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.

Computer-aided simulations are routinely used to predict a prototype's performance. High-fidelity physics-based simulators might be computationally expensive for design and optimization, spurring the development of cheap deep-learning surrogates. The resulting surrogates often struggle to generalize and predict novel scenarios beyond their training domain. We propose a two-stage methodology addressing the challenge of generalization. It employs physics-based simulators, supplemented with ordinary differential equations integrated into the recurrent architecture, to learn the intrinsic dynamics. The proposed approach captures the inherent causality and generalizes the dynamics irrespective of a data source. The presented numerical experiments encompass five fundamental structural engineering scenarios, including beams on Winkler foundations based on Euler-Bernoulli and Timoshenko theories, beams under moving loads, and catenary-pantograph interactions in railways. The proposed methodology outperforms conventional recurrent methods and remains invariant to data sources, showcasing its efficacy. Numerical experiments highlight its prospects for design optimization, predictive maintenance, and enhancing safety measures.

A primary challenge of physics-informed machine learning (PIML) is its generalization beyond the training domain, especially when dealing with complex physical problems represented by partial differential equations (PDEs). This paper aims to enhance the generalization capabilities of PIML, facilitating practical, real-world applications where accurate predictions in unexplored regions are crucial. We leverage the inherent causality and temporal sequential characteristics of PDE solutions to fuse PIML models with recurrent neural architectures based on systems of ordinary differential equations, referred to as neural oscillators. Through effectively capturing long-time dependencies and mitigating the exploding and vanishing gradient problem, neural oscillators foster improved generalization in PIML tasks. Extensive experimentation involving time-dependent nonlinear PDEs and biharmonic beam equations demonstrates the efficacy of the proposed approach. Incorporating neural oscillators outperforms existing state-of-the-art methods on benchmark problems across various metrics. Consequently, the proposed method improves the generalization capabilities of PIML, providing accurate solutions for extrapolation and prediction beyond the training data.

This paper proposes a novel framework for simulating the dynamics of beams on elastic foundations. Specifically, partial differential equations modeling Euler–Bernoulli and Timoshenko beams on the Winkler foundation are simulated using a causal physics-informed neural network (PINN) coupled with transfer learning. Conventional PINNs encounter challenges in handling large space–time domains, even for problems with closed-form analytical solutions. A causality-respecting PINN loss function is employed to overcome this limitation, effectively capturing the underlying physics. However, it is observed that the causality-respecting PINN lacks generalizability. We propose using solutions to similar problems instead of training from scratch by employing transfer learning while adhering to causality to accelerate convergence and ensure accurate results across diverse scenarios. The primary contribution of this paper lies in introducing a causality-respecting PINN loss function in the context of structural engineering and coupling it with transfer learning to enhance the generalizability of PINNs in simulating the dynamics of beams on elastic foundations. Numerical experiments on the Euler–Bernoulli beam highlight the efficacy of the proposed approach for various initial conditions, including those with noise in the initial data. Furthermore, the potential of the proposed method is demonstrated for the Timoshenko beam in an extended spatial and temporal domain. Several comparisons suggest that the proposed method accurately captures the inherent dynamics, outperforming the state-of-the-art physics-informed methods under standard L²-norm metric and accelerating convergence.

This paper presents a new approach to simulate forward and inverse problems of moving loads using physics-informed machine learning (PIML). Physics-informed neural networks (PINNs) utilize the underlying physics of moving load problems and aim to predict the deflection of beams and the magnitude of the loads. The mathematical representation of the moving load considered involves a Dirac delta function, to capture the effect of the load moving across the structure. Approximating the Dirac delta function with PINNs is challenging because of its instantaneous change of output at a single point, causing difficulty in the convergence of the loss function. We propose to approximate the Dirac delta function with a Gaussian function. The incorporated Gaussian function physical equations are used in the physics-informed neural architecture to simulate beam deflections and to predict the magnitude of the load. Numerical results show that PIML is an effective method for simulating the forward and inverse problems for the considered model of a moving load.

The railway industry has the potential to make a strong contribution to the achievement of various sustainable development goals, by an expansion of its role in the transportation system of different countries. To realize this, complex technological and societal challenges are to be addressed, along with the development of suitable state-of-the-art methodologies fully tailored to the particular needs of the wide variety of railway infrastructure types and conditions. Artificial intelligence (AI) methods have been increasingly and successfully applied to solve practical problems in the railway infrastructure domain for over two decades. This paper proposes a review of the development of AI methods in railway infrastructure. First, we present a survey limited to selected journal papers published between 2010 and 2022. Bibliographical statistics are obtained, showing the increasing number of contributions in this field. Then, we select key AI methodologies and discuss their applications in the railway infrastructure. Next, AI methods for key railway components are analyzed. Finally, current challenges and future opportunities are discussed.

The interaction performance of the pantograph-catenary is of great importance as it directly determines the current collection quality and operational safety of trains. The finite element method (FEM) is dominantly used for simulating pantograph-catenary interaction, which is normally computationally heavy. In this work, addressing the tremendous computational cost of FEM models, a surrogate model for fast simulations of pantograph-catenary interaction is proposed using deep learning. A dataset containing 30,000 cases of pantograph-catenary interaction is generated by a validated FEM model. A Long-Short-Term-Memory (LSTM) neural network is proposed to learn the inherent nonlinearity between the input model parameters and the output pantograph-catenary contact force from data. The resulting prediction performance indicates that contact forces predicted by the surrogate model are consistent with those simulated by FEM, while the computational efforts of the surrogate model are negligible compared with FEM. Prediction performances using different network architectures and configurations are compared to determine the optimal setting for a pantograph-catenary system. The LSTM-based surrogate model shows high efficiency for simulating pantograph-catenary interactions and promising practicability in optimising catenary structural parameters for design or upgrade.

Reliable estimation of rail useful lifetime can provide valuable information for predictive maintenance in railway systems. However, in most cases, lifetime data is incomplete because not all pieces of rail experience failure by the end of the study horizon, a problem known as censoring. Ignoring or otherwise mistreating the censored cases might lead to false conclusions. Survival approach is particularly designed to handle censored data for analysing the expected duration of time until one event occurs, which is rail failure in this paper. This paper proposes a deep Bayesian survival approach named BNN-Surv to properly handle censored data for rail useful lifetime modelling. The proposed BNN-Surv model applies the deep neural network in the survival approach to capture the non-linear relationship between covariates and rail useful lifetime. To consider and quantify uncertainty in the model, Monte Carlo dropout, regarded as the approximate Bayesian inference, is incorporated into the deep neural network to provide the confidence interval of the estimated lifetime. The proposed approach is implemented on a four-year dataset including track geometry monitoring data, track characteristics data, various types of defect data, and maintenance and replacement (M&R) data collected from a section of railway tracks in Australia. Through extensive evaluation, including Concordance index (C-index) and root mean square error (RMSE) for evaluating model performance, as well as a proposed CW-index for evaluating uncertainty estimations, the effectiveness of the proposed approach is confirmed. The results show that, compared with other commonly used models, the proposed approach can achieve the best concordance index (C-index) of 0.80, and the estimated rail useful lifetimes are closer to real lifetimes. In addition, the proposed approach can provide the confidence interval of the estimated lifetime, with a correct coverage of 81% of the actual lifetime when the confidence interval is 1.38, which is more useful than point estimates in decision-making and maintenance planning of railroad systems.

This paper addresses the problem of determining the distribution of the return current in electric railway traction systems. The dynamics of traction return current are simulated in all three space dimensions by informing the neural networks with the Partial Differential Equations (PDEs) known as telegraph equations. In addition, this work proposes a method of choosing optimal activation functions for training the physics-informed neural network to solve higher-dimensional PDEs. We propose a Monte Carlo based framework to choose the activation function in lower dimensions, mitigating the need for ensemble training in higher dimensions. To further strengthen the applicability of the Monte Carlo based framework, experiments are presented under two loss functions governed by L2 and L∞ norms. The presented method efficiently simulates the traction return current for electric railway systems, even for three-dimensional problems.

