CN116183609A - Unmanned aerial vehicle spectrum-based pipeline defect detection method and unmanned aerial vehicle - Google Patents

Unmanned aerial vehicle spectrum-based pipeline defect detection method and unmanned aerial vehicle Download PDF

Info

Publication number
CN116183609A
CN116183609A CN202211606143.8A CN202211606143A CN116183609A CN 116183609 A CN116183609 A CN 116183609A CN 202211606143 A CN202211606143 A CN 202211606143A CN 116183609 A CN116183609 A CN 116183609A
Authority
CN
China
Prior art keywords
unmanned aerial
aerial vehicle
pipeline section
spectrum camera
pipeline
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
Application number
CN202211606143.8A
Other languages
Chinese (zh)
Inventor
王艳飞
刘礼波
胡强
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sichuan Hengchuangtiandi Automation Equipment Co ltd
Original Assignee
Sichuan Hengchuangtiandi Automation Equipment Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Sichuan Hengchuangtiandi Automation Equipment Co ltd filed Critical Sichuan Hengchuangtiandi Automation Equipment Co ltd
Priority to CN202211606143.8A priority Critical patent/CN116183609A/en
Publication of CN116183609A publication Critical patent/CN116183609A/en
Pending legal-status Critical Current

Links

Images

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
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64C—AEROPLANES; HELICOPTERS
    • B64C39/00—Aircraft not otherwise provided for
    • B64C39/02—Aircraft not otherwise provided for characterised by special use
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64D—EQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENTS OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
    • B64D47/00—Equipment not otherwise provided for
    • B64D47/08—Arrangements of cameras
    • 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
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
    • Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture

Abstract

The invention provides a detection method of pipeline defects based on unmanned aerial vehicle spectra and an unmanned aerial vehicle, belongs to the technical field of pipeline flaw detection, and is applied to the unmanned aerial vehicle, wherein a spectrum camera capable of rotating relatively is arranged on the unmanned aerial vehicle, and the method comprises the following steps: the unmanned aerial vehicle flies along with the pipeline, a defective pipeline section is determined, and the unmanned aerial vehicle is controlled to fly to the position right above the pipeline section; extracting temperature values T1 and T2 in the edge areas of the two sides of the pipeline section, adjusting the unmanned aerial vehicle to move to one side of the pipeline section where the larger value in the T1 and T2 is located, and determining a temperature value delta T2 in the edge areas of the two sides of the pipeline section at each adjusting position in the adjusting process; and when the delta T2 is not more than the preset temperature difference value, acquiring a target real image and a target hyperspectral image of the current pipeline section at the target adjusting position. The method has the advantages that the workers can collect complete defect forms, the workers can find specific positions of defects conveniently, repair plans for pipelines are formulated in advance, and the efficiency of repairing the pipelines is improved.

