CN113447570A - Ballastless track disease detection method and system based on vehicle-mounted acoustic sensing - Google Patents
Ballastless track disease detection method and system based on vehicle-mounted acoustic sensing Download PDFInfo
- Publication number
- CN113447570A CN113447570A CN202110724372.9A CN202110724372A CN113447570A CN 113447570 A CN113447570 A CN 113447570A CN 202110724372 A CN202110724372 A CN 202110724372A CN 113447570 A CN113447570 A CN 113447570A
- Authority
- CN
- China
- Prior art keywords
- ballastless track
- signal
- sound
- disease
- track structure
- 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
- 201000010099 disease Diseases 0.000 title claims abstract description 71
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 71
- 238000001514 detection method Methods 0.000 title claims abstract description 32
- 230000005855 radiation Effects 0.000 claims abstract description 51
- 238000000034 method Methods 0.000 claims abstract description 33
- 230000005236 sound signal Effects 0.000 claims abstract description 23
- 230000002708 enhancing effect Effects 0.000 claims abstract description 7
- 238000003062 neural network model Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 17
- 230000007547 defect Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 238000005336 cracking Methods 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 7
- 238000012423 maintenance Methods 0.000 claims description 6
- 230000000306 recurrent effect Effects 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims description 6
- 238000012847 principal component analysis method Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 239000011800 void material Substances 0.000 claims description 2
- 230000009466 transformation Effects 0.000 claims 1
- 238000012706 support-vector machine Methods 0.000 description 10
- 230000001133 acceleration Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000003749 cleanliness Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000004570 mortar (masonry) Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000001931 thermography 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
- G01N29/04—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
- G01N29/4445—Classification of defects
-
- 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
- G01N29/4481—Neural networks
-
- 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
- G01N29/46—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by spectral analysis, e.g. Fourier analysis or wavelet analysis
-
- 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
- G01N2291/028—Material parameters
- G01N2291/0289—Internal structure, e.g. defects, grain size, texture
-
- 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
- G01N2291/26—Scanned objects
- G01N2291/262—Linear objects
- G01N2291/2623—Rails; Railroads
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Signal Processing (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Acoustics & Sound (AREA)
- Machines For Laying And Maintaining Railways (AREA)
Abstract
The invention relates to a ballastless track disease detection method based on vehicle-mounted acoustic sensing, which specifically comprises the following steps: s1, collecting original sound signals in the running process of the train; s2, enhancing the sound radiation signal of the ballastless track structure according to the original sound signal; s3, identifying corresponding track diseases according to the enhanced sound radiation signals of the ballastless track structure to obtain a disease identification result of the ballastless track; and S4, judging the line section needing to be maintained according to the disease identification result of the ballastless track. Compared with the prior art, the method has the advantages of saving labor, equipment and time cost, improving the detection efficiency of the ballastless track and the like.
Description
Technical Field
The invention relates to the field of track traffic infrastructure detection, in particular to a ballastless track disease detection method and system based on vehicle-mounted acoustic sensing.
Background
Due to the advantages in the aspects of operation, maintenance and the like, the ballastless track is widely applied to high-speed railway lines. However, as the transportation density of the high-speed railway is gradually increased, the operation speed is continuously increased, and the load grade is gradually increased, the power interaction between the high-speed train and the line infrastructure is more and more severe. Under the condition, diseases such as mortar layer crack separation, track plate emptying, track plate upwarping, track plate and base plate cracking and the like often occur on the ballastless track. These diseases affect the running stability of the vehicle, and even threaten the driving safety when the diseases are serious.
Common non-destructive inspection methods such as ground penetrating radar, ultrasonic techniques, infrared thermography, etc. have limited detection range and usually require external excitation using special equipment. Therefore, the detection can only be carried out in the skylight period of train operation, and the detection efficiency is low. In addition, concrete placement quality and rebar placement can also affect the accuracy of such detection methods.
