CN108469336B - Bolt looseness detection method based on image processing - Google Patents
Bolt looseness detection method based on image processing Download PDFInfo
- Publication number
- CN108469336B CN108469336B CN201810232911.5A CN201810232911A CN108469336B CN 108469336 B CN108469336 B CN 108469336B CN 201810232911 A CN201810232911 A CN 201810232911A CN 108469336 B CN108469336 B CN 108469336B
- Authority
- CN
- China
- Prior art keywords
- bolt
- line
- image
- reference line
- detection method
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a bolt looseness detection method based on image processing, which comprises the following steps of: installing a direction marker on the tightened bolt; taking a relatively fixed structure edge line near the detected bolt as a reference line; aligning a camera with the bolt, the direction marker and the reference line; taking a first image of the bolt tightening state; processing the shot first image through a computer, identifying a bolt center point, a direction marking structure and a reference line, identifying a marking angular point, making a vertical line, making a ray from the bolt center point, and calculating an included angle of the ray relative to the vertical line along the counterclockwise direction from the vertical line at zero degrees; repeating the steps to obtain the angle of the nth time; and comparing the included angle obtained every time with the first included angle, and detecting the loosened bolt tightening when the deviation is large. The invention can continuously obtain the bolt direction in the long-term service process of the equipment and realize the long-term on-line quick detection of the bolt looseness.
Description
Technical Field
The invention relates to a fastener looseness detection technology, in particular to a bolt looseness detection method based on image processing.
Background
The bolt is a common fastener widely applied to the fields of railways, vehicles, bridges, engineering equipment and the like, and is easily loosened, deformed, broken or fallen off due to the influence of factors such as vibration, corrosion, impact and the like in the use process, so that equipment failure and even major accidents are caused. Therefore, the looseness inspection of the bolts is always an important project for the inspection and maintenance of engineering equipment.
Among the detection technologies that have been published at home and abroad, the relatively prominent methods are: a vibration signal analysis method and an image recognition method. In the vibration signal analysis method, one type needs to continuously knock a fixed structure by using a knocking hammer and simultaneously collects and analyzes residual vibration signals, but the knocking hammer mechanism is complex to develop and limits the detection speed during detection, and the other type searches and adopts an ODS (operational Deflection shape) mathematical model to analyze the vibration signals of wheels passing through a certain interval, and artificially observes and screens the abnormal condition of the ODS value to identify a loosening interval, but the method cannot realize the purpose of online rapid diagnosis.
The existing image recognition method needs to mark symbols on a rotating part and a non-rotating part of a bolt connection part, but after the equipment is in service for a long time, the symbols fall off or are covered by dirt, so that image judgment cannot be carried out, and the existing image recognition method cannot meet the actual requirement.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a bolt looseness detection method based on image processing, which can continuously acquire the bolt direction in the long-term service process of equipment and realize the long-term online quick detection of bolt looseness.
In order to achieve the purpose, the invention adopts the following technical scheme:
a bolt looseness detection method based on image processing comprises the following steps:
1) installing a direction marker on the tightened bolt;
2) taking a relatively fixed structure edge line near the detected bolt as a reference line;
3) starting a camera terminal;
4) aligning a camera with the bolt, the direction marker and the reference line;
5) taking a first image of the bolt tightening state;
6) processing the first image by a computer to identify a bolt center point, a direction mark structure and a reference line, identifying a mark angular point of the bolt corresponding to the direction mark structure, drawing a vertical line from the bolt center point to the reference line, drawing a ray from the bolt center point through the mark angular point of the bolt, and calculating an included angle alpha of an emergent ray relative to the vertical line from the vertical line along an anticlockwise direction from zero degree0;
7) Aligning the camera again to the bolt, the direction marker and the reference line;
8) re-capturing a second image of the bolt tightening state;
9) processing the captured secondary image by a computer to identify the center point, the direction mark structure and the reference line of the bolt, identifying the mark angular point of the bolt corresponding to the direction mark structure, making a perpendicular line from the center point to the reference line of the bolt, and marking the bolt from the center point of the boltMaking rays from the corner points, and calculating an included angle alpha of the emergent ray relative to the vertical line in the counterclockwise direction from the vertical line at zero DEG1;
10) Setting an angle deviation threshold beta in the computer, and calculating the angle deviation delta alpha as | alpha1-α0Comparing the angle deviation delta alpha with an angle deviation threshold beta, if the delta alpha is smaller than the beta, returning to the step 8), continuously shooting the image of the nth time, and if the delta alpha is larger than or equal to the beta, detecting the bolt loosening;
11) the bolt detected as loose is tightened.
