---
_id: '10216'
abstract:
- lang: eng
  text: Wet granulation is a frequent process in the pharmaceutical industry. As a
    starting point for numerous dosage forms, the quality of the granulation not only
    affects subsequent production steps but also impacts the quality of the final
    product. It is thus crucial and economical to monitor this operation thoroughly.
    Here, we report on identifying different phases of a granulation process using
    a machine learning approach. The phases reflect the water content which, in turn,
    influences the processability and quality of the granule mass. We used two kinds
    of microphones and an acceleration sensor to capture acoustic emissions and vibrations.
    We trained convolutional neural networks (CNNs) to classify the different phases
    using transformed sound recordings as the input. We achieved a classification
    accuracy of up to 90% using vibrational data and an accuracy of up to 97% using
    the audible microphone data. Our results indicate the suitability of using audible
    sound and machine learning to monitor pharmaceutical processes. Moreover, since
    recording acoustic emissions is contactless, it readily complies with legal regulations
    and presents Good Manufacturing Practices.
article_number: '2153'
author:
- first_name: Ruwen
  full_name: Fulek, Ruwen
  id: '79527'
  last_name: Fulek
- first_name: Selina
  full_name: Ramm, Selina
  id: '68713'
  last_name: Ramm
  orcid: https://orcid.org/0000-0002-0502-8032
- first_name: Christian
  full_name: Kiera, Christian
  last_name: Kiera
- first_name: Miriam
  full_name: Pein-Hackelbusch, Miriam
  id: '64952'
  last_name: Pein-Hackelbusch
  orcid: 0000-0002-7920-0595
- first_name: Ulrich
  full_name: Odefey, Ulrich
  id: '74218'
  last_name: Odefey
citation:
  ama: Fulek R, Ramm S, Kiera C, Pein-Hackelbusch M, Odefey U. A machine learning
    approach to qualitatively evaluate different granulation phases by acoustic emissions.
    <i>Pharmaceutics</i>. 2023;15(8). doi:<a href="https://doi.org/10.3390/pharmaceutics15082153">https://doi.org/10.3390/pharmaceutics15082153</a>
  apa: Fulek, R., Ramm, S., Kiera, C., Pein-Hackelbusch, M., &#38; Odefey, U. (2023).
    A machine learning approach to qualitatively evaluate different granulation phases
    by acoustic emissions. <i>Pharmaceutics</i>, <i>15</i>(8), Article 2153. <a href="https://doi.org/10.3390/pharmaceutics15082153">https://doi.org/10.3390/pharmaceutics15082153</a>
  bjps: <b>Fulek R <i>et al.</i></b> (2023) A Machine Learning Approach to Qualitatively
    Evaluate Different Granulation Phases by Acoustic Emissions. <i>Pharmaceutics</i>
    <b>15</b>.
  chicago: Fulek, Ruwen, Selina Ramm, Christian Kiera, Miriam Pein-Hackelbusch, and
    Ulrich Odefey. “A Machine Learning Approach to Qualitatively Evaluate Different
    Granulation Phases by Acoustic Emissions.” <i>Pharmaceutics</i> 15, no. 8 (2023).
    <a href="https://doi.org/10.3390/pharmaceutics15082153">https://doi.org/10.3390/pharmaceutics15082153</a>.
  chicago-de: Fulek, Ruwen, Selina Ramm, Christian Kiera, Miriam Pein-Hackelbusch
    und Ulrich Odefey. 2023. A machine learning approach to qualitatively evaluate
    different granulation phases by acoustic emissions. <i>Pharmaceutics</i> 15, Nr.
    8. doi:<a href="https://doi.org/10.3390/pharmaceutics15082153">https://doi.org/10.3390/pharmaceutics15082153</a>,
    .
  din1505-2-1: '<span style="font-variant:small-caps;">Fulek, Ruwen</span> ; <span
    style="font-variant:small-caps;">Ramm, Selina</span> ; <span style="font-variant:small-caps;">Kiera,
    Christian</span> ; <span style="font-variant:small-caps;">Pein-Hackelbusch, Miriam</span>
    ; <span style="font-variant:small-caps;">Odefey, Ulrich</span>: A machine learning
    approach to qualitatively evaluate different granulation phases by acoustic emissions.
    In: <i>Pharmaceutics</i> Bd. 15. Basel, MDPI (2023), Nr. 8'
  havard: R. Fulek, S. Ramm, C. Kiera, M. Pein-Hackelbusch, U. Odefey, A machine learning
    approach to qualitatively evaluate different granulation phases by acoustic emissions,
    Pharmaceutics. 15 (2023).
  ieee: 'R. Fulek, S. Ramm, C. Kiera, M. Pein-Hackelbusch, and U. Odefey, “A machine
    learning approach to qualitatively evaluate different granulation phases by acoustic
    emissions,” <i>Pharmaceutics</i>, vol. 15, no. 8, Art. no. 2153, 2023, doi: <a
    href="https://doi.org/10.3390/pharmaceutics15082153">https://doi.org/10.3390/pharmaceutics15082153</a>.'
  mla: Fulek, Ruwen, et al. “A Machine Learning Approach to Qualitatively Evaluate
    Different Granulation Phases by Acoustic Emissions.” <i>Pharmaceutics</i>, vol.
    15, no. 8, 2153, 2023, <a href="https://doi.org/10.3390/pharmaceutics15082153">https://doi.org/10.3390/pharmaceutics15082153</a>.
  short: R. Fulek, S. Ramm, C. Kiera, M. Pein-Hackelbusch, U. Odefey, Pharmaceutics
    15 (2023).
  ufg: '<b>Fulek, Ruwen u. a.</b>: A machine learning approach to qualitatively evaluate
    different granulation phases by acoustic emissions, in: <i>Pharmaceutics</i> 15
    (2023), H. 8.'
  van: Fulek R, Ramm S, Kiera C, Pein-Hackelbusch M, Odefey U. A machine learning
    approach to qualitatively evaluate different granulation phases by acoustic emissions.
    Pharmaceutics. 2023;15(8).
date_created: 2023-08-15T10:48:15Z
date_updated: 2025-07-29T13:21:40Z
department:
- _id: DEP4022
- _id: DEP4028
- _id: DEP4014
doi: https://doi.org/10.3390/pharmaceutics15082153
external_id:
  isi:
  - '001119084200001'
  pmid:
  - '37631367'
intvolume: '        15'
isi: '1'
issue: '8'
keyword:
- wet granulation
- acoustic classification
- machine learning
- convolutional neural networks
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://www.mdpi.com/1999-4923/15/8/2153
oa: '1'
place: Basel
pmid: '1'
publication: Pharmaceutics
publication_identifier:
  eissn:
  - '1999-4923 '
publication_status: published
publisher: MDPI
quality_controlled: '1'
status: public
title: A machine learning approach to qualitatively evaluate different granulation
  phases by acoustic emissions
type: scientific_journal_article
user_id: '83781'
volume: 15
year: '2023'
...