In order to improve the detection efficiency, researchers use a vehicle-mounted acceleration sensor to detect the structural state of the ballastless track. Although the method based on the vehicle-mounted vibration sensor is convenient to measure, the sensitivity to the structural damage under the rail is insufficient. In recent years, vehicle-mounted laser optical sensing systems and vehicle-mounted computer vision systems have become emerging methods for rail state detection. However, both methods require expensive equipment and the detection effect is easily affected by ambient light and the degree of cleanliness of the object surface.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, and provides a ballastless track disease detection method and system based on vehicle-mounted acoustic sensing, which can detect ballastless tracks in real time in the running process of a train, and have high detection efficiency and low cost.
The purpose of the invention can be realized by the following technical scheme:
a ballastless track disease detection method based on vehicle-mounted acoustic sensing specifically comprises the following steps:
s1, collecting original sound signals in the running process of the train;
s2, enhancing the sound radiation signal of the ballastless track structure according to the original sound signal;
s3, identifying corresponding track diseases according to the enhanced sound radiation signals of the ballastless track structure to obtain a disease identification result of the ballastless track;
and S4, judging the line section needing to be maintained according to the disease identification result of the ballastless track.
In the step S2, the sound radiation signal of the ballastless track structure is enhanced by a sound enhancement method based on deep learning.
Further, the deep learning based sound enhancement method comprises a neural network model training phase and a neural network model application phase.
Further, the specific process of the neural network model training phase comprises the following steps:
s201, collecting interference noise in a train operation environment, forming mixed sound together with a ballastless track structure sound radiation signal generated by numerical simulation, and performing short-time Fourier transform on the ballastless track structure sound radiation signal and the mixed sound respectively to obtain a corresponding time-frequency signal;
s202, extracting a time-frequency mask of the sound radiation signal of the ballastless track structure and time-frequency characteristics of mixed sound from the time-frequency signal, wherein the time-frequency mask of the sound radiation signal of the ballastless track structure is used as a training target, and the time-frequency characteristics of the mixed sound are used as input data and input into a recurrent neural network model for training.
Further, the specific process of the neural network model application phase comprises the following steps:
s203, obtaining a corresponding time-frequency signal from the original sound signal through short-time Fourier transform (STFT);
s204, extracting acoustic characteristics from the time-frequency signal of the original sound signal and inputting the acoustic characteristics into the trained recurrent neural network model to obtain a time-frequency mask of the sound radiation signal of the ballastless track structure;
s205, multiplying the time-frequency mask of the ballastless track structure acoustic radiation signal by the acoustic characteristics of the original sound signal, and then performing short-time inverse Fourier transform (iSTFT) to obtain the enhanced ballastless track structure acoustic radiation signal.
In the step S3, the track diseases are identified by a supervised machine learning algorithm, which specifically includes the following steps:
s301, generating an acoustic radiation signal under a typical defect state of a ballastless track structure through numerical simulation, extracting characteristic information of the acoustic radiation signal, processing the characteristic information through a principal component analysis method, and associating the processed characteristic information with the typical defect state of the ballastless track structure to generate a defect dictionary;
s302, taking the processed characteristic information as input data of a training Support Vector Machine (SVM) model, and performing supervised classification training and verification on the SVM model according to a disease dictionary;
and S303, performing feature extraction on the ballastless track structure acoustic radiation signal enhanced in the step S205, inputting the extracted feature into a trained SVM model, classifying the enhanced acoustic radiation signal by the SVM model to obtain a signal classification result, and identifying a corresponding disease type and a disease degree according to the signal classification result to serve as a disease identification result.
Further, the processing types performed on the feature information by the principal component analysis method in step S301 include a decorrelation processing operation and a redundancy removal processing operation.
Further, the typical damage state types of the ballastless track structure comprise track slab emptying, track slab arching, track slab cracking and base plate cracking.
Further, the feature information includes a time domain feature, a frequency domain feature, and a time-frequency domain feature.
