---
_id: '27652'
abstract:
- lang: ger
text: "Aufgrund der Fortschritte der Digitalisierung finden Systeme zur Zustandsüberwachung
vermehrt Einsatz in der Industrie, um durch eine zustandsbasierte oder eine prädiktive
Instandhaltung Vorteile, wie eine verbesserte Zuverlässigkeit und geringere Kosten
zu erzielen. Dabei beruhen Zustandsüberwachungssysteme auf den folgenden Bausteinen:
Sensorik, Datenvorverarbeitung, Merkmalsextraktion und -auswahl, Diagnose bzw.
Prognose sowie einer Entscheidungsfindung basierend auf den Ergebnissen. Jeder
dieser Bausteine erfordert individuelle Einstellungen, um ein geeignetes Zustandsüberwachungssystem
für die jeweilige Anwendung zu entwickeln. Eine offene Fragestellung im Bereich
der Zustandsüberwachung ergibt sich aufgrund der Unsicherheit der Zukunft, die
sich in den zukünftigen Betriebs- und Umgebungsbedingungen zeigt. Diese Unsicherheit
gilt es in allen Bausteinen zu berücksichtigen.\r\nDieser Beitrag konzentriert
sich auf den Baustein Merkmalsextraktion und -selektion, mit dem Ziel anhand geeigneter
Merkmale eine Prognose der nutzbaren Restlebensdauer mit hoher Genauigkeit realisieren
zu können. Daher werden geeignete Merkmale aus dem Zeitbereich und daraus abgeleitete
Zustandsindikatoren für die Restlebensdauerprognose von technischen Systemen vorgestellt.
Dabei sind Zustandsindikatoren Kenngrößen zur Beobachtung des Zustands der kritischen
Systemkomponenten. Anhand dreier Anwendungsbeispiele wird ihre Eignung evaluiert.
Dabei werden Daten aus Lebensdauerversuchen unter instationären Betriebs- und
Umgebungsbedingungen ausgewertet. Die auftretenden Unsicherheiten der Zukunft
werden somit berücksichtigt. Die Beispielsysteme beruhen auf Gummi-Metall-Elementen
und Wälzlagern. Aus den generierten Ergebnissen lässt sich schließen, dass die
Zustandsindikatoren aus der betrachteten Zeitreihen-Toolbox auch unter unbekannten
Betriebs- und Umgebungsbedingungen robust sind.\r\n"
- lang: eng
text: "Due to the advances in digitalization, condition monitoring systems have
found numerous applications in the industry due to benefits such as improved reliability
and lowered costs through condition-based or predictive maintenance. Condition
monitoring systems typically involve elements, such as data acquisition via suitable
sensors, data preprocessing, feature extraction and selection, diagnostics, prognostics
and (maintenance) decisions based on diagnosis or prognosis. For the application-specific
development of a suitable condition monitoring system, each of these elements
requires individual settings. Due to the uncertainty of the future, an open question
arises in the condition monitoring field, which is reflected in unknown future
operating and environmental conditions. This uncertainty needs consideration in
all elements of a condition monitoring system.\r\nThis article focuses on feature
extraction and selection, building on the hypothesis that the remaining useful
life of a technical system can be predicted with high accuracy utilizing suitable
features. In this article, health indicators derived from time-domain features
that permit the monitoring of the health of critical system components are presented
for predicting the remaining useful life of technical systems. Three distinct
application examples based on rubber-metal elements and rolling-element bearings
are evaluated to validate the suitability of the presented methods. Experimental
data from accelerated lifetime tests conducted under non-stationary operating
and environmental conditions are considered to take possible future uncertainties
into account. It can be concluded from the acquired results that health indicators
derived from the presented time series toolbox are robust to varying operating
and environmental conditions.\r\n"
author:
- first_name: Osarenren Kennedy
full_name: Aimiyekagbon, Osarenren Kennedy
id: '9557'
last_name: Aimiyekagbon
- 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: 'Aimiyekagbon OK, Bender A, Sextro W. Extraktion und Selektion geeigneter Merkmale
für die Restlebensdauerprognose von technischen Systemen trotz aleatorischen Unsicherheiten
. In: VDI-Berichte 2391. VDI Verlag GmbH; 2021:197-210.'
