CN111896625A - Real-time monitoring method and monitoring system for rail damage - Google Patents
Real-time monitoring method and monitoring system for rail damage Download PDFInfo
- Publication number
- CN111896625A CN111896625A CN202010826057.2A CN202010826057A CN111896625A CN 111896625 A CN111896625 A CN 111896625A CN 202010826057 A CN202010826057 A CN 202010826057A CN 111896625 A CN111896625 A CN 111896625A
- Authority
- CN
- China
- Prior art keywords
- damage
- real
- rail
- monitoring
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 93
- 238000000034 method Methods 0.000 title claims abstract description 67
- 229910000831 Steel Inorganic materials 0.000 claims abstract description 48
- 239000010959 steel Substances 0.000 claims abstract description 48
- 238000001514 detection method Methods 0.000 claims abstract description 45
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims abstract description 11
- 230000005284 excitation Effects 0.000 claims description 34
- 238000004458 analytical method Methods 0.000 claims description 27
- 238000006073 displacement reaction Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 239000006185 dispersion Substances 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 9
- 238000011176 pooling Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 238000010586 diagram Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 239000013598 vector Substances 0.000 claims description 7
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 230000035945 sensitivity Effects 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 3
- 238000005452 bending Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 abstract description 9
- 230000008901 benefit Effects 0.000 abstract description 2
- 239000000523 sample Substances 0.000 description 8
- 238000009826 distribution Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000005381 potential energy Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
- 238000003466 welding 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
-
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning or like safety means along the route or between vehicles or trains
- B61L23/04—Control, warning or like safety means along the route or between vehicles or trains for monitoring the mechanical state of the route
- B61L23/042—Track changes detection
- B61L23/044—Broken rails
-
- 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
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/023—Solids
- G01N2291/0234—Metals, e.g. steel
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Mechanical Engineering (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Signal Processing (AREA)
- Acoustics & Sound (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention discloses a real-time monitoring method for rail damage, which comprises the steps of arranging monitoring systems on two sides of a rail; acquiring real-time monitoring data obtained by a monitoring system; processing the real-time monitoring data to obtain a processed damage picture; identifying the processed damage picture by adopting a neural network architecture to obtain an identification result; and performing real-time early warning on the rail damage according to the recognition result and realizing real-time monitoring on the rail damage. The invention also discloses a monitoring system for realizing the real-time rail damage monitoring method. The rail damage detection system provided by the invention has the advantages that the ultrasonic transducer is used for monitoring the guide rail in real time, and collecting and processing data in real time, so that the real-time monitoring and damage positioning of the full-life-cycle structural state of the steel rail in the service period are realized, the early warning information is sent out, the rail damage detection accuracy and efficiency are improved, the maintenance and maintenance cost is reduced, the train running safety is improved, and the rail damage detection system is high in reliability, good in real-time performance and high in accuracy.
Description
Technical Field
The invention belongs to the field of steel rail monitoring, and particularly relates to a real-time steel rail damage monitoring method and a monitoring system thereof.
Background
With the development of economic technology and the improvement of living standard of people, the rail transit is widely applied to the production and the life of people, and brings endless convenience to the production and the life of people.
In the rail transit system, one of the threats of safe train operation and normal operation of the rail transit system is rail break. The rail can lead to the rail break because of nuclear damage and welding seam quality, if the rail break appears on the railway transportation line net, cause the transportation delay slightly, then probably cause the train to derail, topple major driving accident such as, and then cause very big casualties and loss of property. Therefore, the real-time monitoring of the whole life cycle of the steel rail in the service period becomes a problem which needs to be solved urgently.
At present, the rail flaw detection management rules of the railway department are compiled based on an ultrasonic detection technology, and basically take artificial flaw detection as a main part and a flaw detection vehicle as an auxiliary part. Once working is done in one period, the missed detection and the false detection are more, and the steel rail state between the two flaw detections cannot be known. The detection blind area exists to rail top surface and near surface fatigue damage, and the efficiency of detecting a flaw is low, can't accomplish the real-time supervision to rail health status and its change. With the development of high-speed railways, the traditional nondestructive detection method cannot meet the requirement of real-time monitoring under new situations.
Disclosure of Invention
The invention aims to provide a real-time rail damage monitoring method which is high in reliability, good in real-time performance and high in accuracy.
The invention also aims to provide a monitoring system for realizing the real-time rail damage monitoring method.
The invention provides a real-time monitoring method for rail damage, which comprises the following steps:
s1, laying monitoring systems on two sides of a steel rail;
s2, acquiring real-time monitoring data obtained by a monitoring system;
s3, performing data processing on the real-time monitoring data acquired in the step S2 to obtain a processed damage picture;
s4, identifying the processed damage picture obtained in the step S3 by adopting a neural network architecture so as to obtain an identification result;
and S5, performing real-time early warning on the rail damage according to the identification result obtained in the step S4, thereby realizing real-time monitoring on the rail damage.
And S1, arranging monitoring systems on two sides of the steel rail, wherein the monitoring systems specifically comprise ultrasonic transducers, signal receiving devices and control modules. Arranging a pair of ultrasonic transducers at two sides of the steel rail at set intervals, thereby dividing the whole detection section into a plurality of small sections and detecting; the data output end of the ultrasonic transducer is connected with the signal receiving device, and the data output end of the signal receiving device is connected with the control module; the ultrasonic transducer is used for generating ultrasonic guided waves and receiving reflected waves; the signal receiving device is used for receiving the reflected wave received by the ultrasonic transducer and uploading the reflected wave to the control module; and the control module is used for monitoring the damage of the steel rail in real time and carrying out early warning according to the received data.
The step S2 of acquiring the real-time monitoring data obtained by the monitoring system includes setting a detection channel and a monitoring frequency by the control module, completing excitation and reception of the ultrasonic guided waves by the ultrasonic transducer, performing digital-to-analog conversion by the signal receiving device, and uploading the digital-to-analog conversion to the control module.
When ultrasonic guided waves are generated, the guided waves in a bending mode are selected, the frequency dispersion characteristics of the guided waves are analyzed by adopting a semi-analytic finite element method, the sensitivity of specific guided waves to damage of different areas in the section of the steel rail is judged through a steel rail section wave structure diagram obtained through calculation, and a receiving position is arranged at a position where the guided waves in the steel rail are large in displacement.
