Transfer learning for improved generalizability in causal physics-informed neural networks for beam simulations

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...

Neural Oscillators for Generalization of Physics-Informed Machine Learning

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...

Rail wear rate on the Belgian railway network: a big-data analysis

This paper presents a big data-based analysis of the rail wear of the whole Belgian railway network measured in 2012 and 2019. Wear rates are reported, discussed, and quantitatively formulated as functions of critical factors in terms of curve radius, annual tonnage (rail age), high rail in curves, an average from both rails in straight...

Physics-Informed Neural Networks for Solving Forward and Inverse Problems in Complex Beam Systems

This article proposes a new framework using physics-informed neural networks (PINNs) to simulate complex structural systems that consist of single and double beams based on Euler–Bernoulli and Timoshenko theories, where the double beams are connected with a Winkler foundation. In particular, forward and inverse problems for the Euler–Bernoulli...

Ground vibration induced by high speed trains on an embankment with pile-board foundation: Modelling and validation with in situ tests

To investigate the train-induced ground vibration, an explicit time-domain, three dimensional (3D) finite element (FE) model is developed. The train, track, embankment, pile-board structure and nearby ground soils are all fully coupled in this model. The complex geometries involving the track components and pile-board structure are all...

A Bayesian Network Approach for Condition Monitoring of High-Speed Railway Catenaries

The growing variety of data from condition monitoring of high-speed railways offer unprecedented opportunities to improve railway infrastructure maintenance. For condition monitoring of railway catenaries, this paper proposes a data-driven approach that uses a Bayesian network (BN) to integrate the inspection data from catenaries into a key...

Entropy-Based Local Irregularity Detection for High-Speed Railway Catenaries With Frequent Inspections

The condition-based maintenance of high-speed railway catenary is an important task to ensure the continuous availability of train power supply. To improve the condition monitoring of catenary, this paper presents a novel scheme to detect catenary local irregularities using pantograph head acceleration measurements. First, a series of...

Analysis of the evolvement of contact wire wear irregularity in railway catenary based on historical data

This paper studies the evolvement of the wear irregularity of contact wire using wire thickness data measured yearly from a section of railway catenary. The power spectral density and time–frequency representation based on the wavelet transform are employed for data analysis, with an emphasis on local wear irregularities that are crucial for...

Ensemble EMD-based automatic extraction of the catenary structure wavelength from the pantograph-catenary contact corce

This paper explores the use of pantograph-catenary contact force (PCCF) for monitoring of the current collection quality and detection of anomalies in the interaction between pantograph and catenary. The concept of catenary structure wavelength (CSW) is proposed as the dominant component of PCCF. It describes the signal components caused by the...