Description

Unmanned aerial vehicle spectrum-based pipeline defect detection method and unmanned aerial vehicle
Technical Field
The invention relates to the technical field of pipeline flaw detection, in particular to a pipeline flaw detection method based on unmanned aerial vehicle spectrum and an unmanned aerial vehicle.
Background
In the inspection of petroleum pipelines, particularly long-distance oil and gas pipelines (the length is within 400 km), regional oil and gas field broken block systems (the area is 100 km) 2 Left-right). The items generally require short detection period, heavy tasks and high quality requirements, and the topography and topography in the area are complex and changeable, and the pipeline often passes through unmanned areas such as desert gobi, deep forests, mountains and the like, and measurement staff and instrument equipment cannot reach a destination quickly, so that remote sensing monitoring of the pipeline by adopting unmanned aerial vehicle remote operation becomes the most rapid and efficient inspection mode.
The patent with publication number of CN112116566A discloses a road-specific pipeline defect diagnosis method based on hyperspectral remote sensing technology, which comprises the steps of inputting hyperspectral images of oil and gas pipelines generated by a spectrum imager into a computer by using the hyperspectral remote sensing technology, marking and training the spectrum data of the oil and gas pipelines obtained by experiments by using a BP neural network and a machine learning method, extracting hyperspectral images and spectrum characteristics of the oil and gas pipelines such as leakage, defects and the like, and determining leakage areas and defect positions of the oil and gas pipelines; the oil and gas pipeline surface data is classified by an unsupervised machine learning entropy method, then is automatically classified according to defect levels by a BP neural network, and is early-warning displayed according to normal, fault and alarm. The technology of unmanned aerial vehicle to oil gas pipeline leakage and defect area remote sensing monitoring has been realized.
However, the defects of the pipeline are various in types and defect degrees, the unmanned aerial vehicle usually shoots remotely from top to bottom, defects distributed at different positions on the pipeline cannot be accurately acquired and shot, therefore, ground personnel can only predict the defect degrees of the pipeline according to long-term working experience, and a maintenance scheme for the pipeline cannot be accurately made before the personnel starts to maintain the pipeline.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a pipeline defect detection method based on unmanned aerial vehicle spectrum and an unmanned aerial vehicle
In order to achieve the above purpose, the invention adopts the following technical scheme:
the first aspect of the embodiment of the invention provides a pipeline defect detection method based on unmanned aerial vehicle spectrum, which is applied to unmanned aerial vehicles, wherein at least a spectrum camera for outputting a real image and a hyperspectral image is arranged on each unmanned aerial vehicle, and the spectrum camera can rotate relative to the unmanned aerial vehicle; the method comprises the following steps:
the unmanned aerial vehicle flies along with the pipeline, a first hyperspectral image of the surface of the pipeline is obtained through the spectrum camera, a defective pipeline section is determined according to analysis of the collected first hyperspectral image of the surface of the pipeline, and the unmanned aerial vehicle is controlled to fly to the position right above the pipeline section;
collecting a second hyperspectral image of the surface of the pipeline section, extracting temperature values T1 and T2 in the edge areas of the two sides of the pipeline section according to the second hyperspectral image, comparing the values of T1 and T2, and when the value difference delta T1 of T1 and T2 is larger than a preset temperature difference value, adjusting the unmanned aerial vehicle to move to one side of the pipeline section where the larger value in the T1 and T2 is located, and determining the temperature value delta T2 in the edge areas of the two sides of the pipeline section in the spectral image collected by the spectral camera on the pipeline section of the adjusting position at each adjusting position in the adjusting process;
when the delta T2 is not greater than the preset temperature difference value, determining a target adjustment position where the unmanned aerial vehicle is currently located;
and determining that the defect part on the pipeline is positioned in the middle of the image range acquired by the spectrum camera based on the current target adjustment position of the unmanned aerial vehicle, and acquiring a target real image and a target hyperspectral image of the current pipeline section under the target adjustment position.
