Railway Power Supply Research Articles

High-Speed Railway Pantograph-Catenary Anomaly Detection Method Based on Depth Vision Neural Network

A pantograph-catenary system (PCS) is an important part of the high-speed railway power supply system. The quality of the PCS determines the stability of the traction power supply quality of the train. Due to the interaction of the pantograph and the catenary, the uneven distribution of the contact points (CPT) of the pantograph and the contact wire can lead to the failure of the PCS. Therefore, it is necessary to monitor the status of the PCS by detecting contact points. However, the detection frame rate of existing methods is low and the detection accuracy still needs to be improved in complex backgrounds. To solve this problem, this paper proposes a deep visual neural network detection method. The proposed method is divided into two stages. In the first stage, a deep pantograph detection network (DPDN) is established to identify pantograph areas in different complex scenarios. In the second stage, the image visual feature extraction (IVFE) algorithm is used to detect the contact point between the pantograph and the catenary in real time in the pantograph area. Finally, the experimental results demonstrated the speed and the accuracy of the proposed method.

Разработка мобильного устройства диагностирования разрегулировок опор контактной сети

An important element of a railway power supply system is the contact lines, which performs the function of transmitting high electric currents from a contact wire through the high-current contact of the “electric rolling stock — current collector” system at specified speeds, regardless of weather conditions. The article deals with the factors leading to the defect of the catenary poles, and a method for controlling misalignment of the poles is proposed. The basic configuration settings of the proposed device before taking measurements are substantiated.

Droop control operation strategy for advanced DC converter-based electrical railway power supply systems for high-speed lines

Advanced DC converter-based electrical railway power supply systems are very promising power supply configurations for the electrification of high-speed lines. Their full controllable converter-based traction substations along with its continuous catenary, enable the reduction of power quality issues while providing an active power management. However, the power operation performance of these new configurations relies on the development of appropriate control systems. In this sense, this paper introduces a novel operation strategy based on a droop control scheme capable of adapting the power sharing between traction substations without any traffic information. The power operation performance of a simple and complex advanced DC converter-based system following the strategy proposed has been analyzed and compared with the conventional electrification approach. According to the results obtained, the operation strategy presented can adequately control the power flow in the railway grid for both scenarios.

DIFFERENTIAL-GAME MODEL OF INFORMATION PROTECTION FOR COMPUTER SYSTEMS OF TRANSPORT INFRASTRUCTURE

The article considers the reliability and protection of information of computer systems of transport infrastructure and describes the synthesis and analysis of differential game models and methods of modeling cyberattack processes on the server of computer information and diagnostic systems of the railway power supply distance. A unified differential-game model of the cyberattack process on the multi-task server of the information-diagnostic computer system of the lower level of the railway has been developed, which allows to obtain optimal strategies for information protection in cyberattacks. The results of modeling the cyberattack process are presented, to assess the integrated indicators of server security, using the optimal strategies for each of the functions. The appearance of the unified model of the computer information system is shown, and the graphs of the transient processes of the probability of the server being in a protected state and the probability of server failure for any of the functionalities are given.

Regina computer system for intelligent monitoring, diagnostics, and management of railway power supply systems

Regina computer system for intelligent monitoring, diagnostics, and management of railway power supply systems

Failure Analysis of the Headspan Suspension in the Railway Power Supply System

Failure Analysis of the Headspan Suspension in the Railway Power Supply System

Intelligent methods for improving the accuracy of prediction of rare hazardous events in railway transportation

