CN114441646A - Full life cycle damage detection method and system for turnout rail member - Google Patents
Full life cycle damage detection method and system for turnout rail member Download PDFInfo
- Publication number
- CN114441646A CN114441646A CN202111361629.5A CN202111361629A CN114441646A CN 114441646 A CN114441646 A CN 114441646A CN 202111361629 A CN202111361629 A CN 202111361629A CN 114441646 A CN114441646 A CN 114441646A
- Authority
- CN
- China
- Prior art keywords
- signal
- damage
- acoustic emission
- independent source
- signals
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 claims abstract description 43
- 238000011084 recovery Methods 0.000 claims abstract description 21
- 238000012880 independent component analysis Methods 0.000 claims abstract description 13
- 230000004044 response Effects 0.000 claims abstract description 8
- 238000012544 monitoring process Methods 0.000 claims description 35
- 238000004458 analytical method Methods 0.000 claims description 8
- 229910000831 Steel Inorganic materials 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 239000010959 steel Substances 0.000 claims description 7
- 238000003909 pattern recognition Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 238000002604 ultrasonography Methods 0.000 abstract description 3
- 230000007547 defect Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 6
- 238000007689 inspection Methods 0.000 description 5
- 239000013307 optical fiber Substances 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000003862 health status Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000006735 deficit Effects 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000009659 non-destructive testing Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 241001391944 Commicarpus scandens Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Images
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
- G01N29/14—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 using acoustic emission techniques
-
- 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
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
-
- 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
- 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
- G01N29/48—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by amplitude comparison
Abstract
The invention discloses a method and a system for detecting the full life cycle damage of a turnout rail member, belonging to the technical field of nondestructive detection, wherein a sensor is used for acquiring the real-time data of the turnout rail member, and the real-time data is preprocessed to obtain an acquired signal; carrying out independent component analysis on the acquired signals to obtain independent source signals, and carrying out amplitude recovery on the independent source signals; judging damage according to the independent source signal after amplitude recovery, and if an acoustic emission signal exists, solving the digital characteristic of the acoustic emission signal and responding; if the acoustic emission signal does not exist, solving the nonlinear characteristic of the independent source signal after amplitude recovery and responding; and obtaining the damage condition of the turnout rail member according to different responses. The invention realizes the identification of micro cracks/micro defects by utilizing nonlinear ultrasound and realizes the detection of macro cracks by utilizing acoustic emission signals, thereby realizing the method and the system for detecting the damage of the turnout rail piece in the whole life cycle.
Description
Technical Field
The invention relates to the technical field of nondestructive testing, in particular to a method and a system for detecting the full life cycle damage of a turnout rail piece.
Background
With the increase of the running speed of the train, the increase of the axle weight and the extension of the service time, the phenomenon that the turnout rail piece is damaged becomes more and more serious. The rail damage directly threatens the safety of the train passing a fork, and the line is in a stop state to influence the running efficiency; heavy causes the train to derail, causing an unpredictable loss. Therefore, monitoring the health status of the turnout rail members is one of the important means for guaranteeing the railway operation safety.
At present, the existing rail damage detection at home and abroad mainly comprises the following methods: large-scale rail flaw detection vehicles, hand-push flaw detection vehicles, rail circuit detection methods, optical fiber detection methods, ultrasonic guided wave detection methods and the like. The detection principle is based on a linear ultrasonic detection method, and the detection method has a defect detection blind area due to the special structure of the steel rail. The track circuit is usually only suitable for detecting that the steel rail is completely broken, and fault conditions such as short circuit between rails, false alarm of red light band and the like often occur in regions with abundant rainwater in south. The optical fiber detection method has high sensitivity and is suitable for places difficult to insulate, but because the optical fiber is fragile, the optical fiber is easy to break due to factors such as bending and the like during construction, installation and maintenance. The ultrasonic guided wave detection method is a method for detecting the damage of the steel rail by utilizing the propagation characteristic of ultrasonic guided waves in a steel rail medium, belongs to a detection mode of mechanical waves, and is not easily influenced by factors such as electromagnetic interference, rail electrical parameters and the like, but the excitation and the reception of the guided waves and the dispersion characteristic in the propagation process are still important factors restricting the development of the guided wave detection method. In conclusion, most of the existing flaw detection technologies cannot meet the flaw detection requirements of high-speed railways in China.
