High-speed train fault detection with unsupervised causality-based feature extraction methods

Abstract With the development of smart sensors, large amount of operating data collected from a complex system as a high-speed train providing opportunities in efficient and effective fault detection and diagnosis (FDD). The data brings also challenges in the FDD modelling process, since the various signals may be redundant, useless and noisy for the FDD modelling of a specific sub-system. The data-driven methods suffer also from the curse of dimensionality. Feature dimension reduction can reduce the dimension of the monitoring dataset and eliminate the useless information. Different from the classical methods based on the correlation among variables, recent studies have shown that causality-based methods can make the FDD model more explanatory and robust. From the adjacency matrix of the causal network diagram, three unsupervised causality-based feature extraction methods for FDD in the braking system of a high-speed train are proposed in this paper. By constructing the causal network diagram among the raw monitoring feature variables through the causal discovery algorithm, the proposed methods extract informative features based on the causal adjacency matrix or the full causal adjacency matrix proposed in this work. These methods are adopted for fault detection with real dataset collected from the braking system in a high-speed train to verify their effectiveness. The experimental results show that the proposed causality-based feature extraction methods are effective and have certain advantages in comparison with the classical correlation-based methods. Especially, the feature extraction method based on the correlation matrix constructed from full causal adjacency matrix achieves better and stable results than the benchmark methods in the experiment.

[1]  Arriving at correct conclusions: the importance of association, causality, and clinical significance. , 2012, Southern medical journal.

[2]  Vahid Rezaei Tabar,et al.  Finding a set of candidate parents using dependency criterion for the K2 algorithm , 2018, Pattern Recognit. Lett..

[3]  Lin Zhang,et al.  Causal feature selection for physical sensing data: a case study on power events prediction , 2019, UbiComp/ISWC Adjunct.

[4]  Yidan Wang,et al.  Fault detection for non-condensing boilers using simulated building automation system sensor data , 2020, Adv. Eng. Informatics.

[5]  Aditi Chattopadhyay,et al.  Real-time anomaly detection framework using a support vector regression for the safety monitoring of commercial aircraft , 2020, Adv. Eng. Informatics.

[6]  Xu-hui He,et al.  Review of aerodynamics of high-speed train-bridge system in crosswinds , 2020, Journal of Central South University.

[7]  Mehmet Akar,et al.  Mechanical fault detection in permanent magnet synchronous motors using equal width discretization-based probability distribution and a neural network model , 2015 .

[8]  Salah Zidi,et al.  Fault Detection in Wireless Sensor Networks Through SVM Classifier , 2018, IEEE Sensors Journal.

[9]  Chen Yang,et al.  RAMS Analysis of Train Air Braking System Based on GO-Bayes Method and Big Data Platform , 2018, Complex..

[10]  Judea Pearl,et al.  Causal Inference , 2010 .

[11]  Yan-Lin He,et al.  A novel scoring function based on family transfer entropy for Bayesian networks learning and its application to industrial alarm systems , 2019 .

[12]  Dino Sejdinovic,et al.  Detecting and quantifying causal associations in large nonlinear time series datasets , 2017, Science Advances.

[13]  Marianne Winslett,et al.  Understanding Social Causalities Behind Human Action Sequences , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[14]  Na Qin,et al.  High-Speed Railway Bogie Fault Diagnosis Using LSTM Neural Network , 2018, 2018 37th Chinese Control Conference (CCC).

[15]  Peter Spirtes,et al.  Causal discovery and inference: concepts and recent methodological advances , 2016, Applied Informatics.

[16]  Qingfeng Du,et al.  A Causality Mining and Knowledge Graph Based Method of Root Cause Diagnosis for Performance Anomaly in Cloud Applications , 2020, Applied Sciences.

[17]  Hu Min,et al.  A Global Discretization and Attribute Reduction Algorithm Based on K-Means Clustering and Rough Sets Theory , 2009, 2009 Second International Symposium on Knowledge Acquisition and Modeling.

[18]  Yan-Fu Li,et al.  A SVM framework for fault detection of the braking system in a high speed train , 2017, Mechanical Systems and Signal Processing.

[19]  Peng Wang,et al.  Classification of Proactive Personality: Text Mining Based on Weibo Text and Short-Answer Questions Text , 2020, IEEE Access.

[20]  Jie Liu,et al.  Fuzzy support vector machine for imbalanced data with borderline noise , 2020, Fuzzy Sets Syst..

