CN115009324B - Rail transit unstable network accident early warning system and method based on cloud edge cooperation - Google Patents
Rail transit unstable network accident early warning system and method based on cloud edge cooperation Download PDFInfo
- Publication number
- CN115009324B CN115009324B CN202210800454.1A CN202210800454A CN115009324B CN 115009324 B CN115009324 B CN 115009324B CN 202210800454 A CN202210800454 A CN 202210800454A CN 115009324 B CN115009324 B CN 115009324B
- Authority
- CN
- China
- Prior art keywords
- train
- early warning
- accident
- carriage
- server
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004891 communication Methods 0.000 claims abstract description 22
- 230000002159 abnormal effect Effects 0.000 claims description 95
- 238000001914 filtration Methods 0.000 claims description 33
- 238000012545 processing Methods 0.000 claims description 22
- 238000005259 measurement Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000005540 biological transmission Effects 0.000 claims description 10
- 238000004140 cleaning Methods 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 9
- 230000005856 abnormality Effects 0.000 claims description 6
- 206010039203 Road traffic accident Diseases 0.000 abstract description 8
- 238000012544 monitoring process Methods 0.000 abstract 1
- 230000009286 beneficial effect Effects 0.000 description 7
- 230000007547 defect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L15/00—Indicators provided on the vehicle or train for signalling purposes
- B61L15/0072—On-board train data handling
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L15/00—Indicators provided on the vehicle or train for signalling purposes
- B61L15/0081—On-board diagnosis or maintenance
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
- B61L27/20—Trackside control of safe travel of vehicle or train, e.g. braking curve calculation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
- B61L27/40—Handling position reports or trackside vehicle data
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a track traffic unstable network accident early warning system and method based on cloud edge cooperation, belonging to the technical field of track traffic on-line monitoring, wherein the system comprises: the system comprises a plurality of carriage end sensors, a plurality of carriage end controllers, a plurality of carriage end servers, a plurality of vehicle side servers, a plurality of train control subsystems, a ground cloud server, a vehicle information table, a line information table and an anomaly code table; the method is an early warning method corresponding to a rail transit unstable network accident early warning system based on cloud edge coordination, and the TCP communication method of network early warning adopted between a vehicle edge server and a ground cloud server is used for realizing the rail transit unstable network accident early warning based on cloud edge coordination, so that the stability and the communication efficiency of a rail transit accident early warning network are improved; the invention solves the problems of unstable and untimely communication of the existing rail traffic accident early warning network.
Description
Technical Field
The invention belongs to the technical field of strain measurement, and particularly relates to a rail transit unstable network accident early warning system and method based on cloud edge cooperation.
Background
Along with the acceleration of urban construction in China, the track mileage is continuously increased, and the total track mileage in China is first worldwide at present. With the increase of rail vehicles, the total mileage of the rail is increased, and the number of rail traffic accidents is also increased. And the casualties, economic accidents and subsequent influences caused by the rail traffic accidents far exceed the common traffic accidents, so that the rail traffic safety problem is gradually highlighted.
Conventional rail traffic accident early warning has the following defects:
(1) The data acquisition frequency is low, the data volume is small, and a plurality of anomalies can not be found
(2) The data acquisition frequency is high, the data volume is large, the network does not support real-time uploading of a large amount of data, and real-time early warning cannot be achieved;
(3) The network is unstable, real-time communication cannot be realized, and the cloud server cannot issue a control instruction to the vehicle in time;
(4) The network is unstable, the vehicle cannot upload the vehicle end alarm in real time, the cloud server cannot acquire the alarm in time, other vehicles on the same line cannot be notified, and other vehicles cannot make evasion actions in time.
Disclosure of Invention
Aiming at the defects in the prior art, the rail traffic unstable network accident early warning system and method based on cloud edge cooperation solve the problems of instability and untimely communication of the existing rail traffic accident early warning network.
