CN115782969A - Data acquisition system applied to environmental monitoring of railway system - Google Patents
Data acquisition system applied to environmental monitoring of railway system Download PDFInfo
- Publication number
- CN115782969A CN115782969A CN202310102073.0A CN202310102073A CN115782969A CN 115782969 A CN115782969 A CN 115782969A CN 202310102073 A CN202310102073 A CN 202310102073A CN 115782969 A CN115782969 A CN 115782969A
- Authority
- CN
- China
- Prior art keywords
- train
- image
- railway
- debris flow
- mountain area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 38
- 230000007613 environmental effect Effects 0.000 title claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000013135 deep learning Methods 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 12
- 230000011218 segmentation Effects 0.000 claims abstract description 12
- 238000001514 detection method Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 230000004888 barrier function Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 150000001875 compounds Chemical class 0.000 claims description 6
- 239000000779 smoke Substances 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 238000003384 imaging method Methods 0.000 claims description 4
- 238000002592 echocardiography Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000001788 irregular Effects 0.000 claims description 3
- 238000012886 linear function Methods 0.000 claims description 3
- GOLXNESZZPUPJE-UHFFFAOYSA-N spiromesifen Chemical compound CC1=CC(C)=CC(C)=C1C(C(O1)=O)=C(OC(=O)CC(C)(C)C)C11CCCC1 GOLXNESZZPUPJE-UHFFFAOYSA-N 0.000 claims description 3
- 229910000831 Steel Inorganic materials 0.000 claims description 2
- 239000012530 fluid Substances 0.000 claims description 2
- 239000010959 steel Substances 0.000 claims description 2
- 238000011897 real-time detection Methods 0.000 claims 1
- 230000009466 transformation Effects 0.000 claims 1
- 239000011435 rock Substances 0.000 description 6
- 230000008859 change Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000003137 locomotive effect Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a data acquisition system applied to railway system environment monitoring, which comprises a train obstacle deflector, an environment acquisition module, an image acquisition module, an energy supply module, a train high-frequency radar detection module, a rainfall early warning module and a railway line debris flow early warning module. The invention collects the environmental data and carries out early warning on flood and debris flow, thereby protecting the life and property safety of train workers and passengers, completing the monitoring of the debris flow on a fine day and improving the comprehensiveness of environmental monitoring; and the pre-processing and super-pixel segmentation method is used for carrying out super-pixel segmentation on the image after the binarization processing and carrying out the training of a crack identification model based on a deep learning framework on the training image obtained in advance, and meanwhile, when the crack identification is carried out on the initial mountain area image or the real-time mountain area image, the image is zoomed and a plurality of pictures with certain sizes are cut, so that the recognition accuracy of the mountain cracks is improved.
Description
Technical Field
The invention relates to the technical field of railway monitoring, in particular to a data acquisition system applied to railway system environment monitoring.
Background
Railway transportation is a type of land transportation in which a locomotive pulls a train vehicle over two parallel rails. Environmental monitoring (environmental monitoring) refers to determining an environmental quality quantity and a trend of change thereof by measuring a representative value of factors affecting the environmental quality. The purpose of environment monitoring is to accurately, timely and comprehensively reflect the current situation and the development trend of the environment quality. Background data is collected, long-term monitoring data is accumulated, and data is provided for researching environmental capacity, implementing total amount control and target management, predicting and forecasting environmental quality. In order to ensure the safety of railway operation and solve the contradiction between speed and safety, it is necessary to establish a railway environment monitoring system.
The railway running system in the railway system is an important unit, and during the running process of a train of the railway running system, most feared that obstacles exist in the running direction, the normal running of the train can be seriously influenced, and even serious accidents can be caused. When the train runs to a mountain ditch area, flood and debris flow disasters in the mountain area need to be predicted, so that the environment of a railway system needs to be monitored and data needs to be collected.
For example, chinese patent 201610086670.9 discloses a railway line inspection system, which comprises an incoming and outgoing train information acquisition subsystem, a data and fault processing subsystem, a flight control subsystem and a data acquisition subsystem, and solves the technical problems that the existing railway line inspection method is single in means, low in reliability, influences normal driving, and cannot meet the requirement of high-speed railway operation safety. However, the above system has the following disadvantages: there are many trains among current railway system can pass through the mountain ditch region, and the mountain ditch region is because its special topography, if meet the condition that flood or mud-rock flow appear easily in emergency, and no matter flood or mud-rock flow all can be to railway system, especially the train causes the injury, and then cause the harm to people's lives and properties, consequently need monitor the environment of railway system and carry out data acquisition, and among the prior art, among the train system is to the environmental monitoring of flood or mud-rock flow, basically be to the monitoring of rainy day, and fine day lacks the monitoring to mud-rock flow, make the comprehensive of environmental monitoring not enough.
