CN107585181A - A kind of train positioning system based on deep learning - Google Patents
A kind of train positioning system based on deep learning Download PDFInfo
- Publication number
- CN107585181A CN107585181A CN201710685925.8A CN201710685925A CN107585181A CN 107585181 A CN107585181 A CN 107585181A CN 201710685925 A CN201710685925 A CN 201710685925A CN 107585181 A CN107585181 A CN 107585181A
- Authority
- CN
- China
- Prior art keywords
- module
- train
- deep learning
- main control
- control module
- 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
Landscapes
- Train Traffic Observation, Control, And Security (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention provides a kind of train positioning system based on deep learning, the system includes：Signal acquisition module, data memory module and interactive module, described signal acquisition module, data memory module and interactive module connect main control module respectively, and the main control module connects power module；The interactive module is used for configuration of the peripheral hardware to the system.The signal intensity that the signal acquisition module receives is input to the main control module and carries out deep learning model calculating, calculates output train information, and the train information is stored in the data memory module.The present invention can provide reference by location for other needs on the premise of safe train operation is not influenceed with the one-to-one data in position (such as train operating mode, energy consumption).
Description
Technical field
Train Positioning Technology field of the present invention, more particularly to a kind of train positioning system based on deep learning.
Background technology
At present, the field such as positioning, mobile terminal location indoors of the wireless location technology based on deep learning
There is wide application.This positioning method in original train operation control system without increasing extra equipment, cost
It is relatively low, and the mode of wireless location only scan for wireless signals intensity, it is not necessary to signalling arrangement is accessed, is not influenceing original system just
Often operation, can complete to position by programming.
At present in track traffic, train operation control system is carried out real-time using track circuit and mobile unit to train
Positioning, also provide data, the train positioner based on deep learning without other mobile units without a kind of.
The content of the invention
The invention provides a kind of train positioning system based on deep learning, is not influenceing the premise of safe train operation
Under, provide reference by location with the one-to-one data in position (such as train operating mode, energy consumption) for other needs.
To achieve these goals, this invention takes following technical scheme：
A kind of train positioning system based on deep learning, including：Signal acquisition module and data memory module, it is described
Signal acquisition module and data memory module connect main control module respectively, and the main control module connects power module；
The signal intensity that the signal acquisition module receives is input to the main control module and carries out deep learning mould
Type calculates, and calculates output train positional information, and the train position information is stored in into the data memory module.
Further, the main control module includes：Deep learning model building module and train position computing module；
The deep learning model building module, train is obtained in each of diverse location using the signal acquisition module
The signal intensity of communication equipment and device identification, obtain the corresponding one group of device identification of train position, described one group of device identification
Corresponding one group of signal strength data, described one group of signal strength data are used to train communication device signal intensity and relevant position
Between relation deep learning model,
The train position computing module, for by the signal intensity number of the communication equipment of any time train present position
According to the deep learning model is inputted, the location of described moment train is exported.
Further, described train position information includes the current time of train position and the train position.
Further, the system also includes interactive module, and the interactive module is connected with the main control module, described
Interactive module is used for configuration of the peripheral hardware to the system.
Further, described device identification is the MAC Address of equipment room media transmission.
As seen from the above technical solution provided by the invention, the present invention can not influence the bar of safe train operation
Realize that train positions under part, precision is at least between a station, meets under different scenes the needs of to positioning precision.
The additional aspect of the present invention and advantage will be set forth in part in the description, and these will become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, required use in being described below to embodiment
Accompanying drawing be briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for this
For the those of ordinary skill of field, without having to pay creative labor, other can also be obtained according to these accompanying drawings
Accompanying drawing.
Fig. 1 is a kind of structural representation of the train positioning system based on deep learning provided in an embodiment of the present invention；
Fig. 2 is main control module schematic diagram in Fig. 1 provided in an embodiment of the present invention；
Fig. 3 is that a kind of deep learning model of train positioning system based on deep learning provided in an embodiment of the present invention is calculated
Method schematic diagram.
Embodiment
Embodiments of the present invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning
Same or similar element is represented to same or similar label eventually or there is the element of same or like function.Below by ginseng
The embodiment for examining accompanying drawing description is exemplary, is only used for explaining the present invention, and is not construed as limiting the claims.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singulative " one " used herein, " one
It is individual ", " described " and "the" may also comprise plural form.It is to be further understood that what is used in the specification of the present invention arranges
Diction " comprising " refer to the feature, integer, step, operation, element and/or component be present, but it is not excluded that in the presence of or addition
One or more other features, integer, step, operation, element, component and/or their groups.It should be understood that when we claim member
Part is " connected " or during " coupled " to another element, and it can be directly connected or coupled to other elements, or there may also be
Intermediary element.In addition, " connection " used herein or " coupling " can include wireless connection or coupling.Wording used herein
"and/or" includes any cell of one or more associated list items and all combined.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific terminology) with the general understanding identical meaning with the those of ordinary skill in art of the present invention.Should also
Understand, those terms defined in such as general dictionary, which should be understood that, to be had and the meaning in the context of prior art
The consistent meaning of justice, and unless defined as here, will not be with idealizing or the implication of overly formal be explained.
