CN111932516A - Mark-free double-nut hexagon bolt looseness detection system based on image processing - Google Patents
Mark-free double-nut hexagon bolt looseness detection system based on image processing Download PDFInfo
- Publication number
- CN111932516A CN111932516A CN202010799061.4A CN202010799061A CN111932516A CN 111932516 A CN111932516 A CN 111932516A CN 202010799061 A CN202010799061 A CN 202010799061A CN 111932516 A CN111932516 A CN 111932516A
- Authority
- CN
- China
- Prior art keywords
- bolt
- nut
- image
- main body
- bolt main
- 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.)
- Pending
Links
- 238000012545 processing Methods 0.000 title claims abstract description 61
- 238000001514 detection method Methods 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 claims description 13
- 238000003384 imaging method Methods 0.000 claims description 10
- 230000001681 protective effect Effects 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 8
- 239000006185 dispersion Substances 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 2
- 239000003550 marker Substances 0.000 claims 7
- 230000004888 barrier function Effects 0.000 abstract description 8
- 238000012423 maintenance Methods 0.000 abstract description 5
- 230000005611 electricity Effects 0.000 abstract description 3
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 5
- 238000009434 installation Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000009413 insulation Methods 0.000 description 2
- 230000008054 signal transmission Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20164—Salient point detection; Corner detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a marker-free double-nut hexagon bolt looseness detection system based on image processing, which belongs to the technical field of sound barrier maintenance and comprises an image acquisition module A, a data processing module B and an early warning module C, wherein the image acquisition module A, the data processing module B and the early warning module C are connected through a wireless network: compared with the traditional manual and mechanical bolt detection method, the detection system provided by the invention saves a large amount of manpower and does not depend on the personal experience of maintainers; compared with sensors based on the principles of sound, light, electricity and the like, the sensor mainly used in the scheme is an industrial camera, the cost is relatively low, due to the fact that non-contact monitoring is conducted, the sensor is not attached to the bolt tightly, normal work of the bolt is not affected, the detection system utilizes the self characteristics of the double-nut bolt as geometric identification, and extra image markers are not needed. The whole detection system can meet the requirement of engineering maintenance and has huge market demand space.
Description
Technical Field
The invention relates to the technical field of sound barrier maintenance, in particular to a marker-free double-nut hexagon bolt looseness detection system based on image processing.
Background
The sound insulation barrier is a sound insulation facility. It is intended to shield direct sound between the source and the receiver by inserting a facility between the source and the receiver to provide a significant additional attenuation of the sound wave propagation, thereby attenuating the noise contribution in the area of the receiver. Sound barriers are mainly used outdoors. As highway traffic noise pollution becomes more severe, various forms of barriers are being employed in large numbers to reduce traffic noise.
The sound barrier is mostly installed in orbital both sides, and the vibrations that the rail train produced when passing through can influence the locking bolt of barrier, need in time investigate the barrier bolt. At present, bolt looseness detection means used on domestic railways still adopt manual visual detection, a hammering method, a torque pulling method and the like, and the methods are relatively simple but have a plurality of limitations. On the one hand, it is time-consuming, labor-intensive and dangerous. On the other hand, the testing accuracy of the methods greatly depends on the personal experience of the testing personnel, and the testing results of different people have large dispersion and poor referential performance.