For example, patent CN205594844U provides a landslide and debris flow early warning system, which includes a monitoring workstation, a control center, and an alarm center, where the monitoring workstation includes an environment information collecting device, an environment information data sorting device, and an environment information data transmitting device, the environment information collecting device is equipped with a radar, a temperature sensor, a humidity sensor, a wind speed sensor, and a camera, an output end of the monitoring workstation is connected with an input end of the control center, and an output end of the control center is connected with the alarm center, but is not connected with a railway system.
An effective solution to the problems in the related art has not been proposed yet.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides a data acquisition system applied to railway system environment monitoring, so as to overcome the technical problems in the prior related art.
Therefore, the invention adopts the following specific technical scheme:
the utility model provides a be applied to data acquisition system of railway system environmental monitoring, this system includes train barrier removal ware, environment acquisition module, image acquisition module, energy supply module, train high frequency radar detection module, rainfall early warning module and railway line mud-rock flow early warning module.
The rail clearance device is used for pushing obstacles on a train track to two sides of a train when the railway train runs, so that the train can run normally.
And the environment acquisition module is used for acquiring the rail side data of the railway train rail, and sending the acquired rail side data to the back-up center after processing the acquired rail side data.
The image acquisition module is used for acquiring images along the railway and transmitting the acquired images along the railway to a vehicle-mounted terminal in the train.
The energy supply module is used for converting light energy into electric energy through the solar component, and is right the environment acquisition module reaches the image acquisition module supplies power, and if there is not sunshine, the storage battery through the pre-configuration does the environment acquisition module reaches the image acquisition module supplies power.
The train high-frequency radar detection module is used for detecting and imaging in real time through a high-frequency radar installed on a train and acquiring remote road condition information.
The rainfall early warning module is used for acquiring the rainfall of any region through weather forecast and issuing early warning alarm to the region according to the rainfall of the weather forecast.
And the railway line debris flow early warning module is used for respectively early warning debris flow disasters in the train running line in sunny days and rainy days.
Furthermore, when the rail side data of the railway train rail is collected, the side surface and the bottom surface of the railway train rail are measured through the surface mount type temperature sensor;
measuring the atmospheric temperature and the atmospheric humidity through an atmospheric temperature sensor and an atmospheric humidity sensor which are arranged on the electric service relay station;
smoke and wind power are measured by a smoke sensor and a wind sensor which are arranged on the electric service relay station.
Furthermore, when the collected rail side data is processed and transmitted to the back-up center, the rail side data is received and processed through the industrial personal computer, the processed rail side data is transmitted to the back-up center, and the attendant of the back-up center arranges train attendants to adjust the speed of the railway train according to the transmitted data.
Furthermore, when the high-frequency radar installed on the train detects and images in real time and acquires long-distance road condition information, the ultrahigh-frequency electromagnetic wave emitted by the high-frequency radar detects and images an object in front of the railway train.
The transmitting antenna of the high-frequency radar transmits carrier-free electromagnetic pulse waves to the front of a railway train, and the receiving antenna receives reflected echoes;
determining whether the running direction of the railway train has an obstacle or not according to the travel time of the reflected echo:
hdistance of the barrier from the train;
xis the distance between the transmitting antenna and the receiving antenna;
vis the radar pulse wave velocity;
when an obstacle appears in the running direction of the railway train, the train is decelerated and finally stopped.
Further, when the rainfall capacity of any area within 24 hours is obtained through the weather forecast, and the early warning alarm is issued to the area according to the rainfall capacity of the weather forecast, a blue alarm is issued to the area when the rainfall capacity of the weather forecast is 120-135 mm, a yellow alarm is issued to the area when the rainfall capacity of the weather forecast is 135-145 mm, an orange alarm is issued to the area when the rainfall capacity of the weather forecast is 145-155 mm, and a red alarm is issued to the area when the rainfall capacity of the weather forecast is higher than 155 mm.
If the area is a mountain ditch area and the rainfall of the weather forecast is higher than 155 mm, the train is required to be forbidden to pass through the area.
