CN110316227B - Heavy-duty train running state identification method and device - Google Patents
Heavy-duty train running state identification method and device Download PDFInfo
- Publication number
- CN110316227B CN110316227B CN201910544615.3A CN201910544615A CN110316227B CN 110316227 B CN110316227 B CN 110316227B CN 201910544615 A CN201910544615 A CN 201910544615A CN 110316227 B CN110316227 B CN 110316227B
- Authority
- CN
- China
- Prior art keywords
- track
- train
- signal diagram
- vibration information
- running
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000010586 diagram Methods 0.000 claims abstract description 123
- 238000005070 sampling Methods 0.000 claims description 61
- 238000003708 edge detection Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 18
- 238000012937 correction Methods 0.000 claims description 15
- 238000001914 filtration Methods 0.000 claims description 10
- 230000001629 suppression Effects 0.000 claims description 10
- 230000009977 dual effect Effects 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 description 16
- 238000004590 computer program Methods 0.000 description 7
- 238000011161 development Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 239000013307 optical fiber Substances 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003137 locomotive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L25/00—Recording or indicating positions or identities of vehicles or trains or setting of track apparatus
- B61L25/02—Indicating or recording positions or identities of vehicles or trains
- B61L25/021—Measuring and recording of train speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L25/00—Recording or indicating positions or identities of vehicles or trains or setting of track apparatus
- B61L25/02—Indicating or recording positions or identities of vehicles or trains
- B61L25/023—Determination of driving direction of vehicle or train
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L25/00—Recording or indicating positions or identities of vehicles or trains or setting of track apparatus
- B61L25/02—Indicating or recording positions or identities of vehicles or trains
- B61L25/025—Absolute localisation, e.g. providing geodetic coordinates
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H9/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
- G01H9/004—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means using fibre optic sensors
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a method and a device for identifying the running state of a heavy-duty train. The method comprises the following steps: acquiring vibration information of a track when a train runs on the track; acquiring a running signal diagram generated when the train runs on the track according to the vibration information; and identifying the running state information of the train according to the running signal diagram and/or the vibration information. By the technical scheme of the invention, the running state information of the train can be automatically identified, so that the information such as the length, the position, the running direction, the running speed, the load and the like of the train can be accurately identified.
Description
Technical Field
The invention relates to the technical field of trains, in particular to a method and a device for identifying the running state of a heavy-duty train.
Background
At present, with the development demand of national economic construction, the construction of heavy haul railways gradually turns into development emphasis, and the freight heavy load and the passenger high speed jointly form two major trends of the development of the Chinese railways. At the same time, however, the rapid development of heavy haul railways has made them a great challenge in terms of operational safety, particularly in terms of monitoring the operating conditions of trains. Therefore, accurately mastering the current running position, running direction, speed and other information of the heavy haul train in real time is important for the running safety of the heavy haul railway.
Disclosure of Invention
The invention provides a method for identifying the running state of a heavy-duty train, which comprises the following steps:
acquiring vibration information of a track when a train runs on the track;
acquiring a running signal diagram generated when the train runs on the track according to the vibration information;
and identifying the running state information of the train according to the running signal diagram and/or the vibration information.
In one embodiment, the obtaining of the operation signal diagram generated when the train operates on the track according to the vibration information includes:
acquiring a plurality of vibration information of the track collected in each sampling period when the train runs on the track;
and acquiring the running signal diagram according to a plurality of vibration information of the track acquired in a plurality of sampling periods, wherein the vibration information comprises amplitude and vibration generation positions.
In one embodiment, the acquiring the operation signal map according to a plurality of vibration information of the track collected in a plurality of sampling periods includes:
performing difference value operation on a plurality of vibration information of the track acquired in a plurality of sampling periods to acquire amplitude difference of the same position on the track in the plurality of sampling periods;
acquiring a reference signal diagram generated when the train runs on the track according to the amplitude difference of the same position on the track;
and performing edge correction on the reference signal diagram by using an edge detection method to obtain the operating signal diagram.