Disclosure of Invention
The invention aims to provide a marker-free double-nut hexagon bolt looseness detection system based on image processing, which saves manpower, is convenient to overhaul and does not influence the normal work of bolts so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
the marker-free double-nut hexagon bolt looseness detection system based on image processing comprises an image acquisition module A, a data processing module B and an early warning module C, wherein the image acquisition module A, the data processing module B and the early warning module C are connected through a wireless network, and the marker-free double-nut hexagon bolt looseness detection system comprises the following steps:
s1: firstly, an image collector is arranged right above a bolt group to be monitored, and whether the communication among the three modules A, B, C is normal is tested;
s2: then starting an image shooting function of the image acquisition module A, and testing whether the mounting point position of the image acquisition device is reasonable, namely whether the bolt body is in the center of an image and whether the imaging is normal;
s3: shooting an initial picture, shooting the bolt main body of the bolt group through an image acquisition module A, and extracting the picture in an initial normal pre-tightening state;
s4: the image acquired by the image acquisition module A is transmitted to the data processing module B through a wireless network, the data processing module B performs image processing on the initial image extracted by the image acquisition module A, and the image is grayed and then subjected to noise reduction in a Gaussian filtering mode;
s5: then, selecting a binarization threshold value based on a maximum inter-class variance method, and carrying out binarization processing on the gray scale picture subjected to noise reduction by the data processing module B;
s6: extracting a bolt head central point of the bolt main body by using circular Hough transform, taking the point as a position characteristic point of each bolt main body, detecting an edge segmentation bolt group picture by using canny operators, obtaining a plurality of single bolt main body pictures, and respectively and sequentially analyzing the pictures;
s7: gather each bolt main part picture and initial picture and contrast, if angular deviation is greater than predetermined corner threshold value, or the data dispersion that certain bolt main part was gathered at each moment in one day is great, then data afferent early warning module C, to measurement personnel transmission signal, inform it and fasten the processing, judge whether the bolt lax condition has appeared through the relative corner and the whole corner between two nuts around the contrast bolt main part is not hard up promptly.
Preferably, the image collector in S1 is required to face the bolt main body, and the bolt main bodies are not shielded from each other, so that the image is free of view angle distortion and is clear in imaging.
Preferably, in S2, if the number of bolts in the bolt main body is large and the mounting point is too close, the image distortion may be generated due to the central projection, and the nut end face image of the bolt main body cannot be completely collected; at the moment, the distance between the image collector and the bolt main body needs to be increased under the condition of ensuring the clear and complete shot picture until the nut edge characteristics of each bolt main body can be displayed.
Preferably, when the bolt body is analyzed in S6, the edge and corner geometric features of the two nuts of the bolt body are extracted, wherein a horizontal reference line is drawn from the central point of the bolt rod, and two minimum angles are extracted in the counterclockwise direction, which represent the initial deviation angles from the reference line of the first nut and the second nut, respectively.
Preferably, in S2, the image collector may collect one picture each time when the light is better in each day, such as 8:00, 10:00, 12:00, 14:00, 16:00 and 18: 00.
Preferably, the components of the detection system comprise an identification main board, a bolt main body, a protective frame and an image collector, wherein the bolt main body and the protective frame are both arranged on the mark main board, the image collector is arranged above the mark main board, the bottom end of the protective frame is welded and fixed with the center of the top surface of the identification main board, the protective frame is kept vertical, the identification main board is movably connected with symmetrically distributed bolt main bodies, the bolt main part runs through the sign mainboard, and the bolt main part is located the both sides that protect the frame, the bolt main part includes first nut, second nut, double-screw bolt and inflation cover, and the double-screw bolt runs through the sign mainboard, and the double-screw bolt passes through the screw thread swing joint inflation cover of its bottom, and the double-screw bolt passes through the first nut of the threaded connection and the second nut on its top, and first nut is located the top of second nut, and first nut and the contact of second nut, first nut and second nut size are the same.
Compared with the prior art, the invention has the beneficial effects that: compared with the traditional manual and mechanical bolt detection method, the marker-free double-nut hexagon bolt looseness detection system based on image processing saves a large amount of manpower, and does not depend on personal experience of maintainers; compared with sensors based on the principles of sound, light, electricity and the like, the sensor mainly used in the scheme is an industrial camera, the cost is relatively low, due to the fact that non-contact monitoring is conducted, the sensor is not attached to the bolt tightly, normal work of the bolt is not affected, the detection system utilizes the self characteristics of the double-nut bolt as geometric identification, and extra image markers are not needed. The whole detection system can meet the requirement of engineering maintenance and has huge market demand space.
Drawings
FIG. 1 is a schematic diagram of the working flow of the detection system of the present invention;
FIG. 2 is a schematic diagram of an image capture module A according to the present invention;
FIG. 3 is a schematic diagram of the operation of the data processing module B according to the present invention;
FIG. 4 is a schematic diagram of the early warning module C of the present invention;
FIG. 5 is a schematic diagram of a logo motherboard according to the present invention;
FIG. 6 is a schematic top view of a logo board according to the present invention;
fig. 7 is a schematic view of the bolt body of the present invention.
In the figure: 1. marking the mainboard; 2. a bolt body; 21. a first nut; 22. a second nut; 23. a stud; 24. an expansion sleeve; 3. protecting the frame; 4. an image collector.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-7, the system for detecting loosening of a marker-free double-nut hexagon bolt based on image processing comprises an image acquisition module a, a data processing module B and an early warning module C, wherein the image acquisition module a, the data processing module B and the early warning module C are connected through a wireless network, an image acquisition unit 4 installed in the image acquisition module a firstly adjusts a machine position angle and a distance, tests imaging quality and signal transmission quality, then transmits an image to the data processing module B, the data processing module B preprocesses the image, segments a bolt group image, extracts geometric features alpha 1 and alpha 2, compares the geometric features in the data processing module B with a preset alarm threshold alpha norm in a time-sharing manner, and sends an alarm when an offset value is larger than the alarm threshold.
The components of the detection system comprise an identification mainboard 1, a bolt main body 2, a protection frame 3 and an image collector 4, wherein both the bolt main body 2 and the protection frame 3 are arranged on the identification mainboard 1, the image collector 4 is arranged above the identification mainboard 1, the bottom end of the protection frame 3 is welded and fixed with the top surface center of the identification mainboard 1, the protection frame 3 is kept vertical, the identification mainboard 1 is movably connected with the bolt main body 2 which is symmetrically distributed, the bolt main body 2 penetrates through the identification mainboard 1, the bolt main body 2 is positioned at two sides of the protection frame 3, the bolt main body 2 comprises a first nut 21, a second nut 22, a stud 23 and an expansion sleeve 24, the stud 23 penetrates through the identification mainboard 1, the stud 23 is movably connected with the expansion sleeve 24 through the thread at the bottom end, the stud 23 is connected with the first nut 21 and the second nut 22 through the thread at the top end, the first nut 21 is positioned above the second nut 22, the first nut 21 is, the first nut 21 is the same size as the second nut 22.
The marker-free double-nut hexagon bolt looseness detection system based on image processing comprises the following steps of:
the first step is as follows: firstly, an image collector 4 is installed right above a bolt group to be monitored, the image collector 4 is required to be right opposite to a bolt main body 2, meanwhile, the bolt main bodies 2 are not mutually shielded, a picture is not distorted in visual angle, and imaging is clear, wherein whether communication among three modules A, B, C is normal or not is tested simultaneously, an image collection module A transmits initial image data information to a data processing module B, and the data processing module B transmits processed data information to an early warning module C;
the second step is that: then starting an image shooting function of the image acquisition module A, testing whether the installation point position of the image acquirer 4 is reasonable, namely whether the bolt main body 2 is in the center of an image or not, and whether the imaging is normal or not, so that the image acquirer 4 in the image acquisition module A can accurately acquire image information of the bolt main body 2, wherein the image acquirer 4 can acquire one picture in each time period of 8:00, 10:00, 12:00, 14:00, 16:00 and 18:00 under the condition of good light every day, so that the effect of acquiring segmented data is achieved, if the number of bolts of the bolt main body 2 is large, and if the installation point position is too close, image distortion is generated due to central projection, and the nut end face image of the bolt main body 2 cannot be completely acquired; at the moment, the distance between the image collector 4 and the bolt main body 2 needs to be increased under the condition of ensuring that the shot picture is clear and complete until the edge characteristics of the nut of each bolt main body 2 can be displayed;
the third step: shooting an initial picture, shooting the bolt main bodies 2 of the bolt group through the image acquisition module A, and extracting the picture in the initial normal pre-tightening state, wherein as shown in the attached figure 6, the bolt group comprises 8 bolt main bodies 2, the 8 bolt main bodies 2 are symmetrically distributed, the 8 bolt main bodies 2 can be numbered from 1 to 8, and the picture in the initial normal pre-tightening state is extracted;
the fourth step: the image acquired by the image acquisition module A is transmitted to the data processing module B through a wireless network, the data processing module B performs image processing on the initial image extracted by the image acquisition module A, and the image is grayed and then subjected to noise reduction in a Gaussian filtering mode, so that noise is reduced, and the image processing effect is ensured;