In order to achieve the aim of the invention, the invention adopts the following technical scheme:
the invention provides a rail transit unstable network accident early warning system based on cloud edge cooperation, which comprises:
the carriage end sensors are used for collecting measurement data of to-be-detected parts of each train carriage when the train runs;
the system comprises a plurality of carriage end controllers, a plurality of vehicle side servers and a plurality of vehicle side servers, wherein the carriage end controllers are used for controlling the corresponding carriage end sensors to output measurement data, performing data cleaning and characteristic value filtering processing on the measurement data by utilizing a characteristic value filtering algorithm model to obtain characteristic values of the controllers, and receiving carriage control instructions transmitted by the vehicle side servers;
the carriage end servers are used for carrying out edge calculation processing on the characteristic values of the controller by utilizing the carriage accident early warning algorithm model to obtain and store corresponding end server characteristic data, and updating the characteristic value filtering algorithm model;
the train side servers are used for processing end server characteristic data based on the vehicle accident early warning algorithm model to obtain train abnormal event information and train accident occurrence probability, respectively transmitting the train abnormal event information and the train accident occurrence probability to the ground cloud server and the train control subsystem, receiving the abnormal early warning information and the train abnormal control instruction, transmitting the train abnormal control instruction to the corresponding train control subsystem and updating the carriage accident early warning algorithm model;
the train control subsystems are used for acquiring train abnormal event information, train accident probability and train abnormal control instructions, checking the train abnormal control instructions and controlling the train to stop at a reduced speed according to the checking result;
the ground cloud server is used for acquiring train abnormal event information and train accident occurrence probability obtained by each vehicle side server, respectively transmitting abnormal early warning information and train abnormal control instructions to each corresponding vehicle side server, and updating a vehicle accident early warning algorithm model;
the vehicle information table is used for displaying the corresponding relation between the train serial number and the train number;
the line information table is used for displaying the train line, the direction, the vehicle section and specific positioning information;
the abnormal code table is used for displaying train serial numbers, abnormal states and safety actions in a corresponding sequence.
The beneficial effects of the invention are as follows: according to the rail transit unstable network accident early warning system based on cloud edge cooperation, the data quantity is reduced through data cleaning, eigenvalue filtering processing and edge computing processing, under the condition that transmission data is larger, the data processing error is smaller compared with that of a traditional carriage end controller, computing is more accurate, and the vehicle accident early warning algorithm model, carriage accident early warning algorithm models and eigenvalue filtering algorithm models provided in the scheme can be updated based on a ground cloud server, so that the system can adapt to higher-strength learning optimization and improve recognition accuracy.
The invention also provides an early warning method of the rail transit unstable network accident early warning system based on cloud edge cooperation, which comprises the following steps:
s1, respectively updating algorithm models of a vehicle side server, a carriage end server and a carriage end controller to obtain updated vehicle accident early-warning algorithm models, carriage accident early-warning algorithm models and characteristic value filtering algorithm models;
s2, acquiring measurement data of to-be-detected parts of each train carriage during train operation, and obtaining end server characteristic data based on the updated vehicle accident early-warning algorithm model, each carriage accident early-warning algorithm model and each characteristic value filtering algorithm model;
s3, utilizing the characteristic data of the receiving end server of each vehicle side server, obtaining train abnormal event information and train accident occurrence probability based on a vehicle accident early warning algorithm model, and respectively transmitting the train abnormal event information and the train accident occurrence probability to a ground cloud server and a train control subsystem;
s4, acquiring abnormal early warning information and a train abnormal control instruction by utilizing the ground cloud server according to the train abnormal event information and the train accident occurrence probability, and transmitting the train abnormal event information and the train accident occurrence probability to each corresponding vehicle side server;
and S5, acquiring train abnormal event information, train accident occurrence probability and train abnormal control instructions by utilizing each train control subsystem, carrying out safety verification on the train abnormal control instructions based on the train abnormal event information and the train accident occurrence probability to obtain a verification result, controlling the train to stop at a reduced speed according to the verification result, and completing early warning of the rail transit unstable network accident based on cloud-edge cooperation.
The beneficial effects of the invention are as follows: the warning method of the rail transit unstable network accident warning system based on cloud edge cooperation is a warning method corresponding to the rail transit unstable network accident warning system based on cloud edge cooperation, and the TCP communication method of network warning adopted between the vehicle edge server and the ground cloud server is used for realizing the rail transit unstable network accident warning based on cloud edge cooperation, so that the stability and the communication efficiency of the rail transit accident warning network are improved.
Further, the step S1 includes the steps of:
s11, updating a vehicle accident early warning algorithm model by using a ground cloud server and transmitting the vehicle accident early warning algorithm model to a vehicle side server;
s12, based on the updated vehicle accident early-warning algorithm model, updating the corresponding carriage accident early-warning algorithm model by using the vehicle side server, and transmitting the carriage accident early-warning algorithm model to each carriage side server;
and S13, updating the corresponding characteristic value filtering algorithm model through a carriage end server based on the updated carriage accident early warning algorithm model, and transmitting the characteristic value filtering algorithm model to each carriage end controller.
