---
_id: '9808'
abstract:
- lang: eng
text: This study presents the methods employed by a team from the department of
Mechatronics and Dynamics at the University of Paderborn, Germany for the 2013
PHM data challenge. The focus of the challenge was on maintenance action recommendation
for an industrial machinery based on remote monitoring and diagnosis. Since an
ensemble of data driven methods has been considered as the state of the art approach
in diagnosis and prognosis, the first approach was to evaluate the performance
of an ensemble of data driven methods using the parametric data as input and problems
(recommended maintenance action) as the output. Due to close correlation of parametric
data of different problems, this approach produced high misclassification rate.
Event-based decision trees were then constructed to identify problems associated
with particular events. To distinguish between problems associated with events
that appeared in multiple problems, support vector machine (SVM) with parameters
optimally tuned using particle swarm optimization (PSO) was employed. Parametric
data was used as the input to the SVM algorithm and majority voting was employed
to determine the final decision for cases with multiple events. A total of 165
SVM models were constructed. This approach improved the overall score from 21
to 48. The method was further enhanced by employing an ensemble of three data
driven methods, that is, SVM, random forests (RF) and bagged trees (BT), to build
the event based models. With this approach, a score of 51 was obtained . The results
demonstrate that the proposed event based method can be effective in maintenance
action recommendation based on events codes and parametric data acquired remotely
from an industrial equipment.
author:
- first_name: James Kuria
full_name: Kimotho, James Kuria
last_name: Kimotho
- first_name: Chritoph
full_name: Sondermann-Wölke, Chritoph
last_name: Sondermann-Wölke
- first_name: Tobias
full_name: Meyer, Tobias
last_name: Meyer
- first_name: Walter
full_name: Sextro, Walter
id: '21220'
last_name: Sextro
citation:
ama: Kimotho JK, Sondermann-Wölke C, Meyer T, Sextro W. Application of Event Based
Decision Tree and Ensemble of Data Driven Methods for Maintenance Action Recommendation.
International Journal of Prognostics and Health Management. 2013;4(2).
apa: Kimotho, J. K., Sondermann-Wölke, C., Meyer, T., & Sextro, W. (2013). Application
of Event Based Decision Tree and Ensemble of Data Driven Methods for Maintenance
Action Recommendation. International Journal of Prognostics and Health Management,
4(2).
bibtex: '@article{Kimotho_Sondermann-Wölke_Meyer_Sextro_2013, title={Application
of Event Based Decision Tree and Ensemble of Data Driven Methods for Maintenance
Action Recommendation}, volume={4}, number={2}, journal={International Journal
of Prognostics and Health Management}, author={Kimotho, James Kuria and Sondermann-Wölke,
Chritoph and Meyer, Tobias and Sextro, Walter}, year={2013} }'
chicago: Kimotho, James Kuria, Chritoph Sondermann-Wölke, Tobias Meyer, and Walter
Sextro. “Application of Event Based Decision Tree and Ensemble of Data Driven
Methods for Maintenance Action Recommendation.” International Journal of Prognostics
and Health Management 4, no. 2 (2013).
ieee: J. K. Kimotho, C. Sondermann-Wölke, T. Meyer, and W. Sextro, “Application
of Event Based Decision Tree and Ensemble of Data Driven Methods for Maintenance
Action Recommendation,” International Journal of Prognostics and Health Management,
vol. 4, no. 2, 2013.
mla: Kimotho, James Kuria, et al. “Application of Event Based Decision Tree and
Ensemble of Data Driven Methods for Maintenance Action Recommendation.” International
Journal of Prognostics and Health Management, vol. 4, no. 2, 2013.
short: J.K. Kimotho, C. Sondermann-Wölke, T. Meyer, W. Sextro, International Journal
of Prognostics and Health Management 4 (2013).
date_created: 2019-05-13T14:15:36Z
date_updated: 2022-01-06T07:04:21Z
department:
- _id: '151'
intvolume: ' 4'
issue: '2'
keyword:
- maintenance decision
- Bagged trees
- Decision trees
- PSO-SVM
- Random forests
language:
- iso: eng
publication: International Journal of Prognostics and Health Management
quality_controlled: '1'
status: public
title: Application of Event Based Decision Tree and Ensemble of Data Driven Methods
for Maintenance Action Recommendation
type: journal_article
user_id: '55222'
volume: 4
year: '2013'
...