KR20160136905A - Bolt-loosening Detection Method and Computer Program Thereof - Google Patents
Bolt-loosening Detection Method and Computer Program Thereof Download PDFInfo
- Publication number
- KR20160136905A KR20160136905A KR1020150071128A KR20150071128A KR20160136905A KR 20160136905 A KR20160136905 A KR 20160136905A KR 1020150071128 A KR1020150071128 A KR 1020150071128A KR 20150071128 A KR20150071128 A KR 20150071128A KR 20160136905 A KR20160136905 A KR 20160136905A
- Authority
- KR
- South Korea
- Prior art keywords
- image
- nut
- bolt
- extracting
- joint plate
- Prior art date
Links
- 238000001514 detection method Methods 0.000 title claims description 37
- 238000004590 computer program Methods 0.000 title claims description 19
- 238000000034 method Methods 0.000 claims abstract description 41
- 238000000605 extraction Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000003702 image correction Methods 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Images
Classifications
-
- 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
- G01B11/26—Measuring arrangements characterised by the use of optical techniques for measuring angles or tapers; for testing the alignment of axes
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16B—DEVICES FOR FASTENING OR SECURING CONSTRUCTIONAL ELEMENTS OR MACHINE PARTS TOGETHER, e.g. NAILS, BOLTS, CIRCLIPS, CLAMPS, CLIPS OR WEDGES; JOINTS OR JOINTING
- F16B39/00—Locking of screws, bolts or nuts
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Data Mining & Analysis (AREA)
- Computational Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Operations Research (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Mechanical Engineering (AREA)
- Image Analysis (AREA)
Abstract
According to an embodiment of the present invention, there is provided a method of detecting bolt loosening in which each step is performed in an arithmetic unit, comprising: an edge extracting step of extracting an edge from a nut image; A straight line detecting step of detecting a straight line component from the image information from which the edge is extracted; And a bolt loosening determination step of calculating a rotation angle of the nut from the slope of the detected straight line and comparing the rotation angle of the calculated nut with the angle of the previously stored nut to determine whether the bolt is loosened.
Description
The present invention relates to a bolt loosening detection method and a computer program. More particularly, the present invention relates to a bolt loosening detection method and a computer program capable of extracting a rotation angle of a nut fastened to a bolt and determining whether the bolt is loosened or not.
Since 2000, many new bridges have been completed in Korea, and Korea Highway Corporation reported that bolt defects occurred in 33.3% of bridges in operation.
Also, bolts are often used for connection of members not only in bridges but also in construction, machinery, and aviation fields. Accurate diagnosis and monitoring are necessary because the defect in the bolt can cause direct collapse of the structure.
However, the visual inspection method used as the bolt loosening detection method can not be confirmed until the bolt is completely eliminated. The impact hammer method and the torque method are dependent on the experience and subjectivity of the inspector, and only a small number of samples are inspected. .
In order to solve the problems of these methods, techniques using a negative elasticity effect, ultrasonic wave, electro-dynamic-impedance, and potential difference have been developed, but it is necessary to attach a sensor and only a small number of bolts per sensor can be inspected. There is a problem in that it is not used in a large-scale structure.
Accordingly, the present inventor overcame the disadvantages of conventional bolt loosening inspection and monitoring techniques and developed a bolt loosening detection method and a computer program according to the present invention utilizing the advantages of image processing technology.
It is an object of the present invention to provide a bolt loosening detection method and a computer program.
Another object of the present invention is to provide a bolt loosening detection method and a computer program capable of easily determining whether a bolt loosens by using a rotation angle of a nut to detect whether or not a bolt loosens.
It is still another object of the present invention to provide a bolt loosening detection method and a computer program capable of determining whether a bolt is loosened with a minimum cost and in a short time using an image technique.
These and other objects of the present invention can be achieved by a bolt loosening detection method and a computer program according to the present invention.
