Fuzzy Classification With Restricted Boltzman Machines and Echo-State Networks for Predicting Potential Railway Door System Failures
作者： Olga Fink , Enrico Zio , Ulrich Weidmann
关键词:
摘要: In this paper, a fuzzy classification approach applying combination of Echo-State Networks (ESNs) and Restricted Boltzmann Machine (RBM) is proposed for predicting potential railway rolling stock system failures using discrete-event diagnostic data. The demonstrated on case study door with real Fuzzy enables the use linguistic variables definition time intervals in which are predicted to occur. It provides more intuitive way handle predictions by users, increases acceptance approach. research results confirm suitability algorithms failures. shows good performance terms prediction accuracy study.
archives-ouvertes.fr
sci-hub.se 参考文章(37)
Geoffrey E. Hinton, A Practical Guide to Training Restricted Boltzmann Machines Neural Networks: Tricks of the Trade (2nd ed.). pp. 599- 619 ,(2012) , 10.1007/978-3-642-35289-8_32
David Verstraeten, Reservoir Computing: computation with dynamical systems Ghent University. Faculty of Engineering. ,(2009)
Simon S. Haykin, Neural Networks And Learning Machines ,(2010)
Olga Fink, Failure and degradation prediction by artificial neural networks Schriftenreihe / Institut für Verkehrsplanung und Transportsysteme. ,vol. 165, ,(2014) , 10.3929/ETHZ-A-010147170
Christopher M. Bishop, Pattern Recognition and Machine Learning ,(2006)
F. B. Zhou, M. D. Duta, M. P. Henry, S. Baker, C. Burton, Remote condition monitoring for railway point machine ASME/IEEE Joint Railroad Conference. pp. 103- 108 ,(2002) , 10.1115/RTD2002-1646
Herbert Jaeger, Mantas Lukoševičius, Dan Popovici, Udo Siewert, 2007 Special Issue: Optimization and applications of echo state networks with leaky- integrator neurons Neural Networks. ,vol. 20, pp. 335- 352 ,(2007) , 10.1016/J.NEUNET.2007.04.016
W.L. Tan, N.M. Nor, M.Z. Abu Bakar, Z. Ahmad, S.A. Sata, Optimum parameters for fault detection and diagnosis system of batch reaction using multiple neural networks Journal of Loss Prevention in The Process Industries. ,vol. 25, pp. 138- 141 ,(2012) , 10.1016/J.JLP.2011.08.002
J. Chen, C. Roberts, P. Weston, Fault detection and diagnosis for railway track circuits using neuro-fuzzy systems Control Engineering Practice. ,vol. 16, pp. 585- 596 ,(2008) , 10.1016/J.CONENGPRAC.2007.06.007
Olga Fink, Enrico Zio, Ulrich Weidmann, Predicting time series of railway speed restrictions with time-dependent machine learning techniques Expert Systems With Applications. ,vol. 40, pp. 6033- 6040 ,(2013) , 10.1016/J.ESWA.2013.04.038