For ease of the understanding to the embodiment of the present invention, done further by taking several specific embodiments as an example below in conjunction with accompanying drawing
Explanation, and each embodiment does not form the restriction to the embodiment of the present invention.
Fig. 1 is system structure diagram of the present invention, and Fig. 2 is the schematic diagram of main control module in Fig. 1, such as Fig. 1,2 institutes
Show：
A kind of train positioning system based on deep learning, including：Signal acquisition module and data memory module, it is described
Signal acquisition module and data memory module connect main control module respectively, and the main control module connects power module；
The signal intensity that the signal acquisition module receives is input to the main control module and carries out deep learning mould
Type calculates, and calculates output train positional information, and the train position information is stored in into the data memory module.
In a specific embodiment, described train position information includes train position and the train position
Current time.
In a specific embodiment, the main control module includes：Deep learning model building module and train position
Put computing module；
The deep learning model building module, train is obtained in each of diverse location using the signal acquisition module
The signal intensity of communication equipment and device identification, obtain the corresponding one group of device identification of train position, described one group of device identification
Corresponding one group of signal strength data, described one group of signal strength data are used to train communication device signal intensity and relevant position
Between relation deep learning model,
The train position computing module, for by the signal intensity number of the communication equipment of any time train present position
According to the deep learning model is inputted, the location of described moment train is exported.
The system also includes interactive module, and the interactive module is connected with the main control module, the interactive module
For configuration of the peripheral hardware to the system.
In a specific embodiment, the interactive module has human-computer interaction interface and button, and interface is used to show
Show the available status information of the other systems such as system present clock, dump energy, device.Button can be that the system is set
Clock.
In a specific embodiment, coordinate GPS (Global Positioning using the interactive module
System, global positioning system), the equipment such as accelerometer, realize train on the ground, the integrated positioning of underground.
In a specific embodiment, described main control module, for respectively with the signal acquisition module, data
Memory module, power module connect with interactive module, set the work clock of system, control system operation or stopping.
In a specific embodiment, the signal acquisition module is wireless signal acquiring module, the wireless signal
Acquisition module is connected with main control module.It has the function of wireless signal scan, for WiFi module but can be not limited only to this.Nothing
Line signal acquisition module continually scans for the wireless signal in space to obtain train in difference with the sweep spacing no more than 200ms
The signal intensity of each Wireless Telecom Equipment at moment and device identification, obtaining one group of moment corresponds to one or more equipment marks
Know, the data acquisition system of the corresponding Wireless Telecom Equipment signal intensity of device identification.The model of wireless signal acquiring module is
Rtl8188eu type wireless network cards.
In a specific embodiment, described device identification is the MAC Address that equipment room media transmit access control.
In a specific embodiment, described data memory module, for being connected with main control module, storage has
The train time of uniform scale, position data.Data storage interval includes but is not limited to 200ms, can be manually set and be not more than
200ms data sampling and the time interval of data storage.Under conditions of data storage interval is met, data memory module can
For the power down such as SD card or FLASH memory not loss storage.
In a specific embodiment, described power module, for electric energy needed for being provided to whole system.By institute
State system to position applied to train, using the power supply mode of external power interface and unrealistic, therefore the system use can fill
Electric lithium battery power supply.The power supply of system includes but is not limited to battery powered.
Fig. 2 is the algorithm schematic diagram of deep learning model in system of the present invention, as shown in Figure 2：
In a specific embodiment, existed using the wireless signal in signal acquisition module scanning space to obtain train
The signal intensity of each Wireless Telecom Equipment of diverse location and device identification, the Wireless Telecom Equipment scanned include but unlimited
In vehicle-ground wireless communication equipment, finally give one group of train position and correspond to one or more device identifications, device identification corresponding one
The data acquisition system of individual Wireless Telecom Equipment signal intensity.The data acquisition system is used to training description Wireless Telecom Equipment signal intensity
The deep learning model of relation between position.
