KR102770142B1 - bolt inspection device using AI vision recognition - Google Patents
bolt inspection device using AI vision recognition Download PDFInfo
- Publication number
- KR102770142B1 KR102770142B1 KR1020220024202A KR20220024202A KR102770142B1 KR 102770142 B1 KR102770142 B1 KR 102770142B1 KR 1020220024202 A KR1020220024202 A KR 1020220024202A KR 20220024202 A KR20220024202 A KR 20220024202A KR 102770142 B1 KR102770142 B1 KR 102770142B1
- Authority
- KR
- South Korea
- Prior art keywords
- bolt
- camera
- inspection device
- vision recognition
- transported
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 34
- 238000005096 rolling process Methods 0.000 claims abstract description 10
- 230000002950 deficient Effects 0.000 claims abstract description 8
- 238000012546 transfer Methods 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 2
- 230000007547 defect Effects 0.000 abstract description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
- G01B11/25—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures by projecting a pattern, e.g. one or more lines, moiré fringes on the object
- G01B11/2518—Projection by scanning of the object
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/9501—Semiconductor wafers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/30—Polynomial surface description
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/94—Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/10—Scanning
- G01N2201/104—Mechano-optical scan, i.e. object and beam moving
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Chemical & Material Sciences (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Algebra (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
본 발명은 AI 비전인식을 이용한 볼트 검사장치에 관한 것으로, 보다 상세하게는 볼트의 외주면을 연속한 이미지를 AI 알고리즘을 통해 3차원으로 분석하여 불량 여부를 검사하기 위한 AI 비전인식을 이용한 볼트 검사장치에 관한 것이다.
또한, 볼트를 순차적으로 공급하는 공급부와 상기 공급부로부터 공급된 볼트가 구르면서 이송되는 이송부와 상기 이송부에서 이송되는 볼트를 촬영하기 위한 카메라와 상기 카메라를 통해 촬영된 이미지를 바탕으로 볼트의 불량 여부를 판단하는 제어부를 포함하는 것을 특징으로 한다.The present invention relates to a bolt inspection device using AI vision recognition, and more specifically, to a bolt inspection device using AI vision recognition for analyzing a continuous image of the outer surface of a bolt in three dimensions using an AI algorithm to inspect for defects.
In addition, it is characterized by including a supply unit that sequentially supplies bolts, a transport unit in which the bolts supplied from the supply unit are transported while rolling, a camera for photographing the bolts transported from the transport unit, and a control unit that determines whether the bolts are defective based on the image photographed by the camera.
Description
본 발명은 AI 비전인식을 이용한 볼트 검사장치에 관한 것으로, 보다 상세하게는 볼트의 외주면을 연속한 이미지를 AI 알고리즘을 통해 3차원으로 분석하여 불량 여부를 검사하기 위한 AI 비전인식을 이용한 볼트 검사장치에 관한 것이다.The present invention relates to a bolt inspection device using AI vision recognition, and more specifically, to a bolt inspection device using AI vision recognition for analyzing a continuous image of the outer surface of a bolt in three dimensions using an AI algorithm to inspect for defects.
전자 산업의 비약적인 발전 및 수요 증대에 힘입어 체결요소 부품도 전자제품의 트렌드를 따라 소형화, 정밀화되고 있다.With the rapid development and increasing demand in the electronics industry, fastener components are also becoming smaller and more precise, following the trend of electronic products.
이러한 전자제품의 고품질화에는 체결요소 부품의 품질 신뢰도 향상도 수반하게 되었으며, 체결요소 부품의 검사는 품질관리의 중요한 부분으로 정착되고 있다.The improvement in the quality of these electronic products has also led to an improvement in the quality reliability of fastening components, and inspection of fastening components is becoming established as an important part of quality control.
체결요소 부품의 검사 방식으로서 일찍이 육안 검사법이 시행되고 있으나, 인력에 의존하는 것이므로 시간과 비용의 소요가 과대하며 신뢰도를 보장하기 어려운 문제점이 있었다.Visual inspection has been implemented as an inspection method for fastening elements, but because it relies on manpower, it takes a lot of time and money and has the problem of making it difficult to guarantee reliability.
