[Legacy Report] SMC Seminar on Build Machine Learning Models for Fault Diagnosis and Prognosis of Railway Signaling Systems
IEEE Northern Jersey Section SMC Chapter Seminar
Build Machine Learning Models for Fault Diagnosis and Prognosis of Railway Signaling Systems
Tianhua Xu, Ph.D. and Associate Professor
Beijing Jiaotong University
Beijing, China
Place: ECE 202
Time: 2pm, Jan. 21, 2016
Abstract: Railway signaling systems are becoming more complex and are subjected to failure modes that impact adversely their reliability, availability, safety and maintainability. Such critical assets are required to be available when needed, and maintained on the basis of their current condition rather than on the basis of scheduled or breakdown maintenance practices. Moreover, on-line, real-time fault diagnosis and prognosis can assist the operator to avoid catastrophic events. Currently, a vast amount of railway signaling fault data is recorded in the forms of repair verbatim in railway maintenance sectors. Efficient machine learning models for knowledge discovery from such maintenance data play an important role in fault diagnosis and prognosis and improving railway signaling systems' reliability, availability, and safety. This seminar will give a brief account of research results carried out on text mining and one-class classification-based fault prognosis and prognosis of railway signaling systems. Finally, it will identify opportunities and challenges in research avenues for collaboration on topics of machine learning and data mining.
Bio-sketch: Tianhua Xu received the BSc, MSc, and Ph.D. degrees in Electrical and Information Engineering from the Xi'an Jiaotong University, Xi'an, China, Shanghai Jiaotong University, Shanghai China and Xidian University, Xi’an, China, in 1993, 2002, and 2005, respectively. He is currently an Associate Professor in Beijing Jiaotong University, Beijing, China. During 2005 and 2007, he was a Postdoctoral Fellow in the State Key Lab for Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing, China. From 2009 to 2010, he was a visiting scholar at the Department of Computer Science at York University, UK. Since 2014, he has been a Visiting Researcher sponsored by the Chinese government with the CSRZIC Laboratory for Rail System Network and Information Technology, New Jersey Institute of Technology (NJIT), USA. His current research interests lie in computer control, data mining, intelligent fault diagnosis and prognosis.
Contact: Prof. Mengchu Zhou at zhou@njit.edu if any question. ECE 202 is located at the intersection between warren St. and Summit St., Newark, NJ 07102.
Add Event to Calendar
