Fuzzy Classification With Restricted Boltzman Machines and Echo-State Networks for Predicting Potential Railway Door System Failures

In this paper, a fuzzy classification approach applying a combination of Echo-State Networks (ESNs) and a Restricted Boltzmann Machine (RBM) is proposed for predicting potential railway rolling stock system failures using discrete-event diagnostic data. The approach is demonstrated on a case study of a railway door system with real data. Fuzzy classification enables the use of linguistic variables for the definition of the time intervals in which the failures are predicted to occur. It provides a more intuitive way to handle the predictions by the users, and increases the acceptance of the proposed approach. The research results confirm the suitability of the proposed combination of algorithms for use in predicting railway rolling stock system failures. The proposed combination of algorithms shows good performance in terms of prediction accuracy on the railway door system case study.

[1]  Zhigang Tian,et al.  A neural network approach for remaining useful life prediction utilizing both failure and suspension histories , 2010 .

[2]  Zainal Ahmad,et al.  Optimum parameters for fault detection and diagnosis system of batch reaction using multiple neural networks , 2012 .

[3]  P. Dersin,et al.  PHM for railway system — A case study on the health assessment of the point machines , 2012, 2012 IEEE Conference on Prognostics and Health Management.

[4]  Mantas Lukosevicius,et al.  A Practical Guide to Applying Echo State Networks , 2012, Neural Networks: Tricks of the Trade.

[5]  Lotfi A. Zadeh,et al.  Outline of a New Approach to the Analysis of Complex Systems and Decision Processes , 1973, IEEE Trans. Syst. Man Cybern..

[6]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[7]  Ulrich Weidmann,et al.  Predicting Potential Railway Operational Disruptions with Echo State Networks , 2013 .

[8]  Clive Roberts,et al.  Industrial fault diagnosis: Pneumatic train door case study , 2002 .

[9]  David W. Coit,et al.  Neural Network Models to Anticipate Failures of Airport Ground Transportation Vehicle Doors , 2010, IEEE Transactions on Automation Science and Engineering.

[10]  A. E. Hoerl,et al.  Ridge regression: biased estimation for nonorthogonal problems , 2000 .

[11]  Herbert Jaeger,et al.  Optimization and applications of echo state networks with leaky- integrator neurons , 2007, Neural Networks.

[12]  Paul Weston,et al.  Fault detection and diagnosis for railway track circuits using neuro-fuzzy systems , 2008 .

[13]  Geoffrey E. Hinton,et al.  Restricted Boltzmann machines for collaborative filtering , 2007, ICML '07.

[14]  Geoffrey E. Hinton,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[15]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[16]  Chee Peng Lim,et al.  Offline and online fault detection and diagnosis of induction motors using a hybrid soft computing model , 2013, Appl. Soft Comput..

[17]  Olga Fink.  Failure and degradation prediction by artificial neural networks , 2014 .

[18]  Enrico Zio,et al.  Extreme learning machines for predicting operation disruption events in railway systems , 2013 .

[19]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[20]  Enrico Zio,et al.  Anticipating railway operation disruption events based on the analysis of discrete-event diagnostic data , 2013 .

[21]  Yoshua Bengio,et al.  Gradient-Based Optimization of Hyperparameters , 2000, Neural Computation.

[22]  K. I. Ramachandran,et al.  Feature selection using Decision Tree and classification through Proximal Support Vector Machine for fault diagnostics of roller bearing , 2007 .

[23]  Khashayar Khorasani,et al.  Fault detection and isolation of a dual spool gas turbine engine using dynamic neural networks and multiple model approach , 2014, Inf. Sci..

[24]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[25]  V. Ebrahimipour,et al.  A flexible algorithm for fault diagnosis in a centrifugal pump with corrupted data and noise based on ANN and support vector machine with hyper-parameters optimization , 2013, Appl. Soft Comput..

[26]  Riti Singh,et al.  Advanced engine diagnostics using artificial neural networks , 2003, Appl. Soft Comput..

[27]  Rob Law,et al.  Complex system fault diagnosis based on a fuzzy robust wavelet support vector classifier and an adaptive Gaussian particle swarm optimization , 2010, Inf. Sci..

[28]  C. Burton,et al.  Remote condition monitoring for railway point machine , 2002, ASME/IEEE Joint Railroad Conference.

[29]  Geoffrey E. Hinton,et al.  Factored conditional restricted Boltzmann Machines for modeling motion style , 2009, ICML '09.

[30]  Daming Lin,et al.  A review on machinery diagnostics and prognostics implementing condition-based maintenance , 2006 .

[31]  Paul Weston,et al.  Failure analysis and diagnostics for railway trackside equipment , 2007 .

[32]  Enrico Zio,et al.  Predicting component reliability and level of degradation with complex-valued neural networks , 2014, Reliab. Eng. Syst. Saf..

[33]  N. R. Sakthivel,et al.  Soft computing approach to fault diagnosis of centrifugal pump , 2012, Appl. Soft Comput..

[34]  David Verstraeten.  Reservoir Computing: computation with dynamical systems , 2009 .

[35]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[36]  Herbert Jaeger,et al.  A tutorial on training recurrent neural networks , covering BPPT , RTRL , EKF and the " echo state network " approach - Semantic Scholar , 2005 .

[37]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[38]  Enrico Zio,et al.  Predicting time series of railway speed restrictions with time-dependent machine learning techniques , 2013, Expert Syst. Appl..