CN108674453A - A kind of rail traffic monitoring system and control method based on AI technologies - Google Patents
A kind of rail traffic monitoring system and control method based on AI technologies Download PDFInfo
- Publication number
- CN108674453A CN108674453A CN201810500152.6A CN201810500152A CN108674453A CN 108674453 A CN108674453 A CN 108674453A CN 201810500152 A CN201810500152 A CN 201810500152A CN 108674453 A CN108674453 A CN 108674453A
- Authority
- CN
- China
- Prior art keywords
- data
- rail traffic
- prediction end
- collection terminal
- technologies
- 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
Classifications
-
- 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
- B61L27/70—Details of trackside communication
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
Abstract
The present invention provides a kind of rail traffic monitoring system and control method based on AI technologies, including pass through the sequentially connected monitoring management platform of network, data collection terminal and data prediction end;The collected fault data of data collection terminal is transmitted through the network to data prediction end, and AI identifications are carried out after the pretreatment at data prediction end, then through network transmission to monitoring management platform.After the present invention collects fault message by data collection terminal, it is pre-processed based on network transmission to the data prediction end being connect with data collection terminal, again AI identifications are carried out through network transmission to the monitoring management platform, to the quick analyzing processing process for realizing acquisition, positioning, find failure, fault zone is rapidly found out by the location information of image, substantially increase the image analysis efficiency in trouble hunting work, accelerate data analyzing speed, the repair time is shortened, ensure that the safe operation of rail traffic vehicles to a certain extent.
Description
Technical field
The invention belongs to technical field of rail traffic, specifically, being a kind of rail traffic monitoring system based on AI technologies
System and control method.
Background technology
Rail traffic refers to that vehicle in use needs a kind of vehicles travelled in certain tracks or transportation system.Most allusion quotation
The rail traffic of type is exactly the railway system being made of traditional train and standard railroad.It is polynary with train and railway technology
Change development, rail traffic shows more and more types, the land transport of long range is not only dispersed throughout, in being also widely used in
In short-range urban public transport.
Common rail traffic failure includes vehicle trouble and orbital facilities failure, for common rail traffic faults into
When row maintenance, it includes manually that vehicle and orbital facilities carry out system to all environment of track by naked eyes to be required to technical staff
It investigates one by one, subjective factor is larger, and the time, long efficiency was low, and the work for the trouble hunting investigation of service personnel brings inconvenience,
Easily there is missing inspection or row the case where can not check in artificial inspection, for rail traffic vehicles safe operation bring it is huge
Security risk.
Invention content
In view of this, the present invention provides a kind of rail traffic monitoring system and control method based on AI technologies, it is intended in
Solve the defects of existing monitoring technology.
To solve the above problems, the present invention provides a kind of rail traffic monitoring system based on AI technologies, including:
Pass through the sequentially connected monitoring management platform of network, data collection terminal and data prediction end;
The collected fault data of data collection terminal is transmitted to the data prediction end, locates in advance by the data
After the pretreatment for managing end, then through network transmission to monitoring management platform progress AI identifications.
Preferably,
The data collection terminal includes terminal hand-held housing, is set to the mobile Universal arm on terminal hand-held housing top,
And the image acquisition units being connect with the terminal hand-held housing by the mobile Universal arm.
Preferably,
The data collection terminal further includes the lighting device being connect with described image collecting unit.
Preferably,
The data collection terminal further includes first processor, first network transmitting device and voice collection device;
The processor is connect with the voice collection device;
The voice collection device is set on the outside of the terminal hand-held housing;
The processor and the first network transmitting device, described image collecting unit, the voice collection device are equal
Connection;
The data collection terminal is connect by the first network transmitting device with the data prediction end.
Preferably,
The data prediction end includes second processor, the second network transmission device, storage device;
The second processor is connect with second network transmission device and the storage device is all connected with.
Preferably,
The data prediction end further includes display device, and the display device is connected to the processor, for showing
The image data that the data collection terminal returns.
Preferably,
The data prediction end further includes location data processing unit, the location data processing unit and the processing
Device connects.
Preferably,
The monitoring management platform includes third processor, and the third network being connect with the third processor passes
Defeated device, data storage device, AI neural network servers;
After data are received by the third network transmission device after the pretreatment that the data prediction end returns, storage
It is identified in the data storage device, and by the AI neural network servers.
Preferably,
The monitoring management platform further includes the service personnel's positioning device being connect with the third processor, for passing through
The location data processing unit at the data prediction end and the recognition result of the AI neural network servers determine
The location information of the service personnel.