the fifth step: then, selecting a binarization threshold value based on a maximum inter-class variance method, and carrying out binarization processing on the gray scale picture subjected to noise reduction by the data processing module B;
and a sixth step: extracting bolt head central points of the bolt main bodies 2 by using circular Hough transform, namely extracting bolt head central points of 8 bolt main bodies 2 by using circular Hough transform, taking the points as position characteristic points of each bolt main body 2, dividing bolt group pictures by using canny operator detection edges to obtain a plurality of single bolt main body 2 pictures, and respectively and sequentially analyzing the pictures, wherein when the bolt main bodies 2 are analyzed, the edges and angular point geometric characteristics of two nuts of the bolt main bodies 2 are firstly extracted, wherein a horizontal datum line is drawn from the bolt rod central point, and two minimum angles are extracted towards the counterclockwise direction, and the two minimum angles respectively represent initial deviation datum line angles of the first nut 21 and the second nut 22;
the seventh step: gather each bolt main part 2 picture and initial picture and contrast, if angular deviation is greater than predetermined corner threshold value, or the data dispersion that certain bolt main part 2 was gathered at each moment in one day is great, then early warning module C is gone into to data, to measurement personnel transmission signal, notifies it and fastens the processing, judges whether the bolt lax condition has appeared through relative corner and whole corner between two nuts around the contrast bolt main part 2 is not hard up promptly.
The marker-free double-nut hexagon bolt looseness detection system based on image processing comprises an image acquisition module A, a data processing module B and an early warning module C, wherein the image acquisition module A, the data processing module B and the early warning module C are connected through a wireless network, an image collector 4 installed in the image acquisition module A firstly adjusts the position angle and distance, tests the imaging quality and the signal transmission quality, then transmits an image to the data processing module B, the data processing module B preprocesses the image, segments the bolt group image, extracts geometric characteristics alpha 1 and alpha 2, compares the geometric characteristics in the data processing module B with a preset alarm threshold alpha norm in a time-sharing way, and sends out an alarm when an offset value is larger than the alarm threshold; the detection system comprises components including an identification mainboard 1, a bolt main body 2, a protection frame 3 and an image collector 4, wherein both the bolt main body 2 and the protection frame 3 are arranged on the identification mainboard 1, the image collector 4 is arranged above the identification mainboard 1, the bolt main body 2 comprises a first nut 21, a second nut 22, a stud 23 and an expansion sleeve 24, the first nut 21 is positioned above the second nut 22, and the first nut 21 and the second nut 22 are the same in size; the detection system is characterized in that an image collector 4 is arranged right above a bolt group to be monitored when in use, the image collector 4 is required to be right opposite to the bolt body 2, meanwhile, the bolt body 2 is not shielded, the picture has no visual angle distortion and is clear in imaging, whether the communication among three modules A, B, C is normal or not is tested simultaneously, then the image shooting function of an image collection module A is started, whether the installation point position of the image collector 4 is reasonable or not is tested, namely whether the bolt body 2 is in the center of the picture or not, and whether the imaging is normal or not is tested, so that the image collector 4 in the image collection module A can accurately collect the image information of the bolt body 2, wherein the image collector 4 carries out data collection in different time periods, the bolt body 2 of the bolt group is shot through the image collection module A, the picture collected by the image collection module A is transmitted to a data, the data processing module B carries out image processing on the initial picture extracted by the image acquisition module A, wherein the picture is subjected to noise reduction in a Gaussian filtering mode after being grayed, then a binarization threshold value is selected based on a maximum inter-class variance method, and binarization processing is carried out on the gray scale picture subjected to noise reduction by the data processing module B; use circular hough transform to extract bolt main part 2's bolt head central point, and gather each bolt main part 2 picture and initial picture and contrast, if angular deviation is greater than predetermined corner threshold value, or the data dispersion that certain bolt main part 2 gathered at each moment in one day is great, then data afferent early warning module C, to measurement personnel transmission signal, inform it and fasten the processing, relative corner and whole corner between two nuts around promptly not hard up through comparison bolt main part 2 judge whether the bolt condition of loosing has appeared, the system just can be high-efficient and accurate like this monitor out the bolt condition of loosing.
