CN113222935B - Method for detecting looseness and pretightening force loss of steel bridge bolt - Google Patents
Method for detecting looseness and pretightening force loss of steel bridge bolt Download PDFInfo
- Publication number
- CN113222935B CN113222935B CN202110522703.0A CN202110522703A CN113222935B CN 113222935 B CN113222935 B CN 113222935B CN 202110522703 A CN202110522703 A CN 202110522703A CN 113222935 B CN113222935 B CN 113222935B
- Authority
- CN
- China
- Prior art keywords
- nut
- image
- bolt
- loosening
- version
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 37
- 239000010959 steel Substances 0.000 title claims abstract description 37
- 238000001514 detection method Methods 0.000 claims abstract description 24
- 230000008569 process Effects 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 230000009466 transformation Effects 0.000 claims abstract description 6
- 230000000877 morphologic effect Effects 0.000 claims abstract description 5
- 230000009467 reduction Effects 0.000 claims abstract description 5
- 239000003550 marker Substances 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000005260 corrosion Methods 0.000 claims description 4
- 230000007797 corrosion Effects 0.000 claims description 4
- 230000008878 coupling Effects 0.000 claims description 3
- 238000010168 coupling process Methods 0.000 claims description 3
- 238000005859 coupling reaction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 abstract 1
- 230000011218 segmentation Effects 0.000 abstract 1
- 238000010276 construction Methods 0.000 description 3
- 238000011179 visual inspection Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009440 infrastructure construction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- 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
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- 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
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for detecting loosening and pretightening force loss of a steel bridge bolt. Belongs to the technical field of steel bridge detection, and comprises the following steps: marking a selected characteristic point of a nut corresponding to a bolt to be detected, and taking the selected characteristic point as a pixel positioning area for algorithm saliency recognition in the bolt loosening process; collecting nut images, and uploading the batch of nut images to a computer; performing image noise reduction through Gaussian filtering, converting RGB color space into HSV color space, combining morphological open operation, image binarization and threshold segmentation to locate nut characteristic mark points, and finishing image preprocessing; and distinguishing geometric centroids of positioning nuts at the boundary between the inner value and the outer value by using hough transformation, identifying coordinates at the characteristic mark points of the nuts by using a harris angular point detection method, deducing the coordinate position change at the characteristic mark points of the nuts between adjacent sample pictures, and calculating the loosening angle and the pretightening force loss value of the bolts. The invention has low detection cost and high precision; bolts in the steel structure bridge can be detected in batches.
Description
Technical Field
The invention belongs to the technical field of steel bridge detection, and relates to a method for detecting loosening and pretightening force loss of a steel bridge bolt; more particularly, the method relates to a method for detecting loosening and pretightening force loss of a steel bridge bolt based on image recognition.
Background
With the development of economy, bridges have become important points of infrastructure construction in China. In recent years, with the continuous increase of the steel yield in China, excessive steel yield is generated, and a plurality of committee stations such as national institutes, urban and rural and housing construction departments, transportation departments and the like take out files successively, so that the steel structure is popularized and widely applied to construction and transportation systems. The proportion of the steel structure bridges is increased year by year, and by the year 2019, the total of the highway and the railway bridges in China is more than 100 ten thousand, and the first bridge in ascend world is the major country.
The steel structure bridge has the outstanding advantages of high bearing capacity, strong spanning capability, wide application range and the like, and gradually becomes a preferred bridge form of a large-span bridge, a viaduct and a overpass bridge.
The high-strength bolt connection gradually replaces the traditional riveting and welding connection mode because of the advantages of simple construction, replaceability, high bearing capacity and the like, and becomes a main connection mode for steel bridge node connection. In the operation process of the bridge structure, the bridge structure is continuously subjected to the action of dynamic load fatigue vibration, so that potential safety hazards are brought to the bridge bolting. The safety of the whole bridge structure can be endangered due to untimely detection of loosening of the bolts. Therefore, a need exists for an efficient method of mass-detecting steel bridge bolts. The traditional bolt detection method mainly comprises manual visual inspection and sensor-based detection. The error of the manual visual inspection method is large, the manual visual inspection method mainly depends on experience of an operator, and the detection efficiency is low; the detection method based on the sensor can only detect one bolt at a time, equipment is high in price and needs to be installed on the bolt to be detected, and the problems that the bolt to be detected is difficult to replace due to expiration and the like exist.