특히, 소형화된 체결요소 부품은 육안으로 직접 검사하기 매우 어려운 문제점이 있었다.In particular, miniaturized fastening elements had the problem of being very difficult to inspect directly with the naked eye.
이에 따라, 한국공개특허 제10-2020-0089077호 "비전 검사장치 및 이를 포함하는 비전 검사시스템"과 같이 카메라를 이용한 비전 검사 방법이 개발되었으나, 볼트의 한쪽 방향만 촬영이 가능하거나, 도 1에 도시된 바와 같이 볼트(100)를 이송시키기 위한 부재(102)에 의해 볼트(100)의 외주면 일부가 가려지는 문제점으로 인하여 볼트(100)의 외주면 전체를 검사하기 어려운 문제점이 있었다.Accordingly, a vision inspection method using a camera has been developed, such as in Korean Patent Publication No. 10-2020-0089077, “Vision Inspection Device and Vision Inspection System Including the Same,” but there was a problem that it was difficult to inspect the entire outer surface of the bolt (100) due to the problem that only one side of the bolt could be photographed or a part of the outer surface of the bolt (100) was covered by a member (102) for transporting the bolt (100), as shown in FIG. 1.
이에 따라, 볼트의 외주면 전체를 검사하기 위한 기술 개발의 필요성이 제기되고 있다.Accordingly, the need for technology development to inspect the entire outer surface of a bolt is being raised.
본 발명의 목적은 상술한 바와 같은 문제점을 해결하기 위해 안출된 것으로서, 볼트의 외주면 전체를 촬영하여 검사하기 위한 AI 비전인식을 이용한 볼트 검사장치를 제공하는 것이다.The purpose of the present invention is to solve the problems described above, and to provide a bolt inspection device using AI vision recognition for photographing and inspecting the entire outer surface of a bolt.
상기 목적을 달성하기 위해 본 발명에 따른 AI 비전인식을 이용한 볼트 검사장치는 볼트를 순차적으로 공급하는 공급부와 상기 공급부로부터 공급된 볼트가 구르면서 이송되는 이송부와 상기 이송부에서 이송되는 볼트를 촬영하기 위한 카메라와 상기 카메라를 통해 촬영된 이미지를 바탕으로 볼트의 불량 여부를 판단하는 제어부를 포함하는 것을 특징으로 한다.In order to achieve the above purpose, the bolt inspection device using AI vision recognition according to the present invention is characterized by including a supply unit that sequentially supplies bolts, a transport unit in which the bolts supplied from the supply unit are rolled and transported, a camera for photographing the bolts transported from the transport unit, and a control unit that determines whether the bolts are defective based on the image photographed by the camera.
또한, 상기 이송부는 바닥면에 소정의 깊이를 가지는 홈이 이송방향을 따라 형성되어 볼트의 헤드가 걸쳐진 상태로 이송되는 것을 특징으로 한다.In addition, the transport unit is characterized in that a groove having a predetermined depth is formed on the bottom surface along the transport direction so that the head of the bolt is transported while hanging over it.
또한, 상기 이송부는 원추 형태로 볼트가 나선 형태로 굴러 중앙에서 낙하하도록 구성되며, 바닥면에 소정의 깊이를 가지는 홈이 나선 형태로 이송방향을 따라 형성되어 볼트의 헤드가 걸쳐진 상태로 이송되는 것을 특징으로 한다.In addition, the transport member is configured to have a cone shape so that the bolt rolls in a spiral shape and falls from the center, and a groove having a predetermined depth is formed in a spiral shape along the transport direction on the bottom surface so that the head of the bolt is transported while hanging on it.
또한, 상기 카메라는 이송부에서 굴러가는 볼트를 연속 촬영하는 방법으로 볼트의 외주면 전체를 촬영하는 것을 특징으로 한다.In addition, the camera is characterized by photographing the entire outer surface of the bolt by continuously photographing the bolt rolling in the conveying section.
