Bearing outer ring surface defect detection device based on machine vision

Through the machine vision-based surface defect detection device of the outer ring of bearing, dynamic rotation and fluorescence enhancement technology, combined with image processing algorithms, efficient and accurate detection of surface defects of the outer ring of bearing is achieved, and the problems of low detection efficiency and poor accuracy in the prior art are solved.

CN223284142UActive Publication Date: 2025-08-29LUOYANG NORMAL UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202422483957.8
Authority / Receiving Office
CN · China
Patent Type
Utility models(China)
Current Assignee / Owner
Filing Date
2024-10-14
Publication Date
2025-08-29
Estimated Expiration
2034-10-14

AI Technical Summary

Technical Problem

The prior art is difficult to efficiently and accurately detect tiny defects on the outer ring surface of the bearing, affecting the performance and service life of the bearing.

Method used

The surface defect detection device of the bearing outer ring based on machine vision is adopted. Through the dynamic rotating bearing outer ring combined with all-round, multi-angle high-definition camera and fluorescence enhancement technology, the camera and magnetized electrodes are used for image capture and analysis, and defect recognition is carried out in combination with image processing algorithms.

Benefits of technology

It realizes accurate capture of subtle defects on the surface and interior of the bearing outer ring, improves the comprehensiveness and accuracy of the inspection, reduces manual intervention and misjudgment, and ensures the non-destructive and efficient detection process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN223284142U_ABST
    Figure CN223284142U_ABST
Patent Text Reader

Abstract

The utility model belongs to the technical field of bearing all-dimensional defect detection, and particularly relates to a bearing outer ring surface defect flaw detection device based on machine vision, which comprises a bearing table, and a driving mechanism for driving a bearing outer ring to rotate is arranged on the bearing table. A plurality of cameras used for shooting images, videos and pictures of the surface of the bearing outer ring are mounted on the bearing table; the bearing outer ring can be driven by the driving mechanism to rotate, all parts of the bearing outer ring can be fully displayed in the rotating process of the bearing outer ring, a plurality of cameras can conveniently shoot image videos and pictures of the surface of the bearing outer ring from a plurality of angles, bearing outer ring detection images are obtained, detection equipment can observe and analyze the images, and the detection efficiency is improved. The possibility of missing detection and misjudgment can be reduced, the manual work intensity of bearing defect detection can be reduced, and the detection efficiency can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The utility model belongs to the technical field of all-round defect detection of bearings, and in particular relates to a device for detecting surface defects of a bearing outer ring based on machine vision. Background Art

[0002] A bearing is a mechanical component primarily used to support a rotating object and reduce friction during its motion, thereby ensuring smooth and precise rotation. It typically consists of inner and outer rings, rolling elements (such as balls and rollers), and a cage. The inner and outer rings are fixed to the rotating component and the supporting element, respectively, while the rolling elements are located between the inner and outer rings, reducing friction and energy loss through rolling.

[0003] During the bearing production process, due to various factors, the outer cylindrical surface and end faces of the bearing may suffer localized physical damage such as scratches and wear, resulting in uneven surface physical properties. These surface defects, such as plaques, scratches, and rust, not only affect the bearing's appearance but can also adversely affect its performance and service life.

[0004] With the continuous advancement of science and technology and the rapid development of industry, bearing inspection technology is also constantly innovating and improving. In the future, bearing inspection technology will develop in the direction of intelligence and automation. By introducing online real-time inspection technology, intelligent inspection technology, non-destructive testing technology, and multi-sensor fusion inspection methods, comprehensive and accurate inspection of bearing surface quality can be achieved. This will help improve product quality, reduce production costs, and enhance the economic benefits of enterprises. Utility Model Content

[0005] The purpose of this utility model is to provide a bearing outer ring surface defect detection device based on machine vision, which uses a camera to capture images, videos and pictures of the bearing outer ring surface for defect identification, helping to reduce the manual labor intensity of bearing defect detection and improve detection efficiency.

[0006] The utility model is achieved through the following technical solutions:

[0007] A device for detecting surface defects of a bearing outer ring based on machine vision comprises a carrier platform, on which a driving mechanism for driving the bearing outer ring to rotate is provided, and on which a plurality of cameras for capturing videos and pictures of the surface of the bearing outer ring are installed. The driving mechanism can drive the bearing outer ring to rotate, and during the rotation of the bearing outer ring, all parts of the bearing outer ring can be fully displayed, so that the plurality of cameras can capture videos and pictures of the surface of the bearing outer ring from multiple angles, thereby obtaining detection images of the bearing outer ring for observation and analysis by detection equipment, thereby reducing the possibility of missed detection and misjudgment. Moreover, compared with static detection, dynamic detection can more comprehensively reflect the performance of the bearing outer ring under different working conditions.

