---
_id: '34196'
abstract:
- lang: eng
  text: <jats:p>Mounting sensors in disk stack separators is often a major challenge
    due to the operating conditions. However, a process cannot be optimally monitored
    without sensors. Virtual sensors can be a solution to calculate the sought parameters
    from measurable values. We measured the vibrations of disk stack separators and
    applied machine learning (ML) to detect whether the separator contains only water
    or whether particles are also present. We combined seven ML classification algorithms
    with three feature engineering strategies and evaluated our model successfully
    on vibration data of an experimental disk stack separator. Our experimental results
    demonstrate that random forest in combination with manual feature engineering
    using domain specific knowledge about suitable features outperforms all other
    models with an accuracy of 91.27 %.</jats:p>
author:
- first_name: Silke
  full_name: Merkelbach, Silke
  last_name: Merkelbach
- first_name: Lameya
  full_name: Afroze, Lameya
  last_name: Afroze
- first_name: Nils
  full_name: Janssen, Nils
  last_name: Janssen
- first_name: Sebastian
  full_name: von Enzberg, Sebastian
  last_name: von Enzberg
- first_name: Arno
  full_name: Kühn, Arno
  last_name: Kühn
- first_name: Roman
  full_name: Dumitrescu, Roman
  last_name: Dumitrescu
citation:
  ama: Merkelbach S, Afroze L, Janssen N, von Enzberg S, Kühn A, Dumitrescu R. Using
    vibration data to classify conditions in disk stack separators. <i>Vibroengineering
    PROCEDIA</i>. 2022;46:21-26. doi:<a href="https://doi.org/10.21595/vp.2022.23000">10.21595/vp.2022.23000</a>
  apa: Merkelbach, S., Afroze, L., Janssen, N., von Enzberg, S., Kühn, A., &#38; Dumitrescu,
    R. (2022). Using vibration data to classify conditions in disk stack separators.
    <i>Vibroengineering PROCEDIA</i>, <i>46</i>, 21–26. <a href="https://doi.org/10.21595/vp.2022.23000">https://doi.org/10.21595/vp.2022.23000</a>
  bibtex: '@article{Merkelbach_Afroze_Janssen_von Enzberg_Kühn_Dumitrescu_2022, title={Using
    vibration data to classify conditions in disk stack separators}, volume={46},
    DOI={<a href="https://doi.org/10.21595/vp.2022.23000">10.21595/vp.2022.23000</a>},
    journal={Vibroengineering PROCEDIA}, publisher={JVE International Ltd.}, author={Merkelbach,
    Silke and Afroze, Lameya and Janssen, Nils and von Enzberg, Sebastian and Kühn,
    Arno and Dumitrescu, Roman}, year={2022}, pages={21–26} }'
  chicago: 'Merkelbach, Silke, Lameya Afroze, Nils Janssen, Sebastian von Enzberg,
    Arno Kühn, and Roman Dumitrescu. “Using Vibration Data to Classify Conditions
    in Disk Stack Separators.” <i>Vibroengineering PROCEDIA</i> 46 (2022): 21–26.
    <a href="https://doi.org/10.21595/vp.2022.23000">https://doi.org/10.21595/vp.2022.23000</a>.'
  ieee: 'S. Merkelbach, L. Afroze, N. Janssen, S. von Enzberg, A. Kühn, and R. Dumitrescu,
    “Using vibration data to classify conditions in disk stack separators,” <i>Vibroengineering
    PROCEDIA</i>, vol. 46, pp. 21–26, 2022, doi: <a href="https://doi.org/10.21595/vp.2022.23000">10.21595/vp.2022.23000</a>.'
  mla: Merkelbach, Silke, et al. “Using Vibration Data to Classify Conditions in Disk
    Stack Separators.” <i>Vibroengineering PROCEDIA</i>, vol. 46, JVE International
    Ltd., 2022, pp. 21–26, doi:<a href="https://doi.org/10.21595/vp.2022.23000">10.21595/vp.2022.23000</a>.
  short: S. Merkelbach, L. Afroze, N. Janssen, S. von Enzberg, A. Kühn, R. Dumitrescu,
    Vibroengineering PROCEDIA 46 (2022) 21–26.
date_created: 2022-12-05T12:47:22Z
date_updated: 2022-12-05T12:51:08Z
department:
- _id: '563'
doi: 10.21595/vp.2022.23000
intvolume: '        46'
keyword:
- General Medicine
language:
- iso: eng
page: 21-26
publication: Vibroengineering PROCEDIA
publication_identifier:
  issn:
  - 2345-0533
  - 2538-8479
publication_status: published
publisher: JVE International Ltd.
status: public
title: Using vibration data to classify conditions in disk stack separators
type: journal_article
user_id: '15782'
volume: 46
year: '2022'
...