Bearing outer ring surface crack detection device

By designing an image optimization device including edge operation equipment, sharpening processing equipment and bilateral filtering equipment, multi-layer sharpening and filtering processing of bearing images, the problem of difficulty in detecting cracks on the outer ring of bearings with high precision is solved in the prior art. , realizes high-precision crack detection and identification.

CN119413720AInactive Publication Date: 2025-02-11NANJING CANHENG RONGZHAO INTELLIGENT TECHNOLOGY CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411631541.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-12-06
Filing Date
2024-11-15
Publication Date
2025-02-11
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The prior art is difficult to detect fine cracks on the outer ring surface of the bearing with high accuracy, resulting in the inability to effectively identify and deal with potential safety hazards.

Method used

A targeted image optimization device including edge operation equipment, sharpening processing equipment and bilateral filtering equipment is designed, and edge sharpening processing, USM filter-based sharpening processing and bilateral filtering processing are performed on bearing images in factory state. , generate a bilateral filtered image with image quality optimization, and determine whether there are cracks on the outer ring surface of the bearing based on the effective number of pixels.

Benefits of technology

It realizes targeted and high-precision detection of cracks on the outer ring surface of the bearing, provides reliable identification information, and ensures the safety and reliability of the bearing.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to a bearing outer ring surface crack detection device. The device comprises a rotary acquisition mechanism, edge operation equipment, sharpening processing equipment, bilateral filtering equipment, a multi-layer detection device and a strategy conversion device. The device can complete targeted and high-precision detection on the surface crack of the bearing outer ring.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of bearing detection, and more specifically, to a device for detecting cracks on the surface of a bearing outer ring. Background Art

[0002] As the signal types become more complex, when the signal to be analyzed cannot meet the conditions of Gaussian distribution and non-minimum phase, there are higher-order spectrum analysis methods. Higher-order spectrum analysis can provide phase information, non-Gaussian information and nonlinear information of the signal; adaptive filtering and equalization are also a major field of applied research. Adaptive filtering includes lateral LMS adaptive filtering, grid adaptive filtering, adaptive cancellation filtering, and adaptive equalization. In addition, there is array signal processing for array signals.

[0003] Signal processing is the basic theory and technology of telecommunications. Its mathematical theories include equation theory, function theory, number theory, random process theory, least square method and optimization theory, and its technical pillars are circuit analysis, synthesis and electronic computer technology. Signal processing is closely related to contemporary pattern recognition, artificial intelligence, neural network computing and multimedia information processing, and it closely links basic theory with engineering applications. Therefore, signal processing is a discipline that has both a complex mathematical analysis background and broad practical engineering prospects.

[0004] Generally, the surface cracks of the outer ring of the bearing are very subtle and difficult to be detected by the naked eye. At the same time, the subtle surface cracks are also difficult to distinguish. However, even the subtlest surface cracks will cause interference and impact on the use of the bearing in terms of safety. Therefore, a high-precision surface crack analysis mechanism for the outer ring of the bearing is required to identify the subtle size of the surface cracks of the outer ring of the bearing on site. The detection methods involved in the field are: "A method and device for detecting black block defects of bearings based on machine vision" with application publication number CN116883343A. This detection method enhances the original image through an improved Gaussian filter image enhancement algorithm to obtain an enhanced image; extracts the ROI of the bearing ring from the enhanced image, and obtains the ROI image containing polar coordinates through polar coordinate transformation; eliminates irrelevant features of the ROI image twice to obtain the image to be determined; and uses a double threshold processing method to determine whether the image to be determined has surface defects. The application publication number is CN116519700A, "A three-dimensional defect detection device and method for bearings". The method includes removing oil droplets from the end face of the bearing to be detected, and then transporting the bearing to the oil droplet detection station and the defect detection station in sequence; photographing the bearing at the oil droplet detection station to obtain a two-dimensional bearing color image, and photographing the bearing at the defect detection station to obtain multiple two-dimensional bearing images; preprocessing the two-dimensional bearing color image and the multiple two-dimensional bearing images to obtain a color preprocessed image and multiple preprocessed images; performing color detection on the color preprocessed image to obtain oil droplet detection results; and inputting the multiple preprocessed images into a pre-trained deep learning model to obtain defect detection results. Summary of the invention

