CN115015375A - Method for identifying middle ring welding seam in pipeline detection - Google Patents
Method for identifying middle ring welding seam in pipeline detection Download PDFInfo
- Publication number
- CN115015375A CN115015375A CN202210379499.6A CN202210379499A CN115015375A CN 115015375 A CN115015375 A CN 115015375A CN 202210379499 A CN202210379499 A CN 202210379499A CN 115015375 A CN115015375 A CN 115015375A
- Authority
- CN
- China
- Prior art keywords
- data
- pipeline
- mileage
- magnetic flux
- weld
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003466 welding Methods 0.000 title claims abstract description 74
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000001514 detection method Methods 0.000 title claims abstract description 18
- 230000004907 flux Effects 0.000 claims abstract description 45
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000001914 filtration Methods 0.000 claims abstract description 10
- 238000005070 sampling Methods 0.000 claims abstract description 9
- 230000000877 morphologic effect Effects 0.000 claims abstract description 7
- 230000007797 corrosion Effects 0.000 claims description 7
- 238000005260 corrosion Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 4
- 238000012552 review Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000005728 strengthening Methods 0.000 abstract description 2
- 230000007547 defect Effects 0.000 description 5
- 238000012549 training Methods 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 239000011324 bead Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
- G01N27/72—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables
- G01N27/82—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws
- G01N27/83—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws by investigating stray magnetic fields
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- 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
- G06T7/0008—Industrial image inspection checking presence/absence
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Electrochemistry (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Investigating Or Analyzing Materials By The Use Of Magnetic Means (AREA)
Abstract
A method for identifying a ring weld in pipeline detection is characterized in that a plurality of magnetic flux leakage sensors are uniformly distributed in a pipeline, mileage sensors are arranged in the circumferential direction of the pipeline, and multichannel original magnetic flux leakage data and mileage wheel data are synchronously acquired in an equal-time-interval sampling mode; then, obtaining a pipeline magnetic flux leakage distribution binary image by utilizing median filtering processing, and strengthening the morphological characteristics of the welding line data by adopting asymmetric closed operation; the method adopts a two-dimensional data analysis mode to carry out image-like processing on the data, enhances the data, highlights morphological characteristics of uneven parts in the data of the magnetic flux leakage sensor, catches out the girth weld from the uneven parts, can judge the girth weld in a two-dimensional space, ensures accuracy, has low requirement on the calibration of the sensor, has low requirement on the computing power of a computer, adopts a circumferential period extension mode in the judgment, and improves the reliability of girth weld identification.
Description
Technical Field
The invention relates to a method for identifying a girth weld, in particular to a method for identifying a girth weld in pipeline detection, and belongs to the technical field of pipeline girth weld detection.
Background
Pipeline transportation is a very important transportation method, and is mainly used for transportation of energy, chemical industry and water resources, and maintenance and monitoring of pipelines need to be performed by using special pipeline detection equipment. After a section of pipeline is detected by using pipeline detection equipment, the collected data needs to be analyzed, whether the pipeline has defects or not is mainly judged through analysis, the defects are positioned, and then the pipeline is repaired in a construction mode. Because the pipeline is usually long, the positioning accuracy is very important, and because the pipeline construction needs excavation, the construction efficiency is greatly influenced by inaccurate positioning.
The pipeline sensor is adopted to detect the pipeline, the sensors are uniformly distributed in the circumferential direction of the detector in the pipeline, all the sensors are synchronously sampled, high-frequency sampling at equal time intervals is adopted to collect data, the obtained data can be reduced into data distributed according to distance with the help of mile wheel data, and the whole data is equivalent to the data of two-dimensional distribution of the cylindrical pipeline wall which is cut into the length of the pipeline and the width of the pipeline, so that the defect distribution condition of the pipeline is represented. This method is to separately determine the waveforms of the individual leakage magnetic sensors. When the magnetic leakage sensor fluctuates, the welding seam possibly exists at the position, then the waveforms of other sensors are judged, when the total number of the sensors which fluctuate nearby the position (usually a distance is set, the magnitude of 10 mm) reaches a set value, whether the number of the sensors which fluctuate at the moment reaches the set value is judged, and the welding seam is judged if the number of the sensors which fluctuate at the moment reaches the set value.
