No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
A feasibility study of train automatic stop control using range sensors
Abstract
Automatic train control plays a key role in improving the
efficiency and safety of train movements, as well as the riding comfort
of passengers. In Japan, train control systems have been successfully
implemented since 1980s. These systems are required to control the train
position and speed as accurately as possible. This is mostly dependent
on the axle generators and transponders. More specifically, the axle
generators measure the speed and moving distance from the reference
points specified by the transponders. However, the train control systems
using these devices still fail to achieve a correct train position, due
to skidding or slipping, until passing over reference points. This paper
focuses on the train automatic stop control (TASC), and presents a new
TASC system using a commercial range sensor instead of transponders so
that the train equiped with the system can detect its position
continuously
... To overcome the skidding and slipping problems related to axle generators and transponders in train correct positioning, Yoshimoto, Kataoka and Komaya [3] introduced a TASC which used range sensors. This method makes it possible for the train to get its position continuously while avoiding skidding and wheel diameter errors. ...
... = ( 1 + 1000 2 ). 2 (3)(4)(5)(6)(7)(8)(9)(10)(11) Where is the air resistance or wind effect (Newton); is train's weight (ton); is train's speed; ...
... The condition of rail in terms of being wet, oily or dry will affect the friction between rails and train wheels which will be captured in our model for TASC simulation by using (3)(4)(5)(6)(7)(8)(9)(10)(11)(12)(13) and (3)(4)(5)(6)(7)(8)(9)(10)(11)(12)(13)(14). Where: ...
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.
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.
... In latest year, new ATP or ATS technologies in railway signaling system are empowered by many applications such as range sensor for measuring the position of train continually [2]. ...
... In order to ensure safe speed of the train when passing a signal or possibility of omission driver to check passed signal status, the monitoring train speed is performed. The brake will be applied automatically by the ATP, if the driver fails to undertake its condition, [1,2,3,4,5,8,9,10,12]. Furthermore, there are some functions of the ATP such on avoiding the fore-back collision [1,7,10,11], assuring the train operation is safe by making interval between two trains [7], and preventing derailment due to over speed [10,14]. ...
... A lot of existing studies have addressed the TSP problem. For example, Yoshimoto et al. applied the predictive fuzzy control technology, which performs better parking accuracy by comparing with proportional-integral-derivative control method [5]. Yasunsbo et al. used fuzzy inference for automatic train parking control. ...
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.
... In all, although the accurate reference positioning devices are of great value for TASC [26], train control systems using them still fail to get correct continuous remaining distance for automatic, accurate and comfortable parking. As mixtures of on-board and wayside devices, range sensors [27] exploit the radar principle to obtain the accurate position continuously, while dedicated stopping measurement devices precisely detect stopping errors based on platform information [28]. However, these mixture devices need to update the existing infrastructure. ...
Balise is a popular wayside device to provide accurate location information for subway station parking by sending telegrams to passing trains. By craftily disturbing wireless signals of balise telegrams, this paper proposes three attacks which may make passengers fall and even cause injury. Concretely, the first attack is to jam telegrams such that balises can not be detected by a passing train; the second attack changes the location of transmitting telegrams by jamming and replaying; and the third attack is to change the total time of transmitting telegrams. All the attacks exploit the train localization mechanism such that a passing train localizes its position inaccurately and then takes improper control actions. Furthermore, since these attacks are independent, they can be launched at the same time to achieve advanced attacks. As the attacks do not require to tamper with the balises, they can be launched easily. Our simulations demonstrate the effectiveness of the proposed attacks. To defeat these attacks, the received telegrams need be verified by a train based on fidelity of telegram data.
... ATP has three functions, including automatic warning, braking curve supervision and train stopping, whereas ATS has only one functionan ATS when a stop signal is passed (Fenner 2002;Pachl 2009). In recent years, new technologies for both ATP and ATS have emerged that empower many applications in railway signalling systems, for example, using range sensors for continuously measuring the position of a train (Yoshimoto, Kataoka, and Komaya 2001). ...