Further, a laser ranging sensor is arranged on the spectrum camera and is used for measuring the distance from a lens of the spectrum camera to a pipeline section positioned in the middle of an image range acquired by the spectrum camera; adjusting unmanned aerial vehicle to T1, the pipeline section one side that the great numerical value was located in the T2 removes, include:
the spectrum camera of the unmanned aerial vehicle is vertically downward, a second hyperspectral image of the surface of the pipeline section is collected, the distance D1 from the spectrum camera lens on the unmanned aerial vehicle to the pipeline section in the middle of the image range collected by the spectrum camera is determined, the unmanned aerial vehicle is adjusted to fly in parallel by taking the D1 as the radius and the pipeline section as the circle center, and the rotation angle of the spectrum camera on the unmanned aerial vehicle is adjusted so that the pipeline section is located in the image range photographed by the spectrum camera.
Further, adjust unmanned aerial vehicle last spectrum camera turned angle to keep the pipeline section to be located the image range that spectrum camera shot, include:
according to a third hyperspectral image acquired by the spectrum camera, identifying the area of the pipeline section in the third hyperspectral image as a first active area, determining the partial areas positioned on two sides of the pipeline section in the third hyperspectral image as adjusting areas, and adjusting the spectrum camera to rotate towards the overlapped adjusting areas when the first active area moves to overlap with one of the two adjusting areas.
Further, a first preset corresponding relation between a plurality of overlapped areas and the rotation speed of the spectrum camera is established; adjusting rotation of the spectral camera toward the overlapping adjustment zone as the first active zone moves into overlapping relation with one of the two adjustment zones, comprising:
identifying an overlap area S1 of the overlap portion when the first active region moves to overlap with one of the two adjustment regions;
determining a target rotation rate based on the corresponding relation between the overlapping area S1 and the first preset;
and controlling the spectrum camera to rotate at the target rotation rate.
Further, the method further comprises:
when the rotating angle of the spectrum camera relative to the unmanned aerial vehicle reaches a preset angle threshold, the spectrum camera is controlled to stop acting, and the real image of the current spectrum camera acquisition pipeline section is determined to be a target real image, and the hyperspectral image is determined to be a target hyperspectral image.
Further, identifying a region of the pipe segment in the third hyperspectral image as a first active region includes:
acquiring a first real image containing a pipeline section by utilizing a spectrum camera, analyzing the acquired first real image through a pre-trained pipeline image network, and determining the area of the pipeline image in the first real image;
and determining that the region of the pipeline image in the first real image is projected as a first active region in the third hyperspectral image by utilizing the overlapping of the first real image and the third hyperspectral image.
Further, the method further comprises:
and extracting temperature values T3 and T4 in the edge areas of two sides of the pipeline section and a temperature value T5 in the middle of the pipeline section according to the target hyperspectral image, respectively comparing the values of T5 and T3 and the values of T5 and T4, and determining that the defect on the pipeline surface is positioned on the back of the pipeline section image acquired by the spectrum camera when the value of T5 is simultaneously smaller than the values of T3 and T4.
The second aspect of the embodiment of the invention provides an unmanned aerial vehicle, which at least comprises an unmanned aerial vehicle body and a spectrum camera, wherein a control device is arranged in the unmanned aerial vehicle body, the control device at least comprises a processor and a controller, the spectrum camera is rotationally arranged at the bottom of the unmanned aerial vehicle body, the spectrum camera is electrically connected with the processor, the controller is electrically connected with the processor, the output end of the controller is connected with the spectrum camera, and the controller is used for driving the spectrum camera to rotate;
the processor is configured to perform a detection method as set forth in the first aspect of the embodiment of the present invention.
