Int J Performability Eng ›› 2015, Vol. 11 ›› Issue (2): 121-134.doi: 10.23940/ijpe.15.2.p121.mag

• Original articles • Previous Articles     Next Articles

Development and Application of Deep Belief Networks for Predicting Railway Operation Disruptions


  1. 1 Institute of Data Analysis and Process Design, Zurich University of Applied Sciences (ZHAW), SWITZERLAND
    2 Department of Civil and Environmental Engineering, Massachusetts Institute of Technology, USA
    3 Chair on Systems Science and the Energetic Challenge, European Foundation for New Energy-Electricité de France (EDF) at école Centrale Paris and SUPELEC, FRANCE
    4 Department of Energy, Politecnico di Milano, ITALY
    5 Institute for Transport Planning and Systems, ETH Zurich, SWITZERLAND


In this paper, we propose to apply deep belief networks (DBN) to predict potential operational disruptions caused by rail vehicle door systems. DBN are a powerful algorithm that is able to detect and extract complex patterns and features in data and has demonstrated superior performance on several benchmark studies. A case study is shown whereby the DBN are trained and applied on real case study from a railway vehicle fleet. The DBN were shown to outperform a feedforward neural network trained by a genetic algorithm.

Received on May 11, 2014, revised on September 25, 2014
References: 24