The beneficial effects of adopting the further scheme are as follows: the vehicle accident early warning algorithm model is updated according to the actual train running position and running condition based on the ground cloud server, and the carriage accident early warning algorithm model and the characteristic value filtering algorithm model are updated layer by layer, so that characteristic values under different train running conditions can be effectively extracted, and train abnormal event information and train accident occurrence probability can be obtained.
Further, the step S2 includes the steps of:
s21, acquiring measurement data of to-be-detected parts of each train carriage when the train runs by using a plurality of carriage end sensors;
s22, carrying out data cleaning and eigenvalue filtering processing on the measured data by utilizing each carriage end controller according to the updated eigenvalue filtering algorithm model to obtain the characteristic value of the controller;
and S23, performing edge calculation processing on the characteristic values of the controller by utilizing a carriage end server according to a carriage accident early warning algorithm model to obtain and store corresponding end server characteristic data.
The beneficial effects of adopting the further scheme are as follows: the existing method generally realizes data acquisition, data cleaning and filtering processing and edge calculation through a carriage end controller, but in the actual working process, under the existing hardware condition, the carriage end controller cannot support the acquisition, cleaning and filtering processing and calculation of high-frequency data (1000 HZ), so that the scheme is rich in data processing process, the carriage end controller is used for carrying out data acquisition and cleaning and filtering processing, and the end server is used for carrying out the edge calculation of the characteristic value of the controller, so that the calculation error is 0.1m at the frequency of 1000HZ when the train runs at high speed of 360 km/h=100 m/s, the more data, the smaller the error is, the more accurate the calculation result is, and the smaller the hardware pressure is.
Further, a TCP communication method of network early warning is adopted between the vehicle side server and the ground cloud server.
The beneficial effects of adopting the further scheme are as follows: the TCP communication method of network early warning adopted between the vehicle side server and the ground cloud server realizes the track traffic unstable network accident early warning of cloud side cooperation, and improves the stability and communication efficiency of the track traffic accident early warning network.
Further, the TCP communication method of the network early warning comprises the following steps:
a1, performing TCP three-way handshake between a vehicle side server and a ground cloud server;
a2, respectively defining a first TCP data format and a second TCP data format of transmission;
a3, transmitting a first TCP data packet comprising train abnormal event information and train accident occurrence probability to a ground cloud server based on a first TCP data format;
a4, analyzing the first TCP data packet by utilizing the ground cloud server according to the vehicle information table, the line information table and the anomaly code table to obtain train anomaly event information and train accident occurrence probability;
a5, based on the train abnormal event information and the train accident occurrence probability, obtaining abnormal early warning information and a train abnormal control instruction;
a6, transmitting a second TCP data packet comprising abnormality early warning information and a train abnormality control instruction to a train side server of other trains on the same line based on a second TCP data format;
and A7, analyzing the second TCP data packet by utilizing each vehicle side server according to the vehicle information table, the line information table and the anomaly code table to obtain anomaly early warning information and a train anomaly control instruction.
The beneficial effects of adopting the further scheme are as follows: according to the scheme, the vehicle side server defines a first TCP data format and a second TCP data format based on a TCP minimum transmission unit when a TCP connection request is initiated to the ground cloud server by the vehicle side server, so that stable and efficient communication between the vehicle side server and the ground cloud server is realized, and traffic instability network accident early warning of cloud side cooperation is realized.
Further, the step A2 includes the steps of:
a21, defining the length of the first TCP data and the second TCP data to be 1460 bytes;
a22, bytes 0 and 1 defining the first TCP data and the second TCP data each describe a vehicle number;
a23, defining the 2 nd byte, the 3 rd byte and the 4 th byte of the first TCP data and the second TCP data, and respectively describing the hour, the minute and the second correspondingly;
a24, defining the 5 th byte and the 6 th byte of the first TCP data and the second TCP data to describe a train line, wherein the 7 th byte describes a train trend, and the 8 th byte to the 10 th byte describe a train specific position;
a25, defining 11 th bytes to 100 th bytes of the first TCP data and the second TCP data to describe train abnormal event information;
a26, defining 101 th byte to 1660 th byte of the first TCP data to describe abnormal event analog quantity and corresponding train accident occurrence probability;
a27, defining 101 th byte to 1660 th byte of the second TCP data to describe abnormal event analog quantity and corresponding train abnormal control instruction.