The excitation position is calculated by adopting the following steps:
A. listing the positions of all external excitable nodes on the cross section of the steel rail, wherein each node has three degrees of freedom in three directions;
B. exciting by adopting a selected guided wave mode, generating three freedom degree displacement vectors of each node position, and drawing a curve graph of the three displacement vectors;
C. based on the statistical rule, removing smaller extreme points smaller than the set value;
D. and finally, according to the remaining local extreme points, taking the maximum amplitude position of 3 degrees of freedom as the optimal excitation point of the mode.
The guided wave excitation frequency and the analysis frequency are determined by the following steps:
a. selecting upper and lower limits of ultrasonic guided wave frequency, and dividing frequency measuring points at the same interval;
b. taking the measuring point frequency as an excitation frequency to carry out guided wave detection;
c. performing time-frequency analysis on the signals received by each measuring point;
d. drawing a guided wave time-frequency analysis graph corresponding to the excitation frequency;
e. the final guided wave excitation frequency and the analysis frequency are selected.
In step S3, the real-time monitoring data obtained in step S2 is subjected to data processing, so as to obtain a processed damage picture, specifically, the following steps are adopted for data processing:
(1) comparing the threshold value of the received real-time monitoring data: when the real-time monitoring data is larger than a set gate threshold value, generating B display data from the monitoring data;
(2) denoising and dividing the B display data obtained in the step (1):
noise reduction: neglecting small damage of less than N reflected echo points, and shielding continuous waveforms with single-point clutter and inconsistent angles by adopting an 8-neighborhood point continuity judgment method; n is a natural number;
and (3) dividing: and (3) segmenting the ultrasonic guided wave echo point close to the position on the B display image into one picture by utilizing a DBSCAN algorithm, thereby ensuring that each picture only contains 1 damage.
The method is characterized in that an ultrasonic guided wave echo point close to the position on a B display image is segmented into one picture by using a DBSCAN algorithm, so that each picture only contains 1 damage, and the method specifically comprises the following steps:
1) finding core points and forming temporary clustering clusters:
scanning all sample points: if the number of points in a certain sample point radius R range is larger than or equal to a set threshold value, taking the points as core points, and forming corresponding temporary clustering clusters by the points with the direct density of the core points;
2) merging the temporary clusters to obtain clusters:
for each temporary cluster, checking whether the point therein is a core point: if so, combining the corresponding temporary cluster with the current temporary cluster to obtain a new temporary cluster; repeating the step until each point in the current temporary clustering cluster is not a core point or the point with direct density is already in the temporary clustering cluster, and converting the temporary clustering cluster into a clustering cluster;
3) and repeating the step 2) until all the temporary clustering clusters are combined.
The neural network architecture of step S4, specifically, the AlexNet convolutional neural network architecture is adopted: the network architecture comprises 10 layers including 1 input layer, 3 convolutional layers, 3 pooling layers, 2 full-connection layers and 1 output layer; the input layer is B display data subjected to data preprocessing; obtaining an oversampling balance data set by adopting a smote algorithm, wherein the size of the processed data is 128 × 16 pixels; the input data is taken out from the whole detection file in a sliding mode, and the sliding step length is 42 pixels; performing feature extraction on input data by a convolution layer through convolution operation; the depth is 100 after passing through the three convolution layers; the pooling layer adopts a mean pooling method; all the activation functions select Relu functions; classifying input data by using a softmax function through fully connected layers, wherein the first fully connected layer is 2048 neurons, and the second fully connected layer comprises 1024 neurons; the output layer divides the damage condition into 8 types; the output layer is the probability of each damage type; randomly selecting 80% of various B display data sample sets as a training set, and using the rest 20% as a test set; early Stopping and dropout methods are adopted in the training process to prevent overfitting; the dropout method is used in two full-connection layers, and connection is closed according to the probability of 50% in the training process; the training learning rate is set to be 0.01, the accuracy of the test set is calculated every 5 rounds, and iteration is stopped after the accuracy is not improved any more after 15 consecutive rounds.
And S5, performing real-time early warning on the rail damage according to the recognition result obtained in the step S4, specifically, according to the rail damage recognition result obtained in the step S4, a control module of the detection system gives a maintenance prompt and a maintenance suggestion according to the type, the severity and the development rule of the damage, so that the purposes of timely finding the damage, processing the damage and performing maintenance at the initial stage of the occurrence of the damage are achieved.
The invention also provides a monitoring system for realizing the real-time monitoring method for the rail damage, which specifically comprises an ultrasonic transducer, a signal receiving device and a control module; arranging a pair of ultrasonic transducers at two sides of the steel rail at set intervals, thereby dividing the whole detection section into a plurality of small sections and detecting; the data output end of the ultrasonic transducer is connected with the signal receiving device, and the data output end of the signal receiving device is connected with the control module; the ultrasonic transducer is used for generating ultrasonic guided waves and receiving reflected waves; the signal receiving device is used for receiving the reflected wave received by the ultrasonic transducer and uploading the reflected wave to the control module; and the control module is used for monitoring the damage of the steel rail in real time and carrying out early warning according to the received data.
According to the rail damage real-time monitoring method and the rail damage real-time monitoring system, the ultrasonic transducer is used for monitoring the guide rail in real time, and collecting and processing data in real time, so that the real-time monitoring and damage positioning of the full-life-cycle structural state of the steel rail in the service period are realized, the early warning information is sent, the rail damage detection accuracy and efficiency are improved, the maintenance and maintenance cost is reduced, the train running safety is improved, and the rail damage real-time monitoring method and the rail damage real-time monitoring system are high in reliability, good in real-time performance and high in accuracy.
Drawings
FIG. 1 is a schematic process flow diagram of the process of the present invention.
FIG. 2 is a functional block diagram of the system of the present invention.
Fig. 3 is a schematic view of an initial interface of data analysis software in a preferred embodiment of a real-time rail damage monitoring method provided by the system of the present invention.
