CN116559172A - Unmanned aerial vehicle-based steel bridge welding seam detection method and system - Google Patents
Unmanned aerial vehicle-based steel bridge welding seam detection method and system Download PDFInfo
- Publication number
- CN116559172A CN116559172A CN202310443128.4A CN202310443128A CN116559172A CN 116559172 A CN116559172 A CN 116559172A CN 202310443128 A CN202310443128 A CN 202310443128A CN 116559172 A CN116559172 A CN 116559172A
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- steel bridge
- welding seam
- video image
- 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
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 55
- 239000010959 steel Substances 0.000 title claims abstract description 55
- 238000001514 detection method Methods 0.000 title claims abstract description 43
- 238000003466 welding Methods 0.000 title claims description 43
- 230000007547 defect Effects 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000013135 deep learning Methods 0.000 claims abstract description 4
- 238000005516 engineering process Methods 0.000 claims description 12
- 230000005540 biological transmission Effects 0.000 claims description 10
- 238000005259 measurement Methods 0.000 claims description 6
- 230000002146 bilateral effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000008054 signal transmission Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 238000010845 search algorithm Methods 0.000 abstract 1
- 239000007822 coupling agent Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G06T5/73—
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/80—Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
-
- 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
- G01N2021/8893—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 providing a video image and a processed signal for helping visual decision
-
- 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
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30132—Masonry; Concrete
-
- 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
- G06T2207/30152—Solder
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Abstract
The invention discloses a steel bridge weld joint detection method and system based on an unmanned aerial vehicle, which relate to the field of partial discharge monitoring of transformers, wherein a weld joint video image of a steel bridge is shot in real time by using an unmanned aerial vehicle carried with a high-definition camera, the weld joint video of the steel bridge is preprocessed by using a space-time context search algorithm and a defogging algorithm, haze and hot waves in the video image are effectively removed, a weld joint video image is identified by using a single-target detection algorithm YOLOv7 based on deep learning, a corresponding weight file is established aiming at a detection target, weld joint defects in the video are identified by selecting a proper threshold value, reasonable identification of the defects is realized, weak GPS signals and magnetic field interference around the steel bridge are important factors for limiting the application of the commercial unmanned aerial vehicle in bridge near-distance detection, and the influence of the GPS signals and the magnetic field interference of the steel bridge is effectively avoided by using the positioning method based on the ultra-wideband.
Description
Technical Field
The invention relates to the field of bridge overhaul, in particular to a steel bridge welding seam detection method and system based on an unmanned aerial vehicle.
Background
The steel bridge is a bridge which uses steel as a main building material and has the advantages of high strength, high rigidity, high spanning capacity, convenience in transportation, high installation speed and the like. It has been found that under the influence of increasing vehicle loads and natural environment erosion, the weld joint may be damaged to different extents, for example fatigue cracking, weld joint corrosion, etc., which may have an adverse effect on the load-carrying capacity of the bridge. Aiming at the damage detection method of the steel bridge welding seam, the identification of the welding seam defect is mainly carried out by an ultrasonic nondestructive detection technology at present. During ultrasonic wave propagation, the detected sound waves are different due to the influence of a plurality of factors, so that a detector judges the welding line defects of the bridge of the steel structure based on the characteristics of the sound waves. In addition, when the weld defect volume is great, ultrasonic detection accuracy can receive great influence, in order to ensure detection accuracy, needs manual assistance. In addition, the requirement on the roughness of the welding seam by the ultrasonic detection technology is relatively high, and if the roughness of the welding seam does not meet the requirement of ultrasonic detection, the technology cannot be adopted for detection.
Aiming at the damage detection method of the steel bridge welding seam, the identification of the welding seam defect is mainly carried out by an ultrasonic nondestructive detection technology at present. When ultrasonic wave propagates, because the influence of a plurality of factors also varies, consequently, the inspector can judge steel construction bridge welding seam defect based on the characteristic of sound wave, in addition, when welding seam defect volume is great, ultrasonic detection accuracy can receive great influence, in order to ensure detection accuracy, needs the manual work to assist, and ultrasonic detection technique's requirement on welding seam roughness is relatively higher, if welding seam roughness does not accord with ultrasonic detection requirement, can not adopt this technique to detect.
