Towards reliable parameter extraction in MEMS final module testing using Bayesian inference

dc.contributor.authorHeringhaus, Monika E.
dc.contributor.authorZhang, Yi
dc.contributor.authorZimmermann, André
dc.contributor.authorMikelsons, Lars
dc.date.accessioned2024-09-27T12:02:26Z
dc.date.available2024-09-27T12:02:26Z
dc.date.issued2022de
dc.date.updated2023-11-14T01:29:29Z
dc.description.abstractIn micro-electro-mechanical systems (MEMS) testing high overall precision and reliability are essential. Due to the additional requirement of runtime efficiency, machine learning methods have been investigated in recent years. However, these methods are often associated with inherent challenges concerning uncertainty quantification and guarantees of reliability. The goal of this paper is therefore to present a new machine learning approach in MEMS testing based on Bayesian inference to determine whether the estimation is trustworthy. The overall predictive performance as well as the uncertainty quantification are evaluated with four methods: Bayesian neural network, mixture density network, probabilistic Bayesian neural network and BayesFlow. They are investigated under the variation in training set size, different additive noise levels, and an out-of-distribution condition, namely the variation in the damping factor of the MEMS device. Furthermore, epistemic and aleatoric uncertainties are evaluated and discussed to encourage thorough inspection of models before deployment striving for reliable and efficient parameter estimation during final module testing of MEMS devices. BayesFlow consistently outperformed the other methods in terms of the predictive performance. As the probabilistic Bayesian neural network enables the distinction between epistemic and aleatoric uncertainty, their share of the total uncertainty has been intensively studied.en
dc.description.sponsorshipGerman Federal Ministry for Economic Affairs and Energy (BMWi)de
dc.identifier.issn1424-8220
dc.identifier.other1903696291
dc.identifier.urihttp://nbn-resolving.de/urn:nbn:de:bsz:93-opus-ds-149953de
dc.identifier.urihttp://elib.uni-stuttgart.de/handle/11682/14995
dc.identifier.urihttp://dx.doi.org/10.18419/opus-14976
dc.language.isoende
dc.relation.uridoi:10.3390/s22145408de
dc.rightsinfo:eu-repo/semantics/openAccessde
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/de
dc.subject.ddc620de
dc.titleTowards reliable parameter extraction in MEMS final module testing using Bayesian inferenceen
dc.typearticlede
ubs.fakultaetKonstruktions-, Produktions- und Fahrzeugtechnikde
ubs.fakultaetExterne wissenschaftliche Einrichtungende
ubs.fakultaetFakultätsübergreifend / Sonstige Einrichtungde
ubs.institutInstitut für Mikrointegrationde
ubs.institutHahn-Schickardde
ubs.institutFakultätsübergreifend / Sonstige Einrichtungde
ubs.publikation.seiten22de
ubs.publikation.sourceSensors 22 (2022), No. 5408de
ubs.publikation.typZeitschriftenartikelde

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
sensors-22-05408-v3.pdf
Size:
5.68 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
3.3 KB
Format:
Item-specific license agreed upon to submission
Description: