document

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

Kapoor, T. (author), Wang, H. (author), Nunez, Alfredo (author), Dollevoet, R.P.B.J. (author)

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...

journal article 2024

document

Condition monitoring of railway transition zones using acceleration measurements on multiple axle boxes: Case studies in the Netherlands, Sweden, and Norway

Wang, L. (author), Unsiwilai, S. (author), Zeng, Y. (author), Shen, C. (author), Hendriks, J.M. (author), Moraal, J. (author), Zoeteman, A. (author), Nunez, Alfredo (author), Dollevoet, R.P.B.J. (author), Li, Z. (author)

Railway transition zones connecting conventional embankments and rigid struc-tures, such as bridges and tunnels, usually degrade much faster than other railway sections. Efficient health condition monitoring of transition zones is important for preventative track maintenance. In this paper, a methodology for monitoring rail-way transition zones...

conference paper 2024

document

Detection of Rail Surface Defects based on Axle Box Acceleration Measurements: A Measurement Campaign in Sweden

Phusakulkajorn, W. (author), Hendriks, J.M. (author), Moraal, J. (author), Shen, C. (author), Zeng, Y. (author), Unsiwilai, S. (author), Bogojevic, B. (author), Asplund, Matthias (author), Zoeteman, A. (author), Nunez, Alfredo (author), Dollevoet, R.P.B.J. (author), Li, Z. (author)

This work presents the results of a measurement campaign to demonstrate the effectiveness of the axle box acceleration (ABA) technology for detecting rail defects. The measurements were conducted along the Iron Ore line between Sweden and Norway for the IN2TRACK3 project. This line is mostly single-track with passenger-freight mixed traffic and...

conference paper 2024

document

Neural Oscillators for Generalization of Physics-Informed Machine Learning

Kapoor, T. (author), Chandra, Abhishek (author), Tartakovsky, Daniel M. (author), Wang, H. (author), Nunez, Alfredo (author), Dollevoet, R.P.B.J. (author)

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...

journal article 2024

document

An Interpretable Method for Operational Modal Analysis in Time-Frequency Representation and Its Applications to Railway Sleepers

Zeng, Y. (author), Shen, C. (author), Nunez, Alfredo (author), Dollevoet, R.P.B.J. (author), Zhang, Weihua (author), Li, Z. (author)

Operational modal analysis (OMA) enables the identification of modal characteristics under operational loads and conditions. Traditional frequency-domain methods cannot directly capture modal changes over time, while existing time-frequency representations are not sufficiently interpretable due to spurious modes and implicit parameter design....

journal article 2023

document

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

Vernaillen, T. (author), Wang, L. (author), Nunez, Alfredo (author), Dollevoet, R.P.B.J. (author), Li, Z. (author)

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...

journal article 2023

document

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

Kapoor, T. (author), Wang, H. (author), Nunez, Alfredo (author), Dollevoet, R.P.B.J. (author)

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...

journal article 2023

document

Intelligent Data Fusion for Anomaly Detection in Dutch Railway Catenary Condition Monitoring

Wang, H. (author), Hendriks, J.M. (author), Dollevoet, R.P.B.J. (author), Zoeteman, Arjen (author), Nunez, Alfredo (author)

Aiming to handle the increasing variety and volume of railway infrastructure monitoring data, this paper explores the use of intelligent data fusion methods for automatic anomaly detection of railway catenaries. Three classical data dimensionality reduction methods, namely the principal component analysis (PCA), the autoencoder neural network,...

conference paper 2022

document

Mechanism of short pitch rail corrugation: initial excitation and frequency selection for consistent initiation and growth

Li, Z. (author), Li, S. (author), Zhang, P. (author), Nunez, Alfredo (author), Dollevoet, R.P.B.J. (author)

This paper proposes a new hypothesis for the formation process of short pitch rail corrugation. An FE wheel-track dynamic model is utilized to verify the hypothesis by reproducing corrugation initiation and consistent growth. It is found longitudinal compression modes are responsible for corrugation initiation with necessary initial...

journal article 2022

document

A multiple spiking neural network architecture based on fuzzy intervals for anomaly detection: a case study of rail defects

Phusakulkajorn, W. (author), Hendriks, J.M. (author), Moraal, J. (author), Dollevoet, R.P.B.J. (author), Li, Z. (author), Nunez, Alfredo (author)

In this paper, a fuzzy interval-based method is proposed for solving the problem of rail defect detection relying on an on-board measurement system and a multiple spiking neural network architecture. Instead of outputting binary values (defect or not defect), all data will belong to both classes with different spreads that are given by two fuzzy...

conference paper 2022

document

Predicting traction return current in electric railway systems through physics-informed neural networks

Kapoor, T. (author), Wang, H. (author), Nunez, Alfredo (author), Dollevoet, R.P.B.J. (author)

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...