[21]  Baigen Cai,et al.  Methods for fault diagnosis of high-speed railways: A review , 2019, Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability.

[22]  He Xiao,et al.  Fault detection of EMU brake cylinder , 2016, 2016 35th Chinese Control Conference (CCC).

[23]  Yinglai Liu,et al.  A Machine-Learning-Based Prediction Method for Hypertension Outcomes Based on Medical Data , 2019, Diagnostics.

[24]  Papia Ray,et al.  Various dimension reduction techniques for high dimensional data analysis: a review , 2021, Artificial Intelligence Review.

[25]  Shubhra Sankar Ray,et al.  Finding optimum width of discretization for gene expressions using functional annotations , 2017, Comput. Biol. Medicine.

[26]  Sunghae Jun,et al.  Graphical causal inference and copula regression model for apple keywords by text mining , 2015, Adv. Eng. Informatics.

[27]  Han Huang,et al.  Causal Discovery Combining K2 with Brain Storm Optimization Algorithm , 2018, Molecules.

[28]  J. Pearl,et al.  Causal Inference , 2011, Twenty-one Mental Models That Can Change Policing.

[29]  Zhen Ji,et al.  A New Structure Learning Method for Constructing Gene Networks , 2009, 2009 3rd International Conference on Bioinformatics and Biomedical Engineering.

[30]  Bin Jiang,et al.  Data-Driven Incipient Sensor Fault Estimation with Application in Inverter of High-Speed Railway , 2017 .

[31]  Steven X. Ding,et al.  Data-Driven Fault Diagnosis for Traction Systems in High-Speed Trains: A Survey, Challenges, and Perspectives , 2022, IEEE Transactions on Intelligent Transportation Systems.

[32]  Raj Kumar Patel,et al.  Development of Feature Extraction and Classification for Bearing Fault Analysis of Induction Motor , 2018, 2018 5th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON).

[33]  P. Spirtes,et al.  Review of Causal Discovery Methods Based on Graphical Models , 2019, Front. Genet..

[34]  Zehui Mao,et al.  Deep PCA Based Real-Time Incipient Fault Detection and Diagnosis Methodology for Electrical Drive in High-Speed Trains , 2018, IEEE Transactions on Vehicular Technology.

[35]  Houxiang Zhang,et al.  A Step-wise Feature Selection Scheme for a Prognostics and Health Management System in Autonomous Ferry Crossing Operation , 2019, 2019 IEEE International Conference on Mechatronics and Automation (ICMA).

[36]  Donghua Zhou,et al.  Fault Detection and Isolation of the Brake Cylinder System for Electric Multiple Units , 2018, IEEE Transactions on Control Systems Technology.

[37]  Rahul Shrivastava,et al.  Application and Evaluation of Random Forest Classifier Technique for Fault Detection in Bioreactor Operation , 2017 .

[38]  Duncan Fyfe Gillies,et al.  A Review of Feature Selection and Feature Extraction Methods Applied on Microarray Data , 2015, Adv. Bioinformatics.

[39]  Anderson C. A. Nascimento,et al.  Efficient and Private Scoring of Decision Trees, Support Vector Machines and Logistic Regression Models Based on Pre-Computation , 2019, IEEE Transactions on Dependable and Secure Computing.

[40]  Sargur N. Srihari,et al.  Bayesian Network Structure Learning Using Causality , 2014, 2014 22nd International Conference on Pattern Recognition.

[41]  T. Windeatt,et al.  Bootstrap Causal Feature Selection for irrelevant feature elimination , 2013, The 6th 2013 Biomedical Engineering International Conference.

[42]  Kui Yu,et al.  Causality-based Feature Selection: Methods and Evaluations , 2019 .

[43]  Nicandro Cruz-Ramírez,et al.  How Good Are the Bayesian Information Criterion and the Minimum Description Length Principle for Model Selection? A Bayesian Network Analysis , 2006, MICAI.

[44]  Edwin R. Hancock,et al.  Spectral embedding of graphs , 2003, Pattern Recognit..

[45]  P. Leary.  Causality, Correlation, and Cardiac Disease: Does Smoking Cause Cardiac Hypertrophy and Diastolic Dysfunction? , 2016, Circulation. Cardiovascular imaging.

[46]  Hui Cheng,et al.  Fault Diagnosis of the Paper Machine Short Circulation Process using Novel Dynamic Causal Digraph Reasoning , 2008 .