Axle Counter Research Articles

Microcontroller-based track axle counter system design

Abstract Axle counting technology is an extremely important part of many aspects in ensuring the safety of railroad operation. Axle counting equipment is set up on the railroad tracks, and through the operation of sensors, it detects the trains that drive into the train operating area where the axle counting equipment is arranged. A common axle counting system uses a detection device that utilizes a wheel sensor that senses the movement of the wheel cutting through magnetic lines of inductance causing a change in the magnetic field within the zone. This paper introduces a track axle counter system, the system will be a microcontroller as the core, the use of ultrasonic detection in the train interval of the train wheel distance changes, instead of the existing axle counting system using wheel sensors to sense the electromagnetic signals generated by the wheels, to achieve the axle counting and counting function, so as to determine the track occupancy.

A deep learning-based approach for axle counter in free-flow tolling systems

Enhancements in the structural and operational aspects of transportation are important for achieving high-quality mobility. Toll plazas are commonly known as a potential bottleneck stretch, as they tend to interfere with the normality of the flow due to the charging points. Focusing on the automation of toll plazas, this research presents the development of an axle counter to compose a free-flow toll collection system. The axle counter is responsible for the interpretation of images through algorithms based on computer vision to determine the number of axles of vehicles crossing in front of a camera. The You Only Look Once (YOLO) model was employed in the first step to identify vehicle wheels. Considering that several versions of this model are available, to select the best model, YOLOv5, YOLOv6, YOLOv7, and YOLOv8 were compared. The YOLOv5m achieved the best result with precision and recall of 99.40% and 98.20%, respectively. A passage manager was developed thereafter to verify when a vehicle passes in front of the camera and store the corresponding frames. These frames are then used by the image reconstruction module which creates an image of the complete vehicle containing all axles. From the sequence of frames, the proposed method is able to identify when a vehicle was passing through the scene, count the number of axles, and automatically generate the appropriate charge to be applied to the vehicle.

Passive magnetic coil design for electromagnetic interference evaluation of axle counters

Measurement of magnetic fields near the railway tracks is crucial to ensure compatibility with the operation of axle counters. According to EN 50592 standard, the magnetic field is detected with a passive magnetic coil and an oscilloscope. From previous studies, in general, there has been no in-depth analysis of how the choice of coil winding parameters could affect the coil output voltage, which then affect the measurement sensitivity, in particular the coil design based on the standard and it is applicability for electromagnetic interference (EMI) evaluation of axle counters. Therefore, this paper will explore the design of a passive magnetic coil to obtain the optimum coil output voltage within the frequency range. Simulations showed that for 10-100 kHz and 100 kHz–1.3 MHz range, the optimum number of turns happened at 60-100 and 15-60 turns, respectively. Based on that, two example coils had been built. Simulations and measurements of their frequency response were in good agreement, with a deviation less than 1.0 dB.

Axle Counter Grounding System on The PPI Madiun Railway Using the Wenner Method

Axle counter is a railway detection equipment producing wave frequencies to count the number of axles passing over the track. The existence of a mismatch between the initial and final count numbers usually leads to a red signal and this can prevent the formation of a travel route. The components of axle counter are often damaged by lightning strikes both directly and through the distribution of excessive currents due to a poor grounding system. However, these excessive currents can be safely grounded without damaging the components through the application of a good grounding system. Therefore, this research aimed to plan an effective grounding system to anticipate the incidents using the Wenner method. Some requirements such as soil type, depth, and electrode rod diameter were used in the process to determine the appropriate resistance value. The design was made based on the simulations that closely resembled real field conditions using Aspix software and grounding resistance values were also measured directly on the field to determine the discrepancies between the planning and actual conditions.

Design of Automatic Truck Axle Counter Using Deep Learning on NVIDIA Jetson Nano

Design of Automatic Truck Axle Counter Using Deep Learning on NVIDIA Jetson Nano

Hunting Network Anomalies in a Railway Axle Counter System.