Detailed Description
FIG. 1 is a schematic flow chart of the method of the present invention: the invention provides a real-time monitoring method for rail damage, which comprises the following steps:
s1, laying monitoring systems on two sides of a steel rail;
s2, acquiring real-time monitoring data obtained by a monitoring system;
in the specific implementation:
when producing ultrasonic guided wave, select the guided wave of bending mode, adopt the frequency dispersion characteristic of semi-analytic finite element method analysis guided wave to the sensitivity of specific guided wave to different regional damages in the rail cross-section is judged to the rail section wave structure picture that obtains through the calculation, and guided wave displacement great department in the rail is established to the receiving position: the semi-analytic finite element method is a calculation method for solving the problem of dispersion in a waveguide medium with a complex cross section; when the method is adopted to calculate the frequency dispersion solution, only finite element dispersion is needed to be carried out on the cross section of the waveguide medium, and the displacement along the propagation direction of the waveguide medium is expressed in a vibration mode of simple harmonic waves; when a semi-analytic finite element method is used for solving, firstly, finite element meshing is carried out on the section of the steel rail, and the section of the plate is dispersed by a one-dimensional three-node unit; according to the Hamilton principle, strain energy and potential energy of any point in a waveguide medium are brought into a Hamilton formula, a wave equation of guided waves is deduced, and then the wave equation is converted into a standard characteristic equation form to be solved, so that the relation between wave number and frequency and the displacement distribution of any node of a steel rail are obtained, and a frequency dispersion characteristic curve is drawn; then, obtaining the displacement distribution of any node of the steel rail section according to a semi-analytic finite element method to obtain a wave structure chart; the wave structure represents the distribution of particle displacement energy along the depth direction in the wave propagation process, so that the propagation characteristics of guided waves with different frequencies and different modes in the steel rail can be visually presented, and damages are distinguished according to the mode vibration type; finally, the distribution of the guided waves in the section of the steel rail shows obvious regionality, and the distribution is influenced by the frequency of the guided waves; calculating to obtain a wave structure diagram through the former, analyzing the guided wave displacement at different positions in the steel rail, wherein the larger the displacement is, the higher the sensitivity of the guided wave to the damage of the area of the section of the steel rail is;
the excitation position is calculated by adopting the following steps:
A. listing the positions of all external excitable nodes on the cross section of the steel rail, wherein each node has three degrees of freedom in three directions;
B. exciting by adopting a selected guided wave mode, generating three freedom degree displacement vectors of each node position, and drawing a curve graph of the three displacement vectors;
the method specifically comprises the following steps: firstly, listing the positions of all external excitable nodes on a steel rail section, and determining the positions as feature points of all modes; setting the total number of all peripheral nodes of the steel rail section to be P, wherein each node comprises three-direction freedom degrees and corresponds to three-direction displacement; the displacement of each degree of freedom is respectively denoted as xi, yi, zi; and (3) sequentially numbering and listing the characteristic points from the left side of the rail bottom along the clockwise direction, and obtaining displacement vectors of three degrees of freedom of each characteristic point after applying excitation of a selected vibration mode: x ═ X1, X2, …, xp ], Y ═ Y1, Y2, …, yp ], Z ═ Z1, Z2, …, zp ];
C. based on the statistical rule, removing smaller extreme points smaller than the set value;
D. finally, according to the remaining local extreme points, taking the maximum amplitude position of 3 degrees of freedom as the optimal excitation point of the mode;
the method specifically comprises the following steps: the basic idea of the optimal excitation position positioning algorithm is to excite at the maximum amplitude position of the three degrees of freedom of the vibration mode, and because vibration curves of different modes are different, the maximum amplitude position needs to be searched for excitation according to the actual conditions of the vibration curves;
the guided wave excitation frequency and the analysis frequency are determined by the following steps:
a. selecting upper and lower limits of ultrasonic guided wave frequency, and dividing frequency measuring points at the same interval;
b. taking the measuring point frequency as an excitation frequency to carry out guided wave detection;
c. performing time-frequency analysis on the signals received by each measuring point;
d. drawing a guided wave time-frequency analysis graph of the excitation frequency corresponding to the selected frequency;
e. selecting a final guided wave excitation frequency and an analysis frequency;
the method specifically comprises the following steps: the ultrasonic guided wave detection frequency range suitable for the steel rail is 30-100 kHz; measuring points are divided at equal intervals within the upper limit frequency range and the lower limit frequency range at 2 kHz; performing guided wave detection by taking the measuring points as excitation frequencies; respectively carrying out wavelet transformation on the received signal of each measuring point to obtain a time-frequency analysis result of the guided wave received signal of each measuring point; adding the amplitudes of the corresponding time points and frequency points in all the time-frequency analysis results respectively to obtain a guided wave time-frequency analysis graph of which the excitation frequency corresponds to the selected frequency range in the guided wave detection, wherein the graph can visually present the distribution, strength and dispersion characteristics of different guided wave modes in each frequency band; according to the time-frequency analysis graph, the frequency with the maximum amplitude near the zero moment in the graph is used as guided wave excitation frequency, the frequency range with the larger amplitude at the receiving moment is used as a guided wave analysis frequency band, and guided wave excitation and analysis frequency which accords with the principles of small mode number, easy identification, ideal amplitude and the like is obtained;
s3, performing data processing on the real-time monitoring data acquired in the step S2 to obtain a processed damage picture; specifically, the following steps are adopted for data processing:
(1) comparing the threshold value of the received real-time monitoring data: when the real-time monitoring data is larger than a set gate threshold value, generating B display data from the monitoring data;
(2) denoising and dividing the B display data obtained in the step (1):
noise reduction: neglecting small damage of less than N reflected echo points, and shielding continuous waveforms with single-point clutter and inconsistent angles by adopting an 8-neighborhood point continuity judgment method; n is a natural number;
and (3) dividing: dividing the ultrasonic guided wave echo point close to the position on the B display image into one picture by using a DBSCAN algorithm, thereby ensuring that each picture only contains 1 damage; the method specifically comprises the following steps:
1) finding core points and forming temporary clustering clusters:
scanning all sample points: if the number of points in a certain sample point radius R range is larger than or equal to a set threshold value, taking the points as core points, and forming corresponding temporary clustering clusters by the points with the direct density of the core points;
2) merging the temporary clusters to obtain clusters:
for each temporary cluster, checking whether the point therein is a core point: if so, combining the corresponding temporary cluster with the current temporary cluster to obtain a new temporary cluster; repeating the step until each point in the current temporary clustering cluster is not a core point or the point with direct density is already in the temporary clustering cluster, and converting the temporary clustering cluster into a clustering cluster;
3) repeating the step 2) until all the temporary clustering clusters are combined;
s4, identifying the processed damage picture obtained in the step S3 by adopting a neural network architecture so as to obtain an identification result; specifically, an AlexNet convolution neural network architecture is adopted: the network architecture comprises 10 layers including 1 input layer, 3 convolutional layers, 3 pooling layers, 2 full-connection layers and 1 output layer; the input layer is B display data subjected to data preprocessing; obtaining an oversampling balance data set by adopting a smote algorithm, wherein the size of the processed data is 128 × 16 pixels; the input data is taken out from the whole detection file in a sliding mode, and the sliding step length is 42 pixels; performing feature extraction on input data by a convolution layer through convolution operation; the depth is 100 after passing through the three convolution layers; the pooling layer adopts a mean pooling method; all the activation functions select Relu functions; classifying input data by using a softmax function through fully connected layers, wherein the first fully connected layer is 2048 neurons, and the second fully connected layer comprises 1024 neurons; the damage condition is divided into 8 types (no damage (including normal screw holes and wire holes), rail head nuclear damage, rail web inclined crack, rail web separation, rail bottom crescent damage, rail joint damage, screw hole crack and other damage) by the output layer, wherein the output layer is the probability of generating each damage type; the output layer is the probability of each damage type; randomly selecting 80% of various B display data sample sets as a training set, and using the rest 20% as a test set; early Stopping and dropout methods are adopted in the training process to prevent overfitting; the dropout method is used in two full-connection layers, and connection is closed according to the probability of 50% in the training process; the training learning rate is set to be 0.01, the accuracy of the test set is calculated every 5 rounds, and iteration is stopped after the accuracy is not improved any more after 15 rounds of continuous training;
and S5, performing real-time early warning on the rail damage according to the identification result obtained in the step S4, thereby realizing real-time monitoring on the rail damage.
FIG. 2 shows a functional block diagram of the system of the present invention: the monitoring system for realizing the real-time monitoring method of the rail damage specifically comprises an ultrasonic transducer, a signal receiving device and a control module; arranging a pair of ultrasonic transducers at two sides of the steel rail at set intervals, thereby dividing the whole detection section into a plurality of small sections and detecting; the data output end of the ultrasonic transducer is connected with the signal receiving device, and the data output end of the signal receiving device is connected with the control module; the ultrasonic transducer is used for generating ultrasonic guided waves and receiving reflected waves; the signal receiving device is used for receiving the reflected wave received by the ultrasonic transducer and uploading the reflected wave to the control module; and the control module is used for monitoring the damage of the steel rail in real time and carrying out early warning according to the received data.
FIG. 3 is a schematic diagram of an initial interface of data analysis software of the system of the present invention: the left side column displays a real-time monitoring early warning result, and each piece of early warning information can be clicked to check the detailed condition of the damage; the checking of a specific analysis object is realized through a menu bar 'loading data', an analysis result is displayed in each sub-window of a page and comprises data information (probe number and detection time), a frequency dispersion curve, an excitation response result, a damage processing picture obtained from B display data, a damage judgment result obtained from a neural network and damage early warning information obtained according to the analysis result; the menu 'acquisition parameter setting' is used for setting acquisition frequency, channels and other damage data acquisition schemes; the menu 'data identification parameter' is used for setting parameter values in the damage data identification calculation such as B display data generation, damage picture processing, neural network algorithm and the like.
The invention provides a rail damage real-time monitoring method based on ultrasonic guided waves, which comprises the following steps: firstly, laying monitoring systems on two sides of a steel rail, wherein each monitoring system comprises an ultrasonic transducer, a signal receiving device and a control module; then, acquiring real-time monitoring data obtained by a monitoring system; then, carrying out data processing on the acquired real-time monitoring data to obtain a processed damage picture; then, recognizing the processed damage picture by adopting a neural network architecture to obtain a recognition result; and finally, performing real-time early warning on the rail damage according to the recognition result, thereby realizing real-time monitoring of the rail damage, being conductive to solving the practical problems of the railway industry at present, providing scientific guarantee for railway safety operation, being conductive to improving the core competitiveness of the high-speed railway technology in China and promoting the international continuous leading effect of high-speed railway in China.
Furthermore, the invention sets an ultrasonic guided wave excitation and receiving scheme for flaw detection from three aspects of guided wave propagation characteristic analysis, guided wave excitation and receiving frequency determination and optimal excitation position positioning analysis, provides real, effective, objective and large amount of data support for all-weather automatic monitoring of the steel rail, greatly reduces the labor intensity of a line flaw detector, and avoids the problems of untimely detection existing in the current period detection and flaw detection blind area, missed detection and mistaken detection existing in an ultrasonic detection device.
The method has the advantages that the steel rail section wave structure diagram obtained by calculation has good intuitiveness, the propagation characteristics of guided waves with different frequencies and modes in the steel rail can be conveniently analyzed, and the method is very suitable for evaluating the sensitivity of the guided waves on the damage of different areas in the steel rail section; the guided wave excitation frequency and the analysis frequency with few modes, easy identification and ideal amplitude can be preferably selected through wavelet transformation analysis, the method has the characteristics of convenience and intuition, and the problem of mismatching between the theoretical analysis based on a frequency dispersion curve and actual guided wave detection when the guided wave excitation frequency is selected is effectively solved; the proper ultrasonic guided wave probe mounting position can be obtained through calculation by an optimal excitation position positioning algorithm, so that the deviation degree between the optimal excitation position and the actual mounting position is small; and then confirm that the frequency dispersion is weak, the attenuation is little, sensitive to damage and have better rail guided wave mode of the recognition degree under the different environment, improve the detection ability to the tiny defect of rail effectively, has guaranteed the rationality and validity that the transducer, guided wave arouse and receiving scheme of rail flaw detection were designed, the practicality of the method is strong.