Disclosure of Invention
The invention aims to provide a steel bridge welding seam detection method and system based on an unmanned aerial vehicle, which are used for solving the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a steel bridge welding seam detection method and system based on unmanned aerial vehicle, the steel bridge welding seam detection steps are:
and S1, shooting a welding line video image of the steel bridge in real time by using an unmanned aerial vehicle-mounted high-definition camera.
S2, preprocessing the steel bridge weld video through a space-time context searching algorithm and a defogging algorithm, and effectively removing haze and heat waves in the video image.
And S3, recognizing a weld joint video image shot by a high-definition camera in real time by utilizing a single-target detection algorithm YOLOv7 based on deep learning, establishing a corresponding weight file aiming at a detection target, and recognizing the weld joint defect in the video by selecting a proper threshold value so as to realize reasonable recognition of the defect.
S4: the space coordinates of four UWB anchor points are measured by the positioning principle of an ultra-wideband positioning method, and then the distance between the beacon and the anchor points on the unmanned aerial vehicle is determined by a bilateral two-way ranging method.
S5: and the defect position and defect type of the steel bridge welding seam are obtained through the image processing technology, and the operation safety of the bridge is evaluated in real time by combining the historical data of the health condition of the steel bridge.
2. The unmanned aerial vehicle-based steel bridge weld detection method and system as claimed in claim 1, wherein: the calculation mode in S4 is as follows: the coordinates of the unmanned aerial vehicle calculated by using the spatial coordinates of the four UWB anchor points measured are (x 1, y1, z 1), (x 2, y2, z 2), (x 3, y3, z 3) and (x 4, y4, z 4), and the linear distances between the four anchor points and the unmanned aerial vehicle are R1, R2, R3 and R4. Based on the four-point three-dimensional space positioning principle, the following equation is obtained:
where i=1, 2,3,4. The above equation can be converted into
When the UWB anchor point is arranged, (x 1, y1, z 1), (x 2, y2, z 2), (x 3, y3, z 3), (x 4, y4, z 4) can be measured, and in order to solve the unmanned aerial vehicle coordinates from the above equation, R1, R2, R3 and R4 at each moment need to be calculated, which means that the accuracy of the unmanned aerial vehicle coordinates is directly related to the accuracy of the distance measurement between the anchor point and the unmanned aerial vehicle.
And (3) setting an ultra-wideband anchor point on the unmanned aerial vehicle as a beacon, determining the distance between the beacon and the anchor point on the unmanned aerial vehicle by adopting a bilateral two-way ranging method, namely, transmitting a ranging signal by the anchor point, and transmitting the ranging signal again by the target beacon on the unmanned aerial vehicle after receiving the target beacon on the unmanned aerial vehicle, and receiving by the anchor point. In the first round of ranging signal transmission and reception, the time difference between transmission and reception of the anchor is set to be around 1, the time difference between transmission and reception of the target beacon is set to be around 1, and the time difference of the second round is set to be around 2 and around 2.
The time of flight (TOF) of a wireless signal can be expressed as:
the above equation can be converted into
T round1 ×T round2 ＝T tof (T round1 +T round2 +T reply1 +T reply2 ) (4)
Get the calculation formula of Ttof
In practical applications, there is an error in the time difference between beacon reception and transmission. The errors of the first and second wheel are denoted e1 and e2, respectively. Thus, the measurement of Ttof can be expressed as:
thus, the error of Ttof is determined by the following formula
The higher order terms are ignored and the higher order terms are ignored,
3. the steel bridge welding seam detection method and system based on the unmanned aerial vehicle, wherein the unmanned aerial vehicle performs the following steps when acquiring the video image of the welding seam of the web bottom plate of the steel box girder:
s1: controlling the unmanned aerial vehicle to fly along the welding seam of the steel box girder web bottom plate through a control source;
s2: acquiring the space position of the advancing unmanned aerial vehicle by a positioning method based on ultra-wideband, and positioning the unmanned aerial vehicle;
s3: in the flight process, acquiring a welding line video image through a high-definition camera;
s4: transmitting the acquired welding line video image to a computer terminal in real time through a 5G network component and an anti-interference component in the multifunctional integrated component;
s5: after analyzing the collected video images, if the requirements are not met, secondary collection is carried out after the parameters such as the flying speed, the flying height and the like are adjusted.