Further, when the early warning is carried out on debris flow disasters in the running route of the train in rainy days, in a mountain area which is focused on, the debris flow measuring sensor is arranged in a groove in the side wall of the debris flow section, and a first voltage value of the debris flow measuring sensor is recorded;
when the sensor is submerged by debris flow, a second voltage value of the debris flow measuring sensor is obtained, and when the second voltage value is far smaller than the first voltage value, debris flow is determined to occur, and debris flow disaster early warning is carried out;
measuring the debris flow depth through an ultrasonic debris level alarm, and judging the scale of the debris flow;
and after the obtained debris flow occurrence information and the debris flow scale information are obtained, the train is required to forbid passing through the area.
Further, when the early warning is carried out on the debris flow disasters in the train running route on a fine day, the high-definition camera and the positioning module are erected on the unmanned aerial vehicle, the unmanned aerial vehicle is controlled to drive the high-definition camera and the positioning module to shoot the focused mountain area at a certain height, the initial mountain area image is obtained, and meanwhile, the length of the crack in the initial mountain area image is obtained through calculation;
in a clear day, the same unmanned aerial vehicle is used for driving a high-definition camera to shoot the same mountain area at a certain height, a real-time mountain area image is obtained, and meanwhile, the length of a crack in the real-time mountain area image is obtained through calculation;
and if the growth rate of the crack length in the real-time mountain area image relative to the crack length in the initial mountain area image is larger than a preset growth threshold value, judging that the mountain area is a dangerous area, and early warning for debris flow disasters.
Further, when the length of the crack in the initial mountain area image or the real-time mountain area image is obtained through calculation, preprocessing is carried out on a training image acquired in advance, and crack recognition is carried out on the preprocessed image on the basis of a noise deep learning framework;
and identifying the cracks of the initial mountain area image or the real-time mountain area image, marking the cracks through the lines, and calculating the length of the lines, namely the length of the cracks.
Further, when the pre-acquired training image is preprocessed and the preprocessed image is subjected to crack recognition based on a caffe deep learning framework, the pre-acquired training image is enhanced through a piecewise linear function:
Denoising the enhanced image;
carrying out binarization processing on the denoised image;
performing superpixel segmentation on the image subjected to binarization processing by a superpixel segmentation method, clustering a plurality of irregular image blocks simultaneously, and storing and establishing a data set of a crack identification model;
training and testing a crack recognition model based on a caffe deep learning frame, and obtaining a trained crack recognition model;
when the crack identification is carried out on the initial mountain area image or the real-time mountain area image, the initial mountain area image or the real-time mountain area image is zoomed, and a picture with a certain size is cut, wherein the cutting processing times are twelve;
and (4) identifying mountain cracks of all cut pictures through the trained crack identification model, and outputting results through a Softmax classifier.
Further, when the result is output through the Softmax classifier, if the probability value of the crack existing in the picture is greater than 0.5, the picture is output as the crack existing.
The invention has the beneficial effects that:
(1) According to the data acquisition system applied to the environmental monitoring of the railway system, the train of the railway system is early warned according to the obtained twenty-four hour rainfall information of a certain area, the train is prevented from being in danger of flood, the debris flow area of a mountain area is measured in rainy days, and after the information about the occurrence of the debris flow and the scale information of the debris flow are obtained, the train is required to be forbidden to pass through the area, so that the life and property safety of people of train workers and passengers are protected.
(2) By analyzing and processing the mountain cracks in a fine day and carrying out debris flow disaster early warning when the mountain cracks grow too much in length, the debris flow monitoring is completed in a fine day, and the comprehensiveness of environment monitoring is improved. And the accuracy of identifying the mountain cracks is improved by preprocessing a training image acquired in advance, performing superpixel segmentation on the image subjected to binarization processing by a superpixel segmentation method, training and testing a crack identification model based on a caffe deep learning framework, zooming the initial mountain area image or the real-time mountain area image when performing crack identification on the initial mountain area image or the real-time mountain area image, and cutting a plurality of pictures with certain sizes.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic block diagram of a data acquisition system for environmental monitoring of a railway system according to an embodiment of the present invention.
In the figure:
1. a train pilot; 2. an environment acquisition module; 3. an image acquisition module; 4. an energy supply module; 5. a train high-frequency radar detection module; 6. a rainfall early warning module; 7. railway line mud-rock flow early warning module.