In addition, compared with the prior art, the method for analyzing the steel rail damage data is designed by adopting a neural network architecture, ultrasonic guided wave B display data is input into the recognition system, the damaged picture is processed by utilizing a DBSCAN algorithm, rules are learned from a large amount of data by utilizing a deep learning method, and the purpose of accurately and quickly extracting data characteristics is achieved, so that the comprehensive and accurate recognition of the steel rail damage position and the damage type is realized, the detection effect with high efficiency and low cost is achieved, meanwhile, technical support is provided for establishing a characteristic database, and more accurate, objective and effective basis is provided for fault troubleshooting and state maintenance. The method converts the problem of object detection into the problem of classification, effectively improves the intuition of the detection result, has good robustness and generalization capability, and has better detection effect and efficiency than the traditional image processing method and manual identification.
Compared with the prior art, the real-time monitoring and early warning system for the damage of the steel rail sends out early warning information on the basis of real-time monitoring of the damage, ensures that the current alarm can be uploaded to a monitoring center and related personnel at the first time in the early stage of rail breakage, is convenient for managers to take measures in time, avoids driving safety accidents and loss of lives and properties, and reduces maintenance cost.
Claims (9)
1. A real-time rail damage monitoring method comprises the following steps:
s1, laying monitoring systems on two sides of a steel rail;
s2, acquiring real-time monitoring data obtained by a monitoring system;
s3, performing data processing on the real-time monitoring data acquired in the step S2 to obtain a processed damage picture;
s4, identifying the processed damage picture obtained in the step S3 by adopting a neural network architecture so as to obtain an identification result;
and S5, performing real-time early warning on the rail damage according to the identification result obtained in the step S4, thereby realizing real-time monitoring on the rail damage.
2. The method for real-time monitoring the rail damage according to claim 1, wherein the monitoring systems are arranged on two sides of the rail in step S1, specifically, a pair of ultrasonic transducers are arranged on two sides of the rail at set intervals, so that the whole detection section is divided into a plurality of small sections for detection; the data output end of the ultrasonic transducer is connected with the signal receiving device, and the data output end of the signal receiving device is connected with the control module; the ultrasonic transducer is used for generating ultrasonic guided waves and receiving reflected waves; the signal receiving device is used for receiving the reflected wave received by the ultrasonic transducer and uploading the reflected wave to the control module; and the control module is used for monitoring the damage of the steel rail in real time and carrying out early warning according to the received data.
3. The method for monitoring the damage of the steel rail in real time according to the claim 2, characterized in that when ultrasonic guided waves are generated, the guided waves in bending mode are selected, the frequency dispersion characteristic of the guided waves is analyzed by adopting a semi-analytic finite element method, the sensitivity of the specific guided waves to the damage of different areas in the section of the steel rail is judged through a steel rail section wave structure diagram obtained by calculation, and the receiving position is arranged at the position of the steel rail where the guided waves have larger displacement.
4. A method for real-time monitoring of rail damage according to claim 2, further characterized by calculating the location of excitation using the steps of:
A. listing the positions of all external excitable nodes on the cross section of the steel rail, wherein each node has three degrees of freedom in three directions;
B. exciting by adopting a selected guided wave mode, generating three freedom degree displacement vectors of each node position, and drawing a curve graph of the three displacement vectors;
C. based on the statistical rule, removing smaller extreme points smaller than the set value;
D. and finally, according to the remaining local extreme points, taking the maximum amplitude position of 3 degrees of freedom as the optimal excitation point of the mode.
5. A rail flaw real-time monitoring method as claimed in claim 2, further characterised by determining the guided wave excitation frequency and the analysis frequency by:
a. selecting upper and lower limits of ultrasonic guided wave frequency, and dividing frequency measuring points at the same interval;
b. taking the measuring point frequency as an excitation frequency to carry out guided wave detection;
c. performing time-frequency analysis on the signals received by each measuring point;
d. drawing a guided wave time-frequency analysis graph of the excitation frequency corresponding to the selected frequency;
e. the final guided wave excitation frequency and the analysis frequency are selected.
6. A rail damage real-time monitoring method according to any one of claims 1 to 5, wherein the step S3 is to perform data processing on the real-time monitoring data obtained in the step S2 to obtain a processed damage picture, and specifically, the data processing is performed by the following steps:
(1) comparing the threshold value of the received real-time monitoring data: when the real-time monitoring data is larger than a set gate threshold value, generating B display data from the monitoring data;
(2) denoising and dividing the B display data obtained in the step (1):
noise reduction: neglecting small damage of less than N reflected echo points, and shielding continuous waveforms with single-point clutter and inconsistent angles by adopting an 8-neighborhood point continuity judgment method; n is a natural number;
and (3) dividing: and (3) segmenting the ultrasonic guided wave echo point close to the position on the B display image into one picture by utilizing a DBSCAN algorithm, thereby ensuring that each picture only contains 1 damage.
7. The method for monitoring the damage to the steel rail in real time according to claim 6, wherein the DBSCAN algorithm is used for dividing the ultrasonic guided wave echo point adjacent to the position on the B-display image into one picture, so that each picture only contains 1 damage, and the method specifically comprises the following steps:
1) finding core points and forming temporary clustering clusters:
scanning all sample points: if the number of points in a certain sample point radius R range is larger than or equal to a set threshold value, taking the points as core points, and forming corresponding temporary clustering clusters by the points with the direct density of the core points;
2) merging the temporary clusters to obtain clusters:
for each temporary cluster, checking whether the point therein is a core point: if so, combining the corresponding temporary cluster with the current temporary cluster to obtain a new temporary cluster; repeating the step until each point in the current temporary clustering cluster is not a core point or the point with direct density is already in the temporary clustering cluster, and converting the temporary clustering cluster into a clustering cluster;
3) and repeating the step 2) until all the temporary clustering clusters are combined.