A method of detecting a bolt loosening according to an embodiment of the present invention is a method in which each step is performed in a computing device, the method comprising: an edge extraction step of extracting an edge from a nut image; A straight line detecting step of detecting a straight line component from the image information from which the edge is extracted; And a bolt loosening determination step of determining the loosening of the bolt by calculating the rotation angle of the nut from the slope of the detected straight line and comparing the calculated rotation angle of the nut with the angle of the previously stored nut.
In the bolt loosening determination step, the rotation angle of the nut can be calculated using the following equation.
Here, θn is the rotation angle of the nut, θ is the slope of the orthogonal line to the origin of the detected straight line, and rem [] is an operator representing the remainder after division.
The method may further include a joint plate image input step including a plurality of nut images before the edge extraction step and a nut image extraction step of extracting an individual nut image from the joint plate image.
Further, it may further include an image correcting step of correcting the perspective of the joint plate image input between the joint plate image input step and the nut image extracting step to derive the front image.
The coordinates of the edge of the joint plate are extracted, and the coordinates of the edge of the joint plate are compared with the coordinates of the edge of the joint plate stored in the storage unit of the arithmetic unit. Then, The frontal image can be derived by correcting the perspective distortion of the plate image.
The frontal image can be derived by correcting so that the side of the joint plate is parallel to the side of the image and the longitudinal side of the joint plate is parallel to the longitudinal side of the image.
In the step of extracting the nut image, the circular shape of the end portion of the bolt is extracted from the input joint plate image, and a square image of n times the predetermined circular diameter centered on the center of the extracted circular shape is extracted as an individual nut image .
In addition, the nut image extracting step may extract the individual nut images by equally dividing the input plate images inputted according to the bolt arrangement information stored in the storage unit of the computing device.
In the nut image extracting step, the uniformly divided image is converted into a gray image, the converted gray image is converted into a monochrome image having a color value of 1 or 0 by using a preset level value, It is possible to extract the image of the position where the maximum value is obtained as the individual nut image.
It can be determined that the bolt is not loosened when the angle difference between the rotation angle of the nut calculated in the bolt loosening determination step and the pre-stored nut is within a predetermined angle.
A computer program according to an embodiment of the present invention is a computer program for causing a computer to execute the steps of a bolt removal detecting method according to an embodiment of the present invention.
The present invention provides a bolt loosening detection method and a computer program capable of determining the loosening of a large number of bolts at a minimum cost and in a short time by using a rotation angle of a nut to detect whether a bolt is loosened .
1 is a schematic view showing a method of detecting a bolt loosening according to the present invention.
2 is a flowchart of a bolt loosening detection method according to an embodiment of the present invention.
3 is a view showing an edge extracted from an input nut image.
4 is a view showing the principle of measuring the rotation angle of the nut.
5 is a flowchart of a bolt loosening detection method according to another embodiment of the present invention.
6 is a view showing an exemplary joint plate image.
7 is a view showing extracting a joint plate from the input image of the joint plate.
FIG. 8 is a diagram showing a distorted frontal image derived from the extracted joint plate image. FIG.
FIG. 9 is a view showing extraction of an individual nut image by evenly dividing a joint plate image. FIG.
FIG. 10 is a diagram showing extraction of an individual nut image by removing ambient noise.
11 is a view showing another embodiment for extracting an individual nut image from a joint plate image.
Fig. 12 is an exemplary view showing the size of a window applied to the method shown in Fig. 11. Fig.
13 is a graph showing the error range of the nut rotation angle measured according to the embodiment of the present invention.
FIG. 14 is a graph showing experimental data measuring a nut rotation angle according to an embodiment of the present invention. FIG.
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, a bolt loosening detection method and a computer program according to the present invention will be described in detail with reference to the accompanying drawings.
In the following description, only parts necessary for understanding a bolt loosening detection method and a computer program according to an embodiment of the present invention will be described, and descriptions of other parts may be omitted so as not to disturb the gist of the present invention.
In addition, terms and words used in the following description and claims should not be construed to be limited to ordinary or dictionary meanings, but are to be construed in a manner consistent with the technical idea of the present invention As well as the concept.
1 is a schematic view showing a method of detecting a bolt loosening according to the present invention.