The beneficial effects of adopting the further scheme are as follows: based on the minimum transmission unit of TCP, a first TCP data format and a second TCP data format are defined, and a basis is provided for the vehicle side server to perform stable and efficient communication between the ground cloud servers.
Drawings
Fig. 1 is a block diagram of a rail transit unstable network accident early warning system based on cloud-edge cooperation in an embodiment of the invention.
Fig. 2 is a flowchart of steps of an early warning method of a rail transit unstable network accident early warning system based on cloud-edge cooperation in an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and all the inventions which make use of the inventive concept are protected by the spirit and scope of the present invention as defined and defined in the appended claims to those skilled in the art.
Example 1
As shown in fig. 1, in one embodiment of the present invention, the present invention provides a rail transit unstable network accident early warning system based on cloud-edge coordination, including:
the carriage end sensors are used for collecting measurement data of to-be-detected parts of each train carriage when the train runs;
the system comprises a plurality of carriage end controllers, a plurality of vehicle side servers and a plurality of vehicle side servers, wherein the carriage end controllers are used for controlling the corresponding carriage end sensors to output measurement data, performing data cleaning and characteristic value filtering processing on the measurement data by utilizing a characteristic value filtering algorithm model to obtain characteristic values of the controllers, and receiving carriage control instructions transmitted by the vehicle side servers;
the carriage end servers are used for carrying out edge calculation processing on the characteristic values of the controller by utilizing the carriage accident early warning algorithm model to obtain and store corresponding end server characteristic data, and updating the characteristic value filtering algorithm model;
the train side servers are used for processing end server characteristic data based on the vehicle accident early warning algorithm model to obtain train abnormal event information and train accident occurrence probability, respectively transmitting the train abnormal event information and the train accident occurrence probability to the ground cloud server and the train control subsystem, receiving the abnormal early warning information and the train abnormal control instruction, transmitting the train abnormal control instruction to the corresponding train control subsystem and updating the carriage accident early warning algorithm model;
the train control subsystems are used for acquiring train abnormal event information, train accident probability and train abnormal control instructions, checking the train abnormal control instructions and controlling the train to stop at a reduced speed according to the checking result;
the ground cloud server is used for acquiring train abnormal event information and train accident occurrence probability obtained by each vehicle side server, respectively transmitting abnormal early warning information and train abnormal control instructions to each corresponding vehicle side server, and updating a vehicle accident early warning algorithm model;
the vehicle information table is used for displaying the corresponding relation between the train serial number and the train number;
the line information table is used for displaying the train line, the direction, the vehicle section and specific positioning information;
the abnormal code table is used for displaying train serial numbers, abnormal states and safety actions in a corresponding sequence.
The warning method of the rail transit unstable network accident warning system based on cloud edge cooperation is a warning method corresponding to the rail transit unstable network accident warning system based on cloud edge cooperation, and the TCP communication method of network warning adopted between the vehicle edge server and the ground cloud server is used for realizing the rail transit unstable network accident warning based on cloud edge cooperation, so that the stability and the communication efficiency of the rail transit accident warning network are improved.
Example 2
As shown in fig. 2, in another embodiment of the present invention, the present invention further provides an early warning method of a rail transit unstable network accident early warning system based on cloud-edge coordination, including the following steps:
s1, respectively updating algorithm models of a vehicle side server, a carriage end server and a carriage end controller to obtain updated vehicle accident early-warning algorithm models, carriage accident early-warning algorithm models and characteristic value filtering algorithm models;
the step S1 includes the steps of:
s11, updating a vehicle accident early warning algorithm model by using a ground cloud server and transmitting the vehicle accident early warning algorithm model to a vehicle side server;
s12, based on the updated vehicle accident early-warning algorithm model, updating the corresponding carriage accident early-warning algorithm model by using the vehicle side server, and transmitting the carriage accident early-warning algorithm model to each carriage side server;
s13, updating a corresponding characteristic value filtering algorithm model through a carriage end server based on the updated carriage accident early warning algorithm model, and transmitting the characteristic value filtering algorithm model to each carriage end controller;
s2, acquiring measurement data of to-be-detected parts of each train carriage during train operation, and obtaining end server characteristic data based on the updated vehicle accident early-warning algorithm model, each carriage accident early-warning algorithm model and each characteristic value filtering algorithm model;
the step S2 includes the steps of:
s21, acquiring measurement data of to-be-detected parts of each train carriage when the train runs by using a plurality of carriage end sensors;
s22, carrying out data cleaning and eigenvalue filtering processing on the measured data by utilizing each carriage end controller according to the updated eigenvalue filtering algorithm model to obtain the characteristic value of the controller;
s23, carrying out edge calculation processing on the characteristic values of the controller by utilizing a carriage end server according to a carriage accident early warning algorithm model to obtain and store corresponding end server characteristic data;