Further, the controller includes micro motor, lead screw subassembly and connecting rod, and lead screw subassembly level sets up on unmanned aerial vehicle's diapire, and micro motor is arranged in order to drive the lead screw rotation in the lead screw subassembly, and movable block in the one end lead screw subassembly of connecting rod is articulated, the other end is connected on spectrum camera's outer wall, and the slide has been seted up to spectrum camera's outer wall perpendicular to spectrum camera's articulated shaft, and the one end that the movable block was kept away from to the connecting rod is followed slide length direction and is slided and can be rotated and be connected in the slide.
The beneficial effects of the invention are as follows: through making unmanned aerial vehicle after detecting the defect position on the pipeline, unmanned aerial vehicle deflects to the one side that has the defect on the pipeline, deflects to after spectral camera centers the defect on the pipeline section in the collection region, can make the staff gather complete defect form, make things convenient for the staff to discover the defect concrete position to make in advance to the repair plan to the pipeline, improve the efficiency of repairing the pipeline.
Drawings
Fig. 1 is a schematic structural diagram of a spectrum camera and a controller according to a first embodiment of the present invention;
fig. 2 is a schematic control logic diagram of a unmanned aerial vehicle according to a second embodiment of the present invention;
fig. 3 is a flow chart illustrating steps of a detection method according to a third embodiment of the present invention.
1, a spectrum camera; 2. a micro motor; 3. a screw assembly; 4. a connecting rod; 5. a laser ranging sensor; 6. unmanned plane; 7. a processor; 8. and a controller.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
Example 1
Referring to fig. 1, the embodiment of the application discloses an unmanned aerial vehicle, including unmanned aerial vehicle 6 body and spectral camera 1, spectral camera 1 rotates the bottom of installing at unmanned aerial vehicle 6 body, and its axis of rotation is horizontal. The unmanned aerial vehicle 6 is internally provided with control equipment, the control equipment at least comprises a processor 7 and a controller 8, the controller 8 and the spectrum camera 1 are electrically connected with the processor 7, and the processor 7 is used for executing a pipeline defect detection method based on unmanned aerial vehicle spectrum. The controller 8 is used for controlling the rotation of the spectrum camera 1 relative to the unmanned aerial vehicle 6 body.
The spectrum camera 1 at least comprises functions of far infrared spectrum shooting and collecting and actual image shooting and collecting, the spectrum camera 1 shoots and collects through infrared spectrum shooting to output hyperspectral images, and shoots and collects through actual images to output actual images. The controller 8 includes a micro motor 2, a screw assembly 3 and a connecting rod 4. The lead screw subassembly 3 includes lead screw and movable block, and the lead screw level sets up, and the both ends of lead screw all rotate with unmanned aerial vehicle 6 body and be connected, and the axis of lead screw is perpendicular to spectral camera 1's axis, and movable block is in the bottom of unmanned aerial vehicle 6 body along the axis direction sliding connection of lead screw, and movable block and lead screw threaded connection. The side wall of the spectrum camera 1, which is close to one side of the screw rod, is provided with a slideway along the direction vertical to the hinge axis of the side wall, one end of the connecting rod 4 is hinged with the moving block, the other end of the connecting rod is connected with a movable head, and the connecting rod 4 slides and rotates through the movable head to be connected in the slideway on the spectrum camera 1. An output shaft of the micro motor 2 is connected with one end of the screw rod and used for driving the screw rod to rotate.
Further, still be provided with the gyroscope on spectral camera 1, can keep unmanned aerial vehicle 6 to detect spectral camera 1 relative unmanned aerial vehicle 6's rotation angle with the horizontal gesture flight in-process, still be equipped with laser rangefinder sensor 5 on spectral camera 1, can detect spectral camera 1 and be apart from the distance of shooing the article through laser rangefinder sensor 5.
Example two
Referring to fig. 2 and 3, based on the same inventive concept, another embodiment of the present application provides a method for detecting a pipeline defect based on an unmanned aerial vehicle spectrum, which is applied to an unmanned aerial vehicle, wherein the unmanned aerial vehicle is at least provided with a spectrum camera for outputting a real image and a hyperspectral image, and the spectrum camera can rotate relative to the unmanned aerial vehicle; the detection method mainly comprises the following steps:
