CN113052022B - Rail defect identification and classification method based on composite electromagnetic detection - Google Patents
Rail defect identification and classification method based on composite electromagnetic detection Download PDFInfo
- Publication number
- CN113052022B CN113052022B CN202110265685.2A CN202110265685A CN113052022B CN 113052022 B CN113052022 B CN 113052022B CN 202110265685 A CN202110265685 A CN 202110265685A CN 113052022 B CN113052022 B CN 113052022B
- Authority
- CN
- China
- Prior art keywords
- defect
- signal
- signals
- buried
- defects
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 146
- 238000001514 detection method Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 21
- 239000002131 composite material Substances 0.000 title claims abstract description 17
- 230000000877 morphologic effect Effects 0.000 claims abstract description 4
- 238000005070 sampling Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 10
- 239000000523 sample Substances 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 230000004907 flux Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000009659 non-destructive testing Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000002500 effect on skin Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
-
- 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
- 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
- G01N27/90—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws using eddy currents
-
- 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
- G01N27/90—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws using eddy currents
- G01N27/9046—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws using eddy currents by analysing electrical signals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Pathology (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- Health & Medical Sciences (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Investigating Or Analyzing Materials By The Use Of Magnetic Means (AREA)
Abstract
The invention discloses a track defect identification and classification method based on composite electromagnetic detection, which comprises the steps of firstly detecting a sample by using a composite electromagnetic detection device, obtaining a magnetic leakage signal and an alternating current vortex IQ demodulation signal, then converting the detection signal into a binary image, identifying the position of a defect signal by applying an opening operation and a closing operation in a morphological operation method, identifying the position of a surface defect signal by a voting system, removing the surface defect signal from the magnetic leakage signal to obtain the magnetic leakage signal only containing a buried defect, and finally identifying the buried defect signal to obtain the position of the buried defect. The method can rapidly, effectively and accurately judge the position and the category of the detected rail defect, and provides help and guidance for the later overhaul and maintenance.
Description
Technical Field
The invention relates to the technical field of nondestructive testing, in particular to a rail defect identification and classification method based on composite electromagnetic detection.
Background
The composite electromagnetic detection technology combines eddy current detection and magnetic leakage detection, and achieves better detection effect by utilizing the characteristics of the eddy current detection and the magnetic leakage detection. The eddy current detection technology can only detect defects on the surface of a sample and cannot detect internal defects because the eddy current has skin effect; the magnetic flux leakage detection technique can detect both surface and buried defects. The method analyzes the respective advantages and disadvantages of the existing rail nondestructive testing technology, and then combines the advantages and disadvantages to make up for the advantages and disadvantages, thereby having important significance for improving the rail crack damage detection precision and guaranteeing the train operation safety.
At present, the compound detection technology can only judge whether the defect exists, but the accurate evaluation of parameters such as the defect position, defect category and the like is difficult, more detailed information of the defect cannot be provided, and the next maintenance work is not facilitated.
Disclosure of Invention
The invention aims to solve the technical problem of providing a track defect identification and classification method based on composite electromagnetic detection aiming at the defects related to the background technology, which can identify and classify signals of the surface and buried defects of magnetic leakage and eddy current detection.
The invention adopts the following technical scheme for solving the technical problems:
a track defect identification and classification method based on composite electromagnetic detection comprises the following steps:
step 1), detecting a sample to be detected by using a composite electromagnetic detection device, and obtaining a magnetic leakage signal and an alternating current vortex IQ demodulation signal;
step 2), converting the detection signal into a binary image, and identifying the position of the defect signal by applying an opening operation and a closing operation in a morphological operation method;
and 3) identifying the positions of the surface defect signals through a voting system, removing the surface defect signals from the magnetic leakage signals to obtain magnetic leakage signals only containing the buried defects, identifying the buried defect signals to obtain the positions of the buried defects, and further completing identification and classification of the surface defects and the buried defects.
