CN111282925B - Switch machine oil pipe inner wall washs and crackle identification system - Google Patents
Switch machine oil pipe inner wall washs and crackle identification system Download PDFInfo
- Publication number
- CN111282925B CN111282925B CN202010077519.5A CN202010077519A CN111282925B CN 111282925 B CN111282925 B CN 111282925B CN 202010077519 A CN202010077519 A CN 202010077519A CN 111282925 B CN111282925 B CN 111282925B
- Authority
- CN
- China
- Prior art keywords
- oil pipe
- image
- wall
- motor
- polishing head
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B08—CLEANING
- B08B—CLEANING IN GENERAL; PREVENTION OF FOULING IN GENERAL
- B08B9/00—Cleaning hollow articles by methods or apparatus specially adapted thereto
- B08B9/02—Cleaning pipes or tubes or systems of pipes or tubes
- B08B9/027—Cleaning the internal surfaces; Removal of blockages
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B08—CLEANING
- B08B—CLEANING IN GENERAL; PREVENTION OF FOULING IN GENERAL
- B08B9/00—Cleaning hollow articles by methods or apparatus specially adapted thereto
- B08B9/02—Cleaning pipes or tubes or systems of pipes or tubes
- B08B9/027—Cleaning the internal surfaces; Removal of blockages
- B08B9/032—Cleaning the internal surfaces; Removal of blockages by the mechanical action of a moving fluid, e.g. by flushing
- B08B9/0321—Cleaning the internal surfaces; Removal of blockages by the mechanical action of a moving fluid, e.g. by flushing using pressurised, pulsating or purging fluid
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B08—CLEANING
- B08B—CLEANING IN GENERAL; PREVENTION OF FOULING IN GENERAL
- B08B9/00—Cleaning hollow articles by methods or apparatus specially adapted thereto
- B08B9/02—Cleaning pipes or tubes or systems of pipes or tubes
- B08B9/027—Cleaning the internal surfaces; Removal of blockages
- B08B9/04—Cleaning the internal surfaces; Removal of blockages using cleaning devices introduced into and moved along the pipes
- B08B9/043—Cleaning the internal surfaces; Removal of blockages using cleaning devices introduced into and moved along the pipes moved by externally powered mechanical linkage, e.g. pushed or drawn through the pipes
- B08B9/0433—Cleaning the internal surfaces; Removal of blockages using cleaning devices introduced into and moved along the pipes moved by externally powered mechanical linkage, e.g. pushed or drawn through the pipes provided exclusively with fluid jets as cleaning tools
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B08—CLEANING
- B08B—CLEANING IN GENERAL; PREVENTION OF FOULING IN GENERAL
- B08B9/00—Cleaning hollow articles by methods or apparatus specially adapted thereto
- B08B9/02—Cleaning pipes or tubes or systems of pipes or tubes
- B08B9/027—Cleaning the internal surfaces; Removal of blockages
- B08B9/04—Cleaning the internal surfaces; Removal of blockages using cleaning devices introduced into and moved along the pipes
- B08B9/043—Cleaning the internal surfaces; Removal of blockages using cleaning devices introduced into and moved along the pipes moved by externally powered mechanical linkage, e.g. pushed or drawn through the pipes
- B08B9/047—Cleaning the internal surfaces; Removal of blockages using cleaning devices introduced into and moved along the pipes moved by externally powered mechanical linkage, e.g. pushed or drawn through the pipes the cleaning devices having internal motors, e.g. turbines for powering cleaning tools
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B27/00—Other grinding machines or devices
- B24B27/033—Other grinding machines or devices for grinding a surface for cleaning purposes, e.g. for descaling or for grinding off flaws in the surface
-
- 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
- G01N21/954—Inspecting the inner surface of hollow bodies, e.g. bores
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B08—CLEANING
- B08B—CLEANING IN GENERAL; PREVENTION OF FOULING IN GENERAL
- B08B2209/00—Details of machines or methods for cleaning hollow articles
- B08B2209/02—Details of apparatuses or methods for cleaning pipes or tubes
- B08B2209/027—Details of apparatuses or methods for cleaning pipes or tubes for cleaning the internal surfaces
- B08B2209/04—Details of apparatuses or methods for cleaning pipes or tubes for cleaning the internal surfaces using cleaning devices introduced into and moved along the pipes
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Pathology (AREA)
- Immunology (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Cleaning In General (AREA)
Abstract
The invention discloses a switch machine oil pipe inner wall cleaning and crack recognition system which comprises a heater, a liquid crystal display screen, a water pipe, a motor, a polishing head, a drill bit, a camera, a plastic coated steel wire rope and a control circuit board, wherein the motor is adopted to drive the polishing head to clean the oil pipe inner wall, the drill bit is adopted to grind the blocked part in the oil pipe to dredge the oil pipe, the cleaned oil pipe inner wall is subjected to crack detection through image recognition, after the switch machine oil pipe is cleaned, dirt in an oil tank can be effectively removed, the blocked part can be dredged, the service life of the oil pipe is prolonged, cracks on the oil tank inner wall are recognized through the image recognition, the damage condition of the oil pipe inner wall can be known in advance, the risk that a switch machine cannot normally work due to oil pipe faults is reduced, the accuracy of switch machine changing ways is improved, and the potential safety hazard of train operation.