[0008] Further definition, the driving mechanism includes two rolling shafts arranged in parallel and spaced apart in the front-to-back direction, each rolling shaft is equipped with two rolling brackets that are symmetrical on the left and right, the outer ring of the bearing can be placed on the four rolling brackets between the two rolling shafts, the central axis of the outer ring of the bearing is parallel to the central axis of the rolling shaft, and when the two rolling shafts rotate synchronously, they can drive the outer ring of the bearing to rotate.

[0009] Further definition, there are three cameras, which are respectively located above, on the left and on the right side of the bearing outer ring on the supporting platform, and can respectively shoot the outer surface of the bearing outer ring and the left and right ends.

[0010] It is further defined that each of the cameras is mounted on the supporting platform via a telescopic arm. By controlling the length of each telescopic arm, the position of each camera can be adjusted so that it can be suitable for detecting bearing outer rings of various sizes. Specifically, after the bearing outer ring is mounted on the driving mechanism, the position of each camera can be adjusted so that it is close to the bearing outer ring for shooting.

[0011] Further definition, the flaw detection device also includes a fluorescent light source installed on the support platform for lighting. The fluorescent light source can provide uniform, shadow-free lighting, so that the defective parts on the surface of the bearing outer ring can be clearly presented, and can reduce reflection interference, so that tiny cracks, scratches and other difficult-to-detect defects can also be accurately captured, which can enhance the accuracy of image analysis. Under good lighting conditions, the machine vision system including multiple cameras can capture the image of the bearing outer ring surface more quickly and accurately and perform analysis and processing, thereby improving detection efficiency.

[0012] Further definition, the support platform is equipped with a magnetized electrode that can be installed in the outer ring of the bearing, the magnetized electrode is externally connected to a high-voltage power supply, and the support platform is equipped with a water pipe that can be used to spray a fluorescent electrolyte onto the surface of the outer ring of the bearing on the magnetized electrode. The fluorescent electrolyte is sprayed onto the surface of the outer ring of the bearing on the magnetized electrode. Under the action of the magnetized electrode and the fluorescent electrolyte, a fluorescent effect is generated, so that the magnetic traces of the defective parts on the surface of the outer ring of the bearing can be more clearly seen, making the defective parts easier to identify and locate, improving the image clarity, thereby improving the sensitivity of the detection and improving the accuracy of the detection. It is a non-destructive test that will not cause any damage to the outer ring of the bearing, thereby ensuring the integrity and performance of the outer ring of the bearing.

[0013] Further definition, the magnetizing electrode is a telescopic structure. After the outer ring of the bearing is placed on the four rolling brackets, the magnetizing electrode is extended so that it can pass through the outer ring of the bearing, making it easy to disassemble and assemble the outer ring of the bearing. A high-voltage power supply is used to pass a large current through the magnetizing electrode to form a strong magnetic field, which can magnetize the outer ring of the bearing.

[0014] Compared with the prior art, the present invention has the following beneficial effects:

[0015] This flaw detection device achieves accurate capture of subtle defects on and inside the bearing outer ring by dynamically rotating the bearing outer ring in combination with all-round, multi-angle high-definition video and fluorescence enhancement technology. Records are saved in the form of video and pictures for effective archiving, which helps to establish a product quality defect sample library. Combined with existing image processing and recognition technologies, the image is first pre-processed, and then the characteristic information of the bearing outer ring surface in the image is extracted based on algorithms such as edge detection and image segmentation. Surface defects of the bearing outer ring are identified, and defect detection on the bearing outer ring surface is completed, laying the foundation for artificial intelligence and machine vision inspection. This flaw detection device can improve the comprehensiveness and accuracy of inspection, reduce human intervention and misjudgment, and at the same time ensure the non-destructive and efficient inspection process. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly describes the drawings required for the specific embodiments or the description of the prior art. Similar elements or parts are generally identified by similar reference numerals throughout the drawings. Elements or parts in the drawings are not necessarily drawn to scale.

[0017] Figure 1 It is a structural schematic diagram of the flaw detection device of the present utility model.

[0018] The names of the components in the figure are: 1. Carrying platform; 2. Rolling shaft; 3. Bearing outer ring; 4. Rolling bracket; 5. Magnetized electrode; 6. Telescopic arm; 7. Camera; 8. Fluorescent light source; 9. Water pipe; 10. High-voltage power supply; 11. Display screen; 12. Control cabinet. DETAILED DESCRIPTION

[0019] The following embodiments of the technical solution of the present invention are described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention and are therefore only examples and are not intended to limit the scope of protection of the present invention.

[0020] In the description of this application, it should be understood that the terms "upper", "lower", "inside", "outside", "front", "back", "left", "right", etc., indicating directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as a limitation on the present invention.