As a further optimization scheme of the track defect identification and classification method based on composite electromagnetic detection, the specific steps of the step 2) are as follows:
step 2.1), normalizing the signal to [0,1] by using a maximum and minimum normalization method]The calculation formula isWherein x is the original signal, x' is the normalized signal, x min Is the minimum value of the signal, x max For maximum signal value, x min And x max The device can also be set manually according to actual conditions; taking the median of the normalized signal as the original direct current bias, and setting the signal bias at 0.5 when no defect exists;
step 2.2), binarizing the magnetic leakage signal and the alternating current vortex IQ demodulation signal by using a local self-adaptive threshold value with a brighter foreground than a background, setting 1 at the part of the positive peak larger than the threshold value, setting 0 at the rest part of the positive peak, and identifying the positive peak; then, binarizing the signal by using a local self-adaptive threshold value with darker foreground than background, setting 1 at the part with the negative peak smaller than the threshold value, setting 0 at the rest, and identifying the negative peak; performing OR operation on the identification results of the positive peak and the negative peak to obtain a binary signal with the peak value of 1 and the rest background signals of 0;
step 2.3), eliminating tiny noise signals which are mistakenly identified in the process of binarizing the signals by utilizing the opening operation of eliminating noise points in the images; because a small amplitude and a background are similar in the process of converting the negative peak to the positive peak and are not easy to identify, the signal after the opening operation is closed, so that the whole defect signal is identified as a continuous and complete signal.
As a further optimization scheme of the track defect identification and classification method based on composite electromagnetic detection, the specific steps of the step 3) are as follows:
step 3.1), identifying a surface defect signal by using the magnetic leakage signal and the alternating current vortex IQ demodulation signal through a 2/3 voting system, traversing each sampling point by the system, and judging the point as a surface defect signal area if two or more than two of three binarization signals of the magnetic leakage signal and the alternating current vortex IQ demodulation signal at the point are 1; respectively selecting 120 multiplied by 1 and 800 multiplied by 1 rectangular structural elements for the voted signals to perform one-time opening and closing operation to obtain surface defect signals;
step 3.2), the first derivative d, d=1 of the binarized surface defect signal is calculated to obtain the defect starting point n 1 The d= -1 part is the defect end point n 2 ；
The front and back of the surface defect are respectively widened by 20000/v sampling points to obtain the starting and ending point position n of each surface defect 1 20000/v and n 2 +20000/v, where v denotes the detected speed in km/h;
the defect signals between the starting and ending points of each defect are kept unchanged, signals between the last defect ending point and the next defect starting point are subjected to transition by linear interpolation to obtain virtual signals only containing surface defects, and original magnetic leakage signals are subtracted from the virtual signals to obtain virtual signals only containing buried defects;
step 3.3), binarizing, opening and closing the signals only containing the buried defects to obtain the identification result of the buried defects;
solving a first derivative of the identification result of the buried defect, wherein a position with the derivative value of 1 is the starting point of the buried defect, a position with the derivative value of-1 is the end point of the buried defect, 10000/v sampling points are taken as the allowance respectively in front and back, and the position of the buried defect is obtained;
and 3.4), intercepting signals between starting and ending points according to the positions of each surface defect and each buried defect, subtracting the bias which is manually applied during defect identification by 0.5, setting the signals without defects to zero, respectively drawing the surface and the buried defect signals, and realizing classification of the surface and the buried defects.
Compared with the prior art, the technical scheme provided by the invention has the following technical effects:
the method can rapidly, effectively and accurately judge the position of the detected rail defect, distinguish the surface and the buried defect, and provide help and guidance for the later overhaul and maintenance.
Drawings
FIG. 1 is a schematic diagram of a composite electromagnetic detection apparatus and principle;
FIG. 2 is a schematic diagram showing a defect top view and a cross-sectional view of a sample to be tested;
FIG. 3 is an original comparison graph of leakage flux, eddy current I-path signal, and eddy current Q-path signal for a defective sample;
FIG. 4 is a schematic diagram of the normalized and offset adjusted signals of FIG. 3;
FIG. 5 is a diagram of the binarized signal of FIG. 4;
FIG. 6 is a diagram of the binary signal of FIG. 5 after the on operation;
FIG. 7 is a diagram of the binary signal after the closing operation in FIG. 6;
FIG. 8 is a schematic diagram of a surface defect recognition result;
FIG. 9 is a schematic diagram of a virtual signal containing only surface defects and a virtual signal containing only buried defects;
FIG. 10 is a schematic diagram showing the result of identifying the buried defect;
FIG. 11 is a schematic diagram showing the surface and buried defect classification results.
