Railway Track Circuits Research Articles

Fault prediction of railway track circuit based on machine learning

Fault prediction of railway track circuit based on machine learning

Fault Prediction of Railway Track Circuit Based on Machine Learning

Fault Prediction of Railway Track Circuit Based on Machine Learning

A Study on the High Reliability Audio Target Frequency Generator for Electronics Industry

The frequency synthesizer performs a simple function of generating a desired frequency by manipulating a reference frequency signal, but stable and precise frequency generation is essential for reliable operation in mechanical equipment such as communication, control, surveillance, medical, and commercial fields. Frequency synthesis, which is commonly used in various contexts, has been used in analog and digital methods or hybrid methods. Especially in the field of communication, a precise frequency synthesizer is required for each frequency band, from very low-frequency AF (audio frequency) to high-frequency microwaves. The purpose of this paper is to design and implement a highly reliable frequency synthesizer for application to a railway track circuit systems using AF frequency only with the logic circuit of an FPGA (field programmable gate array) without using a microprocessor. Therefore, the development trend of analog, digital, and hybrid frequency synthesizers is examined, and a method for precise frequency synthesizer generation on the basis of the digital method is suggested. In this paper, the generated frequency generated by applying the digital frequency synthesizer using the ultra-precision algorithm completed by many trials and errors shows the performance of generating the target frequency with an accuracy of more than 99.999% and a resolution of mHz, which is much higher than the resolution of 5 Hz in the previous study. This highly precise AF-class frequency synthesizer contributes greatly to the safe operation and operation of braking and signaling systems when used in transportation equipment such as railways and subways.

Neural Network-Directed Detection and Localization of Faults in Railway Track Circuits: An Application of Dempster-Shafer Theory

Neural Network-Directed Detection and Localization of Faults in Railway Track Circuits: An Application of Dempster-Shafer Theory

Research on Calculation of Rail Self-Impedance of Track Circuit Based on Partial Element Equivalent Circuit

The self-impedance of the steel rail, as the signal transmission medium in the electrified railway track circuit, has a direct impact on the track circuit’s transmission performance. The finite element method is the most common method for calculating rail impedance, although it has a number of drawbacks, including a complicated model, a long computation time, and poor accuracy. The partial element equivalent circuit (PEEC) approach is used in this paper to provide a method for determining rail self-impedance. Firstly, the rail equivalent method is determined by analyzing the physical model of the rail. Considering the skin effect, the PEEC model of the rail is established. The internal impedance of the rail can be obtained by solving the equivalent circuit. The external impedance considering the influence of the earth is calculated by the Carson impedance calculation formula, which is processed by the segmented linear approximation method. The rail’s self-impedance is determined using the two procedures together. Finally, the actual measurement data verified the PEEC method to calculate the rail impedance. Compared with the finite element method (FEM), the calculation accuracy of the PEEC method is higher. The current frequency, the height of the rail from the ground, and the earth’s conductivity impact on the rail’s self-impedance are analyzed. The results show that the PEEC technique can be used to calculate the rail’s self-impedance and that the impact of current frequency, rail height above the ground, and ground conductivity on the rail’s self-impedance may be accurately represented. The self-impedance computation of the track circuit provides a theoretical basis.

Simulation on adjacent line mutual interference of high-speed railway track circuit

As the density of the high-speed railway network continues to increase, the problem of electromagnetic interference on adjacent lines has become increasingly prominent. This paper focuses on the electromagnetic interference of adjacent lines caused by rail and line in the signal transmission process of the high-speed rail track circuit. Firstly, complete the establishment of the four-terminal network model of the ZPW-2000A track circuit system and the cab signal entry current crosstalk model, calculation of interference voltage under different parallel length of signal frequency. Then the interference factors and coupling mechanism of adjacent lines are analysed to realize calculation of interference amount. Finally, according to the sensitivity index of the cab signal, the maximum parallel length of adjacent sections is given respect, and the interference protection suggestions of adjacent lines are put forward. The research work of this paper provides a theoretical basis for suppressing the interference of adjacent lines and guarantees the safe and efficient operation of high-speed trains.

Identification and Localization of Track Circuit False Occupancy Failures Based on Frequency Domain Reflectometry.

Railway track circuit failures can cause significant train delays and economic losses. A crucial point of the railway operation system is the corrective maintenance process. During this operation, the railway lines have the circulation of trains interrupted in the respective sector, where traffic restoration occurs only after completing the maintenance process. Depending on the cause and length of the track circuit, identifying and solving the problem may take a long time. A tool that assists in track circuit fault detection during an inspection adds agility and efficiency in its restoration and cost reduction. This paper presents a new method, based on frequency domain reflectometry, to diagnose and locate false occupancy failures of track circuits. Initially, simulations are performed considering simplified track circuit approximations to demonstrate the operation of the proposed method, where the fault position is estimated by identifying the null points and through non-linear regression on signal amplitude response. A field test is then carried out in a track circuit approximately 1500 m long to validate the proposed method. The results show that the proposed method can identify and estimate the fault location due to a short circuit between rails with high accuracy.

Railway Track Circuit Signal State Check Using Object Detection

The track circuit is widely used in the railway network for safety, and the corresponding track circuit equipment is laid almost every railway station, which provides an extremely important information service for the safe driving of the train. In this paper, we proposed a two-phase detection algorithm for the state of the signal equipment of the track circuit, which is used for automatic safety detection of the status of the track circuit signal equipment in the railway signal room. Compared with the traditional inspection method of inspection workers, our proposed detection algorithm of signal state greatly improves the efficiency of security inspection, and in the experimental results, the proposed method outperforms other methods in different situations.

Influence of railway line characteristics in inductive interference on railway track circuits

This study firstly presents an algorithm for the study of the 50–60 Hz inductive electromagnetic interference produced by a High Voltage power line on nearby not parallel railway track circuits used for signalling purposes; secondly the algorithm is used for a sensitivity analysis relevant to the level of generated electromagnetic interference depending on the characteristics of the railway line (electrified/not electrified, single/double track) and with reference to the state of rails insulation from the soil.

Software Design of a Railway Signal Monitoring System based on Optical Fiber Sensing

The current railway track circuit monitoring system is prone to disturbances that can result in accidents. Meanwhile, basic signaling equipment is slow and cannot achieve satisfactory real-time data acquisition speed. This study aims to solve the aforementioned problems by designing an online monitoring and management platform for railway signal infrastructure, which is based on the graphical programming language LabVIEW. Online monitoring and management of railways’ basic signaling equipment allow real-time collection and communication of various signal equipment data. These processes also enable signal processing, chart display, acousto-optic alarm, user authority management, data storage, data query analysis, and report printing. The test results show that the LabVIEW-based basic signaling equipment for monitoring and managing railway systems can transmit data correctly and steadily, thereby resulting in convenient and ideal operation.

Application of multifractal detrended fluctuation analysis in fault diagnosis for a railway track circuit

The outdoor equipment failures of track circuits are usually not easy to be detected. In addition, the location of outdoor equipment failures can cause trouble for on-site maintainers. To solve the...

Analysis of disturbing effect of 3 kV DC supplied traction vehicles equipped with two-level and three-level VSI on railway signalling track circuits