Disclosure of Invention
The invention aims to overcome the problems of the flaw detection technology in the prior art and provides a full-life-cycle flaw detection method and system for turnout rail parts.
The purpose of the invention is realized by the following technical scheme:
the method mainly provides a full life cycle damage detection method for turnout rail parts, and comprises the following steps:
the method comprises the steps that a sensor is used for collecting real-time data of turnout rail pieces, and the real-time data are preprocessed to obtain collected signals;
carrying out independent component analysis on the acquired signals to obtain independent source signals, and carrying out amplitude recovery on the independent source signals;
judging damage according to the independent source signal after amplitude recovery, and if an acoustic emission signal exists, solving the digital characteristic of the acoustic emission signal and responding; if the acoustic emission signal does not exist, solving the nonlinear characteristic of the independent source signal after amplitude recovery and responding;
and obtaining the damage condition of the turnout rail member according to different responses.
As an option, the method further comprises:
and judging the state of the sensor according to the amplitude and the signal-to-noise ratio of the acquired signal.
As an option, the preprocessing the real-time data includes:
normalizing the real-time data using a z-score method;
carrying out high-pass filtering processing on the standardized real-time data to remove low-frequency noise in the real-time data;
and performing event interception on the real-time data after the noise is removed to obtain an acquired signal.
As an option, the performing independent component analysis on the collected signal to obtain an independent source signal, and performing amplitude recovery on the independent source signal includes:
estimating the number of independent sources of the acquired signals, and increasing dimensions to obtain the number of the independent sources meeting the estimation;
and carrying out independent component analysis on the acquired signals after the dimension is increased to obtain independent source signals, and carrying out amplitude recovery by a self-adaptive matching method.
As an option, the determining the impairment according to the independent source signal after the amplitude recovery includes:
extracting characteristic parameters of each independent source signal, wherein the characteristic parameters comprise time domain, frequency domain and time-frequency characteristics;
carrying out pattern recognition by using the characteristic parameters, further solving the digital characteristics of the acoustic emission signals if the acoustic emission signals exist, wherein the digital characteristics comprise time, energy and ringing count, and responding according to the digital characteristics;
and if the acoustic emission signal does not exist, solving the nonlinear characteristics of the independent source signal, wherein the nonlinear characteristics comprise second-order nonlinear coefficients, third-order nonlinear coefficients, main frequencies, energy ratios and the like, and responding according to the nonlinear characteristics.
As an option, the responding according to the digital characteristic includes:
and classifying by using the digital characteristics, including cracks and falling blocks, rim friction, turnout movement, temperature force release and the like, and giving an alarm when judging that the independent source signal is an acoustic emission signal generated by the cracks and falling blocks.
As an option, the responding according to the non-linear characteristic includes:
judging whether the independent signal has a nonlinear phenomenon or not by utilizing nonlinear characteristics such as second-order and third-order nonlinear coefficients, a main frequency, an energy ratio and the like;
and counting the frequency of the nonlinear phenomenon by using a sliding window, and once the frequency of the nonlinear phenomenon exceeds a system threshold value, determining that the steel rail has microcracks/micro damage, and sending an alarm by the system.
The invention also provides a full life cycle damage detection system for turnout rail parts, which comprises:
the sensor acquires real-time data of the turnout rail piece;
the monitoring extension set processes and analyzes the real-time data acquired by the sensor and sends an analysis result to the outside;
and the monitoring host receives the analysis result uploaded by the monitoring extension set and obtains the damage condition of the turnout rail piece according to different responses.
As an option, the system further comprises a monitoring center and a client, wherein the monitoring center is connected between the monitoring host and the client.
As an option, the sensor is a piezoelectric sensor.
It should be further noted that the technical features corresponding to the above options can be combined with each other or replaced to form a new technical solution.