8. A rail damage real-time monitoring method according to any one of claims 1 to 5, wherein the neural network architecture of step S4 is specifically an AlexNet convolutional neural network architecture: the network architecture comprises 10 layers including 1 input layer, 3 convolutional layers, 3 pooling layers, 2 full-connection layers and 1 output layer; the input layer is B display data subjected to data preprocessing; obtaining an oversampling balance data set by adopting a smote algorithm, wherein the size of the processed data is 128 × 16 pixels; the input data is taken out from the whole detection file in a sliding mode, and the sliding step length is 42 pixels; performing feature extraction on input data by a convolution layer through convolution operation; the depth is 100 after passing through the three convolution layers; the pooling layer adopts a mean pooling method; all the activation functions select Relu functions; classifying input data by using a softmax function through fully connected layers, wherein the first fully connected layer is 2048 neurons, and the second fully connected layer comprises 1024 neurons; the output layer divides the damage condition into 8 types; the output layer is the probability of each damage type; randomly selecting 80% of various B display data sample sets as a training set, and using the rest 20% as a test set; early Stopping and dropout methods are adopted in the training process to prevent overfitting; the dropout method is used in two full-connection layers, and connection is closed according to the probability of 50% in the training process; the training learning rate is set to be 0.01, the accuracy of the test set is calculated every 5 rounds, and iteration is stopped after the accuracy is not improved any more after 15 consecutive rounds.
9. A monitoring system for realizing the real-time rail damage monitoring method of any one of claims 1 to 8, which is characterized by comprising an ultrasonic transducer, a signal receiving device and a control module; arranging a pair of ultrasonic transducers at two sides of the steel rail at set intervals, thereby dividing the whole detection section into a plurality of small sections and detecting; the data output end of the ultrasonic transducer is connected with the signal receiving device, and the data output end of the signal receiving device is connected with the control module; the ultrasonic transducer is used for generating ultrasonic guided waves and receiving reflected waves; the signal receiving device is used for receiving the reflected wave received by the ultrasonic transducer and uploading the reflected wave to the control module; and the control module is used for monitoring the damage of the steel rail in real time and carrying out early warning according to the received data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010826057.2A CN111896625B (en) | 2020-08-17 | 2020-08-17 | Rail damage real-time monitoring method and monitoring system thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010826057.2A CN111896625B (en) | 2020-08-17 | 2020-08-17 | Rail damage real-time monitoring method and monitoring system thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111896625A true CN111896625A (en) | 2020-11-06 |
CN111896625B CN111896625B (en) | 2023-07-14 |
Family
ID=73230436
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010826057.2A Active CN111896625B (en) | 2020-08-17 | 2020-08-17 | Rail damage real-time monitoring method and monitoring system thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111896625B (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112465684A (en) * | 2020-11-09 | 2021-03-09 | 覃强 | Full life cycle management system of track |
CN112464524A (en) * | 2020-11-07 | 2021-03-09 | 西南交通大学 | Method for determining guided wave propagation characteristics of turnout variable cross-section steel rail |
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 |
CN113239492A (en) * | 2021-04-09 | 2021-08-10 | 山东建筑大学 | Tower crane body steel structure damage positioning and monitoring method |
CN113447572A (en) * | 2021-09-01 | 2021-09-28 | 深圳市信润富联数字科技有限公司 | Steel rail flaw detection method, electronic device, steel rail flaw detection vehicle and readable storage medium |
CN113533511A (en) * | 2021-06-29 | 2021-10-22 | 北京交通大学 | Steel rail weld joint monitoring method based on deep learning network model |
CN113640308A (en) * | 2021-08-31 | 2021-11-12 | 郑州铁路职业技术学院 | Track abnormity monitoring system based on machine vision |
CN113740433A (en) * | 2021-09-18 | 2021-12-03 | 哈尔滨工业大学 | Device and method for detecting large lifting distance of SH guided wave EMAT of rail bottom crack of steel rail |
CN113791034A (en) * | 2021-09-30 | 2021-12-14 | 合肥德泰轨交数据有限公司 | Sample collection and classification supervision system for steel rail flaw detection |
CN113808095A (en) * | 2021-09-13 | 2021-12-17 | 合肥德泰科通测控技术有限公司 | Big data-based intelligent damage identification and analysis system for railway steel rails |
CN113884567A (en) * | 2021-06-29 | 2022-01-04 | 北京交通大学 | Steel rail weld damage detection method and device based on ultrasonic Lamb waves |
CN114062490A (en) * | 2021-06-29 | 2022-02-18 | 北京交通大学 | Rail weld Lamb wave modal decomposition and crack damage monitoring method based on GAN |
CN114802344A (en) * | 2022-04-30 | 2022-07-29 | 西安市轨道交通集团有限公司 | Ultrasonic wave and carrier broken rail monitoring system |
CN114862744A (en) * | 2021-02-04 | 2022-08-05 | 北京洞微科技发展有限公司 | Steel rail support bit classification method and system based on convolutional neural network |
CN115144474A (en) * | 2022-06-27 | 2022-10-04 | 东莞灵虎智能科技有限公司 | Ultrasonic signal data quality detection method |
JP7177561B1 (en) * | 2021-06-11 | 2022-11-24 | 東莞理工学院 | A Method for Detecting Screw Hole Cracks in Rail Joints with Nonlinear Ultrasonic Harmonics |
Citations (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE2500286A1 (en) * | 1975-01-04 | 1976-07-15 | Ruhrkohle Ag | Powered mine support shield units - shifting cylinder channel has floor clearance pusher to remove fine coal |
