Gear inspection apparatus

The gear inspection device addresses alignment and machine learning limitations by generating multiple images and using advanced algorithms to accurately detect gear abnormalities, enhancing precision in identifying defects like scratches.

JP2024162756AActive Publication Date: 2024-11-21TOYOTA JIDOSHA KK
View PDF 11 Cites 0 Cited by

Patent Information

Application Number
JP2023078624
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-11
Publication Date
2024-11-21
Estimated Expiration
2043-05-11

AI Technical Summary

Technical Problem

Existing gear inspection methods struggle with accurately detecting abnormalities such as scratches due to issues like similar brightness between images before and after rotation, alignment challenges with large gears, and limitations in machine learning technology for image analysis.

Method used

A gear inspection device that generates multiple images by rotating the gear by a predetermined angle, using an image acquisition unit, an image extraction unit, and an abnormality determination unit to compare with a master image and determine gear abnormalities based on the number of teeth, employing machine learning models for precise detection.

Benefits of technology

Enhances the accuracy of detecting gear abnormalities, including scratches, by aligning gear phase effectively and utilizing advanced machine learning, ensuring high precision in identifying gear defects.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024162756000001_ABST
    Figure 2024162756000001_ABST
Patent Text Reader

Abstract

To provide a gear inspection apparatus for detecting an anomaly of a gear accurately from an image of the gear.SOLUTION: A gear inspection system includes an edge personal computer (edge PC), an object detection sensor, a PLC (Programmable Logic Controller), a camera, and a rotating device. The edge PC as a gear inspection apparatus includes: an image acquisition unit which acquires a predetermined number of captured images which are generated by imaging teeth of a gear rotated by predetermined angle; an image extraction unit which extracts an inspection image from the captured images by collating a master image with each of the predetermined number of captured images; and an anomaly determination unit which determines whether the gear is abnormal or not, using the inspection image. The predetermined number is the number of captured images generated by the camera for determining an anomaly of the gear, and determined based on the predetermined angle and the number of teeth of the gear.SELECTED DRAWING: Figure 2
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a gear inspection device. [Background technology]

[0002] Conventionally, it is known to inspect gears by analyzing photographed images of the gears, without relying on human visual inspection, in order to detect abnormalities such as scratches that may occur on the gears.

[0003] Patent Document 1 describes a method in which a gear is rotated a predetermined angle at a time and photographed sequentially, and in a differential image generated from the difference between the image taken after the rotation and the image taken before the rotation, a region requiring determination having a brightness exceeding a predetermined threshold is detected, and the inspection region surrounding the region requiring determination is analyzed to determine the surface condition of the gear. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2006-047040 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, gear abnormalities do not necessarily appear as brightness differences between images taken before and after rotation. For example, if a chip in a gear cutter causes similar scratches on all teeth of a gear, the scratches on the gear that should be detected will not appear as brightness differences.

[0006] In addition, in the method described in Patent Document 1, when the gear is rotated, the gear teeth are photographed in response to a detection signal generated when a proximity sensor detects the approach of the gear teeth. However, when the gear to be inspected is large, it is not possible to align the gear to the desired phase (rotation angle) by only detecting the gear teeth, and there is a risk of a decrease in accuracy in determining whether the gear is abnormal.

[0007] Furthermore, Patent Document 1 describes that the presence or absence of damage to a gear is determined by a determination unit configured with a neurocomputer having a learning function. However, machine learning technology for image analysis is continuing to develop, and there is room for improvement in the determination method for gear images.

[0008] In view of the above-mentioned problems, an object of the present invention is to accurately detect gear abnormalities from gear images. [Means for solving the problem]

[0009] In order to solve the above problems, the present invention provides a gear inspection device for inspecting gears, comprising an image acquisition unit that acquires a predetermined number of captured images generated by photographing the teeth of the gear as the gear is rotated by a predetermined angle at a time, an image extraction unit that extracts an inspection image from the captured images by comparing each of the predetermined number of captured images with a master image, and an abnormality determination unit that uses the inspection images to determine the presence or absence of an abnormality in the gear, wherein the predetermined number is determined based on the predetermined angle and the number of teeth of the gear. Effect of the Invention

[0010] According to the present invention, gear abnormalities can be detected with high accuracy from gear images. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram illustrating a schematic configuration of a gear inspection system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a functional block diagram of the processor of the edge PC. [Diagram 3] FIG. 3 is a flowchart showing a control routine for the abnormality determination process in this embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description, like components are designated by like reference numerals.