In addition, to solve the above problems, the present invention also provides a kind of rail traffic control method based on AI technologies, wrap
It includes:
The data to be identified of data collection terminal acquisition trajectory traffic, and data prediction end is transmitted through the network into line number
It is pre-processed according to splitting, obtains preprocessed data;
The preprocessed data is sent to monitoring management platform by the data prediction end, is patted by the monitoring pipe
Platform is carried out to the preprocessed data based on AI technology identifying processings, and generates recognition result, in order to according to the identification
As a result rail traffic failure is found out;
The monitoring management platform analyzes the recognition result, and the recognition result is converted to operational order;
The monitoring management platform returns to the operational order to the data collection terminal.
The present invention provides a kind of rail traffic monitoring system and control method based on AI technologies.Wherein, the present invention is carried
The monitoring system of confession includes:Pass through the sequentially connected monitoring management platform of network, data collection terminal and data prediction end;It is described
The collected fault data of data collection terminal is transmitted through the network to the data prediction end, by the data prediction end
Pretreatment after, then through network transmission to the monitoring management platform carry out AI identifications.The present invention is acquired by data collection terminal
To after fault message, pre-processed based on network transmission to the data prediction end being connect with data collection terminal, then through network
It is transmitted to the monitoring management platform and carries out AI identifications, to the quick analyzing processing for realizing acquisition, positioning, find failure
Journey rapidly finds out fault zone by the location information of image, substantially increase the image analysis effect in trouble hunting work
Rate accelerates data analyzing speed, shortens the repair time, ensure that the safety fortune of rail traffic vehicles to a certain extent
Row.
Description of the drawings
It should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore it is not construed as to model
The restriction enclosed for those of ordinary skill in the art without creative efforts, can also be according to these
Attached drawing obtains other relevant attached drawings.
Fig. 1 is the integrated connection schematic diagram the present invention is based on the rail traffic monitoring system of AI technologies;
Fig. 2 is the connection diagram of the data collection terminal the present invention is based on the rail traffic monitoring system of AI technologies;
Fig. 3 is the connection diagram at the data prediction end the present invention is based on the rail traffic monitoring system of AI technologies;
Fig. 4 is the connection diagram of the monitoring management platform the present invention is based on the rail traffic monitoring system of AI technologies;
Fig. 5 is the overall network connection diagram the present invention is based on the rail traffic monitoring system of AI technologies.
Reference numeral:
Title | Number | Title | Number |
Rail traffic monitoring system based on AI technologies | 1 | Lighting device | 124 |
Monitoring management platform | 11 | First processor | 125 |
Third processor | 111 | First network transmitting device | 126 |
Third network transmission device | 112 | Voice collection device | 127 |
Data storage device | 113 | Data prediction end | 13 |
AI neural network servers | 114 | Second processor | 131 |
Service personnel's positioning device | 115 | Second network transmission device | 132 |
Data collection terminal | 12 | Storage device | 133 |
Terminal hand-held housing | 121 | Display device | 134 |
Mobile Universal arm | 122 | Location data processing unit | 135 |
Image acquisition units | 123 |
Hereinafter, the various embodiments of the disclosure will be described more fully in conjunction with attached drawing.The disclosure can have various realities
Example is applied, and can adjust and change wherein.Therefore, it will in more detail be retouched with reference to the specific embodiment being shown in the accompanying drawings
State the disclosure.It should be understood, however, that:There is no the meanings that the various embodiments of the disclosure are limited to specific embodiment disclosed herein
Figure, but the disclosure should be interpreted as covering all adjustment in the spirit and scope for the various embodiments for falling into the disclosure, etc.
Jljl and/or alternative.Description taken together with the accompanying drawings, the same element of same reference numerals.
Hereinafter, disclosed in the term " comprising " that can be used in the various embodiments of the disclosure or " may include " instruction
Function, operation or the presence of element, and do not limit the increase of one or more functions, operation or element.
In the various embodiments of the disclosure, it includes listing file names with to state "or" or " at least one of A or/and B "
Any combinations of word or all combinations.For example, statement " A or B " or " at least one of A or/and B " may include A, may include
B may include A and B both.
The statement (" first ", " second " etc.) used in the various embodiments of the disclosure can be modified in various implementations
Various constituent element in example, but respective sets can not be limited into element.For example, presented above be not intended to limit the suitable of the element
Sequence and/or importance.The purpose presented above for being only used for differentiating an element and other elements.For example, the first user fills
It sets and indicates different user device with second user device, although the two is all user apparatus.For example, not departing from each of the disclosure
In the case of the range of kind embodiment, first element is referred to alternatively as second element, and similarly, second element is also referred to as first
Element.