The process of judging the line section needing to be maintained in the step S4 includes disease recording, position recording and threshold judgment.
A system using the ballastless track disease detection method based on vehicle-mounted acoustic sensing comprises the following steps:
the acoustic sensor is used for collecting an original sound signal in the running process of the train;
the signal enhancement unit is used for enhancing the sound radiation signal of the ballastless track structure according to the original sound signal;
the disease identification unit is used for identifying the corresponding track disease according to the enhanced acoustic radiation signal to obtain a disease identification result of the ballastless track;
and the maintenance guiding unit is used for judging the line section needing to be maintained according to the disease identification result of the ballastless track.
The acoustic sensor is arranged at the bottom of the train bogie.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention can realize real-time detection in the running process of the train, does not need to lay sensors on a large scale along the railway, reduces the risk of instrument and equipment intruding into the clearance of the railway system, saves labor and time cost, and effectively improves the detection efficiency of the ballastless track.
2. The hardware equipment required by the invention is only the acoustic sensor, the data transmission equipment, the data analysis equipment and the positioning equipment, and the cost is low.
3. The method can judge the line section needing to be maintained, provides more exact guidance for repairing the structural damage of the ballastless track, and accurately judges the road section needing to be repaired.
4. The ballastless track disease detection method is free from light interference and time limitation, and can be widely applied to disease detection of various ballastless track infrastructures of high-speed railways, urban rail transit and the like.
Drawings
FIG. 1 is a schematic flow chart of the detection method of the present invention;
FIG. 2 is a schematic diagram of the system of the present invention;
fig. 3 is a schematic flow chart of the enhanced acoustic radiation signal based on deep learning according to the present invention.
Reference numerals:
1-an acoustic sensor; 2-a signal enhancement unit; 3-a disease identification unit; 4-maintenance guide unit.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
Examples
As shown in fig. 1, a ballastless track disease detection method based on vehicle-mounted acoustic sensing specifically includes the following steps:
s1, collecting original sound signals in the running process of the train;
s2, enhancing the sound radiation signal of the ballastless track structure according to the original sound signal;
s3, identifying corresponding track diseases according to the enhanced sound radiation signals of the ballastless track structure to obtain a disease identification result of the ballastless track;
and S4, judging the line section needing to be maintained according to the disease identification result of the ballastless track.
In step S2, the sound radiation signal of the ballastless track structure is enhanced by a sound enhancement method based on deep learning.
As shown in fig. 3, the deep learning based sound enhancement method includes a neural network model training phase and a neural network model application phase.
The specific process of the neural network model training phase comprises the following steps:
s201, collecting interference noise in a train operation environment, forming mixed sound together with a ballastless track structure sound radiation signal generated by numerical simulation, and performing short-time Fourier transform on the ballastless track structure sound radiation signal and the mixed sound respectively to obtain a corresponding time-frequency signal;
s202, extracting a time-frequency mask of the sound radiation signal of the ballastless track structure and time-frequency characteristics of mixed sound from the time-frequency signal, wherein the time-frequency mask of the sound radiation signal of the ballastless track structure is used as a training target, and the time-frequency characteristics of the mixed sound are used as input data and input into a recurrent neural network model for training.
The specific process of the neural network model application stage comprises the following steps:
s203, obtaining a corresponding time-frequency signal from the original sound signal through short-time Fourier transform (STFT);
s204, extracting acoustic characteristics from the time-frequency signal of the original sound signal and inputting the acoustic characteristics into the trained recurrent neural network model to obtain a time-frequency mask of the sound radiation signal of the ballastless track structure;
s205, multiplying the time-frequency mask of the ballastless track structure acoustic radiation signal by the acoustic characteristics of the original sound signal, and then performing short-time inverse Fourier transform (iSTFT) to obtain the enhanced ballastless track structure acoustic radiation signal.