[0013] Fig. 1 is a diagram illustrating a schematic configuration of a gear inspection system 10 according to an embodiment of the present invention. The gear inspection system 10 is installed in, for example, a gear manufacturing plant or a plant for producing products having gears (such as an automobile assembly plant) and inspects gears. As shown in Fig. 1, the gear inspection system 10 includes an edge personal computer (edge ​​PC) 1, an object detection sensor 2, a PLC (Programmable Logic Controller) 3, a camera 4, and a rotating device 5.

[0014] The edge PC1 is an example of a gear inspection device that inspects gears. In this embodiment, the edge PC1 inspects the appearance of a gear and detects gear abnormalities such as scratches. As shown in Fig. 1, the edge PC1 includes an input / output interface 11, a memory 12, and a processor 13. The input / output interface 11 and the memory 12 are connected to the processor 13 via signal lines.

[0015] The input / output interface 11 has an interface circuit for connecting the edge PC1 to peripheral devices. Outputs of peripheral devices such as the PLC 3 and the camera 4 are input to the edge PC1 via the input / output interface 11, and command signals generated by the processor 13 are output to the peripheral devices such as the camera 4 and the rotation device 5 via the input / output interface 11.

[0016] The memory 12 includes, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. The memory 12 stores computer programs, data, etc. that are used when the processor 13 executes various processes.

[0017] The processor 13 includes one or more central processing units (CPUs) and their peripheral circuits, and may further include an arithmetic circuit such as a logic arithmetic unit or a numerical arithmetic unit.

[0018] The object detection sensor 2 detects the presence or absence of a gear to be inspected. The object detection sensor 2 is configured as, for example, a photoelectric sensor, a proximity sensor, or a microphoto sensor. The object detection sensor 2 is connected to the PLC 3 by wire or wirelessly, and the output of the object detection sensor 2 is transmitted to the PLC 3.

[0019] The PLC 3 is communicatively connected to the object detection sensor 2 and the edge PC 1. The PLC 3 determines the timing of photographing the gear based on the output of the object detection sensor 2, and transmits a command to photograph the gear to the edge PC 1. The PLC 3 is also communicatively connected to other production equipment installed in the factory, and transmits various command signals to each of the production equipment.

[0020] The camera 4 is provided at a predetermined position in a factory or the like so as to photograph the gear. The camera 4 includes a lens and an image sensor, and is, for example, a CMOS (complementary metal oxide semiconductor) camera or a CCD (charge-coupled device) camera. The camera 4 is connected to the edge PC1 by wire or wirelessly. The camera 4 photographs the gear teeth based on a command from the edge PC1 to generate a photographed image (image of the gear teeth). The output of the camera 4, i.e., the photographed image generated by the camera 4, is transmitted to the edge PC1. Note that a lighting device may be provided to illuminate the gear in order to obtain a clear photographed image.

[0021] The rotation device 5 has, for example, a holder that holds the gear to be inspected, and a drive unit (e.g., a stepping motor) that rotates the gear on the holder. The rotation device 5 rotates the gear around its central axis. The rotation device 5 is connected to the edge PC1 by wire or wirelessly. The rotation device 5 rotates the gear by a predetermined angle based on a command from the edge PC1. The camera 4 captures images of the gear teeth in synchronization with the rotation of the gear by the rotation device 5. That is, the camera 4 generates a still image of the gear teeth every time the gear rotates by a predetermined angle.