Description
Technical Field
The invention relates to the field of oil pipe inner wall cleaning and crack identification, in particular to a switch machine oil pipe inner wall cleaning and crack identification system.
Background
The switch machine plays an irreplaceable role in the process of changing the track of the train, and the electro-hydraulic switch machine which is widely applied to the railway at present is powered by a motor and adopts hydraulic transmission. The inner wall of an oil pipe in a hydraulic system can be scaled, rusted and the like to cause the failure of the oil pipe, so that a point switch loses conversion power, a turnout cannot normally act, and the transportation safety of a railway is seriously influenced.
The cleaning of oil pipes in the prior art mainly comprises the following steps: the method comprises a heating cleaning method, a chemical cleaning method, a physical cleaning method and the like, wherein the heating cleaning method comprises medium-high frequency heating cleaning and hot boiling cleaning, and the defects of the methods are mainly as follows: low cleaning efficiency, slow speed and unsatisfactory effect. The chemical cleaning method is mainly characterized in that a chemical cleaning agent is added for cleaning, so that the blocked oil pipe is not easy to clean. Physical cleaning methods include brushing, scraping, drilling through, and the like. In addition, there is a high-pressure cleaning method, but the high-pressure equipment is high in cost and has a certain risk. And the cleaning operation is basically carried out in a special cleaning plant, the construction cost of the cleaning plant is high, the distance from the oil pumping operation site to the cleaning plant is generally long, the transportation time is long, and the cost is high. The method only cleans the inner wall of the oil pipe, and crack detection cannot be performed on the cleaned inner wall of the oil pipe, so that the oil pipe has certain potential safety hazard, and the condition that the switch machine cannot normally work due to oil pipe failure is easy to occur.
Disclosure of Invention
In order to solve the above problems, an object of the present invention is to provide a switch machine oil pipe inner wall cleaning and crack recognition system, wherein a motor is adopted to drive a polishing head to clean the inner wall of the oil pipe, a drill is adopted to grind a blocked place in the oil pipe, the oil pipe is dredged, and then crack detection is performed on the cleaned inner wall of the oil pipe through image recognition, so that the damage condition of the inner wall of the oil pipe can be known in advance, and the risk that the switch machine cannot work normally due to oil pipe failure is reduced.
In order to achieve the above object, the present invention provides a switch machine oil pipe inner wall cleaning and crack recognition system, which is realized by the following steps:
a switch machine oil pipe inner wall cleaning and crack recognition system comprises a heater, a liquid crystal display screen, a water pipe, a motor, a polishing head, a drill bit, a camera, a plastic coated steel wire rope and a control circuit board, wherein a water outlet of the heater is connected with the water pipe, the heater is used for heating water, the other end of the water pipe is connected with the middle part of the polishing head, one end of the plastic coated steel wire rope is connected with the bottom of the motor and used for pulling the motor to move in an oil pipe so as to drive the polishing head to more comprehensively clean the oil pipe, the polishing head is connected with a rotating shaft of the motor, the drill bit is arranged at the front end of the polishing head and is controlled by the control circuit board to rotate so as to drive the polishing head to rotate, the pipe wall of the oil pipe is cleaned, the drill bit at the front end of the polishing head also rotates along with the oil pipe to dredge the blocked place, and the crack of the inner wall of the oil pipe is identified, the liquid crystal display screen and the control circuit board are fixed together and used for displaying the image information of the inner wall of the pipeline collected by the camera, and an operator pulls/pushes the plastic-coated steel wire rope to drive the motor to move in the oil pipe so as to complete the comprehensive cleaning of the oil pipe.
When the oil pipe is cleaned, the oil stain cleaning agent is added into the heater, is fused with hot water in the heater and flows into the polishing head through the water pipe, so that the oil stain removing effect can be achieved.
