Failure Prediction - An Application in the Railway Industry

Machine or system failures have high impact both at technical and economic levels. Most modern equipment has logging systems that allow us to collect a diversity of data regarding their operation and health. Using data mining models for novelty detection enables us to explore those datasets, building classification systems that can detect and issue an alert when a failure starts evolving, avoiding the unknown development up to breakdown. In the present case we use a failure detection system to predict train doors breakdowns before they happen using data from their logging system. We study three methods for failure detection: outlier detection, novelty detection and a supervised SVM. Given the problem’s features, namely the possibility of a passenger interrupting the movement of a door, the three predictors are prone to false alarms. The main contribution of this work is the use of a low-pass filter to process the output of the predictors leading to a strong reduction in the false alarm rate.

[1]  David L. Iverson.  Data Mining Applications for Space Mission Operations System Health Monitoring , 2008 .

[2]  Sameer Singh,et al.  Novelty detection: a review - part 1: statistical approaches , 2003, Signal Process..

[3]  Pascal Poncelet,et al.  SO_MAD: SensOr Mining for Anomaly Detection in Railway Data , 2009, ICDM.

[4]  Anthony M. Smith,et al.  Reliability-Centered Maintenance , 1992 .

[5]  Josiah C. Hoskins,et al.  Artificial neural network models for knowledge representation in chemical engineering , 1990 .

[6]  Eamonn J. Keogh,et al.  Finding surprising patterns in a time series database in linear time and space , 2002, KDD.

[7]  Lyle H. Ungar,et al.  Adaptive networks for fault diagnosis and process control , 1990 .

[8]  Andrew Hess,et al.  A helicopter powertrain diagnostics and prognostics demonstration , 2000, 2000 IEEE Aerospace Conference. Proceedings (Cat. No.00TH8484).

[9]  Srinivas Katipamula,et al.  Review Article: Methods for Fault Detection, Diagnostics, and Prognostics for Building Systems—A Review, Part I , 2005 .

[10]  Nathalie Japkowicz,et al.  A Novelty Detection Approach to Classification , 1995, IJCAI.

[11]  J. Moubray.  Reliability-Centered Maintenance , 1991 .

[12]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[13]  George W. Irwin,et al.  Intelligent Computing in Signal Processing and Pattern Recognition: International Conference on Intelligent Computing, ICIC 2006Kunming, China, August, ... Notes in Control and Information Sciences) , 2006 .

[14]  B. Babu,et al.  ADAPTIVE NETWORKS FOR FAULT DIAGNOSIS AND PROCESS CONTROL , 2002 .

[15]  Fatih Camci,et al.  Failure prediction on railway turnouts using time delay neural networks , 2010, 2010 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications.

[16]  Paul M. Frank,et al.  Issues of Fault Diagnosis for Dynamic Systems , 2010, Springer London.

[17]  Ashraf Saad,et al.  Evolving an artificial neural network classifier for condition monitoring of rotating mechanical systems , 2007, Appl. Soft Comput..

[18]  Jiafan Zhang,et al.  Novel Fault Class Detection Based on Novelty Detection Methods , 2006 .

[19]  Rolf Isermann,et al.  Process fault detection based on modeling and estimation methods - A survey , 1984, Autom..

[20]  Thomas Parisini,et al.  Fault Detection in Mechanical Systems With Friction Phenomena: An Online Neural Approximation Approach , 2007, IEEE Transactions on Neural Networks.

[21]  Venkat Venkatasubramanian,et al.  Representing and diagnosing dynamic process data using neural networks , 1992 .

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

[23]  Stephen Jose Hanson,et al.  A Neural Network Autoassociator for Induction Motor Failure Prediction , 1995, NIPS.

[24]  Michèle Basseville,et al.  Detection of abrupt changes: theory and application , 1993 .

[25]  Peter A. Flach,et al.  Evaluation Measures for Multi-class Subgroup Discovery , 2009, ECML/PKDD.

[26]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[27]  John C. Platt,et al.  Fast training of support vector machines using sequential minimal optimization, advances in kernel methods , 1999 .

[28]  Petra Perner,et al.  Advances in Data Mining , 2002, Lecture Notes in Computer Science.

[29]  Jiawei Han,et al.  Data Mining: Concepts and Techniques , 2000 .

[30]  B. A. Shenoi,et al.  Introduction to Digital Signal Processing and Filter Design , 2005 .

[31]  Eamonn J. Keogh,et al.  A symbolic representation of time series, with implications for streaming algorithms , 2003, DMKD '03.

[32]  Michèle Basseville,et al.  Detecting changes in signals and systems - A survey , 1988, Autom..

[33]  Thorsten Meinl,et al.  KNIME: The Konstanz Information Miner , 2007, GfKl.

[34]  Ian H. Witten,et al.  One-Class Classification by Combining Density and Class Probability Estimation , 2008, ECML/PKDD.

[35]  Venkat Venkatasubramanian,et al.  A neural network methodology for process fault diagnosis , 1989 .

[36]  Charu C. Aggarwal,et al.  Outlier Analysis , 2013, Springer New York.

[37]  Jesús S. Aguilar-Ruiz,et al.  Knowledge discovery from data streams , 2009, Intell. Data Anal..

[38]  Eamonn J. Keogh,et al.  HOT SAX: efficiently finding the most unusual time series subsequence , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[39]  Eamonn J. Keogh,et al.  Efficient Discovery of Unusual Patterns in Time Series , 2006, New Generation Computing.

[40]  Pascal Poncelet,et al.  Anomaly detection in monitoring sensor data for preventive maintenance , 2011, Expert Syst. Appl..