As shown in FIG. 1, in order to detect whether a bolt is loosened by using a bolt loosening detection method according to the present invention, when a user photographs a bolt fastening part as shown in FIG. 1, The arithmetic unit provided with the computer program according to the embodiment of the present invention performs each step of the bolt loosening detection method according to the embodiment of the present invention to determine whether bolt loosening has occurred from the inputted bolt fastener image And provides the result to the user who wants to confirm the bolt loosening.
The bolt loosening detection method according to the present invention can confirm whether or not the bolt is loosened by only photographing the bolt fastening part and inputting the image to the computing device provided with the computer program according to the present invention, The entire bolt fastening part can be checked within a short time without the need of attaching the sensor, so that the cost and time for confirming whether or not the bolt is loosened can be greatly reduced as compared with the prior art.
The method of detecting the bolt loosening according to the present invention will be described in more detail as follows.
FIG. 2 is a flowchart of a bolt loosening detection method according to an embodiment of the present invention.
2, the bolt loosening detection method according to an embodiment of the present invention includes an image input step S100, an edge extraction step S200, a straight line detection step S300, and a bolt loosening determination step S400 .
The image input step S100 is a step in which an image photographed by the bolt fastening part is input to the computing device.
In this case, the input image must include a bolt fastening part, that is, an image of a bolt part installed on the structure, and a nut image fastened to the bolt must be included as shown in FIG. 3 (a). This is because the bolt loosening is caused by the rotation of the nut, not the bolt.
The edge extracting step S200 is a step of extracting an edge from the input image of the bolted portion, more specifically, the nut image.
The reason for extracting the edge is to extract the outline of the nut from the nut image, and it is possible to use known techniques such as Sobel, Prewitt, Roberts, Marr-Hildreth, Laplacial of Gaussian and Canny to extract the edge from the image.
FIG. 3 (b) shows an image obtained by extracting an edge from the image of FIG. 3 (a) using the Canny technique. The Canny technique uses two thresholds using hysteresis thresholding as compared to the other techniques, allowing finer control for edge detection.
The linear detection step S300 is a step of detecting a linear component from the extracted image information.
In order to detect the linear component from the extracted image, Hough transform can be used. In order to be able to express up to the vertical straight line, the following equation can be used.
Here, r is an orthogonal line length from the origin (for example, an arbitrary point preset as the upper left vertex of the four vertexes of the image as shown in FIG. 4) to the straight line, and? Is the slope of the orthogonal line. The x and y axes for determining the slope can use the horizontal and vertical sides of the image.
The bolt loosening determination step S400 is a step of calculating the rotation angle of the nut from the slope of the straight line detected in the straight line detection step and determining whether the bolt is loosened or not.
The nut has a regular hexagonal shape. Therefore, as described above, the sides of the nut are angled by 60 degrees, so that the rotation of the nut can be measured is limited to 0 degrees or less and 60 degrees or less. However, the straight line (ie, one side of the nut) detected by the Hough transform does not necessarily have a value between 0 and 60 degrees. In other words, it is impossible to know which side of the nut will be extracted as a straight line. Therefore, to change to the angle of the straight line to the side within 60 degrees for a straight line exceeding 60 degrees, the following calculation is made so that no deviation of the nut is detected at the straight line detection step, The nut rotation angle can be derived.
Here, θn is the rotation angle of the nut, θ is the slope of the orthogonal line to the origin of the detected straight line, and rem [] is an operator representing the remainder after division.
In general, the angle of the nut is not always 0 ° when the bolt is installed. Therefore, to determine whether the bolt is loosened from the angle of rotation of the derived nut, the angle of the nut in the first or previous state must be stored.
Thus, the computing device can determine whether the bolt has been released by comparing the calculated angle of rotation of the nut with the angle of the pre-stored nut.
Also, when the angle of the pre-stored nut is 5 degrees and the bolt is rotated by 60 degrees until the bolt is released, the rotation angle of the nut derived from the bolt loosening detection method according to the embodiment of the present invention is 5 degrees, . Therefore, in order to detect the bolt loosening according to an embodiment of the present invention, it is desirable to periodically monitor the bolt loosening in a relatively short period (the nut does not rotate more than 60 degrees).
