As an essential subsystem of electrified railway operation and maintenance, intelligent detection of catenary support components still faces several critical challenges: (1) the number of abnormal (negative) samples for components is severely limited; (2) component anomalies are highly diverse and exhibit heterogeneous visual characteristics; and (3) existing models generally show unsatisfactory detection performance when confronted with previously unseen anomaly types. To address these issues, this paper proposes a novel few-shot anomaly detection model for catenary components, termed BCLIP-ADer, built upon a Bayesian prompt contrastive vision–language pretraining framework. Specifically, a Bayesian prompt flow module (PFM) is designed to regularize the text prompt space via the jointly learned image-specific feature distribution (ISFD) and image-agnostic feature distribution (IAFD), thereby mitigating the degradation in detection performance on unseen component anomalies. Monte Carlo sampling over these learned distributions is further employed to generate diverse text prompts, leading to more comprehensive coverage of the prompt space. In addition, a cross-modal feature refinement module (CFRM) is designed to more effectively align dynamic text embeddings with fine-grained image features, thus enhancing anomaly detection at the component level. Finally, extensive experiments conducted on a UAV-based catenary dataset (CSCUD) demonstrate the effectiveness and superiority of the proposed approach. Specifically, the proposed method achieves I-AUROC/I-AP/I-F1_max scores of 94.2/93.2/93.1 under few-shot conditions.

The existing drone-based detection systems for electrified railway catenary support components face the following challenges: 1) the background of aerial images of the catenary support component is complex; 2) a unified model struggles to handle anomaly detection for various component types; and 3) there is inconsistency in the normal region feature information between training and testing images. To address these issues, this article proposed a novel adaptive anomaly detection framework for catenary support component an anomaly detection model based on invariant normal region prototype extraction (INRP-Ader). First, we proposed a new segmentation model (CSC-SAM) that embeds key catenary component location information to extract foreground images. Next, we design an anomaly detection model that directly extracts invariant normal region prototype (INRP) features from the test images. This model includes an INRP extractor constrained by INRP smoothness loss and an INRP-guided decoder, aimed at solving the problem of inconsistency in normal region features between training and testing images and the challenge of adapting a unified model to multiple component types. In addition, a soft mining loss is introduced to further optimize the training process of the multiclass anomaly detection model. Finally, we established a real-world catenary support component dataset, catenary system component UAV dataset (CSCUD), collected by drones, and achieved detection performance of 99.1/98.2/98.2 in image-level metrics (I-AUROC/I-AP/I-F1) and 96.4/37.1/55.7 in pixel-level metrics (P-AUROC/P-AP/P-F1). The proposed method outperforms traditional methods by approximately 0.4%-16.6% across various metrics.

The core task of intelligent detection in electrified railway catenaries is to detect their supporting components. However, due to the large number and variety of components in catenary inspection images, labeled catenary data is often limited, and few studies have focused on leveraging large amounts of unlabeled datasets in this field. This article proposes a novel self-supervised pretraining model catenary support rod masking-based masked image modeling (CSRM-MIM) for detecting catenary support components (CSCs), which effectively utilizes the valuable information in unlabeled catenary data. Specifically, a new semantic catenary support rod area masking (CSRA masking) strategy based on the CSRA features is proposed to guide the model in learning meaningful catenary semantic information during the pretraining process. Additionally, a new Siamese pretrained network framework is designed, incorporating an information interaction enhancement module (IIEM) and a dual reconstruction network to perform dual reconstruction on the semantic mask, thereby extracting global features in the catenary domain. Finally, a multiscale knowledge distillation (MSKD) strategy optimized by the cross-layer fusion module cross-layer fusion decoding (CLFD) is introduced to assist the self-supervised model in acquiring specific-general representations for the catenary field and transferring multiscale information, which benefits subsequent detection tasks. Experimental results demonstrate that this method significantly enhances the detector's performance in identifying CSCs, owing to the retained self-supervised learning (SSL) strategy.