It should be noted that:It, can be by the first composition member if a constituent element ' attach ' to another constituent element by description
Part is directly connected to the second constituent element, and " connection " third can be formed between the first constituent element and the second constituent element
Element.On the contrary, when a constituent element " being directly connected to " is arrived another constituent element, it will be appreciated that in the first constituent element
And second third constituent element is not present between constituent element.
The term used in the various embodiments of the disclosure is used only for the purpose of describing specific embodiments and not anticipates
In the various embodiments of the limitation disclosure.As used herein, singulative is intended to also include plural form, unless context is clear
Chu it is indicated otherwise.Unless otherwise defined, otherwise all terms (including technical terms and scientific terms) used herein have
There is meaning identical with the various normally understood meanings of embodiment one skilled in the art of the disclosure.The term
(term such as limited in the dictionary generally used) is to be interpreted as having and situational meaning in the related technical field
Identical meaning and the meaning that Utopian meaning or too formal will be interpreted as having, unless in the various of the disclosure
It is clearly defined in embodiment.
The present invention provides a kind of rail traffic monitoring system 1 based on AI technologies, including:
Pass through the sequentially connected monitoring management platform 11 of network, data collection terminal 12 and data prediction end 13;
12 collected fault data of the data collection terminal is transmitted to the data prediction end 13, by the data
After the pretreatment for pre-processing end 13, then through network transmission to the monitoring management platform 11 progress AI identifications.
Above-mentioned, fault data is fault zone image or other data informations of fault zone, can be rail traffic
Region to be detected or partial image can be the image of equipment placement area, or the inside of Transit Equipment
It is arranged, the image of spare and accessory parts installation connection etc., for example, the image of portal region security facility display case, shipping headstock behaviour
Make the control area operation image of platform, train video communication video line connects image etc..In addition, fault data may be
Other fault messages, for example, fault zone gas station, infrared distance measurement data, fault zone sound detection data etc..
Terminal device above-mentioned, that the data collection terminal 12 and the data prediction end 13 are held by service personnel,
Can be the mobile terminal device held, or portable mobile computing moves to be hand-held in the present embodiment
Dynamic terminal.Fault data is obtained by data collection terminal 12 and data prediction end 13 and is pre-processed, and terminal can be passed through
The filming apparatus of equipment is obtained, for example, the camera by handheld terminal obtains the fault zone image.
Above-mentioned, monitoring management platform 11 is server-side, and as administrative staff are managed service personnel and assistance is assigned
The platform of the monitoring management of instruction.Data collection terminal 12 that service personnel is held and data prediction end 13 can be acquired
Data received, and carried out to 12 sum number of data collection terminal based on monitoring management platform 11 by GPS signal, image recognition
Data preprocess end 13 is positioned, and the information in the fault data acquired to service personnel carries out AI identifications, judges to be checked
Equipment, facility, placement position, direction, the defect of setting, failure, problem etc. are repaiied,
It is above-mentioned, data prediction end 13 to fault data pretreatment can be data collection terminal 12 in fault data
Image (fault zone image) is acquired, and is carried out after tentatively identifying by data prediction end 13, to the fault zone
Image is split and is screened, and recognizable object therein is identified, and can recognize that object to obtain each
Corresponding subregion.Subregion can be the picture of multiple irregular shapes included in the image of fault zone, as, one
A fault zone image, by the picture for being split as the corresponding irregular shape of multiple recognizable objects.For example, a track is handed over
Logical fault zone image photograph is split as the image sectional drawing of train, image sectional drawing, the signal lamp of track by being identified
Image sectional drawing and platform safety devices image sectional drawing, the image in other regions then abandon should not, only retain above-mentioned image and cut
Figure.
Above-mentioned, data prediction end 13 carries out subregion to generate subregion data packet, wherein can be built according to recognition result
Vertical label corresponding with per sub-regions, such as train label can be established in the image sectional drawing of train, it is stored in subregion data packet
In, then every sub-regions data packet in the fault zone picture is transmitted to background server, in order to background server pair
Every sub-regions data packet is identified and malfunction elimination.
After the present invention collects fault message by data collection terminal 12, connected to data collection terminal 12 based on network transmission
The data prediction end 13 connect is pre-processed, then carries out AI identifications through network transmission to the monitoring management platform 11, to
The quick analyzing processing process for realizing acquisition, positioning, find failure, i.e., rapidly find out faulty section by the location information of image
Domain substantially increases the image analysis efficiency in trouble hunting work, accelerates data analyzing speed, shorten the repair time,
It ensure that the safe operation of rail traffic vehicles to a certain extent.