Compared with the prior art, the invention has the beneficial effects that:
1. the steel bridge weld joint video is preprocessed through a space-time context searching algorithm and a defogging algorithm, so that haze and heat waves in the video image are effectively removed, and the problem that when the YOLOv7 is utilized to identify the weld joint video image, the haze and heat waves affect the weld joint in the video image, so that weld joint defects cannot be accurately identified is avoided. By performing weld defect identification through YOLOv7, the identification speed and accuracy are remarkably improved, and compared with an ultrasonic detection technology, the method effectively avoids the addition of a coupling agent on the surface of the steel box girder and breaks through the limitation of the requirement of the ultrasonic detection technology on the roughness of the weld.
2. The method for positioning the weld defects based on the ultra-wideband effectively avoids the influence of the weak GPS signals and the magnetic field interference of the steel bridge, wherein the weak GPS signals and the magnetic field interference of the surrounding of the steel bridge are important factors for limiting the application of the commercial unmanned aerial vehicle in the short-distance bridge detection.
Drawings
FIG. 1 is a flow chart of video acquisition of a steel box girder weld joint;
FIG. 2 is a schematic view of video acquisition of a steel box girder weld joint according to the present invention;
fig. 3 is a schematic structural view of the unmanned aerial vehicle according to the present invention;
fig. 4 is a schematic diagram of the positioning principle based on the ultra wideband beacon of the present invention.
In the figure: 1. unmanned plane; 2. high definition camera; 3. a support bracket; 4. a rotor; 5. ultra-wideband anchor points; 6. and a multifunctional integrated component.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1 to 4, in the embodiment of the invention, based on the steps of the method and the system for detecting the welding seam of the steel bridge, the high-definition camera 2 is utilized to shoot the video image of the welding seam of the steel bridge in real time, the unmanned aerial vehicle 1 is utilized to carry the high-definition camera 2 to shoot the video image of the welding seam of the steel bridge in real time, as shown in fig. 2, the welding seam of the web plate and the bottom plate of the steel box girder is taken as an example for illustration, and the shot video image information of the welding seam is wirelessly transmitted to a computer terminal in real time through the multifunctional integrated component 5 to detect the welding seam of the steel bridge in real time.
The specific operation mode is as follows:
the steel bridge weld joint video acquired on site through the high-definition camera 2 can be influenced by haze and heat waves, the haze and heat waves in the video image are effectively removed by preprocessing the steel bridge weld joint video through a space-time context searching algorithm and a defogging algorithm, and the effect of haze and heat waves on weld joints in the video image when the YOLOv7 is utilized for identifying the weld joint video image is prevented, so that weld joint defects cannot be accurately identified.
And identifying the weld joint video image shot by the high-definition camera 2 in real time by utilizing a single-target detection algorithm YOLOv7 based on deep learning, establishing a corresponding weight file aiming at a detection target, and identifying the weld joint defect in the video by selecting a proper threshold value to realize reasonable identification of the defect, wherein the excessive or insufficient value of the threshold value can lead to poor target detection precision. By performing weld defect identification through YOLOv7, the identification speed and accuracy are remarkably improved, and compared with an ultrasonic detection technology, the method effectively avoids the addition of a coupling agent on the surface of the steel box girder and breaks through the limitation of the requirement of the ultrasonic detection technology on the roughness of the weld.
The positioning method of the welding seam detection position through the GPS of the commercial unmanned aerial vehicle 1 can be interfered by the magnetic field around the steel bridge, and the identified welding seam defect needs to be positioned through the positioning method based on the ultra-wideband, so that the steel bridge is prevented from interfering the positioning of the unmanned aerial vehicle 1.
Based on the positioning principle of the ultra wideband positioning method, it is assumed that the spatial coordinates of the four UWB anchors are (x 1, y1, z 1), (x 2, y2, z 2), (x 3, y3, z 3) and (x 4, y4, z 4), respectively. The coordinates of the unmanned aerial vehicle 1 to be calculated are (xt, yt, zt), and the straight line distances between the four anchors and the unmanned aerial vehicle 1 are R1, R2, R3 and R4 respectively. Based on the four-point three-dimensional space positioning principle, the following equation is obtained:
where i=1, 2,3,4. The above equation can be converted into
When the UWB anchor point is arranged, (x 1, y1, z 1), (x 2, y2, z 2), (x 3, y3, z 3), (x 4, y4, z 4) can be measured, and in order to solve the unmanned aerial vehicle 1 coordinates from the above equation, R1, R2, R3 and R4 at each moment need to be calculated, which means that the accuracy of the unmanned aerial vehicle 1 coordinates is directly related to the accuracy of the distance measurement between the anchor point and the unmanned aerial vehicle 1.