또한, 상기 카메라는 볼트의 측면을 촬영하는 제1 카메라와 볼트의 상면을 촬영하는 제2 카메라로 구성된 것을 특징으로 한다.In addition, the camera is characterized by comprising a first camera for photographing the side of the bolt and a second camera for photographing the upper surface of the bolt.
또한, 상기 제2 카메라는 굴러가는 볼트의 상면을 소정의 각도로 비스듬하게 촬영하여 헤드에 형성된 소켓의 내부를 연속 촬영하도록 구성된 것을 특징으로 한다.In addition, the second camera is characterized by being configured to photograph the upper surface of the rolling bolt obliquely at a predetermined angle and continuously photograph the inside of the socket formed in the head.
상술한 바와 같이, 본 발명에 따른 AI 비전인식을 이용한 볼트 검사장치에 의하면, 이송부에 의해 순차적으로 굴러가는 볼트를 카메라를 통해 연속 촬영하여 볼트의 외주면 전체를 촬영 및 검사할 수 있는 효과가 있다.As described above, according to the bolt inspection device using AI vision recognition according to the present invention, there is an effect in which the entire outer surface of the bolt can be photographed and inspected by continuously photographing bolts that are sequentially rolled by a conveying unit through a camera.
도 1은 종래의 검사장치를 도시한 도면.
도 2는 본 발명에 따른 AI 비전인식을 이용한 볼트 검사장치를 도시한 도면.
도 3은 본 발명에 따른 AI 비전인식을 이용한 볼트 검사장치의 홈에 걸쳐진 상태로 이송되는 볼트를 도시한 도면.
도 4은 본 발명에 따른 AI 비전인식을 이용한 볼트 검사장치의 홈에 걸쳐진 볼트를 도시한 단면도.
도 5는 본 발명에 따른 AI 비전인식을 이용한 볼트 검사장치의 제 2카메라를 통해 촬영된 이미지를 도시한 도면.
도 6은 본 발명에 따른 AI 비전인식을 이용한 볼트 검사장치의 AI 연산을 간단하게 도시한 도면.Figure 1 is a drawing illustrating a conventional inspection device.
Figure 2 is a drawing illustrating a bolt inspection device using AI vision recognition according to the present invention.
FIG. 3 is a drawing illustrating a bolt being transported while hanging over a groove of a bolt inspection device using AI vision recognition according to the present invention.
FIG. 4 is a cross-sectional view illustrating a bolt spanning a groove of a bolt inspection device using AI vision recognition according to the present invention.
FIG. 5 is a drawing illustrating an image captured through a second camera of a bolt inspection device using AI vision recognition according to the present invention.
Figure 6 is a drawing simply illustrating the AI operation of a bolt inspection device using AI vision recognition according to the present invention.
본 명세서에 개시되어 있는 본 발명의 개념에 따른 실시 예들에 대해서 특정한 구조적 또는 기능적 설명은 단지 본 발명의 개념에 따른 실시 예들을 설명하기 위한 목적으로 예시된 것으로서, 본 발명의 개념에 따른 실시 예들은 다양한 형태들로 실시될 수 있으며 본 명세서에 설명된 실시 예들에 한정되지 않는다.Any specific structural or functional descriptions of embodiments according to the concept of the present invention disclosed in this specification are merely illustrative for the purpose of explaining embodiments according to the concept of the present invention, and embodiments according to the concept of the present invention may be implemented in various forms and are not limited to the embodiments described in this specification.
본 발명의 개념에 따른 실시 예들은 다양한 변경들을 가할 수 있고 여러 가지 형태들을 가질 수 있으므로 실시 예들을 도면에 예시하고 본 명세서에서 상세하게 설명하고자 한다. 그러나, 이는 본 발명의 개념에 따른 실시 예들을 특정한 개시 형태들에 대해 한정하려는 것이 아니며, 본 발명의 사상 및 기술 범위에 포함되는 모든 변경, 균등물, 또는 대체물을 포함한다.Since embodiments according to the concept of the present invention can have various changes and can have various forms, embodiments are illustrated in the drawings and described in detail in the present specification. However, this is not intended to limit embodiments according to the concept of the present invention to specific disclosed forms, but includes all modifications, equivalents, or substitutes included in the spirit and technical scope of the present invention.