apa: Aimiyekagbon, O. K., Bender, A., & Sextro, W. (2021). Extraktion und Selektion
geeigneter Merkmale für die Restlebensdauerprognose von technischen Systemen trotz
aleatorischen Unsicherheiten . VDI-Berichte 2391, 197–210.
bibtex: '@inproceedings{Aimiyekagbon_Bender_Sextro_2021, place={Düsseldorf}, title={Extraktion
und Selektion geeigneter Merkmale für die Restlebensdauerprognose von technischen
Systemen trotz aleatorischen Unsicherheiten }, booktitle={VDI-Berichte 2391},
publisher={VDI Verlag GmbH}, author={Aimiyekagbon, Osarenren Kennedy and Bender,
Amelie and Sextro, Walter}, year={2021}, pages={197–210} }'
chicago: 'Aimiyekagbon, Osarenren Kennedy, Amelie Bender, and Walter Sextro. “Extraktion
und Selektion geeigneter Merkmale für die Restlebensdauerprognose von technischen
Systemen trotz aleatorischen Unsicherheiten .” In VDI-Berichte 2391, 197–210.
Düsseldorf: VDI Verlag GmbH, 2021.'
ieee: O. K. Aimiyekagbon, A. Bender, and W. Sextro, “Extraktion und Selektion geeigneter
Merkmale für die Restlebensdauerprognose von technischen Systemen trotz aleatorischen
Unsicherheiten ,” in VDI-Berichte 2391, Würzburg, 2021, pp. 197–210.
mla: Aimiyekagbon, Osarenren Kennedy, et al. “Extraktion und Selektion geeigneter
Merkmale für die Restlebensdauerprognose von technischen Systemen trotz aleatorischen
Unsicherheiten .” VDI-Berichte 2391, VDI Verlag GmbH, 2021, pp. 197–210.
short: 'O.K. Aimiyekagbon, A. Bender, W. Sextro, in: VDI-Berichte 2391, VDI Verlag
GmbH, Düsseldorf, 2021, pp. 197–210.'
conference:
end_date: 2021-11-17
location: Würzburg
name: '3. VDI-Fachtagung '
start_date: 2021-11-16
date_created: 2021-11-22T07:42:44Z
date_updated: 2022-01-06T06:57:43Z
department:
- _id: '151'
keyword:
- run-to-failure
- rubber-metal element
- bearing prognostics
- non-stationary operating conditions
- varying operating conditions
- feature extraction
- feature selection
language:
- iso: ger
page: 197 - 210
place: Düsseldorf
publication: VDI-Berichte 2391
publication_identifier:
isbn:
- 978-3-18-092391-8
issn:
- '0083-5560 '
publication_status: published
publisher: VDI Verlag GmbH
status: public
title: 'Extraktion und Selektion geeigneter Merkmale für die Restlebensdauerprognose
von technischen Systemen trotz aleatorischen Unsicherheiten '
type: conference
user_id: '9557'
year: '2021'
...
---
_id: '22507'
abstract:
- lang: eng
text: Several methods, including order analysis, wavelet analysis and empirical
mode decomposition have been proposed and successfully employed for the health
state estimation of technical systems operating under varying conditions. However,
where information such as the speed of rotating machinery, component specifications
or other domain-specific information is unavailable, such methods are often infeasible.
Thus, this paper investigates the application of classical time-domain features,
features from the medical field and novel features from the highly comparative
time-series analysis (HCTSA) package, for the health state estimation of rotating
machinery operating under varying conditions. Furthermore, several feature selection
methods are investigated to identify features as viable health indicators for
the diagnostics and prognostics of technical systems. As a case study, the presented
methods are evaluated on real-world and experimentally acquired vibration data
of bearings operating under varying speed. The results show that the selected
features can successfully be employed as health indicators for technical systems
operating under varying conditions.
author:
- first_name: Osarenren Kennedy
full_name: Aimiyekagbon, Osarenren Kennedy
id: '9557'
last_name: Aimiyekagbon
- 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: 'Aimiyekagbon OK, Bender A, Sextro W. On the applicability of time series features
as health indicators for technical systems operating under varying conditions.
