CN109142524A - A kind of track damage detecting method, device and equipment - Google Patents
A kind of track damage detecting method, device and equipment Download PDFInfo
- Publication number
- CN109142524A CN109142524A CN201810922427.5A CN201810922427A CN109142524A CN 109142524 A CN109142524 A CN 109142524A CN 201810922427 A CN201810922427 A CN 201810922427A CN 109142524 A CN109142524 A CN 109142524A
- Authority
- CN
- China
- Prior art keywords
- detection signal
- characteristic value
- track
- signal
- train
- 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
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
- G01N29/045—Analysing solids by imparting shocks to the workpiece and detecting the vibrations or the acoustic waves caused by the shocks
Landscapes
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a kind of track defect detection methods, comprising: the detection signal in acquisition travelling process of train, wherein the detection signal includes vibration acceleration signal and/or impact signal；Feature extraction is carried out to the detection signal and obtains characteristic value；The size for comparing the characteristic value and preset threshold, judges whether the characteristic value exceeds the preset threshold；If exceeding, the hurt type of track is determined according to the characteristic value.The track defect detection method can accurately detect track with the presence or absence of hurt, it is ensured that the accuracy and reliability of track defect detection effectively increase rail safety and train operational safety.The invention also discloses a kind of track defect detection device and equipment, all have above-mentioned technical effect.
Description
Technical field
The present invention relates to track management field, in particular to a kind of track damage detecting method；Further relate to a kind of track wound
Damage detection device and equipment.
Background technique
Device of the track as carrying train load, quality, the quality of state directly influence the operational safety of train.
For this reason, it may be necessary to detect to track, with timely discovery damage, damage is repaired, avoids causing train operation since track damages
Accident.Currently, the mode that track detecting is taken mostly passes through track checking car or defectoscope is detected, and still, above-mentioned detection side
Formula need to be implemented in the period of no train operation, and detection is primary at regular intervals, cause its detection real-time poor, can not be true
Guarantor has found in time and repairs track defect.Alternatively, obtaining orbital image by the vision instrument on train, and then analyze trajectory diagram
As realizing track detecting, although the track detecting mode improves the real-time of track detecting to a certain extent,
Testing cost is higher and detection accuracy is lower, for example, can not detect the internal flaw of track, the blind crack on surface etc.,
To be unable to ensure the accuracy of testing result, track quality not can guarantee, and make train operation there are security risks.
Therefore, a kind of track defect detection scheme how is provided, while realizing real-time track detection, it is ensured that track detecting
Accuracy be those skilled in the art's technical problem urgently to be resolved.
Summary of the invention
The object of the present invention is to provide a kind of track defect detection methods, while real-time track detection may be implemented, really
The accuracy for protecting track detecting, improves the safety of train operation；It is a further object of the present invention to provide a kind of inspections of track defect
Device and equipment are surveyed, above-mentioned technical effect is all had.
In order to solve the above technical problems, the present invention provides a kind of track defect detection methods, comprising:
Acquire travelling process of train in detection signal, wherein the detection signal include vibration acceleration signal and/or
Impact signal；
Feature extraction is carried out to the detection signal and obtains characteristic value；
The size for comparing the characteristic value and preset threshold, judges whether the characteristic value exceeds the preset threshold；
If exceeding, the hurt type of track is determined according to the characteristic value.
Optionally, the detection signal in the acquisition travelling process of train, comprising:
The detection signal of multiple positions of train described in synchronous acquisition.
Optionally, further includes:
The being associated property of detection signal is analyzed and verifies the hurt type based on the analysis results.
It is optionally, described that the being associated property of detection signal is analyzed, comprising:
The left wheel of the train arrived according to synchronous acquisition and the detection signal of right wheel, judge the left wheel
The detection signal and the detection signal of the right wheel characteristic value whether occurs simultaneously beyond the default threshold
The case where value.
It is optionally, described that the being associated property of detection signal is analyzed, comprising:
The front vehicle wheel of the train arrived according to synchronous acquisition and the detection signal of rear wheel, judge the front vehicle wheel
The detection signal and it is default when delay the detection signal of the rear wheel characteristic value whether occur beyond institute
The case where stating preset threshold.
It is optionally, described that characteristic value is obtained to detection signal progress feature extraction, comprising:
Extract the detection temporal signatures value of signal and/or one or more in frequency domain character value.