[0005] In order to accurately detect surface cracks on a bearing outer ring, the present invention provides a detection device for surface cracks on a bearing outer ring. The device can refer to a targeted image optimization device including an edge operation device, a sharpening device and a bilateral filtering device, and sequentially perform edge sharpening processing, sharpening processing based on a USM filter and bilateral filtering processing on a factory environment image corresponding to a bearing in a factory state, so as to obtain a bilateral filtered image with optimized image quality, thereby providing reliable information for subsequent identification of surface cracks on the bearing outer ring. At the same time, based on the number of effective pixels in the bilateral filtered image, it is determined whether there are surface cracks on the bearing outer ring in the bilateral filtered image, thereby completing targeted and high-precision detection of surface cracks on the bearing outer ring.

[0006] Specifically, the device comprises: The rotating acquisition mechanism comprises a rotating platform and an image acquisition device arranged on the rotating platform, wherein the image acquisition device performs image data acquisition of the environment where the outer ring surface of the bearing workpiece in the factory state is located under the rotation of the rotating platform, so as to obtain and output a corresponding factory environment image; An edge operation device, connected to the rotating acquisition mechanism, is used to perform edge sharpening processing on the received factory environment image to obtain and output a corresponding edge sharpened image; A sharpening processing device, connected to the edge operation device, for performing a sharpening process based on a USM filter on the received edge-sharpened image to obtain and output a corresponding instant sharpened image; A bilateral filtering device, connected to the sharpening processing device, for performing a bilateral filtering process on the received instant sharpened image to obtain and output a corresponding bilateral filtered image; a multi-layer detection device, connected to the bilateral filtering device and comprising a pixel resolution device, a numerical analysis device and a signal output device, wherein the numerical analysis device is respectively connected to the pixel resolution device and the signal output device, and the multi-layer detection device is used to perform the following detection operations on a single pixel of the received bilateral filtering image as a current pixel: when the red channel value, green channel value and blue channel value of the current pixel in the RGB color space respectively fall within the red channel value range, green channel value range and blue channel range corresponding to the crack on the outer ring surface of the bearing, the current pixel is regarded as a valid pixel; otherwise, the current pixel is regarded as an invalid pixel, and when the number of valid pixels in the bilateral filtering image exceeds or equals to a set number threshold, a crack extraction success signal is issued; A strategy conversion device, connected to the multi-layer detection device, is used to perform a waste identification process on the bearing workpiece in the factory state when a crack extraction success signal is received, and is also used to not perform a waste identification process on the bearing workpiece in the factory state when a crack extraction failure signal is received; Wherein, the multi-layer detection device is also used to send a crack extraction failure signal when the number of effective pixel points in the bilateral filtering image is less than the set number threshold.

[0007] The detection device for cracks on the surface of the outer ring of the bearing of the present invention is compact in design, safe and reliable. Since the targeted image optimization device can be used to sequentially perform edge sharpening processing, USM filter-based sharpening processing and bilateral filtering processing on the factory environment image corresponding to the bearing in the factory state, a bilateral filtering image with optimized image quality can be obtained, and at the same time, whether there are cracks on the surface of the outer ring of the bearing in the bilateral filtering image is determined based on the number of effective pixels in the bilateral filtering image, thereby completing targeted and high-precision detection of cracks on the surface of the outer ring of the bearing. DETAILED DESCRIPTION

