The advanced traction power supply equipment (ATPSE) based on power electronics technology presents an opportunity to address issues of negative-sequence power quality and neutral section simultaneously. However, existing power-frequency/high-frequency isolation schemes still face challenges such as low power density and high investment costs. To address these issues, a high-frequency isolated ATPSE (HI-ATPSE) based on triple-port high-frequency isolated dc converter and existing traction transformers is proposed. Compared to existing high-frequency isolation schemes, the device volume and initial cost are effectively reduced by sharing output ports in the proposed HI-ATPSE. In addition, considering the power quality issues within the proposed HI-ATPSE, a control strategy is proposed to suppress the dc side double-frequency ripple and negative-sequence while reducing the dc side's capacitance value. Finally, the feasibility and reliability of the proposed HI-ATPSE and control strategy are validated through simulation and experimental verification.

The conventional traction power supply system (TPSS) is limited in its ability to transport energy across regions due to the presence of section posts. In contrast, flexible TPSSs enable system-wide utilization of energy. However, electric locomotives face complex working conditions and experience drastic power fluctuations, making it crucial to address the efficient utilization of energy from multiple traction substations (SSs). This article proposes a multiagent-game-based reinforcement learning (MAG-RL) energy management strategy to facilitate collaborative energy interaction among neighboring SSs. Specifically, a Markov decision process for the energy management process is first established. On this basis, a distributed RL training framework is constructed to reduce the dimensionality of the state space. The multiagent energy game model is also constructed by analyzing the operation mechanism under different operation modes. Additionally, a sequential negotiation method is presented to quickly solve the energy game model. Real-time simulation platform testing indicates that the proposed method reduces the number of convergence iterations by 28.2% compared to the traditional Q-learning approach. Compared to independent operation, the utilization efficiency of regenerative braking energy improves by 30.04%, reaching 93.28%, demonstrating a technical advantage over other strategies.

The traction power supply system (TPSS) is the only source of power for electric locomotives. The huge power fluctuations and complex operating conditions of the TPSS pose a challenge to the efficient operation of energy storage traction substations. The existing energy management strategies are difficult to achieve accurate charging and discharging, difficult to modify the control rules in real time, and have poor migration capability. For comparison, the reinforcement learning (RL) algorithms can address the shortcomings of rule-based energy management strategies due to their model-free feature. Therefore, this article proposes an energy management strategy based on parallel reinforcement learning (PRL) to improve the efficiency of energy utilization while speeding up the convergence of the algorithm. More specifically, a Markov decision framework is established for capturing the energy management process. The Monte Carlo sampling process is also improved to achieve offline optimization by PRL algorithms and reduce the impact of low-value power fragments on iteration speed. Meanwhile, the algorithm is modified to enable online updates. The case study shows that compared with other energy management strategies, the PRL-based energy management strategy has faster convergence speed, higher energy exchange efficiency, and better migration capability, and can adapt to various complex working conditions.

In order to extend the service life of the high-speed railway hybrid energy storage system and reduce the power shock impact of the traction network, an energy management strategy based on double-layer fuzzy logic control is proposed. This strategy can dynamically adjust the discharge threshold according to the external power and the remaining life of the energy storage system, and dynamically allocate power according to the real-time state of charge. At the same time, the strategy uses the rain flow counting method to complete the extraction of the depth of discharge and establishes an equivalent life evaluation model. The simulation results show that this energy management strategy can effectively reduce the frequency and depth of charging and discharging, and reduce the load impact of the traction network. Compared with the threshold-based energy management strategy, the life loss of this method can be reduced by more than 50%, which effectively improves the service life of the energy storage system.

As an important part of the traction power supply system, the research on fault prevention of the catenary system has become a crucial issue for efficient operation and maintenance. In this paper, we propose a data-driven approach to investigate the underlying correlations among catenary components from the historical fault data, so that the fault propagation mechanisms among components can be revealed. Initially, based on the different roles played by components in the fault propagation process, we define fault impactability and susceptibility of components under different mechanical coupling relationships to capture the fault propagation mechanisms. Then, we propose a risk trust function model based on the D-S evidence theory to assess the fault impactability and susceptibility. Meanwhile, a belief and disbelief-based risk coefficient is proposed in the risk trust function model to construct the evidence source. Finally, the case study, based on the fault database of the Chengdu Railway Bureau, demonstrates that the proposed method can effectively assess the fault impactability and susceptibility of components to reveal the fault propagation mechanisms, which provides valuable references for formulating fault prevention strategies.

The advanced cophase power supply system provides an opportunity to eliminate the problems of neutral section and power quality issues. However, the existing schemes still have drawbacks, such as numerous power electronic devices, high initial cost, and poor reliability. Therefore, in this article, a novel hybrid advanced cophase power supply equipment (NH-ACPSE) is proposed based on the existing traction transformer. By the common dc bus of each port, the secondary ripple power of the input ports can be offset. Also, the number of active/passive devices and capacitance capacity can be reduced. Then, aiming at the secondary ripple and load power impact on the dc side, a composite control strategy of NH-ACPSE is proposed to solve the harmonic transmission and impact fluctuation effectively. Finally, the feasibility and reliability of the proposed equipment and its control strategy are verified by simulation and experiment.