Detailed Description
For further explanation of the various embodiments, the drawings are provided as part of the present disclosure and serve primarily to illustrate the embodiments and, together with the description, serve to explain the principles of operation of the embodiments, and to enable others of ordinary skill in the art to understand the various embodiments and with the advantages offered thereby.
According to an embodiment of the invention, a data acquisition system applied to environmental monitoring of a railway system is provided.
Referring to the drawings and the detailed description, as shown in fig. 1, according to the data acquisition system for monitoring the environment of the railway system, the system comprises a train barrier removing device 1, an environment acquisition module 2, an image acquisition module 3, an energy supply module 4, a train high-frequency radar detection module 5, a rainfall early warning module 6 and a railway line debris flow early warning module 7.
The rail-mounted obstacle deflector 1 is used for pushing obstacles on a train rail to two sides of a train when the train runs, so that the train can run normally.
And the environment acquisition module 2 is used for acquiring the rail side data of the railway train track, processing the acquired rail side data and then sending the processed rail side data to the backup center.
In one embodiment, when the rail-side data of the railway train rail is collected, the side surface and the bottom surface of the steel rail of the railway train rail are measured by the patch type temperature sensor;
measuring the atmospheric temperature and the atmospheric humidity through an atmospheric temperature sensor and an atmospheric humidity sensor which are arranged in the electric service relay station;
smoke and wind power are measured by a smoke sensor and a wind sensor which are arranged on the electric service relay station.
In one embodiment, when the collected rail-side data is processed and transmitted to the back-up center, the rail-side data is received and processed by the industrial personal computer, the processed rail-side data is transmitted to the back-up center, and the attendant of the back-up center arranges the train attendant to adjust the speed of the railway train according to the transmitted data.
When the industrial personal computer receives and processes the rail edge data, the acquired analog electric signals are received and converted into digital signals which can be identified by the industrial personal computer and are sent to a computer bus, and data acquisition instructions are sent to the industrial personal computer through the computer bus and are transmitted to various sensors for acquisition.
And the image acquisition module 3 is used for acquiring images along the railway and transmitting the acquired images along the railway to a vehicle-mounted terminal in the train.
Energy supply module 4 for change light energy into the electric energy through solar energy component, and right environment acquisition module 2 reaches image acquisition module 3 supplies power, and if do not have when sunshine, do through the battery of configuration in advance environment acquisition module 2 reaches image acquisition module 3 supplies power.
And the train high-frequency radar detection module 5 is used for detecting and imaging in real time through a high-frequency radar installed on the train and acquiring remote road condition information.
In one embodiment, the high-frequency radar installed on the train detects and images in real time, and when long-distance road condition information is acquired, an object in front of the train is detected and imaged through ultrahigh-frequency electromagnetic waves emitted by the high-frequency radar.
The transmitting antenna of the high-frequency radar transmits carrier-free electromagnetic pulse waves to the front of the railway train, and the receiving antenna receives reflected echoes;
determining whether the running direction of the railway train has an obstacle or not according to the travel time of the reflected echo:
hthe distance between the barrier and the train;
xis the distance between the transmitting antenna and the receiving antenna;
vis the radar pulse wave velocity.
When an obstacle appears in the running direction of the railway train, the train is decelerated and finally stopped.
And the rainfall early warning module 6 is used for acquiring the rainfall of any region through weather forecast and issuing early warning alarm to the region according to the rainfall of the weather forecast.
In one embodiment, when the rainfall capacity of any area within 24 hours is obtained through weather forecast, and early warning alarm is issued to the area according to the rainfall capacity of the weather forecast, when the rainfall capacity (24 hours) of the weather forecast is 120-135 mm, a blue alarm is issued to the area, if the rainfall capacity of the weather forecast is 135-145 mm, a yellow alarm is issued to the area, if the rainfall capacity of the weather forecast is 145-155 mm, an orange alarm is issued to the area, and if the rainfall capacity of the weather forecast is higher than 155 mm, a red alarm is issued to the area;
if the area is a mountain ditch area and the rainfall of the weather forecast is higher than 155 mm, the train is required to be forbidden to pass through the area.
And the railway line debris flow early warning module 7 is used for respectively early warning debris flow disasters in the train running line in sunny days and rainy days.
