[서평]「The Unified Modeling Language User Guide」

An Introduction to Bayesian Inference and Decision

Nowadays, the railway industry is in a position where it is able to exploit the opportunities created by the IIoT (Industrial Internet of Things) and enabling communication technologies under the paradigm of Internet of Trains. This review details the evolution of communication technologies since the deployment of GSM-R, describing the main alternatives and how railway requirements, specifications and recommendations have evolved over time. The advantages of the latest generation of broadband communication systems (e.g., LTE, 5G, IEEE 802.11ad) and the emergence of Wireless Sensor Networks (WSNs) for the railway environment are also explained together with the strategic roadmap to ensure a smooth migration from GSM-R. Furthermore, this survey focuses on providing a holistic approach, identifying scenarios and architectures where railways could leverage better commercial IIoT capabilities. After reviewing the main industrial developments, short and medium-term IIoT-enabled services for smart railways are evaluated. Then, it is analyzed the latest research on predictive maintenance, smart infrastructure, advanced monitoring of assets, video surveillance systems, railway operations, Passenger and Freight Information Systems (PIS/FIS), train control systems, safety assurance, signaling systems, cyber security and energy efficiency. Overall, it can be stated that the aim of this article is to provide a detailed examination of the state-of-the-art of different technologies and services that will revolutionize the railway industry and will allow for confronting today challenges.

https://www.mdpi.com/1424-8220/17/6/1457/pdf

Towards the Internet of Smart Trains: A Review on Industrial IoT-Connected Railways

(4) Whereas the extension of the scope of Directive 98/34/EC should not prevent Member States from taking account of the different social, societal and cultural implications inherent in the advent of the Information Society; whereas, in particular, the use of the procedural rules laid down in that Directive for Information Society services should not affect cultural policy measures, particularly in the audiovisual field, which Member States might adopt in accordance with Community law, taking account of their linguistic diversity, their specific national and regional characteristics and their cultural heritage; whereas the development of the Information Society should ensure, in any event, proper access of European citizens to the European cultural heritage supplied in a digital environment;

Directive 98/48/EC of the European Parliament and of the Council

Template matching is an alternative to perform speech recognition. However, the template matching encountered problems due to speaking rate variability, in which there exist timing differences between the two utterances. Speech has a constantly changing signal, thus it is almost impossible to get the same signal for two same utterances. The problem of time differences can be solved through DTW algorithm: warping the template with the test utterance based on their similarities. So, DTW algorithm actually is a procedure, which combines both warping and distance measurement. DTW is considered as one effective method in speech pattern recognition, however the bad side of this method is that it requires a long processing time plus large storage capacity, especially for real time recognitions.

Dynamic time warping

Global Navigation Satellite Systems (GNSS) are applicable to deliver train locations in real time. This train localization function should comply with railway functional safety standards; thus, the GNSS performance needs to be evaluated in consistent with railway EN 50126 standard [Reliability, Availability, Maintainability, and Safety (RAMS)]. This paper demonstrates the performance of the GNSS receiver for train localization. First, the GNSS performance and railway RAMS properties are compared by definitions. Second, the GNSS receiver measurements are categorized into three states (i.e., up, degraded, and faulty states). The relations between the states are illustrated in a stochastic Petri net model. Finally, the performance properties are evaluated using real data collected on the railway track in High Tatra Mountains in Slovakia. The property evaluation is based on the definitions represented by the modeled states.

Performance Evaluation of GNSS for Train Localization

This paper focuses on GNSS and Inertial Navigation System (INS) integration system based on the loosely coupled (LC) and tightly coupled (TC) schemes. This paper describes the system architechture of two systems and presents the mathematical derivation. In order to evaluate the system performance of the two schemes, a real field experiment was carried in the campus of Beijing Jiaotong University. The experimental results show that the positioning performance is able to verify the theoretical analysis.

Evaluation on loosely and tightly coupled GNSS/INS vehicle navigation system

Global Navigation Satellite Systems (GNSS) are potentially applicable for various railway applications, especially the safety-related applications such as train localisation for the purpose of train control. In order to integrate GNSS for train localisation, a trustable stand-alone GNSS-based localisation unit should be developed. Then to comply with EN 50126 (reliability, availability, maintainability, and safety; RAMS) standards, the demonstration of GNSS quality of service (QoS) should be evaluated in consistent with RAMS. However there are currently no appropriate performance evaluation methods on GNSS for railway safety-related applications.
This dissertation identifies the required performance for train localisation in consideration of GNSS QoS and railway RAMS. The common and different properties of the performance are analysed in detail using consistent attribute hierarchy structures based on UML class diagram. Then formalised performance requirements are proposed quantitatively on four properties (accuracy, reliability, availability, and safety integrity). After that, the evaluation and verification methodologies are introduced. The evaluation methodology is using a reference measurement system for GNSS receiver measured train location accuracy identification, and a stochastic Petri net (SPN) model for GNSS receiver measured train location accuracy categorisation. The SPN model illustrates the GNSS receiver measured train locations into three states (up state, degraded state, and faulty state). Then the four proposed properties are allocated and estimated formally using the three states in the SPN model. The verification methodology is used to verify the GNSS receiver measured train location in real time based on a localisation unit. The GNSS receiver measured train locations are verified using hypothesis testing methods based on the accurate digital track map provided beforehand. Then train location estimation from the localisation unit is verified according to the mileage of the train. With the verified train location estimation from the localisation unit, the corresponding safety margin for each train location is calculated.
The data for evaluation and verification methodologies are collected from a test train running on a railway track in High Tatra Mountains. The results show an approach of the possible certification procedure for the GNSS receivers in railway safety-related applications.