[0021] A device for detecting surface defects of bearing outer ring based on machine vision, such as Figure 1As shown, it is mainly composed of a supporting platform 1, a driving mechanism, a camera 7, a telescopic arm 6, a fluorescent light source 8 and a magnetized electrode 5.

[0022] like Figure 1 As shown, the driving mechanism includes two rolling shafts 2 arranged on the carrier 1 and spaced apart in parallel along the front-to-back direction, and a driving motor and a transmission box installed on the carrier 1 for driving the rolling shafts 2 to rotate synchronously. One end of the two rolling shafts 2 is rotatably connected to the carrier 1, and the other end thereof is connected to the transmission box. The transmission box is connected to the power output end of the driving motor, and the driving motor can drive the two rolling shafts 2 to rotate synchronously through the transmission box.

[0023] Two rolling brackets 4 are installed on each rolling shaft 2, which are symmetrical on the left and right. The outer ring 3 of the bearing can be placed on the four rolling brackets 4 between the two rolling shafts 2. The central axis of the outer ring 3 of the bearing is parallel to the central axis of the rolling shaft 2. When the two rolling shafts 2 rotate synchronously, the outer ring 3 of the bearing can be driven to rotate. Specifically, the rolling bracket 4 is a T-shaped cylindrical structure made of plastic material, which is mounted on and fixed on the rolling shaft 2. Based on the gravity of the outer ring 3 of the bearing and the friction resistance between the outer ring 3 of the bearing and the rolling bracket 4, when the two rolling shafts 2 rotate synchronously, the outer ring 3 of the bearing can be driven to rotate.

[0024] like Figure 1 As shown, three cameras 7 are provided, and three telescopic arms 6 are provided accordingly. One end of each of the three telescopic arms 6 is mounted on the supporting platform 1, and the three cameras 7 are respectively mounted on the other end of each of the three telescopic arms 6. The three cameras 7 are all located above the two rolling shafts 2. When the bearing outer ring 3 is placed on the four rolling brackets 4 between the two rolling shafts 2, the three cameras 7 are respectively located above, on the left side, and on the right side of the bearing outer ring 3, and can respectively shoot the outer surface and the left and right ends of the bearing outer ring 3;

[0025] The telescopic arms 6 are telescopic tubes or telescopic rods with adjustable lengths. By controlling the lengths of the telescopic arms 6 , the positions of the cameras 7 can be adjusted, making them suitable for detecting bearing outer rings 3 of various sizes. Specifically, after the bearing outer ring 3 is mounted on the drive mechanism, the positions of the cameras 7 can be adjusted so that they are close to the bearing outer ring 3 for shooting.

[0026] The fluorescent light source 8 is mounted on the support platform 1 and located above the two rolling shafts 2. The fluorescent light source 8 can provide uniform, shadow-free illumination, allowing defects on the surface of the bearing outer ring 3 to be clearly displayed, reducing reflection interference, and accurately capturing even subtle defects such as tiny cracks and scratches. This can enhance the accuracy of image analysis. Under good lighting conditions, the machine vision system including the three cameras 7 can more quickly and accurately capture images of the surface of the bearing outer ring 3 and perform analysis and processing, thereby improving detection efficiency.

[0027] The camera 7 above the bearing outer ring 3 is fixed on the fluorescent light source 8, and can photograph the defects on the outer surface of the bearing outer ring 3. By controlling the length of the telescopic arm 6 to adjust the distance between the camera 7 and the bearing outer ring 3, bearings of various sizes can be detected; the left and right cameras 7 can respectively photograph the defects on the left and right surfaces of the bearing outer ring 3, and the telescopic arm 6 can also be controlled to allow the left and right cameras 7 to enter the interior of the bearing outer ring 3 for 360° all-round photography.

[0028] like Figure 1 As shown, the magnetizing electrode 5 is mounted on the carrier 1 and is located above the two rolling shafts 2. The magnetizing electrode 5 can be inserted into the bearing outer ring 3. The magnetizing electrode 5 is externally connected to a 380V high-voltage power supply 10. The magnetizing electrode 5 has a telescopic structure. After the bearing outer ring 3 is placed on the four rolling brackets 4, the magnetizing electrode 5 is extended so that it can pass through the bearing outer ring 3, making it easy to disassemble and assemble the bearing outer ring 3. A high current is passed through the magnetizing electrode 5 using the high-voltage power supply 10 to form a strong magnetic field, which can magnetize the bearing outer ring 3.

