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.

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.

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.

Abnormal vibration can lead to frequent maintenance requirements of electric locomotives. Many factors contribute to the vibration, and the influence mechanism of pulsating torque generated by interharmonics in the traction drive system (TDS) is not clear at present. In this paper, an electromechanical coupling model is developed to investigate the influence of harmonics and interharmonics in the electric TDS on the vibration of key locomotive components. Firstly, this paper attempts to analyze the generation mechanisms of interharmonics and their resulting pulsating torque in electric TDS and derives the formulas for calculating interharmonics and pulsating torque frequencies. Then, an electromechanical coupling model is established based on the electric TDS and the multibody dynamics, and the influence of pulsating torque caused by interharmonics on the vibration of the locomotive key components is discussed in detail. It is observed that the locomotive vibrations, especially the longitudinal and vertical vibrations of bogies and wheels, can be significantly influenced by the pulsating torque. It is noticeable that the frequencies of the vibrations are consistent with those of pulsating torque, which proves that electrical parameters can affect the vibrations of key locomotive components. The research of this paper provides a new idea for restraining locomotive vibration.

The electric shoegear-conductor rail system (the shoe-rail system) is one of the electric energy collection devices for metro vehicles. A good interaction performance between the electric shoegear and the conductor rail is essential to ensure the current collection quality and operational safety. The conductor rail irregularities and vehicle-track excitation (induced by track irregularities) are the major disturbances to the shoe-rail interaction. Only the vertical effect of the vehicle-track excitation has been considered in previous studies, which cannot reproduce the realistic behavior of the shoe-rail system. To address this deficiency, this work attempts to build a spatial vehicle-shoe-rail system coupling model, including the disturbances from both the conductor rail irregularities and vehicle-track excitations. The numerical accuracy is verified by comparison with the measurement data collected from Guangzhou Metro Line 5 (Jiaokou to Wenchong section). Then, the effects of conductor rail irregularities, speed, shoe-rail structure parameters, and track irregularities on the interaction performance of the electric shoegear-conductor rail system are analyzed. The results show that the maximum contact force exceeds the safety threshold at a speed of over 120 km/h. The frequency analysis of the contact force at different speeds indicates the necessity to avoid the resonance caused by the match between the span passage frequency and the dominant natural frequency. The stochastic analysis indicates a visible dispersion in contact force standard deviation excited by track irregularities. The dispersion increases from 2.2% to 21.8% with the degradation of the track quality from level 6 to level 1. The statistical maximum of contact force will exceed the safety threshold with poor track quality.