s3, utilizing the characteristic data of the receiving end server of each vehicle side server, obtaining train abnormal event information and train accident occurrence probability based on a vehicle accident early warning algorithm model, and respectively transmitting the train abnormal event information and the train accident occurrence probability to a ground cloud server and a train control subsystem;
s4, acquiring abnormal early warning information and a train abnormal control instruction by utilizing the ground cloud server according to the train abnormal event information and the train accident occurrence probability, and transmitting the train abnormal event information and the train accident occurrence probability to each corresponding vehicle side server;
s5, acquiring train abnormal event information, train accident occurrence probability and train abnormal control instructions by utilizing each train control subsystem, carrying out safety verification on the train abnormal control instructions based on the train abnormal event information and the train accident occurrence probability to obtain a verification result, controlling the train to stop at a reduced speed according to the verification result, and completing early warning of rail transit unstable network accidents based on cloud-edge cooperation;
a TCP communication method of network early warning is adopted between the vehicle side server and the ground cloud server;
the TCP communication method of the network early warning comprises the following steps:
a1, performing TCP three-way handshake between a vehicle side server and a ground cloud server;
a2, respectively defining a first TCP data format and a second TCP data format of transmission;
a3, transmitting a first TCP data packet comprising train abnormal event information and train accident occurrence probability to a ground cloud server based on a first TCP data format;
a4, analyzing the first TCP data packet by utilizing the ground cloud server according to the vehicle information table, the line information table and the anomaly code table to obtain train anomaly event information and train accident occurrence probability;
a5, based on the train abnormal event information and the train accident occurrence probability, obtaining abnormal early warning information and a train abnormal control instruction;
a6, transmitting a second TCP data packet comprising abnormality early warning information and a train abnormality control instruction to a train side server of other trains on the same line based on a second TCP data format;
a7, analyzing the second TCP data packet by utilizing each vehicle side server according to the vehicle information table, the line information table and the anomaly code table to obtain anomaly early warning information and a train anomaly control instruction;
the step A2 comprises the following steps:
a21, defining the length of the first TCP data and the second TCP data to be 1460 bytes;
each data transmission of the TCP protocol depends on MTU (maximum transmission unit of network) and MSS (maximum transmission data of network), MTU=MSS+TCP header+IP header, MSS maximum is 1460 bytes, therefore, the data length defined by the scheme is 1460 bytes, and the TCP message is based on single maximum data length transmission, so that the problems of unpacking, slicing, sticking and the like can be avoided, and the accuracy of the message is ensured;
a22, bytes 0 and 1 defining the first TCP data and the second TCP data each describe a vehicle number;
one byte has 8 bits, 2 8 *2 8 65536 can provide 65536 reservations of vehicle numbers, and can search the number of vehicles, and the like through the vehicle information table,Sequence number correspondence and coded sequence number;
a23, defining the 2 nd byte, the 3 rd byte and the 4 th byte of the first TCP data and the second TCP data, and respectively describing the hour, the minute and the second correspondingly;
due to 2 8 ＝64>24, a single byte can thus be used to describe hours, minutes and seconds in the time information;
a24, defining the 5 th byte and the 6 th byte of the first TCP data and the second TCP data to describe a train line, wherein the 7 th byte describes a train trend, and the 8 th byte to the 10 th byte describe a train specific position;
details of line, trend, and address by byte 5 and byte 6 of TCP data, 2 8 *2 8 *2 8 The method comprises the steps of (1) carrying out (i) 16777216, equally dividing each railway into 16777216 sections, wherein the length of the longest railway Beijing nine railways in China is 2553 km, 2553 x 1000/1048576 is approximately equal to 0.15 m, namely, accurate positioning of the train to the m can be ensured, coding numbers according to a line information table, and writing specific position information of a specific train at specific time;
a25, defining 11 th bytes to 100 th bytes of the first TCP data and the second TCP data to describe train abnormal event information;
a26, defining 101 th byte to 1660 th byte of the first TCP data to describe abnormal event analog quantity and corresponding train accident occurrence probability;
a27, defining 101 th byte to 1660 th byte of the second TCP data to describe abnormal event analog quantity and corresponding train abnormal control instruction;
using binary 1 and 0 in byte information to indicate whether to pre-warn, 2 can be described 8*90 The current alarm information can be judged according to the anomaly code table, and 101-1459 bytes are used for expressing the anomaly event analog quantity and the corresponding train accident occurrence probability or the anomaly event analog quantity and the corresponding train anomaly control instruction, and the specific analog quantity content can be defined according to the scene, so that the stability and the communication efficiency of the rail traffic accident early warning network can be improved;
the warning method of the rail transit unstable network accident warning system based on cloud edge cooperation is a warning method corresponding to the rail transit unstable network accident warning system based on cloud edge cooperation, and the TCP communication method of network warning adopted between the vehicle edge server and the ground cloud server is used for realizing the rail transit unstable network accident warning based on cloud edge cooperation, so that the stability and the communication efficiency of the rail transit accident warning network are improved.
Claims (7)
1. Track traffic unstable network accident early warning system based on cloud limit cooperation, characterized by comprising:
the carriage end sensors are used for collecting measurement data of to-be-detected parts of each train carriage when the train runs;
the system comprises a plurality of carriage end controllers, a plurality of vehicle side servers and a plurality of vehicle side servers, wherein the carriage end controllers are used for controlling the corresponding carriage end sensors to output measurement data, performing data cleaning and characteristic value filtering processing on the measurement data by utilizing a characteristic value filtering algorithm model to obtain characteristic values of the controllers, and receiving carriage control instructions transmitted by the vehicle side servers;
the carriage end servers are used for carrying out edge calculation processing on the characteristic values of the controller by utilizing the carriage accident early warning algorithm model to obtain and store corresponding end server characteristic data, and updating the characteristic value filtering algorithm model;
the train side servers are used for processing end server characteristic data based on the vehicle accident early warning algorithm model to obtain train abnormal event information and train accident occurrence probability, respectively transmitting the train abnormal event information and the train accident occurrence probability to the ground cloud server and the train control subsystem, receiving the abnormal early warning information and the train abnormal control instruction, transmitting the train abnormal control instruction to the corresponding train control subsystem and updating the carriage accident early warning algorithm model;
the train control subsystems are used for acquiring train abnormal event information, train accident probability and train abnormal control instructions, checking the train abnormal control instructions and controlling the train to stop at a reduced speed according to the checking result;
the ground cloud server is used for acquiring train abnormal event information and train accident occurrence probability obtained by each vehicle side server, respectively transmitting abnormal early warning information and train abnormal control instructions to each corresponding vehicle side server, and updating a vehicle accident early warning algorithm model;
the vehicle information table is used for displaying the corresponding relation between the train serial number and the train number;
the line information table is used for displaying the train line, the direction, the vehicle section and specific positioning information;
the abnormal code table is used for displaying train serial numbers, abnormal states and safety actions in a corresponding sequence.
2. The early warning method of the rail transit unstable network accident early warning system based on cloud edge cooperation as claimed in claim 1, is characterized by comprising the following steps:
s1, respectively updating algorithm models of a vehicle side server, a carriage end server and a carriage end controller to obtain updated vehicle accident early-warning algorithm models, carriage accident early-warning algorithm models and characteristic value filtering algorithm models;
s2, acquiring measurement data of to-be-detected parts of each train carriage during train operation, and obtaining end server characteristic data based on the updated vehicle accident early-warning algorithm model, each carriage accident early-warning algorithm model and each characteristic value filtering algorithm model;
s3, utilizing the characteristic data of the receiving end server of each vehicle side server, obtaining train abnormal event information and train accident occurrence probability based on a vehicle accident early warning algorithm model, and respectively transmitting the train abnormal event information and the train accident occurrence probability to a ground cloud server and a train control subsystem;
s4, acquiring abnormal early warning information and a train abnormal control instruction by utilizing the ground cloud server according to the train abnormal event information and the train accident occurrence probability, and transmitting the abnormal early warning information and the train abnormal control instruction to each corresponding vehicle side server;
and S5, acquiring train abnormal event information, train accident occurrence probability and train abnormal control instructions by utilizing each train control subsystem, carrying out safety verification on the train abnormal control instructions based on the train abnormal event information and the train accident occurrence probability to obtain a verification result, controlling the train to stop at a reduced speed according to the verification result, and completing early warning of the rail transit unstable network accident based on cloud-edge cooperation.