This paper presents a comprehensive investigation of machine learning-based intrusion detection methods to reveal cyber attacks in railway axle counting networks. In contrast to the state-of-the-art works, our experimental results are validated with testbed-based real-world axle counting components. Furthermore, we aimed to detect targeted attacks on axle counting systems, which have higher impacts than conventional network attacks. We present a comprehensive investigation of machine learning-based intrusion detection methods to reveal cyber attacks in railway axle counting networks. According to our findings, the proposed machine learning-based models were able to categorize six different network states (normal and under attack). The overall accuracy of the initial models was ca. 70-100% for the test data set in laboratory conditions. In operational conditions, the accuracy decreased to under 50%. To increase the accuracy, we introduce a novel input data-preprocessing method with the denoted gamma parameter. This increased the accuracy of the deep neural network model to 69.52% for six labels, 85.11% for five labels, and 92.02% for two labels. The gamma parameter also removed the dependence on the time series, enabled relevant classification of data in the real network, and increased the accuracy of the model in real operations. This parameter is influenced by simulated attacks and, thus, allows the classification of traffic into specified classes.

Creation of Signals Database for the Development of Speed Estimation in an Axle Counter System

The article presents the process of creation of a signals database for the development of a train speed-estimation method for an axle counter system. In the article the authors present the need for information about the train speed on the railway lines and the possible applications for which the information about the train speed may be used, as well as address the concerns related with the evaluation of the information in axle counter systems. The main goal of the paper is to present the creation process of an axle counter signals database and how to emulate the real signals using the laboratory-obtained ones. A database that has been created for a specific wheel detector is available on request. It contains a variety of signals that are necessary for the development and tests of wheel detector algorithms, in particular the estimation of train speed. Signals were generated for the most commonly used rail profile in Europe and the wheels that are defined in the technical specification of interoperability. Furthermore, the signals were transformed to emulate various speeds, the possible accelerations and to include the disturbance observed in the field.

The Effectiveness of Distributed Acoustic Sensing (DAS) for Broken Rail Detection

Broken rails remain one of the main causes of railway accidents despite improved rail quality and inspections. Today, signalling system with track circuits are often used to detect broken rails, however new signalling systems such as the European Train Control System (ETCS) with axle counters are replacing track circuits and therefore new methods are needed to detect broken rails. One promising technology is distributed acoustic sensing (DAS). The best DAS analytical techniques to show the position of the rail break are gradient analysis, convolution using the train consist and 2 D sinusoidal convolution. This paper describes field tests carried out on DAS to evaluate its ability to detect broken rails and the moment when rails break. The testing showed that DAS has good potential for detecting broken rails in both scenarios. Especially helpful is the ability of DAS to identify the moment of rail breakage and its potential for determining the break’s location on open lines. Recommendations for further research include testing these qualities in more detail and considering how DAS could be efficiently combined with new signalling systems.

Toward the Future Generation of Railway Localization Exploiting RTK and GNSS

Smart sensors have become pervasive in railway transportation applications, particularly in Europe where digital technologies are increasingly being applied to the railway signalling field. In the future, safety-critical track-side train detection equipment, such as track circuits and axle counters, will be eliminated in favor of an accurate position estimate supplied by the train. However, the best approach to calculate an accurate position estimate remains an open research question, especially due to the high availability and reliability required. This paper describes two static experiments performed with a GNSS module, which demonstrate that the real-world accuracy achievable with GNSS and Real Time Kinematic (RTK) alone is not sufficient for safety-critical applications, meaning further complementary sensors are required. Furthermore, a custom sensor node containing a GNSS module with RTK and an Inertial Measurement Unit (IMU) has been used to acquire several data sets from an operating passenger train during dynamic tests on a railway line between Formigine and Modena, in Emilia-Romagna, Italy. These labeled GNSS and IMU data have been made freely available to the scientific community. The positioning accuracy of the GNSS and RTK measurements is evaluated, providing an in-depth study of the localization error and satellite coverage on the entire route. We demonstrate, with experimental evaluation, that centimeter accuracy (1.9 ± 0.8 cm) is achievable under favorable static conditions, while accuracy can deteriorate to 8m with RTK in urban scenarios with many reflections and poor sky view, worse than with GNSS alone. Under controlled conditions we show that shielding the GNSS receiver without RTK with a grounded metal plate causes a reduction in accuracy from 0.80 ± 0.04m to 3.70 ± 0.55m in the least and most shielded case respectively. Our dynamic tests on a train show that although at least meter-level accuracy (1.08 ± 1.30 m) is achievable with GNSS and RTK alone under dynamic conditions, a sensor fusion approach is necessary to accurately localize trains when GNSS conditions are poor or GNSS is unavailable.

