CN106778515B - Automatic identification method for axial magnetic flux leakage array signal of flange - Google Patents
Automatic identification method for axial magnetic flux leakage array signal of flange Download PDFInfo
- Publication number
- CN106778515B CN106778515B CN201611051670.1A CN201611051670A CN106778515B CN 106778515 B CN106778515 B CN 106778515B CN 201611051670 A CN201611051670 A CN 201611051670A CN 106778515 B CN106778515 B CN 106778515B
- Authority
- CN
- China
- Prior art keywords
- flange
- signal
- data
- axial
- magnetic flux
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Measuring Magnetic Variables (AREA)
- Image Processing (AREA)
Abstract
The invention relates to an automatic identification method for axial flange magnetic flux leakage array signals. The method is suitable for the field of magnetic flux leakage internal detection data processing, solves the problems of automatic detection, identification and positioning of axial magnetic flux leakage signals of the flange, and specifically comprises the following steps: firstly, edge enhancement processing is carried out on original data detected in magnetic flux leakage, self-adaptive threshold segmentation is carried out on the preprocessed data to obtain a flange signal coarse detection result, then, vertical projection operation is carried out on the data to obtain flange signal characteristics, and then the flange signal can be identified and positioned. The invention has low computational complexity and high recognition rate, and can meet the requirements of engineering application on the real-time performance and accuracy of big data processing.
Description
Technical Field
The invention belongs to the field of magnetic flux leakage internal detection data processing, and particularly relates to an automatic identification method for an axial magnetic flux leakage array signal of a flange, which is used for solving the problems of automatic detection, identification and positioning of the axial magnetic flux leakage signal of the flange.
Background
The flange magnetic array signal automatic identification and positioning has important engineering practice significance. The flange is used as a structural part for connecting oil and gas pipelines, and has larger hidden danger of corrosion and fracture compared with the pipelines, so that the detection and evaluation of the flange welding line are important measures for ensuring the safe operation of the whole oil and gas passage. The defect position information is recorded by the mileage wheel for the detector in the magnetic leakage, support is provided for pipeline excavation, accumulated errors are generated due to the fact that the mileage wheel slips due to pollutants on the wall of the pipeline, and the flange determined by the position information can be used as a natural positioner and used for automatically calibrating the mileage information, so that accurate defect positioning is achieved. The positions and the number of the flanges are in one-to-one correspondence with the pipelines, a certain pipeline can be automatically positioned by detecting, identifying and positioning a certain welding line and the flanges, and finally, automatic segmentation of mass magnetic flux leakage data can be realized, so that follow-up data query and analysis are facilitated.
The problem that flange magnetic leakage signals are difficult to automatically detect, identify and position from axial magnetic leakage array signals exists in the prior art.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: and automatically detecting, identifying and positioning the flange magnetic leakage signal from the axial magnetic leakage array signal.
According to the invention, the magnetic flux leakage array signal is regarded as a two-dimensional image, on the basis of analyzing the characteristics of the contrast signal, the magnetic flux leakage array signal is preprocessed by a contrast enhancement method, and the flange target is detected, identified and positioned by a threshold segmentation and vertical projection enhancement method, so that a better effect is obtained.
The technical scheme adopted by the invention is as follows:
a flange axial magnetic flux leakage array signal automatic identification method comprises the following steps:
1. carrying out axial edge enhancement pretreatment on the original axial magnetic flux leakage array signal;
2. normalizing the preprocessed data into 0-255 shaping data;
3. calculating a global optimal segmentation point in the shaping data so as to realize threshold segmentation and obtain binary data;
4. performing vertical projection superposition and parameter judgment on the binary data to obtain flange signal characteristics;
5. and carrying out cluster analysis on the flange signal characteristics so as to identify and position the axial coordinate of the flange.
Further, the step 1 of performing axial edge enhancement preprocessing on the original axial magnetic flux leakage array signal specifically includes:
1.1, selecting a convolution kernel T.
