CN117538412A - Ultrasonic detection method for rail crack damage - Google Patents
Ultrasonic detection method for rail crack damage Download PDFInfo
- Publication number
- CN117538412A CN117538412A CN202311495149.7A CN202311495149A CN117538412A CN 117538412 A CN117538412 A CN 117538412A CN 202311495149 A CN202311495149 A CN 202311495149A CN 117538412 A CN117538412 A CN 117538412A
- Authority
- CN
- China
- Prior art keywords
- guided wave
- wave signal
- ultrasonic
- signal
- rail
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 32
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 22
- 230000005284 excitation Effects 0.000 claims abstract description 4
- 230000009466 transformation Effects 0.000 claims abstract description 4
- 238000012706 support-vector machine Methods 0.000 claims description 15
- 230000004927 fusion Effects 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 5
- 238000000034 method Methods 0.000 claims description 4
- 238000005215 recombination Methods 0.000 claims description 4
- 230000006798 recombination Effects 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims 1
- 229910000831 Steel Inorganic materials 0.000 abstract description 6
- 239000010959 steel Substances 0.000 abstract description 6
- 239000013598 vector Substances 0.000 description 4
- 238000005299 abrasion Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000001125 extrusion Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2131—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on a transform domain processing, e.g. wavelet transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2132—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on discrimination criteria, e.g. discriminant analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
-
- 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
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
-
- 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)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Analytical Chemistry (AREA)
- Probability & Statistics with Applications (AREA)
- Pathology (AREA)
- Immunology (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention discloses an ultrasonic detection method for rail crack damage, which is applied to the technical field of damage-free detection. Comprising the following steps: generating a guided wave signal by using coding excitation, decoding the guided wave signal through an optimal filter, and collecting first ultrasonic guided wave signals of rail cracks with different damage degrees; performing time-frequency analysis on the collected first ultrasonic guided wave signal, and extracting various characteristics in an original frequency domain signal; extracting energy and effective frequency band entropy characteristics of different frequency bands after the first ultrasonic guided wave signal is decomposed by using a wavelet packet decomposition algorithm; the features are recombined to obtain new features, the features are extracted again, and projection is carried out through PCA; obtaining optimal characteristics according to PCA projection, and obtaining a second ultrasonic guided wave signal by performing Fourier inverse transformation on the optimal characteristics; and adopting Hilbert Huang Suanfa to perform modal decomposition on the second ultrasonic guided wave signal and performing classification detection on rail cracks. The invention can detect the cracks of the steel rails to ensure the safe operation of railways.
Description
Technical Field
The invention relates to the technical field of nondestructive testing, in particular to an ultrasonic testing method for rail crack damage.
Background
The operation speed and the cargo weight of the train are continuously increased while the operation mileage of the railway is increased, the extrusion and the impact of the steel rail caused by the train are increased, the probability of the damage of the steel rail is increased, and the number of problems caused by the damage is increased. Rail surface damage detection is an important link in railway operation management, and in recent years, a plurality of high and new technologies are applied to rail detection, and the following are commonly used: ultrasonic detection, magnetic leakage detection and eddy current detection. Although the ultrasonic detection has a good detection effect on the defects in the rail, the detection effect on the rail surface damage is not satisfactory.
Under heavy railway transportation pressure, the probability of surface damage of the steel rail due to fatigue and abrasion is greatly improved, and more potential safety hazards are brought to railway transportation. Defects such as crack abrasion and the like are generated due to invisible internal stress concentration caused by extrusion, load and temperature unevenness, and have a great threat to railway safety.
Therefore, an ultrasonic detection method for rail crack damage is provided to solve the difficulty of the prior art, which is a problem to be solved by the skilled person.
Disclosure of Invention
In view of the above, the invention provides an ultrasonic detection method for rail crack damage, which is used for solving the technical problems in the prior art.
In order to achieve the above object, the present invention provides the following technical solutions:
an ultrasonic detection method for rail crack damage, comprising the following steps:
s1, generating a guided wave signal by using coding excitation, decoding the guided wave signal through an optimal matched filter, and collecting first ultrasonic guided wave signals of rail cracks with different damage degrees;
s2, performing time-frequency analysis on the first ultrasonic guided wave signal acquired in the S1, and extracting various characteristics in an original frequency domain signal;
s3, extracting energy and effective frequency band entropy characteristics of different frequency bands after the first ultrasonic guided wave signal is decomposed by utilizing a wavelet packet decomposition algorithm;
s4, recombining the features in the S2 and the S3 to obtain new features, extracting the features again by combining with principal component analysis, and projecting by PCA;
s5, obtaining optimal characteristics according to the PCA projection in the S4, and obtaining a second ultrasonic guided wave signal through Fourier inverse transformation of the optimal characteristics;
s6, carrying out modal decomposition on the second ultrasonic guided wave signal in the S5 by adopting Hilbert Huang Suanfa, and carrying out classification detection on rail cracks with different damage degrees by utilizing an intelligent recognition algorithm.