Detailed Description
The technical scheme of the invention is further described in detail below with reference to the accompanying drawings:
this invention may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. In the drawings, the components are exaggerated for clarity.
The invention discloses a track defect identification and classification method based on composite electromagnetic detection, which comprises the following steps:
step 1), detecting a sample to be detected by using a composite electromagnetic detection device, and obtaining a magnetic leakage signal and an alternating current vortex IQ demodulation signal;
the composite electromagnetic detection device generally comprises a magnetic core, an exciting coil, a differential probe and the like, as shown in fig. 1, when the device is used for detecting a sample to be detected, direct current excitation 50V is applied to the exciting coil, alternating current excitation 50kHz and 10Vpp is applied to the differential coil, sample defects are shown in fig. 2, and acquired magnetic leakage signals and eddy current IQ demodulation signals are shown in fig. 3.
Step 2), converting the detection signal into a binary image, and identifying the position of a defect signal in the signal by applying an opening operation and a closing operation in a morphological operation method:
step 2.1), normalizing the signals to [0,1] by adopting a maximum and minimum normalization method, taking the median of the normalized signals as the original direct current offset, setting the signal offset without defects to be 0.5, and enabling the signals after normalization and offset adjustment to be shown in figure 4;
step 2.2), binarizing the magnetic leakage and eddy current IQ two-path signals by using a local self-adaptive threshold value with a brighter foreground than a background, setting 1 at the part of the positive peak larger than the threshold value, setting 0 at the rest part of the positive peak, and identifying the positive peak; then, binarizing the signal by using a local self-adaptive threshold value with darker foreground than background, setting 1 at the part with the negative peak smaller than the threshold value, setting 0 at the rest, and identifying the negative peak; performing OR operation on the identification results of the positive peak and the negative peak to obtain a binary signal with a peak value of 1 and the rest background signals of 0, wherein a gray area in the figure is a peak value area with a binary value of 1, and a white area is a background signal as shown in FIG. 5;
step 2.3), performing on operation on the binarized signal by adopting a rectangular structural element of 150 multiplied by 1, and eliminating a noise signal to obtain a defect signal as shown in fig. 6; the signals after the opening operation are closed by adopting 700 multiplied by 1 rectangular structural elements, so that the whole defect signals can be identified as a continuous and complete prospect, as shown in fig. 7;
step 3), identifying the positions of the surface defect signals through a voting system, removing the surface defect signals from the magnetic leakage signals to obtain magnetic leakage signals only containing the buried defects, identifying the buried defect signals to obtain the positions of the buried defects, and further completing identification and classification of the surface defects and the buried defects:
step 3.1), identifying a surface defect signal by using a magnetic leakage and eddy current IQ demodulation signal through a 2/3 voting system, traversing each sampling point by the system, judging the point as a surface defect signal area if two or more values in three binarization signals of the magnetic leakage and eddy current IQ demodulation signal are 1, and respectively selecting 120 multiplied by 1 and 800 multiplied by 1 rectangular structural elements for carrying out one-time opening and closing operation on the voted signals to obtain the surface defect signal, wherein the surface defect signal is shown in figure 8;
step 3.2), the first derivative d, d=1 is obtained for the surface defect signal obtained in step 3.1), namely the defect starting point n 1 The d= -1 part is the defect end point n 2 ；
The front and back of the surface defect are respectively widened by 20000/v sampling points to obtain the starting and ending point position n of each surface defect 1 20000/v and n 2 +20000/v, where v denotes the detected speed in km/h;
the defect signal between each defect starting point and each defect ending point is kept unchanged, and the signal between the last defect ending point and the next defect starting point is subjected to transition by linear interpolation to obtain a virtual signal only containing surface defects, as shown by a gray dotted line in fig. 9; subtracting the original magnetic leakage signal from the virtual signal to obtain a virtual signal only containing the buried defect, as shown by a light gray solid line in fig. 9;
step 3.3, performing binarization, opening operation and closing operation on the signal only containing the buried defects, and obtaining the recognition result of the buried defects by adopting the method of step 2), as shown in fig. 10;
step 3.4), intercepting signals between starting and ending points according to each surface defect and the position of the buried defect, subtracting the manually applied bias during defect identification, setting the signals without defects to zero, respectively drawing the surface and the buried defect signals, and realizing classification of the surface and the buried defects, wherein the accuracy and the precision of 11 surface defect identifications are 100%, and no false identification and missing identification phenomenon exists; the identification accuracy rate of 10 buried defects reaches 90 percent, the accuracy rate reaches 100 percent, and the buried defects with the aperture of 2mm and above can be accurately identified.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
While the foregoing is directed to embodiments of the present invention, other and further details of the invention may be had by the present invention, it should be understood that the foregoing description is merely illustrative of the present invention and that no limitations are intended to the scope of the invention, except insofar as modifications, equivalents, improvements or modifications are within the spirit and principles of the invention.