The paperAimsto examine various approaches to the ways of improving the quality of predictions and classification of unbalanced data that allow improving the accuracy of rare event classification. When predicting the onset of rare events using machine learning techniques, researchers face the problem of inconsistency between the quality of trained models and their actual ability to correctly predict the occurrence of a rare event. The paper examines model training under unbalanced initial data. The subject of research is the information on incidents and hazardous events at railway power supply facilities. The problem of unbalanced data is expressed in the noticeable imbalance between the types of observed events, i.e., the numbers of instances.Methods.While handling unbalanced data, depending on the nature of the problem at hand, the quality and size of the initial data, various Data Science-based techniques of improving the quality of classification models and prediction are used. Some of those methods are focused on attributes and parameters of classification models. Those include FAST, CFS, fuzzy classifiers, GridSearchCV, etc. Another group of methods is oriented towards generating representative subsets out of initial datasets, i.e., samples. Data sampling techniques allow examining the effect of class proportions on the quality of machine learning. In particular, in this paper, the NearMiss method is considered in detail.Results.The problem of class imbalance in respect to the analysis of the number of incidents at railway facilities has existed since 2015. Despite the decreasing share of hazardous events at railway power supply facilities in the three years since 2018, an increase in the number of such events cannot be ruled out. Monthly statistics of hazardous event distribution exhibit no trend for declines and peaks. In this context, the optimal period of observation of the number of incidents and hazardous events is a month. A visualization of the class ratio has shown the absence of a clear boundary between the members of the majority class (incidents) and those of the minority class (hazardous events). The class ratio was studied in two and three dimensions, in actual values and using the method of main components. Such “proximity” of classes is one of the causes of wrong predictions. In this paper, the authors analysed past research of the ways of improving the quality of machine learning based on unbalanced data. The terms that describe the degree of class imbalances have been defined and clarified. The strengths and weaknesses of 50 various methods of handling such data were studied and set forth. Out of the set of methods of handling the numbers of class members as part of the classification (prediction of the occurrence) of rare hazardous events in railway transportation, the NearMiss method was chosen. It allows experimenting with the ratios and methods of selecting class members. As the results of a series of experiments, the accuracy of rare hazardous event classification was improved from 0 to 70-90%.

A Classifier of Railway Power Supply Equipment Concern Importance Based on Ensemble Learning

It is of great significance to evaluate the condition of equipment and identify the degree of important concern of equipment for formulating reasonable condition maintenance strategy and ensuring the safe and stable operation of railway power grid. In view of the characteristics that the overload operation state and maintenance interval of equipment are closely related to the equipment state level, the evaluation feature vector composed of five indexes, including overload time of heavy overload equipment, whether the central power supply equipment is in the city center, unrepaired time of equipment, whether it is the power supply equipment and the voltage level of equipment is maintained, is constructed in this subject. In addition, based on the Stacking ensemble learning framework, a hybrid ensemble learning framework algorithm is proposed, which combines the single Bagging and Boosting framework algorithms, and realizes the mapping between feature vectors and importance levels. The data of actual railway power grid equipment are substituted into the model for analysis, and the model is compared with the random forest model based on single ensemble learning algorithm. The simulation results show that compared with other ensemble learning algorithms, the accuracy of equipment state evaluation is significantly improved by using the combination model of stacking ensemble learning method.

철도 급전 부하 공유장치에 대한 연구

This paper is a study on an Energy Sharing and Management system (ESM) that shares loads between substations of a railway system to reduce peak power, improve voltage drop, and maximize regenerative power use. ESM is installed on the sectioning post between two railway substations to prevent inrush current and surge from the insulation section, extending the life of power equipment and improving voltage fluctuations in railway power supply systems. In addition, as the load is divided between substations, the maximum power and power loss are reduced, and the use of regenerative power is maximized, resulting in a great electric energy saving effect. The ESM is applied separately from the breaker for extended power supply, and in the event of a failure, the ESM is automatically disconnected from the system. It is necessary to research, develope an ESM with such advantages and apply it to the railway system as a trial to verify its effectiveness.

Simulation of induced voltages created by the 25 kV traction network across the pipeline in ice melting mode

Long metal structures and facilities can be located along the routes of electrified railways with 25 kV traction networks. A typical example of such facilities is pipelines designed to transport liquid or gaseous products. Due to the electromagnetic effects of electric traction networks, induced voltages can occur on structural parts, which are dangerous for the operating personnel. A set of special measures is needed to improve electrical safety and protect people from the influence of induced voltages. In the context of digitalization of the electric power industry, the choice of such measures requires the use of computer technologies, which can be implemented on the basis of methods and tools for simulation of railway power supply systems developed in Irkutsk State Transport University. The article presents the results of research aimed at the development of computer models designed to determine the electromagnetic effects of electric traction networks on the main ground-laid pipeline in the modes of ice melting.