In the step S3, the track diseases are identified by a supervised machine learning algorithm, which specifically includes the following steps:
s301, generating an acoustic radiation signal under a typical defect state of a ballastless track structure through numerical simulation, extracting characteristic information of the acoustic radiation signal, processing the characteristic information through a principal component analysis method, and associating the processed characteristic information with the typical defect state of the ballastless track structure to generate a defect dictionary;
s302, taking the processed characteristic information as input data of a training Support Vector Machine (SVM) model, and performing supervised classification training and verification on the SVM model according to a disease dictionary;
and S303, performing feature extraction on the ballastless track structure acoustic radiation signal enhanced in the step S205, inputting the extracted feature into a trained SVM model, classifying the enhanced acoustic radiation signal by the SVM model to obtain a signal classification result, and identifying a corresponding disease type and a disease degree according to the signal classification result to serve as a disease identification result.
The types of processing performed on the feature information by the principal component analysis method in step S301 include decorrelation processing operation and redundancy removal processing operation.
Typical damage states of the ballastless track structure comprise track slab void, track slab arch-up, track slab cracking and base plate cracking.
The feature information includes a time domain feature, a frequency domain feature, and a time-frequency domain feature.
In this embodiment, the process of determining the line segment needing to be maintained in step S4 specifically includes the following steps:
s401, recording the disease type and the disease degree in the disease identification result, and simultaneously recording the position of a line where the disease is located;
s402, judging whether the disease degree of each position exceeds a preset damage threshold value;
and S403, detecting the damage position with the damage degree exceeding the damage threshold as a line section needing maintenance.
As shown in fig. 2, a system of a ballastless track disease detection method based on vehicle-mounted acoustic sensing includes:
the acoustic sensor 1 is used for collecting an original sound signal in the running process of a train;
the signal enhancement unit 2 is used for enhancing the sound radiation signal of the ballastless track structure according to the original sound signal;
the disease identification unit 3 is used for identifying the corresponding track disease according to the enhanced acoustic radiation signal to obtain a disease identification result of the ballastless track;
and the maintenance guidance unit 4 is used for judging the line section needing to be maintained according to the disease identification result of the ballastless track.
The acoustic sensor 1 is arranged at the bottom of the train bogie.
In addition, it should be noted that the specific embodiments described in the present specification may have different names, and the above descriptions in the present specification are only illustrations of the structures of the present invention. All equivalent or simple changes in the structure, characteristics and principles of the invention are included in the protection scope of the invention. Various modifications or additions may be made to the described embodiments or methods may be similarly employed by those skilled in the art without departing from the scope of the invention as defined in the appending claims.
Claims (10)
1. A ballastless track disease detection method based on vehicle-mounted acoustic sensing is characterized by comprising the following steps:
s1, collecting original sound signals in the running process of the train;
s2, enhancing the sound radiation signal of the ballastless track structure according to the original sound signal;
s3, identifying corresponding track diseases according to the enhanced sound radiation signals of the ballastless track structure to obtain a disease identification result of the ballastless track;
and S4, judging the line section needing to be maintained according to the disease identification result of the ballastless track.
2. The ballastless track disease detection method based on vehicle-mounted acoustic sensing of claim 1, wherein in step S2, the sound radiation signal of the ballastless track structure is enhanced by a sound enhancement method based on deep learning.
3. The ballastless track disease detection method based on vehicle-mounted acoustic sensing according to claim 2, wherein the sound enhancement method based on deep learning comprises a neural network model training stage and a neural network model application stage.
4. The ballastless track disease detection method based on vehicle-mounted acoustic sensing according to claim 3, wherein the specific process of the neural network model training phase comprises the following steps:
s201, collecting interference noise in a train operation environment, forming mixed sound together with a ballastless track structure sound radiation signal generated by numerical simulation, and performing short-time Fourier transform on the ballastless track structure sound radiation signal and the mixed sound respectively to obtain a corresponding time-frequency signal;
s202, extracting a time-frequency mask of the sound radiation signal of the ballastless track structure and time-frequency characteristics of mixed sound from the time-frequency signal, wherein the time-frequency mask of the sound radiation signal of the ballastless track structure is used as a training target, and the time-frequency characteristics of the mixed sound are used as input data and input into a recurrent neural network model for training.