The wind deflection of overhead contact lines (OCLs) challenges the stable and safe operation of electrified railways. The steady wind causes the static deflection of the contact line, while the fluctuating wind leads to the OCL buffeting. This paper performs a response spectrum analysis of the wind deflection caused by the combined effects of steady and fluctuating winds. Considering the initial configuration of OCL, an absolute nodal coordinate formulation method is employed to model the OCL. A spatial wind field including the fluctuating wind in three directions is constructed and the aerodynamic forces on the OCL are derived. A nonlinear solution procedure is proposed to include the geometrical nonlinearity and dropper slackness in the evaluation of static wind deflection. The pseudo-excitation method is utilised to evaluate the buffeting response of the OCL with stochastic wind load. The analysis results indicate that the dropper slackness has a significant effect on the vertical static deflection. Under an extreme wind speed of 40 m/s, the contact line is always within the safe working range of pantograph head when only the steady wind load is considered. However, the stochastic wind load causes non-negligible fluctuation of OCL, and the contact line may be outside of the pantograph working range under the same wind speed. Sensitivity analyses on the effects of some key parameters to the OCL buffeting suggest that the increases of damping ratio and the tension class are effective measures to improve the wind-resistance capability of OCL.

Brace sleeve (BS) fasteners, i.e., nut and bolt, are small components but play essential roles in fixing BS and cantilever in railway catenary system. They are commonly inspected by onboard cameras using computer vision to ensure the safety of railway operation. However, most BS fasteners cannot be directly localized because they are too small in the inspection images. Instead, the BS is first localized for detecting the BS fastener. This leads to a new problem that the localized BS boxes may not contain the complete BS fasteners due to low localization accuracy, making it infeasible to further diagnose the fastener conditions. To tackle this problem, this article proposes a novel pipeline for BS fastener looseness diagnosis. First, the competitive deep learning model Faster RCNN ResNet101 is used to coarsely localize BSs. Second, an action-driven reinforcement learning agent is adopted to refine the coarse-localized boxes through a dynamic position searching process. Then, BS fasteners are extracted from the refined localized BS image by the deep segmentation model YOLACT++, which is fast and interpretable. Finally, a looseness diagnosis criterion based on segmented information are proposed. We evaluate the performance of submodels independently and the overall performance of the whole model on a real-life catenary image dataset collected from a high-speed line in China. The test results show that the proposed method is effective for BS looseness detection in railway catenary.

In railway pantograph-catenary systems, the contact surfaces undergo wear in long-term operations, directly affecting interaction performance and potentially deteriorating the current collection quality. The effect of contact wire wear (CWW) on the current collection quality should be evaluated to understand the system's health status in operations. This article presents a stochastic analysis of the pantograph-catenary interaction performance with different levels of CWW based on four years of measurement data. The power spectral density (PSD) estimation is carried out on the measured CWW to obtain their frequency representations. The random time histories of CWW are generated based on the PSDs. A nonlinear finite element model of catenary with a lumped-mass pantograph is built. Using the Monte Carlo method, the stochastic analysis of pantograph-catenary contact force is carried out to investigate the distribution and dispersion of assessment indices with different levels of CWW. The results indicate that the CWW mainly affects the maximum and minimum contact forces instead of the contact force standard deviation. The optimal pantograph-catenary interaction performance is observed certain years after CWW is formed, depending on the traffic density of the railway line, which is at the second year in the presented case study. Then, the performance declines with an increase in service time. Also, higher operating speed causes a more significant dispersion in assessment indices representing a lower current collection quality, particularly at the maximum operating speed (70% of the catenary wave propagation speed).