Prototype Model for High Speed Railway Power Supply System Suitable for Indian Traction Sub Stations using Multi Modular Converter

As on 2020, India does not have any globally proven railway lines running with high-speed standards as above 250 km/h. Indian Railways looking at the prospect of high speed rail networks also known as bullet rail network in India. With the present Indian traction supply system which is based on the phase splitting or phase shifting method is not suitable for the high speed railway network unless we eliminate neutral sections as well as mitigating the power quality issues such as voltage unbalance, harmonics and high reactive power drawn from the utility grid. In this paper, Co-phase traction power supply system with zero neutral sections is proposed. Modular multilevel converter based three phase to single phase catenary system through a DC Link has been designed, simulated and laboratory prototype is made. A MATLAB simulation of the suggested method and droop characteristics based on load sharing between the two single phase parallel inverters had executed. The obtained results were satisfactory and shows that the proposed system is very much suitable for high speed railway.

Hybrid compensation method for traction power quality compensators in electrified railway power supply system

In order to improve the Power Quality (PQ) of traction power supply system and reduce the power rating and operation cost of compensator, a Static VAR Compensator (SVC) integrated Railway Power Conditioner (RPC) is presented in this paper. RPC is a widely used device in the AC electrified railway systems to enhance the PQ indices of the main network. The next generation of this equipment is Active Power Quality Compensator (APQC). The major concern of these compensators is their high kVA rating. In this paper, a hybrid technique is proposed to solve aforementioned problems. A combination of SVC as an auxiliary device is employed together with the main compensators, i.e., RPC and APQC that leads on to the reduction of power rating of the main compensators. The use of proposed scheme will cause to reduce significantly the initial investment cost of compensation system. The main compensators are only utilized to balance active powers of two adjacent feeder sections and suppress harmonic currents. The SVCs are used to compensate reactive power and suppress the third and fifth harmonic currents. In this paper firstly, the PQ compensation procedure in AC electrified railway is analyzed step by step. Then, the control strategies for SVC and the main compensators are presented. Finally, a simulation is fulfilled using Matlab/Simulink software to verify the effectiveness and validity of the proposed scheme and compensation strategy and also demonstrate that this technique could compensate all PQ problems.

Feedforward Compensation of Railway Static Power Conditioners in a V/v Traction Power Supply System

Railway static power conditioners (RPC) usually improve the power quality of traction power supply systems only according to the active power of the load, which leads to inaccurate compensation. There are two factors that restrict the performance of RPC, one of which is the reactive power of the load, and the other is the system error. In order to eliminate the compensation error, a compensation optimization method is proposed. First, calculate the reactive power compensation value for the reactive power of the load. Second, introduce the amplitudes and phases of the primary currents of the V/v transformer as references for the compensation error caused by the system loss and then use fuzzy control to optimize compensation. The compensation method proposed in this paper is actually a feedforward control. In addition, this method balances the three-phase currents and enables RPC to be used in railway power supply systems with low locomotive power factors. The effectiveness of the method proposed in this paper has been confirmed by the simulation results.

Reliability analysis of logic control system of automatic ground control neutral section passing

Neutral section passing technology in railway power supply had always been a technical problem in current domestic traction power supply industry. In recent years, there are many technical schemes for passing neutral section. There are two main schemes of automatic neutral section passing at present: the vehicle control neutral section passing and automatic ground control neutral section passing, the automatic ground control neutral section passing is a relatively popular technical route in both schemes. Now incorporating fail-safe principle of signal specialty in automatic ground control neutral section passing and proposing the logic control system of automatic ground control neutral section passing based on the idea of "fail safe" in the interlocking system, and the risk identification and safety analysis are carried out based on the dynamic fault tree and HAZOP method. The fault tree is constructed based on the results of HAZOP analysis. Finally, the system reliability is quantitatively calculated through the fault tree.

Analysis of the Operating Modes of the Stationary Energy Storage Device in DC Railway Power Supply System

Abstract This article analyzes the operating modes of the energy storage. The aim was to conduct laboratory tests in conditions similar to real energy storage and to analyze its basic electrical parameters. A special measuring system has been created for laboratory testing. Real tests took place in the traction substation in Mińsk Mazowiecki, where the energy storage was included in the traction substation system. Based on the laboratory tests carried out and in real conditions it was found that the use of energy storage in the electric traction supply system is justified. It is adapted to work as a device supporting the operation of the traction substation and the section cabin.