s01, utilizing the unmanned aerial vehicle to fly along with the pipeline, collecting a first hyperspectral image with the pipeline surface through a spectrum camera, analyzing and determining a defective pipeline section according to the collected first hyperspectral image of the pipeline surface, and controlling the unmanned aerial vehicle to fly to the position right above the defective pipeline section.
Wherein, unmanned aerial vehicle follows under the pipeline flight state, and spectrum camera is vertical to shoot downwards. Through the pre-trained pipeline image network, various images of pipelines under different environments and terrains can be analyzed, a target pipeline is identified from real images acquired by a spectrum camera, and the pipeline image network is in a test stage and performs recognition training on pipelines needing to be detected under different environments acquired by acquiring images by utilizing a neural network algorithm. By overlapping the real image acquired at the same time with the hyperspectral image, the range of the pipeline in the hyperspectral image can be obtained.
And when the processor or the computer analyzes that the temperature in the pipeline and the surrounding part area in the hyperspectral image exceeds the preset temperature threshold value area, judging that the pipeline has defects. Then, the aircraft is controlled to move in a horizontal posture, so that the highest temperature point in the detected defect patch moves to a horizontal center line position in the acquired image range.
S02, collecting a second hyperspectral image of the surface of the pipeline section, extracting temperature values T1 and T2 in the edge areas of the two sides of the pipeline section according to the second hyperspectral image, comparing the values of T1 and T2, and when the value difference delta T1 of the T1 and T2 is larger than a preset temperature difference, adjusting the unmanned aerial vehicle to move to one side of the pipeline section where the larger value in the T1 and T2 is located, and determining the temperature value delta T2 in the edge areas of the two sides of the pipeline section in the spectral image collected by the spectral camera on the pipeline section of the adjusting position at each adjusting position in the adjusting process.
Wherein the numerical difference between T1 and T2 is an absolute value. Adjusting the unmanned aerial vehicle to remove to pipeline section one side that great numerical value was located in T1, T2 includes:
the spectrum camera of the unmanned aerial vehicle is vertically downward, a second hyperspectral image of the surface of the pipeline section is collected, the distance D1 from the spectrum camera lens on the unmanned aerial vehicle to the pipeline section in the middle of the image range collected by the spectrum camera is determined, the unmanned aerial vehicle is adjusted to fly in parallel by taking the D1 as the radius and the pipeline section as the circle center, and the rotation angle of the spectrum camera on the unmanned aerial vehicle is adjusted so that the pipeline section is located in the image range photographed by the spectrum camera. Through making unmanned aerial vehicle use pipeline section to rotate as the centre of a circle, can make the spectrum camera keep certain focus, accurately clearly gather pipeline section side image.
Each adjusting position in the adjusting process can be the position of the unmanned aerial vehicle after the unmanned aerial vehicle flies to one side of the pipeline section for a fixed distance; the position of the unmanned aerial vehicle can be obtained after the spectrum camera rotates by a fixed angle relative to the unmanned aerial vehicle in the flight process of the unmanned aerial vehicle; the position of the unmanned aerial vehicle can be further determined after the unmanned aerial vehicle flies to one side of the pipeline section for a fixed time.
In the one side flight process of unmanned aerial vehicle to pipeline section, need keep pipeline section in the effective collection region of spectrum camera, therefore spectrum camera needs the relative unmanned aerial vehicle of real time to take place to rotate. Adjusting the rotation angle of the spectrum camera on the unmanned aerial vehicle to keep the pipeline section in the image range shot by the spectrum camera, comprising:
and identifying the region of the pipeline section in the third hyperspectral image as a first active region according to the third hyperspectral image acquired by the spectral camera, wherein the spectral camera is utilized to acquire a first real image containing the pipeline section, and the acquired first real image is analyzed through a pre-trained pipeline image network to determine the region of the pipeline image in the first real image. And determining that the region of the pipeline image in the first real image is projected as a first active region in the third hyperspectral image by utilizing the overlapping of the first real image and the third hyperspectral image.
