CN111853557A - Automatic identification method and system for detecting pipeline leakage based on ground penetrating radar - Google Patents
Automatic identification method and system for detecting pipeline leakage based on ground penetrating radar Download PDFInfo
- Publication number
- CN111853557A CN111853557A CN202010738206.XA CN202010738206A CN111853557A CN 111853557 A CN111853557 A CN 111853557A CN 202010738206 A CN202010738206 A CN 202010738206A CN 111853557 A CN111853557 A CN 111853557A
- Authority
- CN
- China
- Prior art keywords
- edge
- echo
- image
- radar
- hole
- 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.)
- Granted
Links
- 230000000149 penetrating effect Effects 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000001514 detection method Methods 0.000 claims abstract description 46
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000009499 grossing Methods 0.000 claims abstract description 23
- 238000001914 filtration Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 230000008859 change Effects 0.000 claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 230000009977 dual effect Effects 0.000 claims description 4
- 230000035772 mutation Effects 0.000 claims description 2
- 238000003708 edge detection Methods 0.000 abstract description 11
- 238000011179 visual inspection Methods 0.000 abstract description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 30
- 238000012360 testing method Methods 0.000 description 19
- 239000002689 soil Substances 0.000 description 17
- 238000012795 verification Methods 0.000 description 13
- 238000002474 experimental method Methods 0.000 description 10
- 230000000694 effects Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000002592 echocardiography Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 239000004576 sand Substances 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 229910001018 Cast iron Inorganic materials 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 239000011449 brick Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- -1 pipeline Substances 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 239000008399 tap water Substances 0.000 description 1
- 235000020679 tap water Nutrition 0.000 description 1
- 238000012418 validation experiment Methods 0.000 description 1
- 238000003911 water pollution Methods 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
- F17D5/02—Preventing, monitoring, or locating loss
- F17D5/06—Preventing, monitoring, or locating loss using electric or acoustic means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/885—Radar or analogous systems specially adapted for specific applications for ground probing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V3/00—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation
- G01V3/12—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation operating with electromagnetic waves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Electromagnetism (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Quality & Reliability (AREA)
- Environmental & Geological Engineering (AREA)
- Geology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Acoustics & Sound (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Radar Systems Or Details Thereof (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an automatic identification method and system for detecting pipeline leakage based on ground penetrating radar, wherein the method comprises the following steps: preprocessing radar echo images of the ground penetrating radar under different survey lines to obtain gray level images; performing median filtering smoothing processing on the gray level image; identifying the edge of the echo under the hole by using the sudden change of the gray value of the edge region in the image subjected to the median filtering smoothing; and performing circular fitting on the edge of the echo under the hole by using a circular detection function, and identifying the pipeline leakage working condition according to the number of circles obtained by fitting and the parameter information of the circles. The invention realizes the edge detection, the feature identification and the automatic detection of the typical leakage features, particularly can identify the working condition of leakage, does not need to depend on the manual visual inspection of experienced detection personnel, and improves the efficiency and the accuracy.
Description
Technical Field
The invention relates to the technical field of automatic detection of leakage of water supply pipelines and pipe network systems, in particular to an automatic identification method and system for detecting pipeline leakage based on a ground penetrating radar.
Background
Pipeline leakage is a common fault of a water supply network or a pressure water conveying pipeline, and the energy loss of a pipe network, such as running, overflowing, dripping, leakage and a booster pump station, caused by the pipeline leakage is a hot point problem in the global water supply industry.
The current state of the leakage rate investigation of 28 cities and regions in asia shows that the current state of the leakage rate of each city substantially matches the economic development level, with tokyo (japan) being the best (about 3%) and gals answers (india) being relatively poor (up to 60%). The investigation of the urban water supply association shows that the average leakage rate of the tap water in 654 cities in China is up to 15.7 percent, even 70 percent in underdeveloped cities in rural areas, the average yield and sales difference of the urban water supply network is up to 17.9 percent, and the average leakage rate is far lower than the requirement that the leakage rate of the water supply network is controlled within 10 percent according to the action plan for preventing and controlling water pollution in China. Therefore, the research on the theory and the method of early warning, monitoring and positioning the faults of the pipeline water delivery engineering and the urban water supply network is developed, which not only meets the urgent need of water-saving social construction in China, but also has great social, economic and practical significance.