JP2002090308A (en) * | 2000-09-19 | 2002-03-27 | Nippon Denro Kk | Evaluation system for degree of surface degradation of steel using image processing |
US20040085546A1 (en) * | 2002-09-09 | 2004-05-06 | Hill Henry A. | Measurement and compensation of errors in interferometers |
US20040230385A1 (en) * | 2003-05-12 | 2004-11-18 | Bechhoefer Eric Robert | Wire fault detection |
US6846270B1 (en) * | 1999-02-25 | 2005-01-25 | Grant Etnyre | Method and apparatus for assisting or resisting postures or movements related to the joints of humans or devices |
JP2005235258A (en) * | 2004-02-17 | 2005-09-02 | Fuji Electric Holdings Co Ltd | Inspection method of surface of magnetic recording medium |
JP2007004390A (en) * | 2005-06-22 | 2007-01-11 | Ntt Docomo Inc | Sensor network system, cluster formation method, and sensor node |
US20070053588A1 (en) * | 2005-09-08 | 2007-03-08 | Chao-Lieh Chen | Method for retrieving original intact characteristics of heavily polluted images and its image processing |
CN101571519A (en) * | 2009-06-16 | 2009-11-04 | 北京理工大学 | Ultrasonic guided wave detection technology for quantifying defects of composite laminated plate |
CN102175768A (en) * | 2011-02-22 | 2011-09-07 | 哈尔滨工业大学 | Method and device for detecting defects and failures of high-speed rail based on vibration signals |
US20110297829A1 (en) * | 2010-06-08 | 2011-12-08 | Frank Altmann | Three-dimensional hot spot localization |
WO2013097153A1 (en) * | 2011-12-27 | 2013-07-04 | 华南理工大学 | Radio ultrasound wave probe assembly for crawler belt-type steel rail test and test method thereof |
CN104020221A (en) * | 2014-05-30 | 2014-09-03 | 杨媛 | Real-time broken-rail detecting and positioning system based on ultrasonic guided waves |
CN104297346A (en) * | 2014-09-11 | 2015-01-21 | 天津大学 | Nondestructive detection system of sheet metal by ultrasonic planar guided-wave and detection method thereof |
CN205176149U (en) * | 2015-11-10 | 2016-04-20 | 台州红炭电子科技有限公司 | RFID antenna performance testing arrangement on machine is got ready to RFID antenna |
CN108956787A (en) * | 2018-06-13 | 2018-12-07 | 西安理工大学 | A kind of rail failure detection method neural network based |
CN109543303A (en) * | 2018-11-22 | 2019-03-29 | 华北水利水电大学 | A method of the Damage Assessment Method to be perturbed based on class curvature of the flexibility difference matrix and frequency |
CN109649432A (en) * | 2019-01-23 | 2019-04-19 | 浙江大学 | Cloud platform rail integrity monitoring systems and method based on guided wave technology |
WO2019201176A1 (en) * | 2018-04-17 | 2019-10-24 | 江苏必得科技股份有限公司 | Method and device for predicting crack damage of train component |
WO2019201178A1 (en) * | 2018-04-17 | 2019-10-24 | 江苏必得科技股份有限公司 | Train component crack damage detection method and system based on lamb wave imaging |
WO2020156348A1 (en) * | 2019-01-31 | 2020-08-06 | 青岛理工大学 | Structural damage identification method based on ensemble empirical mode decomposition and convolution neural network |
AU2020101234A4 (en) * | 2020-07-02 | 2020-08-06 | Hunan University Of Science And Technology | An Optimization Method for Excitation Parameters of Ultrasonic Infrared Thermography Crack Nondestructive Testing |
-
2020
- 2020-08-17 CN CN202010826057.2A patent/CN111896625B/en active Active
Patent Citations (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE2500286A1 (en) * | 1975-01-04 | 1976-07-15 | Ruhrkohle Ag | Powered mine support shield units - shifting cylinder channel has floor clearance pusher to remove fine coal |
US6846270B1 (en) * | 1999-02-25 | 2005-01-25 | Grant Etnyre | Method and apparatus for assisting or resisting postures or movements related to the joints of humans or devices |
JP2002090308A (en) * | 2000-09-19 | 2002-03-27 | Nippon Denro Kk | Evaluation system for degree of surface degradation of steel using image processing |
US20040085546A1 (en) * | 2002-09-09 | 2004-05-06 | Hill Henry A. | Measurement and compensation of errors in interferometers |
US20040230385A1 (en) * | 2003-05-12 | 2004-11-18 | Bechhoefer Eric Robert | Wire fault detection |
JP2005235258A (en) * | 2004-02-17 | 2005-09-02 | Fuji Electric Holdings Co Ltd | Inspection method of surface of magnetic recording medium |
JP2007004390A (en) * | 2005-06-22 | 2007-01-11 | Ntt Docomo Inc | Sensor network system, cluster formation method, and sensor node |
US20070053588A1 (en) * | 2005-09-08 | 2007-03-08 | Chao-Lieh Chen | Method for retrieving original intact characteristics of heavily polluted images and its image processing |
CN101571519A (en) * | 2009-06-16 | 2009-11-04 | 北京理工大学 | Ultrasonic guided wave detection technology for quantifying defects of composite laminated plate |
US20110297829A1 (en) * | 2010-06-08 | 2011-12-08 | Frank Altmann | Three-dimensional hot spot localization |
CN102175768A (en) * | 2011-02-22 | 2011-09-07 | 哈尔滨工业大学 | Method and device for detecting defects and failures of high-speed rail based on vibration signals |
WO2013097153A1 (en) * | 2011-12-27 | 2013-07-04 | 华南理工大学 | Radio ultrasound wave probe assembly for crawler belt-type steel rail test and test method thereof |
CN104020221A (en) * | 2014-05-30 | 2014-09-03 | 杨媛 | Real-time broken-rail detecting and positioning system based on ultrasonic guided waves |
CN104297346A (en) * | 2014-09-11 | 2015-01-21 | 天津大学 | Nondestructive detection system of sheet metal by ultrasonic planar guided-wave and detection method thereof |
CN205176149U (en) * | 2015-11-10 | 2016-04-20 | 台州红炭电子科技有限公司 | RFID antenna performance testing arrangement on machine is got ready to RFID antenna |
WO2019201176A1 (en) * | 2018-04-17 | 2019-10-24 | 江苏必得科技股份有限公司 | Method and device for predicting crack damage of train component |
WO2019201178A1 (en) * | 2018-04-17 | 2019-10-24 | 江苏必得科技股份有限公司 | Train component crack damage detection method and system based on lamb wave imaging |
CN108956787A (en) * | 2018-06-13 | 2018-12-07 | 西安理工大学 | A kind of rail failure detection method neural network based |
CN109543303A (en) * | 2018-11-22 | 2019-03-29 | 华北水利水电大学 | A method of the Damage Assessment Method to be perturbed based on class curvature of the flexibility difference matrix and frequency |