And then determining partial areas on two sides of the pipeline section in the third hyperspectral image as adjusting areas, wherein the partial areas can be partial areas which are spaced on two sides of the pipeline section and are parallel to the pipeline section in the image areas acquired by the spectrum cameras. And when the first active area moves to overlap with one of the two adjusting areas, adjusting the spectrum camera to rotate towards the adjusting area overlapped. The spectral camera may be automatically deflected so that the spectral camera can be rotated to place the pipe segment within the active area being photographed.
Further, in order to enable the rotation speed of the spectrum camera to be adapted to the flight speed of the unmanned aerial vehicle, the spectrum camera can be aligned to the pipeline section more quickly, a first preset corresponding relation between a plurality of overlapping areas and the rotation speed of the spectrum camera is also established in the embodiment of the application, and the overlapping areas are areas of overlapping portions when the first active area overlaps the adjusting area.
Specifically, when the first active area moves to overlap one of the two adjustment areas, an overlapping area S1 of the overlapping portion is identified, a target rotation rate is determined based on a corresponding relation between the overlapping area S1 and a first preset, and the spectral camera is controlled to rotate at the target rotation rate. In the first preset corresponding relation, the overlapping area and the rotation rate can be inversely proportional, so that when the unmanned aerial vehicle flies at a high speed to enable the first active area and the adjusting area to be overlapped in an accelerating mode, the rotation rate of the spectrum camera is improved, and the images are aligned and aligned quickly.
The unmanned aerial vehicle and the spectrum camera cannot infinitely rotate around the pipeline section under the influence of an actual mechanical structure and an actual environment. In the embodiment of the application, when the rotation angle of the spectrum camera relative to the unmanned aerial vehicle reaches a preset angle threshold, the spectrum camera is controlled to stop acting, and the real image of the pipeline section collected by the current spectrum camera is determined to be a target real image, and the hyperspectral image is determined to be a target hyperspectral image.
The preset angle threshold value is 45 degrees under normal conditions, and the forest environment can be manually set to be 30 degrees or below so as to ensure that the unmanned aerial vehicle flies normally.
S03, when the delta T2 is not larger than the preset temperature difference value, determining the current target adjustment position of the unmanned aerial vehicle.
S04, determining that a defect part on a pipeline is positioned in the middle of an image range acquired by a spectrum camera based on a target adjustment position where the unmanned aerial vehicle is currently positioned, and acquiring a target real image and a target hyperspectral image of a current pipeline section under the target adjustment position.
The collected target real image and target highlight image can be stored in a storage device in the unmanned aerial vehicle, and can be remotely transmitted to a platform such as a worker computer for remote viewing through wireless communication means such as Bluetooth.
And extracting temperature values T3 and T4 in the edge areas of two sides of the pipeline section and a temperature value T5 in the middle of the pipeline section according to the target hyperspectral image, respectively comparing the values of T5 and T3 and the values of T5 and T4, and determining that the defect on the pipeline surface is positioned on the back of the pipeline section image acquired by the spectrum camera when the value of T5 is simultaneously smaller than the values of T3 and T4.
Through making unmanned aerial vehicle fly to the spectrum camera just to the defect position on the pipeline section, carry out true image and hyperspectral image acquisition to the pipeline section again, can make the staff that is located the distance observe the form etc. of defect on the pipeline from the straight face on equipment such as display, computer to and the defect is located concrete position on the pipeline, can make things convenient for the staff to formulate suitable pipeline repair scheme according to defect form in advance, improve the staff and carry out prosthetic efficiency to the pipeline.
It will be apparent to those skilled in the art that while preferred embodiments of the present invention have been described, additional variations and modifications may be made to these embodiments once the basic inventive concepts are known to those skilled in the art. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention. It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims (9)