In one embodiment, the performing an edge correction on the reference signal diagram by using an edge detection method to obtain the operating signal diagram includes:
performing Gaussian filtering on the reference signal diagram by using the edge detection method to obtain a corresponding smooth signal diagram;
acquiring gradient information of the smooth signal diagram in four preset directions;
carrying out non-maximum suppression on the smooth ripple image according to the gradient information to obtain a non-maximum suppressed image;
and processing the non-greatly-suppressed image by using a dynamically-changed double threshold value to obtain the running signal diagram.
In one embodiment, the identifying the operation state information of the train according to the operation signal diagram and/or the vibration information includes:
and identifying the length of the train, the position of the train on the track in each sampling period, the running direction of the train, the running speed of the train and the load of the train according to the running signal diagram and/or the vibration information.
The invention also provides a device for identifying the running state of the heavy-duty train, which comprises:
the system comprises a first acquisition module, a second acquisition module and a control module, wherein the first acquisition module is used for acquiring vibration information of a track when a train runs on the track;
the second acquisition module is used for acquiring a running signal diagram generated when the train runs on the track according to the vibration information;
and the identification module is used for identifying the running state information of the train according to the running signal diagram and/or the vibration information.
In one embodiment, the second obtaining module comprises:
the first acquisition submodule is used for acquiring a plurality of vibration information of the track, which is acquired in each sampling period when the train runs on the track;
and the second acquisition submodule is used for acquiring the running signal diagram according to a plurality of vibration information of the track acquired by a plurality of sampling periods, wherein the vibration information comprises amplitude and vibration generation positions.
In one embodiment, the second obtaining sub-module includes:
the first acquisition unit is used for carrying out difference value operation on a plurality of vibration information of the track acquired in a plurality of sampling periods to acquire amplitude differences of the same position on the track in the plurality of sampling periods;
the second acquisition unit is used for acquiring a reference signal diagram generated when the train runs on the track according to the amplitude difference of the same position on the track;
and the correction unit is used for performing edge correction on the reference signal diagram by using an edge detection method to obtain the operating signal diagram.
In one embodiment, the correction unit includes:
the filtering subunit is configured to perform gaussian filtering on the reference signal map by using the edge detection method to obtain a corresponding smoothed signal map;
the acquisition subunit is used for acquiring gradient information of the smooth signal diagram in four preset directions;
the first processing subunit is used for carrying out non-maximum suppression on the smooth ripple image according to the gradient information to obtain a non-maximum suppressed image;
and the second processing subunit is used for processing the image which is not subjected to the maximum suppression by using a dynamically changed dual threshold value to obtain the running signal diagram.
In one embodiment, the identification module comprises:
and the identification submodule is used for identifying at least one of the length of the train, the position of the train on the track in each sampling period, the running direction of the train, the running speed of the train and the load of the train according to the running signal diagram and/or the vibration information.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:
after the vibration information of the track when the train runs on the track is acquired, the running signal diagram of the train can be acquired according to the vibration information, and then the running state information of the train is automatically identified according to the running signal diagram and/or the vibration information, so that at least one item of information such as the length, the position, the running direction, the running speed, the load and the like of the train is accurately identified in real time.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a flowchart illustrating a method for identifying an operation state of a heavy haul train according to an exemplary embodiment.
Fig. 2 is a flowchart illustrating another method of identifying an operating state of a heavy-duty train in accordance with an exemplary embodiment.
Fig. 3A is a screenshot of a reference signal plot obtained from the amplitude difference of the train at different locations on the track at time 2018-05-05-10-56.
Fig. 3B is a screenshot of a running signal graph obtained using a conventional Canny edge detection method based on fig. 3A.
Fig. 3C is a screenshot of a running signal plot obtained using the Canny edge detection method of the present invention based on fig. 3A.
Fig. 3D is a flowchart of a Canny edge detection method in the related art.
FIG. 3E is a schematic of a gradient template in the x-axis direction.