CN109649432A (en) * | 2019-01-23 | 2019-04-19 | 浙江大学 | Cloud platform rail integrity monitoring systems and method based on guided wave technology |
WO2020156348A1 (en) * | 2019-01-31 | 2020-08-06 | 青岛理工大学 | Structural damage identification method based on ensemble empirical mode decomposition and convolution neural network |
AU2020101234A4 (en) * | 2020-07-02 | 2020-08-06 | Hunan University Of Science And Technology | An Optimization Method for Excitation Parameters of Ultrasonic Infrared Thermography Crack Nondestructive Testing |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112464524A (en) * | 2020-11-07 | 2021-03-09 | 西南交通大学 | Method for determining guided wave propagation characteristics of turnout variable cross-section steel rail |
CN112465684A (en) * | 2020-11-09 | 2021-03-09 | 覃强 | Full life cycle management system of track |
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 |
CN114862744A (en) * | 2021-02-04 | 2022-08-05 | 北京洞微科技发展有限公司 | Steel rail support bit classification method and system based on convolutional neural network |
CN113239492A (en) * | 2021-04-09 | 2021-08-10 | 山东建筑大学 | Tower crane body steel structure damage positioning and monitoring method |
JP7177561B1 (en) * | 2021-06-11 | 2022-11-24 | 東莞理工学院 | A Method for Detecting Screw Hole Cracks in Rail Joints with Nonlinear Ultrasonic Harmonics |
CN113884567A (en) * | 2021-06-29 | 2022-01-04 | 北京交通大学 | Steel rail weld damage detection method and device based on ultrasonic Lamb waves |
CN114062490A (en) * | 2021-06-29 | 2022-02-18 | 北京交通大学 | Rail weld Lamb wave modal decomposition and crack damage monitoring method based on GAN |
CN114062490B (en) * | 2021-06-29 | 2023-12-08 | 北京交通大学 | GAN-based rail weld Lamb wave modal decomposition and crack damage monitoring method |
CN113884567B (en) * | 2021-06-29 | 2023-12-08 | 北京交通大学 | Rail weld damage detection method and device based on ultrasonic Lamb wave |
CN113533511A (en) * | 2021-06-29 | 2021-10-22 | 北京交通大学 | Steel rail weld joint monitoring method based on deep learning network model |
CN113640308A (en) * | 2021-08-31 | 2021-11-12 | 郑州铁路职业技术学院 | Track abnormity monitoring system based on machine vision |
CN113640308B (en) * | 2021-08-31 | 2024-03-29 | 夏冰心 | Rail anomaly monitoring system based on machine vision |
CN113447572A (en) * | 2021-09-01 | 2021-09-28 | 深圳市信润富联数字科技有限公司 | Steel rail flaw detection method, electronic device, steel rail flaw detection vehicle and readable storage medium |
CN113808095A (en) * | 2021-09-13 | 2021-12-17 | 合肥德泰科通测控技术有限公司 | Big data-based intelligent damage identification and analysis system for railway steel rails |
CN113740433A (en) * | 2021-09-18 | 2021-12-03 | 哈尔滨工业大学 | Device and method for detecting large lifting distance of SH guided wave EMAT of rail bottom crack of steel rail |
CN113791034B (en) * | 2021-09-30 | 2022-09-06 | 合肥德泰轨交数据有限公司 | Sample collection and classification supervision system for steel rail flaw detection |
CN113791034A (en) * | 2021-09-30 | 2021-12-14 | 合肥德泰轨交数据有限公司 | Sample collection and classification supervision system for steel rail flaw detection |
CN114802344A (en) * | 2022-04-30 | 2022-07-29 | 西安市轨道交通集团有限公司 | Ultrasonic wave and carrier broken rail monitoring system |
CN115144474A (en) * | 2022-06-27 | 2022-10-04 | 东莞灵虎智能科技有限公司 | Ultrasonic signal data quality detection method |
CN115144474B (en) * | 2022-06-27 | 2024-05-28 | 东莞灵虎智能科技有限公司 | Ultrasonic signal data quality detection method |
Also Published As
Publication number | Publication date |
---|---|
CN111896625B (en) | 2023-07-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111896625A (en) | Real-time monitoring method and monitoring system for rail damage | |
CN108569607B (en) | Elevator fault early warning method based on bidirectional gating cyclic neural network | |
CN101900708B (en) | Vibration and audio signal-based high-speed train track defect detecting method | |
CN111965246B (en) | Scraper machine fault detection method and system based on multi-information fusion | |
CN106274977A (en) | The direct current Magnetic Flux Leakage Testing System of a kind of trigger-type drainage pattern and method thereof | |
CN111767897B (en) | Rail crack defect identification method based on support vector machine | |
CN102735747A (en) | Defect quantitative identification method of high-speed magnetic flux leakage inspection of high-speed railway rails | |
CN1743839A (en) | Structure defect ultrasonic on-line intelligent identifying system and identifying method | |
CN106198749A (en) | A kind of data fusion method of multiple sensor based on Metal Crack monitoring | |
US11821848B2 (en) | Laser-based non-destructive spike defect inspection system | |
CN114166943A (en) | Active rail damage monitoring method and terminal based on nonlinear ultrasonic waves | |
CN111767913A (en) | Motor train unit vehicle fault dynamic image detection method based on deep learning | |
CN117825516A (en) | Ultrasonic defect detection system and method with accurate positioning | |
CN106645399B (en) | A kind of damage Detection of Smart Composite Structure appraisal procedure and system | |
CN113281401B (en) | Detection method, system and device for hidden diseases of ballastless track | |
CN2809640Y (en) | Ultrasonic online intelligent recognition system for structural defect | |
CN113418986A (en) | Voiceprint detection system for bridge tunnel | |
CN108205016A (en) | The industrial computer system of sound emission safety of tower crane detection | |
US20230024104A1 (en) | Identification of false transformer humming using machine learning | |
CN115575508A (en) | Rail transit rail corrugation identification method based on train vibration and sound composite characteristics | |
CN110940732B (en) | Steel rail structure corrosion online monitoring and evaluation method | |
CN115270875A (en) | Diaphragm pump running state monitoring method based on deep learning | |
CN102279222B (en) | 16Mn steel load carrying piece fatigue damage state identification system | |
CN110988138B (en) | Weld assembly quality detection device and method | |
CN112649513A (en) | Railway artificial intelligence damage judging method based on image recognition |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |