Abstract
Obtaining the accurate real-time train number and location in a railway network is necessary for railway traffic operation control. This paper investigates the implementation and optimization method of train number tracking, by which the train number and location information can be captured. According to the characteristics of the train operation, the train moving trajectory and the train number tracking problem, the mathematical description of the problem and the tracking model based on the railway signaling states and train schedules are proposed. Then, a method using a hidden Markov model prediction is proposed in order to improve the correctness of train number tracking. The simulation results are compared with the results obtained under certain restrictions, and the analyses are discussed. The results show that the proposed method can effectively improve the accuracy of train number tracking with better fault-tolerant robustness.
Highlights
Centralized traffic control (CTC) systems are one of the most important and widely used systems for train dispatching in Chinese railways, and they help dispatchers make better train operation decisions
Most of the automatic function of a CTC, such as Automatic Route Setting (ARS), Automatic Train Monitoring (ATM), and Automatic Train Arrival/Departure Time Recording (ATA/DTR) all rely on the train number tracking function, which is one of the cores of train control and dispatching
SIMULATION TEST AND ANALYSIS To verify the effectiveness and the improvement of the proposed Train number tracking (TNT) prediction model and framework, simulation experiments are designed with 10 stations from the historical CTC data collected from the Shijiazhuang-Dezhou Railway in China
Summary
Centralized traffic control (CTC) systems are one of the most important and widely used systems for train dispatching in Chinese railways, and they help dispatchers make better train operation decisions. The main reason for this is that, compared with the increasing system complexity and the effort to improve the reliability of train number tracking, it is much easier for dispatchers to manually find and correct any inaccurate train numbers and locations This is true in railway areas with a low train density where the dispatchers are not busy, while in railway areas with a high train density, train dispatchers need to monitor several types of information simultaneously through CTC screens and monitors, including train locations, speeds, signaling states, block occupation, system devices status, etc. 2) Proposed a prediction framework with the hidden Markov model and a Bayesian prediction method to VOLUME 7, 2019 improve the reliability of the train number tracking for a fixed block railway.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
