METHOD FOR LEAKAGE DETECTION OF UNDERGROUND PIPELINE CORRIDOR BASED ON DYNAMIC INFRARED THERMAL IMAGE PROCESSING

• US 20190331301A1
• Filed: 06/29/2019
• Published: 10/31/2019
• Est. Priority Date: 12/30/2016
• Status: Active Grant

• Current Assignee: Yuchuan Du
• Original Assignee: Yuchuan Du
• Inventors: DU, Yuchuan, SUN, Lijun, PAN, Ning, JIANG, Shengchuan, LIU, Chenglong, YAN, Jun, WANG, Qin
• Granted Patent: US 11,221,107 B2
• Time in Patent Office: Days
• CPC Class Codes: E01C 23/01 Devices or auxiliary means for setting-out or checking the configuration of new surfacing, e.g. templates, screed or reference line supports form rails E01C19/50; Applications of apparatus for measuring, indicating, or recording the surface configuration of existing surfacing, e.g. profilographs E01C23/07 takes precedence; measuring roughness or irregularity in general G01B
• CPC Class Codes: F17D 5/02 Preventing, monitoring, or locating loss
• CPC Class Codes: G01M 3/002 by using thermal means
• CPC Class Codes: G01M 3/38 by using light G01M3/02 takes precedence
• CPC Class Codes: G01M 5/0033 by determining damage, crack or wear
• CPC Class Codes: G01M 5/0066 by exciting or detecting vibration or acceleration vibration testing of structures G01M7/00
• CPC Class Codes: G01N 2021/8845 Multiple wavelengths of illumination or detection
• CPC Class Codes: G01N 21/95 characterised by the material or shape of the object to be examined G01N21/89 - G01N21/91, G01N21/94 take precedence
• CPC Class Codes: G01N 25/72 Investigating presence of flaws
• CPC Class Codes: G01N 3/08 by applying steady tensile or compressive forces G01N3/28 takes precedence
• CPC Class Codes: G01N 33/42 Road-making materials G01N33/38 takes precedence

Abstract

A method for leakage detection of underground pipeline corridor based on dynamic infrared thermal image processing. The leakage can be detected by the following steps, including: converting infrared thermal videos into infrared thermal images; obtaining the gray scale information and temperature information of internal environment of the underground pipeline corridor. The gray scale information can realize the conventional target of pipe line state identification inside the pipeline corridor, and the temperature information can be used to detect the pipe leakage.

Claims

1. A method for leakage detection of underground pipeline corridor based on dynamic infrared thermal image processing, comprising:

a) establishing a crack development degree detection model, comprising;

a1) collecting infrared thermal images of at least ten crack samples on pipe surface of the underground pipeline corridor;

recording a sample ambient temperature and a crack development degree; and

estimating and ranking the crack development degree into three developmental levels;

1, 2, and 3;

a2) processing the infrared thermal images, obtaining the reference temperature difference data between the crack samples and the pipe surface; and

a3) based on the reference temperature difference data, the ambient temperature and the crack development degree, obtaining two classification functions with SVM classification;

Δ

T₁₂=a₁₂T+b₁₂ and Δ

T₂₃=a₂₃T+b₂₃, wherein T is the ambient temperature, and Δ

T is the reference temperature difference data;

b) data collecting;

collecting infrared thermal videos of the fracture zone of underground pipeline corridor, and recording the ambient temperature;

c) data pre-processing;

converting the infrared thermal videos into the infrared thermal images, along with image denoising and grayscale conversion of the collected infrared thermal images;

d) data processing;

processing denoised and grayscale infrared thermal images, including edge detection and image enhancement, edge extraction, impurity removal, and calculating measured temperature difference data;

e) temperature difference data processing;

comprising distortion degree judgment, first correction of the measured temperature difference data, and second correction of the measured temperature difference data; and

f) leakage analysis;

comprising calculating the reference temperature difference data, and determining leakage severity, and determining type of leakage.

2. The method of claim 1, wherein step b) comprises:

b1) collecting with mobile patrol equipment;

using an infrared imaging device-uncooled focal plane infrared detector, which is placed on the mobile patrol equipment, to inspect the fracture zone regularly, a height of the equipment from the surface of the pipe is 0.5-1 m;

collecting the infrared videos of fracture zone of underground pipeline corridor; and

b2) recording the ambient temperature;

using a thermometer in the fracture zone of the underground pipeline corridor and recording the ambient temperature.

