Mid Sweden University

miun.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Trade-off between Spectral Feature Extractors for Machine Health Prognostics on Microcontrollers
Mid Sweden University, Faculty of Science, Technology and Media, Department of Electronics Design. IMMS Institut für Mikroelektronik- und Mechatronik-Systeme gemeinnützige GmbH (IMMS GmbH), Ilmenau, Germany.
2022 (English)In: CIVEMSA 2022 - IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications, Proceedings, IEEE, 2022Conference paper, Published paper (Refereed)
Abstract [en]

Machine learning methods have shown a high impact on machine health prognostics solutions. However, most studies stop after building a model on a server or pc, without deploying it to embedded systems close to the machinery. Bringing machine learning models to small embedded systems with a small energy budget does require adapted models and raw time series data processing to handle resource constraints while maintaining high model performance. Feature extraction plays a crucial role in this process. One of the most common methods for machinery data feature is its spectral information, that are extracted via digital filters. Calculating spectral features on microcontrollers has a great impact on the computational requirements of the overall estimations. In this paper, we analyze mel-spectrogram and infinite impulse response (IIR) based spectral feature extractors regarding their estimation performances and their computational requirements. The goal is to evaluate possible trade-offs when selecting one feature extractor over the other. To achieve this, we study the cost of both methods theoretically and via run-time measurements after analyzing the feature design space to ensure good model performance. Our results show that by selecting an appropriate filter to the problem, its feature space dimensionality and, consequently, its computational load can be reduced. 

Place, publisher, year, edition, pages
IEEE, 2022.
Keywords [en]
embedded system, filter-banks, logarithmic mel-spectrogram, machine condition estimation, machine learning, microcontroller
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:miun:diva-46168DOI: 10.1109/CIVEMSA53371.2022.9853642ISI: 000859912400002Scopus ID: 2-s2.0-85137787617ISBN: 9781665434454 (electronic)OAI: oai:DiVA.org:miun-46168DiVA, id: diva2:1699211
Conference
10th IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications, CIVEMSA 2022, 15 June 2022 through 17 June 2022
Available from: 2022-09-27 Created: 2022-09-27 Last updated: 2022-10-20Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Krug, Silvia

Search in DiVA

By author/editor
Krug, Silvia
By organisation
Department of Electronics Design
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 40 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf