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
Generalization of Electric Vehicles' Battery Cell Models with Machine Learning
KTH, School of Electrical Engineering and Computer Science (EECS).
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Battery cells are the core of any electric vehicles (EV). It is important to get theaccurate value of different characteristics in a battery cell for safety and lifetime concern.And Two machine learning methods, support vector machine for regression(SVR) and multilayer perceptron (MLP) were introduced to improve the performanceof predicting the battery cell voltage using certain circuit related featureslike current, capacity and temperature on two different kinds of datasets. Differentconfigurations are validated using cross-validation to find the most suitable configurationof the parameters of these two machine learning models. Besides directimplementation, another pipeline is to build these machine learning models on oneexist traditional model and improve its performance.

Abstract [sv]

Batterikällor är kärnan i alla elektriska fordon (EV). Det är viktigt att få det exaktavärdet av olika egenskaper i en batterilucka för säkerhet och livslängd. Och två maskininlärningsmetoder,stöd vektor maskin för regression (SVR) och flerlagsperceptron(MLP) introducerades för att förbättra prestanda för att förutsäga batterispänningenmed användning av vissa kretsrelaterade funktioner som ström, kapacitet ochtemperatur på två olika typer av dataset. Olika konfigurationer valideras med hjälpav cross-validering för att hitta den lämpligaste konfigurationen av parametrarnaför dessa två maskininlärningsmodeller. Förutom direkt implementering är en annanpipeline att bygga dessa maskininlärningsmodeller på en existerande traditionellmodell och förbättra prestanda.

Place, publisher, year, edition, pages
2019. , p. 34
Series
TRITA-EECS-EX ; 2019:417
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:kth:diva-266108OAI: oai:DiVA.org:kth-266108DiVA, id: diva2:1381320
External cooperation
Volvo Cars
Educational program
Master of Science - Information and Network Engineering
Examiners
Available from: 2019-12-20 Created: 2019-12-20 Last updated: 2019-12-20Bibliographically approved

Open Access in DiVA

fulltext(4748 kB)17 downloads
File information
File name FULLTEXT01.pdfFile size 4748 kBChecksum SHA-512
a05b078a48a69b07e4fb94591ae9b2e9da63a237c3f55316db2f74e83d27734443b1926ee6fc84f512611d0444b2a159ee826107037e152b9fee17eea2124043
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 17 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: 38 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