Optionally, the coding in S1 is specifically: golay sequence coding and optimal binary codes.
Optionally, the extracting multiple features in the original frequency domain signal in S2 specifically includes:
and extracting the center frequency, the peak value corresponding to the center frequency and the total energy characteristic of the signal in the original frequency domain signal.
Optionally, S3 is specifically:
and carrying out wavelet packet decomposition on the first ultrasonic guided wave signal based on the demy wavelet basis function, and selecting the decomposition layer number by solving the signal-to-noise ratio and the cross correlation coefficient of the recombined signal decomposed by different layers and the original signal.
Optionally, S4 is specifically:
s41, performing four characteristic recombination modes by utilizing the characteristics obtained in the S2 and the S3;
s42, extracting projection values with contribution rate larger than 95% through PCA projection to achieve feature re-extraction, adopting PCA clustering visualization, and comparing clustering effects of different combination feature parameters to obtain optimal features.
Optionally, the hilbert yellow algorithm in S6 specifically includes:
s61, firstly, performing empirical mode decomposition on a second ultrasonic guided wave signal, inputting a signal x (t), finding out all local maximum points and minimum points, solving a mean value m (t), and judging whether h (t) meets an IMF (inertial measurement unit) or not by using a residual signal h (t) =x (t) -m (t);
s62, performing Hilbert transform on each IMF to obtain the instantaneous frequency of each IMF, and finally performing modal decomposition.
Optionally, the intelligent recognition algorithm in S6 is a hybrid intelligent algorithm based on KPCA, WPT and support vector machine.
Optionally, the hybrid intelligent algorithm based on the KPCA, the WPT and the support vector machine specifically comprises the following steps: and carrying out multi-classification detection and comparison based on a support vector machine on the rail crack damage by adopting wavelet packet fusion characteristics based on a core main component and multidimensional scaling wavelet packet fusion characteristics, and carrying out multi-dimensional characteristic performance evaluation on wavelet packet fusion of the rail crack damage by adopting a separability measure based on linear discriminant analysis and a nonlinear support vector machine identification method based on the support vector machine.
Compared with the prior art, the invention discloses an ultrasonic detection method for rail crack damage, which has the beneficial effects that: the cracks of the steel rail can be detected in time to ensure the safe operation of the railway; the structural integrity and the safety of the steel rail are detected in real time under the condition that the safe and normal operation of the train is not affected.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an ultrasonic detection method for rail crack damage provided by the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the invention discloses an ultrasonic detection method for rail crack damage, which comprises the following steps:
s1, generating a guided wave signal by using coding excitation, decoding the guided wave signal through an optimal matched filter, and collecting first ultrasonic guided wave signals of rail cracks with different damage degrees;
s2, performing time-frequency analysis on the first ultrasonic guided wave signal acquired in the S1, and extracting various characteristics in an original frequency domain signal;
s3, extracting energy and effective frequency band entropy characteristics of different frequency bands after the first ultrasonic guided wave signal is decomposed by utilizing a wavelet packet decomposition algorithm;
s4, recombining the features in the S2 and the S3 to obtain new features, extracting the features again by combining with principal component analysis, and projecting by PCA;
s5, obtaining optimal characteristics according to the PCA projection in the S4, and obtaining a second ultrasonic guided wave signal through Fourier inverse transformation of the optimal characteristics;
s6, carrying out modal decomposition on the second ultrasonic guided wave signal in the S5 by adopting Hilbert Huang Suanfa, and carrying out classification detection on rail cracks with different damage degrees by utilizing an intelligent recognition algorithm.
Specifically, the wavelet packet decomposition feature extraction algorithm in S3 specifically includes:
wavelet packet energy (E) feature extraction, firstly solving signal energy on different decomposition scales, and then arranging the energy values into feature vectors which have scale sequences and can be used for identification; wavelet packet local entropy (F) feature extraction, selecting an effective frequency band by using energy values of all sub-frequency bands, and extracting wavelet packet energy entropy (F) corresponding to the effective frequency band i ) As characteristic parameters, i.e. after decomposing each wavelet packet, the energy value and the total energy value of each sub-band are obtainedRatio P of (2) i Selecting sub-bands with the total energy ratio of more than 98%, then solving wavelet packet entropy characteristics of effective k sub-bands, and finally obtaining wavelet packet entropy characteristic vectors F of each sample.