The four openings are arranged at the intersection of the water pipe and the motor and are used for flushing the oil pipe after the polishing head is cleaned, so that the oil stain cleaning agent attached to the inner wall of the oil pipe can be washed away.
The tail part of the drill bit is connected with the polishing flower head, and the head part of the drill bit is designed to be in a spiral cutter type, so that the blocked part in the oil pipe can be removed conveniently in the propelling process of the motor.
The motor base is provided with three cameras for collecting images of the cleaned oil pipe, transmitting the images to the control circuit board for image recognition, recognizing cracks on the inner wall of the oil pipe and displaying the recognized results on the liquid crystal display screen.
The control circuit board comprises an FPGA control board and a motor drive board, wherein the FPGA control board is used for processing image information transmitted by three cameras, identifying cracks on the inner wall of the oil tank according to the transmitted image information, controlling a liquid crystal display screen to display the image and the crack information of the inner wall of the pipeline, and controlling the motor drive board to drive a motor to work so as to complete the cleaning and descaling of the inner wall of the oil tank.
The scheme of the oil pipe inner wall cleaning and crack identification of the invention comprises the following steps:
(1) system initialization processing
The system is restored to the state before use.
(2) Start of cleaning
Adding clear water and greasy dirt cleaner into the heater, incline oil pipe to between 30 ~ 60 degrees, greasy dirt cleaner flows into from the water pipe after dissolving in the hot water and polishes on the flower head, rotate by control circuit board control motor, and then drive the drill bit and polish the flower head and rotate, can let the motor move forward through promoting plastic-coated wire rope, and then realize that the drill bit rejects the place of jam, and make the flower head of polishing brush to having the oil pipe wall to scrub, water in the water pipe is sprayed on the oil pipe inner wall after the washing at four trompils of water pipe after that, realize oil pipe's secondary and wash.
(3) Image acquisition
After the motor, the polishing head and the drill bit clean the oil pipe forward, the three cameras behind the motor collect images of the cleaned oil pipe, transmit the collected images to the control circuit board, and identify cracks on the inner wall of the oil pipe in the control circuit board.
(4) Gray scale processing
And (3) respectively carrying out gray level processing on three pictures transmitted by the three cameras at one time, namely mapping pixels of the images to be between [0, 255 ].
(5) Graph fusion
The images acquired by the three cameras have overlapped places and also have different places, so that the images acquired by the three cameras are subjected to image fusion by adopting an image fusion method based on wavelet change, namely:
carrying out low-pass and high-pass filtering to decompose each picture into 4 sub-images containing different frequency components, and then carrying out wavelet decomposition on each original image to establish wavelet pyramid decomposition of the image; then, carrying out fusion processing on each decomposition layer, and carrying out fusion processing on each layer with different frequencies by adopting different fusion operators according to different requirements to finally obtain a wavelet pyramid; and performing wavelet transformation, namely image reconstruction, on the fused wavelet pyramid, wherein the reconstructed image is a fused image.
(6) Filtering denoising
The image acquisition process is difficult to avoid the influence of water mist in an oil pipe, so that the image contains a large amount of punctiform or peak-shaped noise, and in addition, noise is brought in the image fusion process, therefore, a median filtering method in time domain denoising is adopted to carry out filtering denoising processing on the fused image, and the specific method comprises the following steps:
determining a neighborhood in the image, then sequencing the gray value of the pixel, taking the middle value as a new value of the gray value of the pixel, wherein the neighborhood is a window, and the two-dimensional filtering output is set as g (x, y), then:
g(x,y)＝med{f(x-k),y-l},(k,l∈A) (1)
where g (x, y) is the filtered image, f (x-k, y-l) is the image before filtering, and a is a two-dimensional sliding template, typically a 2 x 2 or 3 x 3 region.
(7) Image segmentation
And (3) segmenting an image with cracks and an image without cracks in the inner wall of the oil pipe by adopting an edge detection segmentation method, and segmenting by detecting different region boundaries of the image on the inner wall of the oil pipe. Converting the image obtained in the step 6 into a binary image, solving the edge of the detected image by using an LOG operator according to the signal to noise ratio, namely, smoothing the image by using a Gaussian function, detecting the edge of the image by using a Laplace operator according to the zero crossing point of a second derivative, and further segmenting the crack in the oil pipe from the background.