The ultra-wideband anchor 54 on the unmanned aerial vehicle 11 is set as a beacon, a bilateral two-way ranging method is adopted to determine the distance between the beacon and the anchor on the unmanned aerial vehicle 1, namely, the anchor transmits a ranging signal, after receiving a target beacon on the unmanned aerial vehicle 1, the target beacon transmits the ranging signal again, the anchor receives, in the first round of ranging signal transmission and reception, the time difference between the transmission and the reception of the anchor is set as around 1, the time difference between the transmission and the reception of the target beacon is set as around 1, and the time difference between the transmission and the reception of the target beacon is set as around 2 and around 2.
The time of flight (TOF) of a wireless signal can be expressed as:
the above equation can be converted into
T round1 ×T round2 ＝T tof (T round1 +T round2 +T reply1 +T reply2 ) (4)
Get the calculation formula of Ttof
In practical applications, there is an error in the time difference between beacon reception and transmission. The errors of the first and second wheel are denoted e1 and e2, respectively. Thus, the measurement of Ttof can be expressed as:
thus, the error of Ttof is determined by the following formula
The higher order terms are ignored and the higher order terms are ignored,
the principle of ultra wideband beacon based positioning is shown in fig. 4.
The YOLOv7 algorithm as used in this application is cited in the literature of YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors, arXiv:2207.02696v1[cs.CV]6Jul 2022.
When the defective position is detected, feeding back the coordinates of the unmanned aerial vehicle 1 in real time, so as to determine the position of the weld defect, and numbering and recording; the drone 1 is kept perpendicular to the longitudinal direction of the weld, and therefore the transverse coordinates of the drone 1 and the weld are consistent.
The defect positions and defect types of the steel bridge welding seams are obtained through the image processing technology, the operation safety of the bridge is evaluated in real time by combining the historical data of the health conditions of the steel bridge, the steel bridge welding seams can be rapidly detected based on the unmanned aerial vehicle 1, the operation safety and the degradation behavior of the steel bridge can be evaluated through the detection data, and data support can be provided for health monitoring, maintenance and daily maintenance of the bridge.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Furthermore, it should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is provided for clarity only, and that the disclosure is not limited to the embodiments described in detail below, and that the embodiments described in the examples may be combined as appropriate to form other embodiments that will be apparent to those skilled in the art.
Claims (3)
1. A steel bridge welding seam detection method and system based on unmanned aerial vehicle is characterized in that the steel bridge welding seam detection method comprises the following steps:
and S1, utilizing an unmanned aerial vehicle (1) to carry a high-definition camera to shoot a welding line video image of the steel bridge in real time.
S2, preprocessing the steel bridge weld video through a space-time context searching algorithm and a defogging algorithm, and effectively removing haze and heat waves in the video image.
And S3, recognizing a weld joint video image shot by a high-definition camera in real time by utilizing a single-target detection algorithm YOLOv7 based on deep learning, establishing a corresponding weight file aiming at a detection target, and recognizing the weld joint defect in the video by selecting a proper threshold value so as to realize reasonable recognition of the defect.
S4: the space coordinates of four UWB anchor points are measured by the positioning principle of an ultra-wideband positioning method, and then the distance between the beacon and the anchor points on the unmanned aerial vehicle (1) is determined by a bilateral two-way ranging method.
S5: and the defect position and defect type of the steel bridge welding seam are obtained through the image processing technology, and the operation safety of the bridge is evaluated in real time by combining the historical data of the health condition of the steel bridge.
2. The unmanned aerial vehicle-based steel bridge weld detection method and system as claimed in claim 1, wherein: the calculation mode in S4 is as follows: the coordinates of the unmanned aerial vehicle (1) calculated by using the spatial coordinates of the four UWB anchor points measured are (x 1, y1, z 1), (x 2, y2, z 2), (x 3, y3, z 3) and (x 4, y4, z 4), and the linear distances between the four UWB anchor points and the unmanned aerial vehicle (1) are R1, R2, R3 and R4. Based on the four-point three-dimensional space positioning principle, the following equation is obtained:
where i=1, 2,3,4. The above equation can be converted into
When the UWB anchor point is arranged, (x 1, y1, z 1), (x 2, y2, z 2), (x 3, y3, z 3), (x 4, y4, z 4) can be measured, and in order to solve the unmanned aerial vehicle (1) coordinates from the above equation, R1, R2, R3 and R4 at each moment need to be calculated, which means that the accuracy of the unmanned aerial vehicle (1) coordinates directly relates to the accuracy of the distance measurement between the anchor point and the unmanned aerial vehicle (1).