Another way is to use a convolutional neural network training model to make the decision. And splitting the data in the circumferential direction, namely obtaining the distribution condition of the two-dimensional magnetic signals of the axial direction of a transverse axis and the axial direction of a longitudinal axis and the whole split pipeline, and then training a convolution neural network which can be used for identifying the pipeline girth weld by marking the girth weld. The method has the defects that 1) because a machine learning mode is adopted, a large number of samples are needed to ensure that the overfitting condition can not occur, and because the training model needs great computing power, a computer for special computation is needed to complete the process; 2) the stability of the detector is high, and when the detector of a new model (caliber) is replaced, or when the probe sensor is replaced by the detector with the caliber and the sensor is not calibrated, the judgment precision of the model can be influenced. Therefore, the method generally comprises the steps of obtaining a new detector, collecting data of a certain distance by the detector entering a pipeline, manually marking the data, importing the data into a model for training, and then matching the detector to realize the identification of the girth weld, so that the early-stage workload is large, and the method is time-consuming and labor-consuming.
Disclosure of Invention
The invention aims to provide a method for identifying a girth weld in pipeline detection, which can judge the girth weld in a two-dimensional space, ensures the accuracy, has low requirements on the calibration of a sensor and the computing capability of a computer, and improves the reliability of girth weld identification by adopting a circumferential period extension mode in the judgment.
In order to achieve the above object, the present invention provides a method for identifying a ring weld in pipeline inspection, comprising the steps of:
step 1: uniformly arranging a plurality of magnetic flux leakage sensors in the pipeline, arranging mileage sensors in the circumferential direction of the pipeline, and synchronously acquiring multichannel original magnetic flux leakage data and mileage wheel data by adopting an equal-time-interval sampling mode;
step 2: firstly, converting the odometer wheel data into an actual odometer value, and then acquiring magnetic flux leakage data of an odometer coordinate in a time alignment mode; comparing the mileage wheel data in a set time range, respectively calculating the pulse number of each mileage wheel data, selecting the mileage wheel corresponding to the maximum pulse number, and calculating the difference of the mileage wheel to obtain the mileage pulse distribution of the mileage wheel; calculating the actual mileage value of the mileage wheel according to the mileage pulse distribution; carrying out data reconstruction by corresponding the magnetic flux leakage data and the actual mileage value at the same time one by one;
and step 3: and (3) processing the data in the step (2) by using a median filtering method, and separating magnetic flux leakage data representing different pipe sections, wherein the method specifically comprises the following steps:
step 31: when an internal detector magnetic leakage sensor is tested before leaving a factory, under a natural condition, the value of the magnetic leakage sensor of the specification fluctuates around a central value N, and the fluctuation range is [ -M/2, M/2 ];
step 32: performing median filtering on the magnetic leakage data processed in the step 2 according to the channels to obtain a median of the magnetic leakage data of each channel;
step 33: drawing an intermediate value curve, wherein the intermediate value curve comprises welding line data and pipeline flat part data, and the ratio of the line width of the welding line data to the line width of the pipeline flat part is 1: 20;
and 4, step 4: and (3) making a difference between the magnetic flux leakage data in the step (2) and the intermediate value data in the step (3), and obtaining a pipeline magnetic flux leakage distribution binary diagram through a threshold value, wherein the method specifically comprises the following steps:
step 41: determining a threshold value as M according to the fluctuation range of the magnetic flux leakage data obtained in the step 31;
step 42: subtracting the magnetic flux leakage data obtained in the step (2) from the intermediate value data obtained in the step (3), then obtaining a binary image through threshold value binarization processing, assigning a part exceeding a threshold value to be one color to represent welding seam data, and assigning another color to be the part not exceeding the threshold value to represent the smooth pipeline;
and 5: processing the binary image by adopting asymmetric closed operation to strengthen the morphological characteristics of the welding line data in the detection data; connecting a plurality of connected domains by adopting asymmetric closed operation and setting the expansion scale to be larger than the corrosion scale; according to the average width W of the welding seam of the pipeline to be detected and the minimum mileage resolution s of the detector, the side length value L of the square expansion core can be set to be W/s, an odd number is upwards taken, and the side length of the square corrosion core is L-2;
