Stender, Merten ; Adams, Christian ; Wedler, Mathies ; Grebel, Antje ; Hoffmann, Nobert (2024)
Explainable machine learning determines effects on the sound absorption coefficient measured in the impedance tube.
In: The Journal of the Acoustical Society of America, 2021, 149 (3)
doi: 10.26083/tuprints-00028662
Artikel, Zweitveröffentlichung, Verlagsversion
 | Es ist eine neuere Version dieses Eintrags verfügbar. |
Kurzbeschreibung (Abstract)
Measurements of acoustic properties of sound absorbing materials in impedance tubes show poor reproducibility, which was demonstrated in round robin tests. The impedance tube measurements are standardized but lack precise definitions of the actual measurement setup, specimen preparation, and other factors that introduce uncertainty in practice. In this paper, machine learning models identify those factors that mostly affect the sound absorption coefficient from a large data set of more than 3000 absorption spectra measured in one impedance tube. The specimens are manufactured from one polyurethane foam, and different cutting technologies, different operators, different specimen diameters, different specimen thicknesses, and two different approaches to mount the specimens in the impedance tube are considered. Explainable machine learning techniques allow the identification and quantification of the most influential factors and, furthermore, the frequency ranges that are the most affected by the choice of these setup factors. The results indicate that besides the specimen thickness, also the operator affects the absorption coefficient by a directional and non-random relationship. Hence, it needs to be controlled carefully. The method proves to be a promising pathway for knowledge discovery from acoustic measurement data using explainability approaches for machine learning models.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2024 |
| Autor(en): | Stender, Merten ; Adams, Christian ; Wedler, Mathies ; Grebel, Antje ; Hoffmann, Nobert |
| Art des Eintrags: | Zweitveröffentlichung |
| Titel: | Explainable machine learning determines effects on the sound absorption coefficient measured in the impedance tube |
| Sprache: | Englisch |
| Publikationsjahr: | 11 November 2024 |
| Ort: | Darmstadt |
| Publikationsdatum der Erstveröffentlichung: | 2021 |
| Ort der Erstveröffentlichung: | Melville, NY |
| Verlag: | AIP Publishing |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | The Journal of the Acoustical Society of America |
| Jahrgang/Volume einer Zeitschrift: | 149 |
| (Heft-)Nummer: | 3 |
| Kollation: | 15 Seiten |
| DOI: | 10.26083/tuprints-00028662 |
| URL / URN: | https://tuprints.ulb.tu-darmstadt.de/28662 |
| Zugehörige Links: | |
| Herkunft: | Zweitveröffentlichungsservice |
| Kurzbeschreibung (Abstract): | Measurements of acoustic properties of sound absorbing materials in impedance tubes show poor reproducibility, which was demonstrated in round robin tests. The impedance tube measurements are standardized but lack precise definitions of the actual measurement setup, specimen preparation, and other factors that introduce uncertainty in practice. In this paper, machine learning models identify those factors that mostly affect the sound absorption coefficient from a large data set of more than 3000 absorption spectra measured in one impedance tube. The specimens are manufactured from one polyurethane foam, and different cutting technologies, different operators, different specimen diameters, different specimen thicknesses, and two different approaches to mount the specimens in the impedance tube are considered. Explainable machine learning techniques allow the identification and quantification of the most influential factors and, furthermore, the frequency ranges that are the most affected by the choice of these setup factors. The results indicate that besides the specimen thickness, also the operator affects the absorption coefficient by a directional and non-random relationship. Hence, it needs to be controlled carefully. The method proves to be a promising pathway for knowledge discovery from acoustic measurement data using explainability approaches for machine learning models. |
| Status: | Verlagsversion |
| URN: | urn:nbn:de:tuda-tuprints-286624 |
| Sachgruppe der Dewey Dezimalklassifikatin (DDC): | 600 Technik, Medizin, angewandte Wissenschaften > 620 Ingenieurwissenschaften und Maschinenbau |
| Fachbereich(e)/-gebiet(e): | 16 Fachbereich Maschinenbau 16 Fachbereich Maschinenbau > Fachgebiet Systemzuverlässigkeit, Adaptronik und Maschinenakustik (SAM) |
| Hinterlegungsdatum: | 11 Nov 2024 10:52 |
| Letzte Änderung: | 12 Nov 2024 07:23 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
Verfügbare Versionen dieses Eintrags
- Explainable machine learning determines effects on the sound absorption coefficient measured in the impedance tube. (deposited 11 Nov 2024 10:52) [Gegenwärtig angezeigt]
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum