CN106228107B - A kind of supersonic guide-wave broken rail monitoring method based on independent component analysis - Google Patents
A kind of supersonic guide-wave broken rail monitoring method based on independent component analysis Download PDFInfo
- Publication number
- CN106228107B CN106228107B CN201610529802.0A CN201610529802A CN106228107B CN 106228107 B CN106228107 B CN 106228107B CN 201610529802 A CN201610529802 A CN 201610529802A CN 106228107 B CN106228107 B CN 106228107B
- Authority
- CN
- China
- Prior art keywords
- matrix
- data matrix
- isolated component
- data
- vector
- 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
Classifications
-
- 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
- G06F18/2134—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on separation criteria, e.g. independent component analysis
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61K—AUXILIARY EQUIPMENT SPECIALLY ADAPTED FOR RAILWAYS, NOT OTHERWISE PROVIDED FOR
- B61K9/00—Railway vehicle profile gauges; Detecting or indicating overheating of components; Apparatus on locomotives or cars to indicate bad track sections; General design of track recording vehicles
- B61K9/08—Measuring installations for surveying permanent way
- B61K9/10—Measuring installations for surveying permanent way for detecting cracks in rails or welds thereof
-
- 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
- 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
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4454—Signal recognition, e.g. specific values or portions, signal events, signatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/023—Solids
- G01N2291/0234—Metals, e.g. steel
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Acoustics & Sound (AREA)
- Mechanical Engineering (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The supersonic guide-wave broken rail monitoring method based on independent component analysis that the invention discloses a kind of.The monitoring signals data that installation ultrasonic transducer acquisition acquisition in region both ends is monitored by being mounted on rail are handled: creation analysis data matrix, initial analysis data matrix is formed by testing data matrix and by reference data matrix, successively carry out centralization and whitening processing, it is decomposed for the analysis data matrix after albefaction, each isolated component generates separation vector iterative calculation and obtains initially-separate vector；It is arranged to make up separation matrix and calculates to obtain weight matrix and isolated component matrix, set reference vector, calculate and obtain its related coefficient, be compared with alarm threshold value, obtain broken rail result and alarm.The present invention can be realized the accurate differentiation under strong noise background for ultrasonic guided wave signals, high sensitivity, and robustness is good.
Description
Technical field
The present invention relates to a kind of supersonic guide-wave monitoring methods, more particularly, to a kind of super based on independent component analysis
Guided Waves broken rail monitoring method.
Background technique
With the gradually quickening of railway construction in China, the monitoring of railway track structure integrality also becomes further important, I
The current most of route of state is assembled with automatic block system, and the core of automatic block system is " track circuit ", i.e., and two
It alives in rail, when train enters block section, the circuit in two tracks is connected car body, so that in block section
Track circuit " short circuit ", the occupied state of route is judged with this, provides information for subsequent train, while can also sentence roughly
The integrality of disconnected track structure.However rely on track circuit monitor rail break presence following problems: track circuit originally experience railway roadbed ginseng
Number situation is affected, short-circuit, red between rail often occurs for the small and southern some areas with heavy rainfall of railway roadbed leakage impedance
The fault conditions such as light belt wrong report；Currently, due to technical reason, China's major part single-track railway is all Semiautomatic block system, i.e.,
The installation of rail-free circuit arrangement.With the application of the BEI-DOU position system of China's independent research, new route and train are all pacified
The intelligent traveling positioning device of the China Zhuan Liao independent research, i.e. automatic block system of new generation, track circuit will be washed in a pan gradually
It eliminates.