In one embodiment, when the early warning is carried out on debris flow disasters in a train running route in rainy days, in a mountain area where attention is focused, a debris flow measuring sensor is arranged in a groove in the side wall of a debris flow section, and a first voltage value of the debris flow measuring sensor is recorded;
when the sensor is submerged by debris fluid, acquiring a second voltage value of the debris flow measuring sensor, and when the second voltage value is far smaller than the first voltage value, determining that debris flow occurs and early warning of debris flow disasters;
measuring the debris flow depth through an ultrasonic debris level alarm, and judging the scale of the debris flow;
and after the obtained debris flow occurrence information and the debris flow scale information are obtained, the train is required to forbid passing through the area.
The debris flow sound is generated by transmitting along the direction of the gully bed in the debris flow movement process, the frequency of the debris flow sound is at least 20 decibels higher than other frequencies in the environment, and the debris flow sound can be used for early warning.
In one embodiment, when the early warning is performed on the debris flow disaster in the train running route on a fine day, the high-definition camera and the positioning module are erected on the unmanned aerial vehicle, the unmanned aerial vehicle is operated to drive the high-definition camera and the positioning module to shoot the mountain area which is focused at a certain height, an initial mountain area image is obtained, and meanwhile, the length of the crack in the initial mountain area image is calculated;
in a sunny day (and in the same way in other non-rainy days), the same unmanned aerial vehicle is used for driving a high-definition camera to shoot the same mountain area at a certain height, a real-time mountain area image is obtained, and the length of a crack in the real-time mountain area image is calculated;
and if the growth rate of the crack length in the real-time mountain area image relative to the crack length in the initial mountain area image is larger than a preset growth threshold value, judging that the mountain area is a dangerous area, and early warning for debris flow disasters. At this time, the mountain is very easy to have debris flow, such as heavy rain attack or other reasons, which causes debris flow disasters.
In one embodiment, when the length of the crack in the initial mountain area image or the real-time mountain area image is obtained through calculation, preprocessing a training image acquired in advance, and identifying the crack in the preprocessed image based on a caffe deep learning framework (a deep learning framework with expressiveness, speed and thinking modularization);
and identifying the cracks of the initial mountain area image or the real-time mountain area image, marking the cracks through the lines, and calculating the length of the lines, namely the length of the cracks.
In one embodiment, when the pre-processing is performed on the pre-acquired training image and the crack recognition is performed on the pre-processed image based on the caffe deep learning framework, the pre-acquired training image is enhanced by a piecewise linear function:
Denoising the enhanced image;
carrying out binarization processing on the denoised image;
carrying out super-pixel segmentation on the image subjected to binarization processing by using a super-pixel segmentation method, clustering a plurality of irregular image blocks, storing and establishing a data set of a crack identification model;
training and testing a crack recognition model based on a caffe deep learning framework, and obtaining the trained crack recognition model;
generating a training set and a verification set which accord with the learning of a cafe deep learning framework based on a data set in a manual labeling mode, wherein the ratio of positive and negative samples is 2.
When the crack identification is carried out on the initial mountain area image or the real-time mountain area image, the initial mountain area image or the real-time mountain area image is zoomed, and a picture with a certain size is cut, and the cutting processing times are twelve, so that the recognition accuracy of the mountain crack is improved.
And identifying mountain cracks on all cut pictures through the trained crack identification model, and outputting results through a Softmax classifier (the Softmax classifier is a logistic regression classifier and is used for generalizing and summarizing a plurality of classifications). And when the result is output, comprehensively considering all the results and finally giving the result to the initial mountain area image or the real-time mountain area image.
In an embodiment, when the result is output through the Softmax classifier, if the probability value of the crack existing in the picture is greater than 0.5, the picture is output as the crack existing.
