Long Yu

Due to their nonbackup characteristics and constant exposure to outdoor conditions, the performance of overhead contact lines (OCLs) will gradually degrade over time and further result in equipment defects or frequent failures. These issues significantly impact system availability and incur substantial repair costs. To tackle these issues, this paper proposes a stochastic colored Petri net (SCPN) model to evaluate the availability of OCLs and estimate the maintenance costs, simultaneously simulating the degradation, failure, inspection, and maintenance processes of critical components and the overall system. Firstly, this model encompasses the nature of a multiple‐stage deterioration process and various maintenance actions available for OCLs. A four‐state transition diagram is developed to capture the intricate dependencies involved. Moreover, a subnet is formulated using SCPN to represent the four‐state transition for critical components, which are described by nine tuples. Additionally, a system model is developed by integrating the subnets of OCL components. To improve simulation speed, an accelerated Monte Carlo simulation algorithm is devised to handle the analytical solution for the complex integration associated with performance transitions. Finally, the proposed approach is demonstrated by its application to an actual high‐speed railway line, showcasing its effectiveness in addressing the degradation and maintenance challenges of OCLs.

As an essential component of the high-speed railway overhead contact lines (OCLs), the insulator supports OCLs while maintaining the insulation between OCLs and Earth. However, because of the lack of defect samples and the variety of defect types, achieving full automation of insulator defect detection using computer vision is still challenging. To overcome these problems, this article proposes a real-time, unsupervised learning siamese defect detection network (SDDN) based on knowledge distillation. It includes a teacher network (TN) and a student network (SN). Our method is mainly divided into two stages. In the first stage, insulators are quickly and accurately localized from OCLs images. Then, insulators are sampled into small patches under the sliding window. These small patches are fed into the SDDN for defect detection in the second stage. Furthermore, the defect scores of samples are determined by SDDN. If the time cost of ImageNet-1k pre-training for the teacher network can be afforded, we provide a faster version: Faster SDDN. However, during the training phase, whether it is SDDN or Faster SDDN, TN only uses normal samples to distill the knowledge of the deep features to SN. The dissimilarity between the distilled features of SN with the TN is applied to score the samples’ defect scores at the testing phase. The defect detection experiment using the insulator dataset of the Linzi-Qingzhou city north high-speed railway proves the effectiveness of our method.

To ensure the high-reliability operation of overhead contact lines (OCLs), this paper proposes a data-driven time dependent reliability prediction approach, incorporating the maintenance factor, common cause failure (CCF), and lightning strike into reliability modeling and prediction for multi-component OCLs. Firstly, a new lightning-related failure probability calculation method is developed, including probabilistic lightning modeling, lightning identification, tracking and association analysis (LITAA), lightning movement trajectory prediction, and electric geometric model-based failure rate calculation. Moreover, a Bayesian network-based reliability model is embedded to integrate historical maintenance information, predictive lightning-related failure rate and fault tree model into reliability assessment of OCLs, which effectively captures the dependencies between failure events and depicts the impact of CCF on OCL components. In this context, the reliability of OCL components and OCLs can be predicted, with update of lightning strike data. Finally, the actual maintenance and lightning-related failure records are implemented to validate the effectiveness of the proposed approach. The result analysis demonstrates that our approach can not only illustrate how the reliability can be predicted using the predictive lightning-related failure rate, simultaneously accounting for imperfect maintenance and CCF, but also enhance risk prevention against lightning strike and faulty OCL components.

Due to highly complicated working conditions of overhead contact lines, it is inevitable to suffer from the dynamic external weather conditions and environmental factors, and further trigger a variety of risk events, even causing a series of serious consequences. To prevent the weather-related risks in advance, this paper proposes a weather-related failure risk prediction approach based on deep gaussian process (DGP), with its superior performance of nonlinear processing and uncertainty quantification. After preprocessing the weather data and the associated failure records, the weather-related failure risk prediction dataset is established for the studied issue of this paper, that is predictive classification problem. To simultaneously predict the lighting-related trip-out, wind-related floater intrusion, and fog-haze-related pollution flashover risk, a multi-task learning framework in DGP is formulated to capture the complex dependencies between weather parameters and OCL failure risk. The extensive experiments investigated on the constructed dataset reflect the effectiveness and superior of the proposed approach, with capacity of uncertainty quantification and giving trustworthy prediction results.

The Pantograph-catenary system is crucial for transferring electrical power from catenary lines to electrified train and the occurrence of arcing could damage railway operations, thus, it is important to detect arcing. Detecting arcing in complex scenes and detecting different size and shape of arcing is still a challenge. To overcome these issues, a robust image-based semantic segmentation model named ArcMSF is proposed for arcing detection of pantograph-catenary, which designs a novel hybrid multi-scale feature fusion model that aggregates Transformer with CNN to realize arcing pixel segmentation. A down-top decoder for combining low-level features with high-level features is designed to achieve multi-scale level arcing feature detecting in complex scenes. Inspired by the arcing image properties that arcing is always the brightest, the global max features and global threshold features are designed to augment the arcing features. Experiments on dataset IVAIS-PCA2021 and comparative experiments are conducted to demonstrate the effectiveness of the ArcMSF, which can achieve 89.13% segmentation accuracy and the fast inference speed of 23.84ms. Moreover, the detection results have a clear depiction of edge details.

Due to being completely exposed outdoors without backup, overhead contact lines (OCLs) are more vulnerable to external weather conditions. To perceive the weather-related failure risk and evaluate the associated potential risks, a multilayer Bayesian network (MLBN) approach is proposed for predictive probabilistic risk assessment for OCLs. More specifically, the weather-driven failure probabilities of OCLs are predicted using a first-layer Bayesian network (BN), including lightning strikes, windstorms, and fog-haze. Then, the weather-driven failure patterns of OCLs are investigated and captured, and furthermore, the second-layer BN is embedded to evaluate the risk propagation. Furthermore, the third-layer BN is implemented to calculate and quantify weather-driven risk consequences from perspectives of economic loss and social trust loss constrained by power outage time and train timetable. The three-layer BN models are built by connecting the nodes with causal relationships, avoiding complicated structure learning. The experiments on the actual OCL failure records and weather data demonstrate that the proposed MLBN approach can identify weather-involved risk activities and comprehensively analyze the weather-driven cumulative risks of OCLs from spatiotemporal perspectives. In addition, it is capable of giving reasonable guiding information for mitigating the operational risks of OCLs against external weather conditions.

Automatic inspections of overhead contact lines (OCLs) are developed to implement anomaly detection during normal operation. It is an essential prerequisite for efficient maintenance of railway electrification system. This paper presents a comprehensive survey on the inspections of OCLs with an emphasis on computer vision technology, which has developed rapidly due to its ability to understand images. Our survey begins with a brief introduction on anomalies in OCL inspections and generic procedures of computer vision inspection for anomaly detection. Subsequently, for detecting deviations of parameters and defective components during OCL inspections, the existing techniques involving stereo vision and object vision, especially convolution neural networks are described in detail from two aspects: measurement of OCL parameters and identification of OCL conditions. Some interference factors in OCL inspection are analyzed. Actual cases of the inspections are also briefly shown. Challenges and suggestions for further research on OCL inspection are drawn toward the end of the paper.