In: Proceedings of the Seventeenth International Conference on Condition Monitoring
and Asset Management (CM 2021).'
apa: Aimiyekagbon, O. K., Bender, A., & Sextro, W. (n.d.). On the applicability
of time series features as health indicators for technical systems operating under
varying conditions. Proceedings of the Seventeenth International Conference
on Condition Monitoring and Asset Management (CM 2021). Seventeenth International
Conference on Condition Monitoring and Asset Management (CM 2021).
bibtex: '@inproceedings{Aimiyekagbon_Bender_Sextro, title={On the applicability
of time series features as health indicators for technical systems operating under
varying conditions}, booktitle={Proceedings of the Seventeenth International Conference
on Condition Monitoring and Asset Management (CM 2021)}, author={Aimiyekagbon,
Osarenren Kennedy and Bender, Amelie and Sextro, Walter} }'
chicago: Aimiyekagbon, Osarenren Kennedy, Amelie Bender, and Walter Sextro. “On
the Applicability of Time Series Features as Health Indicators for Technical Systems
Operating under Varying Conditions.” In Proceedings of the Seventeenth International
Conference on Condition Monitoring and Asset Management (CM 2021), n.d.
ieee: O. K. Aimiyekagbon, A. Bender, and W. Sextro, “On the applicability of time
series features as health indicators for technical systems operating under varying
conditions,” presented at the Seventeenth International Conference on Condition
Monitoring and Asset Management (CM 2021).
mla: Aimiyekagbon, Osarenren Kennedy, et al. “On the Applicability of Time Series
Features as Health Indicators for Technical Systems Operating under Varying Conditions.”
Proceedings of the Seventeenth International Conference on Condition Monitoring
and Asset Management (CM 2021).
short: 'O.K. Aimiyekagbon, A. Bender, W. Sextro, in: Proceedings of the Seventeenth
International Conference on Condition Monitoring and Asset Management (CM 2021),
n.d.'
conference:
end_date: 2021-06-18
name: Seventeenth International Conference on Condition Monitoring and Asset Management
(CM 2021)
start_date: 2021-06-14
date_created: 2021-06-23T05:24:39Z
date_updated: 2023-09-22T08:10:34Z
ddc:
- '620'
department:
- _id: '151'
file:
- access_level: open_access
content_type: application/pdf
creator: kennedy
date_created: 2021-06-23T06:43:44Z
date_updated: 2021-06-23T06:50:07Z
description: 'This is a post-print version of the article presented at the Seventeenth
International Con-ference on Condition Monitoring and Asset Management (CM 2021).
The event websiteis available at: https://www.bindt.org/events/CM-2021/ and the
abstract is available at:https://www.bindt.org/events/CM-2021/abstract-9a7/.'
file_id: '22508'
file_name: Aimiyekagbon_et_al_2021_On_the_applicability_of_time_series_features_as_health_indicators_postPrint.pdf
file_size: 1875572
relation: main_file
title: On the applicability of time series features as health indicators for technical
systems operating under varying conditions
file_date_updated: 2021-06-23T06:50:07Z
has_accepted_license: '1'
keyword:
- Wind turbine diagnostics
- bearing diagnostics
- non-stationary operating conditions
- varying operating conditions
- feature extraction
- feature selection
- fault detection
- failure detection
language:
- iso: eng
oa: '1'
publication: Proceedings of the Seventeenth International Conference on Condition
Monitoring and Asset Management (CM 2021)
publication_status: inpress
quality_controlled: '1'
status: public
title: On the applicability of time series features as health indicators for technical
systems operating under varying conditions
type: conference
user_id: '9557'
year: '2021'
...