(8) Crack identification
And performing pixel integral projection on the segmented image, wherein the accumulation of the gray value of each pixel point on the image in the horizontal direction is horizontal integral projection, and the accumulation in the vertical direction is vertical integral projection. The integral projection formula is as follows:
where f (x, y) is the pixel value of the image and L, V is the horizontal integral projection and the vertical integral projection, respectively. The horizontal integral projection is used as the width of the oil pipe crack, the vertical integral projection is used as the length of the oil pipe crack, and the area of the oil pipe crack can be obtained as follows:
S＝L·V (4)
(9) indicating cracking
The control circuit board controls the liquid crystal display screen to display the fused image, marks the length, width and area of the crack on the image, and provides crack information of the inner wall of the oil pipe for workers.
The motor is adopted to drive the polishing head to clean the inner wall of the oil pipe, the drill is adopted to grind the blocked part in the oil pipe, the oil pipe is dredged, and the structure for detecting cracks on the cleaned inner wall of the oil pipe is identified by images, so that the following beneficial effects can be achieved:
after the oil pipe of the point switch is cleaned, the dirt in the oil tank can be effectively removed, the blocked part can be dredged, the service life of the oil pipe is prolonged, cracks on the inner wall of the oil tank are identified through image identification, the damage condition of the inner wall of the oil pipe is convenient to learn in advance, the risk that the point switch cannot work normally due to oil pipe faults is reduced, the accuracy of track changing of turnouts is improved, and the potential safety hazard of train operation is reduced.
Drawings
FIG. 1 is a schematic diagram of the overall structure of a switch machine oil pipe inner wall cleaning and crack recognition system according to the present invention;
FIG. 2 is a cross-sectional view of a switch machine oil pipe inner wall cleaning and crack identification system according to the present invention;
FIG. 3 is a schematic diagram of a drill head of a switch machine oil pipe inner wall cleaning and crack recognition system according to the present invention;
FIG. 4 is a schematic view of a camera head of the switch machine oil pipe inner wall cleaning and crack recognition system according to the present invention;
FIG. 5 is a flow chart of a scheme of oil pipe inner wall cleaning and crack identification of the switch machine oil pipe inner wall cleaning and crack identification system according to the present invention;
FIG. 6 is a schematic diagram of image fusion of a switch machine oil pipe inner wall cleaning and crack recognition system according to the present invention;
FIG. 7 is a model diagram of a pixel-integrated projection for crack identification of the switch machine oil pipe inner wall cleaning and crack identification system according to the present invention;
fig. 8 is a schematic diagram of the inner wall cleaning and crack recognition system for the switch machine oil tube according to the present invention.
The main elements are indicated by symbols.
| Heating device | 1 | Liquid |
2 |
| |
3 | |
4 |
| |
5 | |
6 |
| |
7 | Plastic coated |
8 |
| |
9 | Opening of the |
10 |
| FPGA control panel | 11 | Motor drive plate | 12 |
Detailed Description
The present invention will be described in further detail with reference to the following examples and drawings.
Referring to fig. 1 to 8, a switch machine oil pipe inner wall cleaning and crack recognition system according to the present invention includes a heater 1, a liquid crystal display 2, a water pipe 3, a motor 4, a polishing head 5, a drill 6, a camera 7, a plastic coated steel wire rope 8, and a control circuit board 9.
As shown in fig. 1, a water outlet of a heater 1 is connected with a water pipe 3, the heater 1 is used for heating water, the other end of the water pipe 3 is connected with the middle of a polishing head 5, one end of a plastic-coated steel wire rope 8 is connected with the bottom of a motor 4 and used for pulling the motor 4 to move in an oil pipe so as to drive the polishing head 5 to more comprehensively clean the oil pipe, the polishing head 5 is connected with a rotating shaft of the motor 4, a drill bit 6 is installed at the front end of the polishing head 5 and is controlled by a control circuit board 9 to rotate so as to drive the polishing head 5 to rotate and clean the wall of the oil pipe, the drill bit 6 at the front end of the polishing head 5 also rotates to dredge the blocked place in the oil pipe, a camera 7 is installed at the bottom of the motor 4 and is used for collecting image information of the inner wall of the cleaned oil pipe and identifying cracks on the inner wall of the, the pipeline inner wall image information is used for displaying the image information of the pipeline inner wall collected by the camera 7, the operating personnel pulls/pushes the plastic coated steel wire rope 8 to drive the motor 4 to move in the oil pipe to complete the comprehensive cleaning of the oil pipe, the control circuit board 9 controls the motor 4 to rotate, hot water in the heater 1 flows to the polishing head 5 along with the water pipe 3, the polishing head 5 cleans the inner wall of the oil pipe along with the rotation of the motor 4, the polishing head 5 cleans the pipe wall forward, and the camera 7 identifies cracks on the cleaned pipe wall at the back.
When cleaning oil pipe, add the greasy dirt cleaner into heater 1, fuse together with hot water in heater 1, flow into on the flower head 5 of polishing through water pipe 3, can reach the effect of deoiling dirty.
As shown in fig. 2, the water pipe 3 is provided with four openings 10 at the intersection with the motor 4, and is used for washing the oil pipe cleaned by the polishing head 5, so as to wash away the oil stain cleaning agent attached to the inner wall of the oil pipe.
As shown in figure 3, the tail part of the drill 6 is connected with the grinding bit 5, and the head part is designed to be in a spiral cutter type, so that the blocked part in the oil pipe can be removed conveniently by the motor 4 in the propelling process. The drill bit 6 is screwed in the front to remove the blocked sundries, so that the oil pipe is smooth, and the dirt on the inner wall of the oil pipe can be removed after the polishing bit 5 is cleaned.
As shown in fig. 4, three cameras 7 are installed on the base of the motor 4, and are used for collecting images of the cleaned oil pipe, transmitting the images to the control circuit board 9 for image recognition, recognizing cracks on the inner wall of the oil pipe, and displaying the recognized results on the liquid crystal display screen 2. And writing an algorithm for identifying cracks in the image into the control circuit board 9, and carrying out a series of operations such as fusion, gray processing, filtering and denoising, image segmentation, pixel integral projection and the like on the image collected by the camera 7 to realize the identification of the cracks on the inner wall of the oil pipe.
As shown in fig. 8, the control circuit board 9 includes an FPGA control board 11 and a motor drive board 12, where the FPGA control board 11 is configured to process image information transmitted from the three cameras 7, identify cracks on the inner wall of the oil tank according to the transmitted image information, control the liquid crystal display 2 to display the image of the inner wall of the pipeline and the crack information, and control the motor drive board 12 to drive the motor 4 to work, thereby completing cleaning and descaling of the inner wall of the oil tank.
As shown in fig. 5, the scheme of oil pipe inner wall cleaning and crack identification is as follows:
(1) system initialization processing
The system is restored to the state before use.
(2) Start of cleaning
Add clear water and greasy dirt cleaner into heater 1, incline oil pipe to between 30 ~ 60 degrees, the greasy dirt cleaner flows into from water pipe 3 after dissolving in the hot water on the flower head 5 of polishing, by control circuit board 9 control motor 4 rotates, and then drive drill bit 6 and the flower head 5 of polishing rotates, it can let motor 4 forward movement to mould wire rope 8 through promoting the package, and then realize that drill bit 6 rejects the place of jam, and make flower head 5 of polishing scrub the tubing wall, water in water pipe 3 is sprayed on the oil pipe inner wall after the washing at four trompils of water pipe 3 after that, realize the secondary of oil pipe and wash.
(3) Image acquisition
After the motor 4, the polishing head 5 and the drill bit 6 clean the oil pipe forwards, the three cameras 7 behind the motor 4 collect images of the cleaned oil pipe, transmit the collected images to the control circuit board 9, and identify cracks on the inner wall of the oil pipe in the control circuit board 9.
(4) Gray scale processing
The three pictures transmitted by the three cameras 7 at a time are respectively subjected to gray processing, namely, pixels of the images are mapped between [0, 255 ]. Compared with a color image, the gray image has less information quantity, can reduce the calculation quantity and is convenient to process.
(6) Graph fusion
The images acquired by the three cameras 7 have overlapped places and also have different places, so that the images acquired by the three cameras 7 are subjected to image fusion by adopting an image fusion method based on wavelet change, namely:
carrying out low-pass and high-pass filtering to decompose each picture into 4 sub-images containing different frequency components, and then carrying out wavelet decomposition on each original image to establish wavelet pyramid decomposition of the image; then, carrying out fusion processing on each decomposition layer, and carrying out fusion processing on each layer with different frequencies by adopting different fusion operators according to different requirements to finally obtain a wavelet pyramid; and performing wavelet transformation, namely image reconstruction, on the fused wavelet pyramid, wherein the reconstructed image is a fused image. Fig. 6 is a schematic diagram of image fusion.
(6) Filtering denoising
The image acquisition process is difficult to avoid being influenced by water mist in an oil pipe, so that the image contains a large amount of punctiform or peak-shaped noises, in addition, noises are brought in the image fusion process, meanwhile, the image is difficult to avoid bringing in some noises in the transmission and conversion processes, and the noises can cause image blurring, image distortion and the like, therefore, the fused image is subjected to filtering and denoising treatment by adopting a median filtering method in time domain denoising, and the specific method is as follows:
determining a neighborhood in the image, then sequencing the gray value of the pixel, taking the middle value as a new value of the gray value of the pixel, wherein the neighborhood is a window, and the two-dimensional filtering output is set as g (x, y), then:
g(x,y)＝med{f(x-k),y-l},(k,l∈A) (1)
where g (x, y) is the filtered image, f (x-k, y-l) is the image before filtering, and a is a two-dimensional sliding template, typically a 2 x 2 or 3 x 3 region.