The application number is: CN202011141777.1, titled: the invention patent of a railway wagon fastening bolt loosening image recognition method, which is provided by the invention patent, is not suitable for rapid batch inspection of bolts used for internal connection of steel structure bridges, does not have the relations of clear bolt types, shooting distances and shooting types, and is not suitable for detection of bolts of various types. Secondly, no report on the research of the pretightening force loss of the detection bolt is found.
Disclosure of Invention
The invention aims to: the invention aims to provide a method for detecting bolt looseness and pretightening force loss of a steel bridge, which has the advantages of low detection cost, high precision, high efficiency, capability of detecting bolt looseness and pretightening force loss in a steel structure bridge in batches and the like.
The technical scheme is as follows: the invention relates to a method for detecting loosening and pretightening force loss of a steel bridge bolt, which comprises the following specific operation steps:
(1.1) classifying samples of the steel structure bridge bolts according to specification types and strength grades, sequentially determining corner points where adjacent two sides of the upper surface of the nut corresponding to each type of bolts intersect, marking by using a marker pen to form characteristic marking points, and using the characteristic marking points as pixel positioning areas for algorithm salient identification;
(1.2) erecting an industrial camera on the front face of the nut marked with the characteristic mark points, namely, the industrial camera lens is opposite to the nut;
(1.3) setting the shooting frequency of the industrial camera, and adopting the set industrial camera to acquire images in the nut loosening process;
(1.4) transmitting the acquired nut image to a computer through a data transmission device, and performing image preprocessing to obtain a final version of the nut image;
(1.5) locating the geometric centroid of the nut surface in the final version of the nut image using hough transform;
(1.6) identifying nut feature mark point coordinates (x 1,y1),(x2,y2),(x3,y3)L(xm,ym) on a circle which takes the geometric centroid of the nut surface in the final version of the nut image as a circle center and takes the distance between the corner point where the measured nut has feature mark points and the opposite corner point as a diameter by adopting a harris corner detection method;
(1.7) substituting coordinates of any two nut feature mark points identified by the harris corner detection method into the following formula, and carrying out angle calculation, wherein the calculation formula is as follows:
Obtaining the angle difference of the characteristic mark points between the two images, namely the loosening angle of the bolt where the nut is positioned;
Wherein x ccd represents the industrial camera pixel size; r represents the distance between the corner where the nut has the characteristic mark point and the opposite corner; d f represents the industrial camera focal length size; d 0 represents the nut to industrial camera lens distance; (x m,ym),(xn,yn) represents the nut feature marker point location coordinates of any two images;
(1.8), substituting the measured bolt loosening angle into the relation between the bolt loosening angle and the pretightening force loss, wherein the specific formula is as follows:
Thereby forming a set of method for deducing the loosening angle of the bolt and judging the pretightening force loss of the bolt in real time;
Wherein θ represents the bolt loosening angle; f f represents the loss of the loosening pretightening force of the bolt; p represents the pitch size of the bolt; k t represents the spring constant of the bolted connection; k c represents the spring constant on the coupling where the bolt is located;
(1.9) repeating the steps (1.1) - (1.8), thereby detecting the loosening condition and the pretightening force loss condition of all shooting bolts.
Further, in the step (1.1), the shape of the feature mark point is a circle, and the radius is less than or equal to 0.5mm.
Further, in the step (1.2), the axial direction of the industrial camera lens is perpendicular to the plane of the nut, and the distance between the end of the industrial camera near the nut sample plane and the nut sample plane is 0.5 m-1.5 m.
Further, in step (1.3), the industrial camera captures a nut image, 2 frames per second.
Further, in the step (1.4), the specific operation steps of the image preprocessing are as follows:
(1.4.1) carrying out noise reduction treatment on the collected nut image by utilizing Gaussian filter transformation, and removing interference points in the nut image to obtain a first version of the nut image;
(1.4.2) converting the RGB color space of the noise-reduced nut image into an HSV color space, and enabling the characteristic mark points on the upper surface of the nut and the color of the upper surface of the nut to form contrast, so as to obtain a nut image two-plate after the color space conversion;
(1.4.3) performing a digital corrosion process on the structural elements of the second version of the nut image by using morphological opening operation, eliminating the connected parts of the structural elements of the second version of the nut image to obtain a third version of the nut image, amplifying the element details of the third version of the nut image by using a digital expansion process to obtain a fourth version of the nut image, and performing a denoising process on the edges of the fourth version of the nut image to obtain a fifth version of the nut image;
And (1.4.4) performing binarization processing on the nut image five-plate to enable the edge outline of the nut image to be clearer, obtaining a nut image six-plate, and dividing the nut image six-plate after the binarization processing into nut characteristic mark points and nut non-characteristic mark points by combining a global threshold value, so as to obtain a nut image final plate.