In conclusion, compared with the traditional manual and mechanical bolt detection method, the marker-free double-nut hexagon bolt looseness detection system based on image processing saves a large amount of manpower, and does not depend on the personal experience of maintainers; compared with sensors based on the principles of sound, light, electricity and the like, the sensor mainly used in the scheme is an industrial camera, the cost is relatively low, due to the fact that non-contact monitoring is conducted, the sensor is not attached to the bolt tightly, normal work of the bolt is not affected, the detection system utilizes the self characteristics of the double-nut bolt as geometric identification, and extra image markers are not needed. The whole detection system can meet the requirement of engineering maintenance and has huge market demand space.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to cover the technical solutions and the inventive concepts of the present invention within the technical scope of the present invention.
Claims (6)
1. Marker double-nut hexagon bolt looseness detecting system based on image processing comprises an image acquisition module A, a data processing module B and an early warning module C, and is characterized in that: the image acquisition module A, the data processing module B and the early warning module C are connected through a wireless network, and the method comprises the following steps:
s1: firstly, an image collector (4) is arranged right above a bolt group to be monitored, and whether the communication among the three modules A, B, C is normal is tested;
s2: then starting an image shooting function of the image acquisition module A, and testing whether the mounting point position of the image acquisition device (4) is reasonable, namely whether the bolt main body (2) is in the center of an image and whether imaging is normal;
s3: shooting an initial picture, shooting a bolt main body (2) of the bolt group through an image acquisition module A, and extracting the picture in an initial normal pre-tightening state;
s4: the image acquired by the image acquisition module A is transmitted to the data processing module B through a wireless network, the data processing module B performs image processing on the initial image extracted by the image acquisition module A, and the image is grayed and then subjected to noise reduction in a Gaussian filtering mode;
s5: then, selecting a binarization threshold value based on a maximum inter-class variance method, and carrying out binarization processing on the gray scale picture subjected to noise reduction by the data processing module B;
s6: extracting a bolt head central point of each bolt main body (2) by using circular Hough transform, taking the point as a position characteristic point of each bolt main body (2), detecting an edge segmentation bolt group picture by using canny operators, obtaining a plurality of single bolt main body (2) pictures, and respectively and sequentially analyzing the pictures;
s7: gather each bolt main part (2) picture and initial picture and contrast, if angular deviation is greater than predetermined corner threshold value, or the data dispersion that each moment was gathered in certain bolt main part (2) one day is great, then data afferent early warning module C, to measurement personnel transmission signal, inform it and fasten the processing, judge whether the bolt lax condition has appeared through relative corner and whole corner between two nuts before and after comparing bolt main part (2) not hard up promptly.
2. The image processing-based marker-free double-nut hexagon bolt looseness detection system based on claim 1, wherein the image collector (4) in the S1 is required to be opposite to the bolt main body (2), meanwhile, the bolt main bodies (2) are not mutually shielded, a picture is free of visual angle distortion, and imaging is clear.