5. The ballastless track disease detection method based on vehicle-mounted acoustic sensing according to claim 4, wherein the specific process of the neural network model application stage comprises the following steps:
s203, obtaining a corresponding time-frequency signal from the original sound signal through short-time Fourier transform;
s204, extracting acoustic characteristics from the time-frequency signal of the original sound signal and inputting the acoustic characteristics into the trained recurrent neural network model to obtain a time-frequency mask of the sound radiation signal of the ballastless track structure;
s205, multiplying the time-frequency mask of the ballastless track structure acoustic radiation signal by the acoustic characteristics of the original sound signal, and performing short-time Fourier inverse transformation to obtain the enhanced ballastless track structure acoustic radiation signal.
6. The ballastless track disease detection method based on vehicle-mounted acoustic sensing of claim 5, wherein the step S3 of identifying track diseases through a supervised machine learning algorithm specifically comprises the following steps:
s301, generating an acoustic radiation signal under a typical defect state of a ballastless track structure through numerical simulation, extracting characteristic information of the acoustic radiation signal, processing the characteristic information through a principal component analysis method, and associating the processed characteristic information with the typical defect state of the ballastless track structure to generate a defect dictionary;
s302, taking the processed characteristic information as input data of the SVM model, and performing supervised classification training and verification on the SVM model according to a disease dictionary;
and S303, performing feature extraction on the ballastless track structure acoustic radiation signal enhanced in the step S205, inputting the extracted feature into a trained SVM model, classifying the enhanced acoustic radiation signal by the SVM model to obtain a signal classification result, and identifying a corresponding disease type and a disease degree according to the signal classification result to serve as a disease identification result.
7. The ballastless track disease detection method based on vehicle-mounted acoustic sensing is characterized in that the typical disease states of the ballastless track structure comprise track slab void, track slab upwarp, track slab cracking and base plate cracking.
8. The ballastless track disease detection method based on vehicle-mounted acoustic sensing of claim 1, wherein the process of determining the line section needing to be maintained in step S4 includes disease recording, position recording and threshold value determination.
9. The system for using the ballastless track disease detection method based on vehicle-mounted acoustic sensing according to claim 1, is characterized by comprising:
the acoustic sensor (1) is used for collecting an original sound signal in the running process of the train;
the signal enhancement unit (2) is used for enhancing the sound radiation signal of the ballastless track structure according to the original sound signal;
the disease identification unit (3) identifies corresponding track diseases according to the enhanced sound radiation signals of the ballastless track structure to obtain a disease identification result of the ballastless track;
and the maintenance guiding unit (4) is used for judging the line section needing to be maintained according to the disease identification result of the ballastless track.
