Industrial AI Enabled Prognostics for High-speed Railway Systems

The vision of pervasive applications of artificial intelligence (AI) and the fact that hardware is becoming more portable and computationally powerful has encouraged the development of industrial AI. High-speed railway (HSR) transportation is an area of focus for industrial AI, since it demands maximized safety, reliability, availability, and minimized cost. Given the system complexity, the predictive maintenance for high-speed railway could hardly sustain with a raw experience-based system. This paper presents a framework for industrial AI enabled PHM system for HSR, which creates cyber twins of physical key subsystems and components to improve the condition transparency and decision efficiency. Enabled by advanced signal processing and machine learning with domain insights on historical data, cyber twins monitor real-time performance and predict potential faults to prevent unexpected downtime and support optimized decisions. Instead of performing analytics with large amount of raw data on the cloud, the cyber railway transportation system leverages the advantage of edge computing for real-time feature extraction and anomaly detection. The proposed framework introduces the general approach of implementing industrial AI. The paper also discusses the key methods of data-driven solutions for selected critical subsystems.

[1]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[2]  Yang Zhao,et al.  Vibration signal analysis and fault diagnosis of bogies of the high-speed train based on deep neural networks , 2017 .

[3]  Jianbo Yu,et al.  A similarity-based prognostics approach for Remaining Useful Life estimation of engineered systems , 2008, 2008 International Conference on Prognostics and Health Management.

[4]  Jay Lee,et al.  Fault detection in a network of similar machines using clustering approach , 2012 .

[5]  Zhen Gao,et al.  Design optimization of a spatial six degree-of-freedom parallel manipulator based on artificial intelligence approaches , 2010 .

[6]  A.T.S. Worth,et al.  Alstom's approach to railway condition monitoring , 2014 .

[7]  Patrice Aknin,et al.  Temporal association rule mining for the preventive diagnosis of onboard subsystems within floating train data framework , 2012, 2012 15th International IEEE Conference on Intelligent Transportation Systems.

[8]  Jay Lee,et al.  A comprehensive framework of factory-to-factory dynamic fleet-level prognostics and operation management for geographically distributed assets , 2015, 2015 IEEE International Conference on Automation Science and Engineering (CASE).

[9]  Jay Lee,et al.  An auto-associative residual based approach for railway point system fault detection and diagnosis , 2018 .

[10]  Rafael Medina Carnicer,et al.  Deep multi-task learning for gait-based biometrics , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[11]  Frederik Petré,et al.  Winding fault diagnosis of a 3-phase induction motor powered by frequency-inverter drive using the current and voltage signals , 2014 .

[12]  Dimitris K. Tasoulis,et al.  Unsupervised clustering on dynamic databases , 2005, Pattern Recognit. Lett..

[13]  Huailong Shi,et al.  Prediction of Wheel Profile Wear and Vehicle Dynamics Evolution Considering Stochastic Parameters for High-Speed Train , 2017 .

[14]  Jay Lee,et al.  Prognostics and health management design for rotary machinery systems—Reviews, methodology and applications , 2014 .

[15]  Noureddine Zerhouni,et al.  Critical Components Selection for a Prognostics and Health Management System Design: an Application to an Overhead Contact System , 2017 .

[16]  David Siegel,et al.  Prognostics and Health Assessment of a Multi-Regime System using a Residual Clustering Health Monitoring Approach , 2013 .

[17]  Wentian Zhao,et al.  Fault diagnosis network design for vehicle on-board equipments of high-speed railway: A deep learning approach , 2016, Eng. Appl. Artif. Intell..

[18]  Jay Lee,et al.  Similarity based method for manufacturing process performance prediction and diagnosis , 2007, Comput. Ind..

[19]  Robert B. Randall,et al.  Rolling element bearing diagnostics—A tutorial , 2011 .

[20]  Jay Lee,et al.  Industrial Big Data Analytics and Cyber-physical Systems for Future Maintenance & Service Innovation , 2015 .

[21]  Li Xiao,et al.  Fault type recognition of High-speed train bogie based on dual-channel integration of information entropy , 2016, 2016 2nd IEEE International Conference on Computer and Communications (ICCC).

[22]  Yonghao Miao,et al.  Detection and recovery of fault impulses via improved harmonic product spectrum and its application in defect size estimation of train bearings , 2016 .

[23]  Kai Goebel,et al.  A Survey of Artificial Intelligence for Prognostics , 2007, AAAI Fall Symposium: Artificial Intelligence for Prognostics.

[24]  Mehmet Karakose,et al.  A New Computer Vision Based Method for Rail Track Detection and Fault Diagnosis in Railways , 2017 .

[25]  Hang Liu,et al.  High-Speed Railway Traction Power Supply Equipment Condition-BasedMaintenance Decision Model Based on Reliability , 2014 .

[26]  Wenyi Xia,et al.  Should China further expand its high-speed rail network? Consider the low-cost carrier factor , 2017 .

[27]  Jay Lee,et al.  Introduction to cyber manufacturing , 2016 .

[28]  Sandra Johnson,et al.  Unmanned Aerial Vehicles (UAVs) and Artificial Intelligence Revolutionizing Wildlife Monitoring and Conservation , 2016, Sensors.

[29]  Zongchang Liu,et al.  A Systematic Framework for Unsupervised Feature Mining and Fault Detection for Wind Turbine Drivetrain Systems , 2016 .

[30]  Hai Qiu,et al.  Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics , 2006 .

[31]  Jay Lee,et al.  Introduction to Data-Driven Methodologies for Prognostics and Health Management , 2017 .

[32]  Jay Lee,et al.  A Cyber-Physical Systems architecture for Industry 4.0-based manufacturing systems , 2015 .

[33]  Slawomir Judek,et al.  3D machine vision system for inspection of contact strips in railway vehicle current collectors , 2014, 2014 International Conference on Applied Electronics.