Compared with the prior art, the invention has the beneficial effects that:
(1) the method comprises the steps of utilizing an independent component analysis method to realize separation of a damage signal and a wheel rail impact noise signal, removing noise interference of an acquired signal, improving the anti-interference capability of a system, utilizing an independent source signal obtained after independent component analysis to judge damage, and if an acoustic emission signal exists in the signal, responding by extracting the digital characteristic of the acoustic emission signal to realize real-time monitoring of serious damage of a turnout rail piece; the method has the advantages that the micro-crack/micro-defect recognition is realized by utilizing the nonlinear ultrasound, the method is more suitable for closed crack detection in the initial stage and the middle stage of the crack, the macro-crack detection is realized by utilizing the acoustic emission signal, and the method is more suitable for the detection in the final stage of the crack development, so that the full life cycle damage monitoring of the turnout rail without the monitoring blind area is realized.
(2) The state of the sensor is judged by utilizing the amplitude and the signal-to-noise ratio of the acquired signal, and if the sensor fails or the background noise is ultrahigh, fault information is sent to a monitoring center through a monitoring host, so that the sensor is monitored, and the accuracy of data is ensured.
(3) The real-time data stream collected by the sensor is filtered, the interference of low-frequency signals is removed, the signal-to-noise ratio of the collected signals can be improved, and therefore the anti-interference capability of the system is improved.
(4) Can realize patrolling and examining more accurate rail damage monitoring than the manual work, supply and gradually replace some present various damage detection methods and means to the switch region, including personnel visual inspection, the inspection of appearance of detecting a flaw, the inspection of detecting a flaw small handcart inspection and large-scale rail inspection car etc. to effectively improved switch damage relevance ratio, reduced all kinds of inspection maintenance equipment and personnel's input.
(5) The system can realize the conversion from 'after alarm' to 'before alarm' of the damage of the turnout rail piece. When the health state of the turnout is abnormal, related departments can be prompted to pay key attention, and the related departments can be helped to make turnout overhaul plans, so that the pertinence of turnout overhaul is improved, and the risk of train accidents caused by rail damage is reduced.
Drawings
FIG. 1 is a flow chart of a method for detecting the full life cycle damage of a turnout rail member according to the present invention;
FIG. 2 is a flow chart of a method for pre-processing real-time data in accordance with the present invention;
fig. 3 is a schematic view of a full life cycle flaw detection system for a switch rail member of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that directions or positional relationships indicated by "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", and the like are directions or positional relationships described based on the drawings, and are only for convenience of description and simplification of description, and do not indicate or imply that the device or element referred to must have a specific orientation, be configured and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly stated or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Furthermore, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The invention mainly utilizes the independent source signal obtained after the independent component analysis, if the signal has the acoustic emission signal, the signal can respond by extracting the digital characteristic of the acoustic emission signal, thereby realizing the real-time monitoring of the serious damage of the turnout rail piece, having the characteristics of strong anti-interference performance and sensitivity to microcracks/microdefects, and realizing the monitoring of the turnout rail piece whole life cycle damage without the monitoring blind zone by analyzing the nonlinear characteristic of the damage signal.
Example 1
In an exemplary embodiment, as shown in fig. 1, there is provided a switch rail member full life cycle impairment detection method, the method comprising:
the method comprises the steps that a sensor is used for collecting real-time data of turnout rail pieces, and the real-time data are preprocessed to obtain collected signals;
carrying out independent component analysis on the acquired signals to obtain independent source signals, and carrying out amplitude recovery on the independent source signals;
judging damage according to the independent source signal after amplitude recovery, and if the acoustic emission signal exists, solving the digital characteristic of the acoustic emission signal and responding; if the acoustic emission signal does not exist, solving the nonlinear characteristic of the independent source signal after amplitude recovery and responding;
in particular, an acoustic emission signal refers to a transient strain energy released by a material during deformation or crack propagation, and this transient energy propagates in a waveguide and forms a stress wave. The technology for identifying the material damage by using the acoustic emission signals is called an acoustic emission technology, is an emerging modern nondestructive testing technology, can evaluate the dynamic characteristics of cracks, and is very suitable for detecting the rail damage in a railway. In short, the acoustic emission technology is to monitor the cracks and evaluate the health status of the rail by using the acoustic emission signals generated by the cracks of the rail.