[0008] Example 1

[0009] The device for detecting cracks on the surface of a bearing outer ring according to embodiment 1 of the present invention comprises: The rotating acquisition mechanism comprises a rotating platform and an image acquisition device arranged on the rotating platform, wherein the image acquisition device performs image data acquisition of the environment where the outer ring surface of the bearing workpiece in the factory state is located under the rotation of the rotating platform, so as to obtain and output a corresponding factory environment image; For example, the rotating acquisition mechanism is also equipped with a main control chip, which is connected to the rotating pan-tilt platform and the image acquisition device respectively, and is used to configure the parameters of the rotating pan-tilt platform and the image acquisition device; An edge operation device, connected to the rotating acquisition mechanism, is used to perform edge sharpening processing on the received factory environment image to obtain and output a corresponding edge sharpened image; A sharpening processing device, connected to the edge operation device, for performing a sharpening process based on a USM filter on the received edge-sharpened image to obtain and output a corresponding instant sharpened image; A bilateral filtering device, connected to the sharpening processing device, for performing a bilateral filtering process on the received instant sharpened image to obtain and output a corresponding bilateral filtered image; A multi-layer detection device is connected to the bilateral filtering device and includes a pixel resolution device, a numerical analysis device and a signal output device. The numerical analysis device is respectively connected to the pixel resolution device and the signal output device. The multi-layer detection device is used to perform the following detection operations on a single pixel of the received bilateral filtering image as a current pixel: when the red channel value, green channel value and blue channel value of the current pixel in the RGB color space fall within the red channel value range, green channel value range and blue channel range corresponding to the crack on the outer ring surface of the bearing, respectively, the current pixel is used as a valid pixel; otherwise, the current pixel is used as an invalid pixel; and when the number of valid pixels in the bilateral filtering image exceeds or equals to a set number threshold, a crack extraction success signal is issued; A strategy conversion device, connected to the multi-layer detection device, is used to perform a waste identification process on the bearing workpiece in the factory state when a crack extraction success signal is received, and is also used to not perform a waste identification process on the bearing workpiece in the factory state when a crack extraction failure signal is received; Wherein, the multi-layer detection device is further used to send a crack extraction failure signal when the number of valid pixel points in the bilateral filter image is less than the set number threshold; Among them, when the red channel value, green channel value and blue channel value of the current pixel point in the RGB color space respectively fall within the red channel value range, green channel value range and blue channel range corresponding to the crack on the outer ring surface of the bearing, the current pixel point is taken as a valid pixel point; otherwise, taking the current pixel point as an invalid pixel point includes: the value of any color channel value among the red channel value, green channel value and blue channel value of the current pixel point in the RGB color space is between 0-255.

[0010] Example 2

[0011] Embodiment 2 of the present invention shows a device for detecting cracks on the surface of a bearing outer ring.

[0012] Different from the first embodiment, the device for detecting cracks on the surface of the bearing outer ring in the second embodiment may further include the following components: A length sensor device, connected to the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device, respectively, for measuring the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device respectively; Wherein, the length sensor device is respectively connected to the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device, and is used to respectively measure the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device, including: the length sensor device includes a plurality of length measurement units, which are respectively connected to the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device, so as to complete the measurement of the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device; Wherein, the length sensor device comprises a plurality of length measuring units, which are respectively connected to the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device to complete the respective measurement of the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device, including: the plurality of length measuring units are a plurality of length sensors, which are respectively connected to the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device to complete the respective measurement of the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device; Wherein, the plurality of length measurement units are a plurality of length sensors, which are used to be respectively connected to the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device to respectively measure the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device, including: the plurality of length sensors have the same structure; Among them, the multiple length measurement units are multiple length sensors, which are used to be connected to the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device respectively to complete the measurement of the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device respectively, and also include: the multiple length sensors have the same length measurement upper limit value and length measurement lower limit value.

[0013] Example 3

[0014] Embodiment 3 of the present invention shows a device for detecting cracks on the surface of a bearing outer ring.