conference paper 2022

document

Multi-criteria evaluation of wheel/rail degradation at railway crossings

Wei, Z. (author), Nunez, Alfredo (author), Liu, Xiubo (author), Dollevoet, R.P.B.J. (author), Li, Z. (author)

This study evaluates the degradation of wheels and rails at railway crossings. The evaluation method is composed of 1) finite element simulation of dynamic wheel/crossing interaction and 2) multi-criteria analysis of wheel/rail degradation in terms of yield behavior, rolling contact fatigue (RCF) and wear. With the aid of this method, we...

journal article 2020

document

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

Wang, H. (author), Nunez, Alfredo (author), Liu, Zhigang (author), Zhang, Dongliang (author), Dollevoet, R.P.B.J. (author)

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...

journal article 2020

document

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

Wang, H. (author), Liu, Zhigang (author), Nunez, Alfredo (author), Dollevoet, R.P.B.J. (author)

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...

journal article 2019

document

Smart technology solutions for the NeTIRail-INFRA case study lines: Axle box acceleration and ultra-low cost smartphones

Nunez, Alfredo (author), Popa, Tudor (author), Anghel, Lucian Emmanuel (author), Hendriks, J.M. (author), Moraal, J. (author), Buretea, Laurentiu Dorin (author), Paragreen, Jon (author), Miron, Berbece (author), Gheorghe, Draghici (author), Campean, Mihail (author), Dollevoet, R.P.B.J. (author), Li, Z. (author)

In this paper, we present preliminary results on the development of smart technology solutions for lower density railway lines. The goal is to reach a cost effective inspection and asset management to minimize maintenance<br/>interventions time/cost without dedicated inspection vehicles. The proposed methods include axle box acceleration...

conference paper 2018

document

Smart technology solutions for the NeTIRail-INFRA case study lines: Axle box acceleration and ultra-low cost smartphones

Nunez, Alfredo (author), Popa, Tudor (author), Anghel, Lucian Emmanuel (author), Hendriks, J.M. (author), Moraal, J. (author), Buretea, Laurentiu Dorin (author), Paragreen, Jon (author), Miron, Berbece (author), Gheorghe, Draghici (author), Campean, Mihail (author), Dollevoet, R.P.B.J. (author), Li, Z. (author)

Results on the development of smart technology solutions for lower density<br/>railway lines are presented. The goal is to reach a cost effective inspection and<br/>asset management to minimize maintenance interventions time/cost without<br/>dedicated inspection vehicles. The proposed methods in this paper include: 1) axle box acceleration...

poster 2018

document

Method for evaluating the performance of railway crossing rails after long-term service

Wei, Z. (author), Nunez, Alfredo (author), Boogaard, M.A. (author), Dollevoet, R.P.B.J. (author), Li, Z. (author)

In this paper, we present a method for evaluating the performance of railway crossing rails after long-term service. The method includes 1) 3D profile and hardness measurements; 2) finite element simulation of wheel/rail interaction; and 3) numerical prediction of rail degradation. We conducted a case study on a crossing that had been in service...

journal article 2018

document

Rail Condition Monitoring using Axle Box Acceleration Measurements: Defect detection in the Netherlands and Romania

Nunez, Alfredo (author), Hendriks, J.M. (author), Moraal, J. (author), Ramirez Fonseca, I. (author), Dollevoet, R.P.B.J. (author), Li, Z. (author)

In this paper we discuss rail condition monitoring based on axle box acceleration (ABA) measurements. We present three case studies. The first one in The Netherlands, the detection of local defects with different severity levels (squat A, squat B and squat C) is analysed. The second case from the Faurei testing ring in Romania, the detection of...

conference paper 2018

document

A decision support approach for condition-based maintenance of rails based on big data analysis

Jamshidi, A. (author), Hajizadeh, S. (author), Su, Z. (author), Naeimi, M. (author), Nunez, Alfredo (author), Dollevoet, R.P.B.J. (author), De Schutter, B.H.K. (author), Li, Z. (author)

In this paper, a decision support approach is proposed for condition-based maintenance of rails relying on expert-based systems. The methodology takes into account both the actual conditions of the rails (using axle box acceleration measurements and rail video images) and the prior knowledge of the railway track. The approach provides an...

journal article 2018

document

A condition-based maintenance methodology for rails in regional railway networks using evolutionary multiobjective optimization: Case study line Braşov to Zărneşti in Romania

Nunez, Alfredo (author), Jamshidi, A. (author), Wang, H. (author), Hendriks, J.M. (author), Ramirez Fonseca, I. (author), Moraal, J. (author), Dollevoet, R.P.B.J. (author), Li, Z. (author)

In this paper, we propose a methodology based on signal processing and evolutionary multiobjective optimization to facilitate the maintenance decision making of infra-managers in regional railways. Using a train in operation (with passengers onboard), we capture the condition of the rails using Axle Box Acceleration measurements. Then, using...

conference paper 2018