이하, 본 발명의 바람직한 실시예를 첨부된 도면을 참조하여 설명하면 다음과 같다.Hereinafter, preferred embodiments of the present invention will be described with reference to the attached drawings.
도 2는 본 발명에 따른 AI 비전인식을 이용한 볼트 검사장치를 도시한 도면이며, 도 3은 본 발명에 따른 AI 비전인식을 이용한 볼트 검사장치의 홈에 걸쳐진 상태로 이송되는 볼트를 도시한 도면이고, 도 4은 본 발명에 따른 AI 비전인식을 이용한 볼트 검사장치의 홈에 걸쳐진 볼트를 도시한 단면도이며, 도 5는 본 발명에 따른 AI 비전인식을 이용한 볼트 검사장치의 제 2카메라를 통해 촬영된 이미지를 도시한 도면이고, 도 6은 본 발명에 따른 AI 비전인식을 이용한 볼트 검사장치의 AI 연산을 간단하게 도시한 도면이다.FIG. 2 is a drawing illustrating a bolt inspection device using AI vision recognition according to the present invention, FIG. 3 is a drawing illustrating a bolt being transported while being hung on a groove of a bolt inspection device using AI vision recognition according to the present invention, FIG. 4 is a cross-sectional view illustrating a bolt hanging on a groove of a bolt inspection device using AI vision recognition according to the present invention, FIG. 5 is a drawing illustrating an image captured through a second camera of a bolt inspection device using AI vision recognition according to the present invention, and FIG. 6 is a drawing simply illustrating an AI operation of a bolt inspection device using AI vision recognition according to the present invention.
도 2에 도시된 바와 같이, 본 발명에 따른 AI 비전인식을 이용한 볼트 검사장치는 호퍼, 볼피더, 선형피더 등을 통해 볼트(100)를 일정한 방향으로 순차적으로 공급하는 공급부(1)와 상기 공급부(1)로부터 공급된 볼트(100)가 구르면서 이송되는 이송부(2)와 상기 이송부(2)에서 이송되는 볼트(100)를 촬영하기 위한 카메라(3)와 상기 카메라(3)를 통해 촬영된 이미지를 바탕으로 이송부(2)에서 이송되는 볼트(100)의 불량 여부를 판단하는 제어부(미도시)를 포함하여 구성된다.As illustrated in FIG. 2, the bolt inspection device using AI vision recognition according to the present invention comprises a supply unit (1) that sequentially supplies bolts (100) in a certain direction through a hopper, a ball feeder, a linear feeder, etc., a transport unit (2) in which the bolts (100) supplied from the supply unit (1) are rolled and transported, a camera (3) for photographing the bolts (100) transported from the transport unit (2), and a control unit (not illustrated) that determines whether the bolts (100) transported from the transport unit (2) are defective based on the images photographed by the camera (3).
또한, 상기 카메라(3)는 상부에서 볼트(100)의 측면을 촬영하는 제1 카메라(3a)와 볼트(100)의 헤드 상면을 촬영하는 제2 카메라(3b)로 구성될 수 있다.Additionally, the camera (3) may be composed of a first camera (3a) that photographs the side of the bolt (100) from above and a second camera (3b) that photographs the upper surface of the head of the bolt (100).
또한, 상기 카메라(3)는 도 3에 도시된 바와 같이 이송부(2)에서 굴러가는 볼트(100)를 연속 촬영하는 방법으로 볼트(100)의 외주면 전체를 촬영하게 된다.In addition, the camera (3) continuously photographs the bolt (100) rolling on the conveyor (2) as shown in Fig. 3, thereby photographing the entire outer surface of the bolt (100).
