Insightful Railway Track Evaluation: Leveraging NARX Feature Interpretation

Authors

  • Pedro H. O. Silva Department of Electrical Engineering, Federal University of Juiz de Fora (UFJF), Juiz de Fora, MG, Brazil,
  • Augusto S. Cerqueira Department of Electrical Engineering, Federal University of Juiz de Fora (UFJF), Juiz de Fora, MG, Brazil,
  • Erivelton Nepomuceno Centre for Ocean Energy Research, Department of Electronic Engineering Maynooth University, Ireland,

DOI:

https://doi.org/10.20906/CBA2024/4848

Keywords:

machine learning, system identification, NARX models, time series classfication, wheel–rail contact dynamic forces, railroad dynamics

Abstract

The classification of time series is essential for extracting meaningful insights and aiding decision-making in engineering domains. Parametric modeling techniques like NARX are invaluable for comprehending intricate processes, such as environmental time series, owing to their easily interpretable and transparent structures. This article introduces a classification algorithm, Logistic-NARX Multinomial, which merges the NARX methodology with logistic regression. This approach not only produces interpretable models but also effectively tackles challenges associated with multiclass classification. Furthermore, this study introduces an innovative methodology tailored for the railway sector, offering a tool by employing NARX models to interpret the multitude of features derived from onboard sensors. This solution provides profound insights through feature importance analysis, enabling informed decision-making regarding safety and maintenance.

Downloads

Published

2024-10-18

Issue

Section

Articles