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
Method for Event Detection in Mechatronic Systems Using Deep Learning
KTH, School of Industrial Engineering and Management (ITM), Machine Design (Dept.), Mechatronics.
KTH, School of Industrial Engineering and Management (ITM), Machine Design (Dept.), Mechatronics.
2018 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Metod för händelsedetektering i mekatroniska system genom djupinlärning (English)
Abstract [en]

Artificial Intelligence and Deep Learning are new drivers for technological change, and finds their way into more and more applications. These technologies have the ability to learn com-plex tasks previously hard to automate. In this thesis, the usage of deep learning is applied and evaluated in the context of product assembly where components are joined together. The specific problem studied is the process of clamping by using threaded fasteners.

The thesis evaluates several deep learning models, such as Recurrent Neural Networks (RNN), Long Short-Term Memory Neural Networks (LSTM) and Convolutional Neural Networks (CNN), and presents a new method for estimating the rotational angle at which the fastener mates with the material, also called snug-angle, using a combined detection-by-classification and regression approach with stacked LSTM neural networks. The method can be imple-mented to make precision clamping using angle tightening instead of torque tightening. Thistightening method offers an increase in clamp force accuracy, from ±43% to ±17%.

Various estimation methods and inference frequencies are evaluated to offer insight in the lim-itations of the model. The top method achieves a precision of 0.05 2.35¶ when estimating the snug-angle and can classify where the snug-angle occurs wi≠th 99.±26% accuracy.

The thesis also takes into account the demanding requirements of an implementation on mechatronic systems and presents advantages and disadvantages of the state-of-the-art model compression methods used to achieve a lightweight and efficient algorithm. Usage of these methods can give compression rates, energy efficiency and speed that are in the order of 10◊ to 100◊ compared to the original model, without loss of performance.

Abstract [sv]

Artificiell Intelligens och djupinlärning är nya drivkrafter för teknologisk förändring och förekommer i allt fler applikationer. Dessa teknologier har förmågan att lära sig komplexa uppgifter som tidigare var svåra att automatisera. I detta examensarbete undersöks möjligheten att använda djupinlärning inom åtdragning av gängade fästelement.

Examensarbetet utvärderar flera djupinlärningsmodeller, såsom Recurrent Neural Networks(RNN), Long Short-Term Memory Neural Networks (LSTM) och Convolutional Neural Networks (CNN) och presenterar en ny metod för att estimera rotationsvinkeln vid vilken fästelement tar i materialet, även kallat snugangle. Detta uppnås med en kombinerad detektering via-klassificering- och regressionsmetod baserat på staplade LSTM-nätverk. Metoden möjliggör precisionsåtdragningar genom vinkelåtdragning istället för moment åtdragning. Denna typ av åtdragning ger en precisionsförbättring frän ±43% to ±17% på uppnådd klämkraft.

Flera estimeringsmetoder och utsignalsfrekvenser utvärderas för att belysa algoritmens begränsningar. Metoden uppnår en noggrannhet på ≠0.05±2.35¶ och klarar att klassificera en händelse med 99.26 % precision.

Examensarbetet tar även hänsyn till de höga krav en implementation av maskininlärning ställer på mekatroniska system och presenterar fördelar och nackdelar med de senaste kompression metoderna som används för att få en lättviktig och effektiv algoritm. Användandet av dessa metoder kan ge ökad energieffektivitet, snabbhet och storleksminskning i storleksordningen 10x till 100x jämfört med originalmodellen, utan att förlora prestanda.

Place, publisher, year, edition, pages
2018. , p. 80
Series
TRITA-ITM-EX 2018 ; 195
National Category
Mechanical Engineering
Identifiers
URN: urn:nbn:se:kth:diva-245181OAI: oai:DiVA.org:kth-245181DiVA, id: diva2:1294113
Supervisors
Examiners
Available from: 2019-03-06 Created: 2019-03-06 Last updated: 2019-03-06Bibliographically approved

Open Access in DiVA

fulltext(3413 kB)29 downloads
File information
File name FULLTEXT01.pdfFile size 3413 kBChecksum SHA-512
008e0a795e77c79d0615ef8facbe9a25c2beb5ce29d33eb6267adb279b6b16b2884963ae19f42e0d199a01a5323911211760ae115fd6256236d6866e8c8214f2
Type fulltextMimetype application/pdf

By organisation
Mechatronics
Mechanical Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 29 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: 84 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