10. The system for detecting the ballastless track damage based on the vehicle-mounted acoustic sensor is characterized in that the acoustic sensor (1) is arranged at the bottom of a train bogie.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110724372.9A CN113447570A (en) | 2021-06-29 | 2021-06-29 | Ballastless track disease detection method and system based on vehicle-mounted acoustic sensing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110724372.9A CN113447570A (en) | 2021-06-29 | 2021-06-29 | Ballastless track disease detection method and system based on vehicle-mounted acoustic sensing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113447570A true CN113447570A (en) | 2021-09-28 |
Family
ID=77813700
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110724372.9A Pending CN113447570A (en) | 2021-06-29 | 2021-06-29 | Ballastless track disease detection method and system based on vehicle-mounted acoustic sensing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113447570A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114818998A (en) * | 2022-06-28 | 2022-07-29 | 浙江大学 | Method for judging mud pumping disease state of ballastless track foundation bed during slurry turning |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110218428A1 (en) * | 2010-03-04 | 2011-09-08 | Medical Scan Technologies, Inc. | System and Method for Three Dimensional Medical Imaging with Structured Light |
EP2570806A1 (en) * | 2010-05-10 | 2013-03-20 | JFE Steel Corporation | Method for subjecting structure form of weld to imaging and device therefor |
CN103198322A (en) * | 2013-01-18 | 2013-07-10 | 江南大学 | Magnetic tile surface defect feature extraction and defect classification method based on machine vision |
US20150278686A1 (en) * | 2014-03-31 | 2015-10-01 | Sony Corporation | Method, system and artificial neural network |
CN107215353A (en) * | 2017-05-26 | 2017-09-29 | 华东交通大学 | A kind of remote monitoring method for early warning of track structure disease |
CN107680611A (en) * | 2017-09-13 | 2018-02-09 | 电子科技大学 | Single channel sound separation method based on convolutional neural networks |
CN108663435A (en) * | 2018-04-12 | 2018-10-16 | 武汉光谷航天三江激光产业技术研究院有限公司 | A kind of distributed acoustic wave train wheel rail detection device and method |
CN109030628A (en) * | 2018-06-25 | 2018-12-18 | 北京交通大学 | Based on the matched track structure Evaluation Method of Mechanical Property of vibration noise spectrum signature |
CN109545228A (en) * | 2018-12-14 | 2019-03-29 | 厦门快商通信息技术有限公司 | A kind of end-to-end speaker's dividing method and system |
CN109785852A (en) * | 2018-12-14 | 2019-05-21 | 厦门快商通信息技术有限公司 | A kind of method and system enhancing speaker's voice |
US20190318757A1 (en) * | 2018-04-11 | 2019-10-17 | Microsoft Technology Licensing, Llc | Multi-microphone speech separation |
CN110763698A (en) * | 2019-10-12 | 2020-02-07 | 仲恺农业工程学院 | Hyperspectral citrus leaf disease identification method based on characteristic wavelength |
CN111627458A (en) * | 2020-05-27 | 2020-09-04 | 北京声智科技有限公司 | Sound source separation method and equipment |
CN112144321A (en) * | 2020-09-18 | 2020-12-29 | 同济大学 | Nondestructive monitoring method for ballastless track slab cracks |
-
2021
- 2021-06-29 CN CN202110724372.9A patent/CN113447570A/en active Pending
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110218428A1 (en) * | 2010-03-04 | 2011-09-08 | Medical Scan Technologies, Inc. | System and Method for Three Dimensional Medical Imaging with Structured Light |
EP2570806A1 (en) * | 2010-05-10 | 2013-03-20 | JFE Steel Corporation | Method for subjecting structure form of weld to imaging and device therefor |
CN103198322A (en) * | 2013-01-18 | 2013-07-10 | 江南大学 | Magnetic tile surface defect feature extraction and defect classification method based on machine vision |
US20150278686A1 (en) * | 2014-03-31 | 2015-10-01 | Sony Corporation | Method, system and artificial neural network |
CN107215353A (en) * | 2017-05-26 | 2017-09-29 | 华东交通大学 | A kind of remote monitoring method for early warning of track structure disease |
CN107680611A (en) * | 2017-09-13 | 2018-02-09 | 电子科技大学 | Single channel sound separation method based on convolutional neural networks |
US20190318757A1 (en) * | 2018-04-11 | 2019-10-17 | Microsoft Technology Licensing, Llc | Multi-microphone speech separation |