[0015] Different from the first embodiment, the device for detecting cracks on the surface of the bearing outer ring in the third embodiment may further include the following components: A length display mechanism, connected to the edge operation device, the sharpening processing device, the bilateral filtering device and the plurality of length measuring units of the multi-layer detection device, respectively, for synchronously displaying the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device respectively; Wherein, the length display mechanism is respectively connected to the edge operation device, the sharpening processing device, the bilateral filtering device and the multiple length measuring units of the multi-layer detection device, and is used to synchronously display the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device respectively, including: the length display mechanism is a touch display screen; Among them, the length display mechanism is respectively connected to multiple length measurement units of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device, and is used to synchronously display the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device. The length display mechanism includes: the length display mechanism is a non-touch display screen.

[0016] In addition, in the detection device for cracks on the surface of the bearing outer ring, when the red channel value, green channel value and blue channel value of the current pixel point in the RGB color space respectively fall within the red channel value range, green channel value range and blue channel range corresponding to the cracks on the surface of the bearing outer ring, the current pixel point is taken as a valid pixel point; otherwise, the current pixel point is taken as an invalid pixel point, and further comprises: using a numerical simulation mode to complete the simulation processing of the data processing process of taking the current pixel point as a valid pixel point when the red channel value, green channel value and blue channel value of the current pixel point in the RGB color space respectively fall within the red channel value range, green channel value range and blue channel range corresponding to the cracks on the surface of the bearing outer ring; otherwise, the current pixel point is taken as an invalid pixel point; Among them, when the red channel value, green channel value and blue channel value of the current pixel point in the RGB color space respectively fall within the red channel value range, green channel value range and blue channel range corresponding to the crack on the surface of the bearing outer ring, the current pixel point is taken as a valid pixel point; otherwise, taking the current pixel point as an invalid pixel point also includes: the value of any channel value of the red channel value, green channel value and blue channel value of the current pixel point in the RGB color space is between 0-255.

[0017] The creativity and technical effects of the present invention are: 1. Use the red channel value range, green channel value range and blue channel range corresponding to the surface cracks of the bearing outer ring to complete the targeted identification of the effective pixel points constituting the surface cracks of the bearing outer ring; 2. Determine whether there are cracks on the surface of the bearing outer ring in the bilateral filtered image based on the number of effective pixels in the bilateral filtered image, thereby completing targeted and high-precision detection of cracks on the surface of the bearing outer ring; 3. A targeted image optimization device including an edge operation device, a sharpening device and a bilateral filtering device is used to sequentially perform edge sharpening processing, sharpening processing based on a USM filter and bilateral filtering processing on the factory environment image corresponding to the bearing in the factory state, so as to obtain a bilateral filtered image with optimized image quality, thereby providing reliable information for the subsequent identification of cracks on the outer ring surface of the bearing.

[0018] Although only exemplary embodiments of the present invention have been described in detail above, those skilled in the art will readily appreciate that many variations are possible in these exemplary embodiments without materially departing from the novel principles and advantages of the present invention. Accordingly, all such variations are intended to be included within the scope of the present invention as defined by the following claims. In the claims, means and function clauses are intended to include structures described herein as performing the recited functions, and include not only structural equivalents, but also equivalent structures.

Claims

1. A device for detecting cracks on the surface of a bearing outer ring, characterized in that: The device comprises: The rotating acquisition mechanism comprises a rotating platform and an image acquisition device arranged on the rotating platform, wherein the image acquisition device performs image data acquisition of the environment where the outer ring surface of the bearing workpiece in the factory state is located under the rotation of the rotating platform, so as to obtain and output a corresponding factory environment image; An edge operation device, connected to the rotating acquisition mechanism, is used to perform edge sharpening processing on the received factory environment image to obtain and output a corresponding edge sharpened image; A sharpening processing device, connected to the edge operation device, for performing a sharpening process based on a USM filter on the received edge-sharpened image to obtain and output a corresponding instant sharpened image; A bilateral filtering device, connected to the sharpening processing device, for performing a bilateral filtering process on the received instant sharpened image to obtain and output a corresponding bilateral filtered image; A multi-layer detection device is connected to the bilateral filtering device and includes a pixel resolution device, a numerical analysis device and a signal output device. The numerical analysis device is respectively connected to the pixel resolution device and the signal output device. The multi-layer detection device is used to perform the following detection operations on a single pixel of the received bilateral filtering image as a current pixel: when the red channel value, green channel value and blue channel value of the current pixel in the RGB color space fall within the red channel value range, green channel value range and blue channel range corresponding to the crack on the outer ring surface of the bearing, respectively, the current pixel is used as a valid pixel; otherwise, the current pixel is used as an invalid pixel; and when the number of valid pixels in the bilateral filtering image exceeds or equals to a set number threshold, a crack extraction success signal is issued; A strategy conversion device, connected to the multi-layer detection device, is used to perform a waste identification process on the bearing workpiece in the factory state when a crack extraction success signal is received, and is also used to not perform a waste identification process on the bearing workpiece in the factory state when a crack extraction failure signal is received; Wherein, the multi-layer detection device is also used to send a crack extraction failure signal when the number of effective pixel points in the bilateral filtering image is less than the set number threshold.

