Performance Benchmarking and Analysis of Prognostic Methods for
| Citations: | 1 - 0 self |
BibTeX
@MISC{Ramasso_performancebenchmarking,
author = {Emmanuel Ramasso and Abhinav Saxena},
title = {Performance Benchmarking and Analysis of Prognostic Methods for},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Six years and more than seventy publications later this paper looks back and analyzes the development of prognostic algo-rithms using C-MAPSS datasets generated and disseminated by the prognostic center of excellence at NASA Ames Re-search Center. Among those datasets are five run-to-failure C-MAPSS datasets that have been popular due to various char-acteristics applicable to prognostics. The C-MAPSS datasets pose several challenges that are inherent to general prognos-tics applications. In particular, management of high vari-ability due to sensor noise, effects of operating conditions, and presence of multiple simultaneous fault modes are some factors that have great impact on the generalization capabil-ities of prognostics algorithms. More than seventy publica-tions have used the C-MAPSS datasets for developing data-driven prognostic algorithms. However, in the absence of per-formance benchmarking results and due to common misun-derstandings in interpreting the relationships between these datasets, it has been difficult for the users to suitably compare their results. In addition to identifying differentiating char-acteristics in these datasets, this paper also provides perfor-mance results for the PHM’08 data challenge wining entries to serve as performance baseline. This paper summarizes var-ious prognostic modeling efforts that used C-MAPSS datasets and provides guidelines and references to further usage of these datasets in a manner that allows clear and consistent comparison between different approaches. 1.
Keyphrases
c-mapss datasets performance benchmarking prognostic method general prognos-tics application performance baseline run-to-failure c-mapss datasets different approach common misun-derstandings great impact high vari-ability consistent comparison multiple simultaneous fault mode per-formance benchmarking result perfor-mance result several challenge var-ious prognostic modeling effort nasa ames re-search center data-driven prognostic algorithm various char-acteristics operating condition generalization capabil-ities seventy publication data challenge prognostic center
