Intelligent Train Automatic Stop Control (Itasc)
Total Page:16
File Type:pdf, Size:1020Kb
INTELLIGENT TRAIN AUTOMATIC STOP CONTROL (ITASC) Ali Siahvashi BSc in Electrical Engineering Shiraz University of Technology MSc in Electrical Railway Engineering Iran University of Science and Technology (IUST) A Thesis Submitted in fulfilment of the requirements for the degree of Doctor of Philosophy in the Department of Computing Faculty of Science and Engineering Macquarie University Supervisor: Prof. Mehmet Orgun Associate Supervisor: Prof. Yang Wang 2020 Keywords Algorithm, Jerk, iTASC, Stopping position, Station, Train, Train automation stop controller, Communication-based train control system, Railway control and signalling system, Rolling stock, Locomotive, Rolling stock brake system, Rolling stock brake distance, Service brake, Normal brake, Emergency brake, wagon brake, Precise stopping, Stopping errors, railway station, Platform screen door, Safety, Punctuality, Automatic train operation, Automatic train protection, Automatic train supervision, Consist, Artificial intelligence, Machine learning, Reinforcement learning, Q-learning, Fuzzy control, Double q-learning, Fuzzy double q-learning. i ii Abstract In a conventional train signalling system, stopping a train at stations is the responsibility of train drivers. Before each station, a signal known as Home Signal in railway terminology, warns the driver that the train is approaching a station. However, due to different brake system characteristics and capabilities, different track profiles as well as different competency levels of drivers, it is a challenging task to stop a train precisely by just one braking action while maintaining a uniform quality of ride. In addition to this, the use of platform screen doors (PSD) in railway stations can introduce various challenges for planners, track engineers, rolling stock manufacturers, brake engineers and PSD suppliers. Monitoring stopping spots, the braking rate, and real data are the initial requirements for any further development and evaluation for a sound and stable train control system. In the last three decades, train automatic stop control (TASC) algorithms have been developed and applied to different metro and heavy haul rail corridors all over the globe. However, even the most developed controllers have relied entirely on station markers such as home signals, on-the-track sensors or Balises. Although, position uncertainty has been considered in several studies before, it has been largely ignored in TASC studies so the foremost shortcoming of previously developed TASC algorithms is that they had not considered position uncertainty. The second most important problem with these algorithms for TASC is the exclusion of the inherent time delay in braking systems in response to any control signal. iii Therefore, to consider those factors, a braking model for station stopping is developed in this thesis, which accounts for the time dependency of the train’s air brake system to improve the accuracy of the train’s stopping. Finally, train position uncertainty, which is a missing concern in previous works, has been added to this thesis’s study. iv Table of Contents Keywords .................................................................................................................................... i Abstract .................................................................................................................................... iii Table of Contents ...................................................................................................................... v List of Figures .......................................................................................................................... vii List of Tables ............................................................................................................................ ix List of Algorithms ...................................................................................................................... x List of Abbreviations ................................................................................................................ xi Statement of Originality ......................................................................................................... xiv Acknowledgements ................................................................................................................. xv Chapter 1: Introduction ..................................................................................... 1 1.1 Background and Motivation ...........................................................................................1 1.2 Research Design, Aims and Objectives of the Thesis .....................................................6 1.3 Significance of this research ...........................................................................................8 1.4 Key Innovations of The Research ....................................................................................9 1.5 Structure of the Thesis ................................................................................................. 10 Chapter 2: Literature Review............................................................................ 15 2.1 Introduction ................................................................................................................. 15 2.2 The Background of the Study ...................................................................................... 18 2.3 Train Automatic Stop Control (TASC) .......................................................................... 23 2.4 Rolling Stock Dynamic Behaviour ................................................................................ 30 2.5 Rolling Stock Braking Model ........................................................................................ 30 2.6 Summary ...................................................................................................................... 31 Chapter 3: Train Dynamic Modelling ................................................................ 39 3.1 Introduction ................................................................................................................. 39 3.2 Train Modelling ............................................................................................................ 40 3.3 Train Active Force Modelling ....................................................................................... 41 3.4 Train Brake Principles .................................................................................................. 43 3.5 Train Brake Modelling .................................................................................................. 54 3.6 TASC Modelling ............................................................................................................ 60 3.7 Brake Parameters ........................................................................................................ 65 3.8 Simulation Parameters ................................................................................................ 66 v 3.9 Conclusion .................................................................................................................... 67 Chapter 4: TASC Benchmark .............................................................................70 4.1 Introduction ................................................................................................................. 70 4.2 TASC Benchmarck ........................................................................................................ 72 4.3 Simulation Data Set ...................................................................................................... 92 4.4 Simulation Results and Comparison ............................................................................ 93 4.5 Conclusion .................................................................................................................... 95 Chapter 5: iTASC ..............................................................................................99 5.1 Introduction ................................................................................................................. 99 5.2 Reinforcement Learning ............................................................................................. 100 5.3 Q-Learning .................................................................................................................. 105 5.4 Fuzzy Double Q-Learning ........................................................................................... 108 5.5 iTASC Closed Control Loop ......................................................................................... 112 5.6 Simulation Results ...................................................................................................... 116 5.7 Conclusion .................................................................................................................. 120 Chapter 6: Conclusions ................................................................................... 124 6.1 Summary .................................................................................................................... 124 6.2 The Main Contribution ............................................................................................... 126 6.3 Future Research Directions ........................................................................................ 126 Bibliography ....................................................................................................