The above status shows a set of dedicated railway track structure integrity monitoring systems (broken rail monitoring system) of urgent need,
The structural intergrity of real time on-line monitoring track, it is accurate to grasp railway infrastructure state, it scientifically carries out quality control and protects
Hinder traffic safety.Supersonic guide-wave monitoring technology is a kind of one of more potential monitoring technology.However making an uproar by force in railway operation
Under sound background, guided wave signals identification becomes abnormal difficult.The invention of Patent No. CN201410246903 proposes a kind of based on super
The real-time broken rail of guided Waves detects positioning system, but it uses relative magnitude and the absolute amplitude of signal to determine whether
Broken rail is difficult to realize in the stronger situation of ambient noise, does not also refer to implementation result in patent.
The invention of Patent No. CN201210342445 proposes a kind of high-speed railway rail based on supersonic guide-wave and wireless network
Health monitoring systems.Noise reduction is carried out using wavelet transformation in text, Hilbert transform extraction envelope is reused and is differentiated, together
Sample, when signal-to-noise ratio is lower than to a certain degree, this method can not also differentiate whether monitoring region is broken.
Summary of the invention
The object of the invention is the deficiency solved in background technology field, proposes that a kind of ultrasound based on independent component analysis is led
Wave broken rail monitoring method realizes that the track integrality based on supersonic guide-wave under strong background noise differentiates.
The invention adopts the following technical scheme:
The present invention will monitor the monitoring signals number that ultrasonic transducer acquisition acquisition is installed at region both ends by being mounted on rail
It is handled according to using following steps:
Step 1: creation analysis data matrix X, the testing data matrix D that will be obtained by the conversion of current Received Signal datac
With the reference data matrix D obtained by reference signal data conversionbInitial analysis data matrix X is formed using following formula:
Wherein, K is the flexible matrix of scale；
Step 2: it carries out centralization processing: all data in initial analysis data matrix X is subtracted to the mean value of matrix:
Wherein,Analysis data matrix after indicating centralization,Indicate the mean value of initial analysis data matrix, X is indicated
Initial analysis data matrix；
Step 3: whitening processing is carried out: the correlation in removing the analysis data matrix after centralization between observation signal
Property, the analysis data matrix after albefaction is obtained using following formula
Wherein, the analysis data matrix after changing centered on REigenvectors matrix, D is characterized value diagonal matrix；
Step 4: for the analysis data matrix after albefactionIt is decomposed, is divided into each mutually independent isolated component,
The number for presetting the isolated component of decomposition generates a separation vector at random and is iterated meter for each isolated component
It calculates, calculates and obtain initially-separate vector Wd；
Step 5: each initially-separate vector W that above-mentioned steps are obtaineddComposition separation is arranged successively as matrix column
Matrix W is calculated using the following equation to obtain weight matrix A and isolated component matrix S；
A=W-1
Wherein,Analysis data matrix after indicating albefaction；
Step 6: right in weight matrix A using each behavior signal in isolated component matrix S as an isolated component
The each weight vectors for being classified as isolated component answered set reference vector B, and calculate for each isolated component and obtain its correlation
Coefficient；
Step 7: setting alarm threshold value TH, if step 6 calculates in the related coefficient obtained, there are more than one phase relations
Number ri> TH, i=1,2,3 ..., M, then it is assumed that broken rail is alarmed, and is otherwise not considered as broken rail, is not alarmed.
Testing data matrix D in the step onecWith reference data matrix DbIt is that will acquire the reception signal number obtained
Row of one group of reception signal as matrix accordingly, and be arranged successively to form acquisition with the time.
Specifically, the data matrix D currently measuredcIt is by signal will be received in current Received Signal data as matrix
Row, and be arranged successively to be formed with the time.The row of different matrixes represents different groups of reception signal.
The reference data matrix DbReception signal data be when preliminary orbit ensures complete acquire obtain.
In the step 1, if testing data matrix DcWith reference data matrix DbCorresponding reception signal data frequency
When consistent, the element in the flexible matrix K of scale is 1.
Scale stretches matrix K in testing data matrix DcWith reference data matrix DbCorresponding reception signal data
Dispersion compensation is realized when frequency is inconsistent.