In order to solve the above technical problems, the present invention also provides a kind of track defect detection devices, comprising:
Acquisition module, for acquiring the detection signal in travelling process of train, wherein the detection signal includes that vibration adds
Speed signal and/or impact signal；
Extraction module obtains characteristic value for carrying out feature extraction to the detection signal；
Analysis module judges whether the characteristic value exceeds institute for the size of the characteristic value and preset threshold
State preset threshold；
Determining module determines track according to the characteristic value if exceeding the preset threshold for the characteristic value
Hurt type.
Optionally, the acquisition module is specifically used for:
The detection signal of multiple positions of train described in synchronous acquisition.
Optionally, further includes:
Validating module, for analyzing the being associated property of detection signal and verifying the hurt class based on the analysis results
Type.
In order to solve the above technical problems, the present invention also provides a kind of track defect detection devices, comprising:
Sensor, for acquiring the detection signal in travelling process of train, wherein the detection signal includes that vibration accelerates
Spend signal and/or impact signal；
Processor obtains characteristic value for carrying out feature extraction to the detection signal, and the characteristic value and pre-
If the size of threshold value, judge whether the characteristic value exceeds the preset threshold, if exceeding, is hurt according to the characteristic value
Pattern-recognition is damaged, determines the hurt type of track.
Track defect detection method provided by the present invention, comprising: the detection signal in acquisition travelling process of train,
In, the detection signal includes vibration acceleration signal and/or impact signal；Feature extraction is carried out to the detection signal to obtain
Characteristic value；The size for comparing the characteristic value and preset threshold, judges whether the characteristic value exceeds the preset threshold；If super
Out, then the hurt type of track is determined according to the characteristic value.
Tradition detects the visual detection method of track defect by vision quasi-instrument, according to the figure of the raceway surface got
As carrying out hurt analysis.Its image it is computationally intensive, image analysis is easy to be influenced by external environment, such as the foreign matter on track,
And it is only able to detect the hurt on track surface layer, and can not know the defect of track interior, the accuracy for causing track defect to detect
Lower with reliability, making train operation, there are security risks.
It compares and above-mentioned visual detection method, track defect detection method provided by the present invention is accelerated by vibration
Degree sensor acquires the vibration acceleration signal in travelling process of train and/or acquires travelling process of train by shock transducer
In impact signal, and according to the vibration acceleration signal and/or impact signal to track defect whether differentiates.Due to vibration
Dynamic acceleration signal and impact signal not only can reflect the hurt situation on track surface layer, but also can embody the defect feelings of track interior
Condition, therefore, through the invention provided by track defect detection method can comprehensively, accurately detect track with the presence or absence of wound
Damage, it is ensured that the accuracy and reliability of track defect detection, to effectively increase rail safety and train operational safety.
Track defect detection device and equipment provided by the present invention, all have above-mentioned technical effect.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to institute in the prior art and embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without creative efforts, can also obtain according to these attached drawings
Obtain other attached drawings.
Fig. 1 is the flow diagram of track defect detection method provided by the embodiment of the present invention；
Fig. 2 is the schematic diagram of track defect detection device provided by the embodiment of the present invention；
Fig. 3 is the schematic diagram of track defect detection device provided by the embodiment of the present invention.
Specific embodiment
Core of the invention is to provide a kind of track defect detection method, while real-time track detection may be implemented, really
The accuracy for protecting track detecting, improves the safety of train operation；Another core of the invention is to provide a kind of track defect inspection
Device and equipment are surveyed, above-mentioned technical effect is all had.
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Referring to FIG. 1, Fig. 1 is the flow diagram of track defect detection method provided by the embodiment of the present invention, reference
Fig. 1 is it is found that the track defect detection method may include:
S10: acquisition travelling process of train in detection signal, wherein the detection signal include vibration acceleration signal and/
Or impact signal；
Specifically, being real-time detection track defect and the accurate detection for realizing track defect, can install ON TRAINS
Vibration acceleration sensor and/or shock transducer, and then during train driving, by vibration acceleration sensor and/
Or shock transducer acquires corresponding vibration acceleration signal and/or impact signal.Wherein, train can only install above-mentioned sensing
Any one of device, it can only installation vibration acceleration sensor, to acquire train using the vibration acceleration sensor
Wheel and vibration acceleration signal when rail contact when driving, and then judge whether track is deposited according to the vibration acceleration signal
In hurt；Or can also only installation shock transducer, then pass through the shock transducer acquisition train driving during rush
Hit signal.Certainly, preferable situation is to install above-mentioned two classes sensor simultaneously on train, to vibration acceleration signal and impact
Signal is acquired, analyzes, to achieve the purpose that detect track defect more accurately.And accelerate for specifically acquiring vibration
Degree signal still acquire impact signal, also or the two acquires, and the present invention does not do unique restriction, can in conjunction be actually needed into
The setting of row otherness.
