adjustment mechanism and multiple guide rollers, the guide rollers being used to clamp the hoses; the guide roller adjustment mechanism is connected to the guide rollers and adjusts the lateral and / or longitudinal distance between adjacent guide rollers to accommodate different hoses.

2. The machine vision-based hose defect detection device according to claim 1, characterized in that, The image acquisition device also includes a fixing part for supporting the image acquisition device and the clamping device; The fixing part includes a support plate and a fixing seat, the fixing seat is connected to the support plate, and the support plate is fixed at the detection position by the fixing seat; The image acquisition device and the clamping device are mounted on the support plate.

3. The machine vision-based hose defect detection device according to claim 2, characterized in that, The image acquisition unit includes: a cylindrical light source, a camera, and a lens; One end of the columnar light source is fixed on the support plate, and the lens is mounted on the camera and is evenly spaced around the circumference of the columnar light source. The cylindrical light source has a placement hole at its center, through which the tube passes. The tube can be photographed through the placement hole by the lens and the camera, capturing image information of the tube from multiple directions.

4. The machine vision-based hose defect detection device according to claim 3, characterized in that, The cylindrical light source has multiple detection holes on its peripheral wall, which are evenly spaced around the peripheral wall of the cylindrical light source. The inner wall of the columnar light source is coated with a white coating to reflect internal light. The lens can be inserted into the detection hole to take pictures of the tubing, and the number of the lens and the camera is the same as the number of detection holes.

5. The machine vision-based hose defect detection device according to claim 3, characterized in that, The drive unit is movably mounted on the support plate; The drive unit includes a servo module, a scale, and a scale indicator; The scale is mounted on the support plate, and the scale indicator is movable on the scale to adjust the position of the servo module during installation. The servo module is fixed on the support plate, the camera is mounted on the servo module, and the servo module controls the position of the camera; The number of the servo module, the scale, the scale indicator, and the camera are the same.

6. The machine vision-based hose defect detection device according to claim 5, characterized in that, The drive unit also includes a fixing plate and a transition plate; The camera is mounted on the fixed plate, the fixed plate is connected to the transition plate, and the transition plate is mounted on the servo module; When the position of the camera needs to be changed, the servo module drives the transition plate to move, and the transition plate drives the camera to move, adjusting the position of the camera so that the shooting distance between the camera and the lens and the tube is constant.

7. The machine vision-based hose defect detection device according to claim 6, characterized in that, The shooting distance of the camera and the lens is adjusted within 100-400mm depending on the outer diameter of the tubing.

8. The machine vision-based hose defect detection device according to claim 1, characterized in that, The clamping device also includes a base plate, and the guide roller adjustment mechanism includes a transverse guide roller adjustment mechanism and a longitudinal guide roller adjustment mechanism, which are disposed on the base plate; The plurality of guide rollers include multiple sets of transverse guide rollers and longitudinal guide rollers arranged along the length of the hose. The transverse guide rollers are connected to the transverse guide roller adjustment mechanism, and the longitudinal guide rollers are connected to the longitudinal guide roller adjustment mechanism. In each set of transverse guide rollers and longitudinal guide rollers, there are two transverse guide rollers and two longitudinal guide rollers. The transverse guide roller adjustment mechanism adjusts the distance between the two transverse guide rollers, and the longitudinal guide roller adjustment mechanism adjusts the distance between the two longitudinal guide rollers. The space formed between the two transverse guide rollers and the two longitudinal guide rollers is used to clamp the rubber tube.

9. A machine vision-based hose defect detection device according to claim 8, characterized in that, The transverse guide roller adjustment mechanism includes a transverse servo motor, and the longitudinal guide roller adjustment mechanism includes a longitudinal servo motor; The transverse servo motor drives the transverse guide roller to move, and the longitudinal servo motor controls the longitudinal guide roller to move.

10. A machine vision-based hose defect detection device according to claim 1, characterized in that, It also includes a control device, which is connected to the image acquisition device and the clamping device; The control device includes a model acquisition mechanism and a detection mechanism; The model acquisition mechanism is connected to the image acquisition device and the clamping device respectively, and is used to acquire the model of the hose and adjust the position of the image acquisition unit and the position of the guide roller according to the model of the hose. The detection mechanism is connected to the image acquisition device and is used to detect defects in the rubber tube in the image information acquired by the image acquisition device.

Images