3. The method of claim 1, wherein step c) comprises:

c1) videos conversion to images;

converting the infrared thermal videos into the infrared thermal images by frame-by-frame extraction;

c2) image denoising;

denoising of the infrared thermal images, and reducing noise interference generated in transmission or in digital processing; and

c3) grayscale conversion;

converting the originally collected color image into a grayscale image, by removing the color information in the image.

4. The method of claim 3, wherein the image denoising in step c2) is performed by one or more of mean filter, adaptive Wiener filter, median filter, morphological noise filter, and wavelet denoising.

5. The method of claim 1, wherein step d) comprises:

d1) edge detection and image enhancement;

using search and zero-crossing to identify significant changes in image properties, and to extract temperature difference points;

d2) edge extraction;

locating crack area and non-crack area, using single threshold segmentation method or multi-threshold segmentation method;

d3) impurity removal;

removing impurities and non-crack area, obtaining effective pipeline region and the effective crack region; and

d4) calculating the measured temperature difference data;

processing the infrared thermal images of the effective pipe surface region and the effective crack region, and obtaining the measured temperature difference data Δ

T.

6. The method of claim 5, wherein an edge detection template used in step d1) is at least one of Laplacian operator, Roberts operator, Sobel operator, log (Laplacian-Gauss) operator, Kirsch operator and Prewitt operator.

7. The method of claim 5, wherein step d4) comprises:

d41) matching the effective pipeline region with legend, and obtaining measured tenperature t₀;

d42) dividing the crack region into p segments, p≥

2;

a length of each segment is l₁, l₂, . . . l_p;

matching each segment with the legend, and obtaining measured temperature T₁, T₂, . . . T_p, respectively;

d43) obtaining measured temperature differences Δ

T₁, Δ

T₂, . . . Δ

T_p; and

d44) calculating measured temperature difference data Δ

T;

Δ

T=(T₁l₁+T₂l₂+ . . . +T_pl_p)/(l₁+l₂+ . . . +l_p).

8. The method of claim 1, wherein step e) comprises:

e1) distortion degree judgment;

comparing measured temperature difference data with the historical period data according to three characteristics of irreversibility, continuity and trend;

e2) first correction of the measured temperature difference data;

selecting and correcting the measured temperature difference data with distortion according to the historical measured temperature difference data and the three characteristics of leakage, to obtain a corrected measured temperature difference data; and

e3) second correction of the measured temperature difference data;

selecting and correcting the measured temperature difference data after the first correction, according to the temperature difference data collected by the optical fiber temperature measurement;

replacing the original temperature difference data by the fiber temperature measurement data if the fiber temperature measurement data is available to obtain the measured temperature difference data after the second correction.

9. The method of claim 1, wherein step f) comprises:

f1) calculating the reference temperature difference data;

calculating the reference temperature difference data based on the crack development degree detection model;

the reference temperature difference data and the second corrected measured temperature difference data are brought into the step a) of detection model to estimate the degree of crack development;

f2) determining leakage severity;

defining the severity of the leakage from the three dimensions of length, width and area, and obtaining G=[0-9.9], wherein G is the leakage severity index, and the result retains 1 decimal place; and

f3) determining type of leakage;

discriminating the characteristics of the fracture zone based on the method of regional feature analysis, considering the roundness and density parameters, and judging the leakage type of the leakage point of the pipeline crack zone.

10. The method of claim 9, wherein the method of determining the type of leakage comprises:

f31) if a perimeter/area of a leaking area is >

0.5, the leak is considered to be a crack;

f32) if the perimeter/area of a leaking area is not >

0.5, and if S₁/S₂>

3.18, the leak is considered to be loose-like leakage of the interface;

f33) if the perimeter/area of a leaking area is not >

0.5, and if 1<

S₁/S₂<

3.18, the leak is considered to be other types of leakage;

wherein in the step f32) and f33), S₁ is the area of the circumscribed rectangle of the leaking region, and S;

is the area of the region.