[0022] Fig. 2 is a functional block diagram of the processor 13 of the edge PC1. As shown in Fig. 2, the processor 13 has an imaging control unit 14, an image acquisition unit 15, an image extraction unit 16, and an abnormality determination unit 17. The imaging control unit 14, the image acquisition unit 15, the image extraction unit 16, and the abnormality determination unit 17 are functional modules that are realized by the processor 13 of the edge PC1 executing a computer program stored in the memory 12 of the edge PC1. Note that these functional modules may each be realized by a dedicated arithmetic circuit provided in the processor 13.

[0023] The imaging control unit 14 controls the imaging of the gear by the camera 4. Specifically, the imaging control unit 14 controls the phase (rotation angle) of the gear by the rotation device 5, and images the gear by the camera 4. When an imaging command is transmitted from the PLC 3 to the edge PC1, the imaging control unit 14 rotates the gear by the rotation device 5, while imaging the gear teeth by the camera 4.

[0024] The image acquisition unit 15 acquires the captured images generated by the camera 4. In this embodiment, the image acquisition unit 15 acquires a predetermined number of captured images generated by capturing images of the gear teeth when the gear is rotated by a predetermined angle. The predetermined angle is a phase shift amount of the gear that is allowed when determining whether the gear is abnormal, and is determined in advance.

[0025] The predetermined number is the number of captured images generated by the camera 4 in order to determine whether there is an abnormality in the gear, and is determined based on the predetermined angle and the number of teeth of the gear. The predetermined number is calculated, for example, by the following formula (1). Predetermined number = 360 / (number of gear teeth x predetermined angle) ... (1)

[0026] As can be seen from the above formula (1), the predetermined number increases as the predetermined angle decreases and as the number of teeth of the gear decreases. For example, when the predetermined angle is 1° and the number of teeth of the gear is 40, the predetermined number is 9. In this case, the imaging control unit 14 rotates the gear 8 times by 1° each time and captures images of the gear a total of 9 times, before the gear is rotated and after the gear is rotated by 1° each time.

[0027] The image extraction unit 16 extracts an inspection image suitable for gear abnormality determination from a predetermined number of captured images acquired by the image acquisition unit 15. In this embodiment, the image extraction unit 16 extracts the inspection image from the captured images by comparing the predetermined number of captured images with a master image. The master image is an image of a normal gear adjusted to a phase most suitable for gear abnormality determination, and is prepared in advance. The image extraction unit 16 extracts a captured image having a minimum positional deviation (e.g., deviation in the x and y directions) from the master image as the inspection image. As a specific example, the image extraction unit 16 extracts the inspection image from the predetermined number of captured images using an image matching method such as phase limited correlation. In this case, the image extraction unit 16 extracts a captured image having the highest similarity to the master image from the predetermined number of captured images as the inspection image.

[0028] The abnormality determination unit 17 determines the presence or absence of a gear abnormality using the inspection image extracted by the image extraction unit 16. For example, the abnormality determination unit 17 determines the presence or absence of a gear abnormality using a classifier that has been trained in advance to output the presence or absence of a gear abnormality from the data of the inspection image. Examples of such a classifier include machine learning models such as a neural network, a support vector machine, and a random forest.

[0029] As described above, in this embodiment, a necessary number of captured images are acquired in consideration of the allowable amount of the gear phase shift, and an abnormality in the gear is judged using an inspection image extracted from these. Therefore, since it is not necessary to photograph the gear after strictly adjusting the gear phase, it is possible to suppress a decrease in the accuracy of judging the abnormality in the gear due to a decrease in the adjustment accuracy of the gear phase. Furthermore, in this embodiment, an abnormality in the gear is judged using an inspection image extracted from a predetermined number of captured images instead of a difference image generated from the difference between the captured image after rotation and the captured image before rotation. Therefore, even if the same damage occurs on all the teeth of the gear, the damage shown in the inspection image can be detected as an abnormality. Therefore, according to this embodiment, an abnormality in the gear can be detected with high accuracy from the image of the gear.

[0030] 3 is a flowchart showing a control routine for the abnormality determination process in this embodiment. This control routine is repeatedly executed by the processor 13 of the edge PC1.

