---
_id: '55568'
abstract:
- lang: eng
text: Historical condition monitoring data from technical systems can be
utilized to develop data-driven models for predicting the remaining useful life
(RUL) of similar systems, whereas the Health Index (HI) often is a crucial component.
The development of robust and accurate models requires meaningful features that
reflect the system’s degradation process, enabling an accurate prediction of the
system's HI. Traditionally, the identification of those is supported by one of
various feature ranking methods. In literature, feature interdependencies and
their transferability across various similar systems are not sufficiently considered
in feature selection, exacerbating the challenge of HI prediction posed by the
scarcity of data and system diversity in real-world applications. This work addresses
this gaps by demonstrating how filter-based feature selection, incorporating failure
thresholds and cross correlations, enhances feature selection leading to improved
HI prediction. The proposed methodology is applied to a novel dataset* obtained
from run-to-failure experiments on geared motors conducted as part of this study,
which presents the aforementioned challenges. It is revealed that classical feature
selection, consisting of feature ranking only, leaves potential untapped, which
is utilized by the proposed selection methodology. It is shown that the proposed
feature selection methodology leads to the best result with a RMSE of 0.14 in
predicting the HI of a constructive different gearbox, while the features, determined
by classical feature selection, lead to a RMSE of 0.19 at best.
author:
- first_name: Alexander
full_name: Löwen, Alexander
id: '47233'
last_name: Löwen
- first_name: Peter
full_name: Wissbrock, Peter
last_name: Wissbrock
- first_name: Amelie
full_name: Bender, Amelie
id: '54290'
last_name: Bender
- first_name: Walter
full_name: Sextro, Walter
id: '21220'
last_name: Sextro
citation:
ama: Löwen A, Wissbrock P, Bender A, Sextro W. Filter-based feature selection for
prognostics incorporating cross correlations and failure thresholds. PHM Society
European Conference. 2024;8(1):955-964. doi:10.36001/phme.2024.v8i1.4075
apa: Löwen, A., Wissbrock, P., Bender, A., & Sextro, W. (2024). Filter-based
feature selection for prognostics incorporating cross correlations and failure
thresholds. PHM Society European Conference, 8(1), 955–964. https://doi.org/10.36001/phme.2024.v8i1.4075
bibtex: '@article{Löwen_Wissbrock_Bender_Sextro_2024, title={Filter-based feature
selection for prognostics incorporating cross correlations and failure thresholds},
volume={8}, DOI={10.36001/phme.2024.v8i1.4075},
number={1}, journal={PHM Society European Conference}, publisher={PHM Society},
author={Löwen, Alexander and Wissbrock, Peter and Bender, Amelie and Sextro, Walter},
year={2024}, pages={955–964} }'
chicago: 'Löwen, Alexander, Peter Wissbrock, Amelie Bender, and Walter Sextro. “Filter-Based
Feature Selection for Prognostics Incorporating Cross Correlations and Failure
Thresholds.” PHM Society European Conference 8, no. 1 (2024): 955–64. https://doi.org/10.36001/phme.2024.v8i1.4075.'
ieee: 'A. Löwen, P. Wissbrock, A. Bender, and W. Sextro, “Filter-based feature selection
for prognostics incorporating cross correlations and failure thresholds,” PHM
Society European Conference, vol. 8, no. 1, pp. 955–964, 2024, doi: 10.36001/phme.2024.v8i1.4075.'
mla: Löwen, Alexander, et al. “Filter-Based Feature Selection for Prognostics Incorporating
Cross Correlations and Failure Thresholds.” PHM Society European Conference,
vol. 8, no. 1, PHM Society, 2024, pp. 955–64, doi:10.36001/phme.2024.v8i1.4075.
short: A. Löwen, P. Wissbrock, A. Bender, W. Sextro, PHM Society European Conference
8 (2024) 955–964.
conference:
end_date: 2024-07-05
location: Prague
name: 8th European Conference of the Prognostics and Health Management Society 2024
start_date: 2024-07-03
date_created: 2024-08-08T09:22:33Z
date_updated: 2025-02-10T10:58:57Z
department:
- _id: '151'
doi: 10.36001/phme.2024.v8i1.4075
intvolume: ' 8'
issue: '1'
language:
- iso: eng
page: 955-964
publication: PHM Society European Conference
publication_identifier:
isbn:
- 978-1-936263-40-0
publication_status: published
publisher: PHM Society
quality_controlled: '1'
related_material:
link:
- relation: confirmation
url: https://papers.phmsociety.org/index.php/phme/article/download/4075/2477
status: public
title: Filter-based feature selection for prognostics incorporating cross correlations
and failure thresholds
type: journal_article
user_id: '47233'
volume: 8
year: '2024'
...