The double-sided power supply railway system increases the simultaneous operation of vehicles on the grid, potentially causing system instability and oscillation overvoltage issues. As vehicles frequently switch operating points during operation, it is essential to analyze system stability across a wide range of conditions. Therefore, accurately identifying the black-box impedance of vehicle converters at multiple operating points is crucial for studying railway vehicle-grid system stability. However, traditional impedance identification methods require extensive data and lack interpretability, leading to significant computational and data burdens. This study introduces an interpretable residual feedforward neural network (ResFNN) combined with SHapley Additive exPlanations for training vehicle impedance models, reducing data requirements while maintaining accuracy. Additionally, a component connection method is proposed for deriving the impedance matrix of a multi-vehicle railway system under the double-sided feeding mode. This method incorporates the dynamic mobility of vehicles and their positional distribution, and it utilizes the ResFNN to identify impedance for stability analysis. Real operational data from actual railway lines is used as case study to analyze the stability of the double-sided power supply railway system. The results demonstrate that this approach accurately assesses both low-frequency and high-frequency instability issues.

The robust topology optimization (RTO) design of multi-material structures holds significant practical implications and theoretical value. The main contribution of this paper is to study the RTO problem of multi-material structures considering load uncertainty, and to propose an innovative non-gradient multi-material RTO approach to multi-material structures considering load uncertainty. To this end, the alternating active-phase algorithm (AAPA) is first applied to decouple this RTO problem, and combined with these approaches (probabilistic approach, density-based approach, and linear combination approach) to construct the RTO model of multi-material structures considering load uncertainty and taking the linear combination of the mean and standard deviation of the structural compliance as the objective function. Subsequently, the superposition principle of linear theory, Monte Carlo simulation (MCS), and orthogonal diagonalization of a symmetric matrix are applied to derive the computational equation for the objective function suitable for an improved proportional topology optimization (IPTO) approach. Based on this, the IPTO approach is employed to solve this RTO model, thereby forming an innovative multi-material non-gradient RTO approach. Finally, two numerical examples are applied to illustrate the efficacy of this new approach and the influence of the filtering radius on the structural RTO design. The results showcase that this new approach can tackle the robust optimization design issues of multi-material structures and yield an optimal structure with enhanced robustness. Moreover, the proposed approach's filtering radius directly influences the shape of the optimized structure.

The pantograph-catenary system (PCS) is a critical component of railway vehicles, and its performance directly affects current collection quality. The arc rate serves as an essential measurement indicator for monitoring the PCS state. However, in complex railway environments-where arc sizes and shapes can vary significantly and are further influenced by factors such as reflected light, glare, and adverse weather-the traditional arc detection methods are easily affected by unstable current collection and power fluctuations, resulting in increased false detection rates and reduced measurement accuracy. Deep learning methods, while promising, also face limitations when dealing with such diverse arc morphologies and strong external interference. To address these challenges, this article proposes a multimodal imitation learning-based arc detection network (MILADNet). First, the measurement system fuses infrared and visible-light image features to enhance arc feature extraction in scenarios with strong glare or reflective interference, thereby mitigating false alarms caused by relying on a single sensor. Second, to overcome the lack of information on small arcs, an online imitation learning framework is introduced to improve the system's detection sensitivity for small arcs. Finally, to address data bias arising from uneven arc distributions, an unsupervised transferable representation learning method is employed to reduce dependence on labeled data and enhance model generalization. Experimental results show that MILADNet exhibits outstanding detection performance for arcs of various sizes and in complex environments, demonstrating both high efficiency and accuracy during measurement and data processing. Beyond improving the precision and reliability of arc detection, this method offers a novel solution for the instrumentation and measurement field and shows significant potential for condition monitoring and anomaly detection in railway systems.

In electric railways, the interaction performance between the pantograph and catenary is crucial for maintaining a stable current supply. Establishing high-fidelity numerical models using the finite element method is generally desirable, yet it involves considerable computational complexity and time demands. In this paper, we propose a novel dynamic prediction model that integrates physical information and data-driven approaches to solve the pantograph-catenary interaction, called FENet. Specifically, there are two significant aspects: (1) A deep learning framework is developed for efficient simulation. The network utilises the temporal convolutional network to extract short-term local features. Simultaneously, the attention-based long short-term memory is leveraged to capture the long-term dependencies in the interaction sequence. FENet establishes the dynamic relationship between the system state and excitation variables, achieving fast and accurate simulation. (2) We integrate multiple physics-informed loss terms to handle implicit constraints within motion equations, which leverages physical principles to guide the learning process. Additionally, a dynamic weighting mechanism adaptively balances the contributions of various terms in the physics-based loss function. Experimental results reveal that FENet exhibits effectiveness and robustness against different external excitations and achieves long-term dynamic response prediction with negligible computational effort. Moreover, it shows promising potential for real-time simulation and feedback in pantograph hardware-in-the-loop test rigs.