차축카운터시스템 적용에 따른 위험분석 및 평가활동 연구

최근 들어 철도신호시스템분야에서 중요한 이슈로 부각되고 있는 시스템 품질보증 방안으로 국제규격(IEC)에 부합하는 SIL인증체계를 활용한 시스템개발 방법이 많이 사용되고 있다. 차축카운터 장치는 불연속 궤도회로를 구성하는 한 방법으로 CBTC열차제어시스템의 상용화가 이루어지면서 선로전환기를 포함한 궤도회로의 구성 등에 필요성이 대두되고 있다. 일반적으로 철도신호에서 연동장치는 SIL4 수준의 안전성을 요구하는 장치로 연동장치에 열차의 유무를 제공하는 궤도회로 또한 매우 중요한 장치로 불연속 궤도회로를 구성하는 차축카운터 시스템 또한 SIL4의 안전성을 요구한다. 특히 차축카운터시스템의 핵심 요소인 차축카운터센서의 위험원을 분석하고, 위험을 저감할 수 있는 방안을 제시하였으며, 차축카운터시스템의 정량적인 안전성 목표를 달성하기 위한 주요기능의 FMEDA를 수행하였다.

Electromagnetic interference measurement for axle counters light rapid transit railway in Indonesia

The measurement and analysis of electromagnetic interference (EMI) from light rapid transit (LRT) axle counters against magnetic field interference in Indonesia has been carried out. The low-cost magnetic sensors were developed according to the British Standard (BS) EN 50592:2016. The measurement setup and magnetic field limit were based on the British Standard EN 50592:2016 and ERA/ERTMS/033281 standard. Two frequency range of the measurements, lower and higher frequencies with two different train running mode, acceleration mode and deceleration mode were applied in this research. The results in lower frequency range (10 to 100 kHz) were very close to the limit value in both acceleration and deceleration mode, especially at the 30 to 50 kHz for the y and z directions. Although there may possibly magnetic interference at low frequencies, most of the magnetic field emissions were still in acceptable range.

On a method for ensuring functional safety of a system with single-channel information processing

The paper Aims to reduce the cost of onboard train control systems by using an architecture with a single-channel source of information (in this case, axle counters) and a two-channel receiver of information (in this case, an on-board control system) instead of the conventional architecture, whereas the generator and receiver are to have at least two channels. Additionally, in order to ensure the system’s safety, the failure detection mechanism embedded in the most common multichannel architecture that involves comparing the outputs of the onboard unit’s channels is complemented by software verification algorithms that enable a SIL4-compliant level of correct failure detection of the single-channel device (in this case, an axle counter). This level is primarily characterized by the quantitative indicator “probability of correct detection” and achieving the goal requires calculating the acceptable and, at the same time, achievable range of this probability and the performance parameters of the verification algorithms, of which it is a function. Methods. The paper shows two safety models of an onboard train control system, i.e., the conventional architecture with two-channel generating and receiving devices and the architecture with a single-channel source and a two-channel receiver of information. The graph models feature similar states and only differ in terms of the model parameters. By applying the topological method [1] to the conditions of the problem, within both models, formulas were derived for calculating the mean time to hazardous failure, rate and probability of hazardous failures. Input values were identified, including the probabilities of correct detection of failure of the on-board system and axle counter, the values of those safety indicators were calculated, allowing to attribute the system to one of the four discrete safety integrity levels. Results. The paper defines the probabilistic performance indicators of failure detection software and hardware for an architecture with a single-channel source and a two-channel receiver of information. Indicator definition involves setting maximum permissible values that enable the quantitative safety indicators (mean time to hazardous failure, rate and probability of hazardous failures) not worse than those of a conventional architecture with twochannel generating and receiving devices. The efficiency parameters that are the most safetycritical due to their significant effect on correct failure detection (in this case, the axle counter) are identified. The findings show that it is possible to reduce hardware-related costs without compromising compliance with the safety requirements when using single-channel sources (in this case, axis counters) and two-channel receivers of information (in this case, an on-board control system) that feature software enabling an appropriately high level of correct failure detection (in this case, of an axle counter).