The purpose of removing noise can be achieved through two-dimensional median filtering, and images can be enhanced. The method is to remove a two-dimensional sliding template of a certain structure, sort the pixel values in the template according to the size, and generate a two-dimensional data series which is monotonically increased (or decreased).
(7) Image segmentation
Because the places with cracks and the places without cracks have obvious boundaries after the inner wall of the oil pipe is cleaned, the gray levels of the crack image and the background image are different, and the boundaries have obvious edges, the image with cracks and the image without cracks in the inner wall of the oil pipe are divided by adopting an edge detection and division method, and the division is carried out by detecting the boundaries of different areas of the image on the inner wall of the oil pipe. Converting the image obtained in the step 6 into a binary image, solving the edge of the detected image by using an LOG operator according to the signal to noise ratio, namely, smoothing the image by using a Gaussian function, detecting the edge of the image by using a Laplace operator according to the zero crossing point of a second derivative, and further segmenting the crack in the oil pipe from the background.
(8) Crack identification
As shown in fig. 7, the divided image is subjected to pixel integral projection, and the accumulation of the gray value of each pixel point on the image in the horizontal direction is horizontal integral projection, and the accumulation in the vertical direction is vertical integral projection. The integral projection formula is as follows:
where f (x, y) is the pixel value of the image and L, V is the horizontal integral projection and the vertical integral projection, respectively. The horizontal integral projection is used as the width of the oil pipe crack, the vertical integral projection is used as the length of the oil pipe crack, and the area of the oil pipe crack can be obtained as follows:
S＝L·V (4)
(9) indicating cracking
The control circuit board 9 controls the liquid crystal display screen 2 to display the fused image, marks the length, width and area of the crack on the image, and provides information of the crack on the inner wall of the oil pipe for workers.
The working principle and the working process of the invention are as follows:
as shown in fig. 8, hot water in the heater 1 flows onto the polishing head 5 along with the water pipe 3, the FPGA control board 11 controls the motor drive board 12 to drive the motor 4 to work, the polishing head 5 rotates along with the motor 4 to clean the inner wall of the oil pipe, the polishing head 5 cleans the pipe wall forward, the FPGA control board 11 identifies cracks on the inner wall of the oil tank according to image information transmitted by the three cameras 7 and controls the liquid crystal display 2 to display the image and the crack information of the inner wall of the oil pipe, and then cleaning and descaling of the inner wall of the oil tank are completed.
Claims (6)
1. A method for cleaning and identifying cracks on the inner wall of a switch machine oil pipe is applied to a system for cleaning and identifying cracks on the inner wall of the switch machine oil pipe, and is characterized in that: the system comprises a heater, a liquid crystal display screen, a water pipe, a motor, a polishing head, a drill bit, a camera, a plastic-coated steel wire rope and a control circuit board, wherein a water outlet of the heater is connected with the water pipe, the heater is used for heating water, the other end of the water pipe is connected with the middle part of the polishing head, one end of the plastic-coated steel wire rope is connected with the bottom of the motor and used for pulling the motor to move in the oil pipe so as to drive the polishing head to more comprehensively clean the oil pipe, the polishing head is connected with a rotating shaft of the motor, the drill bit is arranged at the front end of the polishing head and is controlled by the control circuit board to rotate so as to drive the polishing head to rotate, the pipe wall of the oil pipe is cleaned, meanwhile, the drill bit at the front end of the polishing head also rotates along with the motor to dredge the blocked place in the oil pipe, the liquid crystal display screen is fixed with the control circuit board and used for displaying image information of the inner wall of the pipeline collected by the camera, an operator pulls/pushes the plastic-coated steel wire rope to drive the motor to move in the oil pipe so as to complete the overall cleaning of the oil pipe, the control circuit board controls the motor to rotate, hot water in the heater flows onto the polishing head along with the water pipe, the polishing head cleans the inner wall of the oil pipe along with the rotation of the motor, the polishing head cleans the pipe wall forwards, and the camera identifies cracks on the cleaned pipe wall backwards;
the method for cleaning the inner wall of the oil pipe and identifying the cracks comprises the following steps:
(1) system initialization processing
Restoring the system to a state before use;
(2) start of cleaning
