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
Design and implementation of a data acquisition system with filter quality evaluation
KTH, School of Electrical Engineering and Computer Science (EECS), Communication Systems, CoS. (CCS)
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Design och implementering av ett datainsamlingssystem med filterkvalitet utvärdering (Swedish)
Abstract [en]

Particulate matter is a growing health concern that is considered to contribute to many diseases. To develop appropriate air filtration systems, we need to understand how particulate matter affects air filters. In this project, we implement an automated data acquisition system for an air filter test rig. The data acquisition system allows us to gather empirical data on how particle matter affects air filters over time. Although the quality of the air filters does not reach critical levels, there is a measurable degradation. The collected data is used to train and validate a machine learning model that can evaluate air filter quality. This machine learning proved to be a powerful tool in air filter evaluation and performs with 99% accuracy on test data. The result of this project is a fully functioning data acquisition system along with a user interface that considerably reduces the number of man-hours needed to perform tests of filters. In addition, the automated data acquisition system can notify the operator when the rig needs a change of filter or when certain faults occur. Unfortunately, the project did not reach its original goal of being able to automatically determine when the test rig needs maintenance or re-calibration.

Abstract [sv]

Luftburna partiklar är en växande hälsorisk som anses bidra till ohälsa. För att utveckla lämpliga luftfiltreringssystem måste en bättre förståelse nås för hur luftburna partiklar degraderar luftfilter. I det här projektet så implementeras ett automatiskt datainsamlingssystem i en testrigg för luftfilter. Datainsamlingssystemet samlar in empiriska data för hur luftburna partiklar degraderar filter över tid. Även om luftfiltren inte når kritiska nivåer, visar testerna på en mätbar degradering. Insamlat data används för att träna och validera en maskininlärningsmodell för att utvärdera filterkvalitet. Maskininlärning visade sig vara en kraftfull metod för att utvärdera luftfilter med 99% noggrannhet för testdata. Resultatet av det här projektet är ett fullt fungerande datainsamlingssystem tillsammans med ett användargränssnitt som avsevärt minskar tidsåtgången för att utföra test och utvärdera filter. Dessutom kan det automatiska datainsamlingssystemet meddela operatören när riggen behöver byta filter eller när vissa fel uppstår. Återstående arbete består i att implementera när testriggen behöver service eller kalibrering.

Place, publisher, year, edition, pages
2019. , p. xiii,47
Series
TRITA-EECS-EX ; 2019:178
Keywords [en]
Data acquisition, Automation, Particulate matter filtration, Filter quality evaluation, Machine learning
Keywords [sv]
Datainsamling, Automatisering, Partikelämnen filtrering, Filter kvalitetsutvärdering, Maskininlärning
National Category
Embedded Systems
Identifiers
URN: urn:nbn:se:kth:diva-254817OAI: oai:DiVA.org:kth-254817DiVA, id: diva2:1335461
External cooperation
Blueair Cabin Air
Presentation
2019-06-14, Seminar room Grimeton, Kistagången 16, Kista, 13:00 (English)
Supervisors
Examiners
Available from: 2019-08-08 Created: 2019-07-05 Last updated: 2019-08-08Bibliographically approved

Open Access in DiVA

fulltext(2306 kB)19 downloads
File information
File name FULLTEXT01.pdfFile size 2306 kBChecksum SHA-512
7dac0e9ba3603854d00b08e83c0c6c6113634e77ac47ecb147950ad6947af3c77f1baf52fb3292eaf77c0b6a633d1a97f04014c92710599ee81d3786ee701d95
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Karlsson, Örn Arnar
By organisation
Communication Systems, CoS
Embedded Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 19 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 58 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