이를 통해, 볼트(100)를 촬영하는 동안 특정 부분이 가려지지 않고, 외주면 전체를 촬영할 수 있다.Through this, when shooting a bolt (100), a specific part is not covered and the entire outer surface can be shot.
이때, 상기 이송부(2)는 도 2 내지 도 4에 도시된 바와 같이 볼트(100)가 항상 같은 경로를 따라 굴러갈 수 있도록 바닥면에 소정의 깊이를 가지는 홈(4)이 볼트(100)가 굴러가는 이송방향을 따라 형성됨으로써 볼트(100)의 헤드가 홈(4)에 걸쳐진 상태로 굴러서 이송되도록 구성될 수 있다.At this time, the transfer unit (2) may be configured such that a groove (4) having a predetermined depth is formed on the bottom surface along the transfer direction in which the bolt (100) rolls so that the bolt (100) can always roll along the same path as shown in FIGS. 2 to 4, thereby allowing the head of the bolt (100) to roll and be transferred while hanging over the groove (4).
또한, 상기 이송부(2)는 원추 형태로 볼트(100)가 나선 형태로 굴러 중앙에서 낙하하도록 구성될 수 있으며, 이때 바닥면에 형성되는 홈(4)은 나선 형태로 이송방향을 따라 형성됨이 바람직하다.In addition, the above-mentioned transport part (2) may be configured to have a cone shape so that the bolt (100) rolls in a spiral shape and falls from the center, and at this time, it is preferable that the groove (4) formed on the bottom surface is formed in a spiral shape along the transport direction.
또 다른 실시예로써, 상기 이송부(2)가 이송방향을 향해 하향으로 경사진 직선 형태를 가지며, 홈(4)도 이송방향을 따라 직선형태로 구성될 수도 있다.As another embodiment, the transport section (2) may have a straight shape that slopes downward in the transport direction, and the groove (4) may also be configured in a straight shape along the transport direction.
또한, 도 5에 도시된 바와 같이 상기 제2 카메라(3b)는 굴러가는 볼트(100)의 헤드 상면에 수직한 방향에서 볼트(100)를 촬영하도록 구성될 수 있으며, 이때홈에 걸쳐진 헤드의 일부가 가려질 수 있으나, 제2 카메라(3b)를 통해 굴러가는 볼트(100)를 연속 촬영하여 볼트(100)의 상면 전체를 촬영 및 검사하게 된다.In addition, as shown in FIG. 5, the second camera (3b) can be configured to photograph the bolt (100) in a direction perpendicular to the upper surface of the head of the rolling bolt (100). At this time, a part of the head that is over the groove may be covered, but by continuously photographing the rolling bolt (100) through the second camera (3b), the entire upper surface of the bolt (100) is photographed and inspected.
또는, 상기 제2 카메라(3b)가 볼트(100)의 상면을 소정의 각도로 비스듬하게 촬영하여 볼트(100)의 상면 전체를 한번에 촬영하거나, 볼트(100)의 헤드에 형성된 소켓(101)의 내부를 연속 촬영하여 제어부가 소켓(101) 내부의 가공 불량 여부를 검사할 수 있도록 실시될 수도 있다.Alternatively, the second camera (3b) may be configured to photograph the upper surface of the bolt (100) at a predetermined angle to photograph the entire upper surface of the bolt (100) at once, or to continuously photograph the inside of the socket (101) formed in the head of the bolt (100) so that the control unit can inspect the inside of the socket (101) for processing defects.
이와 같이, 상기 카메라(3)를 통해 촬영된 이미지를 바탕으로 제어부가 볼트의 형상을 3차원으로 복원하여 기 설정된 데이트와 비교 연산하여 볼트의 불량 여부를 판단하게 된다.In this way, based on the image captured through the camera (3), the control unit restores the shape of the bolt in three dimensions and compares it with the preset date to determine whether the bolt is defective.