And 1.2, setting the leakage magnetic array signal as f (x, y), calculating the convolution of the f (x, y) and T, and obtaining edge enhancement data q (x, y):
q(x,y)=f(x,y)*T(x,y) (2)。
further, the step 2 of normalizing the preprocessed data into 0-255 shaping data specifically includes:
calculating the maximum value Mx and the minimum value Mi of the data q (x, y) after the edge enhancement processing, and completing data normalization by the following formula:
Further, the step 3 of calculating a global optimal segmentation point in the shaping data to realize threshold segmentation, and obtaining the binarized data specifically includes:
3.1, regarding the normalized data as a two-dimensional image, the number of image pixel points is N, the image gray level is L, NiNumber of pixel points, p, of gray level iiThe probability of the occurrence of the pixel point with the gray level i is
pi=ni/N i=0,1,2…255 (4)
3.2, divide the image pixel into two categories, namely C0Class and C1Class;
calculating C0The mean and weight of the class are
Wherein k is a pixel grayscale boundary value;
C1the mean and weight of the class are
Wherein, L is the image gray level;
Then the between-class variance is
3.3 let k be [0, 255]Traverse the value in the range whenThe maximum corresponding k value is the global optimal segmentation point of the image;
and 3.4, traversing the two-dimensional magnetic flux leakage array image, setting the point with the numerical value larger than the global optimal segmentation point as 1, and otherwise, setting the point as 0, thereby obtaining binary data b (x, y).
Further, step 4, performing vertical projection superposition and parameter judgment on the binary data, and obtaining flange signal characteristics specifically includes:
4.1, performing vertical projection enhancement on the binary data b (x, y):
wherein, s (y) is a one-dimensional signal after vertical projection enhancement, wherein M is the number of axial signal points;
4.2, calculating signal characteristics:
traversing all sampling points of the one-dimensional signal s (y) after the vertical projection enhancement, judging whether the point is the flange signal characteristic or not according to the flange judgment threshold T,
where t (i) is a signal feature, and when t (i) is 1, it means that t (i) is a flange signal feature, and when t (i) is 0, it means that t (i) is not a flange signal feature.
Further, the step 5 of performing cluster analysis on the flange signal characteristics so as to identify and locate the axial coordinates of the flange specifically includes:
5.1, traversing signal characteristics t (i), and if the axial distance of any two non-zero characteristic points is smaller than an axial distance threshold value D, considering the two points to be from the same flange;
5.2, traversing and searching the left and right boundary point coordinates of the flange signal, wherein the left and right boundary point coordinates of the flange signal are d respectivelylAnd drFinally identifying and positioning the axial coordinate d of the flangef
df=(dl+dr)/2 (10)。
Has the advantages that:
(1) the invention has low computational complexity and high recognition rate, and can meet the requirements of engineering application on the real-time performance and accuracy of big data processing.
(2) The positioning information obtained by the invention can be used for equipment mileage correction.
Drawings
FIG. 1 is a flow chart of the method of the present invention
FIG. 2 is a schematic diagram of axial flux leakage array signals
FIG. 3 is a schematic diagram of a flange signal identification and positioning result after vertical projection
Detailed Description
The technical solution of the present invention will be further explained and explained in detail with reference to the drawings and the detailed description.
A flange axial magnetic flux leakage array signal automatic identification method comprises the following steps:
(1) the method comprises the following specific implementation steps of carrying out axial edge enhancement pretreatment on an original axial magnetic flux leakage array signal so as to improve the contrast of a target signal:
selecting convolution kernel T.
Secondly, setting the magnetic leakage array signal as f (x, y), calculating the convolution of the f (x, y) and T, and obtaining edge enhancement data q (x, y):
q(x,y)=f(x,y)*T(x,y) (2)
(2) normalizing the preprocessed data into 0-255 shaping data, and specifically realizing the steps as follows:
and calculating the maximum Mx and the minimum Mi of q (x, y), and completing the data normalization operation according to the following formula.
(3) Calculating a global optimal segmentation point of the data, realizing threshold segmentation and obtaining binary data, wherein the specific realization steps are as follows:
3.1 regarding the normalized data as a two-dimensional image, the number of image pixels is N, and the gray scale range is [0, 255 ]],niNumber of points with gray level i, piIs the probability of the occurrence of the gray level i, then
pi=ni/N i=0,1,2…255 (4)
3.2 calculation of C0The mean and weight of the class are
C1The mean and weight of the class are
3.3 let k be [0, 255 ]]Value of ergodicity in the range whenThe maximum k value is the selected threshold.
And 3.4, traversing the two-dimensional magnetic flux leakage array image, setting the point with the value larger than k as 1, and otherwise, setting the point as 0 to obtain binary data b (x, y).
