CN113259840A - Train positioning system based on LTE performance parameters - Google Patents
Train positioning system based on LTE performance parametersDownload PDFInfo
- Publication number
- CN113259840A CN113259840ACN202110533933.7ACN202110533933ACN113259840ACN 113259840 ACN113259840 ACN 113259840ACN 202110533933 ACN202110533933 ACN 202110533933ACN 113259840 ACN113259840 ACN 113259840A
- Authority
- CN
- China
- Prior art keywords
- positioning
- fingerprint
- train
- lte
- technology
- 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
Images
Classifications
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/023—Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/42—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for mass transport vehicles, e.g. buses, trains or aircraft
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medical Informatics (AREA)
- Human Computer Interaction (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Multimedia (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
Translated fromChinese
Description
Technical Field
The invention relates to the technical field of train positioning, in particular to a system for positioning a train based on LTE performance parameters.
Background
Railroads play an important role in mass travel. According to statistics of general companies of China railway, 1013.1 ten thousand persons are used for traveling on the railway nationwide during the spring transportation period of 2017, 111.8 ten thousand persons are increased on a year-by-year basis, and the growth rate is 12.4%. Railways have entered a phase of rapid development in recent years.
Train location information is one of the important parameters in a train control system. The method for obtaining train positioning mainly comprises the following 6 methods:
firstly, speed measurement and positioning, secondly, inquiring/answering machine, thirdly, track circuit, fourthly, Doppler radar, fifthly, GPS/Beidou satellite positioning system and sixthly, wireless spread spectrum train positioning.
At present, urban rail trains in China are generally positioned accurately and are subjected to distance measurement/speed measurement auxiliary positioning through passive transponders, but in order to improve the accuracy of the positioning mode, a large number of response devices need to be arranged, and the maintenance cost of the devices is increased. And errors in positioning can occur due to wheel spin, slip, and lock.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a train positioning system based on LTE performance parameters, and solves the problems.
In order to achieve the purpose, the invention provides the following technical scheme: the LTE positioning system comprises a fingerprint positioning method, a matching positioning method, a fingerprint positioning technology, LTE related performance, research contents, a research method and a research technical route, and the LTE positioning system is used for positioning a train by utilizing wireless communication and an efficient position positioning technology and can enable people to obtain the current position of the train.
Preferably, the fingerprint positioning comprises position fingerprints, fingerprint signal strength and a position fingerprint positioning technology, the position fingerprints are obtained by associating a certain fingerprint with an actual position, each position corresponds to a unique fingerprint, the fingerprint signal strength is obtained by selecting the signal strength as the fingerprint when selecting, the position fingerprint positioning technology is obtained by forming a fingerprint database by using collected signals and position coordinates, then a target position is obtained by online matching, and the position of a target train can be accurately obtained by combining the signals and the position coordinates.
Preferably, the matching positioning method comprises a fingerprint matching method, a deterministic algorithm, a probabilistic algorithm, a k-nearest neighbor algorithm and a bayesian algorithm, the basic idea of the fingerprint matching method is to match signal intensity information measured by the mobile terminal with signal intensity in a fingerprint database by using a certain method to obtain the position of the target to be positioned, the deterministic algorithm and the probabilistic algorithm are matching methods of common fingerprints, the deterministic algorithm comprises the k-nearest neighbor algorithm, the probabilistic algorithm comprises the bayesian algorithm, and required data can be accurately obtained through the k-nearest neighbor algorithm and the bayesian algorithm, so that the position of the target can be determined through the signal intensity.
Preferably, the fingerprint positioning technology includes WiFi fingerprint positioning, software location and intelligent terminal, WiFi fingerprint positioning is based on the indoor location of fingerprint accurate positioning technology, software location includes GPS positioning technology, wireless local area network facility and WiFi access point, intelligent terminal need popularize, but need not extra professional equipment, utilizes WiFi fingerprint and software just can carry out location service.
Preferably, the LTE-related performance includes a wireless data communication technology, a TDD mode and an FDD mode, the wireless data communication technology is provided for meeting the requirement of a client for wireless communication, the TDD mode and the FDD mode are two main flow modes of LTE, FDD-LTE is widely applied internationally, TD-LTE is common in China, the current goal of LTE is to improve the data transmission capability and data transmission speed of a wireless network by means of a new technology and a modulation method, and a long-term goal of LTE is to simplify and redesign a network architecture to make it an IP network, which helps to reduce potential adverse factors in 3G conversion.
Preferably, the research content comprises consulting data, learning and positioning methods, collecting train-mounted access units and learning based on a Pythrch frame, the consulting data is based on a positioning method of position fingerprints, researching an indoor WiFi fingerprint positioning principle, comparing the principle and the advantages and the disadvantages of NN, KNN and WKNN methods in an online positioning stage in the existing train positioning technology, the collecting train-mounted access units are recorded LTE performance parameter data and train position data, the learning based on the Pythrch frame is complex deep learning, an activation function and cost function calculation method selected by modifying a neural network and continuously collecting data for deep learning, and finally realizing accurate positioning when improving the positioning precision of the model.
Preferably, the research method comprises the steps of determining a subject selection direction, looking up related documents and writing codes, wherein the subject selection direction is determined by analyzing problems existing in the current train and knowledge contacted during practice, the general direction of the research is determined, the looking up related documents are obtained by searching data and comparing advantages and disadvantages of each method in train positioning, each technical difficulty of a positioning system is analyzed and corrected, the writing codes are the most important technology, a model needs to be built, and a test set needs to be used for completing model prediction accuracy testing.
Preferably, the technical route of the research includes data collection by using TAU, selection of an appropriate processing method, testing of model accuracy, and summarization of a method with highest positioning accuracy by improving the data processing method, which is a whole set of design process for performing feasibility research.
Compared with the prior art, the invention provides a train positioning system based on LTE performance parameters, which has the following beneficial effects:
1. this design builds neural network model based on the Pythrch frame. The Pythrch provides many existing loss function, back propagation, gradient descent algorithms, and provides design assistance.
2. After the program reads the data, the abnormal data can be deleted through a programming method, and the positioning precision is improved. And finally, obtaining a model with accurate positioning after continuous training by modifying and adjusting parameters for multiple times.
Drawings
FIG. 1 is an overall block diagram of the present invention;
FIG. 2 is a flow chart of fingerprint location of the present invention;
FIG. 3 is a flow chart of a matching location method of the present invention;
FIG. 4 is a flow chart of a fingerprint location technique of the present invention;
FIG. 5 is a block diagram of LTE related performance of the present invention;
FIG. 6 is a flow chart of the contents of a study of the present invention;
FIG. 7 is a flow chart of a method of investigation of the present invention;
fig. 8 is a flow chart of a technical route of the study of the present invention.
In the figure: 1. fingerprint positioning; 2. matching and positioning methods; 3. fingerprint positioning technology; 4. LTE related performance; 5. the content of the study; 6. the method of investigation; 7. the technical route studied; 11. a location fingerprint; 12. Fingerprint signal strength; 13. a location fingerprint positioning technique; 21. a fingerprint matching method; 22. a deterministic algorithm; 23. a probabilistic algorithm; 220. k nearest neighbor algorithm; 230. a Bayesian algorithm; 31. WiFi fingerprint positioning; 32. positioning software; 33. an intelligent terminal; 41. wireless data communication technology; 42. a TDD mode; 43. FDD mode; 51. looking up the data; 52. learning a positioning method; 53. collecting train-mounted access units; 54. learning is based on a Pythrch framework; 61. determining the direction of the selected questions; 62. relevant documents are consulted; 63. and writing codes.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-8, in this embodiment: the system comprises an LTE positioning system, wherein the LTE positioning system comprises a fingerprint positioning 1, a matching positioning method 2, a fingerprint positioning technology 3, LTE related performance 4,research content 5, aresearch method 6 and a research technical route 7, and the LTE positioning system is used for positioning a train by utilizing wireless communication and an efficient position positioning technology and can enable people to obtain the current position of the train.
The fingerprint positioning method comprises the steps that the fingerprint positioning 1 comprises a position fingerprint 11, fingerprint signal intensity 12 and a position fingerprint positioning technology 13, the position fingerprint 11 is to link a certain fingerprint with an actual position, each position corresponds to a unique fingerprint, the fingerprint signal intensity 12 is to select the signal intensity as the fingerprint when selecting, and the position fingerprint positioning technology 13 is to form a fingerprint database by collected signals and position coordinates and then obtain a target position through online matching.