At present, the pipeline leakage detection method mainly comprises two types: direct detection methods and indirect detection methods. The direct detection method is mainly based on hardware equipment, and judges the position of leakage by analyzing data detected by the hardware equipment which is installed on the pipeline in advance.
And an indirect detection method of the pipeline leakage detection technology based on the ground penetrating radar becomes a nondestructive detection method with great prospect and high practicability. The basic principle of the method is that when electromagnetic waves transmitted by a radar meet interfaces or objects with electrical difference in the propagation process, the electromagnetic waves are reflected, and the spatial position, structure, form and depth of an underground medium can be inferred according to the characteristics of the received electromagnetic waves such as waveform, amplitude intensity and time change. Therefore, the pipeline leakage detection technology based on the ground penetrating radar is also used for essentially identifying the leakage position by detecting the abnormality of the radar reflected wave caused by local soil cavity or soil infiltration caused by leakage, for example, the depth change of the pipeline represented by the change of the dielectric constant of the soil around the pipeline caused by leakage in the radar reflected wave image, and the difference of the dielectric constants of different media (dry sand soil, pipeline, water and wet sand soil) is large, so that the difference of the radar wave images reflected by the leakage state is large, and the pipeline and the leakage parameter can be identified accordingly.
For example, the method for detecting leakage of a water supply pipeline based on ground penetrating radar image feature signal identification disclosed in chinese patent application CN110376584A combines hyperbolic signal features and multiple wave forming principle and their position information on an image to observe features of signals in the image, and identifies pipeline leakage signals and interference signals in the image, so as to accurately identify pipeline leakage information in the image. However, the solution has the following problems in practical application:
(1) the scheme can only identify whether the pipeline leakage occurs or not, and cannot accurately identify different leakage states, such as the working condition of leakage;
(2) the scheme identifies pipeline leakage based on images and needs to rely on experienced detection personnel. For example, the leakage characteristics are mainly explained by comparing ground penetrating radar echoes obtained at the initial and final stages of leakage through manual visual inspection, detection personnel are required to have high-level professional knowledge and rich professional practice, and additional parameter information is required to complete the analysis;
(3) since the geometric expandability of the ground penetrating radar reflected waves and the main surface reflected waves cover the reflection and scattering of other underground facilities, even if the echoes provide useful information, the images are not easy to interpret, thereby influencing the identification of the leakage characteristics.
In view of this, it is urgently needed to provide an improvement on the existing detection method for detecting pipeline leakage based on ground penetrating radar, and by automatically identifying the detection image, edge detection, feature identification and automatic detection of typical leakage features are realized, and the operability and effectiveness of applying the leakage ground penetrating radar detection method to actual pipeline engineering are improved.
Disclosure of Invention
The invention aims to solve the technical problems that the existing detection method for detecting the pipeline leakage based on the ground penetrating radar needs to rely on experienced detection personnel and cannot accurately identify different leakage states.
In order to solve the technical problems, the technical scheme adopted by the invention is to provide an automatic identification method for detecting pipeline leakage based on a ground penetrating radar, which comprises the following steps:
preprocessing radar echo images of the ground penetrating radar under different survey lines to obtain gray level images;
performing median filtering smoothing processing on the gray level image;
identifying the edge of the echo under the hole by using the sudden change of the gray value of the edge region in the image subjected to the median filtering smoothing;
and performing circular fitting on the edge of the echo under the hole by using a circular detection function, and identifying the pipeline leakage working condition according to the number of circles obtained by fitting and the parameter information of the circles.
In the method, the existing circular detection function cv2. Houghcirles in the existing Python platform module is used for carrying out circular fitting on the edge of the echo under the hole, so as to obtain the number of circles and the parameter information of the circles.
In the method, a pipeline leakage working condition result is obtained according to whether the number of circles exceeds a set early warning threshold value.
In the method, the value formula of the gray value Y adopted by the preprocessing is as follows: y ═ 0.299 · R +0.587 · G +0.114 · B, where: r, G, B is the color value of any pixel point in the radar echo image for preprocessing.
In the method, when the median filtering smoothing processing is performed on the gray-scale image, firstly, a Gauss filter is adopted to suppress false edges and impulse noise in the gray-scale image.