Automatic train protection (ATP) is a vital part of the signalling system that prevents collisions between trains, especially on densely trafficked lines. Conventionally, ATP uses a transponder to communicate between an onboard train device and a trackside device. In Indonesia, ATP is not yet implemented and all trains are currently operated by drivers. It has now become a necessity to install ATP in Indonesia in order to protect train operations. However, as in many tropical and developing countries there are some environmental problems, especially heavy rain, as well as the theft of trackside equipment that influences performance. Installed trackside devices must therefore meet certain criteria such as low-cost configuration, minimalized devices on the track, ease of maintenance, etc. To address the necessity of ATP and to meet these criteria for trackside devices, we develop ATP using an infrared system. This type of ATP – the intermittent ATP system – consists of onboard devices and infrared sensors as trackside equipment. This approach to ATP offers a cost-effective solution and ensures the safety of train movements.
... Previous research has investigated the effects of platform screen doors on things such as particulate matter concentrations [5], emergency evacuation under crowded conditions [6], and acoustic characteristics [7]. Train stop detection in an environment without platform screen doors was previously investigated in several ways such as using range sensors [8], Doppler radar sensors [9], and stereo cameras [10,11]. Train stop detection in an environment with platform screen doors was introduced to improve the safety of platform screen doors [11][12][13][14][15]. ...
Precision stopping of an urban train at a railway station with platform screen doors is essential to passenger safety and timely revenue service. This paper presents a precision stopping measurement device to automatically detect the position error of an urban train at a railway station with platform screen doors; the device is used primarily for initial calibration during test runs before revenue service begins. The precision stopping measurement device that has been developed is composed of a platform module to detect the stopping error of the train using laser light, a vertical pattern to reflect the laser light, and an on-board module to record the stopping error automatically via wireless communication. The usefulness of the precision stopping measurement device presented here has been demonstrated using field tests with an actual Maglev train in Korea.
... However, the radio system has some drawbacks, especially in a short range wireless communication system, such as multipath fading, source of bandwidth limitation [15], and interference from other users [11][12][13]. Moreover, the radio system is very expensive [14] when installed in large numbers. On the other hand, radio based equipment is commonly installed on tracksides where the performance will potentially be influenced by pooling water and poor track maintenance in a country with a humid climate. ...
The conventional track to train communication is commonly using radio based equipment such as transponder or balise to transmit the data. However, there are some drawbacks of the conventional equipment, for example multipath fading, source of bandwidth limitation, and interference from other users. Moreover, the radio based equipment is very expensive when installed in large numbers. To address these problems, we propose infrared system for trackside to train communication system. Infrared system offers a transmission of data to train and it can be processed to obtain at least a train location. Infrared communication protocol provides practical wireless data communication for direct dedication configuration. Furthermore, on the pole configuration the infrared system provides an abundant bandwidth, an economically sensible, minimalized installation of equipment on the trackside and reliability for heavy rain environment. This paper concentrates on the communication function and measurement performance evaluation. The proposed trackside to train communication system covers about 6 meters between infrared receiver and infrared transmitter, whereas the half angle of the transmitter is set to 19.65^{\circ} and the receiver angle is 15^{\circ}.
... It monitors a train speed to ensure the train passes a signal with safe speed or to prevent a possibility of omission driver to check passed signal status. The brake will be applied automatically when the driver fails to do its condition [1][2][3][4][5][6][7][8][9][10]. To build communication between trackside and train, some devices are used such as mechanical devices, electrical contacts, electromagnetics and transponder [1], [11][12]. ...
Train speed control is a vital part of train protection to build safe movement at an operation track. There is a special condition of track that needs more attention to protect the train, for example in slope area. Moreover, in developing country with vandalism problem, it requires to install minimalized equipment on the trackside. In addition, in tropical country, on tracksides it will be potentially pooling water that influences to the performance of trackside equipment. To address these problems, we propose the train speed control for slope area using infrared system. By installing on the pole configuration, the system offers a less challenging, economically sensible, minimalized installation of equipment on the trackside and reliability for heavy rain environment. This paper concentrates on the controlling train speed and measurement performance evaluation in slope area. The proposed train speed control system can monitor and control the speed in sloping area with maximum 3.6% and controlled speed about 20 km per h.