This paper is dedicated to the following objectives: with the precondition of circumventing sensitivity analysis, addressing the structural topology optimization problem that considers volume constraints and minimizes structural compliance, and obtaining a clear optimized structure with smooth boundaries. To achieve these objectives, this paper designs a novel floating projection filter and uses it to develop two enhanced proportional topology optimization (EPTO) methods, which are named EPTO_A and EPTO_B, respectively. Among these, the EPTO_A is proposed by modifying the proportional topology optimization (PTO) method using this novel floating projection filter, an improved material interpolation model, and a density filter. Although the EPTO_A can yield a clear optimized structure, this structure suffers from saw-tooth boundaries. To tackle this problem, a smooth operation is applied to modify density results from the EPTO_A, thereby proposing the EPTO_B. Subsequently, numerical examples and comparison methods are applied to evaluate these two new methods and the influence of the material interpolation model on the EPTO_A. The results show that the material interpolation model affects the EPTO_A’s convergence performance and ability to search for the optimal solution. Simultaneously, the EPTO_A exhibits a stronger searching ability for the optimal solution and possesses some other advantages, such as stable convergence performance, faster convergence speed, and a stronger ability to obtain a clear optimized structure. For the EPTO_B, its most outstanding advantage is that it can get a clear optimized structure with smooth boundaries. In addition, although the EPTO_B is not as good as the EPTO_A in the convergence speed and optimal solution searching ability, it can still showcase the characteristics of stable convergence performance and fast convergence speed.

In electric railways, the interaction performance of the pantograph-catenary systems (PCS) is crucial for maintaining a stable current supply. Establishing high-fidelity numerical models based on the finite-element method (FEM) is a common practice, but it also has substantial computational complexity. The Koopman operator, a promising candidate for data-driven modeling, provides a global linear representation of nonlinear dynamic systems. In this article, we develop a novel generalized Koopman neural operator (GKNO) implemented by an autoencoder and an improved Transformer for modeling complex nonlinear dynamic systems with large-scale degrees of freedom. It consists of an observable function, an evolution function, and an invertible observable function. First, the encoder, as the embedding model, maps the state variables of the original system into observable space with linear dynamics. Then, an improved Transformer model is proposed to learn the evolution function in the embedding space based on an autoregressive task. Finally, the decoder reconstructs the state variables of the original system from the embedding space. Experimental results on the PCS model demonstrate that GKNO can capture the intrinsic evolution patterns to represent high-dimensional and nonlinear PCS dynamics, significantly reducing computational complexity and solution time. Comparative experiments show that GKNO achieved considerable solution accuracy with negligible consumption of computing resources, providing a promising potential for parameter optimization and pantograph hardware-in-the-loop (HIL) test rigs.

In electric railways, the current collection quality of pantograph-catenary systems (PCSs) is typically evaluated through numerical simulations using the finite element method, which is computationally expensive and time-consuming. To address this challenge, we propose a surrogate modeling approach that trains a conditional generative model to approximate the output of the reference numerical model. Specifically, we introduce dual-domain conditional generative adversarial networks (DD-CGAN) to generate contact force (CF) curves for various PCS parameter configurations. The generator network takes system parameters as input and produces the corresponding CF curve, while the discriminator network distinguishes between real and predicted curves in both the time and frequency domains, ensuring greater consistency. Furthermore, the feature fusion module is proposed to extract and integrate time- and frequency-domain features by using a multiscale channel attention (MSCA) mechanism. Extensive experimental results demonstrate the effectiveness and advantages of DD-CGAN for surrogate modeling of pantograph-catenary interactions. The CF curves generated by our method exhibit high consistency with simulation results from high-fidelity numerical models with a mean absolute error (MAE) of 0.9815, which is six times more accurate than state-of-the-art methods. Most importantly, our method achieves a speedup of nearly 1000x compared to traditional numerical simulations, highlighting its potential for practical use in designing and optimizing catenary structural parameters.