2. The device for detecting cracks on the surface of a bearing outer ring according to claim 1, characterized in that: When the red channel value, green channel value and blue channel value of the current pixel point in the RGB color space respectively fall within the red channel value range, green channel value range and blue channel range corresponding to the crack on the outer ring surface of the bearing, the current pixel point is taken as a valid pixel point; otherwise, the current pixel point is taken as an invalid pixel point, including: the value of any color channel value among the red channel value, green channel value and blue channel value of the current pixel point in the RGB color space is between 0-255.

3. The device for detecting cracks on the surface of the bearing outer ring according to claim 2, characterized in that: The device also includes: A length sensor device, connected to the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device, respectively, for measuring the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device respectively; Among them, the length sensor device is respectively connected to the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device, and is used to respectively measure the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device. The length sensor device includes multiple length measurement units, which are respectively connected to the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device to complete the measurement of the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device.

4. The device for detecting cracks on the surface of a bearing outer ring according to claim 3, characterized in that: The length sensor device includes a plurality of length measurement units, which are used to be respectively connected to the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device to complete the respective measurement of the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device. The plurality of length measurement units are a plurality of length sensors, which are used to be respectively connected to the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device to complete the respective measurement of the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device.

5. The device for detecting cracks on the surface of a bearing outer ring according to claim 4, characterized in that: The multiple length measurement units are multiple length sensors, which are used to be connected to the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device respectively, so as to complete the measurement of the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device respectively, including: the structures of the multiple length sensors are the same.

6. The device for detecting cracks on the surface of a bearing outer ring according to claim 5, characterized in that: The multiple length measurement units are multiple length sensors, which are used to be connected to the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device respectively to complete the measurement of the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device respectively, and also include: the multiple length sensors have the same length measurement upper limit value and length measurement lower limit value.

7. The device for detecting cracks on the surface of a bearing outer ring according to any one of claims 3 to 6, characterized in that: The device also includes: The length display mechanism is respectively connected to the edge operation device, the sharpening processing device, the bilateral filtering device and the multiple length measurement units of the multi-layer detection device, and is used to synchronously display the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device.

8. The device for detecting cracks on the surface of a bearing outer ring according to claim 7, characterized in that: The length display mechanism is respectively connected to the edge operation device, the sharpening processing device, the bilateral filtering device and multiple length measurement units of the multi-layer detection device, and is used to synchronously display the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device. The length display mechanism is a touch display screen.

9. The device for detecting cracks on the surface of a bearing outer ring according to claim 7, characterized in that: The length display mechanism is respectively connected to the edge operation device, the sharpening processing device, the bilateral filtering device and multiple length measurement units of the multi-layer detection device, and is used to synchronously display the current real-time length values ​​of the edge operation device, the sharpening processing device, the bilateral filtering device and the multi-layer detection device. The length display mechanism is a non-touch display screen.

Citation Information

Patent Citations

  • Three-dimensional defect detection system and method for bearing

    CN116519700A

  • Bearing black block defect detection method and device based on machine vision

    CN116883343A