Analysis data matrix after centralization in the step 3Eigenvectors matrix R and characteristic value diagonal matrix
D is calculated using following formula:
E{XXT}=RDRT
Wherein, the transposition of subscript T representing matrix；E { } indicates operation of averaging.
The step 4 specifically:
4.1) it sets and needs the number for the isolated component estimated as M, d indicates iteration count, and when iteration starts, initialization changes
It is d=1 that generation, which counts d,；
4.2) initially-separate vector W is constructedd, WdThe column vector for being N for data amount check, N DbAnd DcMiddle signal number it
With initially-separate vector WdMiddle primary data is random real number；
4.3) it is calculated in order using the Newton iteration mode of following formula:
③Wd=Wd/‖Wd‖
In formula, E { } indicates operation of averaging,Analysis data matrix after indicating albefaction, g (x) are a non-linear letter
Number, g ' (x) indicate the derivative of g (x),Indicate initially-separate vector WdTransposition, WII time iteration is completed before expression
Initially-separate vector, I=1,2,3 ..., d-1, as d=1, I=0, WI=0, ‖ Wd‖ indicates WdMould；
Nonlinear function g (x) is calculated using the following equation:
Wherein, e is the truth of a matter of natural logrithm, and x indicates the argument of function；
If 4.4) WdReturn step 4.3 if not restraining)；
4.5) d=d+1 is enabled, if d is not more than M, return step 4.2).
The step 6 specifically:
6.1) corresponding in weight matrix A using each behavior signal in isolated component matrix S as an isolated component
Each weight vectors for being classified as isolated component set reference vector B:
Wherein, m is benchmark data matrix DbIn signal number, n be testing data matrix DcIn signal number；
6.2) it is calculated using the following equation again in reference vector B and weight matrix A between the weight vectors of each isolated component
Related coefficient:
Wherein, aiIndicate the i-th column in weight matrix A, i=1,2,3 ..., M, M is the columns of weight matrix A, is as divided
The number for the isolated component managed out；ai,jIndicate that the numerical value of the i-th column, jth row in weight matrix A, j=1,2,3 ..., N, N are power
The line number of weight matrix A,Indicate the mean value of the i-th column in weight matrix A；BjIndicate j-th of numerical value in reference vector B,Table
Show the mean value of reference vector B；riIndicate the related coefficient of the i-th column and reference vector B in weight matrix A.
The line number N of the weight matrix A is testing data matrix DcWith reference data matrix DbIn signal number it
With i.e. N=m+n.
The beneficial effects of the present invention are:
The method of the present invention can extract isolated component under strong noise background, to differentiate whether energy converter receives
Guided wave signals realize the fast and accurately differentiation whether being broken for monitoring region, high sensitivity, strong robustness.
Detailed description of the invention
Fig. 1 is the flow chart of monitoring method.
Fig. 2 is the measuring signal of benchmark signal and two kinds of situations.
Fig. 3 is the isolated component and its weight vectors isolated in matrix when not being broken.
Fig. 4 is the isolated component and its weight vectors isolated in signal matrix when being broken.
Specific embodiment
Below in conjunction with the drawings and specific embodiments, invention is further explained.
The embodiment of the present invention and its specific implementation course of work are as follows:
Embodiment installs energy converter in supersonic guide-wave monitoring implementation process, at monitoring region both ends, it is ensured that monitoring region
In complete situation, one end energy converter continuously emits one section of sinusoidal guided wave signals, and the energy converter of the other end receives.
Acquisition once comprising multiple groups reception signal as benchmark receive signal data, benchmark reception signal data in
Signal is received as row, each group is received signal, and chronologically sequence forms reference data matrix D downwardsb.In actual monitoring process
In, certain interval of time carries out one acquisition, and multiple groups receive signal as current Received Signal data when acquisition every time, currently connects
Collection of letters number is to receive signal as row, and by the multiple groups acquired every time reception signal, chronologically sequence forms testing data downwards
Matrix Dc。
The frequency of current Received Signal data and benchmark reception signal data are inconsistent, then the guided wave modal motivated is different
It causes, the flexible matrix K of a scale is needed to realize the dispersion compensation of current Received Signal data, when the two frequency is consistent, K square at this time
All elements are all 1 in battle array.