FIG. 3F is a schematic diagram of a gradient template in the y-axis direction.
FIG. 3G is a schematic of a gradient template at 45 orientation.
Fig. 3H is a schematic diagram of a 135 ° directional gradient template.
Fig. 4 is a block diagram illustrating a heavy haul train operation state identification apparatus according to an exemplary embodiment.
Fig. 5 is a block diagram illustrating another heavy haul train operation state identification apparatus according to an exemplary embodiment.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
In order to solve the above technical problem, an embodiment of the present disclosure provides a method for identifying an operation state of a heavy haul train, where the method is applied to a train information identification program, system or device, an execution subject of the method is a terminal or a server, as shown in fig. 1, the method includes steps S101 to S103, where:
in step S101, vibration information of the rail is acquired while the train is running on the rail.
The track may be a rail or rail; when vibration information is obtained, standby communication optical cables on two sides of a track can be used as optical fiber sensors, and the optical fiber sensors and optical signal processing equipment of a communication machine room jointly form a distributed optical fiber vibration monitoring (DAS) system, so that vibration generated by vibration of a steel rail during running of a train can be sampled uninterruptedly and periodically.
The train may be a heavy haul train.
In step S102, an operation signal diagram generated when the train operates on the track is acquired based on the vibration information.
The operation signal diagram is a relationship diagram of the track position and the time, the pixel value of each pixel point in the diagram corresponds to the vibration information, the vibration information corresponding to each track position in each sampling period is different, and the pixel value of the track position in the operation signal diagram is also different.
In step S103, the train operation state information is identified based on the operation signal diagram and/or the vibration information.
After the vibration information of the track when the train runs on the track is acquired, the running signal diagram of the train can be acquired according to the vibration information, and then the running state information of the train is automatically identified according to the running signal diagram and/or the vibration information, so that at least one item of information such as the length, the position, the running direction, the running speed, the load and the like of the train is accurately identified in real time.
As shown in fig. 2, in an embodiment, the step S102 in fig. 1, namely obtaining the operation signal diagram generated when the train operates on the track according to the vibration information, may include:
in step S201, a plurality of vibration information of the rail collected in each sampling period when the train runs on the rail is obtained;
and acquiring a plurality of vibration information of the track in each sampling period, namely the vibration amplitude of each position on the track in each sampling period. And the vibration information may include vibration time, i.e., sampling period, in addition to the amplitude of each location on the track.
The sampling period may be in the order of milliseconds, such as 200 or 300 times per second, so as to improve the accuracy of the acquired vibration information and further ensure the accuracy of the operation signal diagram.
In step S202, a running signal diagram is obtained according to a plurality of vibration information of the track acquired in a plurality of sampling periods, where the vibration information includes an amplitude and a vibration generation position (i.e., each position on the track), and the plurality of vibration information of the track acquired in the plurality of sampling periods is vibration information of different positions on the track acquired in each sampling period under N sampling periods.
When the operation signal diagram is obtained, the vibration information, namely the vibration information, collected in each sampling period during the operation of the train on the track, of each position on the track can be obtained firstly, and then the operation signal diagram is accurately obtained according to the vibration information collected in the sampling periods, so that the operation state information of the train can be conveniently identified later.
In one embodiment, acquiring a running signal map according to a plurality of vibration information of the track acquired in a plurality of sampling periods includes:
performing difference value operation on a plurality of vibration information of the track acquired in a plurality of sampling periods to acquire amplitude difference of the same position on the track in the plurality of sampling periods;
before the difference operation is performed, denoising processing (namely, removing noises of environments, circuits, electronic components and the like) can be performed on the vibration information, and a denoising method can be multi-scale wavelet decomposition and reconstruction (sym8 wavelet, 3 level).
