Prediction Capability Assessment of Data-Driven Prognostic Methods for Railway Applications

Francesco Di Maio, Pietro Turati, and Enrico Zio
Submission Type: 
Full Paper
AttachmentSizeTimestamp
phmec_16_048.pdf1.03 MBJune 27, 2016 - 5:09am

In the development of Prognostics and Health Management (PHM) for industrial applications, the question of which predictive method to use is fundamental. The choice is typically driven by the data and/or the physics-based models available, and the cost-benefit considerations related to PHM implementation, wherein prediction capability plays an important role. By prediction capability of a prognostic method we refer to its ability to provide trustable predictions of the Remaining Useful Life (RUL) of a component or system, with the characteristics required by the given application. A set of Prognostic Performance Indicators (PPIs) is used to guide the choice of the method to be implemented. These PPIs measure different characteristics of a prognostic method and need to be aggregated to enable a final choice of prognostic method, based on its overall performance. We propose an aggregation strategy to identify the prognostic method with the best compromise performance on all PPIs. The strategy is exemplified on a case study with real data taken from industry, whose structure is general and, therefore, applicable to railway industry.

Publication Year: 
2016
Publication Volume: 
7
Publication Control Number: 
048
Submission Keywords: 
Prognostic Perfomance Indicators (PPI)
prediction capability
quality assessment
aggregation strategy
Submission Topic Areas: 
Health management system design and engineering
Submitted by: 
  
 
 
 

follow us

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