3. The image processing-based marker-free double-nut hexagon bolt looseness detection system based on claim 1, wherein in the step S2, if the number of bolts of the bolt main body (2) is large, and the mounting point is too close, image distortion is generated due to central projection, and the nut end face image of the bolt main body (2) cannot be completely collected; at the moment, the distance between the image collector (4) and the bolt main body (2) needs to be increased under the condition that the shot picture is clear and complete until the nut edge characteristics of each bolt main body (2) can be displayed.
4. The image-processing-based marker-free double-nut hexagon bolt looseness detection system based on claim 1, wherein during the analysis of the bolt body (2) in the step S6, edge and corner geometrical characteristics of two nuts of the bolt body (2) are extracted, wherein a horizontal reference line is drawn from a central point of a bolt rod, and two minimum angles are extracted towards a counterclockwise direction, and the minimum angles represent initial off-reference line angles of the first nut (21) and the second nut (22).
5. The image processing-based marker-free double-nut hexagon bolt looseness detection system according to claim 1, wherein the image collector (4) in the S2 can collect one picture in the better light condition of each day, such as 8:00, 10:00, 12:00, 14:00, 16:00 and 18: 00.
6. The image processing-based marker-free double-nut hexagon bolt looseness detection system based on the image processing, which is characterized in that components of the detection system comprise a marker mainboard (1), a bolt main body (2), a protective frame (3) and an image collector (4), wherein both the bolt main body (2) and the protective frame (3) are arranged on the marker mainboard (1), the image collector (4) is arranged above the marker mainboard (1), the bottom end of the protective frame (3) is welded and fixed with the center of the top surface of the marker mainboard (1), the protective frame (3) is kept vertical, the marker mainboard (1) is movably connected with the bolt main bodies (2) which are symmetrically distributed, the bolt main body (2) penetrates through the marker mainboard (1), the bolt main body (2) is located on two sides of the protective frame (3), and the bolt main body (2) comprises a first nut (21), Second nut (22), double-screw bolt (23) and inflation cover (24), sign mainboard (1) is run through in double-screw bolt (23), and double-screw bolt (23) are through the screw thread swing joint inflation cover (24) of its bottom, and first nut (21) of threaded connection and second nut (22) on double-screw bolt (23) through its top, and first nut (21) are located the top of second nut (22), and first nut (21) and second nut (22) contact, and first nut (21) are the same with second nut (22) size.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010799061.4A CN111932516A (en) | 2020-08-11 | 2020-08-11 | Mark-free double-nut hexagon bolt looseness detection system based on image processing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010799061.4A CN111932516A (en) | 2020-08-11 | 2020-08-11 | Mark-free double-nut hexagon bolt looseness detection system based on image processing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111932516A true CN111932516A (en) | 2020-11-13 |
Family
ID=73307306
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010799061.4A Pending CN111932516A (en) | 2020-08-11 | 2020-08-11 | Mark-free double-nut hexagon bolt looseness detection system based on image processing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111932516A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN112986146A (en) * | 2021-05-06 | 2021-06-18 | 上海建工集团股份有限公司 | Image recognition-based guide rail frame bolt connection reliability detection device |
CN114627059A (en) * | 2022-02-27 | 2022-06-14 | 扬州孚泰电气有限公司 | Data processing-based stockbridge damper bolt detection method |
CN114820620A (en) * | 2022-06-29 | 2022-07-29 | 中冶建筑研究总院(深圳)有限公司 | Bolt loosening defect detection method, system and device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202848953U (en) * | 2012-10-19 | 2013-04-03 | 武汉钢铁(集团)公司 | Rope loosing detecting device of winch |