Further, the codes in S1 are specifically: golay sequence coding and optimal binary codes.
Specifically, the signal-to-noise ratio and the propagation distance of the received signal can be greatly improved by adopting Golay coding.
Further, the extracting multiple features in the original frequency domain signal in S2 specifically includes:
and extracting the center frequency, the peak value corresponding to the center frequency and the total energy characteristic of the signal in the original frequency domain signal.
Further, S3 is specifically:
and carrying out wavelet packet decomposition on the first ultrasonic guided wave signal based on the demy wavelet basis function, and selecting the decomposition layer number by solving the signal-to-noise ratio and the cross correlation coefficient of the recombined signal decomposed by different layers and the original signal.
Further, S4 is specifically:
s41, performing four characteristic recombination modes by utilizing the characteristics obtained in the S2 and the S3;
s42, extracting projection values with contribution rate larger than 95% through PCA projection to achieve feature re-extraction, adopting PCA clustering visualization, and comparing clustering effects of different combination feature parameters to obtain optimal features.
Specifically, the four characteristic recombination modes are total energy+wavelet packet energy entropy, center frequency+wavelet packet energy entropy, center frequency peak value+wavelet packet energy entropy, wavelet packet energy entropy, peak value corresponding to center frequency+center frequency+signal total energy+wavelet packet energy entropy. However, when the number of dimensions of the recombined feature vector is large, an excessive learning problem is liable to occur. Therefore, feature vectors are further extracted through a PCA algorithm, and finally, four kinds of recombined features are named as New feature 1, new feature 2, new feature 3 and New feature 4, and the advantages and disadvantages of the New features are pre-judged through clustering results.
Further, the hilbert yellow algorithm in S6 specifically includes:
s61, firstly, performing empirical mode decomposition on a second ultrasonic guided wave signal, inputting a signal x (t), finding out all local maximum points and minimum points, solving a mean value m (t), and judging whether h (t) meets an IMF (inertial measurement unit) or not by using a residual signal h (t) =x (t) -m (t);
s62, performing Hilbert transform on each IMF to obtain the instantaneous frequency of each IMF, and finally performing modal decomposition.
Further, the intelligent recognition algorithm in the S6 is a hybrid intelligent algorithm based on KPCA, WPT and a support vector machine.
Further, the hybrid intelligent algorithm based on the KPCA, the WPT and the support vector machine is specifically as follows: and carrying out multi-classification detection and comparison based on a support vector machine on the rail crack damage by adopting wavelet packet fusion characteristics based on a core main component and multidimensional scaling wavelet packet fusion characteristics, and carrying out multi-dimensional characteristic performance evaluation on wavelet packet fusion of the rail crack damage by adopting a separability measure based on linear discriminant analysis and a nonlinear support vector machine identification method based on the support vector machine.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. An ultrasonic detection method for rail crack damage is characterized by comprising the following steps:
s1, generating a guided wave signal by using coding excitation, decoding the guided wave signal through an optimal matched filter, and collecting first ultrasonic guided wave signals of rail cracks with different damage degrees;
s2, performing time-frequency analysis on the first ultrasonic guided wave signal acquired in the S1, and extracting various characteristics in an original frequency domain signal;
s3, extracting energy and effective frequency band entropy characteristics of different frequency bands after the first ultrasonic guided wave signal is decomposed by utilizing a wavelet packet decomposition algorithm;
s4, recombining the features in the S2 and the S3 to obtain new features, extracting the features again by combining with principal component analysis, and projecting by PCA;
s5, obtaining optimal characteristics according to the PCA projection in the S4, and obtaining a second ultrasonic guided wave signal through Fourier inverse transformation of the optimal characteristics;
s6, carrying out modal decomposition on the second ultrasonic guided wave signal in the S5 by adopting Hilbert Huang Suanfa, and carrying out classification detection on rail cracks with different damage degrees by utilizing an intelligent recognition algorithm.
2. An ultrasonic inspection method for rail crack damage as claimed in claim 1, wherein,
the codes in S1 are specifically: golay sequence coding and optimal binary codes.
3. The ultrasonic detection method for rail crack damage according to claim 1, wherein the extracting of the plurality of features in the original frequency domain signal in S2 is specifically:
and extracting the center frequency, the peak value corresponding to the center frequency and the total energy characteristic of the signal in the original frequency domain signal.