In the following description of the bolt loosening detection method according to an embodiment of the present invention, one nut image is included in one image as shown in FIG.
However, in general, a plurality of bolts are fastened to a bolt fastening plate, and in order to be able to apply the bolt fastening detecting method according to the present invention more easily to an actual industrial field, it is more preferable that the bolt fastening plate So as to judge each bolt loosening.
Also, since the bolt loosening detection method according to the present invention does not always fix the camera for photographing the bolt fastening part in the actual industrial field, rotation of the camera at the time of shooting affects calculation of the nut rotation angle, Can be derived. Therefore, since the reference object is necessary to correct the rotation or the perspective distortion of the camera, it is more preferable to use the image of the entire bolt fastening plate.
Therefore, the bolt loosening detection method according to another embodiment of the present invention will be described in detail below, in which an image taken of the entire bolt fastening plate is inputted to a computing device provided with a computer program according to the present invention.
5, the bolt loosening detection method according to another exemplary embodiment of the present invention includes a joint plate image input step S110, a joint plate extraction step S120, an image correction step S130, an individual nut image extraction step S140), an edge extraction step S200, a straight line detection step S300, and a bolt loosening determination step S400.
The bolt loosening detection method according to another embodiment of the present invention includes a plurality of nut images that are not one nut image in the image input step S100 of the bolt loosening detection method according to the embodiment of the present invention shown in Fig. The edge extraction step S200, the straight line detection step S300, the bolt loosening determination step S400 (step S400), and the bolt loosening step S400 Is the same as the method of detecting the bolt loosening according to the embodiment of the present invention described above, so that the description of the overlapping steps will be omitted and the description will be omitted.
An image of the joint plate image input step S110 is shown in FIG. 6, in which an image of a joint plate having a plurality of bolts and nuts fastened thereto is input to the arithmetic unit, and the joint plate is photographed.
The image of the joint plate can be input to the arithmetic unit through wired / wireless communication. If the arithmetic unit is a device capable of photographing and carrying, the joint plate image is photographed by the photographing function of the arithmetic unit, Can be input.
The joining plate extracting step S120 is a step of extracting a joining plate from the input joining plate image. As shown in Fig. 7 (c), a straight line is detected in the joining plate image using the Hough transform, Four edges of the joint plate can be extracted.
However, in the case where a different linear image is included in the joint plate image, it is preferable to select a schematic joint plate region using a quadrangular window as shown in FIG. 7 (b), and a schematic joint plate region It can be selected automatically or manually by the user.
The image correction step (S130) is a step of correcting the perspective and / or rotation distortion generated when photographing the joint plate.
That is, as shown in FIG. 7, the input plate image is not an image taken from the front face of the plate, and when the rotational angle of the nut is calculated from the distorted image, the result is unreliable.
Therefore, it is necessary to correct the input board image to the same front image as the front board image.
To do this, we extract the four corner coordinates of the joint plate extracted in the joint plate extraction step and compare it with the ratio of the lengths of the horizontal and vertical sides of the joint plate stored in the arithmetic unit storage unit. Can be determined.
That is, when there is a perspective distortion as shown in FIG. 8 (a), the lengths of two opposing corners are not the same, and the ratio of lengths of the horizontal and vertical edges is different from that of the front.
As a result, the two corners facing each other are equal in length, and the image is corrected so that the length ratio of the horizontal and vertical corners becomes equal to the previously stored ratio. Thus, as shown in FIG. 8B, Correction can be performed.
In addition, since rotation angle during shooting can act as a factor of error in the rotation angle of the nut when shooting at the time of shooting, when correcting with the front image, the front image is corrected so that it is parallel to the side and longitudinal sides of the junction plate and the longitudinal side image .
The individual nut image extracting step S140 is a step of extracting the individual nut images from the plurality of nut images fastened to the joint plate to determine the bolt loosening for each nut.
An exemplary method of extracting an individual nut image will now be described with reference to FIGS. 9 and 10. FIG.