3. The method for early warning of the rail transit unstable network accident early warning system based on cloud edge cooperation according to claim 2, wherein the step S1 comprises the following steps:
s11, updating a vehicle accident early warning algorithm model by using a ground cloud server and transmitting the vehicle accident early warning algorithm model to a vehicle side server;
s12, based on the updated vehicle accident early-warning algorithm model, updating the corresponding carriage accident early-warning algorithm model by using the vehicle side server, and transmitting the carriage accident early-warning algorithm model to each carriage side server;
and S13, updating the corresponding characteristic value filtering algorithm model through a carriage end server based on the updated carriage accident early warning algorithm model, and transmitting the characteristic value filtering algorithm model to each carriage end controller.
4. The method for early warning of the rail transit unstable network accident early warning system based on cloud edge cooperation according to claim 3, wherein the step S2 comprises the following steps:
s21, acquiring measurement data of to-be-detected parts of each train carriage when the train runs by using a plurality of carriage end sensors;
s22, carrying out data cleaning and characteristic value filtering processing on the measured data by utilizing each carriage end controller according to the updated characteristic value filtering algorithm model to obtain a controller characteristic value;
and S23, performing edge calculation processing on the characteristic values of the controller by utilizing a carriage end server according to a carriage accident early warning algorithm model to obtain and store corresponding end server characteristic data.
5. The early warning method of the rail transit unstable network accident early warning system based on cloud edge coordination according to claim 4, wherein a TCP communication method of network early warning is adopted between the vehicle edge server and the ground cloud server.
6. The early warning method of the rail transit unstable network accident early warning system based on cloud edge cooperation according to claim 5, wherein the TCP communication method of the network early warning comprises the following steps:
a1, performing TCP three-way handshake between a vehicle side server and a ground cloud server;
a2, respectively defining a first TCP data format and a second TCP data format of transmission;
a3, transmitting a first TCP data packet comprising train abnormal event information and train accident occurrence probability to a ground cloud server based on a first TCP data format;
a4, analyzing the first TCP data packet by utilizing the ground cloud server according to the vehicle information table, the line information table and the anomaly code table to obtain train anomaly event information and train accident occurrence probability;
a5, based on the train abnormal event information and the train accident occurrence probability, obtaining abnormal early warning information and a train abnormal control instruction;
a6, transmitting a second TCP data packet comprising abnormality early warning information and a train abnormality control instruction to a train side server of other trains on the same line based on a second TCP data format;
and A7, analyzing the second TCP data packet by utilizing each vehicle side server according to the vehicle information table, the line information table and the anomaly code table to obtain anomaly early warning information and a train anomaly control instruction.
7. The method for early warning of the rail transit unstable network accident early warning system based on cloud edge cooperation according to claim 6, wherein the step A2 comprises the following steps:
a21, defining the length of the first TCP data and the second TCP data to be 1460 bytes;
a22, bytes 0 and 1 defining the first TCP data and the second TCP data each describe a vehicle number;
a23, defining the 2 nd byte, the 3 rd byte and the 4 th byte of the first TCP data and the second TCP data, and respectively describing the hour, the minute and the second correspondingly;
a24, defining the 5 th byte and the 6 th byte of the first TCP data and the second TCP data to describe a train line, wherein the 7 th byte describes a train trend, and the 8 th byte to the 10 th byte describe a train specific position;
a25, defining 11 th bytes to 100 th bytes of the first TCP data and the second TCP data to describe train abnormal event information;
a26, defining 101 th byte to 1660 th byte of the first TCP data to describe abnormal event analog quantity and corresponding train accident occurrence probability;
a27, defining 101 th byte to 1660 th byte of the second TCP data to describe abnormal event analog quantity and corresponding train abnormal control instruction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210800454.1A CN115009324B (en) | 2022-07-08 | 2022-07-08 | Rail transit unstable network accident early warning system and method based on cloud edge cooperation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210800454.1A CN115009324B (en) | 2022-07-08 | 2022-07-08 | Rail transit unstable network accident early warning system and method based on cloud edge cooperation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115009324A CN115009324A (en) | 2022-09-06 |