Under strong noise background, guided wave signals occur significantly to decay after long distance transmission, are finally submerged in background
In noise, it can not only judge to monitor whether region is broken from time-domain signal.Such as Fig. 2 is the actual measurement of a certain iron leg route
Data, two groups of energy converters are mounted on the web of the rail position of rail, and at a distance of 2 kilometers, signal data, Fig. 2 (b) are received on the basis of Fig. 2 (a)
Measurement data when not to be broken, Fig. 2 (c) are measurement data when being broken, in the case of three kinds, tranmitting frequency one
It causes.Both (b) and (c) measurement data comparisons in Fig. 2 can not find out apparent difference to judge to monitor whether region breaks
It splits.
Following embodiment process is handled using the method for the present invention:
Step 1: creation analysis data matrix X, the testing data matrix D that will be obtained by the conversion of current Received Signal datac
With the reference data matrix D obtained by reference signal data conversionbForm initial analysis data matrix X；
Step 2: it carries out centralization processing: all data in initial analysis data matrix X is subtracted to the mean value of matrix；
Step 3: whitening processing is carried out: the correlation in removing the analysis data matrix after centralization between observation signal
Property, the analysis data matrix after obtaining albefaction
Step 4: for the analysis data matrix after albefactionIt is decomposed, is divided into each mutually independent isolated component,
The number for presetting the isolated component of decomposition generates a separation vector at random and is iterated meter for each isolated component
It calculates, calculates and obtain initially-separate vector Wd；
Step 5: each initially-separate vector W that above-mentioned steps are obtaineddComposition separation is arranged successively as matrix column
Matrix W calculates to obtain weight matrix A and isolated component matrix S；
Step 6: Fig. 3 and Fig. 4 is the independence point for monitoring region and not occurring to be broken and isolate when being broken signal respectively
Amount and its weight vectors, it can be seen from the figure that there are the weight vectors of an isolated component when monitoring region is broken
In there are apparent step feature, the isolated component mostly come from energy converter transmitting signal, when monitoring region do not break
When splitting, which accounts for the main component of signal, and after being broken, weight shared by the isolated component is almost nil, therefore,
Occurs step feature in weight vectors.Element number is equal to the sum of all signal numbers in analysis matrix in weight vectors, by
The step signal vector B of this one standard of building is as reference vector, then calculates for each isolated component and obtain its phase relation
Number；
Step 7: when there are step features in weight vectors, then calculate in resulting related coefficient that there are some phase relations
Number is in close proximity to 1.So an alarm threshold value TH can be set, if the weight vectors of each isolated component of weight matrix A are corresponding
All related coefficients in there are more than one correlation coefficient rsi> TH, i=1,2,3 ..., M are then sounded an alarm, otherwise by setting
It is measured next time after determining interval time.
If monitoring region is not broken when measurement, after this method is handled, the weight of the isolated component isolated to
Measure no apparent step feature.The isolated component decomposed after three kinds of measurement data this method processing of Fig. 2 is as shown in figure 3, a left side
The signal of side four is four isolated components isolated, and four, right side signal is corresponding weight vectors, it can be seen that weight to
Exist in amount without apparent step feature.
If monitoring region has occurred and that fracture when measurement, after this method is handled, the power for the isolated component that sub-argument goes out
There are one or above weight vectors apparent step feature in weight vector, as shown in figure 4, first isolated component
Weight vectors there is apparent step feature, from there through the phase for calculating weight vectors and the reference vector with step feature
Relationship number can set alarm threshold value and be differentiated.