In addition, after collecting fault message by data collection terminal 12, connected to data collection terminal 12 based on network transmission
The data prediction end 13 connect is pre-processed, and AI identifications are carried out, and fault zone image is divided into multiple and different recognizable pairs
As corresponding subregion, and then the subregion data packet that the subregion generates is transmitted to background server again, in order to rear
Platform server-side carries out malfunction elimination according to the subregion in each sub-regions data packet, realizes the automatic of fault zone image
Arrangement and transmission process are split, the efficiency of transmission in trouble hunting work is substantially increased, accelerates data transmission bauds, shorten
Repair time avoids data packet excessive excessive the case where leading to network congestion data delay, ensure that a certain extent
The safe operation of rail traffic vehicles.
Preferably,
The data collection terminal 12 includes terminal hand-held housing 121, is set to the movement on 121 top of terminal hand-held housing
Universal arm 122, and the image acquisition units that are connect with the terminal hand-held housing 121 by the mobile Universal arm 122
123。
It is above-mentioned, it should be noted that mobile Universal arm 122 is holder or the extension that can carry out multiple directions extension and movement
Arm by flexible, and extends and changes direction for example, can be the Universal arm of telescopic two section, make image acquisition units
123 carry out image acquisition in different environments.In the present embodiment, due to service personnel to multiple and different environment into line number
When according to acquisition, component environment such as train driving device region, transmission device region, the subregions such as train body bottom, inspection
The personnel of repairing can not pierce in it and overhaul, and in existing repair method, flashlight progress can only be held by service personnel
It is far to observe under lighting condition, investigate failure problems.In the present embodiment, service personnel by hand-held data gathering end 12, and
Direction by mobile 122 change data collecting unit of Universal arm and length, can not touch some service personnel, can not
The region of entrance carries out data acquisition, image taking, is service personnel's to expand the scope of repair of service personnel significantly
Service work provides a convenient, and further reduces the security risk in rail traffic.
In addition, the mobile Universal arm 122 that the present embodiment is provided, can also be connected with and automatically move operating device, it is described
The motor that operating device includes the terminal hand-held housing 121 set on the data collection terminal 12 is automatically moved, the data are set to
The operation button of 12 terminal hand-held housing 121 of collection terminal, operates operation button by service personnel, to motor
Start and stop are controlled, and then are controlled the moving direction and development length of mobile Universal arm 122, realize mobile Universal arm
122 are automatically brought into operation.For example, it can be equipped with motor, or there are one motors for setting at each linear joint, it is universal to movement
Arm 122 is controlled.
Above-mentioned, terminal hand-held housing 121 is held in service personnel and includes that data collection terminal 12 is all for convenience
The shell of component plays the role of supporting, facilitates grip, can be the shapes such as pistol dress or cylinder, and data acquisition unit is logical
It crosses and moves Universal arm 122 and connect with terminal hand-held housing 121.
Above-mentioned, data acquisition unit can be the image collecting devices such as camera, camera.
Preferably,
The data collection terminal 12 further includes the lighting device 124 being connect with described image collecting unit 123.
Above-mentioned, lighting device 124 is LED light in the present embodiment, when for the progress data acquisition of data collection terminal 12
Illuminating effect.
In addition, lighting device 124 can be set at data acquisition unit, can be worked together with data acquisition unit,
When data acquisition unit starts data acquisition, you can carry out opening lighting device 124, to realize photograph when acquiring data
It is bright.
Preferably,
The data collection terminal 12 further includes first processor 125, first network transmitting device 126 and voice collection device
127;
The processor is connect with the voice collection device 127;
The voice collection device 127 is set to 121 outside of the terminal hand-held housing;
The processor and the first network transmitting device 126, described image collecting unit 123, the sound collection
Device 127 is all connected with;
The data collection terminal 12 is connect by the first network transmitting device 126 with the data prediction end 13.
Above-mentioned, data collection terminal 12 further includes processor, first network transmitting device 126, voice collection device 127;
Above-mentioned, first network transmitting device 126 can be network data ports, such as can be that wifi is wirelessly connected end
Mouthful, can be wirelessly connected, or wan mouthful, to connect network data line, in addition it is also possible to be miniusb,
Microusb etc. data port, to be attached with data prediction end 13 and data interaction.
Above-mentioned, voice collection device 127 can be sound transducer;It should be noted that the effect phase of sound transducer
When in a microphone (microphone).It is used for receiving sound wave, shows the vibrational diagram of sound, but cannot be carried out to the intensity of noise
It measures.A condenser type Electret condenser microphone to sound sensitive built in the sensor.Sound wave makes the electret film in microphone shake
It is dynamic, lead to the variation of capacitance, and generate the small voltage for variation of being corresponding to it.This voltage is subsequently converted into the electricity of 0-5V
Pressure is converted by A/D and is received by data collector, and sends computer to.
Include the circuit maintenance and overhaul of the equipments for train carriage, wherein need in the trouble hunting of rail traffic
The operating condition of the car body driving device such as engine of train is overhauled, maintenance process includes for engine operation sound
The judgement of sound in existing repair method, needs the experience all the year round by service personnel to go to listen to judge that engine is run
Whether situation or pipeline are unobstructed;In the present embodiment, by using voice collection device 127, to train body operating condition
Sound is obtained, and can further be preserved or identified by data prediction end 13, or pass through the data prediction
End 13 is transmitted to monitoring management platform 11 and carries out the preservation to sound and identification, to find out potential faults, carries out malfunction elimination,
Positioning failure reason.
Preferably,
The data prediction end 13 includes second processor 131, the second network transmission device 132, storage device 133;
The second processor 131 is connect with second network transmission device 132 and the storage device 133 connects
It connects.
Above-mentioned, storage device 133 can be the storage devices 133 such as hard disk, datarams card.
It is above-mentioned, data prediction end 13 can also include for electric installation, such as lithium battery to pretreatment end all parts into
Row power supply.
Above-mentioned, the second network transmission device 132 can be network data ports, such as can be that wifi is wirelessly connected end
Mouthful, can be wirelessly connected, or wan mouthful, to connect network data line, in addition it is also possible to be miniusb,
Microusb etc. data port, to data collection terminal 12, monitoring management platform 11 is attached and data interaction.
Preferably,
The data prediction end 13 further includes display device 134, and the display device 134 is connected to the processor,
The image data returned for showing the data collection terminal 12.
Above-mentioned, display device 134 can be liquid crystal display, in addition, for convenience in the operation of service personnel, Ke Yiwei
Capacitance touch screen, resistance touch screen, to realize touch control operation.
In addition, data prediction end 13 can also include fingerprint identification device, to carry out identification to service personnel
And preservation establishes the data connection with monitoring management platform 11, to improve data after to the identity validation of service personnel
Safety.
In addition, data prediction end 13 may include the data encryption device being connect with processor, it is used for and monitoring management
Encrypted data interaction between platform 11, can be further encrypted by data encryption device.For example, can be based on non-
The data encryption device of symmetric cryptosystem.
Wherein, can be to be based on data encryption device as the asymmetric data encryption between terminal and server-side, it is described
Terminal device provides RSA public keys to background server request;Wherein, the background server is according to requesting to generate
RSA public keys and RSA private keys, and the RSA public keys are sent to the terminal device;The terminal device receives the server-side
The RSA public keys issued;The terminal device is encrypted the subregion data packet using the RSA public keys, obtains with institute
The subregion data packet for stating RSA public key encryptions, in order to which the terminal device is by the sub-district of the RSA public key encryptions
Numeric field data packet is sent to the background server and decrypts.The background server receives the son of the RSA public key encryptions
Area data packet;The background server is decrypted the subregion data packet using RSA private keys, obtains the subregion
The difference in the fault zone image in data packet can recognize that object.
Preferably,
The data prediction end 13 further includes location data processing unit 135, the location data processing unit 135 with
The processor connection.
Preferably,
The monitoring management platform 11 includes third processor 111, and the connect with the third processor 111
Three network transmission devices 112, data storage device 113, AI neural network servers 114;
Data are received by the third network transmission device 112 after the pretreatment that the data prediction end 13 returns
Afterwards, it is stored in the data storage device 113, and is identified by the AI neural network servers 114.
It is above-mentioned, location data processing unit 135, for obtaining the current location information acquired in data collection terminal 12, and
Carry out storage generate current location data or device itself include GPS chip or by the localization method of base station to obtain
The location data got.
It is above-mentioned, it is to be understood that artificial intelligence (Artificial Intelligence), english abbreviation AI.It is
Theory, a new technology of method, technology and application system for the intelligence of research, exploitation for simulating, extending and extending people
Science.Artificial intelligence is a branch of computer science, it attempts to understand essence of intelligence, and produce it is a kind of it is new can be with
The research of the intelligence machine that the similar mode of human intelligence is made a response, the field includes robot, language identification, image knowledge
Not, natural language processing and expert system etc..Artificial intelligence is since the birth, and theory and technology is increasingly mature, application field
Constantly expand, it is contemplated that the sci-tech product that the following artificial intelligence is brought, it will be the wisdom of humanity " container ".Artificial intelligence
It can be to the simulation of the information process of the consciousness of people, thinking.Artificial intelligence is not the intelligence of people, but can think deeply as people,
It can exceed that the intelligence of people.