Furthermore, the existence of the acoustic emission signal does not necessarily represent that the crack is generated, the material deformation also generates the acoustic emission signal, but the acoustic emission signals of the deformation and the crack have different characteristics, and whether the acoustic emission signal is generated by the crack can be further confirmed through the signal characteristics; secondly, the acoustic emission signals do not exist and represent no damage, the frequency and the amplitude of the acoustic emission are low at the initial stage of crack generation, and the acoustic emission signals can not be collected by the sensor.
Therefore, whether the acoustic emission signals exist in the independent source signals is analyzed, if yes, acoustic emission judgment logic is executed, namely, whether the acoustic emission signals are the acoustic emission signals generated by the cracks is judged by utilizing parameter analysis and pattern recognition, and if the acoustic emission signals are the acoustic emission signals generated by the cracks, an alarm is sent; if the acoustic emission signal is a non-crack generation acoustic emission signal, no alarm is issued. When the acoustic emission signal does not exist in the independent source signal, nonlinear ultrasonic judgment logic is utilized, and the nonlinear ultrasonic is used for identifying the micro-damage according to the nonlinear phenomena of harmonic waves, subharmonic waves, frequency drift and the like generated by the excitation signal at the micro-crack/micro-damage position.
In short, the micro-crack/micro-defect identification is realized by using the nonlinear ultrasound (the detection is more suitable for the closed crack in the early stage and the middle stage of the crack), and the macro-crack detection is realized by using the acoustic emission signal (the detection is more suitable for the crack in the late stage of the development). Therefore, the method for detecting the damage of the turnout rail member in the whole life cycle is realized.
Further, the damage condition of the turnout rail piece is obtained according to different responses. Specifically, because the collected real-time data may contain the damage signal and the wheel-rail impact noise signal of the turnout rail piece, the method utilizes an independent component analysis method to realize the separation of the damage signal and the wheel-rail impact noise signal, thereby removing the noise interference of the collected signal and improving the anti-interference capability of the system, utilizes an independent source signal obtained after the independent component analysis to judge the damage, and can respond by extracting the digital characteristic of the acoustic emission signal if the acoustic emission signal exists in the signal to realize the real-time monitoring of the serious damage of the turnout rail piece.
Example 2
Based on embodiment 1, there is provided a method for detecting a full life cycle damage of a turnout rail member, as shown in fig. 2, where the preprocessing the real-time data includes:
normalizing the real-time data using a z-score method;
carrying out high-pass filtering processing on the standardized real-time data to remove low-frequency noise in the real-time data;
and performing event interception on the real-time data after the noise is removed to obtain an acquired signal.
Specifically, the real-time data stream collected by the sensor is filtered, the interference of low-frequency signals is removed, and the signal-to-noise ratio of the collected signals can be improved, so that the anti-interference capability of the system is improved.
Further, the method further comprises: and judging the state of the sensor according to the amplitude and the signal-to-noise ratio of the acquired signal. Specifically, the state of the sensor is judged by using the amplitude and the signal-to-noise ratio of the acquired signal, and if the sensor fails or the background noise is ultrahigh, fault information is sent out, so that the sensor is monitored, and the accuracy of data is ensured.
Example 3
Based on the above embodiments, a method for detecting a full life cycle damage of a turnout rail member is provided, where the determining of the damage according to an independent source signal after amplitude recovery includes:
extracting characteristic parameters of each independent source signal, wherein the characteristic parameters comprise time domain, frequency domain and time-frequency characteristics;
carrying out pattern recognition by using the characteristic parameters, further solving the digital characteristics of the acoustic emission signals if the acoustic emission signals exist, wherein the digital characteristics comprise time, energy and ringing count, and responding according to the digital characteristics;
and if the acoustic emission signal does not exist, solving the nonlinear characteristics of the independent source signal, wherein the nonlinear characteristics comprise second-order nonlinear coefficients, third-order nonlinear coefficients, main frequencies, energy ratio and the like, and responding according to the nonlinear characteristics.