First, in most joint plates, bolts are fastened in N × M shapes. Therefore, information on how the bolts are fastened to the joint plate may be obtained from the design of the bridge or the like and stored in the storage unit of the arithmetic unit, and the arithmetic unit may use the stored information as shown in FIG. 9 The joint plate is evenly divided into N × M images.
The edge extracting step (S200), the straight line detecting step (S300), and the bolt loosening determining step (S400) can be performed on the uniformly divided image to determine whether the bolt is loosened or not.
However, the image of the joint plate that is uniformly divided into N × M images may include not only the nut image but also ambient noise (rust, foreign matter, paint texture, etc.), and such ambient noise may cause a large error factor Lt; / RTI >
Therefore, it is desirable to remove such ambient noise. For this purpose, the uniformly divided nut image is converted into a gray image as shown in FIG. 10 (a). The image may be converted into a gray image before dividing as shown in FIG.
An image converted into a gray image has a level value of 8 bits from 0 (black) to 256 (white). If a threshold is applied to the following expression, a gray image is displayed in black and white Image.
if pixel (r, c)> threshold
pixel (r, c) = 1 else pixel (r, c) = 0
Here, r and c represent the pixel position of the image, respectively, and have a value within the size of the image from 1.
As shown in FIG. 10 (b), a position where a sum of pixel colors in a window reaches a maximum value is selected as shown in the following equation while moving a predetermined size window (suitable for including a nut image) in such a monochrome image , And this position becomes an optimum nut image from which ambient noise is removed.
find r, c
Maximize
Here, r w and c w indicate the size of the window, and if there are several pairs of r and c, which are the maximum, the position is determined as an average of these pairs.
Using the above method, an individual nut image is extracted as shown in Fig. 10 (c).
Another method of extracting an individual nut image is to extract a circle shape of the end portion of the bolt using a circular Hough Transform as shown in FIG. 11, and then extract a square of a predetermined size centered on the center of the bolt as an individual nut image have.
As shown in FIG. 12, since the distance (R) from the center of the nut to the vertex of the regular hexagon is about 1.4 to 1.6 times the radius of the bolt, the size of one side of the square for extracting the individual nut image is 5 times the radius of the bolt is appropriate.
Although the methods of extracting the individual nut images have been described so far, the method of extracting the individual nut images is not limited to the above-described methods, and any method capable of extracting the individual nut images may be used.
If the individual nut images are extracted in this manner, the edge extraction step S200, the straight line detection step S300, and the bolt loosening determination step S400 may be performed to determine whether the bolts are loosened or not.
According to the embodiment of the present invention described above, the detection of the bolt loosening was carried out, and the angle of the bolt was measured with an actual digital protractor. As a result, as shown in FIG. 13, it can be seen that an error of about ± 2 degrees occurs between the measurement result according to the embodiment of the present invention and the measurement result with the digital protractor.
14 (b) and 14 (c)), when the variation of the nut angle is within ± 2 degrees in consideration of the error range in detecting the bolt loosening according to the embodiment of the present invention, It is determined that there is no bolt loosening, and it is preferable to determine that bolt loosening has occurred when the change in the nut angle exceeds +/- 2 degrees (Fig. 14 (a)).
The error range is set in advance in the computing device for determining the bolt loosening according to the embodiment of the present invention, and when the angle change within the error range is measured in the bolt loosening determination step (S400), the result is output as the bolt is not loosened Is preferably used.
The method of detecting bolt loosening and the computer program according to an embodiment of the present invention have been described with reference to specific embodiments. It is to be understood, however, that the invention is not limited to those precise embodiments, and that various changes and modifications may be made therein without departing from the spirit and scope of the invention as claimed.
Claims (11)
An edge extraction step of extracting an edge from the nut image;
A straight line detecting step of detecting a straight line component from the image information from which the edge is extracted; And
A bolt loosening determination step of calculating a rotation angle of the nut from the slope of the detected straight line and comparing the rotation angle of the calculated nut with the angle of the previously stored nut to determine whether the bolt is loosened;
And the bolt loosening detection method.