Above-mentioned, recognizable object can be the image in preset recognizable region, pass through the failure acquired in terminal device
The identification of area image, and then fault zone image is matched with the image in recognizable region.It wherein, can when being matched
Multiple and different recognizable regions to be identified, by judging matched likelihood, to judge the fault zone image
In with the presence or absence of recognizable region, and then obtain the location information in multiple and different recognizable regions in the image of fault zone.
Preferably,
The monitoring management platform 11 further includes the service personnel's positioning device 115 being connect with the third processor 111,
For by the data prediction end 13 the location data processing unit 135 and the AI neural network servers
114 recognition result determines the location information of the service personnel.
It is above-mentioned, the current location information of staff that data prediction end is passed back, and pass through AI neural network servers
Location information in the image identified by above two location information to the positioning in service personnel, pass through
The grasp staff position of administrative staff's first time can more accurately be found out or be made to positioning to service personnel.
In addition, the location information that the staff that passes back of data prediction end is current, and identified by AI neural network servers
Different weights can be arranged in both location informations in image out, accurate to improve by the algorithm of the synthesis of weight
Rate, for example, the current location information of the staff that passes back of data prediction end is since there are precision for GPS or other positioning methods
The problems such as error, shared weight can be 0.3, and the positioning in the image identified by AI neural network servers is believed
The shared weight of breath is 0.7.
In addition, to solve the above problems, the present invention also provides a kind of rail traffic control method based on AI technologies, wrap
It includes:
The data to be identified of 12 acquisition trajectory traffic of data collection terminal, and be transmitted through the network to data prediction end 13 into
Row data split pretreatment, obtain preprocessed data;
The preprocessed data is sent to monitoring management platform 11 by the data prediction end 13, passes through the monitoring pipe
Platform 11 is carried out to the preprocessed data based on AI technology identifying processings, and generates recognition result, in order to according to institute
It states recognition result and finds out rail traffic failure;
The monitoring management platform 11 analyzes the recognition result, and the recognition result, which is converted to operation, to be referred to
It enables;
The monitoring management platform 11 returns to the operational order to the data collection terminal 12.
It is above-mentioned, by data collection terminal 12 to the fault message (fault picture data, failure voice data) of rail traffic
It is acquired, and is pre-processed by data prediction end 13, including storage, fractionation, packing and integration, pre-processed
Data, and it is sent to monitoring management platform 11, it is carried out to the preprocessed data based on AI skills by monitoring management platform 11
Art identifying processing, and recognition result is generated, in order to find out rail traffic failure according to the recognition result;Wherein, including it is logical
It crosses to positioning of the fault picture data to service personnel and fault zone, the positioning by GPS information to service personnel.Monitoring pipe
Platform 11 analyzes the recognition result, and recognition result is converted to operational order;Monitoring management platform 11 is to described
Data collection terminal 12 returns to the operational order.
Above-mentioned, operational order is the action order for service personnel, for example, being adopted to data by monitoring management platform 11
Collect end 12 and send vibration signal, and send text information and voice messaging, to prompt service personnel to place under repair fault zone.
It should be appreciated that although this specification is described in terms of embodiments, but not each embodiment only includes one
A independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should will say
As a whole, the technical solution in each embodiment may also be suitably combined to form those skilled in the art can for bright book
With the other embodiment of understanding.
Inventor states that the present invention can only for of the invention by the series of detailed descriptions listed above
Row embodiment illustrates, but the invention is not limited in above-mentioned detailed process equipment and technological processes.And i.e. not
Mean that the present invention should rely on above-mentioned detailed process equipment and technological process and could implement.Person of ordinary skill in the field answers
This is illustrated, any improvement in the present invention, and the equivalence replacement and auxiliary element to each raw material of product of the present invention add, are specific square
The selection etc. of formula, all falls within protection scope of the present invention and the open scope.
Claims (10)
1. a kind of rail traffic monitoring system based on AI technologies, which is characterized in that including:
Pass through the sequentially connected monitoring management platform of network, data collection terminal and data prediction end;
The collected fault data of data collection terminal is transmitted to the data prediction end, by the data prediction end
Pretreatment after, then through network transmission to the monitoring management platform carry out AI identifications.
2. the rail traffic monitoring system as described in claim 1 based on AI technologies, which is characterized in that the data collection terminal packet
Include terminal hand-held housing, be set to terminal hand-held housing top mobile Universal arm, and by the mobile Universal arm with
The image acquisition units of the terminal hand-held housing connection.
3. the rail traffic monitoring system as claimed in claim 2 based on AI technologies, which is characterized in that the data collection terminal is also
It include the lighting device being connect with described image collecting unit.