In addition, the manner of obtaining the amplitude difference may be as follows:if a plurality of adjacent sampling periods are respectively t1Sampling period, t2Sampling period, t3Sampling period … … tnSampling period, t1The amplitude of the position A on the track under the sampling period is a1、t2Amplitude of a at position A in the sampling period2、t3Amplitude of a at position A in the sampling period3，……，tnAmplitude of a at position A in the sampling periodnThen the amplitude difference at position a at t1 sampling period may be a1-a2，t2The amplitude difference at position A is a in the sampling period2-a3，……，tn-1The amplitude difference at position A is a in the sampling periodn-1-an. Of course, if these vibration differences are negative values, the absolute values may be taken.
Acquiring a reference signal diagram generated when a train runs on a track according to the amplitude difference of the same position on the track;
the reference signal diagram is a gray scale diagram converted from vibration information generated by vibration of a track caused by running of a train on the track, the horizontal axis of the gray scale diagram is the position Distance of the track, the vertical axis of the gray scale diagram is the sampling period Time, and the pixel value of the pixel point at the position (d1, t1) in the gray scale diagram and the amplitude difference a of the d1 position on the track under the sampling period of t1 are respectively the amplitude difference a1-a2Correspondingly, when a train passes through and when no train passes through, the amplitude difference at the same position is different, and accordingly, the pixel values of the pixel points at the same position are different, so that the two ends (namely the edges of the train head and the train tail) of the train can be determined based on the reference signal diagram, and the running state information of the train can be identified.
And performing edge correction on the reference signal diagram by using an edge detection method to obtain a running signal diagram.
By carrying out difference value operation, the amplitude difference of the same position on the track under a plurality of sampling periods can be obtained to remove the interference of high-speed noise, instrument error and the like in the vibration amplitude, image conversion is further carried out according to the amplitude difference of different track positions on the whole track under the plurality of sampling periods to obtain a reference signal diagram generated when the train runs on the track, namely a gray level diagram, and then edge correction is carried out on the reference signal diagram by utilizing an edge detection method to obtain an accurate running signal diagram, so that the identification accuracy of the train running state information is improved.
The edge detection method is an improved canny edge detection algorithm.
In one embodiment, the edge-modifying the reference signal diagram by using an edge detection method to obtain the operation signal diagram comprises:
using an edge detection method to perform Gaussian filtering on the reference signal graph to obtain a corresponding smooth signal graph (or called smooth ripple graph);
acquiring gradient information of the smooth signal diagram in four preset directions;
four preset directions, namely 0 °, 45 °, 90 ° and 135 ° directions. Gradient information is the strength of the gradient and the direction of the gradient.
Carrying out non-maximum suppression on the smooth ripple image according to the gradient information to obtain a non-maximum suppressed image;
and processing the image which is not greatly inhibited by utilizing the dynamically changed double thresholds to obtain a running signal diagram.
When the operation signal diagram is obtained, Gaussian filtering can be carried out on the reference signal diagram to obtain a smooth signal diagram, then gradient information in four directions is obtained, non-maximum suppression is further carried out to obtain a non-maximum-suppression image, finally the non-maximum-suppression image is processed by utilizing a dynamically-changed double threshold value, noise points are removed, and the operation signal diagram with clear edges can be obtained.
The dual thresholds (i.e., the upper threshold and the lower threshold) in the canny edge detection algorithm in the related art are fixed and only two preset directions are 0 ° and 90 ° (i.e., the x-axis and the y-axis), respectively, so that the accuracy of the operating signal diagram can be improved by using the improved edge detection method (i.e., obtaining the gradient information in the four preset directions and the dynamically changing dual thresholds) compared with the canny algorithm in the related art.
In one embodiment, identifying the train operation state information according to the operation signal diagram and/or the vibration information comprises:
at least one of a length of the train, a position of the train on the track per sampling period, a traveling direction of the train, a traveling speed of the train, and a load of the train is identified based on the operation signal map and/or the vibration information. The horizontal axis of the operation signal diagram is position, and the vertical axis is sampling period.