And in the bolt loosening determination step, the rotation angle of the nut is calculated using the following equation.
Here, θn is the rotation angle of the nut, θ is the slope of the orthogonal line to the origin of the detected straight line, and rem [] is an operator indicating the remainder after division
Before the edge extraction step
A joint plate image input step including a plurality of nut images; And
A nut image extraction step of extracting an individual nut image from the joint plate image;
Further comprising a bolt loosening detection method.
And correcting the perspective of the joint plate image input between the joint plate image input step and the nut image extracting step to derive a front image.
Wherein the front image is derived by correcting the transverse side of the joint plate to be parallel to the transverse side of the image and to make the longitudinal side of the joint plate parallel to the longitudinal side of the image.
Wherein the extracting of the nut image comprises extracting a circular shape of the end portion of the bolt from the input joint plate image and extracting a rectangular image of a predetermined size centered on the center of the extracted circular shape as an individual nut image.
Wherein the extracting of the nut image comprises extracting the individual nut image by equally dividing the joint plate image inputted according to the bolt arrangement information stored in the storage unit of the arithmetic unit.
The nut image extracting step converts the uniformly divided image into a gray image, converts the gray image converted using the preset level value into a monochrome image having a color value of 1 or 0, And extracting the image of the position where the maximum value is obtained as the individual nut image.
And determining that the bolt is not loosened when the angle difference between the rotation angle of the nut calculated in the bolt loosening determination step and the pre-stored nut is within a predetermined angle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020150071128A KR20160136905A (en) | 2015-05-21 | 2015-05-21 | Bolt-loosening Detection Method and Computer Program Thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020150071128A KR20160136905A (en) | 2015-05-21 | 2015-05-21 | Bolt-loosening Detection Method and Computer Program Thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| KR20160136905A true KR20160136905A (en) | 2016-11-30 |
Family
ID=57707091
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| KR1020150071128A KR20160136905A (en) | 2015-05-21 | 2015-05-21 | Bolt-loosening Detection Method and Computer Program Thereof |
Country Status (1)
| Country | Link |
|---|---|
| KR (1) | KR20160136905A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019183475A1 (en) * | 2018-03-23 | 2019-09-26 | University Of Kansas | Vision-based fastener loosening detection |
| CN110304106A (en) * | 2019-06-21 | 2019-10-08 | 中国铁建重工集团股份有限公司 | Detection method, the detection system and detection device of bolt state of bolt state |
| CN111814709A (en) * | 2020-07-14 | 2020-10-23 | 南京航空航天大学苏州研究院 | Airplane surface bolt tightening detection method |
| CN112419297A (en) * | 2020-12-04 | 2021-02-26 | 中冶建筑研究总院（深圳）有限公司 | Bolt looseness detection method, device, equipment and storage medium |
| KR20210057887A (en) * | 2019-11-12 | 2021-05-24 | 부경대학교 산학협력단 | Deep learning and image processing based bolt loosening detection method |
| CN112862889A (en) * | 2021-01-29 | 2021-05-28 | 珠海迪沃航空工程有限公司 | Recognition correction system, method and device based on image recognition |
| CN113128400A (en) * | 2021-04-19 | 2021-07-16 | 北京明略软件***有限公司 | Bolt loosening angle identification method and system |
| CN113222935A (en) * | 2021-05-13 | 2021-08-06 | 江苏科技大学 | Method for detecting looseness and pretightening force loss of steel bridge bolt |
| US11714024B2 (en) | 2017-11-30 | 2023-08-01 | University Of Kansas | Vision-based fatigue crack detection using feature tracking |
| US11954844B2 (en) | 2018-08-21 | 2024-04-09 | University Of Kansas | Fatigue crack detection in civil infrastructure |
-
2015
- 2015-05-21 KR KR1020150071128A patent/KR20160136905A/en not_active Application Discontinuation