4. the rail traffic monitoring system as claimed in claim 3 based on AI technologies, which is characterized in that the data collection terminal is also
Including first processor, first network transmitting device and voice collection device;
The processor is connect with the voice collection device;
The voice collection device is set on the outside of the terminal hand-held housing;
The processor is all connected with the first network transmitting device, described image collecting unit, the voice collection device;
The data collection terminal is connect by the first network transmitting device with the data prediction end.
5. the rail traffic monitoring system as claimed in claim 4 based on AI technologies, which is characterized in that
The data prediction end includes second processor, the second network transmission device, storage device;
The second processor is connect with second network transmission device and the storage device is all connected with.
6. the rail traffic monitoring system as claimed in claim 5 based on AI technologies, which is characterized in that the data prediction end
Further include display device, the display device is connected to the processor, the image returned for showing the data collection terminal
Data.
7. the rail traffic monitoring system as claimed in claim 6 based on AI technologies, which is characterized in that the data prediction end
Further include location data processing unit, the location data processing unit is connected to the processor.
8. the rail traffic monitoring system as claimed in claim 7 based on AI technologies, which is characterized in that the monitoring management platform
Including third processor, and the third network transmission device, data storage device, the AI that are connect with the third processor refreshing
Through network server;
After data are received by the third network transmission device after the pretreatment that the data prediction end returns, it is stored in institute
Data storage device is stated, and is identified by the AI neural network servers.
9. the rail traffic monitoring system as claimed in claim 8 based on AI technologies, which is characterized in that the monitoring management platform
Further include the service personnel's positioning device being connect with the third processor, for passing through the described fixed of the data prediction end
Position data processing equipment and the recognition result of the AI neural network servers determine the location information of the service personnel.
10. a kind of rail traffic control method based on AI technologies, which is characterized in that including:
The data to be identified of data collection terminal acquisition trajectory traffic, and be transmitted through the network to data prediction end progress data and tear open
Divide pretreatment, obtains preprocessed data;
The preprocessed data is sent to monitoring management platform by the data prediction end, by the monitoring management platform into
It goes to the preprocessed data based on AI technology identifying processings, and generates recognition result, in order to according to the recognition result
Find out rail traffic failure;
The monitoring management platform analyzes the recognition result, and the recognition result is converted to operational order;
The monitoring management platform returns to the operational order to the data collection terminal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810500152.6A CN108674453A (en) | 2018-05-23 | 2018-05-23 | A kind of rail traffic monitoring system and control method based on AI technologies |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810500152.6A CN108674453A (en) | 2018-05-23 | 2018-05-23 | A kind of rail traffic monitoring system and control method based on AI technologies |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108674453A true CN108674453A (en) | 2018-10-19 |
Family
ID=63807999
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810500152.6A Pending CN108674453A (en) | 2018-05-23 | 2018-05-23 | A kind of rail traffic monitoring system and control method based on AI technologies |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108674453A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110430395A (en) * | 2019-07-19 | 2019-11-08 | 苏州维众数据技术有限公司 | Video data AI processing system and processing method |
CN110533016A (en) * | 2019-09-03 | 2019-12-03 | 深圳市海洋王照明工程有限公司 | Movable lighting system |
CN113884842A (en) * | 2021-11-15 | 2022-01-04 | 国网湖南省电力有限公司 | Partial discharge monitoring system suitable for ring net cage |
CN114987582A (en) * | 2022-06-24 | 2022-09-02 | 株洲嘉成科技发展股份有限公司 | Distributed network control system of rail engineering vehicle |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102085873A (en) * | 2011-01-04 | 2011-06-08 | 北京清网华科技有限公司 | System and method for remote diagnosis of faults of train on passage |
CN202144257U (en) * | 2011-06-07 | 2012-02-15 | 北京清网华科技有限公司 | Passenger train inspection operation management and midway vehicle malfunction remote diagnosis system |
CN103745229A (en) * | 2013-12-31 | 2014-04-23 | 北京泰乐德信息技术有限公司 | Method and system of fault diagnosis of rail transit based on SVM (Support Vector Machine) |