(4) And (3) performing vertical projection superposition and parameter judgment on the binary data to obtain a method signal characteristic, wherein the method signal characteristic is specifically realized by the following steps:
b (x, y) is subjected to vertical projection enhancement:
and s (y) is the one-dimensional signal after the vertical projection enhancement, wherein M is the number of the axial signal points.
Calculating signal characteristics:
traversing s (y) all sampling points, judging whether the sampling points are flange signal characteristics or not according to the threshold value T,
(5) the method comprises the following steps of performing cluster analysis on flange signal characteristics, and identifying and positioning axial coordinates of a flange, wherein the specific steps are as follows:
firstly, traversing the signal characteristics t (i), and if the axial distance between any two non-zero characteristic points is smaller than a threshold value D, the two points are considered to be from the same flange.
Searching the coordinates of the left and right boundary points of the flange signal by traversal and respectively dlAnd drFinally, the positioning coordinate point is identified as df
df=(dl+dr)/2 (10)。
Compared with the prior art, the method adopts a scheme of combining threshold segmentation and projection enhancement, converts the multi-dimensional signal detection and identification problem into the one-dimensional signal detection and identification problem, and reduces the complexity of the method.
The above-mentioned embodiments are only used for explaining and explaining the technical solution of the present invention, but should not be construed as limiting the scope of the claims. It should be clear to those skilled in the art that any simple modification or replacement based on the technical solution of the present invention will also result in new technical solutions that fall within the scope of the present invention.
Claims (3)
1. The method for automatically identifying the axial magnetic flux leakage array signal of the flange is characterized by comprising the following steps of:
step 1, carrying out axial edge enhancement pretreatment on an original axial magnetic flux leakage array signal; the method specifically comprises the following steps:
1.1 selecting a convolution kernel T
And 1.2, setting the leakage magnetic array signal as f (x, y), calculating the convolution of the f (x, y) and T, and obtaining edge enhancement data q (x, y):
q(x,y)=f(x,y)*T(x,y) (2)
step 2, normalizing the preprocessed data into 0-255 shaping data; the method specifically comprises the following steps:
calculating the maximum value Mx and the minimum value Mi of the data q (x, y) after the edge enhancement processing, and completing data normalization by the following formula:
step 3, calculating a global optimal segmentation point in the shaping data so as to realize threshold segmentation and obtain binary data;
step 4, performing vertical projection superposition and parameter judgment on the binary data to obtain flange signal characteristics; the method specifically comprises the following steps:
4.1, performing vertical projection enhancement on the binary data b (x, y):
wherein, s (y) is a one-dimensional signal after vertical projection enhancement, wherein M is the number of axial signal points;
4.2, calculating signal characteristics:
traversing all sampling points of the one-dimensional signal s (y) after the vertical projection enhancement, judging whether the point is the flange signal characteristic or not according to the flange judgment threshold T,
wherein, t (i) is a signal feature, and when t (i) is 1, it means that t (i) is a flange signal feature, and when t (i) is 0, it means that t (i) is not a flange signal feature;
and 5, carrying out cluster analysis on the flange signal characteristics so as to identify and position the axial coordinate of the flange.
2. The method as claimed in claim 1, wherein the step 3 of calculating a global optimal segmentation point in the shaping data to implement threshold segmentation, and obtaining the binarized data specifically includes:
3.1, regarding the normalized data as a two-dimensional image, the number of image pixel points is N, the image gray level is L, NiNumber of pixel points, p, of gray level iiThe probability of the occurrence of the pixel point with the gray level i is
pi=ni/N i=0,1,2…255 (4)
3.2, divide the image pixel points intoAre of two types, i.e. C0Class and C1Class;
calculating C0The mean and weight of the class are
Wherein k is a pixel grayscale boundary value;
C1the mean and weight of the class are
Wherein, L is the image gray level;
Then the between-class variance is
3.3 let k be [0, 255]Traverse the value in the range whenThe maximum corresponding k value is the global optimal segmentation point of the image;
and 3.4, traversing the two-dimensional magnetic flux leakage array image, setting the point with the numerical value larger than the global optimal segmentation point as 1, and otherwise, setting the point as 0, thereby obtaining binary data b (x, y).