1. A detection method of pipeline defects based on unmanned aerial vehicle spectra is characterized by comprising the following steps: the method is applied to the unmanned aerial vehicle, and the unmanned aerial vehicle is at least provided with a spectrum camera for outputting a real image and a hyperspectral image, wherein the spectrum camera can rotate relative to the unmanned aerial vehicle; the method comprises the following steps:
the unmanned aerial vehicle flies along with the pipeline, a first hyperspectral image of the surface of the pipeline is obtained through the spectrum camera, a defective pipeline section is determined according to the collected first hyperspectral image analysis of the surface of the pipeline, and the unmanned aerial vehicle is controlled to fly to the position right above the pipeline section;
collecting a second hyperspectral image of the surface of the pipeline section, extracting temperature values T1 and T2 in edge areas on two sides of the pipeline section according to the second hyperspectral image, comparing the values of T1 and T2, adjusting the unmanned aerial vehicle to move to one side of the pipeline section where a larger value in T1 and T2 is located when the value difference delta T1 of T1 and T2 is larger than a preset temperature difference, and determining the temperature value delta T2 in the edge areas on two sides of the pipeline section in the spectral image collected by the spectral camera on the pipeline section at the adjusting position in each adjusting position in the adjusting process;
when the delta T2 is not larger than a preset temperature difference value, determining a target adjustment position where the unmanned aerial vehicle is currently located;
and determining that the defect part on the pipeline is positioned in the middle of the image range acquired by the spectrum camera based on the current target adjustment position of the unmanned aerial vehicle, and acquiring a target real image and a target hyperspectral image of the current pipeline section under the target adjustment position.
2. The unmanned aerial vehicle spectrum-based pipeline defect detection method according to claim 1, wherein a laser ranging sensor is arranged on the spectrum camera and is used for measuring the distance from a lens of the spectrum camera to a pipeline section positioned in the middle of an image range acquired by the spectrum camera; adjusting the unmanned aerial vehicle to remove to pipeline section one side that great numerical value was located in T1, T2 includes:
the unmanned aerial vehicle spectrum camera is vertically downward, a second hyperspectral image of the surface of the pipeline section is collected, the distance D1 from the spectrum camera lens on the unmanned aerial vehicle to the pipeline section in the middle of the image range collected by the spectrum camera is determined, the unmanned aerial vehicle is adjusted to fly in parallel by taking the D1 as a radius and the pipeline section as a circle center, and the rotation angle of the spectrum camera on the unmanned aerial vehicle is adjusted, so that the pipeline section is located in the image range shot by the spectrum camera.
3. The method for detecting a pipeline defect based on an unmanned aerial vehicle spectrum according to claim 2, wherein adjusting the rotation angle of the spectrum camera on the unmanned aerial vehicle to keep the pipeline section within the image range shot by the spectrum camera comprises:
and identifying the region of the pipeline section in the third hyperspectral image as a first active region according to the third hyperspectral image acquired by the spectrum camera, determining the partial regions positioned at two sides of the pipeline section in the third hyperspectral image as adjusting regions, and adjusting the spectrum camera to rotate towards the overlapped adjusting regions when the first active region moves to overlap with one of the two adjusting regions.
4. The method for detecting pipeline defects based on unmanned aerial vehicle spectra according to claim 3, wherein a first preset correspondence relationship between a plurality of overlapping areas and the rotation rate of the spectrum camera is established; adjusting rotation of the spectral camera toward an overlapping adjustment region when the first active region moves to overlap one of two adjustment regions, comprising:
identifying an overlap area S1 of the overlap portion when the first active region moves to overlap one of the two adjustment regions;
determining a target rotation rate based on the overlapping area S1 and a first preset corresponding relation;
and controlling the spectrum camera to rotate at a target rotation rate.
5. A method for detecting a pipe defect based on unmanned aerial vehicle spectroscopy according to claim 3, wherein the method further comprises:
and when the rotating angle of the spectrum camera relative to the unmanned aerial vehicle reaches a preset angle threshold, controlling the spectrum camera to stop acting, and determining that the real image of the current spectrum camera acquisition pipeline section is a target real image and the hyperspectral image is a target hyperspectral image.
6. A method of detecting a pipe defect based on unmanned aerial vehicle spectroscopy as defined in claim 3, wherein identifying the region of the pipe section in the third hyperspectral image as the first active region comprises:
acquiring a first real image containing a pipeline section by utilizing a spectrum camera, analyzing the acquired first real image through a pre-trained pipeline image network, and determining the area of the pipeline image in the first real image;
and determining that the region of the pipeline image in the first real image is projected as a first active region in the third hyperspectral image by utilizing the overlapping of the first real image and the third hyperspectral image.
7. The method for detecting a pipe defect based on unmanned aerial vehicle spectroscopy according to claim 1, further comprising:
and extracting temperature values T3 and T4 in the edge areas of two sides of the pipeline section and a temperature value T5 in the middle of the pipeline section according to the target hyperspectral image, respectively comparing the values of T5 and T3 and the values of T5 and T4, and determining that the defect on the pipeline surface is positioned on the back of the pipeline section image acquired by the spectrum camera when the value of T5 is simultaneously smaller than the values of T3 and T4.
8. The unmanned aerial vehicle is characterized by at least comprising an unmanned aerial vehicle (6) body and a spectrum camera (1), wherein control equipment is arranged in the unmanned aerial vehicle (6), the control equipment at least comprises a processor (7) and a controller (8), the spectrum camera (1) is rotationally arranged at the bottom of the unmanned aerial vehicle (6) body, the spectrum camera (1) is electrically connected with the processor (7), the controller (8) is electrically connected with the processor (7), the output end of the controller (8) is connected with the spectrum camera (1), and the controller (8) is used for driving the spectrum camera (1) to rotate;
said processor (7) being adapted to perform a detection method as claimed in any one of claims 1-7.
9. A drone as claimed in claim 8, wherein: the controller (8) comprises a micro motor (2), a screw rod assembly (3) and a connecting rod (4), the screw rod assembly (3) is horizontally arranged on the bottom wall of the unmanned aerial vehicle (6), the micro motor (2) is used for driving a screw rod in the screw rod assembly (3) to rotate, a moving block in the screw rod assembly (3) at one end of the connecting rod (4) is hinged, the other end of the moving block is connected to the outer wall of the spectrum camera (1), a slide way is arranged on the outer wall of the spectrum camera (1) perpendicular to a hinge shaft of the spectrum camera (1), and one end of the connecting rod (4) away from the moving block slides along the length direction of the slide way and can be rotationally connected in the slide way.
CN202211606143.8A 2022-12-12 2022-12-12 Unmanned aerial vehicle spectrum-based pipeline defect detection method and unmanned aerial vehicle Pending CN116183609A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211606143.8A CN116183609A (en) 2022-12-12 2022-12-12 Unmanned aerial vehicle spectrum-based pipeline defect detection method and unmanned aerial vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211606143.8A CN116183609A (en) 2022-12-12 2022-12-12 Unmanned aerial vehicle spectrum-based pipeline defect detection method and unmanned aerial vehicle