| CN115009324B true CN115009324B (en) | 2023-11-03 |
Family
ID=83078320
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210800454.1A Active CN115009324B (en) | 2022-07-08 | 2022-07-08 | Rail transit unstable network accident early warning system and method based on cloud edge cooperation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115009324B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019128479A1 (en) * | 2017-12-26 | 2019-07-04 | 中车大连机车车辆有限公司 | Wireless uploading and expert diagnosis system for medium-low speed magnetic levitation train based on trdp protocol |
| CN110239577A (en) * | 2019-07-25 | 2019-09-17 | 中南大学 | A kind of in-vehicle exposure environment Train occupant's health protection system and method |
| CN110312230A (en) * | 2019-07-08 | 2019-10-08 | 中国科学院计算机网络信息中心 | Communication means, device and the train system of train system |
| CN111547103A (en) * | 2020-05-26 | 2020-08-18 | 通号(北京)轨道工业集团有限公司轨道交通技术研究院 | Train derailment detection method and device and server |
| CN112347864A (en) * | 2020-10-21 | 2021-02-09 | 北京市地铁运营有限公司地铁运营技术研发中心 | Method, device, equipment and system for sensing and inducing rail transit passenger flow |
| WO2021159604A1 (en) * | 2020-02-12 | 2021-08-19 | 中车唐山机车车辆有限公司 | Monitoring system, monitoring method, and monitoring device for railway train |
-
2022
- 2022-07-08 CN CN202210800454.1A patent/CN115009324B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019128479A1 (en) * | 2017-12-26 | 2019-07-04 | 中车大连机车车辆有限公司 | Wireless uploading and expert diagnosis system for medium-low speed magnetic levitation train based on trdp protocol |
| CN110312230A (en) * | 2019-07-08 | 2019-10-08 | 中国科学院计算机网络信息中心 | Communication means, device and the train system of train system |
| CN110239577A (en) * | 2019-07-25 | 2019-09-17 | 中南大学 | A kind of in-vehicle exposure environment Train occupant's health protection system and method |
| WO2021159604A1 (en) * | 2020-02-12 | 2021-08-19 | 中车唐山机车车辆有限公司 | Monitoring system, monitoring method, and monitoring device for railway train |
| CN111547103A (en) * | 2020-05-26 | 2020-08-18 | 通号(北京)轨道工业集团有限公司轨道交通技术研究院 | Train derailment detection method and device and server |
| CN112347864A (en) * | 2020-10-21 | 2021-02-09 | 北京市地铁运营有限公司地铁运营技术研发中心 | Method, device, equipment and system for sensing and inducing rail transit passenger flow |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115009324A (en) | 2022-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111322143B (en) | Diagnosis method of diesel engine particle trap, cloud server and vehicle-mounted terminal | |
| CN108501983B (en) | Vehicle-mounted equipment running state monitoring system | |
| EP2765053B1 (en) | A rail train diagnostics system | |
| CN108230673B (en) | Vehicle driving route monitoring method, driver client and server | |
| CN109636946A (en) | A kind of calculation method for log of driving a vehicle | |
| CN115009324B (en) | Rail transit unstable network accident early warning system and method based on cloud edge cooperation | |
| CN111661113A (en) | Operation and maintenance method and system for rail transit vehicle | |
| CN106926699A (en) | The control display methods and its control system of Digital Automobile combination instrument | |
| CN114139949A (en) | Intelligent operation and maintenance system and method for rail transit based on edge calculation and machine learning | |
| CN113254569A (en) | Positioning deviation rectifying method and device | |
| CN112762877B (en) | Subway contact net rigid contact line abrasion early warning method and device | |
| CN107765617B (en) | Train axle temperature data processing method and device | |
| CN105988460B (en) | Vehicle runway dynamic testing method, device and system | |
| CN102156471A (en) | Method for remotely monitoring running mileage of hybrid vehicle | |
| CN117092953A (en) | Production data acquisition management and control system based on industrial Internet of things | |
| CN114527729A (en) | Vehicle health state remote monitoring system and method based on cloud platform | |
| CN111361608A (en) | Train online operation and maintenance method for subway signals | |
| CN116155720A (en) | CAN data acquisition remote configuration method in T-BOX | |
| CN105572493A (en) | Vehicle-mounted-ground auxiliary inverter remote fault diagnosis system | |
| CN113823013A (en) | Uninterrupted inspection system for power equipment based on digital twin technology | |
| CN111831658A (en) | Rail transit big data analysis method and system | |
| CN112710919A (en) | Mountain area power distribution network line fault cause diagnosis method | |
| CN116723482A (en) | Vehicle track backtracking display system based on 5G intelligent vehicle-mounted terminal | |
| CN214376004U (en) | Intelligent driving area controller | |
| CN117227769B (en) | Real-time dynamic control method for temporary speed limit disclosure |
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 |