And the ultra-wideband anchor point (4) on the unmanned aerial vehicle (1) is set as a beacon, then a bilateral two-way ranging method is adopted to determine the distance between the beacon on the unmanned aerial vehicle (1) and the anchor point, namely, the anchor point transmits a ranging signal, and after the target beacon on the unmanned aerial vehicle (1) is received, the target beacon transmits the ranging signal again, and the anchor point is received.
In the first round of ranging signal transmission and reception, the time difference between transmission and reception of the anchor is set to be around 1, the time difference between transmission and reception of the target beacon is set to be around 1, and the time difference of the second round is set to be around 2 and around 2.
The time of flight (TOF) of a wireless signal can be expressed as:
the above equation can be converted into
T round1 ×T round2 ＝T tof (T round1 +T round2 +T reply1 +T reply2 ) (4)
Get the calculation formula of Ttof
In practical applications, there is an error in the time difference between beacon reception and transmission. The errors of the first and second wheel are denoted e1 and e2, respectively. Thus, the measurement of Ttof can be expressed as:
thus, the error of Ttof is determined by the following formula
The higher order terms are ignored and the higher order terms are ignored,
3. the steel bridge welding seam detection method and system based on the unmanned aerial vehicle according to claim 1, wherein the unmanned aerial vehicle (1) performs the following steps when performing video image acquisition on the welding seam of the web plate of the steel box girder:
s1: controlling the unmanned aerial vehicle (1) to fly along the welding seam of the steel box girder web bottom plate through a control source;
s2: the method comprises the steps of collecting the space position of a traveling unmanned aerial vehicle (1) through a positioning method based on ultra-wideband, and positioning;
s3: in the flight process, acquiring a welding line video image through a high-definition camera (2);
s4: transmitting the acquired welding seam video image to a computer terminal in real time through a 5G network component and an anti-interference component in the multifunctional integrated component (5);
s5: after analyzing the collected video images, if the requirements are not met, secondary collection is carried out after the parameters such as the flying speed, the flying height and the like are adjusted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310443128.4A CN116559172A (en) | 2023-04-23 | 2023-04-23 | Unmanned aerial vehicle-based steel bridge welding seam detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310443128.4A CN116559172A (en) | 2023-04-23 | 2023-04-23 | Unmanned aerial vehicle-based steel bridge welding seam detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116559172A true CN116559172A (en) | 2023-08-08 |
Family
ID=87489039
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310443128.4A Pending CN116559172A (en) | 2023-04-23 | 2023-04-23 | Unmanned aerial vehicle-based steel bridge welding seam detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116559172A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111964680A (en) * | 2020-07-29 | 2020-11-20 | 中国安全生产科学研究院 | Real-time positioning method of inspection robot |
| CN113807464A (en) * | 2021-09-29 | 2021-12-17 | 东南大学 | Unmanned aerial vehicle aerial image target detection method based on improved YOLO V5 |
| CN114266299A (en) * | 2021-12-16 | 2022-04-01 | 京沪高速铁路股份有限公司 | Method and system for detecting defects of steel structure of railway bridge based on unmanned aerial vehicle operation |
| CN115078393A (en) * | 2022-08-23 | 2022-09-20 | 兰州交通大学 | Method for detecting damage of hinge joint of simply supported hollow slab bridge based on computer vision |
| CN115397012A (en) * | 2022-08-05 | 2022-11-25 | 南京信息工程大学 | Realization method of UWB positioning tracking system based on TWR-TDOA estimation and MPGA layout optimization |
| KR20230053352A (en) * | 2021-10-14 | 2023-04-21 | 주식회사 스카이솔루션 | Ship inspection system using drone |
| CN116485709A (en) * | 2023-02-01 | 2023-07-25 | 武汉科技大学 | Bridge concrete crack detection method based on YOLOv5 improved algorithm |
-
2023
- 2023-04-23 CN CN202310443128.4A patent/CN116559172A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111964680A (en) * | 2020-07-29 | 2020-11-20 | 中国安全生产科学研究院 | Real-time positioning method of inspection robot |