이때, 상기 제어부는 도 6에 도시된 바와 같이 카메라를 통해 촬영된 이미지 중 누락된 방향의 형상은 Denoising Auto-Encoding 기법을 활용한 AI 딥러닝을 통해 누락 이미지를 복원한 후 불량 여부를 판단하도록 구성될 수 있다.At this time, the control unit can be configured to determine whether or not a shape in a missing direction among images captured by the camera, as shown in Fig. 6, is defective after restoring the missing image through AI deep learning using the Denoising Auto-Encoding technique.
이상과 같이 본 발명은 첨부된 도면을 참조하여 바람직한 실시예를 중심으로 기술되었지만 당업자라면 이러한 기재로부터 본 발명의 범주를 벗어남이 없이 많은 다양한 자명한 변형이 가능하다는 것은 명백하다. 따라서 본 발명의 범주는 이러한 많은 변형의 예들을 포함하도록 기술된 청구범위에 의해서 해석되어져야 한다.As described above, the present invention has been described with reference to the attached drawings, focusing on preferred embodiments, but it is obvious to those skilled in the art that many obvious modifications can be made without departing from the scope of the present invention from this description. Accordingly, the scope of the present invention should be interpreted by the claims, which are described to include examples of many such modifications.
1 : 공급부
2 : 이송부
3 : 카메라
4 : 홈
100 : 볼트
101 : 소켓1: Supply Department
2: Transfer section
3: Camera
4 : Home
100 : Volt
101 : Socket
Claims (8)
상기 공급부로부터 공급된 볼트가 구르면서 이송되는 이송부와;
상기 이송부에서 이송되는 볼트를 촬영하기 위한 카메라와;
상기 카메라를 통해 촬영된 이미지를 바탕으로 볼트의 불량 여부를 판단하는 제어부를 포함하며,
상기 이송부는
원추 형태로 볼트가 나선 형태로 굴러 중앙에서 낙하하도록 구성되며,
바닥면에 소정의 깊이를 가지는 홈이 나선 형태로 이송방향을 따라 형성되어 볼트의 헤드가 걸쳐진 상태로 이송되는 것을 특징으로 하는
AI 비전인식을 이용한 볼트 검사장치.
A supply unit that supplies bolts sequentially;
A transport section in which bolts supplied from the above supply section are transported while rolling;
A camera for photographing the bolts being transported in the above transport section;
It includes a control unit that determines whether the bolt is defective based on the image captured by the above camera.
The above transfer part
It is designed so that the bolt rolls in a spiral shape in the shape of a cone and falls from the center.
It is characterized in that a groove having a predetermined depth on the bottom surface is formed in a spiral shape along the transport direction and the head of the bolt is transported while hanging over it.
Bolt inspection device using AI vision recognition.
상기 공급부로부터 공급된 볼트가 구르면서 이송되는 이송부와;
상기 이송부에서 이송되는 볼트를 촬영하기 위한 카메라와;
상기 카메라를 통해 촬영된 이미지를 바탕으로 볼트의 형상을 3차원으로 복원하여 볼트의 불량 여부를 판단하는 제어부를 포함하며,
상기 이송부는
원추 형태로 볼트가 나선 형태로 굴러 중앙에서 낙하하도록 구성되며,
바닥면에 소정의 깊이를 가지는 홈이 나선 형태로 이송방향을 따라 형성되어 볼트의 헤드가 걸쳐진 상태로 이송되는 것을 특징으로 하는
AI 비전인식을 이용한 볼트 검사장치.
A supply unit that supplies bolts sequentially;
A transport section in which bolts supplied from the above supply section are transported while rolling;
A camera for photographing the bolts being transported in the above transport section;
It includes a control unit that restores the shape of the bolt in three dimensions based on the image captured by the above camera and determines whether the bolt is defective.
The above transfer part
It is designed so that the bolt rolls in a spiral shape in the shape of a cone and falls from the center.
It is characterized in that a groove having a predetermined depth on the bottom surface is formed in a spiral shape along the transport direction and the head of the bolt is transported while hanging over it.
Bolt inspection device using AI vision recognition.