3. The method according to any one of claims 1-2, wherein the step 5 of performing cluster analysis on the flange signal features to identify and locate flange axial coordinates specifically comprises:
5.1, traversing signal characteristics t (i), and if the axial distance of any two non-zero characteristic points is smaller than an axial distance threshold value D, considering the two points to be from the same flange;
5.2, traversing and searching the left and right boundary point coordinates of the flange signal, wherein the left and right boundary point coordinates of the flange signal are d respectivelylAnd drFinally identifying and positioning the axial coordinate d of the flangef
df=(dl+dr)/2 (10)。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611051670.1A CN106778515B (en) | 2016-11-24 | 2016-11-24 | Automatic identification method for axial magnetic flux leakage array signal of flange |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611051670.1A CN106778515B (en) | 2016-11-24 | 2016-11-24 | Automatic identification method for axial magnetic flux leakage array signal of flange |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106778515A CN106778515A (en) | 2017-05-31 |
CN106778515B true CN106778515B (en) | 2020-12-04 |
Family
ID=58912846
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611051670.1A Active CN106778515B (en) | 2016-11-24 | 2016-11-24 | Automatic identification method for axial magnetic flux leakage array signal of flange |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106778515B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107884471B (en) * | 2017-09-28 | 2021-04-20 | 北京华航无线电测量研究所 | Axial magnetic flux leakage signal defect detection method based on image processing |
DE102019219743A1 (en) * | 2019-12-16 | 2021-06-17 | PLR Prüftechnik Linke & Rühe GmbH | Method for characterizing a weld seam |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0018325A1 (en) * | 1979-04-19 | 1980-10-29 | Alfred Rossier | Closable container made of semi-rigid material, manufacturing process and means for using it |
US10546372B2 (en) * | 2007-12-21 | 2020-01-28 | Kinder Morgan, Inc. | Method, machine, and computer medium having computer program to detect and evaluate structural anomalies in circumferentially welded pipelines |
CN103235034A (en) * | 2013-03-29 | 2013-08-07 | 中国石油集团西部管道有限责任公司 | Natural gas long-distance pipeline three-dimensional high-definition magnetic leakage internal detection apparatus |
-
2016
- 2016-11-24 CN CN201611051670.1A patent/CN106778515B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN106778515A (en) | 2017-05-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110930357B (en) | In-service steel wire rope surface defect detection method and system based on deep learning | |
CN110906875B (en) | Visual processing method for aperture measurement | |
CN115115638B (en) | Oil leakage detection and judgment method for hydraulic system | |
CN110146589B (en) | High-definition visualization method for pipeline magnetic flux leakage data | |
CN111667470B (en) | Industrial pipeline flaw detection inner wall detection method based on digital image | |
CN109508709B (en) | Single pointer instrument reading method based on machine vision | |
CN115841449B (en) | Monocular distance measurement method for longitudinal positioning of structural defect of drainage pipeline and storage medium | |
CN105930852A (en) | Method for identifying bubble image | |
CN109359604B (en) | Method for identifying instrument under shadow interference facing inspection robot | |
CN106778515B (en) | Automatic identification method for axial magnetic flux leakage array signal of flange | |
CN105184792B (en) | A kind of saw blade wear extent On-line Measuring Method | |
CN104574417A (en) | Image edge grey level fluctuation measurement and adaptive detection method | |
CN110533650B (en) | AUV underwater pipeline detection tracking method based on vision | |
CN103196356A (en) | Oil tube defect quantitative recognition method based on support vector machine | |
CN113012181B (en) | Novel quasi-circular detection method based on Hough transformation | |
CN117036358B (en) | Method and system for detecting tool wear of numerical control machine tool | |
WO2021103875A1 (en) | Laser sensor-based plane detection method and device | |
CN117475154A (en) | Instrument image recognition method and system based on optimized Canny edge detection | |
CN116152674A (en) | Dam unmanned aerial vehicle image crack intelligent recognition method based on improved U-Net model | |
TW201601119A (en) | Method for recognizing and locating object | |
CN112560839A (en) | Automatic identification method and system for reading of pointer instrument | |
CN111192358A (en) | Pipeline crack detection method, device, equipment and storage medium based on three dimensions | |
CN115311287A (en) | Method for detecting production abnormity of common rail oil injector | |
CN112734745B (en) | Unmanned aerial vehicle thermal infrared image heating pipeline leakage detection method fusing GIS data | |
CN113487589A (en) | Sub-pixel circle center detection method and system |
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 |