| CN113807464A (en) * | 2021-09-29 | 2021-12-17 | 东南大学 | Unmanned aerial vehicle aerial image target detection method based on improved YOLO V5 |
| KR20230053352A (en) * | 2021-10-14 | 2023-04-21 | 주식회사 스카이솔루션 | Ship inspection system using drone |
| CN114266299A (en) * | 2021-12-16 | 2022-04-01 | 京沪高速铁路股份有限公司 | Method and system for detecting defects of steel structure of railway bridge based on unmanned aerial vehicle operation |
| CN115397012A (en) * | 2022-08-05 | 2022-11-25 | 南京信息工程大学 | Realization method of UWB positioning tracking system based on TWR-TDOA estimation and MPGA layout optimization |
| CN115078393A (en) * | 2022-08-23 | 2022-09-20 | 兰州交通大学 | Method for detecting damage of hinge joint of simply supported hollow slab bridge based on computer vision |
| CN116485709A (en) * | 2023-02-01 | 2023-07-25 | 武汉科技大学 | Bridge concrete crack detection method based on YOLOv5 improved algorithm |
Non-Patent Citations (6)
| Title |
|---|
| BRUNO JOSÉ SOUZA 等: "Hybrid-YOLO for classification of insulators defects in transmission lines based on UAV", 《INTERNATIONAL JOURNAL OF ELECTRICAL POWER AND ENERGY SYSTEMS》, vol. 1, pages 258 - 263 * |
| 卢靖宇 等: "基于超宽带的移动机器人室内定位系统设计", 《电子技术应用》, vol. 43, no. 5, pages 25 - 28 * |
| 张炜尧: "基于GPU的焊缝缺陷智能识别系统设计", 《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》, no. 1, pages 30 - 46 * |
| 徐梓惠: "基于深度学习的机器人焊接熔池图像分析与焊接质量预测研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》, no. 1, pages 12 - 26 * |
| 涂宙霖 等: "基于YOLOv7与Jetson Orin 的路面破损检测系统的设计与实现", 《电脑知识与技术》, vol. 19, no. 9, pages 50 - 52 * |
| 赵陈磊: "基于双目机器视觉的焊接路径重建方法研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》, no. 1, pages 24 - 42 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110159869B (en) | Pipeline detection robot and multi-sensor fusion detection method thereof | |
| CN102419437B (en) | Track-before-detect method based on flight path inspection | |
| CN105404844A (en) | Road boundary detection method based on multi-line laser radar | |
| CN104359983B (en) | The center support system and method for a kind of steel rail flaw detection device | |
| CN101833099B (en) | Locked tracking method of helicopter in the inspection process of electric power circuits | |
| EP3333043B1 (en) | Rail inspection system and method | |
| CN105184816A (en) | Visual inspection and water surface target tracking system based on USV and detection tracking method thereof | |
| CN207649604U (en) | A kind of intelligent landform survey system based on unmanned plane | |
| CN110375700B (en) | Large spiral steel pipe quality detection equipment and method | |
| CN109213204A (en) | AUV sub-sea floor targets based on data-driven search navigation system and method | |
| CN107830860A (en) | A kind of unmanned boat lifting recovery visual guide method | |
| CN111692456A (en) | SLAM system and method for pipeline detection | |
| CN110136186A (en) | A kind of detection target matching method for mobile robot object ranging | |
| CN111267912B (en) | Train positioning method and system based on multi-source information fusion | |
| CN110441388A (en) | A kind of jacket platform underwater portion non-destructive testing method of detection | |
| CN113791074A (en) | Unmanned aerial vehicle bridge crack inspection system and method based on multi-sensor fusion | |
| CN114812403A (en) | Large-span steel structure hoisting deformation monitoring method based on unmanned aerial vehicle and machine vision | |
| CN115019412A (en) | Underwater AUV (autonomous underwater vehicle) submarine cable inspection system and method based on multiple sensors | |
| CN113776467A (en) | Highway ramp road surface technical condition detecting system based on unmanned aerial vehicle platform | |
| CN116559172A (en) | Unmanned aerial vehicle-based steel bridge welding seam detection method and system | |
| CN108181313A (en) | A kind of device and method suitable for the detection of contact net running environment safe condition | |
| CN115560640B (en) | Projectile miss distance online automatic detection method and system based on double-station observation | |
| CN105129295A (en) | Backing-up control method, device and system and rubbish transfer truck | |
| CN111926700B (en) | UWB-based bridge cable defect detection positioning system and method | |
| CN112506206A (en) | Coal mine rescue robot and obstacle avoidance method thereof |
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 |