Adding clean water and an oil stain cleaning agent into a heater, inclining an oil pipe to a range of 30-60 degrees, enabling the oil stain cleaning agent to flow onto a polishing head from the water pipe after being dissolved in hot water, controlling a motor to rotate by a control circuit board, further driving a drill bit and the polishing head to rotate, enabling the motor to move forwards by pushing a plastic-coated steel wire rope, further removing blocked places by the drill bit, enabling the polishing head to scrub the wall of the oil pipe, and then spraying water in the water pipe onto the inner wall of the cleaned oil pipe through four openings of the water pipe, so as to realize secondary washing of the oil pipe;
(3) image acquisition
After the motor, the polishing head and the drill bit clean the oil pipe forward, three cameras behind the motor collect images of the cleaned oil pipe, and transmit the collected images to the control circuit board at the same time, so that cracks on the inner wall of the oil pipe are identified in the control circuit board;
(4) gray scale processing
Carrying out gray processing on three pictures transmitted by the three cameras at one time respectively, namely mapping pixels of the images between [0, 255 ];
(5) graph fusion
The image fusion method based on wavelet change is adopted to perform image fusion on the images acquired by the three cameras, namely:
carrying out low-pass and high-pass filtering to decompose each picture into 4 sub-images containing different frequency components, and then carrying out wavelet decomposition on each original image to establish wavelet pyramid decomposition of the image; then, carrying out fusion processing on each decomposition layer, and carrying out fusion processing on each layer with different frequencies by adopting different fusion operators according to different requirements to finally obtain a wavelet pyramid; performing wavelet transformation, namely image reconstruction, on the fused wavelet pyramid, wherein the reconstructed image is a fused image;
(6) filtering denoising
Filtering and denoising the fused image by adopting a median filtering method in time domain denoising, wherein the specific method comprises the following steps:
determining a neighborhood in the image, then sequencing the gray value of the pixel, taking the middle value as a new value of the gray value of the pixel, wherein the neighborhood is a window, and the two-dimensional filtering output is set as g (x, y), then:
g(x,y)＝med{f(x-k),y-l},(k,l∈A)
wherein g (x, y) is the filtered image, f (x-k, y-l) is the image before filtering, a is a two-dimensional sliding template, typically a 2 x 2 or 3 x 3 region;
(7) image segmentation
Dividing an image with cracks and an image without cracks in the inner wall of the oil pipe by adopting an edge detection and division method, dividing different region boundaries of the image with the inner wall of the oil pipe by detecting, converting the image obtained in the step 6 into a binary image, solving the edge of the detected image by adopting an LOG (level of gravity) operator according to a signal-to-noise ratio, namely, smoothing the image by adopting a Gaussian function, detecting the edge of the image by adopting a Laplace operator according to a second derivative zero crossing point, and further dividing the cracks in the oil pipe from the background;
(8) crack identification
And performing pixel integral projection on the segmented image, wherein the accumulation of the gray value of each pixel point on the image in the horizontal direction is horizontal integral projection, the accumulation in the vertical direction is vertical integral projection, and the integral projection formula is as follows:
wherein f (x, y) is a pixel value of the image, L, V is a horizontal integral projection and a vertical integral projection respectively, the horizontal integral projection is used as the width of the oil pipe crack, the vertical integral projection is used as the length of the oil pipe crack, and the area of the oil pipe crack can be obtained as follows:
S＝L·V
(9) indicating cracking
The control circuit board controls the liquid crystal display screen to display the fused image, marks the length, width and area of the crack on the image, and provides crack information of the inner wall of the oil pipe for workers.
2. The switch machine oil pipe inner wall cleaning and crack recognition method according to claim 1, wherein: the water pipe is provided with four openings at the intersection with the motor and is used for flushing the oil pipe after the polishing head is cleaned.
3. The switch machine oil pipe inner wall cleaning and crack recognition method according to claim 1, wherein: the tail part of the drill bit is connected with the polishing head, and the head part of the drill bit is designed to be in a spiral cutter type.
4. The switch machine oil pipe inner wall cleaning and crack recognition method according to claim 1, wherein: and the motor base is provided with three cameras for collecting images of the cleaned oil pipe, transmitting the images to the control circuit board for image recognition, recognizing cracks on the inner wall of the oil pipe and displaying the recognized results on the liquid crystal display screen.
5. The switch machine oil pipe inner wall cleaning and crack recognition method according to claim 4, wherein: and writing an algorithm for identifying cracks in the image into the control circuit board, and carrying out fusion, gray processing, filtering and denoising, image segmentation and pixel integral projection on the image collected by the camera to identify the cracks on the inner wall of the oil pipe.