Abstract Electric traction vehicles cooperating with a 3kV DC traction system and equipped with drive systems based on voltage source inverters are the most significant sources of disturbances for a railway signalling system. Every traction vehicle to be authorised for operation on railway lines must fulfil the limits imposed on current harmonics magnitudes and those provided by railway operators. The solution introduced for prototypes of most modern traction drives is to replace the two-level inverters with three-level topology. Therefore, it is essential to establish the influence of the new solution on the railway signalling system. This paper presents a comparative analysis between simulation results delivered for two and three-level traction drive system regarding generation of disturbing current harmonics. Two types of VSI modulation techniques were taken under consideration: sinusoidal PWM (SPWM) and a new one, proposed by the authors, based on selective harmonic elimination (SHE). Furthermore, the authors presented application of one of the SHE based optimization techniques for shaping the EMU’s (electric multiple unit) DC side input current harmonics spectrum in order to meet the required limits. The described technique is based on off-line generation of a set of solutions for each of the VSI operating points and selection of the best solution for the assumed criteria. The applied simulation models and the concept of SHE control were verified in a laboratory by means of a low-power drive stand. Using the three-level inverter in traction drives system results in less current harmonics than using two-level topology without modification of the modulation technique. Thus, it does not guarantee fulfilling all limits assumed in this paper. The proposed modulation technique allows for fulfilling the limits, and the technical implementation of the proposed technique in a traction drive system will be considered in future studies.

Fault diagnosis using spatial and temporal information with application to railway track circuits

Adequate fault diagnosis requires actual system data to discriminate between healthy behavior and various types of faulty behavior. Especially in large networks, it is often impracticable to monitor a large number of variables for each subsystem. This results in a need for fault diagnosis methods that can work with a limited set of monitoring signals. In this paper, we propose such an approach for fault diagnosis in networks. This approach is knowledge-based and uses the temporal, spatial, and spatio-temporal network dependencies as diagnostic features. These features can be derived from the existing monitoring signals; so no additional sensors are required. Besides that the proposed approach requires only a few monitoring devices, it is, thanks to the use of the spatial dependencies, robust with respect to environmental disturbances. For a railway track circuit example, we show that, without the temporal, spatial, and spatio-temporal features, it is not possible to identify the cause of a detected fault. Including the additional features allows potential causes to be identified. For the track circuit case, based on one signal, we can distinguish between six fault classes.

Geomagnetic Storms’ Influence on Intercity Railway Track Circuit

Geomagnetic storms can cause earth surface potentials (ESPs) in the ground. ESP produces geomagnetically induced current (GIC) in a loop which is made up by rails and ground. If GIC flows into intercity railway track circuit, it will threaten the normal operation of track circuit. The reason that geomagnetic storms invade the track circuit was analyzed, and then how GIC affects the characteristics of choke transformers, was found. The calculation method of GIC according to a simulation based on the GIC flow path in the track circuit was built. Electromagnetic system model of choke transformer and track relay were designed in Maxwell software to get the magnetic flux density distribution of them. The results show that GIC values of 2.4 A can bring about serious direct current bias of choke transformers and cause the terminal voltage of track relay to decrease, resulting in relay malfunction. The numerical calculation results show that geomagnetic storms will interfere with intercity railway track circuit, which is in accordance with some phenomenon happened in some rail tracks. This method proves geomagnetic storms’ influence on intercity railway track circuit and attentions should be paid to this influence.

Railway Track Circuit Fault Diagnosis Using Recurrent Neural Networks.

Timely detection and identification of faults in railway track circuits are crucial for the safety and availability of railway networks. In this paper, the use of the long-short-term memory (LSTM) recurrent neural network is proposed to accomplish these tasks based on the commonly available measurement signals. By considering the signals from multiple track circuits in a geographic area, faults are diagnosed from their spatial and temporal dependences. A generative model is used to show that the LSTM network can learn these dependences directly from the data. The network correctly classifies 99.7% of the test input sequences, with no false positive fault detections. In addition, the t-Distributed Stochastic Neighbor Embedding (t-SNE) method is used to examine the resulting network, further showing that it has learned the relevant dependences in the data. Finally, we compare our LSTM network with a convolutional network trained on the same task. From this comparison, we conclude that the LSTM network architecture is better suited for the railway track circuit fault detection and identification tasks than the convolutional network.

A novel approach in the measurement of high frequency disturbances from very large electrical systems

This paper demonstrates the feasibility of an interactive distributed measurement system having the capability of wireless triggering and time synchronisation for the purpose of detection, measurement and location of disturbances from very large electrical systems. System design, laboratory testing and preliminary site trials are discussed. Examples of how the system might be used are included. The first example relates to railway track circuit monitoring; the 2nd example relates to multi ended PD monitoring for insulated power cables; third example relates to radiometric partial discharge monitoring in substations and the last example relates to power quality monitoring and phasor measurements.