Claims (1)
1. The track defect identification and classification method based on composite electromagnetic detection is characterized by comprising the following steps of:
step 1), detecting a sample to be detected by using a composite electromagnetic detection device, and obtaining a magnetic leakage signal and an alternating current vortex IQ demodulation signal;
step 2), converting the detection signal into a binary image, and identifying the position of the defect signal by applying an opening operation and a closing operation in a morphological operation method;
step 2.1), normalizing the signals by a maximum and minimum normalization methodTo [0,1]]The calculation formula isWherein x is the original signal, x' is the normalized signal, x min Is the minimum value of the signal, x max Is the signal maximum;
according to the formula x "=x' -x mid +0.5 bias adjustment of the signal, set the signal bias at 0.5 for defect free, where x mid The median of the normalized signal;
step 2.2), applying image binarization to detection signals, firstly, binarizing the signals by using a local self-adaptive threshold value with brighter foreground than background, and identifying positive peaks; then, binarizing the signal by using a local self-adaptive threshold value with darker foreground than background, and identifying a negative peak; finally, carrying out OR operation on the identification results of the positive peak and the negative peak, wherein the signal value of the defect position after signal binarization is 1, and the signal of the defect position is 0;
step 2.3), eliminating tiny noise signals which are mistakenly identified in the process of binarizing the signals by utilizing the opening operation of eliminating noise points in the images; closing the signals after the opening operation to enable the whole defect signal to be identified as a continuous and complete signal;
step 3), recognizing the positions of the surface defect signals through a voting system, removing the surface defect signals from the magnetic leakage signals to obtain magnetic leakage signals only containing the buried defects, recognizing the buried defect signals to obtain the positions of the buried defects, and further completing recognition and classification of the surface defects and the buried defects;
step 3.1), identifying a surface defect signal by using the magnetic leakage signal and the alternating current vortex IQ demodulation signal through a 2/3 voting system, traversing each sampling point by the system, and judging the point as a surface defect signal area if two or more than two of three binarization signals of the magnetic leakage signal and the alternating current vortex IQ demodulation signal at the point are 1; respectively selecting 120 multiplied by 1 and 800 multiplied by 1 rectangular structural elements for the voted signals to perform one-time opening and closing operation to obtain surface defect signals;
step 3.2), the first derivative d, d=1 of the binarized surface defect signal is obtained to be the defectTrap start point n 1 The d= -1 part is the defect end point n 2 ；
The front and back of the surface defect are respectively widened by 20000/v sampling points to obtain the starting and ending point position n of each surface defect 1 20000/v and n 2 +20000/v, where v denotes the detected speed in km/h;
the defect signals between the starting and ending points of each defect are kept unchanged, signals between the last defect ending point and the next defect starting point are subjected to transition by linear interpolation to obtain virtual signals only containing surface defects, and original magnetic leakage signals are subtracted from the virtual signals to obtain virtual signals only containing buried defects;
step 3.3), binarizing, opening and closing the signals only containing the buried defects to obtain the identification result of the buried defects;
solving a first derivative of the identification result of the buried defect, wherein a position with the derivative value of 1 is the starting point of the buried defect, a position with the derivative value of-1 is the end point of the buried defect, 10000/v sampling points are taken as the allowance respectively in front and back, and the position of the buried defect is obtained;