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11714024B2 (en) | 2017-11-30 | 2023-08-01 | University Of Kansas | Vision-based fatigue crack detection using feature tracking |
| US11354814B2 (en) | 2018-03-23 | 2022-06-07 | University Of Kansas | Vision-based fastener loosening detection |
| WO2019183475A1 (en) * | 2018-03-23 | 2019-09-26 | University Of Kansas | Vision-based fastener loosening detection |
| US11954844B2 (en) | 2018-08-21 | 2024-04-09 | University Of Kansas | Fatigue crack detection in civil infrastructure |
| CN110304106A (en) * | 2019-06-21 | 2019-10-08 | 中国铁建重工集团股份有限公司 | Detection method, the detection system and detection device of bolt state of bolt state |
| KR20210057887A (en) * | 2019-11-12 | 2021-05-24 | 부경대학교 산학협력단 | Deep learning and image processing based bolt loosening detection method |
| CN111814709A (en) * | 2020-07-14 | 2020-10-23 | 南京航空航天大学苏州研究院 | Airplane surface bolt tightening detection method |
| CN112419297A (en) * | 2020-12-04 | 2021-02-26 | 中冶建筑研究总院（深圳）有限公司 | Bolt looseness detection method, device, equipment and storage medium |
| CN112419297B (en) * | 2020-12-04 | 2024-06-04 | 中冶建筑研究总院（深圳）有限公司 | Bolt loosening detection method, device, equipment and storage medium |
| CN112862889A (en) * | 2021-01-29 | 2021-05-28 | 珠海迪沃航空工程有限公司 | Recognition correction system, method and device based on image recognition |
| CN113128400A (en) * | 2021-04-19 | 2021-07-16 | 北京明略软件***有限公司 | Bolt loosening angle identification method and system |
| CN113222935A (en) * | 2021-05-13 | 2021-08-06 | 江苏科技大学 | Method for detecting looseness and pretightening force loss of steel bridge bolt |
| CN113222935B (en) * | 2021-05-13 | 2024-04-23 | 江苏科技大学 | Method for detecting looseness and pretightening force loss of steel bridge bolt |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR20160136905A (en) | Bolt-loosening Detection Method and Computer Program Thereof | |
| Cha et al. | Vision-based detection of loosened bolts using the Hough transform and support vector machines | |
| US8103085B1 (en) | System and method for detecting flaws in objects using machine vision | |
| CN114387268A (en) | Bolt looseness detection method and device | |
| JP2017053819A (en) | Crack detection method and detection program of concrete | |
| US20230080178A1 (en) | Automated assessment of cracks using lidar and camera data | |
| CN103149222A (en) | Flaw detection device in real-time imaging of ray | |
| CN105205803A (en) | Display panel defect detection method | |
| JP4488308B2 (en) | Method for detecting cracks on the surface of structures | |
| US10375383B2 (en) | Method and apparatus for adjusting installation flatness of lens in real time | |
| Barkavi et al. | Processing digital image for measurement of crack dimensions in concrete | |
| CN112991374A (en) | Canny algorithm-based edge enhancement method, device, equipment and storage medium | |
| Chen et al. | Sub-pixel edge detection of led probes based on canny edge detection and iterative curve fitting | |
| US20140297224A1 (en) | Data processing method of tire shape inspecting device | |
| JP4680659B2 (en) | Product tire appearance inspection method and product tire appearance inspection auxiliary device | |
| JP2019120644A (en) | Surface inspection device and surface inspection method | |
| WO2021079727A1 (en) | Appearance inspection device, appearance inspection method, and appearance inspection program | |
| CN204649642U (en) | A kind of device of detection plane defect | |
| Mo et al. | Development of 3D camera-based robust bolt-hole detection system for bolting cabin | |
| CN109118511B (en) | Image processing method of tilt sensor | |
| TWI638992B (en) | Method for detecting defect at painting | |
| JP6883458B2 (en) | Diagnostic method for amorphous sealant | |
| CN109215068B (en) | Image magnification measuring method and device | |
| Pan et al. | Edge detection of tobacco leaf images based on fuzzy mathematical morphology | |
| CN104713887A (en) | Planar flaw detecting method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A201 | Request for examination | ||
| E902 | Notification of reason for refusal | ||
| E601 | Decision to refuse application |