Further, in step (1.6), the nut feature mark points identified by the harris corner detection method are on a circle with the geometric centroid of the nut surface in the final version of the nut image as the center of a circle and the distance between the corner point where the measured nut feature mark points are located and the opposite corner point of the measured nut feature mark points as the diameter.
Further, the bolt where the nut is located is a large hexagon head high-strength bolt used for internal connection of the steel structure bridge.
The beneficial effects are that: compared with the prior art, the invention has the advantages of low detection cost, high precision, high efficiency, capability of detecting the loosening condition and the pretightening force loss condition of bolts in the steel structure bridge in batches, and the like.
Drawings
FIG. 1 is a schematic flow chart of the present invention;
the point 1 in fig. 2 is the selected position of the characteristic mark point of the nut in the invention;
the point shown at 2 in fig. 3 is the geometric centroid of the nut surface in the final version of the nut image in accordance with the present invention.
Detailed Description
The following describes the implementation of the present invention in detail with reference to the accompanying drawings.
The invention discloses a method for detecting loosening and pretightening force loss of a steel bridge bolt, which comprises the following specific operation steps:
(1.1) classifying samples of the steel structure bridge bolts according to specification types and strength grades, sequentially determining corner points where adjacent two sides of the upper surface of the nut corresponding to each type of bolts intersect, marking by using a marker pen to form characteristic marking points, and using the characteristic marking points as pixel positioning areas for algorithm salient identification;
(1.2) erecting an industrial camera on the front face of the nut marked with the characteristic mark points, namely, the industrial camera lens is opposite to the nut;
(1.3) setting the shooting frequency of the industrial camera, and adopting the set industrial camera to acquire images in the nut loosening process;
(1.4) transmitting the acquired nut image to a computer through a data transmission device, and performing image preprocessing to obtain a final version of the nut image;
(1.5) locating the geometric centroid of the nut surface in the final version of the nut image using hough transform;
(1.6) identifying nut feature mark point coordinates (x 1,y1),(x2,y2),(x3,y3)L(xm,ym) on a circle which takes the geometric centroid of the nut surface in the final version of the nut image as a circle center and takes the distance between the corner point where the measured nut has feature mark points and the opposite corner point as a diameter by adopting a harris corner detection method;
(1.7) substituting coordinates of any two nut feature mark points identified by the harris corner detection method into the following formula, and carrying out angle calculation, wherein the calculation formula is as follows:
Obtaining the angle difference of the characteristic mark points between the two images, namely the loosening angle of the bolt where the nut is positioned;
Wherein x ccd represents the industrial camera pixel size; r represents the distance between the corner where the nut has the characteristic mark point and the opposite corner; d f represents the industrial camera focal length size; d 0 represents the nut to industrial camera lens distance; (x m,ym),(xn,yn) represents the nut feature marker point location coordinates of any two images;
(1.8), substituting the measured bolt loosening angle into the relation between the bolt loosening angle and the pretightening force loss, wherein the specific formula is as follows:
Thereby forming a set of method for deducing the loosening angle of the bolt and judging the pretightening force loss of the bolt in real time;
Wherein θ represents the bolt loosening angle; f f represents the loss of the loosening pretightening force of the bolt; p represents the pitch size of the bolt; k t represents the spring constant of the bolted connection; k c represents the spring constant on the coupling where the bolt is located;
(1.9) repeating the steps (1.1) - (1.8), thereby detecting the loosening condition and the pretightening force loss condition of all shooting bolts.
Further, in the step (1.1), the shape of the feature mark point is a circle, and the radius is less than or equal to 0.5mm.
Further, in the step (1.2), the axial direction of the industrial camera lens is perpendicular to the plane of the nut, and the distance between the end of the industrial camera near the nut sample plane and the nut sample plane is 0.5 m-1.5 m.
Further, in step (1.3), the industrial camera captures a nut image, 2 frames per second.