step 6: extracting straight line segments in the binary image by using Hough transform, judging whether the straight line segments are girth welds or not, and registering weld information into a weld list if the straight line segments are girth welds;
step 61: finding straight line segments with the length being 2/3 of the circumference of the pipeline, and uniformly extracting the straight line segments as girth welds;
step 62: because the girth welding seam is perpendicular to the pipeline extending direction, according to the inclination angle that exists in the detector operation process, the straightway that satisfies the following formula is also extracted together:
|(x2-x1)/(y2-y1)|＜tan(5°)
wherein, (x1, y1), (x2, y2) are coordinates of two end points of a straight line segment;
and 63, removing a plurality of straight line segments in the same welding line obtained in the steps 61 and 62, and only leaving one straight line segment to represent the girth welding line:
firstly, expressing a straight line segment by using a mileage coordinate of a midpoint of the straight line segment, and marking the straight line segment as X, wherein X is (X1+ X2)/2, data corresponding to a serial number is Xn, and is expressed by a set { Xn }, and n is the number of the straight line segments;
then sorting the data in the set { Xn }, selecting the first data X1, and removing all X data with the distance to X1 less than d, wherein the calculation formula of d is as follows:
d＝w/2s
in the formula: w is the shortest distance between two girth welds in the pipeline construction standard;
for the first data X1, { Xn } subset { Xm1| | | Xm1-X1| < d }, then all xms belong to the same weld with X1, and are removed, leaving only the first data X1 to represent this weld; { Xn } after { Xm1| | Xm1-X1| < d } is removed, continuing to circulate the process until all elements in the set { Xn } are traversed, and finally obtaining a set containing a mileage value list, wherein each mileage value corresponds to one girth joint;
and 7, judging the welding seam list information, judging whether the welding seam is missed to be detected or not, and rechecking and recording the missed position.
The process of rechecking and recording the missed detection position in the step 7 is as follows:
the length of the single pipeline is limited, the distribution condition of the whole girth weld is scanned after a weld list is generated, when the length of the single pipeline is larger than the longest length of the single pipeline and the girth weld is not found, the data in the interval are extracted again, and the step 4-6 is executed repeatedly; and simultaneously reducing the threshold value set in the step 4, supplementing the welding seam into the list if the welding seam is found, adding the midpoint coordinate of the pipeline into the list as welding seam data if the welding seam is not found, and marking the suspected undetected welding seam at the midpoint coordinate for the manual review of data staff.
Compared with the prior art, the magnetic leakage sensor and the mileage wheel synchronous acquisition method have the advantages that the magnetic leakage sensors are uniformly distributed in the pipeline, the mileage sensors are arranged in the circumferential direction of the pipeline, and multichannel original magnetic leakage data and mileage wheel data are synchronously acquired in an equal time interval sampling mode; then, obtaining a pipeline magnetic flux leakage distribution binary image by using median filtering processing, and strengthening the morphological characteristics of the welding line data by adopting asymmetric closed operation; the method adopts a two-dimensional data analysis mode to carry out image-like processing on the data, enhances the data, highlights morphological characteristics of uneven parts in the data of the magnetic leakage sensor, and catches out the girth weld from the data. The method can judge in a two-dimensional space, ensures the accuracy, has low requirement on the calibration of the sensor due to the adoption of a method for early-stage reinforcement such as a self-adaptive threshold value, has low dimensionality in the final judging method, judges from the integral form of an uneven connected domain, has low requirement on the computing power of a computer, adopts a circumferential period extension mode in the judgment, and improves the reliability.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic diagram illustrating magnetic flux leakage data fluctuation near a weld at a certain position in an embodiment of the present invention;
FIG. 3 is a gray scale graph after adaptive thresholding in an embodiment of the invention;
FIG. 4 is a schematic diagram of a circumferential weld extracted by using Hough transform in the embodiment of the present invention;
FIG. 5 shows the magnetic flux leakage data fluctuation situation near a weld at a certain position in the embodiment of the present invention, in which a short pipe exists, and the positions of two circumferential welds are very close;
FIG. 6 is a schematic representation of a weld signal converted to a grayscale map by adaptive thresholding in an embodiment of the present invention;
fig. 7 is a schematic diagram of two welds extracted by signal enhancement in the embodiment of the present invention.
Detailed Description
The invention will be further explained with reference to the drawings.