---
_id: '15488'
abstract:
- lang: eng
text: The continuous refinement of sensor technologies enables the manufacturing
industry to capture increasing amounts of data during the production process.
As processes take time to complete, sensors register large amounts of time-series-like
data for each product. In order to make this data usable, a feature extraction
is mandatory. In this work, we discuss and evaluate different network architectures,
input pre-processing and cost functions regarding, among other aspects, their
suitability for time series of different lengths.
author:
- first_name: Christian
full_name: Thiel, Christian
last_name: Thiel
- first_name: Carolin
full_name: Steidl, Carolin
last_name: Steidl
- first_name: Bernd
full_name: Henning, Bernd
id: '213'
last_name: Henning
citation:
ama: 'Thiel C, Steidl C, Henning B. P2.9 Comparison of deep feature extraction techniques
for varying-length time series from an industrial piercing press. In: AMA Service
GmbH, ed. 20. GMA/ITG-Fachtagung. Sensoren Und Messsysteme 2019. Von-Münchhausen-Str.
49, 31515 Wunstorf; 2019. doi:10.5162/SENSOREN2019/P2.9'
apa: Thiel, C., Steidl, C., & Henning, B. (2019). P2.9 Comparison of deep feature
extraction techniques for varying-length time series from an industrial piercing
press. In AMA Service GmbH (Ed.), 20. GMA/ITG-Fachtagung. Sensoren und Messsysteme
2019. Von-Münchhausen-Str. 49, 31515 Wunstorf. https://doi.org/10.5162/SENSOREN2019/P2.9
bibtex: '@inproceedings{Thiel_Steidl_Henning_2019, place={Von-Münchhausen-Str. 49,
31515 Wunstorf}, title={P2.9 Comparison of deep feature extraction techniques
for varying-length time series from an industrial piercing press}, DOI={10.5162/SENSOREN2019/P2.9},
booktitle={20. GMA/ITG-Fachtagung. Sensoren und Messsysteme 2019}, author={Thiel,
Christian and Steidl, Carolin and Henning, Bernd}, editor={AMA Service GmbHEditor},
year={2019} }'
chicago: Thiel, Christian, Carolin Steidl, and Bernd Henning. “P2.9 Comparison of
Deep Feature Extraction Techniques for Varying-Length Time Series from an Industrial
Piercing Press.” In 20. GMA/ITG-Fachtagung. Sensoren Und Messsysteme 2019,
edited by AMA Service GmbH. Von-Münchhausen-Str. 49, 31515 Wunstorf, 2019. https://doi.org/10.5162/SENSOREN2019/P2.9.
ieee: C. Thiel, C. Steidl, and B. Henning, “P2.9 Comparison of deep feature extraction
techniques for varying-length time series from an industrial piercing press,”
in 20. GMA/ITG-Fachtagung. Sensoren und Messsysteme 2019, 2019.
mla: Thiel, Christian, et al. “P2.9 Comparison of Deep Feature Extraction Techniques
for Varying-Length Time Series from an Industrial Piercing Press.” 20. GMA/ITG-Fachtagung.
Sensoren Und Messsysteme 2019, edited by AMA Service GmbH, 2019, doi:10.5162/SENSOREN2019/P2.9.
short: 'C. Thiel, C. Steidl, B. Henning, in: AMA Service GmbH (Ed.), 20. GMA/ITG-Fachtagung.
Sensoren Und Messsysteme 2019, Von-Münchhausen-Str. 49, 31515 Wunstorf, 2019.'
corporate_editor:
- AMA Service GmbH
date_created: 2020-01-10T16:03:58Z
date_updated: 2022-01-06T06:52:27Z
department:
- _id: '49'
doi: 10.5162/SENSOREN2019/P2.9
keyword:
- Dynamic Time Warping
- Feature Extraction
- Masking
- Neural Networks
language:
- iso: eng
place: Von-Münchhausen-Str. 49, 31515 Wunstorf
publication: 20. GMA/ITG-Fachtagung. Sensoren und Messsysteme 2019
publication_identifier:
isbn:
- 978-3-9819376-0-2
status: public
title: P2.9 Comparison of deep feature extraction techniques for varying-length time
series from an industrial piercing press
type: conference
user_id: '11829'
year: '2019'
...
---
_id: '15873'
author:
- first_name: Alexander
full_name: Boschmann, Alexander
last_name: Boschmann
- first_name: Andreas
full_name: Agne, Andreas
last_name: Agne
- first_name: Linus Matthias
full_name: Witschen, Linus Matthias
id: '49051'
last_name: Witschen
- first_name: Georg
full_name: Thombansen, Georg
last_name: Thombansen
- first_name: Florian
full_name: Kraus, Florian
last_name: Kraus
- first_name: Marco
full_name: Platzner, Marco
id: '398'
last_name: Platzner
citation:
ama: 'Boschmann A, Agne A, Witschen LM, Thombansen G, Kraus F, Platzner M. FPGA-based
acceleration of high density myoelectric signal processing. In: 2015 International
Conference on ReConFigurable Computing and FPGAs (ReConFig). IEEE; 2016. doi:10.1109/reconfig.2015.7393312'
apa: 'Boschmann, A., Agne, A., Witschen, L. M., Thombansen, G., Kraus, F., &
Platzner, M. (2016). FPGA-based acceleration of high density myoelectric signal
processing. In 2015 International Conference on ReConFigurable Computing and
FPGAs (ReConFig). Mexiko City, Mexiko: IEEE. https://doi.org/10.1109/reconfig.2015.7393312'
bibtex: '@inproceedings{Boschmann_Agne_Witschen_Thombansen_Kraus_Platzner_2016,
title={FPGA-based acceleration of high density myoelectric signal processing},
DOI={10.1109/reconfig.2015.7393312},
booktitle={2015 International Conference on ReConFigurable Computing and FPGAs
(ReConFig)}, publisher={IEEE}, author={Boschmann, Alexander and Agne, Andreas
and Witschen, Linus Matthias and Thombansen, Georg and Kraus, Florian and Platzner,
Marco}, year={2016} }'
chicago: Boschmann, Alexander, Andreas Agne, Linus Matthias Witschen, Georg Thombansen,
Florian Kraus, and Marco Platzner. “FPGA-Based Acceleration of High Density Myoelectric
Signal Processing.” In 2015 International Conference on ReConFigurable Computing
and FPGAs (ReConFig). IEEE, 2016. https://doi.org/10.1109/reconfig.2015.7393312.
ieee: A. Boschmann, A. Agne, L. M. Witschen, G. Thombansen, F. Kraus, and M. Platzner,
“FPGA-based acceleration of high density myoelectric signal processing,” in 2015
International Conference on ReConFigurable Computing and FPGAs (ReConFig),
Mexiko City, Mexiko, 2016.
mla: Boschmann, Alexander, et al. “FPGA-Based Acceleration of High Density Myoelectric
Signal Processing.” 2015 International Conference on ReConFigurable Computing
and FPGAs (ReConFig), IEEE, 2016, doi:10.1109/reconfig.2015.7393312.
short: 'A. Boschmann, A. Agne, L.M. Witschen, G. Thombansen, F. Kraus, M. Platzner,
in: 2015 International Conference on ReConFigurable Computing and FPGAs (ReConFig),
IEEE, 2016.'
conference:
location: Mexiko City, Mexiko
name: 2015 International Conference on ReConFigurable Computing and FPGAs (ReConFig)
date_created: 2020-02-11T07:48:56Z
date_updated: 2022-01-06T06:52:38Z
department:
- _id: '78'
doi: 10.1109/reconfig.2015.7393312
keyword:
- Electromyography
- Feature extraction
- Delays
- Hardware Pattern recognition
- Prosthetics
- High definition video
language:
- iso: eng
publication: 2015 International Conference on ReConFigurable Computing and FPGAs (ReConFig)
publication_identifier:
isbn:
- '9781467394062'
publication_status: published
publisher: IEEE
status: public
title: FPGA-based acceleration of high density myoelectric signal processing
type: conference
user_id: '49051'
year: '2016'
...
---
_id: '9880'
abstract:
- lang: eng
text: With the paradigm shift towards prognostic and health management (PHM) of
machinery, there is need for reliable PHM methodologies with narrow error bounds
to allow maintenance engineers take decisive maintenance actions based on the
prognostic results. Prognostics is mainly concerned with the estimation of the
remaining useful life (RUL) or time to failure (TTF). The accuracy of PHM methods
is usually a function of the features extracted from the raw data obtained from
sensors. In cases where the extracted features do not display clear degradation
trends, for instance highly loaded bearings, the accuracy of the state of the
art PHM methods is significantly affected. The data which lacks clear degradation
trend is referred to as non-trending data. This study presents a method for extracting
degradation trends from non-trending condition monitoring data for RUL estimation.
The raw signals are first filtered using a discrete wavelet transform (DWT) denoising
filter to remove noise from the acquired signals. Time domain, frequency domain
and time-frequency domain features are then extracted from the filtered signals.
An autoregressive model is then applied to the extracted features to identify
the degradation trends. Features representing the maximum health information are
then selected based on a performance evaluation criteria using extreme learning
machine (ELM) algorithm. The selected features can then be used as inputs in a
prognostic algorithm. The feasibility of the method is demonstrated using experimental
bearing vibration data. The performance of the method is evaluated on the accuracy
of RUL estimation and the results show that the method can be used to accurately
estimate RUL with a maximum error of 10\%.
author:
- first_name: James Kuria
full_name: Kimotho, James Kuria
last_name: Kimotho
- first_name: Walter
full_name: Sextro, Walter
id: '21220'
last_name: Sextro
citation:
ama: 'Kimotho JK, Sextro W. An approach for feature extraction and selection from
non-trending data for machinery prognosis. In: Proceedings of the Second European
Conference of the Prognostics and Health Management Society 2014. Vol 5. ;
2014.'
apa: Kimotho, J. K., & Sextro, W. (2014). An approach for feature extraction
and selection from non-trending data for machinery prognosis. In Proceedings
of the Second European Conference of the Prognostics and Health Management Society
2014 (Vol. 5).
bibtex: '@inproceedings{Kimotho_Sextro_2014, title={An approach for feature extraction
and selection from non-trending data for machinery prognosis}, volume={5}, booktitle={Proceedings
of the Second European Conference of the Prognostics and Health Management Society
2014}, author={Kimotho, James Kuria and Sextro, Walter}, year={2014} }'
chicago: Kimotho, James Kuria, and Walter Sextro. “An Approach for Feature Extraction
and Selection from Non-Trending Data for Machinery Prognosis.” In Proceedings
of the Second European Conference of the Prognostics and Health Management Society
2014, Vol. 5, 2014.
ieee: J. K. Kimotho and W. Sextro, “An approach for feature extraction and selection
from non-trending data for machinery prognosis,” in Proceedings of the Second
European Conference of the Prognostics and Health Management Society 2014,
2014, vol. 5.
mla: Kimotho, James Kuria, and Walter Sextro. “An Approach for Feature Extraction
and Selection from Non-Trending Data for Machinery Prognosis.” Proceedings
of the Second European Conference of the Prognostics and Health Management Society
2014, vol. 5, 2014.
short: 'J.K. Kimotho, W. Sextro, in: Proceedings of the Second European Conference
of the Prognostics and Health Management Society 2014, 2014.'
date_created: 2019-05-20T13:13:00Z
date_updated: 2019-09-16T10:37:35Z
department:
- _id: '151'
intvolume: ' 5'
keyword:
- autoregressive model ELM feature extraction feature selection non-trending Remaining
useful Life
language:
- iso: eng
publication: Proceedings of the Second European Conference of the Prognostics and
Health Management Society 2014
quality_controlled: '1'
status: public
title: An approach for feature extraction and selection from non-trending data for
machinery prognosis
type: conference
user_id: '55222'
volume: 5
year: '2014'
...