In the above method, identifying the "echo under hole" edge comprises the steps of:
adopting first order differential in a 2' 2 neighborhood to calculate the intensity gradient D and the direction q of a pixel point in the radar echo image, wherein:
in the formula, x and y are coordinates of pixel points in the radar echo image;
traversing all values on the intensity gradient matrix, and only reserving pixel points with maximum values in the edge direction;
and screening the authenticity of the edge by using a Canny dual threshold, eliminating the false edge and reserving the true edge line.
The invention also provides an automatic identification system for detecting pipeline leakage based on ground penetrating radar, which comprises:
the preprocessing module is used for preprocessing radar echo images of the ground penetrating radar under different measuring lines to obtain gray level images;
the smoothing processing module is used for carrying out median filtering smoothing processing on the gray level image;
the under-hole echo edge identification module is used for identifying an under-hole echo edge by utilizing the mutation of the gray value of the edge region in the image subjected to the median filtering smoothing processing;
and the pipeline leakage working condition identification module is used for performing circular fitting on the edge of the hole echo by using a circular detection function and identifying the pipeline leakage working condition according to the number of circles obtained by fitting and the parameter information of the circles.
In the above system, the "echo under hole" edge identification module identifies the "echo under hole" edge by:
adopting first order differential in a 2' 2 neighborhood to calculate the intensity gradient D and the direction q of a pixel point in the radar echo image, wherein:
in the formula, x and y are coordinates of pixel points in the radar echo image;
traversing all values on the intensity gradient matrix, and only reserving pixel points with maximum values in the edge direction;
and screening the authenticity of the edge by using a Canny dual threshold, eliminating the false edge and reserving the true edge line.
Compared with the prior art, the automatic identification method and system for detecting the pipeline leakage based on the ground penetrating radar, provided by the invention, utilize the abrupt change of the gray value of the edge area in the image after the median filtering smoothing processing to identify the edge of the echo under the hole; and performing circular fitting on the edge of the echo under the hole by using a circular detection function, and identifying the pipeline leakage working condition according to the number of circles obtained by fitting and the parameter information of the circles. The edge detection, the feature recognition and the automatic detection of the typical leakage features are realized, the leakage working condition can be particularly recognized, the manual visual inspection by experienced detection personnel is not needed, and the efficiency and the accuracy are improved.
Drawings
FIG. 1 is a flow chart of an automatic identification method for detecting pipeline leakage based on ground penetrating radar in the present invention;
FIG. 2 is a schematic diagram of an automatic identification system for pipeline leakage detection based on ground penetrating radar according to the present invention;
FIG. 3 is a schematic diagram of the transmission and reception of electromagnetic wave signals during scanning of radar waves in a direction perpendicular to a pipe;
FIG. 4 is a schematic view of the layout of the test lines in the verification experiment of the present invention;
FIG. 5 is a radar echo image under different working conditions under Y-9 survey line in the verification experiment of the invention;
FIG. 6 shows radar echo images under different conditions under X-11 line measurement in a verification experiment according to the present invention;
FIG. 7 is a radar echo image under Y-9 line of sight when a pipe leaks under the condition of embedding a small ball in a verification experiment of the invention;
FIG. 8 is a comparison of radar echo images after graying processing in step 110 in a verification experiment according to the present invention;
FIG. 9 is a comparison of radar echo images after the median filtering smoothing process of step 120 in a validation experiment according to the present invention;
FIG. 10 is a comparison graph of the edge detection of "echo under hole" using different operators in the verification experiment of the present invention;
FIG. 11 is an alarm prompt diagram of the pipeline test result in the verification experiment of the present invention.
Detailed Description
The invention provides an automatic identification method for detecting pipeline leakage based on a ground penetrating radar, which can automatically detect and identify the pipeline leakage working condition from a radar echo image, particularly identify the working condition of leakage, does not need to compare based on the image by a professional, and improves the efficiency and the accuracy. The invention is described in detail below with reference to the drawings and the detailed description.
Fig. 1 is a flowchart of an automatic identification method for detecting pipeline leakage based on a ground penetrating radar, which includes the following steps:
and step 110, loading radar echo images of the ground penetrating radar under different survey lines, and performing gray processing (namely preprocessing) on the radar echo images to obtain gray images of the radar echo images.
In this step, the value formula of the gray value Y of the pixel point to be subjected to gray processing is as follows:
Y=0.299·R+0.587·G+0.114·B。
in the formula: r, G, B is the color value of the pixel point of the radar echo image subjected to gray scale processing.