When the operation signal diagram is obtained, the operation state information of the train can be accurately identified, and the operation signal diagram is a waterfall diagram as shown in fig. 3C, wherein the waterfall diagram is an inclined strip diagram, the width of the strip diagram is the length of the train, the position of the strip diagram is the position of the train, the inclined direction of the strip diagram is the driving direction of the train, the reverse slope of the strip diagram is the driving speed of the train, namely, a white area formed by dense white pixel points in the middle of fig. 3C is the waterfall diagram, and the width of the white area is the length of the train, and the positions of the two ends of the edge of the white area are the positions of the train on the track.
Since the amplitude of the same position on the track is different due to different loads of the train, the load of the train can be accurately determined according to the amplitude of the different positions on the track, and in order to ensure the accuracy of the load, different operation processes such as an average algorithm and the like can be performed by using the amplitude of the different positions on the track in a plurality of sampling periods to obtain the load of the train.
The Canny edge detection method of the present invention will be described in further detail below:
1) as shown in fig. 3D, this is a Canny edge detection method in the related art.
2) Improved edge detection algorithm
The traditional Canny algorithm calculates the gradient amplitude of an image by using the finite difference in 2 multiplied by 2 neighborhoods (namely 4 neighborhoods of 0-90 degrees, 90-180 degrees, 180-270 degrees and 270-360 degrees), and has the defects of being greatly influenced by noise and easily causing false detection and missed detection. The method improves the traditional Canny algorithm, and increases two directional gradients of 45 degrees and 135 degrees. First order gradient component G in four directionsx、Gy、G45、G135The filtered images may be respectively filtered by four first order gradient templates as shown belowAnd (4) performing convolution to obtain the product. And the new gradients and angles are as follows:
the improved gradient calculation method fully considers the gradient conditions in 8 neighborhoods (namely 8 neighborhoods of 0-45 degrees, 45-90 degrees, 90-135 degrees, 135-180 degrees, 180-225 degrees, 225-270 degrees, 270-315 degrees and 315-360 degrees), so that the gradient calculation is more accurate.
FIG. 3E shows a gradient template in the x-axis direction, FIG. 3F shows a gradient template in the y-axis direction, FIG. 3G shows a gradient template in the 45 ° direction, and FIG. 3H shows a gradient template in the 135 ° direction.
Second, the conventional Canny algorithm requires a high-low threshold (i.e., a double threshold) to be manually preset, a threshold set too high may cause edge breakage and discontinuity, and a threshold set too low may detect false edges or lose local edges. Under the influence of environmental noise along the railway, the adaptive threshold selection method based on the OSTU algorithm is utilized to improve the accuracy of train identification. The specific operation is as follows:
let {0,1,2, …, L-1} represent L different gray levels in an image with size M × N, the probability of occurrence of a pixel with gray value k is denoted as p (k), L ═ 8, M, N are the number of pixels in the gray-scale image in the horizontal and vertical directions, respectively, and the range of k is 0 to 255, then:
if a threshold value t (t is more than 0 and less than L-1) exists, the image is divided into a foreground type and a background type, the gray value range of pixels of the foreground part is [0, t ], the gray value range of pixels of the background part is [ t +1, L-1], the proportion of the foreground and the background in the whole image is respectively formula 1 and formula 2, the gray average values of the foreground and the background are respectively formula 3 and formula 4, the gray average value of the whole image is formula 5, and the between-class variance of the foreground and the background is formula 6.
Equation 1:
equation 2:
equation 3:
equation 4:
equation 5: mu-omega0(t)μ0(t)+ω1(t)μ1(t)
Equation 6:
the best threshold is the value of T at which g (T) is the maximum, and if the T values satisfying the condition are not unique, all the T values are averaged, and the average value is used as the high threshold T in the Canny algorithmhReuse of Tl＝0.5*ThFinding a Low threshold Tl. The OSTU algorithm is introduced into the Canny algorithm, so that the most appropriate threshold value can be selected by the improved Canny algorithm according to the characteristics of the image, and the self-adaptive capacity of the algorithm is enhanced.
