Rail Crack Propagation Forecasting Using Multi-horizons RNNs - IRT SystemX Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Rail Crack Propagation Forecasting Using Multi-horizons RNNs

Sara Yasmine Ouerk
  • Fonction : Auteur
Olivier Vo Van
  • Fonction : Auteur
Mouadh Yagoubi
  • Fonction : Auteur

Résumé

The prediction of rail crack length propagation plays a crucial role in the maintenance and safety assessment of materials and structures. Traditional methods rely on physical models and empirical equations such as Paris' law, which often have limitations in capturing the complex nature of crack growth. In recent years, machine learning techniques, particularly Recurrent Neural Networks (RNNs), have emerged as promising methods for time series forecasting. They allow to model time series data, and to incorporate exogenous variables into the model. The proposed approach involves collecting real data on the French rail network that includes historical crack length measurements, along with relevant exogenous factors that may influence crack growth. First, a preprocessing phase was performed to prepare a consistent data set for learning. Then, a suitable Bayesian multi-horizons recurrent architecture was designed to model the crack propagation phenomenon. Obtained results show that the Multi-horizons model outperforms state-of-the-art models such as LSTM and GRU.
Fichier principal
Vignette du fichier
ECML_2023 (20).pdf (914.78 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04212352 , version 1 (20-09-2023)

Identifiants

  • HAL Id : hal-04212352 , version 1

Citer

Sara Yasmine Ouerk, Olivier Vo Van, Mouadh Yagoubi. Rail Crack Propagation Forecasting Using Multi-horizons RNNs. Advanced Analytics and Learning on Temporal Data | Workshop and Tutorial @ ECML-PKDD 2023, Sep 2023, Turin (Italie), Italy. ⟨hal-04212352⟩

Collections

IRT-SYSTEMX
43 Consultations
13 Téléchargements

Partager

Gmail Facebook X LinkedIn More