Development and performance analysis of a novel impedance bond for railway track circuits

The ZPW-2000 track circuit is the dominant track circuit system used in China. On standard plain line track it is used as a jointless track circuit where ‘tuned zones’ are used to separate adjacent tracks operating at different frequencies. Owing to the complexities of station layouts it is not possible to use the ZPW-2000 as a jointless track circuit within stations, so a solution incorporating mechanical joints is commonly used. The station environment is known to have high levels of electromagnetic interference, and such environments can cause interference in the track circuit resulting in signal degradation and failure. An integrated solution that allows the ZPW-2000 track circuit to be used dependably in jointed operation that is able to cope with the electromagnetic environment found in stations is therefore required. In this study, a solution based on impedance bonds is developed to alleviate interference problems with the ZPW-2000 in harsh electromagnetic environments. The study presents an innovative design of impedance bond incorporating an air gap transformer and a double function filter circuit. The impedance bond was found to have an impedance of below 0.01 Ω at the resonant frequency of 50 Hz, and in excess of 17 Ω at other signal frequencies. The impedance bond is shown to eliminate interference while meeting the requirements of signal transmission on rail tracks. In this study, both theoretical analysis and the results of laboratory tests are presented.

Partially supervised Independent Factor Analysis using soft labels elicited from multiple experts: application to railway track circuit diagnosis

Using a statistical model in a diagnosis task generally requires a large amount of labeled data. When ground truth information is not available, too expensive or difficult to collect, one has to rely on expert knowledge. In this paper, it is proposed to use partial information from domain experts expressed as belief functions. Expert opinions are combined in this framework and used with measurement data to estimate the parameters of a statistical model using a variant of the EM algorithm. The particular application investigated here concerns the diagnosis of railway track circuits. A noiseless Independent Factor Analysis model is postulated, assuming the observed variables extracted from railway track inspection signals to be generated by a linear mixture of independent latent variables linked to the system component states. Usually, learning with this statistical model is performed in an unsupervised way using unlabeled examples only. In this paper, it is proposed to handle this learning process in a soft-supervised way using imperfect information on the system component states. Fusing partially reliable information about cluster membership is shown to significantly improve classification results.

Fault diagnosis of a railway device using semi-supervised independent factor analysis with mixing constraints

Independent factor analysis (IFA) defines a generative model for observed data that are assumed to be linear mixtures of some unknown non-Gaussian, mutually independent latent variables (also called sources or independent components). The probability density function of each individual latent variable is modelled by a mixture of Gaussians. Learning in the context of this model is usually performed within an unsupervised framework in which only unlabelled samples are used. Both the mixing matrix and the parameters of latent variable densities are learned from the observed data. This paper investigates the possibility of estimating an IFA model in a noiseless setting when two kinds of prior information are incorporated, namely constraints on the mixing process and partial knowledge on the cluster membership of some training samples. Semi-supervised or partially supervised learning frameworks can thus be handled. The investigation of these two kinds of prior information was motivated by a real-world application concerning the fault diagnosis of railway track circuits. Simulated data, resulting from both these applications, are provided to demonstrate the capacity of our approach to enhance estimation accuracy and remove the indeterminacy commonly encountered in unsupervised IFA, such as source permutations.

Availability analysis of railway track circuits

Railways are expected to operate with ever increasing availability. The availability of railway systems and subsystems influences the overall operational availability. As the track circuit is a key component of railway signalling and control, it can contribute significantly to the loss of availability of the railway system. One way to increase the availability of the track circuit is by implementing a proper maintenance policy. In this article, Petri-nets have been used to develop models for availability analysis of the track circuit for both time-based and condition-based maintenance. A sensitivity analysis has been performed to estimate the effect of maintenance parameters on availability performance using cost—benefit analysis.