In summary, according to the data acquisition system applied to the environmental monitoring of the railway system, the train of the railway system is warned in advance according to the obtained twenty-four hour rainfall information of a certain area, so that the train is prevented from being in a flood danger, the debris flow area of the mountainous area is measured in rainy days, and after the information about the occurrence of the debris flow and the scale information of the debris flow are obtained, the train is required to be forbidden to pass through the area, and the life and property safety of people and passengers of the train are protected. By analyzing and processing the cracks of the mountain in a fine day and carrying out debris flow disaster early warning when the length of the cracks of the mountain is excessively increased, the debris flow monitoring is finished in a fine day, and the comprehensiveness of environment monitoring is improved. And preprocessing a training image acquired in advance, performing superpixel segmentation on the image subjected to binarization processing by a superpixel segmentation method, and training and testing a crack identification model based on a caffe deep learning framework, and zooming the initial mountain area image or the real-time mountain area image and cutting a plurality of pictures with certain sizes when performing crack identification on the initial mountain area image or the real-time mountain area image, so that the accuracy of identifying the mountain cracks is improved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. A data acquisition system applied to environmental monitoring of a railway system is characterized by comprising a train barrier removing device, an environment acquisition module, an image acquisition module, an energy supply module, a train high-frequency radar detection module, a rainfall early warning module and a railway line debris flow early warning module;
wherein, the train barrier-removing device is used for removing the barrier in the running process of the railway train, pushing the barriers on the train track to the two sides of the train to enable the train to normally run;
the environment acquisition module is used for acquiring the rail side data of the railway train rail, processing the acquired rail side data and then sending the processed rail side data to the backup center;
the image acquisition module is used for acquiring railway line images and transmitting the acquired railway line images to a vehicle-mounted terminal in a train;
the energy supply module is used for converting light energy into electric energy through the solar component, supplying power to the environment acquisition module and the image acquisition module, and supplying power to the environment acquisition module and the image acquisition module through a pre-configured storage battery if sunlight does not exist;
the train high-frequency radar detection module is used for detecting and imaging in real time through a high-frequency radar installed on a train and acquiring long-distance road condition information;
the rainfall early warning module is used for acquiring the rainfall of any region through weather forecast and issuing early warning alarm to the region according to the rainfall of the weather forecast;
the railway line debris flow early warning module is used for respectively early warning debris flow disasters in a train running line in sunny days and rainy days; when the early warning is carried out on debris flow disasters in a train running route on a fine day, the high-definition camera and the positioning module are erected on the unmanned aerial vehicle, the unmanned aerial vehicle is controlled to drive the high-definition camera and the positioning module to shoot a mountain area which is focused at a certain height, an initial mountain area image is obtained, and meanwhile the length of a crack in the initial mountain area image is obtained through calculation.
2. The data acquisition system applied to the environmental monitoring of the railway system as claimed in claim 1, wherein, when the rail edge data of the railway train rail is acquired, the side surface and the bottom surface of the steel rail of the railway train rail are measured by a patch type temperature sensor;
measuring the atmospheric temperature and the atmospheric humidity through an atmospheric temperature sensor and an atmospheric humidity sensor which are arranged on the electric service relay station;
smoke and wind power are measured by a smoke sensor and a wind sensor which are arranged on the electric service relay station.
3. The data acquisition system applied to environmental monitoring of a railway system as claimed in claim 2, wherein the collected data on the track side is processed and then transmitted to the back-up center, the industrial personal computer receives and processes the data on the track side and transmits the processed data on the track side to the back-up center, and a attendant at the back-up center arranges a train attendant to adjust the speed of the railway train according to the transmitted data.
4. The data acquisition system applied to environmental monitoring of a railway system according to claim 1, wherein the high frequency radar installed on the train is used for real-time detection and imaging, and when long-distance road condition information is acquired, an object in front of the railway train is detected and imaged through ultrahigh frequency electromagnetic waves emitted by the high frequency radar;
the transmitting antenna of the high-frequency radar transmits carrier-free electromagnetic pulse waves to the front of the railway train, and the receiving antenna receives reflected echoes;
determining whether the running direction of the railway train has an obstacle or not according to the travel time of the reflected echo:
hdistance of the barrier from the train;
xis the distance between the transmitting antenna and the receiving antenna;
vis the radar pulse wave velocity;
when an obstacle appears in the running direction of the railway train, the train is decelerated and finally stopped.
5. The data acquisition system applied to the environmental monitoring of the railway system as claimed in claim 1, wherein the rainfall in any area within 24 hours is obtained through weather forecast, and when the area is issued with early warning alarm according to the rainfall in the weather forecast, the rainfall in the weather forecast is 120-135 mm, then a blue alarm is issued to the area, if the rainfall in the weather forecast is 135-145 mm, then a yellow alarm is issued to the area, if the rainfall in the weather forecast is 145-155 mm, then an orange alarm is issued to the area, if the rainfall in the weather forecast is higher than 155 mm, then a red alarm is issued to the area;
if the area is a mountain ditch area and the rainfall of the weather forecast is higher than 155 mm, the train is required to be forbidden to pass through the area.