CN108663435A (en) * | 2018-04-12 | 2018-10-16 | 武汉光谷航天三江激光产业技术研究院有限公司 | A kind of distributed acoustic wave train wheel rail detection device and method |
CN109030628A (en) * | 2018-06-25 | 2018-12-18 | 北京交通大学 | Based on the matched track structure Evaluation Method of Mechanical Property of vibration noise spectrum signature |
CN109545228A (en) * | 2018-12-14 | 2019-03-29 | 厦门快商通信息技术有限公司 | A kind of end-to-end speaker's dividing method and system |
CN109785852A (en) * | 2018-12-14 | 2019-05-21 | 厦门快商通信息技术有限公司 | A kind of method and system enhancing speaker's voice |
CN110763698A (en) * | 2019-10-12 | 2020-02-07 | 仲恺农业工程学院 | Hyperspectral citrus leaf disease identification method based on characteristic wavelength |
CN111627458A (en) * | 2020-05-27 | 2020-09-04 | 北京声智科技有限公司 | Sound source separation method and equipment |
CN112144321A (en) * | 2020-09-18 | 2020-12-29 | 同济大学 | Nondestructive monitoring method for ballastless track slab cracks |
Non-Patent Citations (2)
Title |
---|
武思思: "《基于瞬态冲击响应的CRTS Ⅱ型板式无砟轨道脱空检测方法研究》", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 * |
维纳 K 英格尔: "《数字信号处理(MATLAB版)》", 31 July 2013, 西安交通大学出版社 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114818998A (en) * | 2022-06-28 | 2022-07-29 | 浙江大学 | Method for judging mud pumping disease state of ballastless track foundation bed during slurry turning |
CN114818998B (en) * | 2022-06-28 | 2022-09-13 | 浙江大学 | Method for judging mud pumping disease state of ballastless track foundation bed during slurry turning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Malekjafarian et al. | A review of mobile sensing of bridges using moving vehicles: Progress to date, challenges and future trends | |
CN106198062A (en) | The vehicle-mounted acoustic testing system of track vehicle fault and detection method | |
CN113705412B (en) | Track state detection method and device for multi-source data fusion based on deep learning | |
Liu et al. | Deep learning based identification and uncertainty analysis of metro train induced ground-borne vibration | |
Liang et al. | A traffic noise source identification method for buildings adjacent to multiple transport infrastructures based on deep learning | |
CN115879343B (en) | Ballastless track self-compacting concrete void two-stage identification method | |
Ramos-Romero et al. | Identification and mapping of asphalt surface deterioration by tyre-pavement interaction noise measurement | |
CN102157148A (en) | DTW (dynamic time warping) voice recognition-based truck examining method | |
CN113420367A (en) | Subway rail corrugation detection method and device based on vibration and noise response | |
CN113447570A (en) | Ballastless track disease detection method and system based on vehicle-mounted acoustic sensing | |
CN116842775A (en) | Bridge modal shape driving identification method capable of eliminating influence of road surface roughness | |
CN113281401B (en) | Detection method, system and device for hidden diseases of ballastless track | |
Zhang et al. | Ballasted track behaviour induced by absent sleeper support and its detection based on a convolutional neural network using track data | |
Siddiqui et al. | IoT based railway track faults detection and localization using acoustic analysis | |
Wang et al. | Damage detection of spatial track–bridge system with interlayer connection using high-speed train response and sensitivity analysis | |
Kojima et al. | Fault detection of railway track by multi-resolution analysis | |
Huang et al. | Quantification of dynamic track stiffness using machine learning | |
Karimpour et al. | A novel method in light-rail condition monitoring using smartphones | |
CN115575508A (en) | Rail transit rail corrugation identification method based on train vibration and sound composite characteristics | |
Elhattab | Drive-by bridge damage monitoring: Concise review | |
Miao et al. | Ballastless track mortar layer void detection by high-order statistical analysis of axle box acceleration | |
Uygun et al. | Acoustic monitoring of railway defects using deep learning with audio to spectrogram conversion | |
CN111354191B (en) | Lane driving condition determining method, device and equipment and storage medium | |
Li | Rail crack monitoring using acoustic emission technique | |
Zhou et al. | Detection of rail bottom damage based on BLS |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210928 |