and 3.4), intercepting signals between starting and ending points according to the positions of each surface defect and each buried defect, subtracting the bias which is manually applied during defect identification by 0.5, setting the signals without defects to zero, respectively drawing the surface and the buried defect signals, and realizing classification of the surface and the buried defects.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110265685.2A CN113052022B (en) | 2021-03-11 | 2021-03-11 | Rail defect identification and classification method based on composite electromagnetic detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110265685.2A CN113052022B (en) | 2021-03-11 | 2021-03-11 | Rail defect identification and classification method based on composite electromagnetic detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113052022A CN113052022A (en) | 2021-06-29 |
| CN113052022B true CN113052022B (en) | 2024-03-22 |
Family
ID=76511457
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110265685.2A Active CN113052022B (en) | 2021-03-11 | 2021-03-11 | Rail defect identification and classification method based on composite electromagnetic detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113052022B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111337567A (en) * | 2020-03-27 | 2020-06-26 | 南京航空航天大学 | Defect type evaluation method based on eddy current and magnetic flux leakage detection signal fusion |
| WO2021008249A1 (en) * | 2019-07-16 | 2021-01-21 | 南京航空航天大学 | Differential-type high-speed track defect inspection method combining magnetic flux leakage and eddy current |
-
2021
- 2021-03-11 CN CN202110265685.2A patent/CN113052022B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021008249A1 (en) * | 2019-07-16 | 2021-01-21 | 南京航空航天大学 | Differential-type high-speed track defect inspection method combining magnetic flux leakage and eddy current |
| CN111337567A (en) * | 2020-03-27 | 2020-06-26 | 南京航空航天大学 | Defect type evaluation method based on eddy current and magnetic flux leakage detection signal fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113052022A (en) | 2021-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110057904B (en) | Method and device for quantitatively detecting defects of moving metal component | |
| CN102759567A (en) | Eddy current testing recognition and evaluation method for defects of inner wall and outer wall of steel pipe under direct current magnetization | |
| CN106340011B (en) | A kind of automatic detection recognition method that lorry door is opened | |
| CN111337567B (en) | Defect type assessment method based on eddy current and magnetic flux leakage detection signal fusion | |
| CN108335294A (en) | The power distribution room abnormality image-recognizing method of complex condition | |
| CN106296687A (en) | Magnet ring method for extracting surface defects based on mask technique | |
| Hu et al. | Rail surface spalling detection based on visual saliency | |
| CN114972325A (en) | Automobile hub defect detection method based on image processing | |
| CN113052022B (en) | Rail defect identification and classification method based on composite electromagnetic detection | |
| JP4622742B2 (en) | Method and apparatus for detecting eddy current in metal strip | |
| Fu et al. | Research on image-based detection and recognition technologies for cracks on rail surface | |
| CN111638218A (en) | Method for detecting surface defects of coating | |
| Szugs et al. | Combination of ultrasonic and eddy current testing with imaging for characterization of rolling contact fatigue | |
| CN105740831B (en) | A kind of stopping line detecting method applied to intelligent driving | |
| CN108872252A (en) | A kind of girder steel flaw detection system | |
| CN109459489B (en) | Elevator crack detection method based on magnetic memory detection principle | |
| CN109870500B (en) | Method and system for real-time defect discrimination based on alternating current magnetic field detection | |
| JP2004037216A (en) | Leakage flux flaw detecting method | |
| CN108828058B (en) | Method for distinguishing defects of upper surface and lower surface of steel plate based on pulse magnetic flux leakage detection | |
| CN113393440B (en) | Method for automatically enhancing and identifying weld defects based on magneto-optical imaging | |
| CN102759565B (en) | A kind of steel band in length and breadth to defects detection and identify leakage magnetic detection device and method | |
| Liao et al. | Surface defect detection of Si3N4 ceramic bearing ball based on improved homomorphic filter-Gaussian filter coupling algorithm | |
| CN116342966B (en) | Rail inspection method, device, equipment and medium based on deep learning | |
| CN112330633B (en) | Jumper wire adhesive tape damage fault image segmentation method based on self-adaptive band-pass filtering | |
| Liang et al. | Study on Image Identification Method of In-service Pipeline Corrosion Fault |
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 |