Example 4
Based on embodiment 3, there is provided a method for detecting a full-life-cycle damage of a turnout rail member, wherein the responding according to the digital characteristics comprises:
and classifying by using the digital characteristics, including cracks and falling blocks, rim friction, turnout movement, temperature force release and the like, and giving an alarm when judging that the independent source signal is an acoustic emission signal generated by the cracks and falling blocks.
Further, the responding according to the nonlinear characteristic includes:
judging whether the independent signal has a nonlinear phenomenon or not by utilizing nonlinear characteristics such as second-order and third-order nonlinear coefficients, a main frequency, an energy ratio and the like;
and counting the frequency of the nonlinear phenomenon by using a sliding window, and once the frequency of the nonlinear phenomenon exceeds a system threshold value, determining that the steel rail has microcracks/micro damage, and sending an alarm by the system.
Example 5
In this embodiment, a switch rail member full life cycle damage detection system is provided, as shown in fig. 3, the system comprising:
the sensor collects real-time data of the turnout rail piece, is used for monitoring the turnout rail piece damage, the rail environment, video shooting and the like, is deployed at rail base angle positions of the switch rail, the center rail, the wing rail and the stock rail, and can realize full coverage of monitoring the turnout area rail piece damage.
And the monitoring extension set processes and analyzes the real-time data acquired by the sensor, performs independent source number estimation, dimension increasing processing, amplitude recovery and the like on the acquired signals to obtain an analysis result, and transmits the analysis result outwards.
The monitoring extension also carries out damage judgment according to the independent source signal after amplitude recovery, and if the acoustic emission signal exists, the digital characteristic of the acoustic emission signal is solved and response is carried out; and if the acoustic emission signal does not exist, solving the nonlinear characteristic of the independent source signal after the amplitude recovery and responding. Specifically, the monitoring extension is deployed beside a monitored turnout rail and comprises a data acquisition module, a data processing module, an industrial switch, a photoelectric converter, a lightning protection module with an auxiliary function and a power module, wherein the monitoring extension is responsible for processing data acquired by a sensor and sending a processing result to a monitoring host. In the figure, the monitoring extension sets 1 and 2 have the same functions, and the number of the specific monitoring extension sets is selected according to actual requirements.
And the monitoring host receives the analysis result uploaded by the monitoring extension set and obtains the damage condition of the turnout rail piece according to different responses.
Further, as shown in fig. 3, the system further includes a monitoring center and a client, where the monitoring center is connected between the monitoring host and the client.
The monitoring host is used for storing and managing data transmitted by the monitoring extension set and issuing monitoring information to the monitoring center and the connected client. The monitoring center is arranged indoors and is responsible for storing and managing data transmitted by the monitoring host and sending monitoring information to the clients at all levels. The client may receive information including switch information, sensor deployment information, and rail health status information.
Further, the sensor comprises a piezoelectric sensor.
The above detailed description is for the purpose of describing the invention in detail, and it should not be construed that the detailed description is limited to the description, and it will be apparent to those skilled in the art that various modifications and substitutions can be made without departing from the spirit of the invention.
Claims (10)
1. A full life cycle damage detection method for a turnout rail member, the method comprising:
the method comprises the steps that a sensor is used for collecting real-time data of turnout rail pieces, and the real-time data are preprocessed to obtain collected signals;
carrying out independent component analysis on the acquired signals to obtain independent source signals, and carrying out amplitude recovery on the independent source signals;
judging damage according to the independent source signal after amplitude recovery, and if an acoustic emission signal exists, solving the digital characteristic of the acoustic emission signal and responding; if the acoustic emission signal does not exist, solving the nonlinear characteristic of the independent source signal after amplitude recovery and responding;
and obtaining the damage condition of the turnout rail member according to different responses.