The present invention can differentiate whether energy converter receives guided wave signals under strong noise background, to differentiate monitoring region
Structural intergrity, high sensitivity, robustness are good.Above-mentioned implementation method is used only to explain the present invention, specific reality of the invention
Applying method includes but is not limited to method mentioned above, in scope of the presently claimed invention all to any modification of the invention
It belongs to the scope of protection of the present invention.
Claims (7)
1. a kind of supersonic guide-wave broken rail monitoring method based on independent component analysis, it is characterised in that will be by being mounted on rail prison
The monitoring signals data that installation ultrasonic transducer acquisition in region both ends obtains are surveyed to be handled using following steps:
Step 1: creation analysis data matrix X, the testing data matrix D that will be obtained by the conversion of current Received Signal datacWith by
The reference data matrix D that reference signal data conversion obtainsbInitial analysis data matrix X is formed using following formula:
Wherein, K is the flexible matrix of scale；
Step 2: it carries out centralization processing: all data in initial analysis data matrix X is subtracted to the mean value of matrix:
Wherein,Analysis data matrix after indicating centralization,Indicate the mean value of initial analysis data matrix, X indicates initial point
Analyse data matrix；
Step 3: carry out whitening processing: the correlation in removing the analysis data matrix after centralization between observation signal is adopted
Analysis data matrix after obtaining albefaction with following formula
Wherein, the analysis data matrix after changing centered on REigenvectors matrix, D is characterized value diagonal matrix；
Step 4: for the analysis data matrix after albefactionIt is decomposed, is divided into each mutually independent isolated component, in advance
The number for setting the isolated component decomposed generates a separation vector at random and is iterated calculating, count for each isolated component
It calculates and obtains initially-separate vector Wd；
Step 5: each initially-separate vector W that above-mentioned steps are obtaineddComposition separation matrix is arranged successively as matrix column
W is calculated using the following equation to obtain weight matrix A and isolated component matrix S；
A=W-1
Wherein,Analysis data matrix after indicating albefaction；
Step 6: corresponding in weight matrix A using each behavior signal in isolated component matrix S as an isolated component
Each weight vectors for being classified as isolated component set reference vector B, and calculate for each isolated component and obtain its phase relation
Number；
Step 7: setting alarm threshold value TH, if step 6 calculates in the related coefficient obtained, there are more than one correlation coefficient rsi>
TH, i=1,2,3 ..., M, then it is assumed that otherwise broken rail is not considered as broken rail；
The step 6 specifically:
6.1) corresponding each in weight matrix A using each behavior signal in isolated component matrix S as an isolated component
The weight vectors of isolated component are classified as, reference vector B is set:
Wherein, m is benchmark data matrix DbIn signal number, n be testing data matrix DcIn signal number；
6.2) it is calculated using the following equation the phase in reference vector B and weight matrix A between the weight vectors of each isolated component again
Relationship number:
Wherein, aiIndicate the i-th column in weight matrix A, i=1,2,3 ..., M, M is the columns of weight matrix A；ai,jIndicate weight
The numerical value of i-th column, jth row in matrix A, j=1,2,3 ..., N, N are the line number of weight matrix A,It indicates the in weight matrix A
The mean value of i column；BjIndicate j-th of numerical value in reference vector B,Indicate the mean value of reference vector B；riIt indicates in weight matrix A
The related coefficient of i-th column and reference vector B.
2. a kind of supersonic guide-wave broken rail monitoring method based on independent component analysis according to claim 1, feature exist
In: testing data matrix D in the step onecWith reference data matrix DbBe will acquire obtain reception signal data with
Row of one group of reception signal as matrix, and be arranged successively to form acquisition with the time.
3. a kind of supersonic guide-wave broken rail monitoring method based on independent component analysis according to claim 2, feature exist
In: the reference data matrix DbReception signal data be when preliminary orbit ensures complete acquire obtain.