[0031] First, in step S101, the photography control unit 14 of the processor 13 determines whether or not a photography command has been received from the PLC 3. The PLC 3 transmits a photography command to the edge PC1 when the gear to be inspected is detected by the object detection sensor 2. If it is determined in step S101 that a photography command has not been received, this control routine ends. On the other hand, if it is determined in step S101 that a photography command has been received, this control routine proceeds to step S102.

[0032] In step S102, the photography control unit 14 photographs the gear teeth with the camera 4. The photographed image generated by the camera 4 is transmitted to the edge PC1, and the image acquisition unit 15 of the processor 13 stores the photographed image in, for example, the memory 12 of the edge PC1.

[0033] Next, in step S103, the imaging control unit 14 rotates the gear by a predetermined angle using the rotation device 5. The predetermined angle is the amount of phase shift of the gear that is permitted when determining whether the gear is abnormal, and is determined in advance.

[0034] Next, in step S104, the photography control unit 14 determines whether or not the number of captured images generated by the camera 4, i.e., the number of times photography has been performed by the camera 4, has reached a predetermined number. The predetermined number is determined based on a predetermined angle and the number of gear teeth, and is calculated, for example, by the above formula (1). If it is determined in step S104 that the number of captured images has not reached the predetermined number, this control routine returns to step S102, and steps S102 and S103 are executed again.

[0035] On the other hand, if it is determined in step S104 that the number of captured images has reached the predetermined number, the control routine proceeds to step S105. In step S105, the image extraction unit 16 of the processor 13 extracts an inspection image from the captured images by comparing the predetermined number of captured images with the master image using the method described above.

[0036] Next, in step S106, the abnormality determination unit 17 of the processor 13 performs preprocessing on the inspection image. For example, as preprocessing, the abnormality determination unit 17 performs color correction, resizing, normalization, noise removal, filtering, etc. When color correction is performed as preprocessing, for example, a master image with optimized luminance is prepared, and the abnormality determination unit 17 brings the luminance of the inspection image closer to the luminance of the master image.

[0037] Next, in step S107, the abnormality determination unit 17 determines whether or not there is an abnormality in the gear using the inspection image. The abnormality in the gear is a scratch, a dent, or the like that occurs on the surface of the gear. The result of the gear abnormality determination is displayed, for example, on the display of the edge PC1. The result of the gear abnormality determination may be transmitted to the PLC 3. After step S107, this control routine ends.

[0038] Note that the pre-processing of step S106 may be omitted. In the above control routine, an abnormality is determined for one tooth of the gear, but an abnormality may be determined for all teeth of the gear. In this case, the processing of steps S102 to S107 is repeated a number of times corresponding to the number of teeth of the gear.

[0039] Although the preferred embodiments of the present invention have been described above, the present invention is not limited to these embodiments, and various modifications and changes can be made within the scope of the claims. For example, communication between the edge PC1 and the peripheral devices may be performed wirelessly, and the edge PC1 may be provided outside the factory. [Explanation of symbols]

[0040] 1. Edge PC 13 Processors 14. Shooting control section 15 Image acquisition section 16 Image Extraction Section 17 Abnormality determination section

Claims

[Claim 1] A gear inspection device for inspecting a gear, comprising: an image acquisition unit that acquires a predetermined number of captured images generated by capturing images of the teeth of the gear when the gear is rotated by a predetermined angle at a time; an image extraction unit that extracts an inspection image from the photographed images by comparing each of the predetermined number of photographed images with a master image; an abnormality determination unit that determines whether or not there is an abnormality in the gear using the inspection image; Equipped with The predetermined number is determined based on the predetermined angle and the number of teeth of the gear.

Citation Information

Patent Citations

  • Visual examination processing system and program thereof

    JP2009109440A

  • Device and method for detecting position of target object

    JP2010191593A

  • Workpiece inspection apparatus and workpiece inspection method

    JP2012063268A

  • Inspection robot system

    JP2017100242A

  • Appearance inspection system

    JP2017172984A