2. The method of claim 1, wherein the method further comprises:
and judging the state of the sensor according to the amplitude and the signal-to-noise ratio of the acquired signal.
3. The method for detecting full-life-cycle damage to switch rail members as claimed in claim 1, wherein said preprocessing said real-time data comprises:
normalizing the real-time data using a z-score method;
carrying out high-pass filtering processing on the standardized real-time data to remove low-frequency noise in the real-time data;
and performing event interception on the real-time data after the noise is removed to obtain an acquired signal.
4. The method for detecting the full-life-cycle damage of the turnout rail member according to claim 1, wherein the independent component analysis of the collected signal to obtain an independent source signal and the amplitude recovery of the independent source signal comprises:
estimating the number of independent sources of the acquired signals, and increasing dimensions to obtain the number of the independent sources meeting the estimation;
and carrying out independent component analysis on the signals after the dimension is increased to obtain independent source signals, and carrying out amplitude recovery by a self-adaptive matching method.
5. The method for detecting the full-life damage of the turnout rail member according to claim 4, wherein the judging the damage according to the independent source signal after the amplitude is recovered comprises the following steps:
extracting characteristic parameters of each independent source signal, wherein the characteristic parameters comprise time domain, frequency domain and time-frequency characteristics;
carrying out pattern recognition by using the characteristic parameters, further solving the digital characteristics of the acoustic emission signals if the acoustic emission signals exist, wherein the digital characteristics comprise time, energy and ringing count, and responding according to the digital characteristics;
and if the acoustic emission signal does not exist, solving the nonlinear characteristics of the independent source signal, wherein the nonlinear characteristics comprise second-order nonlinear coefficients, third-order nonlinear coefficients, main frequencies, energy ratio and the like, and responding according to the nonlinear characteristics.
6. The method of claim 5, wherein said responding according to said numerical signature comprises:
and classifying by using the digital characteristics, including cracks and falling blocks, rim friction, turnout movement, temperature force release and the like, and giving an alarm when judging that the independent source signal is an acoustic emission signal generated by the cracks and falling blocks.
7. The method of claim 5, wherein said responding according to said non-linear characteristic comprises:
judging whether the independent signal has a nonlinear phenomenon or not by utilizing nonlinear characteristics such as second-order and third-order nonlinear coefficients, a main frequency, an energy ratio and the like;
and counting the frequency of the nonlinear phenomenon by using a sliding window, and once the frequency of the nonlinear phenomenon exceeds a system threshold value, determining that the steel rail has microcracks/micro damage, and sending an alarm by the system.
8. A switch rail member full life cycle damage detection system, said system comprising:
the sensor acquires real-time data of the turnout rail piece;
the monitoring extension set processes and analyzes the real-time data acquired by the sensor and sends an analysis result to the outside;
and the monitoring host receives the analysis result uploaded by the monitoring extension set and obtains the damage condition of the turnout rail member according to different responses.
9. The switch rail member full life cycle damage detection system of claim 8, further comprising a monitoring center and a client, wherein said monitoring center is connected between said monitoring host and said client.