In the present invention, a ten thousand ton full-axle train is considered, and when the train is towed by 4 SS618313 high-power locomotives and 132 cars of the C64K type are mounted, the actual length is 30 × 4+132 × 13.438+135 × 0.845 to 2007.891 meters. And fig. 3A, 3B and 3C respectively show the running signals (obtained after difference processing) of the trains 2018-05-05-10-56 at the moment, the traditional Canny algorithm and the improved Canny algorithm identification result.
As shown in fig. 4, the present invention also provides a device for identifying the operation state of a heavy-duty train, comprising:
a first obtaining module 401 configured to obtain vibration information of a rail when a train runs on the rail;
a second obtaining module 402, configured to obtain an operation signal diagram generated when the train operates on the track according to the vibration information;
and the identification module 403 is configured to identify the running state information of the train according to the running signal diagram and/or the vibration information.
As shown in fig. 5, in one embodiment, the second obtaining module 402 includes:
the first acquisition sub-module 4021 is configured to acquire a plurality of vibration information of the rail, which is acquired in each sampling period when the train runs on the rail;
the second obtaining sub-module 4022 is configured to obtain an operation signal diagram according to a plurality of vibration information of the track collected in a plurality of sampling periods, where the vibration information includes an amplitude and a vibration generation position.
In one embodiment, the second obtaining sub-module includes:
the first acquisition unit is configured to perform difference operation on a plurality of vibration information of the track acquired in a plurality of sampling periods to acquire amplitude differences of the same position on the track in the plurality of sampling periods;
the second acquisition unit is configured to acquire a reference signal diagram generated when the train runs on the track according to the amplitude difference of the same position on the track;
and the correction unit is configured to perform edge correction on the reference signal diagram by using an edge detection method to obtain a running signal diagram.
In one embodiment, the correction unit includes:
a filtering subunit, configured to perform gaussian filtering on the reference signal map by using an edge detection method to obtain a corresponding smoothed signal map;
the acquisition subunit is configured to acquire gradient information of the smoothed signal diagram in four preset directions;
the first processing subunit is configured to perform non-maximum suppression on the smooth moire map according to the gradient information to obtain a non-maximum suppressed image;
and the second processing subunit is configured to process the non-greatly-suppressed image by using the dynamically-changed dual threshold value to obtain a running signal diagram.
In one embodiment, the identification module comprises:
and the identification submodule is configured to identify at least one of the length of the train, the position of the train on the track in each sampling period, the running direction of the train, the running speed of the train and the load of the train according to the running signal diagram and/or the vibration information.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Finally, the heavy-duty train running state recognition device is suitable for terminal equipment. For example, it may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, etc.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (8)
1. A method for identifying the running state of a heavy-duty train is characterized by comprising the following steps:
acquiring vibration information of a track when a train runs on the track;
acquiring a running signal diagram generated when the train runs on the track according to the vibration information;
identifying the running state information of the train according to the running signal diagram and/or the vibration information;
the obtaining of the operation signal diagram generated when the train operates on the track according to the vibration information includes:
acquiring a plurality of vibration information of the track collected in each sampling period when the train runs on the track;
and acquiring the running signal diagram according to a plurality of vibration information of the track acquired in a plurality of sampling periods, wherein the vibration information comprises amplitude and a vibration generation position, the running signal diagram is a relation diagram of the track position and time, and the pixel value of each pixel point in the diagram corresponds to the vibration information.
2. The method of claim 1,
the acquiring the operation signal diagram according to the plurality of vibration information of the track acquired by the plurality of sampling periods includes:
performing difference value operation on a plurality of vibration information of the track acquired in a plurality of sampling periods to acquire amplitude difference of the same position on the track in the plurality of sampling periods;
acquiring a reference signal diagram generated when the train runs on the track according to the amplitude difference of the same position on the track;
and performing edge correction on the reference signal diagram by using an edge detection method to obtain the operating signal diagram.