6. The data acquisition system applied to the environmental monitoring of the railway system as claimed in claim 1, wherein when the early warning is performed on the debris flow disaster in the running route of the train in rainy days, the debris flow measuring sensor is arranged in a groove on the side wall of the debris flow section in the mountain area where the attention is focused, and a first voltage value of the debris flow measuring sensor is recorded;
when the sensor is submerged by debris fluid, acquiring a second voltage value of the debris flow measuring sensor, and when the second voltage value is far smaller than the first voltage value, determining that debris flow occurs and early warning of debris flow disasters;
measuring the debris flow depth through an ultrasonic debris level alarm, and judging the scale of the debris flow;
and after the obtained debris flow occurrence information and the debris flow scale information are obtained, the train is required to forbid passing through the area.
7. The data acquisition system applied to the environmental monitoring of the railway system as claimed in claim 1, wherein in a sunny day, the same unmanned aerial vehicle is used to drive the high-definition camera to shoot the same mountain area at a certain height, a real-time image of the mountain area is obtained, and the length of the crack in the real-time image of the mountain area is calculated;
if the growth rate of the length of the crack in the real-time mountain area image relative to the length of the crack in the initial mountain area image is larger than a preset growth threshold value, judging that the mountain area is a dangerous area, and early warning the debris flow disaster;
when the length of the crack in the initial mountain area image or the real-time mountain area image is obtained through calculation, preprocessing a training image acquired in advance, and recognizing the crack of the preprocessed image based on a caffe deep learning framework;
identifying cracks on the initial mountain area image or the real-time mountain area image, marking the cracks through lines, and calculating the length of the lines, namely the length of the cracks;
when the pre-processing is carried out on the training image obtained in advance and the crack recognition is carried out on the pre-processed image based on the mask deep learning framework, the training image obtained in advance is enhanced through a piecewise linear function:
denoising the enhanced image;
carrying out binarization processing on the denoised image;
performing superpixel segmentation on the image subjected to binarization processing by a superpixel segmentation method, clustering a plurality of irregular image blocks simultaneously, and storing and establishing a data set of a crack identification model;
training and testing a crack recognition model based on a caffe deep learning framework, and obtaining the trained crack recognition model;
when the crack identification is carried out on the initial mountain area image or the real-time mountain area image, the initial mountain area image or the real-time mountain area image is zoomed, and a picture with a certain size is cut, wherein the cutting processing times are twelve;
and (4) identifying mountain cracks of all cut pictures through the trained crack identification model, and outputting results through a Softmax classifier.
8. The data acquisition system applied to environmental monitoring of a railway system as claimed in claim 1, wherein when the result is output through the Softmax classifier, if the probability value of the crack existing in the picture is greater than 0.5, the picture is output as the crack existing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310102073.0A CN115782969A (en) | 2023-02-13 | 2023-02-13 | Data acquisition system applied to environmental monitoring of railway system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310102073.0A CN115782969A (en) | 2023-02-13 | 2023-02-13 | Data acquisition system applied to environmental monitoring of railway system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115782969A true CN115782969A (en) | 2023-03-14 |
Family
ID=85430936
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310102073.0A Pending CN115782969A (en) | 2023-02-13 | 2023-02-13 | Data acquisition system applied to environmental monitoring of railway system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115782969A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117687032A (en) * | 2024-02-04 | 2024-03-12 | 上海联赣光电科技有限公司 | System and method for regulating and controlling micro rain radar |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201820337U (en) * | 2010-10-28 | 2011-05-04 | 成都智胜通科技有限责任公司 | Railway geological disaster forecasting and monitoring system |
| CN103033808A (en) * | 2012-12-24 | 2013-04-10 | 西安电子工程研究所 | Method and device of railway roadblock detection and alarm based on radar return characteristics |
