Extreme learning machines for predicting operation disruption events in railway systems

Olga Fink (1) , Enrico Zio (2) , Ulrich Weidmann (1)

1 Institute for Transport Planning and Systems
2 SSEC - Chaire Sciences des Systèmes et Défis Energétiques EDF/ECP/Supélec

European passenger rail systems are massively interconnected and operate with very high frequency. The impacts of component failures on these types of systems can significantly aff ect technical and operational reliability. Therefore, many advanced railway systems and components are equipped with monitoring and diagnostic tools to improve reliability and reduce maintenance expenditures. Approaches to predict component failure and remaining useful life are usually based on continuously measured data. The use of event data is limited, especially for predicting failures in railway systems. In this paper, we apply Extreme Learning Machines (ELM) to predict the occurrence of railway operation disruptions based on discrete-event data. ELM exhibit a good generalization ability, are computationally very e cient and do not require tuning of network parameters. For exemplification purposes, a case study with real data is considered concerning failures that cause undemanded service brake application of railway vehicles. While other machine learning techniques, such as multilayer perceptrons and feed forward neural networks with learning based on genetic algorithms, were not able to extract patterns in the diagnostic event data, the proposed approach was capable of predicting 98% of the operation disruption events correctly.

Domains: Engineering Sciences [physics]; Other

Olga Fink, Enrico Zio, Ulrich Weidmann. Extreme learning machines for predicting operation disruption events in railway systems. ESREL 2013, Sep 2013, Amsterdam, Netherlands. pp.1-8. ⟨hal-00930954⟩