3. The method of claim 2,
the performing edge correction on the reference signal diagram by using an edge detection method to obtain the operating signal diagram includes:
performing Gaussian filtering on the reference signal graph by using the edge detection method to obtain a corresponding smooth ripple graph;
acquiring gradient information of the smooth ripple graph in four preset directions;
carrying out non-maximum suppression on the smooth ripple image according to the gradient information to obtain a non-maximum suppressed image;
and processing the image after the non-maximum value suppression by using a dynamically changed double threshold value to obtain the running signal diagram.
4. The method according to any one of claims 1 to 3,
the identifying the running state information of the train according to the running signal diagram and/or the vibration information comprises:
and identifying the length of the train, the position of the train on the track in each sampling period, the running direction of the train, the running speed of the train and the load of the train according to the running signal diagram and/or the vibration information.
5. The utility model provides a heavy haul train running state recognition device which characterized in that includes:
the system comprises a first acquisition module, a second acquisition module and a control module, wherein the first acquisition module is used for acquiring vibration information of a track when a train runs on the track;
the second acquisition module is used for acquiring a running signal diagram generated when the train runs on the track according to the vibration information;
the identification module is used for identifying the running state information of the train according to the running signal diagram and/or the vibration information;
the second acquisition module includes:
the first acquisition submodule is used for acquiring a plurality of vibration information of the track, which is acquired in each sampling period when the train runs on the track;
and the second acquisition submodule is used for acquiring the running signal diagram according to a plurality of vibration information of the track acquired by a plurality of sampling periods, wherein the vibration information comprises amplitude and vibration generation positions, the running signal diagram is a relation diagram of the track position and time, and the pixel value of each pixel point in the diagram corresponds to the vibration information.
6. The apparatus of claim 5,
the second acquisition sub-module includes:
the first acquisition unit is used for carrying out difference value operation on a plurality of vibration information of the track acquired in a plurality of sampling periods to acquire amplitude differences of the same position on the track in the plurality of sampling periods;
the second acquisition unit is used for acquiring a reference signal diagram generated when the train runs on the track according to the amplitude difference of the same position on the track;
and the correction unit is used for performing edge correction on the reference signal diagram by using an edge detection method to obtain the operating signal diagram.
7. The apparatus of claim 6,
the correction unit includes:
the filtering subunit is configured to perform gaussian filtering on the reference signal map by using the edge detection method to obtain a corresponding smooth ripple map;
the acquiring subunit is used for acquiring gradient information of the smooth ripple image in four preset directions;
the first processing subunit is used for carrying out non-maximum suppression on the smooth moire map according to the gradient information to obtain a non-maximum suppressed image;
and the second processing subunit is used for processing the image after the non-maximum value suppression by using a dynamically changed dual threshold value to obtain the running signal diagram.
8. The apparatus according to any one of claims 5 to 7,
the identification module comprises:
and the identification submodule is used for identifying the length of the train, the position of the train on the track in each sampling period, the running direction of the train, the running speed of the train and the load of the train according to the running signal diagram and/or the vibration information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910544615.3A CN110316227B (en) | 2019-06-21 | 2019-06-21 | Heavy-duty train running state identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910544615.3A CN110316227B (en) | 2019-06-21 | 2019-06-21 | Heavy-duty train running state identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110316227A CN110316227A (en) | 2019-10-11 |
| CN110316227B true CN110316227B (en) | 2021-06-04 |
Family