The direction marker can also be mounted on the bolt head or the nut.
A is0∈[0°,360°)。
A is1∈[0°,360°)。
In the above technical solution, the bolt looseness detection method based on image processing provided by the present invention further has the following beneficial effects:
1. the invention breaks through the limitation that the mark symbol falls off or is covered by dirt, and the bolt direction is continuously obtained in the long-term service of the equipment;
2. the invention can diagnose the bolt looseness on line, quickly and accurately, and has high detection efficiency.
Drawings
FIG. 1 is a flow chart of the detection method of the present invention;
FIG. 2 is a schematic view of the first intake bolt tightening state of the present invention;
fig. 3 is a schematic view showing a bolt tightening state at the nth time of the intake of the present invention.
Detailed Description
The technical scheme of the invention is further explained by combining the drawings and the embodiment.
Referring to fig. 1 to 3, a method for detecting bolt loosening based on image processing according to the present invention includes the following steps:
1) after the bolt 1 is tightened, the direction marker 2 is mounted on the bolt 1 or the nut;
2) taking a relatively fixed structure edge line near the detected bolt 1 as a reference line 3;
3) starting a camera terminal;
4) aligning a camera with the bolt 1 or the nut, the direction marker 2 and the reference line 3;
5) taking a first image of the bolt tightening state;
6) processing the captured first image through a computer, identifying a bolt center point 101, a direction marking structure 201 and a reference line 3, identifying a marking angle point 102 of the bolt 1 or the nut corresponding to the direction marking structure 201, drawing a vertical line 4 from the bolt center point 101 to the reference line 3, drawing a ray 5 from the bolt center point 101 through the marking angle point 102 of the bolt 1 or the nut, and calculating an included angle alpha of the emergent line 5 relative to the vertical line from the vertical line 4 in a counterclockwise direction starting from zero degree along the vertical line 40Of size range alpha0∈[0°,360°);
7) Aligning the camera again to the bolt 1 or the nut, the direction marker 2 and the reference line 3;
8) re-capturing a second image of the bolt tightening state;
9) processing the shot second image through a computer, identifying a bolt center point 101, a direction marking structure 201 and a reference line 3, identifying a marking angle point 102 of the bolt 1 or the nut corresponding to the direction marking structure 201, drawing a vertical line 4 from the bolt center point 101 to the reference line 3, drawing a ray 5 from the bolt center point 101 through the marking angle point 102 of the bolt 1 or the nut, and calculating an included angle alpha of the emergent line 5 relative to the vertical line along the counterclockwise direction from the vertical line 4 at zero degree1Of size range alpha1∈[0°,360°);
10) Setting an angle deviation threshold beta in the computer, and calculating the angle deviation delta alpha as | alpha1-α0Comparing the angle deviation delta alpha with an angle deviation threshold beta, if the delta alpha is smaller than the beta, returning to the step 8), continuously shooting the image of the nth time, and if the delta alpha is larger than or equal to the beta, detecting the bolt loosening;
11) the bolt detected as loose is tightened.
Preferably, the direction marker 2 can be installed on the head of the bolt 1 or on the nut.
In summary, the present invention aims to overcome the defects in the prior art, and can continuously obtain the bolt direction in the long-term service process of the equipment, so as to realize the long-term online rapid detection of the bolt looseness. The invention breaks through the limitation that the mark symbol falls off or is covered by dirt, and the bolt direction is continuously obtained in the long-term service of the equipment; the bolt loosening can be diagnosed on line, quickly and accurately, and the detection efficiency is high.
It should be understood by those skilled in the art that the above embodiments are only for illustrating the present invention and are not to be used as a limitation of the present invention, and that changes and modifications to the above described embodiments are within the scope of the claims of the present invention as long as they are within the spirit and scope of the present invention.