4. a kind of supersonic guide-wave broken rail monitoring method based on independent component analysis according to claim 1, feature exist
In: in the step 1, if testing data matrix DcWith reference data matrix DbCorresponding reception signal data frequency is consistent
When, scale stretch matrix K in element be 1.
5. a kind of supersonic guide-wave broken rail monitoring method based on independent component analysis according to claim 1, feature exist
In: the analysis data matrix after the centralization in the step 3Eigenvectors matrix R and characteristic value diagonal matrix D use
Following formula is calculated:
E{XXT}=RDRT
Wherein, the transposition of subscript T representing matrix；E { } indicates operation of averaging.
6. a kind of supersonic guide-wave broken rail monitoring method based on independent component analysis according to claim 1, feature exist
In: the step 4 specifically:
4.1) it sets and needs the number for the isolated component estimated as M, d indicates iteration count, when iteration starts, initializes iteration meter
Number d is d=1；
4.2) initially-separate vector W is constructedd, WdThe column vector for being N for data amount check, N DbAnd DcThe sum of middle signal number, initially
Separate vector WdMiddle primary data is random real number；
4.3) it is calculated in order using the Newton iteration mode of following formula:
①
②
③Wd=Wd/‖Wd‖
In formula, E { } indicates operation of averaging,Analysis data matrix after indicating albefaction, g (x) are a nonlinear function,
G ' (x) indicates the derivative of g (x),Indicate initially-separate vector WdTransposition, WII time iteration is completed initial before expression
Separation vector, I=1,2,3 ..., d-1, as d=1, I=0, WI=0, ‖ Wd‖ indicates WdMould；
Nonlinear function g (x) is calculated using the following equation:
Wherein, e is the truth of a matter of natural logrithm, and x indicates the independent variable of nonlinear function g (x)；
If 4.4) WdReturn step 4.3 if not restraining)；
4.5) d=d+1 is enabled, if d is not more than M, return step 4.2).
7. a kind of supersonic guide-wave broken rail monitoring method based on independent component analysis according to claim 1, feature exist
In: the line number N of the weight matrix A is testing data matrix DcWith reference data matrix DbIn the sum of signal number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610529802.0A CN106228107B (en) | 2016-06-30 | 2016-06-30 | A kind of supersonic guide-wave broken rail monitoring method based on independent component analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610529802.0A CN106228107B (en) | 2016-06-30 | 2016-06-30 | A kind of supersonic guide-wave broken rail monitoring method based on independent component analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106228107A CN106228107A (en) | 2016-12-14 |
| CN106228107B true CN106228107B (en) | 2019-05-21 |
Family
ID=57520048
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610529802.0A Active CN106228107B (en) | 2016-06-30 | 2016-06-30 | A kind of supersonic guide-wave broken rail monitoring method based on independent component analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106228107B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107966206B (en) * | 2017-11-07 | 2019-01-04 | 华北电力大学（保定） | A kind of array signal denoising method of fiber ultrasonic sensor array |
| CN108225329B (en) * | 2017-12-28 | 2021-10-29 | 杨艳华 | Accurate indoor positioning method |
| CN108709932B (en) * | 2018-04-04 | 2021-04-06 | 西安理工大学 | Track state detection method based on ultrasonic guided wave broken track detection system |
| CN109649432B (en) * | 2019-01-23 | 2020-06-23 | 浙江大学 | System and method for monitoring integrity of steel rail of cloud platform based on guided wave technology |
| CN111694328B (en) * | 2019-03-12 | 2022-03-18 | 宁波大学 | Distributed process monitoring method based on multiple independent component analysis algorithms |
| CN113415309A (en) * | 2021-06-16 | 2021-09-21 | 西安交通大学 | Vehicle-mounted steel rail disease monitoring device based on visual analysis and working method thereof |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006208075A (en) * | 2005-01-26 | 2006-08-10 | Hitachi Ltd | Abnormality diagnosis apparatus, method and program |