As shown in fig. 1, a method for identifying a ring weld in pipeline inspection includes the following steps:
step 1: uniformly arranging a plurality of magnetic flux leakage sensors in the pipeline, arranging mileage sensors in the circumferential direction of the pipeline, and synchronously acquiring multichannel original magnetic flux leakage data and mileage wheel data by adopting an equal-time-interval sampling mode;
step 2: firstly, converting mileage wheel data into an actual mileage value, and then acquiring magnetic flux leakage data of a mileage coordinate in a time alignment mode; comparing the mileage wheel data in a set time range, respectively calculating the pulse number of each mileage wheel data, selecting the mileage wheel corresponding to the maximum pulse number, and calculating the difference of the mileage wheel to obtain the mileage pulse distribution of the mileage wheel; calculating the actual mileage value of the mileage wheel according to the mileage pulse distribution; carrying out data reconstruction by corresponding the magnetic flux leakage data and the actual mileage value at the same time one by one;
and step 3: and (3) processing the data in the step (2) by using a median filtering method, and separating magnetic flux leakage data representing different pipe sections, wherein the method specifically comprises the following steps:
step 31: when an internal detector magnetic leakage sensor is tested before leaving a factory, under a natural condition, the value of the magnetic leakage sensor of the specification fluctuates around a central value N, and the fluctuation range is [ -M/2, M/2 ];
step 32: performing median filtering on the magnetic leakage data processed in the step 2 according to the channels to obtain a median of the magnetic leakage data of each channel;
step 33: drawing an intermediate value curve, wherein the intermediate value curve comprises welding line data and pipeline flat part data, and the ratio of the line width of the welding line data to the line width of the pipeline flat part is 1: 20;
and 4, step 4: and (3) making a difference between the magnetic flux leakage data in the step (2) and the intermediate value data in the step (3), and obtaining a pipeline magnetic flux leakage distribution binary diagram through a threshold value, wherein the method specifically comprises the following steps of:
step 41: determining a threshold value as M according to the fluctuation range of the magnetic flux leakage data obtained in the step 31;
step 42: subtracting the magnetic flux leakage data obtained in the step (2) from the intermediate value data obtained in the step (3), then obtaining a binary image through threshold value binarization processing, assigning a part exceeding a threshold value to be one color to represent welding seam data, and assigning another color to be the part not exceeding the threshold value to represent the smooth pipeline;
and 5: processing the binary image by adopting asymmetric closed operation to strengthen the morphological characteristics of the welding line data in the detection data; connecting a plurality of connected domains by adopting asymmetric closed operation and setting the expansion scale to be larger than the corrosion scale; according to the average width W of the welding seam of the pipeline to be detected and the minimum mileage resolution s of the detector, the side length value L of the square expansion core can be set to be W/s, an odd number is upwards taken, and the side length of the square corrosion core is L-2;
step 6: extracting straight line segments in the binary image by using Hough transform, judging whether the straight line segments are girth welds or not, and registering weld information into a weld list if the straight line segments are girth welds;
step 61: finding straight line segments with the length being 2/3 of the circumference of the pipeline, and uniformly extracting the straight line segments as girth welds;
step 62: because the girth weld is perpendicular to the pipeline extending direction, the straight line sections meeting the following formula are extracted together according to the inclined angle existing in the running process of the detector:
|(x2-x1)/(y2-y1)|＜tan(5°)
wherein, (x1, y1), (x2, y2) are coordinates of two end points of a straight line segment;
and 63, removing a plurality of straight line segments in the same welding line obtained in the steps 61 and 62, and only leaving one straight line segment to represent the girth welding line:
firstly, expressing a straight line segment by using a mileage coordinate of a midpoint of the straight line segment, and marking the straight line segment as X, wherein X is (X1+ X2)/2, data corresponding to a serial number is Xn, and is expressed by a set { Xn }, and n is the number of the straight line segments;
then sorting the data in the set { Xn }, selecting the first data X1, and removing all X data with the distance to X1 less than d, wherein the calculation formula of d is as follows:
d＝w/2s
in the formula: w is the shortest distance between two girth welds in the pipeline construction standard;
for the first data X1, { Xn } subset { Xm1| | | Xm1-X1| < d }, then all xms belong to the same weld with X1, and are removed, leaving only the first data X1 to represent this weld; { Xn } after { Xm1| | Xm1-X1| < d } is removed, continuing to circulate the process until all elements in the set { Xn } are traversed, and finally obtaining a set containing a mileage value list, wherein each mileage value corresponds to one girth joint;
and 7, judging the welding seam list information, judging whether the welding seam is missed to be detected or not, and rechecking and recording the missed position.