[0029] A water pipe 9 is installed on the supporting platform 1 for spraying fluorescent electrolyte onto the surface of the bearing outer ring 3 on the magnetized electrode 5. There are two water pipes 9, and their water outlets are located on the left and right sides of the bearing outer ring 3. Specifically, the water outlet of the water pipe 9 is a certain distance away from the bearing outer ring 3. The liquid supply system pumps the fluorescent electrolyte into the water pipe 9 and sprays the fluorescent electrolyte onto the surface of the bearing outer ring 3 on the magnetized electrode 5. Under the action of the magnetized electrode 5 and the fluorescent electrolyte, a fluorescent effect is generated, so that the magnetic traces of the defective parts on the surface of the bearing outer ring 3 can be more clearly seen, making the defective parts easier to identify and locate, improving the image clarity, thereby improving the sensitivity of the detection and improving the accuracy of the detection. It is a non-destructive test that will not cause any damage to the bearing outer ring 3, thereby ensuring the integrity and performance of the bearing outer ring 3.

[0030] In this embodiment, Figure 1 As shown, the flaw detection device also includes a control cabinet 12 and a display screen 11. The control cabinet 12 can control the start and stop of the two rolling shafts 2, the start and stop of the fluorescent light source 8, the liquid supply to the water pipe 9, and the capture of images by the three cameras 7. In addition, the control cabinet 12 is also equipped with a machine vision system (including a computer), which can receive images transmitted by the camera 7 and pre-process the images. Then, based on edge detection, image segmentation and other algorithms, feature information of the surface of the bearing outer ring 3 in the image is extracted to identify defects on the surface of the bearing outer ring 3, thereby completing defect detection on the surface of the bearing outer ring 3. The detection structure can be displayed on the display screen 11.

[0031] The working principle of this embodiment is as follows:

[0032] Retract the magnetizing electrode 5 and place the bearing outer ring 3 on the four rolling brackets 4 between the two rolling shafts 2. Extend the magnetizing electrode 5 so that it passes through the inside of the bearing outer ring 3. Adjust the three telescopic arms 6 to adjust the distance between the three cameras 7 and the bearing outer ring 3. Apply power to the magnetizing electrode 5 with a 380V high-voltage power supply 10, using the magnetizing electrode 5 to generate a strong magnetic field to magnetize the bearing outer ring 3.

[0033] Start the switch, drive the motor to drive the two rolling shafts 2 to rotate synchronously, and the two rolling shafts 2 drive the bearing outer ring 3 to start rotating. At the same time, turn on the fluorescent light source 8 and pump fluorescent electrolyte to the two water pipes 9 to spray the fluorescent electrolyte on the surface of the bearing outer ring 3. After spraying the fluorescent electrolyte for a period of time, start the three cameras 7 and control the three cameras 7 to take images of the inner and outer surfaces of the bearing outer ring 3 respectively. The machine vision system of the control cabinet 12 receives the image and pre-processes the collected image. Then, based on edge detection, image segmentation and other algorithms, the feature information of the surface of the bearing outer ring 3 in the image is extracted to identify the surface defects of the bearing outer ring 3 and complete the defect detection of the surface of the bearing outer ring 3. The detection structure can be displayed on the display screen 11. This automated detection method can greatly improve the efficiency of surface defect detection of the bearing outer ring 3 and reduce manual intervention and detection time.

[0034] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and description of the present invention.

Claims

1. A device for detecting surface defects of a bearing outer ring based on machine vision, comprising a support platform (1), characterized in that: The carrier platform (1) is provided with a driving mechanism for driving the bearing outer ring (3) to rotate, and the carrier platform (1) is provided with a plurality of cameras (7) for shooting videos and pictures of the surface images of the bearing outer ring (3).

2. The device for detecting surface defects of a bearing outer ring based on machine vision according to claim 1, characterized in that: The driving mechanism comprises two rolling shafts (2) arranged in parallel and spaced apart in the front-to-back direction, and each rolling shaft (2) is provided with two rolling brackets (4) which are symmetrical on both sides.

3. The device for detecting surface defects of a bearing outer ring based on machine vision according to claim 1, characterized in that: Three cameras (7) are provided, and the three cameras (7) are respectively located above, on the left side, and on the right side of the bearing outer ring (3) on the supporting platform (1).

4. The device for detecting surface defects of a bearing outer ring based on machine vision according to claim 3 is characterized in that: Each of the cameras (7) is mounted on the supporting platform (1) via a telescopic arm (6).

5. The device for detecting surface defects of a bearing outer ring based on machine vision according to claim 1, characterized in that: The flaw detection device also includes a fluorescent light source (8) mounted on the carrier platform (1) for illumination.

6. The device for detecting surface defects of a bearing outer ring based on machine vision according to claim 5, characterized in that: The carrier platform (1) is provided with a magnetizing electrode (5) that can be inserted into the bearing outer ring (3), the magnetizing electrode (5) is externally connected to a high-voltage power supply (10), and the carrier platform (1) is provided with a water pipe (9) that can be used to spray a fluorescent electrolyte onto the surface of the bearing outer ring (3) on the magnetizing electrode (5).

7. The device for detecting surface defects of a bearing outer ring based on machine vision according to claim 6, characterized in that: The magnetizing electrode (5) is a telescopic structure.