In a specific embodiment, described deep learning mode input is wireless device signal intensity, output
Be the wireless device signal intensity correspond to diverse location probability.Input layer number is by the wireless signal equipment mark that collects
The number of knowledge determines that the number of plies and number of hidden layer are obtained by test of many times, and the number of output layer is by the individual of train estimated location
Number determines.The algorithm that model parameter initialization uses (Stacked DenosingAutoencoders, stacks noise reduction certainly for SDA
Encoder), the algorithm that parameter optimization uses is BP (Back Propagation, back-propagation algorithm) and SGD (Stochastic
GradientDescent, stochastic gradient descent) algorithm, the algorithm that model output layer uses is Softmax regression models.Use
Computer language describes the deep learning model, by the signal strength data of the communication equipment of any time train present position
The deep learning model is inputted, exports the location of described moment train.
In summary, system of the present invention can realize that train positions under conditions of safe train operation is not influenceed,
Precision is at least between a station, meets under different scenes the needs of to positioning precision.The system can be other needs and position
One-to-one data (such as train energy consumption) provide reference by location, are associated between different pieces of information by the uniform scale moment.
The system can identify external equipment and be attached, and the data of storage are transmitted.
One of ordinary skill in the art will appreciate that：Accompanying drawing is the schematic diagram of one embodiment, module in accompanying drawing or
Flow is not necessarily implemented necessary to the present invention.
Each embodiment in this specification is described by the way of progressive, identical similar portion between each embodiment
Divide mutually referring to what each embodiment stressed is the difference with other embodiment.Especially for device or
For system embodiment, because it is substantially similar to embodiment of the method, so describing fairly simple, related part is referring to method
The part explanation of embodiment.Apparatus and system embodiment described above is only schematical, wherein the conduct
The unit that separating component illustrates can be or may not be it is physically separate, can be as the part that unit is shown or
Person may not be physical location, you can with positioned at a place, or can also be distributed on multiple NEs.Can root
Factually border needs to select some or all of module therein realize the purpose of this embodiment scheme.Ordinary skill
Personnel are without creative efforts, you can to understand and implement.
The foregoing is only a preferred embodiment of the present invention, but protection scope of the present invention be not limited thereto,
Any one skilled in the art the invention discloses technical scope in, the change or replacement that can readily occur in,
It should all be included within the scope of the present invention.Therefore, protection scope of the present invention should be with scope of the claims
It is defined.
Claims (5)
- A kind of 1. train positioning system based on deep learning, it is characterised in that including：Signal acquisition module and data storage mould Block, described signal acquisition module and data memory module connect main control module respectively, and the main control module connects power supply Module；The signal intensity that the signal acquisition module receives is input to the main control module and carries out deep learning model meter Calculate, calculate output train positional information, and the train position information is stored in the data memory module.
- 2. system according to claim 1, it is characterised in that the main control module includes：Deep learning model is established Module and train position computing module；The deep learning model building module, each communication of the train in diverse location is obtained using the signal acquisition module The signal intensity of equipment and device identification, obtain the corresponding one group of device identification of train position, and described one group of device identification is corresponding One group of signal strength data, described one group of signal strength data are used to train between communication device signal intensity and relevant position The deep learning model of relation,The train position computing module, for the signal strength data of the communication equipment of any time train present position is defeated Enter the deep learning model, export the location of described moment train.
- 3. system according to claim 1, it is characterised in that described train position information includes train position and institute State the current time of train position.
- 4. system according to claim 1, it is characterised in that the system also includes interactive module, the interactive module It is connected with the main control module, the interactive module is used for configuration of the peripheral hardware to the system.
