Set-Membership Type-1 Fuzzy Logic System Applied to Fault Classification in a Switch Machine

This paper focuses on the classification of faults in an electromechanical switch machine, which is an equipment used for handling railroad switches. In this paper, we introduce the use of Set-Membership concept, derived from the adaptive filter theory, into the training procedure of type-1 and singleton/non-singleton fuzzy logic systems, in order to reduce computational complexity and to increase convergence speed. We also present different criteria for using along with Set-Membership. Furthermore, we discuss the usefulness of delta rule delta, local Lipschitz estimation, variable step size, and variable step size adaptive techniques to yield additional improvement in terms of computational complexity reduction and convergence speed. Based on data set provided by a Brazilian railway company, which covers the four possible faults in a switch machine, we present performance analysis in terms of classification ratio, convergence speed, and computational complexity reduction. The reported results show that the proposed models result in improved convergence speed, slightly higher classification ratio, and remarkable computation complexity reduction when we limit the number of epochs for training, which may be required due to real-time constraint or low computational resource availability.

[1]  Yongduan Song,et al.  Neuro-Adaptive Fault-Tolerant Approach for Active Suspension Control of High-Speed Trains , 2015, IEEE Transactions on Intelligent Transportation Systems.

[2]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[3]  Joaquín Maroto,et al.  Methodology for Multiobjective Optimization of the AC Railway Power Supply System , 2015, IEEE Transactions on Intelligent Transportation Systems.

[4]  Jerry M. Mendel,et al.  Tutorial on higher-order statistics (spectra) in signal processing and system theory: theoretical results and some applications , 1991, Proc. IEEE.

[5]  Clive Roberts,et al.  Life cycle costs for railway condition monitoring , 2008 .

[6]  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.

[7]  M.V. Ribeiro,et al.  Signal Decomposition With Reduced Complexity for Classification of Isolated and Multiple Disturbances in Electric Signals , 2009, IEEE Transactions on Power Delivery.

[8]  T. Asada,et al.  Development of an effective condition monitoring system for AC point machines , 2011 .

[9]  F. Camci,et al.  Failure diagnostics for railway point machines using expert systems , 2009, 2009 IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives.

[10]  Tao Tang,et al.  Measurements and Analysis of Large-Scale Fading Characteristics in Curved Subway Tunnels at 920 MHz, 2400 MHz, and 5705 MHz , 2015, IEEE Transactions on Intelligent Transportation Systems.

[11]  Rodrigo C. de Lamare,et al.  Low-Complexity Reduced-Rank Linear Interference Suppression Based on Set-Membership Joint Iterative Optimization for DS-CDMA Systems , 2011, IEEE Transactions on Vehicular Technology.

[12]  Mehmet Sevkli,et al.  A Simple State-Based Prognostic Model for Railway Turnout Systems , 2011, IEEE Transactions on Industrial Electronics.

[13]  L. Armijo.  Minimization of functions having Lipschitz continuous first partial derivatives. , 1966 .

[14]  George D. Magoulas,et al.  Improving the Convergence of the Backpropagation Algorithm Using Learning Rate Adaptation Methods , 1999, Neural Computation.

[15]  Ricardo Tanscheit,et al.  EANN 2014: a fuzzy logic system trained by conjugate gradient methods for fault classification in a switch machine , 2015, Neural Computing and Applications.

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

[17]  Hamid Eskandari,et al.  Performance study of Set-Membership NLMS algorithm over an adaptive incremental network , 2013, ICCKE 2013.

[18]  Jovan M. Nahman.  Dependability of Engineering Systems , 2002 .

[19]  Plamen Angelov,et al.  Real-Time Fault Detection Using Recursive Density Estimation , 2014, Journal of Control, Automation and Electrical Systems.

[20]  F Garciamarquez,et al.  A reliability centered approach to remote condition monitoring. A railway points case study , 2003 .

[21]  Nan Yu,et al.  Application of Delta-bar-Delta Rules Trained Back-Propagation Neural Networks in Nuclear Fusion Pattern Recognition , 2010, 2010 International Symposium on Intelligence Information Processing and Trusted Computing.

[22]  Yongbin Wei,et al.  The stability of variable step-size LMS algorithms , 1999, IEEE Trans. Signal Process..

[23]  T. Feuring,et al.  A fuzzy-controlled delta-bar-delta learning rule , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[24]  Moises V. Ribeiro,et al.  Reduced Rank Adaptive Filter with Variable Step Size for Impulsive UWB PLC Systems , 2015 .

[25]  Ricardo Tanscheit,et al.  Classification of Events in Switch Machines Using Bayes, Fuzzy Logic System and Neural Network , 2014, EANN.

[26]  Paulo S. R. Diniz,et al.  Adaptive Filtering: Algorithms and Practical Implementation , 1997 .

[27]  Simon Haykin,et al.  Adaptive filter theory (2nd ed.) , 1991 .

[28]  J. Mendel.  Uncertain Rule-Based Fuzzy Logic Systems: Introduction and New Directions , 2001 .

[29]  Moisés Vidal Ribeiro,et al.  Learning Rate Updating Methods Applied to Adaptive Fuzzy Equalizers for Broadband Power Line Communications , 2004, EURASIP J. Adv. Signal Process..

[30]  Plamen P. Angelov,et al.  Fully unsupervised fault detection and identification based on recursive density estimation and self-evolving cloud-based classifier , 2015, Neurocomputing.

[31]  Rodrigo C. de Lamare,et al.  Low-Complexity Constrained Adaptive Reduced-Rank Beamforming Algorithms , 2013, IEEE Transactions on Aerospace and Electronic Systems.

[32]  Robert A. Jacobs,et al.  Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.

[33]  Richard W. Harris,et al.  A variable step (VS) adaptive filter algorithm , 1986, IEEE Trans. Acoust. Speech Signal Process..

[34]  Ping Xue,et al.  Analysis and implementation of variable step size adaptive algorithms , 1993, IEEE Trans. Signal Process..

[35]  Razali Ngah,et al.  Variable step-size l0-norm NLMS algorithm for sparse channel estimation , 2014, 2014 IEEE Asia Pacific Conference on Wireless and Mobile.