The longitudinal movement of the girder has a significant effect on the service lifespan of girder-end restraint devices used in suspension bridges. Accurately predicting the girder-end displacement during train passage is essential for optimizing the design, monitoring, and maintenance of these devices. A refined finite element model can effectively predict the girder-end longitudinal movement under traffic loads. However, the transient analysis of moving loads faces challenges such as high computational cost and significant complexity due to the nonlinear behavior of railway suspension bridges. This study proposes an analytical approach for predicting the girder-end longitudinal movement considering various nonlinear resistances. This approach begins by formulating the cable deformation under vertical loads using single cable theory. The longitudinal displacement of the stiffening girders is determined by coordinating the forces and deformations of the hanger, main cable, and girder. After that, nonlinear single-degree-of-freedom (SDOF) model is proposed to predict the longitudinal movement of the stiffening girder under train loads, incorporating viscous dampers and bearing friction. Finally, the proposed method is validated through a full-scale test and nonlinear finite element models of a 660-meter railway suspension bridge. Results show that the longitudinal displacement of the main cable is associated with its vertical displacement. The main cable resists vertical loads by altering its geometric profile, inducing the girder longitudinal displacement. The proposed method demonstrates high accuracy and efficiency, requiring only 0.69 % of the time needed for finite element transient analysis, with an error not exceeding 8.1 %. Parametric analysis shows that low-exponent fluid viscous dampers effectively control the girder-end longitudinal movement. Excessive friction might hinder the normal reset of the stiffening girder. These findings provide insights into the longitudinal motion mechanism of girder ends in railway suspension bridges, facilitating the optimization of restraint device designs.

The pantograph-catenary system (PCS) is a critical interface for stable power acquisition in high-speed railways, and its dynamic interaction performance directly dictates the safety and reliability of train operation. As operating speeds increase, traditional passive pantographs experience severe fluctuations in contact force, leading to electrical arcing and mechanical wear, becoming a key bottleneck to further speed advancements. Active control technology, which integrates sensors, controllers, and actuators to regulate the pantograph’s behavior dynamically, is a core solution for addressing these challenges and ensuring superior current collection quality. This review aims to systematically survey and summarize the state of the art and future trends in active control for the pantograph-catenary system. Firstly, the core dynamic challenges and the necessity of active control are discussed before detailing the key modeling techniques required for simulation and real-time control design. Secondly, existing active control strategies are meticulously classified and reviewed. Subsequently, the essential hardware implementation platforms, including actuators, sensor technologies, real-time controllers, and Hardware-in-the-Loop (HIL) testing rigs, are systematically outlined, thereby bridging theory and practical verification. Additionally, the emerging concept of active catenary control is also explored. Finally, present an in-depth discussion and outlook on the current status and limitations. This review is intended to provide a comprehensive and insightful reference for researchers and engineers in the relevant fields.