4. The ultrasonic detection method for rail crack damage according to claim 1, wherein S3 specifically comprises:
and carrying out wavelet packet decomposition on the first ultrasonic guided wave signal based on the demy wavelet basis function, and selecting the decomposition layer number by solving the signal-to-noise ratio and the cross correlation coefficient of the recombined signal decomposed by different layers and the original signal.
5. The ultrasonic detection method for rail crack damage according to claim 1, wherein S4 is specifically:
s41, performing four characteristic recombination modes by utilizing the characteristics obtained in the S2 and the S3;
s42, extracting projection values with contribution rate larger than 95% through PCA projection to achieve feature re-extraction, adopting PCA clustering visualization, and comparing clustering effects of different combination feature parameters to obtain optimal features.
6. The ultrasonic detection method for rail crack damage according to claim 1, wherein the hilbert yellow algorithm in S6 is specifically:
s61, firstly, performing empirical mode decomposition on a second ultrasonic guided wave signal, inputting a signal x (t), finding out all local maximum points and minimum points, solving a mean value m (t), and judging whether h (t) meets an IMF (inertial measurement unit) or not by using a residual signal h (t) =x (t) -m (t);
s62, performing Hilbert transform on each IMF to obtain the instantaneous frequency of each IMF, and finally performing modal decomposition.
7. The ultrasonic detection method for rail crack damage according to claim 1, wherein the intelligent recognition algorithm in S6 is a hybrid intelligent algorithm based on KPCA, WPT and a support vector machine.
8. The ultrasonic detection method for rail crack damage according to claim 7, wherein the hybrid intelligent algorithm based on KPCA, WPT and support vector machine is specifically: and carrying out multi-classification detection and comparison based on a support vector machine on the rail crack damage by adopting wavelet packet fusion characteristics based on a core main component and multidimensional scaling wavelet packet fusion characteristics, and carrying out multi-dimensional characteristic performance evaluation on wavelet packet fusion of the rail crack damage by adopting a separability measure based on linear discriminant analysis and a nonlinear support vector machine identification method based on the support vector machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311495149.7A CN117538412B (en) | 2023-11-09 | 2023-11-09 | Ultrasonic detection method for rail crack damage |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311495149.7A CN117538412B (en) | 2023-11-09 | 2023-11-09 | Ultrasonic detection method for rail crack damage |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117538412A true CN117538412A (en) | 2024-02-09 |
| CN117538412B CN117538412B (en) | 2024-05-14 |
Family
ID=89781822
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311495149.7A Active CN117538412B (en) | 2023-11-09 | 2023-11-09 | Ultrasonic detection method for rail crack damage |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117538412B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101571513A (en) * | 2009-06-16 | 2009-11-04 | 北京理工大学 | Ultrasonic guided wave detection device for quality evaluation of composite laminated plate |
| US20150073729A1 (en) * | 2012-05-25 | 2015-03-12 | Fbs, Inc. | Systems and methods for damage detection in structures using guided wave phased arrays |
| CN104833729A (en) * | 2015-05-05 | 2015-08-12 | 北京工业大学 | Ultrasonic guided-wave based calculation method for separating flexural mode reflected signal |
| CN104990980A (en) * | 2015-06-19 | 2015-10-21 | 西安理工大学 | Steel rail damage judgment method based on ultrasonic guided-waves |
| WO2019201177A1 (en) * | 2018-04-17 | 2019-10-24 | 江苏必得科技股份有限公司 | Train component crack damage monitoring method and system |
| CN113533510A (en) * | 2021-06-29 | 2021-10-22 | 北京交通大学 | Method and device for identifying fatigue microcracks of steel rail |
| CN113935231A (en) * | 2021-09-14 | 2022-01-14 | 南京邮电大学 | Large-scale structural damage monitoring and evaluating method based on sparse array |
| CN114166943A (en) * | 2021-12-03 | 2022-03-11 | 四川西南交大铁路发展股份有限公司 | Active rail damage monitoring method and terminal based on nonlinear ultrasonic waves |
| US20220135094A1 (en) * | 2018-08-01 | 2022-05-05 | Commissariat A L'energie Atomique Et Aux Energies Alternatives | Inspection of rail health |
-
2023
- 2023-11-09 CN CN202311495149.7A patent/CN117538412B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101571513A (en) * | 2009-06-16 | 2009-11-04 | 北京理工大学 | Ultrasonic guided wave detection device for quality evaluation of composite laminated plate |
