Developing Train Station Parking Algorithms: New Frameworks Based on Fuzzy Reinforcement Learning

Train station parking (TSP) accuracy is important to enhance the efficiency of train operation and the safety of passengers for urban rail transit. However, TSP is always subject to a series of uncertain factors such as extreme weather and uncertain conditions of rail track resistances. To increase...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of advanced transportation Jg. 2019; H. 2019; S. 1 - 9
Hauptverfasser: Chen, Dewang, Yin, Jiateng, Xian, Kai, Li, Wei
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Cairo, Egypt Hindawi Publishing Corporation 2019
Hindawi
John Wiley & Sons, Inc
Wiley
Schlagworte:
Algorithms
Braking
Computer simulation
Control algorithms
Data mining
Distance learning
Extreme weather
Learning
Light rail transit
Light rail transportation
Machine learning
Parking
Passenger safety
Railroads
Railway stations
Reinforcement
Simulation
Stations
Theory
Urban rail
Weather
China
ISSN:0197-6729, 2042-3195
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Train station parking (TSP) accuracy is important to enhance the efficiency of train operation and the safety of passengers for urban rail transit. However, TSP is always subject to a series of uncertain factors such as extreme weather and uncertain conditions of rail track resistances. To increase the parking accuracy, robustness, and self-learning ability, we propose new train station parking frameworks by using the reinforcement learning (RL) theory combined with the information of balises. Three algorithms were developed, involving a stochastic optimal selection algorithm (SOSA), a Q-learning algorithm (QLA), and a fuzzy function based Q-learning algorithm (FQLA) in order to reduce the parking error in urban rail transit. Meanwhile, five braking rates are adopted as the action vector of the three algorithms and some statistical indices are developed to evaluate parking errors. Simulation results based on real-world data show that the parking errors of the three algorithms are all within the ±30cm, which meet the requirement of urban rail transit.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0197-6729
2042-3195
DOI:10.1155/2019/3072495