Objective The coupled dynamics of the pantograph-catenary system are a critical determinant of current collection stability and the overall operational efficiency of high-speed trains. This study proposes an active control strategy that addresses complex operating conditions to mitigate fluctuations in pantograph-catenary contact force. Conventional approaches face inherent limitations: model-free Reinforcement Learning (RL) suffers from low sample efficiency and a tendency to converge to local optima, while Model Predictive Control (MPC) is constrained by its short optimization horizon. To integrate their complementary advantages, this paper develops a Reinforcement Learning-Guided Model Predictive Control (RL-GMPC) algorithm for active pantograph control. The objective is to design a controller that combines the long-term planning capability of RL with the online optimization and constraint-handling features of MPC. This hybrid framework is intended to overcome the challenges of sample inefficiency, short-sighted planning, and limited adaptability, thereby achieving improved suppression of contact force fluctuations across diverse operating speeds and environmental disturbances. Methods A finite element model of the pantograph-catenary system is established, in which a simplified three-mass pantograph model is integrated with nonlinear catenary components to simulate dynamic interactions. The reinforcement learning framework is designed with an adaptive latent dynamics model to capture system behavior and a robust reward estimation module to normalize multi-scale rewards. The RL GMPC algorithm is formulated by combining MPC for short-term trajectory optimization with a terminal state value function for estimating long-term cumulative rewards, thus balancing immediate and future performance. A Markov decision process environment is constructed by defining the state variables (pantograph displacement, velocity, acceleration, and contact force), the action space (pneumatic lift force adjustment), and the reward function, which penalizes contact force deviations and abrupt control changes. Results and Discussions Experimental validation under Beijing-Shanghai line conditions demonstrates significant reductions in contact force standard deviations: 14.29%, 18.07%, 21.52%, and 34.87% at 290, 320, 350, and 380 km/h, respectively. The RL-GMPC algorithm outperforms conventional H infinity control and Proximal Policy Optimization (PPO) by generating smoother control inputs and suppressing high-frequency oscillations. Robustness tests under 20% random wind disturbances show a 30.17% reduction in contact force variations, confirming adaptability to dynamic perturbations. Cross-validation with different catenary configurations (Beijing-Guangzhou and Beijing-Tianjin lines) reveals consistent performance improvements, with deviations reduced by 17.04%' 33.62% across speed profiles. Training efficiency analysis indicates that RL-GMPC requires 57% fewer interaction samples than PPO to achieve convergence, demonstrating superior sample efficiency. Conclusions The RL-GMPC algorithm integrates the predictive capabilities of model-based control with the adaptive learning strengths of reinforcement learning. By dynamically optimizing pantograph posture, it enhances contact stability across varying speeds and environmental disturbances. Its demonstrated robustness to parameter variations and external perturbations highlights its practical applicability in high-speed railway systems. This study establishes a novel framework for improving pantograph-catenary interaction quality, reducing maintenance costs, and advancing the development of next-generation high-speed trains.

The pantograph–catenary system is a critical component of railway vehicles, and its performance directly affects the quality of current collection. Accurately measuring the arcing rate is essential for monitoring the system’s condition and ensuring safe operation. However, traditional arc detection methods are prone to increased false detection rates and reduced measurement accuracy in complex railway environments due to the diversity of arc sizes and shapes, environmental interference, instability in current collection, and power fluctuations. While deep learning-based methods can effectively address environmental interference, obtaining sufficient labeled training data is challenging because arc events occur infrequently. Moreover, a large number of unlabeled images of pantograph–catenary contacts cannot be directly utilized due to the lack of annotations. To solve these issues, a novel arc detection method is proposed: a multimodal arc detection network based on denoising diffusion probabilistic models (DDPMs-MILNet). First, a DDPM is pretrained using a large set of unlabeled images to acquire advanced image features. This model serves as a feature extractor, and a hierarchical variation semantic decoder is fine-tuned, thereby improving performance under small-sample conditions and reducing dependence on extensive labeled datasets. Building on this, an audiovisual semantic decoder is designed to incorporate audio signals as semantic cues, providing additional modality information for visual features. This approach not only reduces the model’s reliance on visual information but also enables it to locate the visual target of the arc even when the object is not simultaneously seen and heard, further alleviating the challenges posed by limited sample sizes. Experimental results demonstrate that DDPM-MILNet achieves excellent detection performance with minimal data in complex railway environments, indicating significant application potential, particularly in the state monitoring and anomaly detection of railway systems.

Previous reinforcement learning (RL) methods suffer significant performance degradation or collapse when deployed to the real world due to the huge sim-real gap. This article proposes a hybrid offline-and-online meta-RL (HOMRL) algorithm that leverages prior task experience to learn and adapt to new pantograph active control tasks in real-world applications. The policy learning process consists of three phases: offline meta-policy pretraining, online adaptation, and fine-tuning. First, we construct an offline meta-RL approach that learns from the massive and heterogeneous static training datasets, eliminating online interaction's high cost and hazard. Second, we combine context-based meta-RL with online fine-tuning to generalize to challenging tasks, while high safety and success rates are critical in railway applications. Finally, the proposed environment-sensitive task encoder (TE) and well-trained agent can adapt to new tasks quickly and efficiently, even in unseen tasks and nonstationary environments. If the new task is similar to the prior data, the contextual meta-learner adapts immediately. If it is too different, it gradually adapts through fine-tuning.