| US20150073729A1 (en) * | 2012-05-25 | 2015-03-12 | Fbs, Inc. | Systems and methods for damage detection in structures using guided wave phased arrays |
| CN104833729A (en) * | 2015-05-05 | 2015-08-12 | 北京工业大学 | Ultrasonic guided-wave based calculation method for separating flexural mode reflected signal |
| CN104990980A (en) * | 2015-06-19 | 2015-10-21 | 西安理工大学 | Steel rail damage judgment method based on ultrasonic guided-waves |
| WO2019201177A1 (en) * | 2018-04-17 | 2019-10-24 | 江苏必得科技股份有限公司 | Train component crack damage monitoring method and system |
| US20220135094A1 (en) * | 2018-08-01 | 2022-05-05 | Commissariat A L'energie Atomique Et Aux Energies Alternatives | Inspection of rail health |
| CN113533510A (en) * | 2021-06-29 | 2021-10-22 | 北京交通大学 | Method and device for identifying fatigue microcracks of steel rail |
| CN113935231A (en) * | 2021-09-14 | 2022-01-14 | 南京邮电大学 | Large-scale structural damage monitoring and evaluating method based on sparse array |
| CN114166943A (en) * | 2021-12-03 | 2022-03-11 | 四川西南交大铁路发展股份有限公司 | Active rail damage monitoring method and terminal based on nonlinear ultrasonic waves |
Non-Patent Citations (2)
| Title |
|---|
| 吴斌;邓菲;何存富;: "超声导波无损检测中的信号处理研究进展", 北京工业大学学报, no. 04, 15 April 2007 (2007-04-15), pages 342 - 348 * |
| 张永宏;郝培培;许学明;孙亚杰;: "基于改进Hilbert-Huang变换的超声回波信号去噪研究", 科学技术与工程, no. 12, 28 April 2013 (2013-04-28), pages 3481 - 3487 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117538412B (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103398769B (en) | Transformer on-line fault detecting method based on sampling integrated SVM (support vector machine) under wavelet GGD (general Gaussian distribution) feather and unbalanced K-mean value | |
| Murthy et al. | Insulator condition analysis for overhead distribution lines using combined wavelet support vector machine (SVM) | |
| CN110415709B (en) | Transformer working state identification method based on voiceprint identification model | |
| Seo et al. | Probabilistic wavelet transform for partial discharge measurement of transformer | |
| CN115879343B (en) | Ballastless track self-compacting concrete void two-stage identification method | |
| CN104573321A (en) | Recognition and processing method of bad data of dissolved gas in transformer oil | |
| CN105785236A (en) | GIS local discharge detection external interference signal elimination method | |
| Alshahrani et al. | Evaluation and classification of power quality disturbances based on discrete wavelet transform and artificial neural networks | |
| Xue et al. | Application of feature extraction method based on 2D—LPEWT in cable partial discharge analysis | |
| CN117538412B (en) | Ultrasonic detection method for rail crack damage | |
| Swedan et al. | Acoustic detection of partial discharge using signal processing and pattern recognition techniques | |
| CN116189711B (en) | Transformer fault identification method and device based on acoustic wave signal monitoring | |
| CN102879474B (en) | Characterization and quantitative evaluation system for fatigue damage state of in-service 16Mn manganese steel bearing part based on WPT (wavelet packet tactic) and DF (double focusing spectrum) tactic | |
| CN112986388B (en) | Turnout switch blade defect detection method and system based on broadband excitation | |
| Ghaderi et al. | Fourier transform and correlation-based feature selection for fault detection of automobile engines | |
| CN113588568B (en) | Method for detecting environment-friendly insulating gas decomposition product | |
| Zhao et al. | Track irregularity feature extraction based on the improved ensemble empirical mode decomposition | |
| Zhang et al. | Flaw classification in ultrasonic guided waves signal using Wavelet Transform and PNN classifier | |
| CN102890119A (en) | Characterization and quantitative evaluation system for fatigue damage state of in-service AZ31 magnesium alloy structural member based on WPT (Wavelet Packet Transform) strategy and DF (Dual-Frequency) strategy | |
| Wang | Research on application of wavelet denoising into broken wire damage detection of mine steel wire rope | |
| Shi et al. | Wavelet de-noising method analysis of pipeline magnetic flux leakage in-line inspection based on coefficient of variation | |
| Kabiri et al. | Automobile independent fault detection based on acoustic emission using wavelet | |
| KR20210034171A (en) | Diagnosis method for wedge of a stator of a generator | |
| Cui et al. | Feature Extraction Method of Converter Transformer Vibration Signal Based on Multi-feature Fusion | |
| Mahidhar et al. | Understanding of Incipient discharges in Transformer Insulation by reconstruction of Digital Twins for the discharges using Generative Adversarial Networks |
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 |