상기 제어부는
카메라를 통해 촬영된 이미지 중 누락된 방향의 형상은 Denoising Auto-Encoding 기법을 활용한 AI 딥러닝을 통해 누락 이미지를 복원한 후 불량 여부를 판단하는 것을 특징으로 하는
AI 비전인식을 이용한 볼트 검사장치.
In paragraph 1 or 2,
The above control unit
The missing direction shape among the images captured by the camera is restored through AI deep learning using the Denoising Auto-Encoding technique, and then it is judged whether it is defective or not.
Bolt inspection device using AI vision recognition.
상기 이송부는
바닥면에 소정의 깊이를 가지는 홈이 이송방향을 따라 형성되어 볼트의 헤드가 걸쳐진 상태로 이송되는 것을 특징으로 하는
AI 비전인식을 이용한 볼트 검사장치.
In paragraph 1 or 2,
The above transfer part
It is characterized in that a groove having a predetermined depth is formed along the transport direction on the bottom surface and the head of the bolt is transported while hanging over it.
Bolt inspection device using AI vision recognition.
상기 카메라는
이송부에서 굴러가는 볼트를 연속 촬영하는 방법으로 볼트의 외주면 전체를 촬영하는 것을 특징으로 하는
AI 비전인식을 이용한 볼트 검사장치.
In paragraph 1 or 2,
The above camera
A method of continuously photographing a bolt rolling in a conveyor belt, characterized by photographing the entire outer surface of the bolt.
Bolt inspection device using AI vision recognition.
상기 카메라는
볼트의 측면을 촬영하는 제1 카메라와;
볼트의 상면을 촬영하는 제2 카메라로 구성된 것을 특징으로 하는
AI 비전인식을 이용한 볼트 검사장치.
In paragraph 1 or 2,
The above camera
A first camera takes pictures of the side of the bolt;
characterized by a second camera that photographs the upper surface of the bolt.
Bolt inspection device using AI vision recognition.
상기 카메라는
볼트의 측면을 촬영하는 제1 카메라와;
볼트의 상면을 촬영하는 제2 카메라로 구성되며,
상기 제2 카메라는
굴러가는 볼트의 상면을 소정의 각도로 비스듬하게 촬영하여 헤드에 형성된 소켓의 내부를 연속 촬영하도록 구성된 것을 특징으로 하는
AI 비전인식을 이용한 볼트 검사장치.
In paragraph 1 or 2,
The above camera
A first camera takes pictures of the side of the bolt;
It consists of a second camera that photographs the upper surface of the bolt.
The second camera above
It is characterized by being configured to photograph the upper surface of a rolling bolt obliquely at a predetermined angle and continuously photograph the inside of a socket formed in the head.
Bolt inspection device using AI vision recognition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020220024202A KR102770142B1 (en) | 2022-02-24 | 2022-02-24 | bolt inspection device using AI vision recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020220024202A KR102770142B1 (en) | 2022-02-24 | 2022-02-24 | bolt inspection device using AI vision recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| KR20230126861A KR20230126861A (en) | 2023-08-31 |
| KR102770142B1 true KR102770142B1 (en) | 2025-02-20 |
Family
ID=87847689
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| KR1020220024202A Active KR102770142B1 (en) | 2022-02-24 | 2022-02-24 | bolt inspection device using AI vision recognition |
Country Status (1)
| Country | Link |
|---|---|
| KR (1) | KR102770142B1 (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004354367A (en) * | 2003-05-06 | 2004-12-16 | Yutaka:Kk | Inspection device and method for screw equipped with head, and detection method for crack of punch |
| KR101079164B1 (en) * | 2009-02-27 | 2011-11-02 | 주식회사 심텍 | Arranging and seperating device for router bit |
| JP2012025560A (en) | 2010-07-26 | 2012-02-09 | Tdk Corp | Parts feeder device |
| KR102150673B1 (en) | 2018-10-02 | 2020-09-01 | (주)지엘테크 | Inspection method for appearance badness and inspection system for appearance badness |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101366190B1 (en) * | 2012-02-03 | 2014-03-14 | 주식회사 서울금속 | Vision inspection apparatus having side surface inspecting function |
| WO2019164382A1 (en) * | 2018-02-26 | 2019-08-29 | 주식회사 고영테크놀러지 | Method for inspecting mounting state of component, printed circuit board inspection apparatus, and computer readable recording medium |