The process of rechecking and recording the missed detection position in the step 7 is as follows:
the length of the single-section pipeline is limited, the distribution condition of the whole girth weld is scanned after a weld list is generated, when the girth weld is not found even if the length of the single-section pipeline is larger than the longest length of the single-section pipeline, the data of the interval are extracted again, and the step 4-6 is executed repeatedly; and simultaneously reducing the threshold value set in the step 4, supplementing the welding seam into the list if the welding seam is found, adding the midpoint coordinate of the pipeline into the list as welding seam data if the welding seam is not found, and marking the suspected undetected welding seam at the midpoint coordinate for the manual review of data staff.
An embodiment of the invention is given below, comprising the steps of:
step 1: acquiring original magnetic flux leakage data and odometer wheel data, synchronously acquiring the original magnetic flux leakage data by using a composite magnetic flux leakage probe (or a magnetic flux leakage sensor) in an equal-time-interval sampling mode, and synchronously sampling mileage data information in a pipeline by using the odometer sensor, wherein the acquired magnetic flux leakage original data are shown in fig. 2 and 5;
step 2: generating magnetic leakage data of a mileage coordinate, calculating an arc on a mileage wheel corresponding to two adjacent pulses according to the pulse number corresponding to one rotation of the mileage wheel and the perimeter of the mileage wheel by using the mileage data sampled by a mileage sensor as a pulse signal in the step 1, and obtaining a minimum unit of the mileage value, wherein the product of the pulse number and the minimum unit is to convert the pulse signal into an actually corresponding mileage value. In the embodiment, 3 mileage sensors are arranged on the circumference of the pipeline, the number of pulses passing through three mileage wheels is calculated within a certain time (for example, 5s), the wheel with the largest number of pulses is selected, and the difference of the wheel is calculated to obtain the distribution of mileage pulses. And calculating the actual mileage value traveled by the selected mileage wheel according to the mileage pulse distribution and the minimum unit. And carrying out data reconstruction by corresponding the magnetic flux leakage data and the actual mileage value at the same time one by one.
When data are reconstructed, when the difference value of the selected mileage wheel is smaller than 1, selecting a frame of data representing the current mileage as an actual mileage value; when the difference value is N >1, the data of the frame is copied for N times, the mileage difference is compensated, and the actual mileage value of the whole data is ensured to be distributed at equal intervals.
And step 3: and carrying out median filtering on the magnetic flux leakage data according to the channels to obtain magnetic flux leakage intermediate value data of each channel.
Because different pipe sections of the detected pipeline may have differences in material, wall thickness, inner diameter and the like, the differences all affect the base value of magnetic flux leakage detection, that is, under the condition that the pipeline is flat, the measured values of the different pipe sections also have differences, which affects the setting of the threshold value of the integral pipeline discrimination parameter. The embodiment finds out through experiments that the fluctuation of the detector is in a relatively stable interval, which is [ -2,2], and only the central value of the fluctuation changes along with the difference, and the embodiment introduces a median filter to deal with the difference in order to improve the adaptivity of the analysis. For a detector with the sampling frequency of 2000Hz, assuming that 256 pulses are generated in one circle of a mileage wheel, the mileage resolution is 0.98mm under the condition that the diameter of the mileage wheel is 80mm, a welding line is usually about 10mm, calculating a one-dimensional median of 101 points in each channel, ensuring that the line width of welding line data is far smaller than that of a flat part, obtaining the integral trend of a curve after the median is made, and distinguishing different pipe sections.
And 4, step 4: the magnetic flux leakage data in the step 2 and the intermediate value data in the step 3 are subjected to subtraction, and a pipeline magnetic flux leakage distribution binary diagram is obtained through a threshold value, as shown in fig. 3 and 6;
the threshold value of the embodiment is set to 4, the magnetic leakage data obtained in the step 2 and the intermediate value data obtained in the step 3 are subjected to difference, the part exceeding the threshold value is assigned to be white through threshold value binarization processing, in a binarized graph, the distribution of the sensors circumferentially arranged on the inner detector is longitudinally represented, and the position of the mileage where the data is collected is transversely represented.
