Early Warnings for failing Train Axle Bearings based on Temperature

Margot F.E. Peters
Submission Type: 
Full Paper
phmc_17_041.pdf588.94 KBSeptember 6, 2017 - 5:20am

Early Warnings for failing Train Axle Bearings based on Temperature

Peters, MFE, Netherlands Railways (NS)

By studying the temperature behavior of axle bearings both statistically and physically, the research and development (R&D) department of Netherlands Railways (NS) has successfully developed and implemented a health monitoring system for bearings. In an early stage of degradation, temperature deviations are detected and the level of severity of the degradation is identified through a decision tree. This method enables us to detect bearing failures one to three months earlier than any other method in use, in more than half of the cases. Different handling scenarios per type of temperature behavior have been designed in a way that minimizes impact on train service.

Publication Year: 
Publication Volume: 
Publication Control Number: 
Page Count: 
Submission Keywords: 
bearing fault detection
PHM in Railways
decision tree
rule-based classifier
Submission Topic Areas: 
Component-level PHM
Data-driven methods for fault detection, diagnosis, and prognosis
Health management system design and engineering
Industrial applications
Submitted by: 

follow us

PHM Society on Facebook Follow PHM Society on Twitter PHM Society on LinkedIn PHM Society RSS News Feed