Claims (4)
1. A bolt looseness detection method based on image processing is characterized by comprising the following steps:
1) installing a direction marker on the tightened bolt;
2) taking a relatively fixed structure edge line near the detected bolt as a reference line;
3) starting a camera terminal;
4) aligning a camera with the bolt, the direction marker and the reference line;
5) taking a first image of the bolt tightening state;
6) processing the first image by a computer to identify a bolt center point, a direction mark structure and a reference line, identifying a mark angular point of the bolt corresponding to the direction mark structure, drawing a vertical line from the bolt center point to the reference line, drawing a ray from the bolt center point through the mark angular point of the bolt, and calculating an included angle alpha of an emergent ray relative to the vertical line from the vertical line along an anticlockwise direction from zero degree0;
7) Aligning the camera again to the bolt, the direction marker and the reference line;
8) re-capturing a second image of the bolt tightening state;
9) by computer for the second image takenProcessing is carried out, a bolt central point, a direction marking structure and a reference line are identified, then a marking angular point of the bolt corresponding to the direction marking structure is identified, then a perpendicular line is drawn from the bolt central point to the reference line, a ray is drawn from the bolt central point through the marking angular point of the bolt, and an included angle alpha of an emergent ray relative to the perpendicular line is calculated from the perpendicular line in a counterclockwise direction from zero degree1;
10) Setting an angle deviation threshold beta in the computer, and calculating the angle deviation delta alpha as | alpha1-α0Comparing the angle deviation delta alpha with an angle deviation threshold beta, if the delta alpha is smaller than the beta, returning to the step 8), continuously shooting the image of the nth time, and if the delta alpha is larger than or equal to the beta, detecting the bolt loosening;
11) the bolt detected as loose is tightened.
2. The bolt looseness detection method based on image processing as claimed in claim 1, wherein: the orientation marker can also be mounted on the bolt head or nut.
3. The bolt looseness detection method based on image processing as claimed in claim 1, wherein: a is0∈[0°,360°)。
4. The bolt looseness detection method based on image processing as claimed in claim 1, wherein: a is1∈[0°,360°)。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810232911.5A CN108469336B (en) | 2018-03-21 | 2018-03-21 | Bolt looseness detection method based on image processing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810232911.5A CN108469336B (en) | 2018-03-21 | 2018-03-21 | Bolt looseness detection method based on image processing |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108469336A CN108469336A (en) | 2018-08-31 |
CN108469336B true CN108469336B (en) | 2020-01-21 |
Family
ID=63264609
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810232911.5A Active CN108469336B (en) | 2018-03-21 | 2018-03-21 | Bolt looseness detection method based on image processing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108469336B (en) |
Families Citing this family (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108982042A (en) * | 2018-09-21 | 2018-12-11 | 中国航空工业集团公司沈阳飞机设计研究所 | A kind of rivet resistance to shock test structure |
CN109389566B (en) * | 2018-10-19 | 2022-01-11 | 辽宁奇辉电子系统工程有限公司 | Method for detecting bad state of fastening nut of subway height adjusting valve based on boundary characteristics |
CN109631779A (en) * | 2018-11-09 | 2019-04-16 | 四川国软科技发展有限责任公司 | A kind of detection method and system that the superstructure loosening based on 3D rendering processing falls off |
CN109373934A (en) * | 2018-11-28 | 2019-02-22 | 中国建筑第四工程局有限公司 | Super-high pier verticality measuring method |
CN110304106B (en) * | 2019-06-21 | 2020-10-02 | 中国铁建重工集团股份有限公司 | Bolt state detection method, bolt state detection system and bolt state detection equipment |
CN110349104A (en) * | 2019-07-08 | 2019-10-18 | 创新奇智(南京)科技有限公司 | A kind of method of the COMPUTER DETECTION with groove bolt looseness, computer-readable medium and system |
CN112330615B (en) * | 2020-10-27 | 2022-11-29 | 华能新能源股份有限公司河北分公司 | Method and system for monitoring state of high-strength bolt of rotating part |