10. The switch rail member full life cycle damage detection system of claim 8, wherein said sensor is a piezoelectric sensor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111361629.5A CN114441646A (en) | 2021-11-17 | 2021-11-17 | Full life cycle damage detection method and system for turnout rail member |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111361629.5A CN114441646A (en) | 2021-11-17 | 2021-11-17 | Full life cycle damage detection method and system for turnout rail member |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114441646A true CN114441646A (en) | 2022-05-06 |
Family
ID=81364567
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111361629.5A Pending CN114441646A (en) | 2021-11-17 | 2021-11-17 | Full life cycle damage detection method and system for turnout rail member |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114441646A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101806778A (en) * | 2010-03-05 | 2010-08-18 | 北京工业大学 | Method for non-linear ultrasonic online detection of early fatigue damage to metal material |
| CN104359977A (en) * | 2014-10-22 | 2015-02-18 | 北京理工大学 | Acoustic surface wave high-order nonlinear parameter representation method for bending fatigue state of metal plate |
| KR101716877B1 (en) * | 2016-06-09 | 2017-03-15 | 세종대학교산학협력단 | Apparatus and method for detecting fatigue crack using nonlinear ultrasonic based on self- piezoelectric sensing |
| CN106596735A (en) * | 2016-12-09 | 2017-04-26 | 四川西南交大铁路发展股份有限公司 | Denoising and feature extraction method and system for acoustic emission signals of rail cracks |
| CN112697877A (en) * | 2020-11-07 | 2021-04-23 | 西南交通大学 | Turnout steel rail damage detection method based on nonlinear ultrasonic guided waves |
-
2021
- 2021-11-17 CN CN202111361629.5A patent/CN114441646A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101806778A (en) * | 2010-03-05 | 2010-08-18 | 北京工业大学 | Method for non-linear ultrasonic online detection of early fatigue damage to metal material |
| CN104359977A (en) * | 2014-10-22 | 2015-02-18 | 北京理工大学 | Acoustic surface wave high-order nonlinear parameter representation method for bending fatigue state of metal plate |
| KR101716877B1 (en) * | 2016-06-09 | 2017-03-15 | 세종대학교산학협력단 | Apparatus and method for detecting fatigue crack using nonlinear ultrasonic based on self- piezoelectric sensing |
| CN106596735A (en) * | 2016-12-09 | 2017-04-26 | 四川西南交大铁路发展股份有限公司 | Denoising and feature extraction method and system for acoustic emission signals of rail cracks |
| CN112697877A (en) * | 2020-11-07 | 2021-04-23 | 西南交通大学 | Turnout steel rail damage detection method based on nonlinear ultrasonic guided waves |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN204689281U (en) | For the lift management system that elevator faults is diagnosed in advance | |
| CN106441893B (en) | Train rolling bearing fault vibrates differentiating method with impurity | |
| CN202038323U (en) | Online operation status detection display system for urban mass transit | |
| CN108848571B (en) | Rail transit safety monitoring system and monitoring method based on MEMS sensor | |
| CN105000032A (en) | Digitization method for railway vehicle bearing acoustic detection system and implementation device for digitization method | |
| CN211401691U (en) | Different-sound rail bottom acoustic diagnosis device for driving mechanism of running part of motor train unit | |
| CN104691575A (en) | Online rail fault diagnosis system and method | |
| CN106574863A (en) | Power equipment sound diagnosis system | |
| CN106679999A (en) | Built-in-compartment high-speed train running part online fault detection device | |
| CN103175897B (en) | A kind of high-speed switch hurt recognition methods based on vibration signal end-point detection | |
| CN113988326A (en) | Subway equipment maintenance optimization method and system | |
| CN111055881A (en) | Wheel-rail interface damage evolution monitoring method based on noise signals | |
| CN114166943A (en) | Active rail damage monitoring method and terminal based on nonlinear ultrasonic waves | |
| CN108709932A (en) | A kind of track condition detection method based on supersonic guide-wave broken rail detecting system | |
| CN114660181A (en) | Safety monitoring system, early warning system and detection method based on acoustic emission sensor | |
| CN112666430B (en) | Intelligent fault detection method and system for voiceprint of transformer | |
| CN104309642A (en) | High-speed turnout crack monitoring device and method based on vibration mode analysis technology | |
| CN108111583B (en) | Bogie rotating part safety monitoring system based on wireless sensor network | |
| CN114441646A (en) | Full life cycle damage detection method and system for turnout rail member | |
| CN111301489A (en) | Method for monitoring track cracks on line | |
| CN114655279A (en) | Real-time monitoring method for health state of railway turnout | |
| CN109572757B (en) | Method and device for detecting and positioning railway falling rocks | |
| CN107664662B (en) | Long-distance steel rail damage detector | |
| CN204210490U (en) | Based on the high-speed switch crackle monitoring device of vibration-mode analysis technology | |
| CN114084198A (en) | Train state identification and warning system and method based on distributed sound wave sensing |
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 |