And 5: carrying out asymmetric closing operation on the image to strengthen the part which is not flat and closed in the detection;
because the image directly obtained by binarization is uneven due to the welding seam, the white part can be broken, and in order to connect the broken parts and prevent the scale of the white part from being changed too much, the closing operation is selected. The general closing operation has a good effect on noise inside one connected domain, but has a bad effect on connection between two connected domains, and an asymmetric closing operation is adopted, namely, the expansion scale is larger than the corrosion scale, so that the connection among a plurality of connected domains can be realized. To ensure the longitudinal connection, the expanded cores are selected to be rectangular in the transverse direction 7 and the longitudinal direction 9, and the eroded cores are selected to be rectangular in the transverse direction 5 and the longitudinal direction 7, which results are shown in fig. 4 and 7.
Step 6: extracting the white part characteristics in the binary image, judging whether the white part characteristics are girth welds or not, and registering weld information into a weld list;
in the binary image, a white part is a part with uneven pipelines, the white part contains the characteristics of the pipelines, including defects, pipeline components and welding line information, the form of a circumferential welding line is obviously different from that of other characteristics, the circumferential welding line is perpendicular to the direction of the pipelines, the length of the circumferential welding line is equal to the circumference of the pipelines, and in the binary image, the circumferential welding line is a longitudinal straight line segment. The Hough transform is adopted to extract the linear features in the weld bead, and the weld bead screening is realized by setting some filtering conditions.
The hough transform extracts straight line segments from the white part, and the length directions of the straight line segments can be extracted as long as the straight line segments are within the white area, so that some conditions need to be set for screening. The data obtained by hough transform are two end points (x1, y1), (x2, y2) of a straight line segment.
In this embodiment, a straight line segment is extracted by using the length (condition 1), the length of the weld is the circumference of the pipe, considering that the connection may be broken, the length is set to 2/3 of the circumference, for example, a detector of 264 magnetic leakage channels, and the straight line obtained by hough transform leaves a length of 176 at least. The step can be directly set in Hough transform, and the obtained line segment is the line segment meeting the condition.
In this embodiment, a slope inclination angle is used again to extract a straight line segment (condition 2), a circumferential weld is perpendicular to the extending direction of the pipe, and considering that the detector sometimes has a certain inclination in operation, the angular swing range is set to 5 °.
|(x2-x1)/(y2-y1)|＜tan(5°)
The embodiment utilizes the width of the welding seam to process the line segment selected by the length and the inclination angle:
due to the fact that the welding seam has a certain width, the situation that a plurality of straight lines collected by Hough transform exist in the same welding seam after the condition 1 and the condition 2 inevitably exists. At this time, the line segment data is processed, each data is represented by two end points (X1, y1), (X2, y2), each data is represented by (X1+ X2)/2, the data is marked as X, the data with the corresponding serial number is Xn, namely the line segment is represented by the mileage coordinate of the midpoint of the line segment, the set { Xn } is used for representing the line segment, then the mileage data is sorted, the first data X1 is selected, and all X data with the distance to the X1 being less than d are removed. Usually, the width of the welding seam is about 10mm, and the nearest condition of the adjacent welding seam is about 200mm, wherein d is set as the number of pixel points corresponding to 100mm and used for distinguishing the line segments belonging to different welding seams. Taking the mileage resolution as 0.98mm as an example:
d＝100/0.98
then for X1, the subset of { Xn } { Xm1| | | Xm1-X1| < d }, all xms are considered to belong to the same weld as X1 and should be removed, leaving only X1 to represent this weld. { Xn } after removing { Xm1| | Xm1-X1| < d }, the process continues to loop until all elements in the set { Xn } are traversed. The resulting set is a list of mileage values, each of which corresponds to a girth weld.
And 7, judging the welding seam list information, judging whether the welding seam is likely to be missed for detection, and rechecking and recording the missed detection position.
The maximum welding seam distance exists, the length of a single section of the longest pipeline of the laid pipeline does not exceed 13 meters, the distribution condition of the whole girth welding seam is scanned after a welding seam list is generated, when no girth welding seam exists in a range larger than 15 meters, data in the range are extracted again, the step 4-6 is carried out again, the threshold value in the step 4 is reduced from 4 to 3, if the welding seam is found, the welding seam is supplemented into the list, if the welding seam is not found, the middle point coordinate of the section of the pipeline is taken as welding seam data and added into the list, and the suspected welding seam is marked for manual review by data staff.