CN112945437A (en) * | 2021-01-29 | 2021-06-11 | 优势博研(北京)科技有限公司 | Bolt looseness detection device based on visual monitoring |
CN113118681A (en) * | 2021-04-06 | 2021-07-16 | 中铁第四勘察设计院集团有限公司 | Robot system for detecting and welding weld joints of sound barrier stand columns |
CN113128400A (en) * | 2021-04-19 | 2021-07-16 | 北京明略软件系统有限公司 | Bolt loosening angle identification method and system |
CN114593672B (en) * | 2022-02-17 | 2023-06-23 | 阿尔法森紧固科技(常州)有限公司 | Rivet tightness detection device and application method thereof |
CN115908951B (en) * | 2023-01-06 | 2023-05-26 | 长江勘测规划设计研究有限责任公司 | Method for identifying pre-tightening bolt state in real time through machine vision |
CN118392050B (en) * | 2024-06-28 | 2024-08-23 | 昆明学院 | In-service bridge disease inspection device and inspection method based on proximity photogrammetry |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103317477A (en) * | 2013-06-18 | 2013-09-25 | 利丰海洋工程(深圳)有限公司 | Angle anchoring bolt tightening method and tightening device |
CN104680517A (en) * | 2015-01-22 | 2015-06-03 | 清华大学 | Looseness detection method of bolt |
-
2018
- 2018-03-21 CN CN201810232911.5A patent/CN108469336B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103317477A (en) * | 2013-06-18 | 2013-09-25 | 利丰海洋工程(深圳)有限公司 | Angle anchoring bolt tightening method and tightening device |
CN104680517A (en) * | 2015-01-22 | 2015-06-03 | 清华大学 | Looseness detection method of bolt |
Also Published As
Publication number | Publication date |
---|---|
CN108469336A (en) | 2018-08-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108469336B (en) | Bolt looseness detection method based on image processing | |
CN104680517B (en) | A kind of detection method of bolt looseness | |
CN100485371C (en) | Automatic online detection method for defects on upper and lower surfaces during steel plate pretreatment process | |
CN110567680B (en) | Track fastener looseness detection method based on angle comparison | |
TWI504478B (en) | Monitoring System of Ball Screw Pre - pressure and Its Monitoring Method | |
CN110688944B (en) | Bolt looseness monitoring method based on image recognition and machine learning | |
CN113379712B (en) | Steel bridge bolt disease detection method and system based on computer vision | |
KR102265496B1 (en) | Tongue Rail Approach Detector | |
CN103422417A (en) | Dynamic identification system and method for detecting road surface damages | |
CN110304106B (en) | Bolt state detection method, bolt state detection system and bolt state detection equipment | |
WO2018103805A1 (en) | Pre-tensioning of bolts | |
CN105068139A (en) | Detection technology for mounting condition of piston cooling nozzle | |
CN103344418A (en) | Method for correcting automobile headlamp detecting light bundle shining direction deviation | |
CN211710846U (en) | Intelligent detection system for crack opening state of CRTS II type ballastless track slab | |
CN117759491A (en) | Wind turbine generator set bolt fault monitoring method | |
EP2418377B1 (en) | Method for determining defects in a wind turbine blade root attachment | |
CN113191239A (en) | Vehicle overall dimension dynamic detection system based on computer vision | |
CN112027566A (en) | Conveying belt deviation type judging and deviation measuring and calculating system based on laser scanning | |
CN109631752A (en) | A kind of engine main bearing cover assembly vision inspection apparatus and method | |
CN107654848A (en) | A kind of pipeline location and direction detection method | |
CN115541109A (en) | Method for monitoring unbalance of impeller based on machine vision | |
CN209342917U (en) | A kind of high-resolution multi-target tracking radar | |
CN111222428B (en) | Detection method for device fastening operation based on monitoring video | |
CN209784259U (en) | Automatic wall-climbing far-field vortex and video detection system for water wall tube of power station boiler | |
CN114299403A (en) | Electricity tower bolt detection method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20210908 Address after: 200125 No. 3261 Dongfang Road, Shanghai, Pudong New Area Patentee after: SHANGHAI ZHENHUA HEAVY INDUSTRIES Co.,Ltd. Patentee after: CCCC HIGHWAY BRIDGES NATIONAL ENGINEERING RESEARCH CENTER Co.,Ltd. Address before: 200125 No. 3261 Dongfang Road, Shanghai, Pudong New Area Patentee before: SHANGHAI ZHENHUA HEAVY INDUSTRIES Co.,Ltd. |