Further, in the step (1.4), the specific operation steps of the image preprocessing are as follows:
(1.4.1) carrying out noise reduction treatment on the collected nut image by utilizing Gaussian filter transformation, and removing interference points in the nut image to obtain a first version of the nut image;
(1.4.2) converting the RGB color space of the noise-reduced nut image into an HSV color space, and enabling the characteristic mark points on the upper surface of the nut and the color of the upper surface of the nut to form contrast, so as to obtain a nut image two-plate after the color space conversion;
(1.4.3) performing a digital corrosion process on the structural elements of the second version of the nut image by using morphological opening operation, eliminating the connected parts of the structural elements of the second version of the nut image to obtain a third version of the nut image, amplifying the element details of the third version of the nut image by using a digital expansion process to obtain a fourth version of the nut image, and performing a denoising process on the edges of the fourth version of the nut image to obtain a fifth version of the nut image;
And (1.4.4) performing binarization processing on the nut image five-plate to enable the edge outline of the nut image to be clearer, obtaining a nut image six-plate, and dividing the nut image six-plate after the binarization processing into nut characteristic mark points and nut non-characteristic mark points by combining a global threshold value, so as to obtain a nut image final plate.
Further, in step (1.6), the nut feature mark points identified by the harris corner detection method are on a circle with the geometric centroid of the nut surface in the final version of the nut image as the center of a circle and the distance between the corner point where the measured nut feature mark points are located and the opposite corner point of the measured nut feature mark points as the diameter.
Furthermore, the bolts where the nuts are located are large hexagon head high-strength bolts of M20, M22, M24, M27 or M30 types, which are used for internal connection of the steel structure bridge.
Specifically, as shown in fig. 1, the novel method for detecting loosening and pretightening force loss of a steel bridge bolt comprises the following specific steps:
Firstly, classifying samples of steel structure bridge bolts according to specification types and strength grades, selecting M30 and 10.9S large hexagon head bolts in the steel structure bridge as acquisition samples, sequentially determining corner points where two adjacent edges of the upper surface of a nut corresponding to the type bolts intersect, marking the corner points where the two adjacent edges of the upper surface of the nut intersect by adopting a red marker pen to form feature marking points, and taking the feature marking points as pixel positioning areas which are highlighted and identified by an algorithm;
Secondly, erecting an industrial camera with a sea Conway view MV-CA020-10GC, and erecting the industrial camera on the front surface of the nut with the characteristic mark points, namely, the industrial camera lens is opposite to the nut, the axial direction of the industrial camera lens is perpendicular to the plane of the nut, and the distance between the sample plane end of the industrial camera near the nut and the plane of the nut is 0.5 m;
Setting the shooting frequency of the industrial camera to be 2 frames per second, and taking the initial position of the nut with the characteristic mark point as the reference, sequentially loosening the nut with the characteristic mark point by 10 degrees, 20 degrees and 30 degrees, and adopting the set industrial camera to acquire images;
Step four, transmitting the acquired nut image to a computer through a data transmission device, and carrying out image preprocessing;
preferentially, the specific content and steps of the image preprocessing comprise:
step 1, carrying out noise reduction treatment on the collected nut image by utilizing Gaussian filter transformation, and removing interference points in the nut image to obtain a first version of the nut image;
Step2, converting the RGB color space of the noise-reduced nut image into an HSV color space, and enabling the characteristic mark points on the upper surface of the nut and the color of the upper surface of the nut to form contrast, so as to obtain a nut image two-plate after the color space conversion;
step 3, performing a digital corrosion process on the two-version structural elements of the nut image by using morphological opening operation, eliminating the connected parts of the two-version structural elements of the nut image to obtain a three-version nut image, amplifying the element details of the three-version nut image by using a digital expansion process to obtain a four-version nut image, and performing a denoising process on the edges of the four-version nut image to obtain a five-version nut image;
Step 4, performing binarization processing on the nut image five-plate to enable the edge contour of the nut image to be clearer, obtaining a nut image six-plate, and dividing the nut image six-plate after the binarization processing into nut characteristic mark points and nut non-characteristic mark points by combining a global threshold value to obtain a nut image final plate;
fifthly, adopting hough transformation to position the geometric centroid of the nut surface in the final version of the nut image;
Sixthly, recognizing that coordinates of nut feature mark points on a circle taking a geometric centroid of a nut surface in a final version of the nut image as a circle center and taking a distance between an angular point where the nut feature mark points are located and a relative angular point as a diameter are respectively (x 1＝925,y1＝772);(x2＝943,y2 =771) by adopting a harris angular point detection method;
(x3＝960,y3＝769);(x4＝976,y4＝768)；
Seventhly, substituting coordinates of centers of any two nut mark areas identified by the harris corner detection method into the following formula to calculate angles:
Wherein: the dimension x ccd of the industrial camera pixel is 4.5x10 -6 mm; the distance R between the corner point where the characteristic mark point of the nut is positioned and the opposite corner point of the nut is 56.63mm; the focal length D f of the industrial camera is 12mm; the nut-to-industrial camera lens distance D 0 is 5 x 10 2 mm.