The active pantograph is a promising technology to suppress contact force fluctuation in pantograph catenary systems (PCS). Recently, the rapid development of reinforcement learning techniques has dramatically facilitated complex system controllers' design. However, the low data efficiency problem is fatal because data collection is costly. In this paper, We propose the Ensemble Q-functions Model-based Reinforcement Learning algorithm (EQ-MBRL) to achieve data-efficient reinforcement learning. First, we introduce an ensemble probabilistic neural network to estimate the distribution and uncertainty of the dynamics model and adopt multi-step loss to constraint accumulation error in the long-length model rollout. Second, we employ a short-term rollout of the model to trade off the ease of data generation and the error of the model-generated data. Finally, we propose ensemble Q functions and in-target minimization techniques to help stabilize the training process of value functions and improve the accuracy of value estimation. In addition, we discussed the appropriate model-based rollout length and explored the performance of network update rates with different strategies. The experimental results demonstrate that the proposed approach outperforms compared algorithms and delivers a state-of-the-art performance on the PCS benchmark. The controller learned robust motion patterns using only 50K collected transitions, which was more than ten times faster than compared baseline.

In this survey paper, we comprehensively examine the ongoing research concerning the interaction between pantographs and catenaries, a vital aspect in ensuring uninterrupted electricity supply to trains. Future perspectives for future studies to ensure satisfactory performance at 400 km/h and above are preliminarily explored. Initially, this paper provides an overview of the current design and assessment system. A systematic survey on the numerical modelling of pantograph-catenary interaction is conducted. The applicability of current assessment quantities to speeds of 400 km/h and above is preliminarily investigated with a numerical model. The potential of optimising parameters for improving interaction performance is also explored at this speed level. The paper further reviews and preliminarily analyses the effects of common disturbances, such as geometric deviation and aerodynamics, on the pantograph-catenary interaction performance at 400 km/h and above. To prolong the expectancy life of the system, the paper also reviews contact wire wear prediction models and discusses their potential application at 400 km/h and above. Overall, this paper offers insights into the current state of research on pantograph-catenary interaction for high-speed railways and proposes future directions for improving the system to ensure optimal performance at speeds of 400 km/h and above.

The pantograph—catenary system (PCS) is vital for high-speed trains to collect electrical power, where the contact force fluctuation seriously reduces the current collection quality, increases maintenance costs, and affects operation safety. Reinforcement learning (RL) is an attractive approach for learning active pantograph control policy by trial and error. However, the traditional RL methods suffer significant performance degradation or collapse when deployed to the real world due to the huge sim-real gap. We propose a hybrid offline-and-online reinforcement learning (HO2RL) algorithm to solve active pantograph control tasks, which elegantly combines RL policy pretraining with offline transitions and performance enhancement with online data collection. The proposed algorithm provides generalized pretrained models by learning effective behavior policy from offline experiences and then performs multidomain adaptation by online performance improvement with dynamics-aware policy evaluation. Experimental results demonstrate that the HO2RL algorithm efficiently learns from large and diverse static datasets and enables steady performance improvement by fine-tuning with online interactions. The proposed method solves active pantograph control tasks in various operation scenarios and demonstrates SOTA performance on the PCS standard benchmark.

The pantograph-catenary system (PCS) is the essential power supply system in the high-speed railway, but its coupling performance is influenced significantly by the rapidly increasing train speed. The actively controlled pantograph is one of the promising technologies to suppress the fluctuation of the pantograph-catenary contact force (PCCF). In this paper, we propose a novel pantograph control strategy based on deep reinforcement learning (DRL) to overcome the complex time-varying characteristic of PCS, which distorts the system identification of the classical control methods. First, a non-linear pantograph-catenary system model is established based on the finite element and multi-body dynamics theory as the simulation environment in DRL. Then, the state space, action space, and reward in DRL are redesigned to train the agent, which is suitable for PCS. Finally, the effectiveness and robustness of our proposed method are verified under various working conditions and parameter disturbances. The experiment results show that our control strategy can reduce the PCCF fluctuation up to 40% and reject parametric perturbation while achieving state-of-the-art performance on the benchmarks.