| KR20200089077A (en) | 2019-01-16 | 2020-07-24 | (주)아이피에스오토 | Vision inspection device and vision inspection system comprising it |
-
2022
- 2022-02-24 KR KR1020220024202A patent/KR102770142B1/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004354367A (en) * | 2003-05-06 | 2004-12-16 | Yutaka:Kk | Inspection device and method for screw equipped with head, and detection method for crack of punch |
| KR101079164B1 (en) * | 2009-02-27 | 2011-11-02 | 주식회사 심텍 | Arranging and seperating device for router bit |
| JP2012025560A (en) | 2010-07-26 | 2012-02-09 | Tdk Corp | Parts feeder device |
| KR102150673B1 (en) | 2018-10-02 | 2020-09-01 | (주)지엘테크 | Inspection method for appearance badness and inspection system for appearance badness |
Also Published As
| Publication number | Publication date |
|---|---|
| KR20230126861A (en) | 2023-08-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TW201640101A (en) | Device for examining surface defect in hot-dipped steel plate, and method for examining surface defect | |
| WO2019138930A1 (en) | Tablet inspection method and tablet inspection device | |
| WO2017141813A1 (en) | Egg surface inspection apparatus | |
| US20120105624A1 (en) | Method and device for defect inspection in separated transparent and/or semi-transparent body | |
| TW202403293A (en) | Apparatus and method for inspecting a glass sheet | |
| KR102770142B1 (en) | bolt inspection device using AI vision recognition | |
| JP6752986B1 (en) | Tube container inspection device | |
| JP7075218B2 (en) | Tablet inspection method and tablet inspection equipment | |
| JPWO2023171625A5 (en) | ||
| JP6521227B2 (en) | Parts inspection device | |
| JPH1035862A (en) | Carrying device and visual inspection device | |
| JP4050942B2 (en) | Appearance inspection device | |
| CN113554588A (en) | Product flaw detection device and method | |
| JP7083646B2 (en) | Tablet inspection method and tablet inspection equipment | |
| JP3974015B2 (en) | Item inspection system | |
| JP2000266514A (en) | Method and device for inspecting metallic sheet | |
| WO2011101893A1 (en) | Method and device for detecting flaw on surface of flexible object to be tested | |
| JP6980538B2 (en) | Tablet inspection method and tablet inspection equipment | |
| JP2014038014A (en) | Paper dust adhesion amount inspection method and paper dust adhesion amount inspection device | |
| JP2000266685A (en) | Method and apparatus for visual inspection of object | |
| JPH11241999A (en) | Flat tablet side inspection device and appearance inspection device equipped with the side inspection device | |
| TW201804980A (en) | Method for generating template for solid preparation, computer-readable storage media storing program for generating template for solid preparation, method for inspecting print on solid preparation, and device for inspecting print on solid preparation | |
| JP4135367B2 (en) | Defect detection method | |
| JP2025084454A (en) | Inspection Systems | |
| TWM587271U (en) | Automatic screw inspection device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PA0109 | Patent application |
Patent event code: PA01091R01D Comment text: Patent Application Patent event date: 20220224 |
|
| PA0201 | Request for examination | ||
| PN2301 | Change of applicant |
Patent event date: 20220302 Comment text: Notification of Change of Applicant Patent event code: PN23011R01D |
|
| PG1501 | Laying open of application | ||
| E701 | Decision to grant or registration of patent right | ||
| PE0701 | Decision of registration |
Patent event code: PE07011S01D Comment text: Decision to Grant Registration Patent event date: 20250210 |
|
| PG1601 | Publication of registration |