Precision stopping of an urban train at a station is prerequisite before starting revenue service due to screen doors. Regulation for precision stopping of the urban train requires ±30 cm in general in Korea. Since there is no device to detect stopping error automatically, it takes long time to gather stopping error data at each station due to manual measurement using a ruler. In this paper, we present a principle and design of a precision stopping measurement device (PSMD) which can be easily used for error detection of precision stopping of urban trains. The PSMD developed in our laboratory uses a non-contact optical laser sensor installed at the platform to generate pulse signals from vertical black and white patterns attached on a train side. The number of the generated pulses is counted using a microcontroller, and then is sent to a notebook computer on the train via wireless RF communication. The performance of the PSMD is tested at the lab experimentally under indoor and outdoor environments.
For urban metro systems with platform screen doors, train automatic stop control (TASC) has recently attracted significant attention from both industry and academia. Existing solutions to TASC are challenged by uncertain stopping errors and the fast decrease in service life of braking systems. In this paper, we try to solve the TASC problem using a new machine learning technique and propose a novel online learning control strategy with the help of the precise location data of balises installed at stations. By modeling and analysis, we find that the learning-based TASC is a challenging problem, having characteristics of small sample sizes and online learning. We then propose three algorithms for TASC by referring to heuristics, gradient descent, and reinforcement learning (RL), which are called heuristic online learning algorithm (HOA), gradient-descent-based online learning algorithm (GOA), and RL-based online learning algorithm (RLA), respectively. We also perform an extensive comparison study on a real-world data set collected in the Beijing subway. Our experimental results show that our approaches control all stopping errors in the range of ±0.30 m under various disturbances. In addition, our approaches can greatly increase the service life of braking systems by only changing the deceleration rate a few times, which is similar to experienced drivers. Among the three algorithms, RLA achieves the best results, and GOA is a little better than HOA. As online learning algorithms can dynamically reduce stopping errors by using the precise location data from balises, it is a promising technique in solving real-world problems.
This paper is about the study for tracing the stopping point of train through modeling of multi-braking force based on information
of remaining distance in case that "slide (abrupt variation of deceleration)" occurs caused by external environmental factor,
not by normal breaking of train in the automated system. We worked on modeling the operation of our train by using and analyzing
its characteristic and adopted to "Daejeon Metro Line #1 ATO System", hereby completed the proper stopping point tracing.
Keywordsmulti-braking force-slide-slip-deceleration-ATO-stopping point
This paper presents three models – a linear model, a generalized regression neural network (GRNN) and an adaptive network based fuzzy inference system (ANFIS) – to estimate the train station parking (TSP) error in urban rail transit. We also develop some statistical indices to evaluate the probability of controlling parking errors in a certain range. By comparing modeling errors, the subtractive clustering method other than grid partition method is chosen to generate an initial fuzzy system for ANFIS. Then, the collected TSP data from two railway stations are employed to identify the parameters of the proposed three models. The three models can make the average parking errors under an acceptable error, and tuning the parameters of the models is effective in dynamically reducing parking errors. Experiments in two stations indicate that, among the three models, (1) the linear model ranks the third in training and the second in testing, nevertheless, it can meet the required reliability for two stations, (2) the GRNN based model achieves the best performance in training, but the poorest one in testing due to overfitting, resulting in failing to meet the required reliability for the two stations, (3) the ANFIS based model obtains better performance than model 1 both in training and testing. After analyzing parking error characteristics and developing a parking strategy, finally, we confirm the effectiveness of the proposed ANFIS model in the real-world application.
Automatic Driving System
- Masami Tobioka
Automatic Control Devices Applied an Expert System
- H Tainoshou
- Nakano
- Takada
- H Ikeda
- Ochiai
A Knowledge Engineering Approach to Train Automatic Stop Control
- H Itou
- H Morihara
- S Ikeda
- Araya