6. The switch machine oil pipe inner wall cleaning and crack recognition method according to claim 5, wherein: the control circuit board comprises an FPGA control board and a motor drive board, wherein the FPGA control board is used for processing image information transmitted by the three cameras, identifying cracks on the inner wall of the oil tank according to the transmitted image information, controlling the liquid crystal display screen to display the image and the crack information of the inner wall of the pipeline, and controlling the motor drive board to drive the motor to work so as to complete cleaning and descaling of the inner wall of the oil tank.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010077519.5A CN111282925B (en) | 2020-01-30 | 2020-01-30 | Switch machine oil pipe inner wall washs and crackle identification system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010077519.5A CN111282925B (en) | 2020-01-30 | 2020-01-30 | Switch machine oil pipe inner wall washs and crackle identification system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111282925A CN111282925A (en) | 2020-06-16 |
| CN111282925B true CN111282925B (en) | 2021-04-23 |
Family
ID=71023423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010077519.5A Active CN111282925B (en) | 2020-01-30 | 2020-01-30 | Switch machine oil pipe inner wall washs and crackle identification system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111282925B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112067619B (en) * | 2020-08-05 | 2021-04-20 | 四川大学 | Visual peeping instrument for detecting cracks on surface of geological micropore and crack detection method |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN200998723Y (en) * | 2007-01-13 | 2008-01-02 | 管序荣 | Oil pipe purifier |
| CN201008862Y (en) * | 2007-03-20 | 2008-01-23 | 吐哈石油勘探开发指挥部机械厂 | Derusting, contaminant removing, cleaning apparatus for internal wall of oil pipe with high pressure water shoot |
| CN201180527Y (en) * | 2008-04-16 | 2009-01-14 | 王志杰 | Descaling apparatus for inner wall of oil pipe |
| CN103846257A (en) * | 2012-11-29 | 2014-06-11 | 大连凯泓科技有限公司 | Reinforced oil pipe washer |
| CN106909926A (en) * | 2015-12-21 | 2017-06-30 | 深圳市科彩印务有限公司 | A kind of uniformity detecting method and device of cigarette bag printing color |
| CN108961230B (en) * | 2018-06-28 | 2020-09-11 | 武汉大学 | Identification and extraction method for structural surface crack characteristics |
| CN209049853U (en) * | 2018-09-24 | 2019-07-02 | 张小红 | A kind of water conservancy construction pipe-dredging diversing flow system |
-
2020
- 2020-01-30 CN CN202010077519.5A patent/CN111282925B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111282925A (en) | 2020-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN203263303U (en) | Electric sweeping and washing device | |
| CN204722984U (en) | One washes ground dryer | |
| CN206448209U (en) | A kind of town road guard bar washing device of rinse water recycling | |
| CN105455748B (en) | Multi-modal robot for cleaning wall surface control method | |
| CN111282925B (en) | Switch machine oil pipe inner wall washs and crackle identification system | |
| CN104670173A (en) | Device for cleaning whole locomotive | |
| CN115924020A (en) | Cleaning disc for ultrahigh-pressure water jet flow rust removal and control method thereof | |
| CN109249903B (en) | Automatic cleaning device for high-speed train | |
| CN117364912A (en) | Two-section intelligent robot for dredging urban drainage pipeline and working method thereof | |
| CN104438377A (en) | Automatic control system and method for strip steel surface rust removal | |
| CN207343328U (en) | A kind of coal dewatering screen cleaning device | |
| CN203438083U (en) | Multidimensional rotary abrasive jet cleaning device | |
| CN104324902A (en) | Device for removing oxide layers of steel strips | |
| CN202896537U (en) | Full-automatic wheel cleaner | |
| CN215289972U (en) | Small-size plane steel gate panel robot of decontaminating | |
| CN108043801A (en) | A kind of head signboard cleaning device | |
| CN108625317A (en) | A kind of road identification system for Environmental sanitation cleaning vehicle | |
| CN214355926U (en) | Blowing dust removal equipment | |
| CN209815714U (en) | Slag guiding device for grid slag remover | |
| CN208949810U (en) | A kind of fast sweep mechanism of sweeper | |
| CN208303446U (en) | A kind of industrial goods cleaning machine | |
| CN104805800B (en) | Dykes and dams purging system and method for work that ultrasound, cleaning brush, the liquid whistle cooperate | |
| CN109356076A (en) | A kind of ladder advanceable road surface flusher and its cleaning method | |
| CN216026849U (en) | Petroleum pipeline cleaning device | |
| CN211538749U (en) | 3D model repairing and cleaning device |
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 |