- 5. system according to claim 2, it is characterised in that described device identification is the MAC of equipment room media transmission Address.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710685925.8A CN107585181A (en) | 2017-08-11 | 2017-08-11 | A kind of train positioning system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710685925.8A CN107585181A (en) | 2017-08-11 | 2017-08-11 | A kind of train positioning system based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107585181A true CN107585181A (en) | 2018-01-16 |
Family
ID=61041604
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710685925.8A Pending CN107585181A (en) | 2017-08-11 | 2017-08-11 | A kind of train positioning system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107585181A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110139207A (en) * | 2018-02-08 | 2019-08-16 | 北京神州泰岳软件股份有限公司 | A kind of subway localization method and device based on mobile communication |
| CN110450821A (en) * | 2019-08-19 | 2019-11-15 | 武汉虹信通信技术有限责任公司 | A kind of train position information real time acquiring method and device |
| CN112224240A (en) * | 2020-10-28 | 2021-01-15 | 重庆交通大学 | High-speed train positioning system and positioning method |
| CN112429044A (en) * | 2020-11-27 | 2021-03-02 | 株洲中车时代软件技术有限公司 | Method and system for positioning running train position based on nonlinear compensation |
| CN114954575A (en) * | 2022-06-29 | 2022-08-30 | 宁波极晋科技开发有限公司 | Train-ground information transmission system and accurate positioning method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015093532A (en) * | 2013-11-11 | 2015-05-18 | 株式会社明電舎 | Self-position estimation device for train |
| CN105358402A (en) * | 2013-05-03 | 2016-02-24 | 泰利斯加拿大公司 | Vehicle position determining system and method of using the same |
| CN106428122A (en) * | 2016-09-26 | 2017-02-22 | 北京交通大学 | Train locating method based on signal strength of train-ground wireless communication equipment |
-
2017
- 2017-08-11 CN CN201710685925.8A patent/CN107585181A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105358402A (en) * | 2013-05-03 | 2016-02-24 | 泰利斯加拿大公司 | Vehicle position determining system and method of using the same |
| JP2015093532A (en) * | 2013-11-11 | 2015-05-18 | 株式会社明電舎 | Self-position estimation device for train |
| CN106428122A (en) * | 2016-09-26 | 2017-02-22 | 北京交通大学 | Train locating method based on signal strength of train-ground wireless communication equipment |
Non-Patent Citations (1)
| Title |
|---|
| 刘侃等: ""一种基于深度神经网络的无线定位方法"", 《计算机工程》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110139207A (en) * | 2018-02-08 | 2019-08-16 | 北京神州泰岳软件股份有限公司 | A kind of subway localization method and device based on mobile communication |
| CN110450821A (en) * | 2019-08-19 | 2019-11-15 | 武汉虹信通信技术有限责任公司 | A kind of train position information real time acquiring method and device |
| CN112224240A (en) * | 2020-10-28 | 2021-01-15 | 重庆交通大学 | High-speed train positioning system and positioning method |
| CN112429044A (en) * | 2020-11-27 | 2021-03-02 | 株洲中车时代软件技术有限公司 | Method and system for positioning running train position based on nonlinear compensation |
| CN112429044B (en) * | 2020-11-27 | 2023-02-28 | 株洲中车时代软件技术有限公司 | Method and system for positioning running train position based on nonlinear compensation |
| CN114954575A (en) * | 2022-06-29 | 2022-08-30 | 宁波极晋科技开发有限公司 | Train-ground information transmission system and accurate positioning method |
| CN114954575B (en) * | 2022-06-29 | 2024-03-12 | 宁波极晋科技开发有限公司 | Vehicle-ground information transmission system and accurate positioning method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107585181A (en) | A kind of train positioning system based on deep learning | |
| CN103925853B (en) | A kind of carrier rocket ground testing system device | |
| CN107515370A (en) | A kind of PCBA detection means and detection method | |
| CN103220050B (en) | A kind of CIR comprehensive diagnos testing equipment and method | |
| CN204425399U (en) | A kind of hydrometeorological operation system based on cloud computing | |
| CN105871672A (en) | One-host multi-slave communication system and data transmission method thereof | |
| CN106325239A (en) | Base station for gathering data from localized sensors | |
| CN106249707A (en) | Information Collection System, information collecting terminal device, information collecting server device and formation gathering method | |
| CN103279897B (en) | Power scheduling monitoring information methods of exhibiting and system | |
| CN106598530A (en) | Display panel configuration method and device | |
| CN104484257B (en) | A kind of general 1553B bus communication emulation test system and method | |
| CN106991001A (en) | Radionavigation recognizes simulation system | |
| CN104750633A (en) | Field programmable gate array (FPGA) device access verification device and method | |
| CN117213650A (en) | Bus temperature monitoring system and method based on UHF RFID | |
| CN108072855A (en) | A kind of test device and test system | |
| CN104717093B (en) | Method for managing an electrical device and a system for managing such a device | |
| CN106662849A (en) | Mobile human machine interface for control devices | |
| CN113179201B (en) | Multi-region multi-device remote combined debugging and testing system and method | |
| CN109474878A (en) | A kind of Carplay Auto-Test System and method | |
| CN109388121A (en) | A kind of flight control computer test device | |
| CN114563017A (en) | Navigation performance test system and method for strapdown inertial navigation device | |
| CN105487412B (en) | A kind of acquisition cascade method and system of remotely electricity tune antenna control unit | |
| CN106488380B (en) | Data transmission module, data transmission system or data transmission method | |
| CN203643817U (en) | Automobile instrument program write-in device based on three-axis positioning | |
| CN202584235U (en) | Network attendance machine |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180116 |