CN103295027A (en) * | 2013-05-17 | 2013-09-11 | 北京康拓红外技术股份有限公司 | Freight wagon blocking key missing fault identification method based on support vector machine |
CN110688944A (en) * | 2019-09-26 | 2020-01-14 | 西南交通大学 | Bolt looseness monitoring method based on image recognition and machine learning |
-
2020
- 2020-08-11 CN CN202010799061.4A patent/CN111932516A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202848953U (en) * | 2012-10-19 | 2013-04-03 | 武汉钢铁(集团)公司 | Rope loosing detecting device of winch |
CN103295027A (en) * | 2013-05-17 | 2013-09-11 | 北京康拓红外技术股份有限公司 | Freight wagon blocking key missing fault identification method based on support vector machine |
CN110688944A (en) * | 2019-09-26 | 2020-01-14 | 西南交通大学 | Bolt looseness monitoring method based on image recognition and machine learning |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN112986146A (en) * | 2021-05-06 | 2021-06-18 | 上海建工集团股份有限公司 | Image recognition-based guide rail frame bolt connection reliability detection device |
CN114627059A (en) * | 2022-02-27 | 2022-06-14 | 扬州孚泰电气有限公司 | Data processing-based stockbridge damper bolt detection method |
CN114627059B (en) * | 2022-02-27 | 2022-12-13 | 扬州孚泰电气有限公司 | Data processing-based stockbridge damper bolt detection method |
CN114820620A (en) * | 2022-06-29 | 2022-07-29 | 中冶建筑研究总院(深圳)有限公司 | Bolt loosening defect detection method, system and device |
CN114820620B (en) * | 2022-06-29 | 2022-09-13 | 中冶建筑研究总院(深圳)有限公司 | Bolt loosening defect detection method, system and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111932516A (en) | Mark-free double-nut hexagon bolt looseness detection system based on image processing | |
CN103778681B (en) | A kind of vehicle-mounted highway cruising inspection system and data acquisition and disposal route | |
CN104318582B (en) | Detection method for bad state of rotating double-lug component pin of high-speed rail contact network | |
CN102759347B (en) | Online in-process quality control device and method for high-speed rail contact networks and composed high-speed rail contact network detection system thereof | |
CN110688944B (en) | Bolt looseness monitoring method based on image recognition and machine learning | |
CN104359418A (en) | Laser and video infused automatic railway snow depth multi-point measuring device and method | |
CN105976610B (en) | Bayonet crosses the detection Control for Dependability method and system of vehicle | |
CN111626204B (en) | Railway foreign matter invasion monitoring method and system | |
CN106485694A (en) | A kind of high ferro contact net double-jacket tube connector six-sided nut based on cascade classifier comes off defective mode detection method | |
CN103729908A (en) | Intelligent inspection device of railway tunnel and application method thereof | |
CN107391631A (en) | A kind of electric transmission line channel solid space monitoring and fast ranging method | |
CN105718964A (en) | Transmission line vibration damper visual detection method | |
CN113371028A (en) | Intelligent inspection system and method for electric bus-mounted track | |
KR102265496B1 (en) | Tongue Rail Approach Detector | |
CN116291724A (en) | Real-time early warning detection method and system for highway tunnel construction | |
CN111127409A (en) | Train component detection method based on SIFT image registration and cosine similarity | |
CN111553500B (en) | Railway traffic contact net inspection method based on attention mechanism full convolution network | |
CN204887277U (en) | Tunnel water damage intelligent monitoring system based on video event detection | |
CN111767913A (en) | Motor train unit vehicle fault dynamic image detection method based on deep learning | |
CN111664946A (en) | Wide-area temperature screening equipment | |
CN115755069A (en) | Track foreign matter detection device, detection system and detection method | |
CN112285111A (en) | Pantograph front carbon sliding plate defect detection method, device, system and medium | |
CN116129611A (en) | River bank collapse monitoring system and monitoring device | |
CN112946779B (en) | Point domain identification system and method for tunnel security monitoring | |
CN112508916A (en) | Road well lid damage and loss detection method based on mobile video analysis |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201113 |