Claims (2)
1. A method for identifying a ring weld in pipeline detection is characterized by comprising the following steps:
step 1: uniformly arranging a plurality of magnetic flux leakage sensors in the pipeline, arranging mileage sensors in the circumferential direction of the pipeline, and synchronously acquiring multi-channel original magnetic flux leakage data and mileage wheel data in an equal time interval sampling mode;
step 2: firstly, converting the odometer wheel data into an actual odometer value, and then acquiring magnetic flux leakage data of an odometer coordinate in a time alignment mode; comparing the mileage wheel data in a set time range, respectively calculating the pulse number of each mileage wheel data, selecting the mileage wheel corresponding to the maximum pulse number, and calculating the difference of the mileage wheel to obtain the mileage pulse distribution of the mileage wheel; calculating the actual mileage value of the mileage wheel according to the mileage pulse distribution; carrying out data reconstruction by corresponding the magnetic flux leakage data and the actual mileage value at the same time one by one;
and step 3: and (3) processing the data in the step (2) by using a median filtering method, and separating magnetic flux leakage data representing different pipe sections, wherein the method specifically comprises the following steps:
step 31: when an internal detector magnetic leakage sensor is tested before leaving a factory, under a natural condition, the value of the magnetic leakage sensor of the specification fluctuates around a central value N, and the fluctuation range is [ -M/2, M/2 ];
step 32: performing median filtering on the magnetic leakage data processed in the step 2 according to the channels to obtain a median of the magnetic leakage data of each channel;
step 33: drawing an intermediate value curve, wherein the intermediate value curve comprises welding line data and pipeline flat part data, and the ratio of the line width of the welding line data to the line width of the pipeline flat part is 1: 20;
and 4, step 4: and (3) making a difference between the magnetic flux leakage data in the step (2) and the intermediate value data in the step (3), and obtaining a pipeline magnetic flux leakage distribution binary diagram through a threshold value, wherein the method specifically comprises the following steps:
step 41: determining a threshold value as M according to the fluctuation range of the magnetic flux leakage data obtained in the step 31;
step 42: subtracting the magnetic flux leakage data obtained in the step (2) from the intermediate value data obtained in the step (3), then obtaining a binary image through threshold value binarization processing, assigning a part exceeding a threshold value to be one color to represent welding seam data, and assigning another color to be the part not exceeding the threshold value to represent the smooth pipeline;
and 5: processing the binary image by adopting asymmetric closed operation to strengthen the morphological characteristics of the welding line data in the detection data; connecting a plurality of connected domains by adopting asymmetric closed operation and setting the expansion scale to be larger than the corrosion scale; setting the side length value L of a square expansion core as W/s, taking an odd number upwards and setting the side length of a square corrosion core as L-2 according to the average width W of the welding seam of the pipeline to be detected and the minimum mileage resolution s of the detector;
step 6: extracting straight line segments in the binary image by using Hough transform, judging whether the straight line segments are circumferential welds or not, and registering weld information into a weld list if the straight line segments are circumferential welds;
step 61: finding straight line segments with the length being 2/3 of the circumference of the pipeline, and uniformly extracting the straight line segments as girth welds;
step 62: because the girth welding seam is perpendicular to the pipeline extending direction, according to the inclination angle that exists in the detector operation process, the straightway that satisfies the following formula is also extracted together:
|(x2-x1)/(y2-y1)|＜tan(5°)
wherein, (x1, y1), (x2, y2) are coordinates of two end points of a straight line segment;
and 63, removing a plurality of straight line segments in the same welding line obtained in the steps 61 and 62, and only leaving one straight line segment to represent the girth welding line:
firstly, expressing a straight line segment by using a mileage coordinate of a midpoint of the straight line segment, and marking the straight line segment as X, wherein X is (X1+ X2)/2, data corresponding to a serial number is Xn, and is expressed by a set { Xn }, and n is the number of the straight line segments;
then sorting the data in the set { Xn }, selecting the first data X1, and removing all X data with the distance to X1 less than d, wherein the calculation formula of d is as follows:
d＝w/2s
in the formula: w is the shortest distance between two girth welds in the pipeline construction standard;
for the first data X1, a subset { Xn } { Xm1| | | Xm1-X1| < d }, then all Xms belong to the same weld with X1, and are removed, leaving only the first data X1 to represent the weld; removing { Xn } { Xm1| | Xm1-X1| < d }, and then continuing to circulate the process until all elements in the set { Xn } are traversed to finally obtain a set containing a mileage value list, wherein each mileage value corresponds to one girth weld;
and 7, judging the welding seam list information, judging whether the welding seam is missed to be detected or not, and rechecking and recording the missed position.