Simulation Modeling of Switching over Current of Circuit Breaker in Intercity Train

The main interference source of axle counter is the over-current caused by the operation of circuit breaker by intercity train. This paper focuses on the simulation modeling technology of switching over-current of intercity train circuit breaker. Firstly, the mechanism of the interference when the circuit breaker is closed is studied by theoretical analysis; Then, the interference source model is established when the circuit breaker is closed, and the equivalent circuit model of interference path including vehicle body, vehicle body grounding system, traction network and high-voltage cable is obtained through calculation and analysis. The current of transformer primary grounding wire is measured on the actual vehicle, and the accuracy of the model is verified by comparing with the simulation model. Finally, the spectrum characteristics of the interference current in the rail are obtained by Fourier transform. In this paper, a simulation modeling method for analyzing the operating overcurrent of intercity vehicle circuit breaker is proposed, which can effectively evaluate the magnitude of the interference current generated by closing the circuit breaker into the rail, and provide a research basis for the follow-up study of the interference characteristics of the radiation field of rail current on the trackside axle counter.

Implementation of the test method for trackside emissions of magnetic disturbances from rolling stock according to ERA/ERTMS/033281

The aim of the work presented in this article was to made and implement original computer software made in the LabVIEW environment. That program automate the measurement of emissions of magnetic disturbances coming from rolling stock. It is dedicated for oscilloscope card and RSAL 5340, RSAH 5324 rolling stock antennas for axle counter. The indicated algorithms of proceeding coming directly from the standards, additional own methods of fast data analysis was made. Communication between the measurement cards and computer using USB with self-power USB hab was used. The softawer is fully compatible with the requirements contained in the ERA/ERTMS/033281 [6].

Об определении мест установки счетчиков осей в горловинах станций

The use of axle counters makes it possible to automate the processes of station car model formation and renewal. The existing approaches to define installation sites for axle counters at station necks, fixed by regulatory documentation, are in the location of counting points next to all insulating joints of track chains that leads to equipment redundancy. At the same time, the application of axle counters qua the only control device of track freedom faces a number of obstacles among which we can outline the lack of technical means of rail thread integrity control, the need to apply additional devices for organizing the transmission of locomotive automatic signaling codes to rolling stock etc. In this paper, an approach is considered that allows to set axle counters not at edges of each track chain but at single points which provide for the control of technological process accomplishment. It is shown that the refuse from attachment of axle counters to track chain edges allows to reduce the number of needed equipment. The comparison of track chains and axle counters in part of equipment reliability and this equipment impact on station operation technological process is carried out.

ТЕХНОЛОГИЯ МОНИТОРИНГА ПОДВИЖНОГО СОСТАВА НА ОСНОВЕ ДИСТАНЦИОННОГО АКУСТИЧЕСКОГО ЗОНДИРОВАНИЯ

The functionality of information-measuring systems for remote detection of faulty parts of the undercarriage of cars in motion is considered. The features of the use of fiber-optic cables laid along the railway tracks as sensors for detecting defects in the rolling stock and infrastructure of railway lines are evaluated. The functional features of the influence of external physical influences impact on the length of the reflected wave fiber Bragg gratings. The possibility of using remote acoustic sensing to determine defects in parts and assemblies of rolling stock while the train is in motion is shown, the possibilities of joint application of the remote acoustic sounding technology with axle counters and a wheel passage registration system are noted. An assessment of the conditions for ensuring the operability and adjustment of a distributed fiberoptic line of sensors for a railway section is proposed. A scheme for the planned placement of remote acoustic sounding devices at the training ground of the Belarusian Railways has been developed. The possibility of immediate detection of defective wheelsets with a maximum allowable value of sliders exceeding 1.0 mm, as well as a break in the side frame of a wagon bogie to prevent dangerous emergencies, has been established. A method is proposed for continuous monitoring of the technical condition of rolling stock in motion, providing increased control over the serviceability of parts and units of the rolling stock.