Wherein, statistics of bolt recognition loosening angle and accuracy are shown in table 1;
Table 1: m30 bolt 5X 10 2 mm horizontal distance sample algorithm identification result
Eighth, substituting the angle identified by the algorithm into the relation between the loosening angle of the bolt and the pretightening force loss of the bolt:
Wherein: the bolt loosening angle theta identified by the algorithm is shown in the table 1; the pre-tightening force loss of the bolt is F f, and the details are shown in Table 2; the pitch dimension P of the M30 bolt is 3.5mm; the spring constant K t of the bolt connection is 8.8X10- 4 kg/mm; the spring constant K c of the connecting piece where the bolt is positioned is 126 multiplied by 10 4 kg/mm;
table 2: m30 bolt 5X 10 2 mm horizontal distance sample algorithm identification result
Ninth step: repeating the steps, and detecting all shooting bolt loosening conditions and pretightening force loss conditions.
Claims (7)
1. A method for detecting loosening and pretightening force loss of a steel bridge bolt, characterized by: the specific operation steps are as follows:
(1.1) classifying samples of the steel structure bridge bolts according to specification types and strength grades, sequentially determining corner points where adjacent two sides of the upper surface of the nut corresponding to each type of bolts intersect, marking by using a marker pen to form characteristic marking points, and using the characteristic marking points as pixel positioning areas for algorithm salient identification;
(1.2) erecting an industrial camera on the front face of the nut marked with the characteristic mark points, namely, the industrial camera lens is opposite to the nut;
(1.3) setting the shooting frequency of the industrial camera, and adopting the set industrial camera to acquire images in the nut loosening process;
(1.4) transmitting the acquired nut image to a computer through a data transmission device, and performing image preprocessing to obtain a final version of the nut image;
(1.5) locating the geometric centroid of the nut surface in the final version of the nut image using hough transform;
(1.6) identifying nut feature mark point coordinates (x 1,y1),(x2,y2),(x3,y3)L(xm,ym) on a circle which takes the geometric centroid of the nut surface in the final version of the nut image as a circle center and takes the distance between the corner point where the measured nut has feature mark points and the opposite corner point as a diameter by adopting a harris corner detection method;
(1.7) substituting coordinates of any two nut feature mark points identified by the harris corner detection method into the following formula, and carrying out angle calculation, wherein the calculation formula is as follows:
Obtaining the angle difference of the characteristic mark points between the two images, namely the loosening angle of the bolt where the nut is positioned;
Wherein x ccd represents the industrial camera pixel size; r represents the distance between the corner where the nut has the characteristic mark point and the opposite corner; d f represents the industrial camera focal length size; d 0 represents the nut to industrial camera lens distance; (x m,ym),(xn,yn) represents the nut feature marker point location coordinates of any two images;
(1.8), substituting the measured bolt loosening angle into the relation between the bolt loosening angle and the pretightening force loss, wherein the specific formula is as follows:
Thereby forming a set of method for deducing the loosening angle of the bolt and judging the pretightening force loss of the bolt in real time;
Wherein θ represents the bolt loosening angle; f f represents the loss of the loosening pretightening force of the bolt; p represents the pitch size of the bolt; k t represents the spring constant of the bolted connection; k c represents the spring constant on the coupling where the bolt is located;
(1.9) repeating the steps (1.1) - (1.8), thereby detecting the loosening condition and the pretightening force loss condition of all shooting bolts.
2. The method for detecting loosening and loss of pretension of a steel bridge bolt according to claim 1, wherein in step (1.1), the feature-marked point is circular in shape with a radius of 0.5mm or less.