2. The method for identifying the circular weld seam in the pipeline inspection as claimed in claim 1, wherein the process of rechecking and recording the missed inspection position in the step 7 is as follows:
the length of the single-section pipeline is limited, the distribution condition of the whole girth weld is scanned after a weld list is generated, when the girth weld is not found even if the length of the single-section pipeline is larger than the longest length of the single-section pipeline, the data of the interval are extracted again, and the step 4-6 is executed repeatedly; and simultaneously reducing the threshold value set in the step 4, supplementing the welding seam into the list if the welding seam is found, adding the midpoint coordinate of the pipeline into the list as welding seam data if the welding seam is not found, and marking the suspected undetected welding seam at the midpoint coordinate for the manual review of data staff.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210379499.6A CN115015375A (en) | 2022-04-12 | 2022-04-12 | Method for identifying middle ring welding seam in pipeline detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210379499.6A CN115015375A (en) | 2022-04-12 | 2022-04-12 | Method for identifying middle ring welding seam in pipeline detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115015375A true CN115015375A (en) | 2022-09-06 |
Family
ID=83067992
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210379499.6A Pending CN115015375A (en) | 2022-04-12 | 2022-04-12 | Method for identifying middle ring welding seam in pipeline detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115015375A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102607277B1 (en) * | 2023-06-07 | 2023-11-29 | 한전케이피에스 주식회사 | System for detecting fault and method thereof |
-
2022
- 2022-04-12 CN CN202210379499.6A patent/CN115015375A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102607277B1 (en) * | 2023-06-07 | 2023-11-29 | 한전케이피에스 주식회사 | System for detecting fault and method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104514987B (en) | Three-dimensional pipeline flux leakage imaging defect quantizing method | |
| CN111855810B (en) | Rail foot damage identification method and system based on recurrent neural network | |
| RU2419787C2 (en) | System and method to control pipelines by pulsed eddy currents | |
| CN114799610B (en) | Welding quality real-time detection method and system based on inverse Fourier transform and self-encoder | |
| CN112147221B (en) | Steel rail screw hole crack identification method and system based on ultrasonic flaw detector data | |
| CN103196989A (en) | ACFM different-angle crack detection system based on rotating magnetic field | |
| CN111024728A (en) | Railway detection method and system based on computer vision and ultrasonic flaw detection | |
| JP2002022708A (en) | Eddy current flaw detection signal evaluating method and its device | |
| CN105243089B (en) | A kind of pipeline detection data processing method | |
| CN110751604A (en) | Machine vision-based steel pipe weld defect online detection method | |
| CN109239081B (en) | Weld quality parameter detection method based on structured light and visual imaging | |
| CN111305774B (en) | Online monitoring and cleaning system for oil-water well operation and online monitoring method thereof | |
| CN115803619A (en) | Information processing device, determination method, and information processing program | |
| CN115015375A (en) | Method for identifying middle ring welding seam in pipeline detection | |
| CN108918679A (en) | Based on elastic wave and the prefabricated post sleeve of machine learning grouting lossless detection method | |
| CN108844856B (en) | Sleeve grouting defect nondestructive testing method based on impact elastic wave and machine learning | |
| CN110441388A (en) | A kind of jacket platform underwater portion non-destructive testing method of detection | |
| CN114878582A (en) | Defect detection and analysis method and system for special steel | |
| CN114088808B (en) | Pipeline crack visual detection method and system for three-dimensional induced eddy magnetic field cloud picture | |
| CN108181377B (en) | Intelligent interpretation system and method for broken PCCP steel wire | |
| CN111145168A (en) | Method and system for detecting defects of carbon fiber composite material and storage medium | |
| Ren et al. | Shaking noise elimination for detecting local flaw in steel wire ropes based on magnetic flux leakage detection | |
| CN115144259B (en) | Method and system for detecting deformation resistance of steel | |
| CN107178710B (en) | It is a kind of based on it is inside and outside detection signal characteristic abstraction defect of pipeline inside and outside discrimination method | |
| Cui et al. | A recognition algorithm to detect pipe weld defects |
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 |