And 120, performing median filtering smoothing processing on the gray level image of the radar echo image.
In the step, firstly, a Gauss filter is adopted to restrain false edges and impulse noise in the gray level image, and then a median filtering algorithm is adopted to carry out smoothing processing so as to protect edges of key positions of the gray level image.
And step 130, identifying the edge of the echo under the hole by using the abrupt change of the gray value of the edge region in the image after the median filtering smoothing processing.
In this step, identifying the "echo under hole" edge comprises the steps of:
step 131, calculating the intensity gradient Δ and the direction θ of the pixel points in the radar echo image by adopting the first-order differential in the 2' 2 neighborhood, wherein:
in the formula, x and y are coordinates of pixel points in the radar echo image.
Step 132, traverse all values on the intensity gradient matrix, and only keep the pixel points with the maximum value in the "echo under hole" edge direction.
And step 133, screening the authenticity of the edge of the echo under the hole by using a Canny edge detection operator with strong adaptability and using the double thresholds of the Canny edge detection operator, eliminating the false edge, and reserving the true edge line.
And 140, performing circle fitting on the edge of the echo under the hole by using a circle detection function, and identifying the pipeline leakage working condition according to the number of circles obtained by fitting and the parameter information of the circles.
In the step, firstly, a circle detection function cv2. Houghcirles in the existing Python platform module is used for carrying out circle fitting on the edge of the echo under the hole to obtain the number of circles and the parameter information of the circles (mainly comprising a parameter 1: a threshold value of a circle center accumulator in the detection process; a parameter 2: the minimum radius of the detected circle; a parameter 3: the maximum radius of the detected circle); and then, obtaining a pipeline leakage working condition result according to whether the number of the circles exceeds a set early warning threshold value.
If the number of the circles exceeds a set early warning threshold value, a popup window prompts that the pipeline under the measuring line has leakage; otherwise, the pop-up window prompts that no leakage exists under the measuring line. The early warning threshold value can be set to 0-2 according to the actual environment.
Based on the above method, the present invention further provides an automatic identification system for detecting pipeline leakage based on a ground penetrating radar, as shown in fig. 2, the system includes:
the preprocessing module 10 is configured to perform gray processing (i.e., preprocessing) on radar echo images of the ground penetrating radar under different survey lines to obtain a gray image of the radar echo image;
a smoothing module 20, configured to perform median filtering smoothing on the grayscale image;
the "echo under hole" edge identification module 30 is configured to identify an "echo under hole" edge by using a sudden change of a gray value of an edge region in an image subjected to median filtering smoothing processing;
and the pipeline leakage working condition identification module 40 is used for performing circular fitting on the edge of the hole echo by using a circular detection function and identifying the pipeline leakage working condition according to the number of circles obtained by fitting and the parameter information of the circles.
The feasibility of the above method and system is verified by specific verification experiments.
FIG. 3 is a schematic diagram of the transmission and reception of electromagnetic wave signals during scanning of radar waves perpendicular to the direction of a pipe. According to the radar wave reflection principle, the relation between the two-way propagation time t, the propagation speed v of the electromagnetic wave in the soil medium and the travel L of the ground penetrating radar at any position can be established,
in the formula: h is the thickness of the pipeline covering soil; r is the pipe radius; d is the distance between the transmitting antenna and the receiving antenna of the ground penetrating radar system, and if the transmitting antenna and the receiving antenna are coupled and integrated in a box, the distance is a fixed value, for example, d is 10 cm.
When L is 0, namely the ground penetrating radar is positioned right above the pipeline
The propagation velocity v of the electromagnetic wave in the soil medium can be expressed as
In the formula: c is the propagation speed of the electromagnetic wave in vacuum, and c is 30 cm/ns;
is the dielectric constant of each layer of the dielectricm/0WhereinmIs the dielectric permittivity;0is the air dielectric coefficient.
For pipeline detection or pipeline leak detection, H, r sum is an unknown quantity, and needs to be interpreted and identified from the radar return image.
From the above formula, the depth of pipeline can be obtained as
It is noted that the pipe casing medium is generally assumed to be homogeneous and therefore constant in value. When other different media are encountered in radar wave scanning, the propagation speed of the radar wave and the echo image are affected due to the difference of the medium values.