GNSS for Train Localisation Performance Evaluation and Verification

GNSS (Global Navigation Satellite Systems) have been widely applied in railway applications as timing, passenger information, track survey, and also safety relevant applications as train localization for train control purposes on lines like Chicago-Detroit Line, Qinghai-Tibet railway line, etc. However, due to the continuous dynamic movement of the locomotive, it goes through various environments as tunnels, bridges, mountainous areas, urban canyons, etc. GNSS performance is affected and thus degraded in some GNSS signal reception constrained environment scenarios, which leads the localization result not meeting the required accuracy and safety requirements. With the dynamic movement of the locomotive, the measurement results are not abundantly enough. It is quite necessary to investigate the methodology for GNSS performance evaluation in signal reception constrained environments using both simulation and field test results together. This will reduce the test complexity and also provide the possibility to compare between different parameters. In this paper, a 3-km-long railway environment scenario in Qinghai-Tibet railway is selected and modelled with signal reception limitations recorded several times in the on-board log files. After an investigation of the terrain structure of the environment, a hill near the railway tracks namely mountainous environment is causing the “half sky” signal blocking scenario. The terrain is modelled using Google SketchUp. Then, the model data is converted into QualiSIM, which is a matlab-based tool to provide the possibility to understand the sky plot of the location according to almanac and relevant information. The satellite visibility, satellite geometry and signal propagation trajectories are calculated and illustrated in QualiSIM. Using the output from QualiSIM, the locomotive operation route, 3D environment “half sky” model and signal propagation trajectory are all configured and simulated using Spirent GSS8000 system. The GNSS signals are repeated using Spirent GSS8000 together with Spirent SimGEN software. A UBLOX M8N and Unicore UB370 GNSS receivers were used to test and compare the performance of both receivers under the modelled mountainous environment. The accuracy levels of both receivers are compared by satellite visible number, HDOP (Horizontal Dilution of Precision) and position error. The measurement errors are illustrated using error ellipse, which shows the different accuracy level and the reliability level for the two receivers. Comparing the recorded results of open sky and different levels of obstruction, GNSS performance can be gradually degraded when the degree of obstruction is increased.

Quantitative analysis of GNSS performance under railway obstruction environment

The usage of filter techniques for position estimation for safety-relevant purposes is an extensive field of research. Depending on the needed application for the Global Navigation Satellite System (GNSS) the state estimation can be achieved by several techniques. State estimation by means of Kalman Filter (KF), as well as Extended Kalman Filter (EKF) and Particle Filter (PF) have been developed and tested. Map-matching algorithms integrate the localisation data provided by GNSS with spatial road network data (also called “digital map”) to identify the correct line (or track) on which a vehicle is traveling and to determine the location of a vehicle within the line (or track). The goal of map-matching techniques is to exploit prior information contained in road or railway networks. However, incorporating digital map information within the conventional KF framework is not easy, because this constraint leads to highly non-Gaussian posterior densities that are difficult to represent accurately using conventional techniques. Since the PF approach presents no restrictions regarding non-linearity of models and noise distribution the velocity and heading measurement errors can be accurately modelled. The most significant advantages of the PF approach for map-matching application are: 1) PF approach provides a natural way for road map information to be incorporated into vehicle position estimation. 2) PF approach is capable of capturing multi-modal distributions. The selected PF-based location estimators presented here is oriented to work within an intelligent GNSS-based localisation system. The PF-based map matching techniques are presented in a mathematical ground and tests are performed, as part of a developed satellite localisation system based on artificial intelligence (AI) tools. In the railway domain the same integration can be performed by means of a “digital trap map” to identify the location within the tracks. A map-matching algorithm can be the key component of the data fusion to improve the performance of localisation systems that support the navigation function of intelligent transport systems (ITS).

Debiao Lu

Papers

Performance Evaluation of GNSS for Train Localization

Evaluation on loosely and tightly coupled GNSS/INS vehicle navigation system

GNSS for Train Localisation Performance Evaluation and Verification

Quantitative analysis of GNSS performance under railway obstruction environment

Particle Filter technique for position estimation in GNSS-based localisation systems