ID=68120090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910544615.3A Expired - Fee Related CN110316227B (en) | 2019-06-21 | 2019-06-21 | Heavy-duty train running state identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110316227B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102534694B1 (en) * | 2021-07-29 | 2023-05-26 | 한국철도기술연구원 | Method for train localization and train integrity verification using distributed acoustic sensing technology |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106394612A (en) * | 2016-10-24 | 2017-02-15 | 南京派光信息技术有限公司 | Crossing train approaching real-time pre-warning system and method based on distributed optical fibers |
| CN107452007A (en) * | 2017-07-05 | 2017-12-08 | 国网河南省电力公司 | A kind of visible ray insulator method for detecting image edge |
| CN108109155A (en) * | 2017-11-28 | 2018-06-01 | 东北林业大学 | A kind of automatic threshold edge detection method based on improvement Canny |
| JP2018114790A (en) * | 2017-01-17 | 2018-07-26 | 東日本旅客鉄道株式会社 | Railway control system using optical cable |
| CN108875684A (en) * | 2018-06-29 | 2018-11-23 | 电子科技大学 | Train operation state method for parameter estimation based on optical fiber sensing time-frequency figure processing |
| CN109357747A (en) * | 2018-10-25 | 2019-02-19 | 南京航空航天大学 | A kind of identification of online train and speed estimation method based on fiber-optic vibration signal |
-
2019
- 2019-06-21 CN CN201910544615.3A patent/CN110316227B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106394612A (en) * | 2016-10-24 | 2017-02-15 | 南京派光信息技术有限公司 | Crossing train approaching real-time pre-warning system and method based on distributed optical fibers |
| JP2018114790A (en) * | 2017-01-17 | 2018-07-26 | 東日本旅客鉄道株式会社 | Railway control system using optical cable |
| CN107452007A (en) * | 2017-07-05 | 2017-12-08 | 国网河南省电力公司 | A kind of visible ray insulator method for detecting image edge |
| CN108109155A (en) * | 2017-11-28 | 2018-06-01 | 东北林业大学 | A kind of automatic threshold edge detection method based on improvement Canny |
| CN108875684A (en) * | 2018-06-29 | 2018-11-23 | 电子科技大学 | Train operation state method for parameter estimation based on optical fiber sensing time-frequency figure processing |
| CN109357747A (en) * | 2018-10-25 | 2019-02-19 | 南京航空航天大学 | A kind of identification of online train and speed estimation method based on fiber-optic vibration signal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110316227A (en) | 2019-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112767326B (en) | Rail surface defect detection method, device, equipment and storage medium | |
| CN115272334A (en) | Method for detecting micro defects on surface of steel rail under complex background | |
| FR2549259A1 (en) | CHARACTER RECOGNIZING METHOD AND DEVICE | |
| JP2022549541A (en) | Defect detection method, apparatus, electronic equipment and computer storage medium | |
| CN110298323B (en) | Frame-fighting detection method, system and device based on video analysis | |
| CN110316227B (en) | Heavy-duty train running state identification method and device | |
| CN113034439B (en) | High-speed railway sound barrier defect detection method and device | |
| CN107609510A (en) | Truck positioning method and apparatus under a kind of gantry crane | |
| CN112862706A (en) | Pavement crack image preprocessing method and device, electronic equipment and storage medium | |
| CN111126248A (en) | Method and device for identifying shielded vehicle | |
| CN111027459A (en) | Ship track prediction method and system | |
| CN112037182B (en) | Locomotive running part fault detection method and device based on time sequence image and storage medium | |
| CN112749735B (en) | Converter tapping steel flow identification method, system, medium and terminal based on deep learning | |
| CN111242051B (en) | Vehicle identification optimization method, device and storage medium | |
| CN117132990A (en) | Railway carriage information identification method, device, electronic equipment and storage medium | |
| CN111985461A (en) | Rail vehicle number identification method and system | |
| Lei et al. | Research of the real-time detection of traffic flow based on OpenCV | |
| CN113487620A (en) | Railway insulation section detection method and device | |
| CN114581472A (en) | Image edge detection method and device, electronic equipment and storage medium | |
| CN114581876A (en) | Method for constructing lane detection model under complex scene and method for detecting lane line | |
| CN114332202B (en) | Vascular model processing method and device and computer readable storage medium | |
| CN111532312A (en) | Track turnout identification method and device | |
| CN112465859A (en) | Method, device, equipment and storage medium for detecting fast moving object | |
| CN114565889B (en) | Method and device for determining vehicle line pressing state, electronic equipment and medium | |
| CN113344963B (en) | Seed point self-adaptive target tracking system based on image segmentation |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210604 |