When the pipeline leaks, the leaking water can wet the nearby soil, the dielectric constant of dry sand soil is 3-6, and the dielectric constant of water is 81, so that the buried depth value of the above pipeline changes, the radar reflected wave is abnormal, and the leakage is identified by the depth change of the pipeline represented by the abnormal information.
A radar leakage detection indoor test platform is set up for researching radar echo characteristics and identification algorithms of the water pipeline under different covering layer media. The length, width and height of the inner diameter of the test pool are respectively 3m, 3m and 1m, the test pool is of a brick concrete structure, and the wall thickness is 25 cm. A cast iron pipeline is adopted to simulate a pipeline in a city water supply system, the diameter of the pipeline is 10cm, the pipeline is L-shaped, the length of a part buried in sandy soil is 2.6m, the pipeline is parallel to the upper plane of a test pool, and the distance between the top of the pipeline and the upper plane of the test pool is 0.4 m. The tail end of the water supply pipeline is blocked, and the other end of the water supply pipeline penetrates through the soil blocking plate and then is bent upwards to be connected with the exhaust hole and the water inlet pipe; the leakage hole is arranged in the middle of the buried pipeline, the opening is vertical upwards, and the leakage amount can be adjusted by a screw device. The exhaust hole is vertically upward and is provided with an opening and closing valve; the water inlet pipe is connected with the water inlet soft plastic pipe horizontally and outwards.
After the pipe is buried in the test pool and covered with sandy soil, a wire measuring board with the thickness of 1cm is laid at the top end of the test pool, so that the radar distance measuring wheel can conveniently walk. The size of the line testing plate is 3m multiplied by 3m, ground penetrating radar measuring lines are arranged on the line testing plate, measuring lines are respectively arranged at intervals of 15cm along the vertical direction and the parallel direction of the pipeline, the total number of the measuring lines is 42, the position of the pipeline to be tested is positioned on the X11 measuring line in the middle of the test pool, a leakage point is positioned right above the middle of the pipeline, and the intersection point of the X11 measuring line and the Y9 perpendicular to the pipeline is shown in figure 4.
When a detection test is carried out, a trolley carrying a radar machine is propelled along a measuring line at a constant speed, and after each measuring line is propelled, radar echo image data under the measuring line are obtained and stored on a terminal machine. In the experiment, the sampling points are set to be 1024, namely 1024 sampling points are uniformly set in the depth range of each track number point. The water leakage rate of the test pipeline is stabilized at 1 multiplied by 10-4m3/s。
The radar echo images of different working conditions under a typical survey line obtained by the test are shown in fig. 5 and 6. A large number of repeated tests and researches show that the pipeline in leakage has unique 'echo under hole' characteristics on X-11 and Y-9 radar echo images, and the generated reasons are that the leakage holes continuously seep water to external sandy soil in leakage, the volume of the dry sandy soil is reduced or the dry sandy soil is washed away by the leaked water after being wetted, a water accumulation area exists at the lower part of the pipeline, the original dry sandy soil is replaced by water, and the saturated water generates a strong reflection mechanism mode for electromagnetic waves, so that a round bright spot area appears in the echo. And traversing radar echoes under all measuring lines in each group for verification, wherein the radar echoes under other measuring lines have no characteristic. The final determination of "echo under hole" is the only echo signature that the pipe has when leaking.
1. And (5) verifying the detection test of embedding the radar echo image into the small ball.
In the experiment, 3 round balls are embedded into a radar echo image under a Y-9 measuring line when leakage occurs, the method of the invention of the step 110, the step 120 and the step 130 is used for detecting a circle-like figure in the image, and the detection result is shown in FIG. 7.
The four pictures in fig. 7 are, from left to right, an original ground penetrating radar echo image, a grayed processed image, a result obtained after an edge is extracted by using a Canny edge detection operator, and a result of circle detection based on Hough transform (cv2. houghcirles). As can be seen from the detection results, the small ball and the 'echo under the hole' in the radar echo image under the Y-9 survey line embedded with the small ball are both detected, so that the effectiveness of the circular pattern recognition of the method is verified.