Optionally, the detection signal in above-mentioned acquisition travelling process of train may include: multiple positions of synchronous acquisition train
The detection signal set.
Specifically, the sensor can be installed respectively in each wheel in front, rear, left and right of the same bogie of train；Or
Person can also be respectively mounted the sensor in the different bogies of train；Or above-mentioned sensing can be also installed in different vehicle
Device.Thus the detection signal of multiple positions using each the sensor synchronous acquisition train, and then according to multiple position
It detects signal and carries out hurt judgement.Wherein, for the specific form of sensor, the application is equally without limiting.Except can be with
It is independent outside the sensor, it can also be using the composite sensing for being packaged with shock transducer and vibration acceleration sensor
Device.
S20: feature extraction is carried out to detection signal and obtains characteristic value；
Specifically, can carry out feature extraction on the basis of collecting above-mentioned detection signal to detection signal, obtain spy
Value indicative, further to execute subsequent operation.Wherein, the characteristic value for detecting signal may include temporal signatures value and frequency domain character
Value, temporal signatures value and frequency domain character value separately include multiclass feature value again, as temporal signatures value comprising maximum value, peak-to-peak value,
Virtual value, kurtosis, rise time and Ring-down count；Frequency domain character value includes crest frequency and frequency mass center.It, can in practical application
It is one or more in above-mentioned all multiple characteristic values to extract, or can also all extract.It can integrate and extract workload, differentiate
The factors such as precision determine the concrete type and quantity for the characteristic value extracted.In addition, the above-mentioned characteristic value referred to, can also be and pass through
The characteristic value that the artificial intelligence approach of machine learning class is excavated and trained, is such as trained using artificial neural network
The characteristic value arrived.
Optionally, it is above-mentioned to detection signal carry out feature extraction obtain characteristic value may include: extract detection signal when
It is one or more in characteristic of field value and/or frequency domain character value.
Specifically, the present embodiment only extracts the partial feature value in detection signal, for example, mentioning when carrying out characteristics extraction
Take the peak-to-peak value in the temporal signatures value of detection signal；Or respectively extract detection signal temporal signatures value in maximum value with
Frequency mass center in frequency domain character value.One in the temporal signatures value and/or frequency domain character value of signal is detected by the extraction
Or the mode of multinomial characteristic value, it can effectively simplify the operating quantity of extraction and the differentiation of subsequent characteristics value.
In addition, to reject train faults itself, such as wheel tread removing, scratch or bearing fault, gear distress to rail
The interference of road hurt detection accuracy.Detection signal is being carried out before feature extraction obtains characteristic value, it can be first to collecting
Detection signal be filtered, with consider except detection signal in periodic signal because the periodic signal is often as arranging
What vehicle faults itself generated.Further, signal enhanced processing is carried out to filtered detection signal, reduces train as far as possible certainly
Barrier of dieing detects the influence of accuracy to track defect.
S30: whether the size of comparative feature value and preset threshold, judging characteristic value exceed preset threshold；
Specifically, the characteristic value extracted is preset with corresponding after extracting corresponding characteristic value in detection signal
Threshold value is compared, and whether judging characteristic value exceeds corresponding characteristic threshold value.So-called preset threshold differentiates that track whether there is
The a reference value of hurt, for example, the peak-to-peak value of vibration acceleration is 0.5g when track is without hurt, it then can be corresponding by characteristic value
Preset threshold be set as 0.5g.
Wherein, track defect has differences the impact effect of detection signal characteristic value, may make some of which feature
The numerical value of value becomes larger, and the numerical value of other characteristic value is made to become smaller, and therefore, whether judging characteristic value exceeds the mode of preset threshold
It may include whether judging characteristic value is greater than preset threshold and whether feature is less than preset threshold, i.e. characteristic value exceeds default threshold
The case where value, had not only included the case where that characteristic value was greater than preset threshold but also had included the case where that characteristic value is less than preset threshold.
Additionally, it is to be appreciated that different types of detection signal, preset threshold corresponding to characteristic value may exist
Difference, as the corresponding preset threshold of the peak-to-peak value of vibration acceleration signal preset threshold corresponding with the peak-to-peak value of impact signal can
With difference.It therefore, need to be respectively that its adaptable preset threshold is arranged in all kinds of detection signals.
S40: if exceeding, the hurt type of track is determined according to characteristic value.