Efficient Formulations and Decomposition Approaches for Power Peak Reduction in Railway Traffic via Timetabling

Over the last few years, optimization models for the energy-efficient operation of railway traffic have received more and more attention, particularly in connection with timetable design. In this work, we study the effect of load management via timetabling. The idea is to consider trains as time-flexible consumers in the railway power supply network and to use slight shifts in the departure times from the stations to avoid too many simultaneous departures. This limits peak consumption and can help to improve the stability of the power supply. To this end, we derive efficient formulations for the problem of an optimal timetable adjustment based on a given timetable draft, two of which even allow for totally unimodular polyhedral descriptions. The proper choice of the objective function allows the incorporation of the priorities of either the train operating companies or the infrastructure manager. These include the avoidance of large peaks in average or instantaneous consumption and the improved use of recuperated braking energy. To solve the arising optimization models efficiently, we develop specially tailored exact Benders decomposition schemes that allow for the computation of high-quality solutions within a very short time. In an extensive case study for German railway passenger traffic, we show that our methods are capable of solving the problem on a nationwide scale. We see that the optimal adjustment of timetables entails a tremendous potential for reducing energy consumption.

A Novel Multistation Cooperative Negative Sequence Current Compensation Method for High-Speed Railway

Nowadays, the negative sequence current (NSC) issue is the most serious power quality problem for the high-speed railway power supply system, and the single substation NSC compensation methods cannot reduce the installed capacity of the compensating devices any further. A novel NSC compensation method, multistation cooperative compensation (MSCC), is proposed in this article. In order to adapt to the MSCC, a new NSC compensation principle, which is different from the traditional compensation principles, is carried out. Then, the cooperative control strategy is analyzed according to the new NSC compensation principle and the topology of the multiple traction substations. The compensating device is based on three-phase, cascaded, H-bridge converter which is suitable for the new NSC compensation principle. The capacity analysis results show that the MSCC can reduce the installed capacity of the compensating device for each single substation by 33.3% and even more under the constraint condition. A lower installed capacity means lower cost and smaller size. This advantage and the effectiveness of the MSCC are verified by both simulations and small-capacity experiments.

The use of energy routers to improve reliability of power supply to non-traction consumers

The purpose of the studies presented in the article was to determine the effectiveness of the use of energy routers (ER) in railway power supply systems to increase the uninterrupted power supply to non-traction consumers, reduce unbalance and nonsinusoidality, and reduce voltage dips in emergency modes. The research was carried out by means of computer modeling using the Matlab software system based on the developed models of power supply systems (PSS) equipped with ER with energy storage devices. The results obtained show that in standard circuits of PSS for linear consumers with short circuits in the supply network, voltage dips occur, the depth of which reaches 100%. The use of an ER and an energy storage device connected to DC buses allows maintaining voltage at consumer clamps near the nominal value in case of short circuits in the 10 kV feed line and 25 kV overhead contact system. The ER significantly limits the recharge of the short circuit location from the power storage. In addition, on the basis of the ER it is possible to provide the normative quality of electricity considering voltage deviations, asymmetry and harmonic distortions on the 0.4 kV buses of the substation that feeds non-traction consumers.

Методика выбора мест установки систем автоматического резервирования мощности тяговых подстанций постоянного тока

The paper presents a method for selecting the installation locations of power reservation systems of traction substations to reduce electricity losses in the system of traction power supply of DC railways. The analysis of the main criteria affecting the efficiency and reliability of the DC traction power supply system is carried out. The algorithm for selecting the installation locations of power reservation systems has been developed, which allows selecting traction substations that provide the greatest energy effect during the installation of systems

Study on Power Quality Evaluation of Traction Power Supply System of High-speed Railway

With the continuous development and progress of China's high-speed railway system, the power supply of high-speed railway has become an important load of the power system. The introduction of large load will bring certain voltage fluctuation, harmonic interference and other random problems to the power system. In this paper, the positive sequence, negative sequence and zero sequence component models of current and voltage are established to solve the problem of equivalent modeling for power quality assessment of high-speed railway power supply system. Firstly, the positive sequence, negative sequence and zero sequence component models of current and voltage based on symmetric component method are established. Through Fourier transform, the phase Angle of fundamental wave is solved, and the positive sequence, negative sequence, zero sequence component, sequence component diagram and current spectrum diagram of current and voltage under three actual working conditions are obtained Through the analysis of the whole train operation process, the amplitude graphs of the positive sequence, negative sequence and zero sequence components of the current and the curves of the third harmonic possession with time are obtained by using the above methods.