2. Automatic identification of radar wave reflection image under pipeline leakage working condition
And (3) performing leakage detection on radar echo images of the water supply pipeline of the Y measuring line during leakage, wherein 12 groups of tests are counted, each group of tests comprises 20 pipeline echo images from the Y-2 measuring line to the Y-20 measuring line, and the total number of radar echo images is about 240. The typical line Y-9 is selected for the description of the application of the invention.
Verification effect of step 110:
the results of the inventive gray scale processing of the radar echo image under any Y-9 line are shown in fig. 8.
The two pictures in fig. 8 are, from left to right, an original ground penetrating radar echo image and an image obtained by gray processing, as can be seen from fig. 8, the gray image basically includes "echo under hole" and other echo information except the echo under hole, and is not omitted.
Verification effect of step 120:
the image processed in this step is shown in fig. 9, where the images are, from left to right, an unprocessed radar echo image, an image processed in grayscale in step 110, an image processed by applying a smoothing filter in step 120, and an image obtained by performing edge detection on the filtered image. As can be seen from fig. 9, the median filter has a good degree of edge protection for the image, removes many false edges, and has a good noise suppression effect.
The verification effect of step 130.
The results of processing with different edge detection operators are shown in fig. 10. In comparison, the detection result of the Canny edge detection operator is totally satisfactory, the outline of the leakage characteristic is well reserved, the noise suppression effect is also very good, the operator has a self-band filter which can filter the noise, and due to the double-threshold effect, most of false edges can be well screened out, and the leakage characteristic is accurately positioned.
The verification effect of step 140.
The result of the processing through step 140 is shown in fig. 11. As can be seen from fig. 11, the leak hole and its location in this case can be accurately identified by applying the method of the present invention.
The pictures are sequentially from left to right: the method comprises the steps of obtaining an original radar echo picture, a gray level image, an image after median filtering processing and an edge detection result image.
Aiming at other working conditions in the experimental platform, radar echo images under Y-2 to Y-20 measuring lines in each group are processed and identified by applying the method, radar echo images of water supply pipelines under 6 working conditions are randomly extracted for longitudinal identification rate analysis, and the detection results are shown in tables 1 and 2. From the recognition accuracy of the six groups, the accuracy of the algorithm reaches 95% or more, specific recognition can be performed on the echo under the hole, and the detection result is totally satisfactory.
TABLE 1 summary of radar echo image recognition accuracy of 1 st to 3 th groups of water supply pipelines
TABLE 2 radar echo image identification accuracy summary of groups 4-6 of water supply pipelines
The present invention is not limited to the above-mentioned preferred embodiments, and any structural changes made under the teaching of the present invention shall fall within the scope of the present invention, which is similar or similar to the technical solutions of the present invention.
Claims (8)
1. An automatic identification method for detecting pipeline leakage based on ground penetrating radar is characterized by comprising the following steps:
preprocessing radar echo images of the ground penetrating radar under different survey lines to obtain gray level images;
performing median filtering smoothing processing on the gray level image;
identifying the edge of the echo under the hole by using the sudden change of the gray value of the edge region in the image subjected to the median filtering smoothing;
and performing circular fitting on the edge of the echo under the hole by using a circular detection function, and identifying the pipeline leakage working condition according to the number of circles obtained by fitting and the parameter information of the circles.
2. The method according to claim 1, wherein the circle fitting is performed on the "echo under hole" edge by using the existing circle detection function cv2. houghcirles in the Python platform module to obtain the number of circles and the parameter information of the circles.
3. The method of claim 1, wherein the pipeline leakage condition result is obtained according to whether the number of circles exceeds a set early warning threshold.
4. The method according to claim 1, wherein the preprocessing employs a gray value Y value formula as follows: y ═ 0.299 · R +0.587 · G +0.114 · B, where: r, G, B is the color value of any pixel point in the radar echo image for preprocessing.
5. The method according to claim 1, wherein when performing median filtering smoothing processing on the grayscale image, firstly, a Gauss filter is used to suppress false edges and impulse noise in the grayscale image.
6. The method of claim 1, wherein identifying the "echo under hole" edge comprises the steps of:
adopting first order differential in a 2' 2 neighborhood to calculate the intensity gradient D and the direction q of a pixel point in the radar echo image, wherein:
in the formula, x and y are coordinates of pixel points in the radar echo image;
traversing all values on the intensity gradient matrix, and only reserving pixel points with maximum values in the edge direction;
and screening the authenticity of the edge by using a Canny dual threshold, eliminating the false edge and reserving the true edge line.