Specifically, judging characteristic value further carries out hurt pattern-recognition according to this feature value, really beyond after preset threshold
The hurt type in orbit determination road, wherein hurt type may include chip off-falling, fracture, crackle, removing, internal flaw etc..And for true
Specific method used by the hurt type in orbit determination road, the present invention is equally without limitation.For example, can be to known each failure
After the numerical value of the corresponding characteristic value of mode carries out machine learning, by the characteristic value of the detection signal of actual extracting and machine learning
Numerical value is compared, and determines hurt mode according to comparison result；Alternatively, can use multiple characteristic values of detection signal, pass through
The method of dimensionality reduction carries out hurt pattern-recognition in higher dimension, determines hurt type etc..
In conclusion track defect detection method provided by the present invention, acquires train by vibration acceleration sensor
Vibration acceleration signal in driving conditions and/or the impact signal in travelling process of train is acquired by shock transducer, and
Judge whether according to the vibration acceleration signal and/or impact signal to track defect.Due to vibration acceleration signal with
Impact signal not only can reflect the hurt situation on track surface layer, but also can embody the defect situation of track interior, therefore, pass through this
Track defect detection method provided by inventing can comprehensively, accurately detect track with the presence or absence of hurt, it is ensured that track defect
The accuracy and reliability of detection, to effectively increase rail safety and train operational safety.
It on the basis of the above embodiments, optionally, can also include: to the analysis of detection being associated property of signal and basis
Analyze check of results hurt type.
Specifically, to further ensure that accuracy that track defect type determines, can also hurt type to track into
Row is verified, to determine it is errorless whether hurt type differentiates.It such as, can be to detection when the hurt type for determining track is crack
It is analysis whether to verify the hurt type of track really for crack that signal, which is associated, so that exclude track seam can
Energy.Detection signal association analysis mode is carried out, can be believed to pass through analysis train left wheel and the detection of opposite right wheel
Number with the presence or absence of association, or can also be whether to be deposited by the front vehicle wheel for analyzing train the same side and the detection signal of rear wheel
It is being associated with, and then it is errorless to judge whether hurt type determines.It is, of course, also possible to using other being associated property of mode analyses.
Optionally, above-mentioned to detection being associated property of signal analysis, it may include: a left side for the train arrived according to synchronous acquisition
Whether the detection signal of wheel and right wheel, the detection signal for analyzing left wheel with the detection signal of right wheel occur feature simultaneously
The case where value is beyond preset threshold.
Specifically, since whole track is spliced by more piece rail, and the usual symmetry arrangement of track two sides rail, then
It is possible that there is a situation where the seam of interorbital or weld seam are mistaken for track fracture or track crackle etc..For this purpose, can be in train
Opposite left wheel and right wheel are respectively mounted vibrating sensor and/or shock transducer, and then the left vehicle arrived according to synchronous acquisition
Detection signal when detection signal and right wheel and right rail when wheel is contacted with left rail contact, judges on synchronization
State two detection signals whether and meanwhile there is a situation where characteristic values beyond preset threshold, if occurring simultaneously, the hurt class of track
Type is seam or weld seam；The hurt type of track may be fracture, crackle etc. if not occurring simultaneously.Then, if according to feature
The hurt type for being worth determining track is fracture, then it is errorless to may check that hurt type determines by above-mentioned association analysis.
Optionally, above-mentioned to detection being associated property of signal analysis, before may include: the train arrived according to synchronous acquisition
The detection signal of wheel and rear wheel, analyze front vehicle wheel detection signal whether with it is default when the detection signal of rear wheel delayed
There is a situation where characteristic values to exceed preset threshold.
Specifically, the failure on train wheel may be mistaken for the hurt on track, for example, by the crack of wheel, falling
Block is mistaken for the crack of track, chip off-falling.Therefore, vibrating sensor can be respectively mounted in the front vehicle wheel and rear wheel of train the same side
And/or shock transducer, and then the detection signal of the front vehicle wheel and rear wheel arrived according to synchronous acquisition, judgement are delayed when default,
When i.e. forward and backward wheel is successively contacted with the same position of track, whether above-mentioned two detection signal occurs characteristic value beyond pre-
If the case where threshold value, if occurring, there are hurts for track；Conversely, then hurt, predetermined hurt type is not present in track
Actually be train itself failure, thus verify hurt type determine it is wrong.
The present invention also provides a kind of track defect detection devices, referring to FIG. 2, Fig. 2 is provided by the embodiment of the present invention
Track defect detection device schematic diagram, known by Fig. 2, which may include:
Acquisition module 10, for acquiring the detection signal in travelling process of train, wherein detection signal includes that vibration accelerates
Spend signal and/or impact signal；
Extraction module 20 obtains characteristic value for carrying out feature extraction to detection signal；
Analysis module 30, for the size of comparative feature value and preset threshold, whether judging characteristic value exceeds preset threshold；
Determining module 40 carries out hurt pattern-recognition according to characteristic value, determines if exceeding preset threshold for characteristic value
The hurt type of track.
On the basis of the above embodiments, optionally, acquisition module 10 is specifically used for: multiple positions of synchronous acquisition train
Detection signal.
On the basis of the various embodiments described above, optionally, can also include:
Validating module, for analyzing detection being associated property of signal and verifying hurt type based on the analysis results.
On the basis of the various embodiments described above, optionally, validating module may include:
First judging submodule, the detection signal of the left wheel of the train for being arrived according to synchronous acquisition and right wheel, sentences
Whether there is a situation where characteristic values to exceed preset threshold simultaneously with the detection signal of right wheel for the detection signal of disconnected left wheel.
Optional on the basis of the various embodiments described above, validating module may include:
Second judgment submodule, the front vehicle wheel of the train for being arrived according to synchronous acquisition and the detection signal of rear wheel, sentence
The detection signal of disconnected front vehicle wheel whether with it is default when delay the detection signal of rear wheel and characteristic value occurs exceed preset threshold
Situation.
The present invention also provides a kind of track defect detection device, the track defect detection device described below can be with
Above-described track defect detection method corresponds to each other reference.Referring to FIG. 3, Fig. 3 is rail provided by the embodiment of the present invention
The schematic diagram of road hurt detection device, as shown in Figure 3 the track defect detection device may include:
Sensor 1, for acquiring the detection signal in travelling process of train, wherein detection signal includes vibration acceleration
Signal and/or impact signal；
Processor 2 carries out feature extraction to detection signal and obtains characteristic value, and comparative feature for receiving detection signal
The size of value and preset threshold, whether judging characteristic value exceeds preset threshold, if exceeding, carries out hurt mode according to characteristic value
Identification, determines the hurt type of track.
Because situation is complicated, it can not enumerate and be illustrated, those skilled in the art should be able to be, it is realized that mention in the present invention
It combines actual conditions to may exist multiple examples under the basic principle of the embodiment of confession, is not paying enough creative works
Under, it should be within the scope of the present invention.
Each embodiment is described in a progressive manner in specification, the highlights of each of the examples are with other realities
The difference of example is applied, the same or similar parts in each embodiment may refer to each other.
Track defect detection method, device and equipment provided by the present invention are described in detail above.Herein
Apply that a specific example illustrates the principle and implementation of the invention, the explanation of above example is only intended to help
Understand method and its core concept of the invention.It should be pointed out that for those skilled in the art, not taking off
, can be with several improvements and modifications are made to the present invention under the premise of from the principle of the invention, these improvement and modification also fall into this
Invention scope of protection of the claims.
Claims (10)
1. a kind of track defect detection method characterized by comprising
Acquire the detection signal in travelling process of train, wherein the detection signal includes vibration acceleration signal and/or impact
Signal；
Feature extraction is carried out to the detection signal and obtains characteristic value；
The size for comparing the characteristic value and preset threshold, judges whether the characteristic value exceeds the preset threshold；
If exceeding, the hurt type of track is determined according to the characteristic value.
2. track defect detection method according to claim 1, which is characterized in that in the acquisition travelling process of train
Detect signal, comprising:
The detection signal of multiple positions of train described in synchronous acquisition.
3. track defect detection method according to claim 2, which is characterized in that further include:
The being associated property of detection signal is analyzed and verifies the hurt type based on the analysis results.
4. track defect detection method according to claim 3, which is characterized in that described to be closed to the detection signal
The analysis of connection property, comprising:
The left wheel of the train arrived according to synchronous acquisition and the detection signal of right wheel, judge the institute of the left wheel
Whether the detection signal for stating detection signal and the right wheel occurs the characteristic value beyond the preset threshold simultaneously
Situation.
5. track defect detection method according to claim 3, which is characterized in that described to be closed to the detection signal
The analysis of connection property, comprising:
The front vehicle wheel of the train arrived according to synchronous acquisition and the detection signal of rear wheel, judge the institute of the front vehicle wheel
State detection signal and it is default when delay the rear wheel the detection signal whether occur the characteristic value exceed it is described pre-
If the case where threshold value.
6. track defect detection method according to claim 5, which is characterized in that described to carry out spy to the detection signal
Sign is extracted and obtains characteristic value, comprising:
Extract the detection temporal signatures value of signal and/or one or more in frequency domain character value.
7. a kind of track defect detection device characterized by comprising
Acquisition module, for acquiring the detection signal in travelling process of train, wherein the detection signal includes vibration acceleration
Signal and/or impact signal；
Extraction module obtains characteristic value for carrying out feature extraction to the detection signal；
It is described pre- to judge whether the characteristic value exceeds for the size of the characteristic value and preset threshold for analysis module
If threshold value；
Determining module determines the hurt of track according to the characteristic value if exceeding the preset threshold for the characteristic value
Type.
8. track defect detection device according to claim 7, which is characterized in that the acquisition module is specifically used for:
The detection signal of multiple positions of train described in synchronous acquisition.
9. track defect detection device according to claim 8, which is characterized in that further include:
Validating module, for analyzing the being associated property of detection signal and verifying the hurt type based on the analysis results.
10. a kind of track defect detection device characterized by comprising
Sensor, for acquiring the detection signal in travelling process of train, wherein the detection signal includes vibration acceleration letter
Number and/or impact signal；
Processor obtains characteristic value, and the characteristic value and default threshold for carrying out feature extraction to the detection signal
The size of value, judges whether the characteristic value exceeds the preset threshold, if exceeding, carries out hurt mould according to the characteristic value
Formula identification, determines the hurt type of track.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810922427.5A CN109142524A (en) | 2018-08-14 | 2018-08-14 | A kind of track damage detecting method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810922427.5A CN109142524A (en) | 2018-08-14 | 2018-08-14 | A kind of track damage detecting method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109142524A true CN109142524A (en) | 2019-01-04 |
Family
ID=64793364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810922427.5A Pending CN109142524A (en) | 2018-08-14 | 2018-08-14 | A kind of track damage detecting method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109142524A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109828033A (en) * | 2019-01-08 | 2019-05-31 | 上海卫星工程研究所 | Damnification recognition method and system based on vibratory response similarity analysis |
| CN110261483A (en) * | 2019-07-31 | 2019-09-20 | 三一汽车起重机械有限公司 | Weld defect detection method, device, detection device and readable storage medium storing program for executing |
| CN110988142A (en) * | 2019-12-18 | 2020-04-10 | 交控科技股份有限公司 | Track aging fault detection system and method |
| CN111252110A (en) * | 2020-01-17 | 2020-06-09 | 杭州中车车辆有限公司 | Track beam detection system and detection method for straddle type single-track inspection vehicle |
| CN111319655A (en) * | 2020-03-09 | 2020-06-23 | 唐智科技湖南发展有限公司 | Track damage detection method and device and computer readable storage medium |
| CN111562307A (en) * | 2020-04-22 | 2020-08-21 | 南京航空航天大学 | Real-time statistical method for steel rail damage quantity based on direct-current magnetic flux leakage principle |
| CN112014593A (en) * | 2019-05-28 | 2020-12-01 | 浙江德盛铁路器材股份有限公司 | Device and method for monitoring and evaluating quality condition of railway track basic equipment |
| CN112013895A (en) * | 2019-05-28 | 2020-12-01 | 浙江德盛铁路器材股份有限公司 | Method for monitoring and evaluating quality condition of railway track basic equipment |
| CN112649513A (en) * | 2020-12-30 | 2021-04-13 | 天津精益铁安机电技术有限公司 | Railway artificial intelligence damage judging method based on image recognition |
| CN112765857A (en) * | 2021-01-22 | 2021-05-07 | 中车青岛四方机车车辆股份有限公司 | Train structure damage identification method and device, electronic equipment and storage medium |
| CN113281414A (en) * | 2021-06-30 | 2021-08-20 | 中国国家铁路集团有限公司 | Method and device for identifying short-wave disease types of steel rails and electronic equipment |
| CN113945700A (en) * | 2021-10-18 | 2022-01-18 | 北京唐智科技发展有限公司 | Track damage detection method, device, equipment and storage medium |
| CN114413759A (en) * | 2022-02-08 | 2022-04-29 | 北京城建设计发展集团股份有限公司 | Track operation and maintenance system and method and electronic equipment |
| CN114426038A (en) * | 2020-10-29 | 2022-05-03 | 北京潼荔科技有限公司 | Wheel-rail abnormity monitoring equipment |
| CN114659611A (en) * | 2022-03-16 | 2022-06-24 | 武汉理工大学 | Track fastener state monitoring system based on fiber grating array |
| CN116881783A (en) * | 2023-06-21 | 2023-10-13 | 清华大学 | Road damage detection method, device, computer equipment and storage medium |
| WO2023207346A1 (en) * | 2022-04-28 | 2023-11-02 | 中兴通讯股份有限公司 | Detection method and apparatus applied to railway track, and detection device |
| CN117349640A (en) * | 2023-12-04 | 2024-01-05 | 成都盛锴科技有限公司 | Vehicle-mounted vibration acceleration data analysis method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3994459A (en) * | 1974-04-18 | 1976-11-30 | M.L. Engineering (Plymouth) Limited | Railway vehicle derailment detection system |
| CN101264767A (en) * | 2007-03-15 | 2008-09-17 | 唐德尧 | Steel rail fracture vehicle-carrying non-contact fast monitoring technique |
| CN104228872A (en) * | 2014-09-28 | 2014-12-24 | 江苏润仪仪表有限公司 | Portable track irregularity online monitoring device and method |
| CN105346561A (en) * | 2015-12-02 | 2016-02-24 | 北京交通大学 | Rail turnout disease detection system based on operating vehicle and rail turnout disease detection method based on operating vehicle |
| CN106018557A (en) * | 2016-07-28 | 2016-10-12 | 南京理工大学 | Track surface indentation detection method based on wavelet analysis |
| CN106687353A (en) * | 2014-09-12 | 2017-05-17 | Ntn株式会社 | Railroad car bearing abnormality sensing system |
| CN108290585A (en) * | 2015-11-11 | 2018-07-17 | 克诺尔轨道车辆系统有限公司 | For to compare the method and apparatus of control mode detection derailing |
-
2018
- 2018-08-14 CN CN201810922427.5A patent/CN109142524A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3994459A (en) * | 1974-04-18 | 1976-11-30 | M.L. Engineering (Plymouth) Limited | Railway vehicle derailment detection system |
| CN101264767A (en) * | 2007-03-15 | 2008-09-17 | 唐德尧 | Steel rail fracture vehicle-carrying non-contact fast monitoring technique |
| CN106687353A (en) * | 2014-09-12 | 2017-05-17 | Ntn株式会社 | Railroad car bearing abnormality sensing system |
| CN104228872A (en) * | 2014-09-28 | 2014-12-24 | 江苏润仪仪表有限公司 | Portable track irregularity online monitoring device and method |
| CN108290585A (en) * | 2015-11-11 | 2018-07-17 | 克诺尔轨道车辆系统有限公司 | For to compare the method and apparatus of control mode detection derailing |
| CN105346561A (en) * | 2015-12-02 | 2016-02-24 | 北京交通大学 | Rail turnout disease detection system based on operating vehicle and rail turnout disease detection method based on operating vehicle |
| CN106018557A (en) * | 2016-07-28 | 2016-10-12 | 南京理工大学 | Track surface indentation detection method based on wavelet analysis |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109828033A (en) * | 2019-01-08 | 2019-05-31 | 上海卫星工程研究所 | Damnification recognition method and system based on vibratory response similarity analysis |
| CN109828033B (en) * | 2019-01-08 | 2021-08-03 | 上海卫星工程研究所 | Damage identification method and system based on vibration response similarity analysis |
| CN112013895A (en) * | 2019-05-28 | 2020-12-01 | 浙江德盛铁路器材股份有限公司 | Method for monitoring and evaluating quality condition of railway track basic equipment |
| CN112014593A (en) * | 2019-05-28 | 2020-12-01 | 浙江德盛铁路器材股份有限公司 | Device and method for monitoring and evaluating quality condition of railway track basic equipment |
| CN110261483A (en) * | 2019-07-31 | 2019-09-20 | 三一汽车起重机械有限公司 | Weld defect detection method, device, detection device and readable storage medium storing program for executing |
| CN110988142A (en) * | 2019-12-18 | 2020-04-10 | 交控科技股份有限公司 | Track aging fault detection system and method |
| CN110988142B (en) * | 2019-12-18 | 2022-09-02 | 交控科技股份有限公司 | Track aging fault detection system and method |
| CN111252110A (en) * | 2020-01-17 | 2020-06-09 | 杭州中车车辆有限公司 | Track beam detection system and detection method for straddle type single-track inspection vehicle |
| CN111252110B (en) * | 2020-01-17 | 2021-01-26 | 杭州中车车辆有限公司 | Track beam detection system and detection method for straddle type single-track inspection vehicle |
| CN111319655A (en) * | 2020-03-09 | 2020-06-23 | 唐智科技湖南发展有限公司 | Track damage detection method and device and computer readable storage medium |
| CN111562307A (en) * | 2020-04-22 | 2020-08-21 | 南京航空航天大学 | Real-time statistical method for steel rail damage quantity based on direct-current magnetic flux leakage principle |
| CN114426038A (en) * | 2020-10-29 | 2022-05-03 | 北京潼荔科技有限公司 | Wheel-rail abnormity monitoring equipment |
| CN112649513A (en) * | 2020-12-30 | 2021-04-13 | 天津精益铁安机电技术有限公司 | Railway artificial intelligence damage judging method based on image recognition |
| CN112765857A (en) * | 2021-01-22 | 2021-05-07 | 中车青岛四方机车车辆股份有限公司 | Train structure damage identification method and device, electronic equipment and storage medium |
| CN113281414A (en) * | 2021-06-30 | 2021-08-20 | 中国国家铁路集团有限公司 | Method and device for identifying short-wave disease types of steel rails and electronic equipment |
| CN113281414B (en) * | 2021-06-30 | 2022-10-25 | 中国国家铁路集团有限公司 | Method and device for identifying short-wave disease types of steel rails and electronic equipment |
| CN113945700A (en) * | 2021-10-18 | 2022-01-18 | 北京唐智科技发展有限公司 | Track damage detection method, device, equipment and storage medium |
| CN114413759A (en) * | 2022-02-08 | 2022-04-29 | 北京城建设计发展集团股份有限公司 | Track operation and maintenance system and method and electronic equipment |
| CN114659611A (en) * | 2022-03-16 | 2022-06-24 | 武汉理工大学 | Track fastener state monitoring system based on fiber grating array |
| CN114659611B (en) * | 2022-03-16 | 2024-05-14 | 武汉理工大学 | Track fastener state monitoring system based on fiber bragg grating array |
| WO2023207346A1 (en) * | 2022-04-28 | 2023-11-02 | 中兴通讯股份有限公司 | Detection method and apparatus applied to railway track, and detection device |
| CN116881783A (en) * | 2023-06-21 | 2023-10-13 | 清华大学 | Road damage detection method, device, computer equipment and storage medium |
| CN116881783B (en) * | 2023-06-21 | 2024-04-09 | 清华大学 | Road damage detection method, device, computer equipment and storage medium |
| CN117349640A (en) * | 2023-12-04 | 2024-01-05 | 成都盛锴科技有限公司 | Vehicle-mounted vibration acceleration data analysis method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109142524A (en) | A kind of track damage detecting method, device and equipment | |
| CN104990709B (en) | Method for detecting Locomotive Bearing failure | |
| US9714043B2 (en) | Abnormal vehicle dynamics detection | |
| CN102548828B (en) | Method and instrumentation for detection of rail defects, in particular rail top defects | |
| CN104316729B (en) | Self-diagnosis method of acceleration sensors for locomotive bogie detection | |
| RU2507403C2 (en) | Method and system for turbojet control | |
| CN105092467B (en) | A kind of quick monitoring device of high-speed railway wheel tread flat and method | |
| CN104280397B (en) | A kind of eddy current video synthesis check and evaluation method of in-service rail tread fish scale crackle | |
| JP6874858B2 (en) | Damage diagnostic equipment, damage diagnostic methods, and damage diagnostic programs | |
| CN105929025B (en) | One kind is based on the continuous wheel tread of the time and space and rail deformation detection method | |
| CN108415009A (en) | A kind of train speed computational methods and system | |
| CN113776760B (en) | Train wheel set out-of-round fault monitoring method and system based on whole-axis vibration analysis | |
| CN109919066A (en) | The method and apparatus of passenger's density anomaly in a kind of detection rail transit cars | |
| CN103106811A (en) | Recognition method of motor vehicle valid traffic conflict based on crashing time of two vehicles | |
| WO2022213596A1 (en) | Big data-based new energy vehicle overload detection method | |
| RU2596048C2 (en) | Method of monitoring rail contact with wheel | |
| CN113032907A (en) | Method and system for correcting vehicle shaking disease data deviation based on waveform correlation | |
| CN103746871B (en) | Data validity detection means and detection method | |
| CN110171442A (en) | Detection system, the detection method of wheel flat | |
| CN110220726A (en) | Detection system, the detection method of wheel out of round | |
| KR101463797B1 (en) | Method and apparatus for diagnosing railway by using driving noise of railway vehicle | |
| CN105424803B (en) | A kind of Railway wheelset flaw detection processing method and processing device | |
| KR102369916B1 (en) | Rail fracture decision system and method for deciding rail fracture using the same | |
| CN105277622B (en) | A kind of Railway wheelset method for detection fault detection and device | |
| CN210591925U (en) | Axle box vibrating wheel diameter difference detection system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190104 |
|
| RJ01 | Rejection of invention patent application after publication |