3. The method for detecting loosening and loss of pretightening force of a steel bridge bolt according to claim 1, wherein in step (1.2), the axial direction of the industrial camera lens is perpendicular to the plane of the nut, and the distance between the end of the industrial camera near the nut sample plane and the nut sample plane is 0.5m to 1.5m.
4. A method for detecting steel bridge bolt loosening and pretensioning loss according to claim 1, wherein in step (1.3), the industrial camera takes a nut image of 2 frames per second.
5. The method for detecting loosening and loss of pretension of steel bridge bolts according to claim 1, wherein in step (1.4), the specific operation steps of the image preprocessing are as follows:
(1.4.1) carrying out noise reduction treatment on the collected nut image by utilizing Gaussian filter transformation, and removing interference points in the nut image to obtain a first version of the nut image;
(1.4.2) converting the RGB color space of the noise-reduced nut image into an HSV color space, and enabling the characteristic mark points on the upper surface of the nut and the color of the upper surface of the nut to form contrast, so as to obtain a nut image two-plate after the color space conversion;
(1.4.3) performing a digital corrosion process on the structural elements of the second version of the nut image by using morphological opening operation, eliminating the connected parts of the structural elements of the second version of the nut image to obtain a third version of the nut image, amplifying the element details of the third version of the nut image by using a digital expansion process to obtain a fourth version of the nut image, and performing a denoising process on the edges of the fourth version of the nut image to obtain a fifth version of the nut image;
And (1.4.4) performing binarization processing on the nut image five-plate to enable the edge outline of the nut image to be clearer, obtaining a nut image six-plate, and dividing the nut image six-plate after the binarization processing into nut characteristic mark points and nut non-characteristic mark points by combining a global threshold value, so as to obtain a nut image final plate.
6. The method for detecting loosening and loss of pretightening force of a steel bridge bolt according to claim 1, wherein in step (1.6), the nut feature mark points identified by the harris corner detection method are on a circle having a center of a geometric centroid of a nut surface in a final version of the nut image and a diameter of a corner where the detected nut feature mark points are located and a distance of a relative corner thereof.
7. The method for detecting loosening and pretightening force loss of a steel bridge bolt according to claims 1 to 6, wherein the bolt where the nut is located is a large hexagon head high strength bolt used for internal connection of a steel bridge.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110522703.0A CN113222935B (en) | 2021-05-13 | 2021-05-13 | Method for detecting looseness and pretightening force loss of steel bridge bolt |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110522703.0A CN113222935B (en) | 2021-05-13 | 2021-05-13 | Method for detecting looseness and pretightening force loss of steel bridge bolt |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113222935A CN113222935A (en) | 2021-08-06 |
| CN113222935B true CN113222935B (en) | 2024-04-23 |
Family
ID=77095336
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110522703.0A Active CN113222935B (en) | 2021-05-13 | 2021-05-13 | Method for detecting looseness and pretightening force loss of steel bridge bolt |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113222935B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN117853420B (en) * | 2023-12-18 | 2024-10-29 | 天津农学院 | Steel structure bolt loosening detection method based on machine vision |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104680517A (en) * | 2015-01-22 | 2015-06-03 | 清华大学 | Looseness detection method of bolt |
| US9127998B1 (en) * | 2012-09-04 | 2015-09-08 | University Of South Florida | Active ultrasonic method of quantifying bolt tightening and loosening |
| KR20160136905A (en) * | 2015-05-21 | 2016-11-30 | 부경대학교 산학협력단 | Bolt-loosening Detection Method and Computer Program Thereof |
| CN107145905A (en) * | 2017-05-02 | 2017-09-08 | 重庆大学 | Image Recognition Detection Method for Elevator Fastening Nut Looseness |
| KR101819711B1 (en) * | 2016-07-22 | 2018-01-29 | 충북대학교 산학협력단 | Apparatus and method for detecting nut locking using machine vision |
