A SVM framework for fault detection of the braking system in a high speed train

Abstract In April 2015, the number of operating High Speed Trains (HSTs) in the world has reached 3603. An efficient, effective and very reliable braking system is evidently very critical for trains running at a speed around 300 km/h. Failure of a highly reliable braking system is a rare event and, consequently, informative recorded data on fault conditions are scarce. This renders the fault detection problem a classification problem with highly unbalanced data. In this paper, a Support Vector Machine (SVM) framework, including feature selection, feature vector selection, model construction and decision boundary optimization, is proposed for tackling this problem. Feature vector selection can largely reduce the data size and, thus, the computational burden. The constructed model is a modified version of the least square SVM, in which a higher cost is assigned to the error of classification of faulty conditions than the error of classification of normal conditions. The proposed framework is successfully validated on a number of public unbalanced datasets. Then, it is applied for the fault detection of braking systems in HST: in comparison with several SVM approaches for unbalanced datasets, the proposed framework gives better results.

[1]  Pierluigi Siano,et al.  A Novel RBF Training Algorithm for Short-Term Electric Load Forecasting and Comparative Studies , 2015, IEEE Transactions on Industrial Electronics.

[2]  Neeraj Kumar,et al.  Decision Tree and SVM-Based Data Analytics for Theft Detection in Smart Grid , 2016, IEEE Transactions on Industrial Informatics.

[3]  Enrico Zio,et al.  An adaptive online learning approach for Support Vector Regression: Online-SVR-FID , 2016 .

[4]  Davide Anguita,et al.  Condition Based Maintenance in Railway Transportation Systems Based on Big Data Streaming Analysis , 2015, INNS Conference on Big Data.

[5]  V. Sugumaran,et al.  Fault diagnosis of automobile hydraulic brake system using statistical features and support vector machines , 2015 .

[6]  Pei-Jen Wang,et al.  Analysis of eddy-current brakes for high speed railway , 1998 .

[7]  Daniel Hissel,et al.  Diagnosis for PEMFC Systems: A Data-Driven Approach With the Capabilities of Online Adaptation and Novel Fault Detection , 2015, IEEE Transactions on Industrial Electronics.

[8]  Enrico Zio,et al.  Feature vector regression with efficient hyperparameters tuning and geometric interpretation , 2016, Neurocomputing.

[9]  Faruk Kazi,et al.  Support-Vector-Machine-Based Proactive Cascade Prediction in Smart Grid Using Probabilistic Framework , 2015, IEEE Transactions on Industrial Electronics.

[10]  Qinghua Hu,et al.  Mechanical fault diagnosis based on redundant second generation wavelet packet transform, neighborhood rough set and support vector machine , 2012 .

[11]  Nathalie Japkowicz,et al.  The Class Imbalance Problem: Significance and Strategies , 2000 .

[12]  Enrico Zio,et al.  Nuclear Power Plant Components Condition Monitoring by Probabilistic Support Vector Machine , 2013 .

[13]  Shibin Wang,et al.  Time-frequency atoms-driven support vector machine method for bearings incipient fault diagnosis , 2016 .

[14]  Enrico Zio,et al.  System reliability prediction by support vector regression with analytic selection and genetic algorithm parameters selection , 2015, Appl. Soft Comput..

[15]  María José del Jesús,et al.  KEEL: a software tool to assess evolutionary algorithms for data mining problems , 2008, Soft Comput..

[16]  Zhi-Hua Zhou,et al.  Cost-Sensitive Face Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Chul-Goo Kang.  Analysis of the braking system of the Korean High-Speed Train using real-time simulations , 2007 .

[18]  Changyin Sun,et al.  Support vector machine-based optimized decision threshold adjustment strategy for classifying imbalanced data , 2015, Knowl. Based Syst..

[19]  Enrico Zio,et al.  A dynamic particle filter-support vector regression method for reliability prediction , 2013, Reliab. Eng. Syst. Saf..

[20]  Feng Jia,et al.  An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data , 2016, IEEE Transactions on Industrial Electronics.

[21]  Gustavo E. A. P. A. Batista,et al.  A study of the behavior of several methods for balancing machine learning training data , 2004, SKDD.

[22]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[23]  Enrico Meli,et al.  Development of efficient models of Magnetic Braking Systems of railway vehicles , 2015 .

[24]  Moshe Givoni,et al.  Development and Impact of the Modern High‐speed Train: A Review , 2006 .

[25]  G. Baudat,et al.  Feature vector selection and projection using kernels , 2003, Neurocomputing.

[26]  Fanrang Kong,et al.  Wayside acoustic diagnosis of defective train bearings based on signal resampling and information enhancement , 2013 .

[27]  D. W. Wightman,et al.  Proportional hazards modelling in reliability analysis: an application to brake discs on high speed trains , 1986 .

[28]  Kezhi Mao,et al.  RBF neural network center selection based on Fisher ratio class separability measure , 2002, IEEE Trans. Neural Networks.