7. The utility model provides an automatic identification system based on ground penetrating radar detects pipeline leakage which characterized in that includes:
the preprocessing module is used for preprocessing radar echo images of the ground penetrating radar under different measuring lines to obtain gray level images;
the smoothing processing module is used for carrying out median filtering smoothing processing on the gray level image;
the under-hole echo edge identification module is used for identifying an under-hole echo edge by utilizing the mutation of the gray value of the edge region in the image subjected to the median filtering smoothing processing;
and the pipeline leakage working condition identification module is used for performing circular fitting on the edge of the hole echo by using a circular detection function and identifying the pipeline leakage working condition according to the number of circles obtained by fitting and the parameter information of the circles.
8. The system of claim 7, wherein the "echo under hole" edge identification module identifies the "echo under hole" edge by:
adopting first order differential in a 2' 2 neighborhood to calculate the intensity gradient D and the direction q of a pixel point in the radar echo image, wherein:
in the formula, x and y are coordinates of pixel points in the radar echo image;
traversing all values on the intensity gradient matrix, and only reserving pixel points with maximum values in the edge direction;
and screening the authenticity of the edge by using a Canny dual threshold, eliminating the false edge and reserving the true edge line.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010738206.XA CN111853557B (en) | 2020-07-28 | 2020-07-28 | Automatic identification method and system for detecting pipeline leakage based on ground penetrating radar |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010738206.XA CN111853557B (en) | 2020-07-28 | 2020-07-28 | Automatic identification method and system for detecting pipeline leakage based on ground penetrating radar |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111853557A true CN111853557A (en) | 2020-10-30 |
CN111853557B CN111853557B (en) | 2021-06-08 |
Family
ID=72948094
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010738206.XA Active CN111853557B (en) | 2020-07-28 | 2020-07-28 | Automatic identification method and system for detecting pipeline leakage based on ground penetrating radar |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111853557B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111708022A (en) * | 2020-07-15 | 2020-09-25 | 四川长虹电器股份有限公司 | Method and device for calculating scanning area boundary of millimeter wave radar |
EP4253931A1 (en) | 2022-03-30 | 2023-10-04 | Dyrecta Lab S.r.l. | Non-invasive diagnostic system for real time detection of near-surface water leakage in urban and suburban contexts |
CN117092644A (en) * | 2023-10-17 | 2023-11-21 | 中国电建集团江西省电力设计院有限公司 | Underground pipeline detection method |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120262326A1 (en) * | 2009-10-15 | 2012-10-18 | Staffan Abrahamson | Device and method for detection of water flow in ground |
EP2679973A1 (en) * | 2012-06-28 | 2014-01-01 | Commissariat A L'energie Atomique Et Aux Energies Alternatives | Location of a leak in a pipeline |
CN105930854A (en) * | 2016-04-19 | 2016-09-07 | 东华大学 | Manipulator visual system |
CN108387896A (en) * | 2018-01-03 | 2018-08-10 | 厦门大学 | A kind of automatic convergence imaging method based on Ground Penetrating Radar echo data |
CN109410230A (en) * | 2018-09-07 | 2019-03-01 | 南京航空航天大学 | One kind can antimierophonic improvement Canny method for detecting image edge |
CN109886989A (en) * | 2019-02-18 | 2019-06-14 | 哈尔滨工业大学 | A kind of automatic tracing of horizons method of Ground Penetrating Radar based on Canny operator |
CN110230780A (en) * | 2019-06-12 | 2019-09-13 | 浙江大学 | Water supply line soil's rigidity method based on Ground Penetrating Radar 3-D image attributive analysis |
CN110376584A (en) * | 2019-06-28 | 2019-10-25 | 浙江大学 | Water supply line soil's rigidity method based on the identification of ground penetrating radar image characteristic signal |
-
2020
- 2020-07-28 CN CN202010738206.XA patent/CN111853557B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120262326A1 (en) * | 2009-10-15 | 2012-10-18 | Staffan Abrahamson | Device and method for detection of water flow in ground |