The matching positioning method 2 comprises a fingerprint matching method 21, adeterministic algorithm 22, aprobabilistic algorithm 23, a k-nearest neighbor algorithm 220 and aBayesian algorithm 230, the basic idea of the fingerprint matching method 21 is to match the signal intensity information measured by the mobile terminal with the signal intensity in a fingerprint database by using a certain method to obtain the position of the target to be positioned, thedeterministic algorithm 22 and theprobabilistic algorithm 23 are matching methods for common fingerprints, thedeterministic algorithm 22 comprises the k-nearest neighbor algorithm 220, and theprobabilistic algorithm 23 comprises theBayesian algorithm 230.
Fingerprint location technique 3 includes wiFi fingerprint location 31, software location 32 and intelligent terminal 33, wiFi fingerprint location 31 is the indoor location based on fingerprint accurate positioning technique, software location 32 includes GPS positioning technique, wireless LAN facility and WIFi access point, intelligent terminal 33 needs to popularize, but need not extra professional equipment.
The LTE related performance 4 includes a wireless data communication technology 41, a TDD mode 42, and an FDD mode 43, where the wireless data communication technology 41 is proposed to meet the requirement of a client for wireless communication, and the TDD mode 42 and the FDD mode 43 are two main flow modes of LTE, where FDD-LTE is widely used internationally, and TD-LTE is more common in China.
Theresearch content 5 comprises consulting data 51, learning and positioning method 52, collecting train-mounted access unit 53 and learning Pytorch frame-based lower 54, wherein the consulting data 51 is used for comparing and analyzing advantages and disadvantages of various train positioning methods by learning the principle of the existing train positioning technology and conceiving the starting point of optimization research of the train positioning technology, the learning and positioning method 52 is used for researching the indoor WiFi fingerprint positioning 31 principle and comparing the principles and advantages and disadvantages of NN, KNN and WKNN methods in the online positioning stage, the collecting train-mounted access unit 53 is used for recording LTE performance parameter data and train position data, and the learning Pytorch frame-based lower 54 is used for complex deep learning.
Theresearch method 6 comprises the steps of determining a subject selecting direction 61, consultingrelated documents 62 and compilingcodes 63, wherein the subject selecting direction 61 is determined by analyzing problems existing in a current train and knowledge contacted during practice, the general direction of research is determined, the consulting relateddocuments 62 are obtained by comparing advantages and disadvantages of methods in train positioning and analyzing and correcting various technical difficulties of a positioning system, and the compilingcodes 63 are the most main technology, and a model needs to be built and a model prediction accuracy test needs to be completed by using a test set.
The technical route 7 of the research includes data collection by TAU, selection of an appropriate processing method, testing of model accuracy, and summarization of a method with the highest positioning accuracy by improving the data processing method, which is a whole set of design process for feasibility research.
As a preferred technical solution of the present invention, an expression of case representation is as follows:
the principle of the design is as follows: the method is used for model training in the neural network by collecting geographic positions and PCIs and corresponding RSRPs at various positions. In the on-line positioning stage, a user provides the PCI and RSRP acquired by the to-be-positioned point, and the PCI and RSRP is transmitted forward through a neural network to predict the longitude and latitude of the train at the moment. And predicting the approximate position of the train according to a plurality of currently acquired cell numbers provided by the vehicle-mounted TAU and the reference signal receiving power corresponding to the cell numbers, and finishing the accurate positioning of the train.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110533933.7ACN113259840A (en) | 2021-05-15 | 2021-05-15 | Train positioning system based on LTE performance parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110533933.7ACN113259840A (en) | 2021-05-15 | 2021-05-15 | Train positioning system based on LTE performance parameters |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113259840Atrue CN113259840A (en) | 2021-08-13 |
Family
ID=77182275
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110533933.7APendingCN113259840A (en) | 2021-05-15 | 2021-05-15 | Train positioning system based on LTE performance parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113259840A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107264573A (en)* | 2017-07-20 | 2017-10-20 | 中国铁道科学研究院通信信号研究所 | Train positioning system based on satellite navigation, wireless fingerprint and Big Dipper short message communication |
| CN108462966A (en)* | 2017-02-21 | 2018-08-28 | 中国移动通信集团浙江有限公司 | One kind being based on 2G networks high-speed rail cell RRU positioning identifying methods and system |
| CN108924732A (en)* | 2017-04-26 | 2018-11-30 | 中国移动通信集团设计院有限公司 | A kind of high-speed rail user facility positioning method and device |
| CN109849976A (en)* | 2017-11-30 | 2019-06-07 | 河南星云慧通信技术有限公司 | A kind of train positioning system based on GPS, ODO and WKNN combination |
| CN111652035A (en)* | 2020-03-30 | 2020-09-11 | 武汉大学 | A method and system for pedestrian re-identification based on ST-SSCA-Net |
| CN112165684A (en)* | 2020-09-28 | 2021-01-01 | 上海大学 | High-precision indoor positioning method based on joint vision and wireless signal features |
- 2021
- 2021-05-15CNCN202110533933.7Apatent/CN113259840A/enactivePending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108462966A (en)* | 2017-02-21 | 2018-08-28 | 中国移动通信集团浙江有限公司 | One kind being based on 2G networks high-speed rail cell RRU positioning identifying methods and system |
| CN108924732A (en)* | 2017-04-26 | 2018-11-30 | 中国移动通信集团设计院有限公司 | A kind of high-speed rail user facility positioning method and device |
| CN107264573A (en)* | 2017-07-20 | 2017-10-20 | 中国铁道科学研究院通信信号研究所 | Train positioning system based on satellite navigation, wireless fingerprint and Big Dipper short message communication |
| CN109849976A (en)* | 2017-11-30 | 2019-06-07 | 河南星云慧通信技术有限公司 | A kind of train positioning system based on GPS, ODO and WKNN combination |
| CN111652035A (en)* | 2020-03-30 | 2020-09-11 | 武汉大学 | A method and system for pedestrian re-identification based on ST-SSCA-Net |
| CN112165684A (en)* | 2020-09-28 | 2021-01-01 | 上海大学 | High-precision indoor positioning method based on joint vision and wireless signal features |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11959900B2 (en) | Health early warning system for passengers on a train in an outdoor air polluted environment and method thereof | |
| Liu et al. | Exploring data validity in transportation systems for smart cities | |
| Chen et al. | A short-term traffic prediction model in the vehicular cyber–physical systems | |
| CN106604228B (en) | A kind of fingerprint positioning method based on LTE signaling data | |
| CN103678917B (en) | A kind of real-time arrival time Forecasting Methodology of public transport based on simulated annealing | |
| CN106503843A (en) | A kind of regular public traffic line network optimization and method of adjustment based on mobile phone signaling data | |
| Zhang et al. | Daily OD matrix estimation using cellular probe data | |
| CN102708680A (en) | Commute travel mode identification method based on AGPS technology | |
| CN111461251A (en) | Indoor positioning method of WiFi fingerprint based on random forest and self-encoder | |
| Ding et al. | Two-stage travel itinerary recommendation optimization model considering stochastic traffic time | |
| CN115967950B (en) | Feature and time sequence dual-drive inter-city travel mode identification method based on mobile phone data | |
| CN111710160A (en) | A Travel Time Prediction Method Based on Floating Car Data | |
| CN112511982A (en) | Subway passenger track real-time tracing and restoring method with automatic trip semantic annotation | |
| Shen et al. | A deep convolutional neural network based metro passenger flow forecasting system using a fusion of time and space | |
| CN120148258A (en) | Dynamic traffic environment monitoring method and device | |
| CN114004409B (en) | A method for predicting instant delivery routes based on multi-source data | |
| CN107655490A (en) | Hotspot path based on mobile subscriber track segmentation and most hot search finds method | |
| CN113259840A (en) | Train positioning system based on LTE performance parameters | |
| CN109470257A (en) | A method of guiding lost people based on blockchain technology | |
| CN111372182A (en) | A positioning method, apparatus, device and computer-readable storage medium | |
| CN118795522A (en) | Train route map construction method and device | |
| JP6693993B2 (en) | Information generating device, program, and information generating method | |
| JP6616860B2 (en) | Information generating apparatus, program, and information generating method | |
| CN108520044A (en) | A Least Square Path Prediction Algorithm Based on the Idea of Commensurability | |
| CN115829147A (en) | Passenger flow OD correction method based on machine simulation under rapid and slow vehicle schedule change and application |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | Application publication date:20210813 |