Publications (1)

Publication Number Publication Date
CN116183609A true CN116183609A (en) 2023-05-30

Family

ID=86431702

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211606143.8A Pending CN116183609A (en) 2022-12-12 2022-12-12 Unmanned aerial vehicle spectrum-based pipeline defect detection method and unmanned aerial vehicle

Country Status (1)

Country Link
CN (1) CN116183609A (en)

Similar Documents

Publication Publication Date Title
JP7030431B2 (en) Inspection support system and inspection support control program
US7460980B2 (en) Method for the control of a pipe inspection system and for the evaluation of the inspection data
CN108258613B (en) Intelligent line inspection photoelectric pod and line inspection realization method
CN109978820B (en) Unmanned aerial vehicle route acquisition method, system and equipment based on laser point cloud
CN109325520B (en) Method, device and system for checking petroleum leakage
CN103674839B (en) A kind of visual Sample location operating system based on spot detection and method
CN109780452A (en) Gas based on laser telemetry technology leaks unmanned plane inspection retrieving concentration method
CN102434403A (en) System and method used for checking wind turbine
WO2015059241A1 (en) Collaborative robot for visually inspecting an aircraft
CN112348034A (en) Crane defect detection system based on unmanned aerial vehicle image recognition and working method
KR101634937B1 (en) System for automatic vision inspection, method using the same
CN113299035A (en) Fire identification method and system based on artificial intelligence and binocular vision
CN111038721A (en) Wind turbine blade inspection unmanned aerial vehicle and inspection method based on image recognition
CN113900436B (en) Inspection control method, inspection control device, inspection control equipment and storage medium
CN113877124A (en) Intelligent control system for jet flow falling point of fire monitor
CN113780246A (en) Unmanned aerial vehicle three-dimensional track monitoring method and system and three-dimensional monitoring device
KR20160123551A (en) System and method for controlling video information based automatic of the drone for the inspection of electric power facilities
CN113985907A (en) Tree barrier risk prediction and optimization method based on multi-load data of unmanned aerial vehicle
CN113034599A (en) Hole detection device and method for aircraft engine
CN116183609A (en) Unmanned aerial vehicle spectrum-based pipeline defect detection method and unmanned aerial vehicle
WO2022247597A1 (en) Papi flight inspection method and system based on unmanned aerial vehicle
CN112101450A (en) Non-contact vibration measurement equipment and method based on deep learning and multi-sensor fusion
CN116538025A (en) Wind-powered electricity generation wheel hub intelligence system of patrolling and examining based on AR equipment
Mitra et al. A UAV Payload for Real-time Inspection of Highway Ancillary Structures
CN114193425A (en) Inspection device and method based on visual detection

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