EP2679973A1 (en) * | 2012-06-28 | 2014-01-01 | Commissariat A L'energie Atomique Et Aux Energies Alternatives | Location of a leak in a pipeline |
CN105930854A (en) * | 2016-04-19 | 2016-09-07 | 东华大学 | Manipulator visual system |
CN108387896A (en) * | 2018-01-03 | 2018-08-10 | 厦门大学 | A kind of automatic convergence imaging method based on Ground Penetrating Radar echo data |
CN109410230A (en) * | 2018-09-07 | 2019-03-01 | 南京航空航天大学 | One kind can antimierophonic improvement Canny method for detecting image edge |
CN109886989A (en) * | 2019-02-18 | 2019-06-14 | 哈尔滨工业大学 | A kind of automatic tracing of horizons method of Ground Penetrating Radar based on Canny operator |
CN110230780A (en) * | 2019-06-12 | 2019-09-13 | 浙江大学 | Water supply line soil's rigidity method based on Ground Penetrating Radar 3-D image attributive analysis |
CN110376584A (en) * | 2019-06-28 | 2019-10-25 | 浙江大学 | Water supply line soil's rigidity method based on the identification of ground penetrating radar image characteristic signal |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111708022A (en) * | 2020-07-15 | 2020-09-25 | 四川长虹电器股份有限公司 | Method and device for calculating scanning area boundary of millimeter wave radar |
EP4253931A1 (en) | 2022-03-30 | 2023-10-04 | Dyrecta Lab S.r.l. | Non-invasive diagnostic system for real time detection of near-surface water leakage in urban and suburban contexts |
CN117092644A (en) * | 2023-10-17 | 2023-11-21 | 中国电建集团江西省电力设计院有限公司 | Underground pipeline detection method |
CN117092644B (en) * | 2023-10-17 | 2024-01-26 | 中国电建集团江西省电力设计院有限公司 | Underground pipeline detection method |
Also Published As
Publication number | Publication date |
---|---|
CN111853557B (en) | 2021-06-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111853557B (en) | Automatic identification method and system for detecting pipeline leakage based on ground penetrating radar | |
US11900630B2 (en) | Method for detecting leakage of water supply pipe based on ground-penetrating radar three-dimensional image attribute analysis | |
US7234355B2 (en) | Method and system for inspecting flaws using ultrasound scan data | |
CN109343022B (en) | Method for estimating interlayer soil water content | |
WO2016038527A1 (en) | Device and method for fluid leakage detection in pressurized pipes | |
Cheung et al. | Field validation of water‐pipe leakage detection through spatial and time‐lapse analysis of GPR wave velocity | |
CN111007572B (en) | Automatic identification method, device and system for road underground cavity | |
Anastasopoulos et al. | ACOUSTIC EMISSION LEAK DETECTION OF LIQUID FILLED BURIED PIPELINE. | |
Xiang et al. | Integrated approach to simultaneously determine 3D location and size of rebar in GPR data | |
Zhang et al. | Automatic corrosive environment detection of RC bridge decks from ground-penetrating radar data based on deep learning | |
Romanova et al. | Sewer inspection and comparison of acoustic and CCTV methods | |
KR102002480B1 (en) | Systems for maintaining, managing and exploring pipe networks | |
Ristić et al. | Automated data extraction from synthetic and real radargrams of district heating pipelines | |
CN112180452B (en) | Underground pipeline buried depth estimation method based on ground penetrating radar and three-dimensional velocity spectrum | |
CN107656270A (en) | The measurement apparatus and measuring method of a kind of contactless buried pipe track forces cun | |
Gao et al. | Model test study on oil leakage and underground pipelines using ground penetrating radar | |
Zhang et al. | Automatic Rebar Picking for Corrosion Assessment of RC Bridge Decks with Ground-Penetrating Radar Data | |
CN207180585U (en) | A kind of underground piping dimension measuring device | |
CN106897687A (en) | A kind of oil-containing deposit automatic identifying method and system based on sonar technique | |
Song et al. | Underground diseases identification of airport runway using GPR | |
Kourousis et al. | Acoustic emission leak detection of buried oil pipelines, river and road crossings | |
CN208044086U (en) | A kind of saturating ground electromagnetic wave detecting system of underground utilities multi information inverting | |
Cheung et al. | Field validation of water pipe leak by spatial and time-lapsed measurement of GPR wave velocity | |
CN111175836A (en) | Pipeline carrier radar damage detection process | |
Lei et al. | Target detection based on automatic threshold edge detection and template matching algorithm in GPR |
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 |