| CN103978996A (en) * | 2014-05-15 | 2014-08-13 | 南京理工大学 | High speed railway environmental information collection, assessment and early warning device and method |
| WO2018016703A1 (en) * | 2016-07-18 | 2018-01-25 | 연세대학교 산학협력단 | Wireless sensor network measurement system and measurement method for monitoring, forecasting and alarming landslide |
| CN109840483A (en) * | 2019-01-11 | 2019-06-04 | 深圳大学 | A kind of method and device of landslide fissure detection and identification |
| CN110415491A (en) * | 2019-08-09 | 2019-11-05 | 华北科技学院 | Mud-stone flow disaster Integrated Monitoring System and visualization early warning cloud platform |
| CN115578725A (en) * | 2022-09-08 | 2023-01-06 | 中国地质环境监测院(自然资源部地质灾害技术指导中心) | Landslide boundary and crack marking method and system based on man-machine cooperation |
-
2023
- 2023-02-13 CN CN202310102073.0A patent/CN115782969A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201820337U (en) * | 2010-10-28 | 2011-05-04 | 成都智胜通科技有限责任公司 | Railway geological disaster forecasting and monitoring system |
| CN103033808A (en) * | 2012-12-24 | 2013-04-10 | 西安电子工程研究所 | Method and device of railway roadblock detection and alarm based on radar return characteristics |
| CN103978996A (en) * | 2014-05-15 | 2014-08-13 | 南京理工大学 | High speed railway environmental information collection, assessment and early warning device and method |
| WO2018016703A1 (en) * | 2016-07-18 | 2018-01-25 | 연세대학교 산학협력단 | Wireless sensor network measurement system and measurement method for monitoring, forecasting and alarming landslide |
| CN109840483A (en) * | 2019-01-11 | 2019-06-04 | 深圳大学 | A kind of method and device of landslide fissure detection and identification |
| CN110415491A (en) * | 2019-08-09 | 2019-11-05 | 华北科技学院 | Mud-stone flow disaster Integrated Monitoring System and visualization early warning cloud platform |
| CN115578725A (en) * | 2022-09-08 | 2023-01-06 | 中国地质环境监测院(自然资源部地质灾害技术指导中心) | Landslide boundary and crack marking method and system based on man-machine cooperation |
Non-Patent Citations (1)
| Title |
|---|
| 杨凯等: "《MATLAB基础应用及仿真实现》", 西南交通大学出版社, pages: 162 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117687032A (en) * | 2024-02-04 | 2024-03-12 | 上海联赣光电科技有限公司 | System and method for regulating and controlling micro rain radar |
| CN117687032B (en) * | 2024-02-04 | 2024-04-26 | 上海联赣光电科技有限公司 | System and method for regulating and controlling micro rain radar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100440269C (en) | Intelligent detecting prewarning method for expressway automobile running and prewaring system thereof | |
| EP3885794A1 (en) | Track and road obstacle detecting method | |
| CN103287464B (en) | Intelligent video surveillance system at railway crossing and implement method of system | |
| CN109552366B (en) | Intelligent detection and alarm system for locomotive-mounted railway obstacles and early warning method thereof | |
| CN111225189B (en) | Middle and small-sized channel bridge monitoring device | |
| CN104916166A (en) | Bridge anti-collision warning system and realization method | |
| CN113799852B (en) | Intelligent active obstacle identification protection method supporting dynamic mode switching | |
| CN109977748A (en) | A kind of train obstacle detection method of more integration technologies | |
| CN115782969A (en) | Data acquisition system applied to environmental monitoring of railway system | |
| CN109544991A (en) | A kind of bus or train route collaboration bend vehicle meeting early warning system and control method | |
| CN112061179A (en) | Active anti-collision device and method for rail vehicle based on unmanned aerial vehicle | |
| CN115497340A (en) | Inland waterway traffic state holographic sensing system and method | |
| KR102302476B1 (en) | Real-time obstacle detection system for a railway vehicle | |
| CN109572757B (en) | Method and device for detecting and positioning railway falling rocks | |
| CN111062268A (en) | Trackside object intrusion detection method and system | |
| CN116165655A (en) | Global vehicle track tracking system based on millimeter wave radar group | |
| CN115743195A (en) | Mining intelligent flatbed | |
| CN110501699A (en) | Obstacle detection system and detection method between a kind of shield door and car body | |
| CN116118827A (en) | Unmanned crossing remote early warning method, system, equipment and storage medium | |
| CN115620000A (en) | Intelligent identification method for accumulated water of slag-free ballast bed | |
| CN111114587A (en) | Station train receiving and dispatching early warning system and image preprocessing method thereof | |
| CN113386825A (en) | Monitoring processing system and method | |
| CN114802354B (en) | Intrusion detection system, method and early warning system for track construction section | |
| CN221438012U (en) | Railway line foreign matter intrusion monitoring alarm device | |
| CN112896231B (en) | Railway track sand burying degree monitoring device and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230314 |