CN104427218A (en) * | 2013-09-02 | 2015-03-18 | 北京计算机技术及应用研究所 | Ultra high definition CCD (charge coupled device) multichannel acquisition and real-time transmission system and method |
CN105991153A (en) * | 2016-06-02 | 2016-10-05 | 上海控创信息技术股份有限公司 | Rail transit maintenance management integrated intelligent terminal based on safe operation |
CN106709511A (en) * | 2016-12-08 | 2017-05-24 | 华中师范大学 | Urban rail transit panoramic monitoring video fault detection method based on depth learning |
CN107274404A (en) * | 2017-07-25 | 2017-10-20 | 青岛大学附属医院 | A kind of pathological analysis system and method based on image |
CN107392197A (en) * | 2017-07-27 | 2017-11-24 | 武汉汉云亚信科技有限公司 | A kind of locomotive identification identification and locomotive component fault detection method and system |
-
2018
- 2018-05-23 CN CN201810500152.6A patent/CN108674453A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102085873A (en) * | 2011-01-04 | 2011-06-08 | 北京清网华科技有限公司 | System and method for remote diagnosis of faults of train on passage |
CN202144257U (en) * | 2011-06-07 | 2012-02-15 | 北京清网华科技有限公司 | Passenger train inspection operation management and midway vehicle malfunction remote diagnosis system |
CN104427218A (en) * | 2013-09-02 | 2015-03-18 | 北京计算机技术及应用研究所 | Ultra high definition CCD (charge coupled device) multichannel acquisition and real-time transmission system and method |
CN103745229A (en) * | 2013-12-31 | 2014-04-23 | 北京泰乐德信息技术有限公司 | Method and system of fault diagnosis of rail transit based on SVM (Support Vector Machine) |
CN105991153A (en) * | 2016-06-02 | 2016-10-05 | 上海控创信息技术股份有限公司 | Rail transit maintenance management integrated intelligent terminal based on safe operation |
CN106709511A (en) * | 2016-12-08 | 2017-05-24 | 华中师范大学 | Urban rail transit panoramic monitoring video fault detection method based on depth learning |
CN107274404A (en) * | 2017-07-25 | 2017-10-20 | 青岛大学附属医院 | A kind of pathological analysis system and method based on image |
CN107392197A (en) * | 2017-07-27 | 2017-11-24 | 武汉汉云亚信科技有限公司 | A kind of locomotive identification identification and locomotive component fault detection method and system |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110430395A (en) * | 2019-07-19 | 2019-11-08 | 苏州维众数据技术有限公司 | Video data AI processing system and processing method |
CN110533016A (en) * | 2019-09-03 | 2019-12-03 | 深圳市海洋王照明工程有限公司 | Movable lighting system |
CN110533016B (en) * | 2019-09-03 | 2022-07-26 | 深圳市海洋王铁路照明技术有限公司 | Mobile lighting system |
CN113884842A (en) * | 2021-11-15 | 2022-01-04 | 国网湖南省电力有限公司 | Partial discharge monitoring system suitable for ring net cage |
CN114987582A (en) * | 2022-06-24 | 2022-09-02 | 株洲嘉成科技发展股份有限公司 | Distributed network control system of rail engineering vehicle |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108674453A (en) | A kind of rail traffic monitoring system and control method based on AI technologies | |
CN205721347U (en) | Vehicle breakdown diagnostic system | |
CN106228497A (en) | A kind of multi-operation mode emergency commading system and method for work thereof | |
CN108769191A (en) | A kind of wisdom building site management monitoring system and its implementation based on Internet of Things | |
CN107566327A (en) | One kind is intelligent vehicle-carried to drive training monitoring system | |
CN108765398B (en) | Rail transit monitoring management platform | |
US9224296B1 (en) | School child tracking system | |
CN110390372B (en) | Circuit inspection method and system based on dynamic random two-dimensional code and holographic projection technology | |
CN110930804A (en) | Clinical medicine education system based on cloud platform | |
CN104966140B (en) | The mobile engineer station of power grid work compound | |
CN108932581A (en) | The autonomous cognitive method and system of more physics domain information fusions | |
CN113344351A (en) | Internet of things sensing and emergency disposal system for smart park | |
CN108960547A (en) | Emergency preplan aided management system | |
CN103576691B (en) | 3G police service unmanned plane managing and control system | |
CN107621522A (en) | A kind of Around ambient air quality monitoring system based on unmanned plane | |
CN116128390B (en) | Medical consumable cold chain transportation monitoring method based on Internet of things | |
KR20190036425A (en) | System and Method for Handling Baggage Using Patrol Tray | |
KR101610886B1 (en) | Method for Diagnosing Personal Health State Based on Big Data and System for the Same | |
Tsunashima et al. | Condition monitoring of railway tracks using compact size on-board monitoring device | |
CN109145285A (en) | Phrase extraction text analyzing method and system | |
CN106570801A (en) | Electronic driving trainer central control system for driving training | |
RU2652338C1 (en) | System for monitoring and control of railway status | |
CN105974904A (en) | Subway vehicle safety protection system and method thereof | |
CN108022442A (en) | A kind of vehicle monitoring system and its application method based on cloud pipe end | |
CN108389282A (en) | A kind of vehicle mounted failure self diagnosis early warning cloud system |
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 |
Application publication date: 20181019 |
|
RJ01 | Rejection of invention patent application after publication |