| CN111002259A (en) * | 2019-10-23 | 2020-04-14 | 武汉理工大学 | Rail nut loosening detection and maintenance device and method based on CCD camera |
| CN112545790A (en) * | 2020-11-20 | 2021-03-26 | 江苏科技大学 | Combined bed-chair integrated equipment and control method thereof |
| CN112767359A (en) * | 2021-01-21 | 2021-05-07 | 中南大学 | Steel plate corner detection method and system under complex background |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019153138A1 (en) * | 2018-02-07 | 2019-08-15 | 大连理工大学 | Real-time high-precision bolt preload detection method and system employing piezoelectric ultrasonic chip |
-
2021
- 2021-05-13 CN CN202110522703.0A patent/CN113222935B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9127998B1 (en) * | 2012-09-04 | 2015-09-08 | University Of South Florida | Active ultrasonic method of quantifying bolt tightening and loosening |
| CN104680517A (en) * | 2015-01-22 | 2015-06-03 | 清华大学 | Looseness detection method of bolt |
| KR20160136905A (en) * | 2015-05-21 | 2016-11-30 | 부경대학교 산학협력단 | Bolt-loosening Detection Method and Computer Program Thereof |
| KR101819711B1 (en) * | 2016-07-22 | 2018-01-29 | 충북대학교 산학협력단 | Apparatus and method for detecting nut locking using machine vision |
| CN107145905A (en) * | 2017-05-02 | 2017-09-08 | 重庆大学 | Image Recognition Detection Method for Elevator Fastening Nut Looseness |
| CN111002259A (en) * | 2019-10-23 | 2020-04-14 | 武汉理工大学 | Rail nut loosening detection and maintenance device and method based on CCD camera |
| CN112545790A (en) * | 2020-11-20 | 2021-03-26 | 江苏科技大学 | Combined bed-chair integrated equipment and control method thereof |
| CN112767359A (en) * | 2021-01-21 | 2021-05-07 | 中南大学 | Steel plate corner detection method and system under complex background |
Non-Patent Citations (3)
| Title |
|---|
| 基于图像识别技术的电机换向片自动检测系统;张建辉，宋平岗;电工电能新技术;-;第-卷(第04期);全文 * |
| 基于归一化频响函数曲率差的钢-木组合梁螺栓松动定位方法;刘景良;陈飞宇;郑文婷;盛叶;骆勇鹏;铁道科学与工程学报(第002期);全文 * |
| 郭珍珠1 ; 赵伟1,2.公路钢桥高强度螺栓松动检测技术研究进展.中国钢结构协会结构稳定与疲劳分会第17届(ISSF-2021)学术交流会暨教学研讨会.2020,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113222935A (en) | 2021-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113222935B (en) | Method for detecting looseness and pretightening force loss of steel bridge bolt | |
| Kim et al. | Unmanned aerial vehicle (UAV)-powered concrete crack detection based on digital image processing | |
| CN107169953B (en) | Detection method of bridge concrete surface cracks based on HOG feature | |
| CN104608799B (en) | Based on information fusion technology Railway wheelset tread damage on-line checking and recognition methodss | |
| US11354814B2 (en) | Vision-based fastener loosening detection | |
| CN109682839B (en) | Online detection method for surface defects of metal arc-shaped workpiece | |
| CN110211101A (en) | A kind of rail surface defect rapid detection system and method | |
| Schmugge et al. | Crack segmentation by leveraging multiple frames of varying illumination | |
| CN105865344A (en) | Workpiece dimension measuring method and device based on machine vision | |
| CN101807352A (en) | Method for detecting parking stalls on basis of fuzzy pattern recognition | |
| CN106845444A (en) | A kind of vehicle well cover detection method combined based on acnode | |
| CN113469966A (en) | Train bolt looseness detection method based on anti-loosening line identification | |
| CN110610516B (en) | Railway fastener nut center positioning method | |
| CN108694349B (en) | Pantograph image extraction method and device based on linear array camera | |
| CN112102287B (en) | An image-based automatic detection and identification method of green ball cracks | |
| CN108764234A (en) | A kind of liquid level instrument Recognition of Reading method based on crusing robot | |
| CN114219773B (en) | Pre-screening and calibrating method for bridge crack detection data set | |
| CN113516629A (en) | TFDS passed the job intelligent detection system | |
| CN111027530A (en) | Preprocessing method based on tire embossed character recognition | |
| CN114581385A (en) | Welding seam defect area mapping algorithm based on circle positioning | |
| CN112710632A (en) | Method and system for detecting high and low refractive indexes of glass beads | |
| CN109934135A (en) | A low-rank matrix factorization-based method for detecting foreign objects in railway tracks | |
| CN106504246A (en) | The image processing method of tunnel slot detection | |
| Berwo et al. | Automotive engine cylinder head crack detection: Canny edge detection with morphological dilation | |
| CN108645865A (en) | A kind of measurement method of the submerged-arc welding steel pipe weld seam amount of the being partially welded parameter based on CCD |
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 |