Flexible traction substation (FTSS) integrates PVs, energy storage systems (ESSs), and railway power flow controllers (RPFCs) into the existing split-phase traction substation. It is a vital solution in advancing electric railways towards a low-carbon, efficient, and grid-friendly future. To improve the techno-economic performance of FTSSs, this paper proposes a sizing method to jointly size PV, RPFC, and battery-ultracapacitor hybrid ESS (HESS). Firstly, a flexible operation model of FTSS is established. It fully uses the capacity of RPFCs for improving the three-phase voltage unbalance and average power factor, thus, reducing the capacity requirements of RPFCs. Next, a linearized approach is developed for estimating battery aging affected by battery cycles, depth of discharge, state of charge, and calendar time. It facilitates obtaining battery sizing with relatively accurate life evaluation in sizing optimization. Then, a joint sizing optimization model of PV, HESS, and RPFC is established to minimize the total annualized investment and operation cost of an FTSS, and it is formulated as mixed-integer second-order programming. Finally, case studies show that the proposed method can optimize the total annualized cost of FTSSs while ensuring efficient energy utilization and improvements of the three-phase voltage unbalance and average power factor.

The novel hybrid advanced traction power supply device (NH-ATPSD), which consists of a traction transformer and a “two-phase-parallel-input to single-phase-cascaded-output” (2AC-AC) converter, has been proposed recently. It provides opportunities for solving the neutral section and negative-sequence power quality problems. However, different from the single-level power electronic device with cascade structure, the negative-sequence current and healthy module overload may occur when the input- or output-module fault occurs in NH-ATPSD. Thus, a dynamic fault-tolerant control for NH-ATPSD is proposed in this paper. For input module faults, the healthy module overload is avoided by the proposed dynamic modulation coefficient, which can dynamically adjust the power allocation between output port modules. In addition, the negative-sequence current is suppressed by controlling the partial power imbalance between the 2AC input modules. For output module faults, the active bypass of faulty module and increased voltage methods are adopted to keep the rated voltage and power output. Finally, the simulation and experiment results verify the effectiveness and efficiency of the proposed control strategy under different fault types.

The traction power supply system (TPSS) consumes a large amount of electrical energy for locomotive traction every year. To effectively utilize the regenerative braking energy of locomotives and reduce the overall traction energy consumption, the reinforcement learning (RL) method is introduced into energy management strategy in this paper. A reinforcement-learning framework for energy management is constructed to enhance energy utilization efficiency in traction scenario and regenerative braking scenario respectively, and to achieve the effect of adaptive charging and discharging by setting multiple reward functions. Meanwhile, due to the model-free energy management strategy, which avoids modeling the traditional circuit model and has the ability to update online, it is more flexible compared to the rule-based class approach. The simulation test results show that compared with the traditional rule-based energy management method, the RL-based energy management strategy can effectively improve the utilization efficiency in different electric locomotive operating scenarios, reduce the power impact of the traction power supply system, and improve the system operation economy.

The catenary system is a crucial part of the traction power supply system, consisting of multiple components interconnected through mechanical coupling. To reveal the risk characteristics of fault propagation between catenary components, this paper presents a reasoning approach-based pattern graph for analyzing the risk level of correlations of components considering time distribution from a statistical perspective. Initially, we define simultaneous fault correlations and sequential fault correlations among faulty components based on the different time distributions to capture the risk propagation features among components. Then, the MYCIN model is introduced to construct a certainty factor considering the belief and disbelief of fault correlations to calculate the risk levels of simultaneous/sequential fault correlations. Finally, we develop a risk pattern graph by linking the virtual paths to assess the risk level of inexplicit correlations hidden within the historical dataset. Simulation results, conducted based on the fault database of the Chengdu Railway Bureau, show the proposed method can effectively assess the risk level of correlations among faulty components to reveal the fault propagation features, which provides valuable references for proactive maintenance.

随着我国高速铁路网络规模的持续扩大,高速铁路牵引能耗高,机车再生制动能量利用率低等问题日益凸显.在碳中和的背景下,为降低牵引能耗,对铁路储能领域可用的储能介质进行比较分析,结合各介质特点全面说明地面固定式、车载移动式、地面-车载混合式三类储能方案拓扑结构,并从优化模型的角度阐述了不同拓扑结构下的容量配置方法.在此基础上,综述以基于阈值及分配比例为代表的能量管理方案,并简述基于铁路储能系统的"源-网-储-车"云感知能量管理系统,强调源、网、储、车的协调配合.系统论述了当前高速铁路储能系统容量配置和能量管理的研究现状,并对关键技术问题进行总结,展望高速铁路储能系统的未来发展方向,为高速铁路储能系统工程化提供相应参考.

High-speed railway has the advantages of fast speed and large transportation volume, but it is also accompanied by huge power consumption. The development of energy storage technology provides new ideas for solving this problem. As the foundation of the energy storage system, capacity configuration is directly related to the economic operation of the energy storage system. This paper establishes a multi-objective optimization model with the lowest equivalent annual value and the highest monthly income for the high-speed railway hybrid energy storage system (HESS). The number of series and parallel connections of each energy storage medium is used as the control variable, and the electrical and non-electric constraints are fully considered in this model. The test case shows that the model can effectively filter out the Pareto solution sets that meet the conditions of traction power supply system, and improve the economics of the energy storage system to provide corresponding references for actual projects.