UNIFIED VERIFICATION METHOD OF ELECTROMAGNETIC COMPATIBILITY BETWEEN ROLLING STOCK AND TRAIN DETECTION SYSTEMS

Purpose. Axle counters are more and more often applied in train detection systems. The wheel sensor is a main part of each axle counter system. In parallel, more and more complex railway vehicles, especially traction ones, are a potential source of interferences influencing the operation of these train detection systems. It is the reason to verify the electromagnetic compatibility (EMC) between the signalling equipment, particularly train detection systems and new vehicles in the process of obtaining the permission for their exploitation. The measurement of interfering magnetic fields generated by vehicles is one of tests to be carried out. Methodology. For the simplification and unification purpose of the applied interference test methods the EN 50238 standard and TS 50238-3 technical specification were developed. The specification defines unified testing procedures. However, it is necessary to verify if it may replace different testing methods used in particular European states. It is the goal of the European research project financed from the TEN-T network resources. Findings and originality. This project is part of the larger project of facilitation and speeding up the ERTMS system deployment. One of nine measurement campaigns planned in the frame of this project was conducted in Poland by Railway Research Institute.

Application of Convolutional Neural Networks for Recognizing Long Structural Elements of Rails in Eddy-Current Defectograms

To ensure traffic safety of railway transport, non-destructive test of rails is regularly carried out by using various approaches and methods, including eddy-current flaw detection methods. An automatic analysis of large data sets (defectograms) that come from the corresponding equipment is an actual problem. The analysis means a process of determining the presence of defective sections along with identifying structural elements of railway tracks in defectograms. This article is devoted to the problem of recognizing images of long structural elements of rails in eddy-current defectograms. Two classes of rail track structural elements are considered: 1) rolling stock axle counters, 2) rail crossings. Long marks that cannot be assigned to these two classes are conditionally considered as defects and are placed in a separate third class. For image recognition of structural elements in defectograms a convolutional neural network is applied. The neural network is implemented by using the open library TensorFlow. To this purpose each selected (picked out) area of a defectogram is converted into a graphic image in a grayscale with size of 30 x 140 points.

Comparison of Filtering Methods for Enhanced Reliability of a Train Axle Counter System.

This paper presents signal filtering methods that can be effectively applied to train detection systems based on the axle counter systems that are currently in operation for train detection and provide information on the unoccupied status of railway tracks and turnouts. Signals from the wheel detectors contain noise, may be impulsive and time-varying, which means that even for the same train, the signals from the following wheels may be different. A problem appears when already homologated hardware (axle counter system) is working in a harsh environment, exposed to disturbances whose parameters significantly exceed standard thresholds. Despite this, the system must continue to provide reliable information. The authors present research on the application of such filters as median, Savitzkey-Golay, and moving average which can be implemented in the equipment currently in use under specific constraints (e.g., limited computational resources). The research results show that appropriately adjusted filters, for example, in terms of type and window size, increase the signal quality and thereby provide reliable information about passing trains, as well as enhance the availability and safety of the axle counter system performance.

A methodology for the design of sections block length on ETCS L2 railway networks

This paper presents an analytical-based methodology that computes the optimal length of block sections and the marker boards’ location following headway requirements, with the lowest amount of signalling equipment, for an ETCS L2 railway networks.It is applied to the Danish Fjernbane Infrastructure East project, which aims at replacing the existing signalling system with a new one based on ETCS Level 2. Starting from track layout, rolling stock information and headway scenario, and knowing the trains features, an easy backward calculation, using OpenTrack tool, defines the first signalling equipment position (i.e. Marker Boards, Axle Counter) to fulfil the headway requirements.The application to the main passenger and freight lines in Danish Fjernbane Infrastructure East area shows the significance of the proposed methodology able to define a robust signalling configuration which also provides a satisfying trade-off between total cost and railway operational performance.