| CN101927773A (en) * | 2010-08-17 | 2010-12-29 | 华南理工大学 | Blind signal separation technology-based railway track safety detection system and method |
| CN104020221A (en) * | 2014-05-30 | 2014-09-03 | 杨媛 | Real-time broken-rail detecting and positioning system based on ultrasonic guided waves |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9950715B2 (en) * | 2012-04-06 | 2018-04-24 | The Regents Of The University Of California | Air-coupled ultrasonic inspection of rails |
-
2016
- 2016-06-30 CN CN201610529802.0A patent/CN106228107B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006208075A (en) * | 2005-01-26 | 2006-08-10 | Hitachi Ltd | Abnormality diagnosis apparatus, method and program |
| CN101927773A (en) * | 2010-08-17 | 2010-12-29 | 华南理工大学 | Blind signal separation technology-based railway track safety detection system and method |
| CN104020221A (en) * | 2014-05-30 | 2014-09-03 | 杨媛 | Real-time broken-rail detecting and positioning system based on ultrasonic guided waves |
Non-Patent Citations (2)
| Title |
|---|
| A Single Probe Spatial Averaging Technique for Guided Waves and Its Application to Surface Wave Rail Inspection;Daniel Hesse et.al;《ieee transactions on ultrasonics, ferroelectrics, and frequency control》;20071130;第54卷(第1期);第2344-2356页 |
| 基于超声导波的无缝线路断轨检测***;李浩 等;《电子设计工程》;20150831;第23卷(第16期);第126-129页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106228107A (en) | 2016-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106228107B (en) | A kind of supersonic guide-wave broken rail monitoring method based on independent component analysis | |
| CN101900708B (en) | Vibration and audio signal-based high-speed train track defect detecting method | |
| CN108050396B (en) | A kind of fluid line source of leaks monitoring and positioning system and method | |
| CN105241660B (en) | High-speed rail large bridge performance test methods based on health monitoring data | |
| CN103076393B (en) | Knocking scan type bridge damage detecting system | |
| Kalhori et al. | Non-intrusive schemes for speed and axle identification in bridge-weigh-in-motion systems | |
| CN111982273B (en) | Noise monitoring method for rail transit station platform | |
| CN202404166U (en) | On-line monitoring system for vibration performance of transformer | |
| CN107621591B (en) | A kind of transmission line of electricity iteration distance measuring method based on zero mould traveling wave speed variation characteristic | |
| CN102616156B (en) | Device and method for detecting and elevating contact network state based on electrical capacity analysis | |
| KR101531641B1 (en) | A partial discharge measuring apparatus in a power cable and a method therof | |
| CN110907755A (en) | Power transmission line online monitoring fault recognition method | |
| CN105093059B (en) | A kind of transformer winding working state detecting method based on normalization singular spectrum entropy | |
| CN109116196B (en) | Intelligent power cable fault discharge sound identification method | |
| CN107356417B (en) | A kind of bolted joint damnification recognition method merging Time-Series analysis and comentropy | |
| CN106950227A (en) | A kind of composite insulator defect lossless detection method | |
| CN105137277A (en) | Diagnosis method of winding machinery state in case of sudden short circuit of transformer | |
| CN113029327B (en) | Tunnel fan embedded foundation damage identification method based on metric attention convolutional neural network | |
| CN112963740B (en) | Method for monitoring and positioning leakage of fire fighting pipeline of convertor station | |
| CN106338662A (en) | Transformer winding deformation diagnosis method based on mathematical morphology | |
| CN108520227A (en) | A kind of Bridge Structural Damage localization method of the transfer entropy based on dual sensor information | |
| CN113483877A (en) | Dynamic monitoring system based on internet load sensor | |
| CN104848973A (en) | Method for measuring pulling force of steel rope based on ultrasonic guided wave notch | |
| De Andrade et al. | Travelling wave based fault location analysis for transmission lines | |
| GB2496121A (en) | Fault location in a vehicle electrical system by time domain reflectometry |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |