kth.sePublications
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
Artificial Intelligence in Semiconductor Production: Sustaining Moore’s Law
KTH, School of Electrical Engineering and Computer Science (EECS).
KTH, School of Electrical Engineering and Computer Science (EECS).
2024 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
Artificiell Intelligens i Halvledarproduktion : Att Upprätthålla Moores Lag (Swedish)
Abstract [en]

The semiconductor industry has since the 1960s been following the pace set by Moore’s Law. In recent years, artificial intelligence, specifically machine learning and deep learning, has started to become commonly used in the semiconductor industry. This thesis aims to examine how artificial intelligence is being used in the production processes of semiconductors and how the effects of using it will lead to the continuation of Moore’s Law. The study focuses on three areas where artificial intelligence is being used in production which are chip design, defect inspection, and predictive maintenance. Through a literature review, the thesis highlights the advantages found by the integration of artificial intelligence in the three areas. Artificial intelligence in chip design leads to an optimized design process resulting in improved power, performance, and area metrics. Additionally, artificial intelligence enhances defect inspection by identifying defects more precisely and reducing false positives. Predictive maintenance powered by artificial intelligence leads to a maximized runtime while reducing unscheduled downtime by predicting equipment failure. The findings indicate that artificial intelligence contributes to the efficiency and reliability of semiconductor production. Moreover, it allows increase in costs while improving performance and thereby supporting the continuation of Moore’s Law.

Abstract [sv]

Sedan 1960-talet har halvledarindustrin följt takten satt av Moores lag. Under de senaste åren har användadet av Artificiell Intelligens, specifikt maskininlärning och djupinlärning, blivit vanligare inom halvledar industrin. Arbeter syftar till att undersöka hur artificiell intelligens används i produktionsprocesserna av halvledare och hur påverkan av denna använding leder till fortsättningen av Moores lag. Studien fokuserar på tre områden där Artificiell Intelligens används, dessa är chipdesign, defektinspektion samt prediktivt underhåll. Genom en litterturstudie belyser avhandlingen fördelarna med att använda Artificiell Intelligens inom dessa tre områden. Användandet av Artificiell Intelligens inom chipdesign leder till en optimerad chipdesign process vilket resulterar i förbättrade kraft-, prestanda- och ytmått. Dessutom förbättrar Artificiell Intelligens defektinspektion genom att identifiera defekter mer exakt och att minska falskt positiva resultat. Prediktivt underhåll, som drivs av Artificiell Intelligens leder till en maximerad körtid medan den minskar oplanerade uppehåll genom att förutspå utrsutningsfel. Resultaten indikerar att Artificiell Intelligens bidrar till effektivitet och tillförlitlighet i halveldartillverkningen. Dessutom medger den en minskad kostnad och en ökad prestanda som därmed stödjer fortsättningen av Moores lag.

Place, publisher, year, edition, pages
2024. , p. 44
Series
TRITA-EECS-EX ; 2024:664
Keywords [en]
Semiconductors, Artificial Intelligience, Machine Learning, Deep Learning, Moore’s Law, Transistors, Predictive Maintenance, Chip Design, Defect Inspection
Keywords [sv]
Halvledare, Artificiell Intelligens, Djupinlärning, Maskininlärning, Moores lag, Transistorer, Prediktivt Underhåll, Chipdesign, Defekt Inspektion
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-354551OAI: oai:DiVA.org:kth-354551DiVA, id: diva2:1903934
Supervisors
Examiners
Available from: 2025-01-20 Created: 2024-10-07 Last updated: 2025-01-20Bibliographically approved

Open Access in DiVA

fulltext(542 kB)141 downloads
File information
File name FULLTEXT01.pdfFile size 542 kBChecksum SHA-512
71c31b25eaf0d4bb998316c8140d291767f9d6acd76262e4760896162888bdaff4cb5fedd620c26441ba7ee5ff4d60b75cc491233195381c8fbefd935159ace8
Type fulltextMimetype application/pdf

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

Search outside of DiVA

GoogleGoogle Scholar
Total: 141 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: 479 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