2020
DOI: 10.1365/s40702-020-00641-8
|View full text |Cite
|
Sign up to set email alerts
|

Mit Computer Vision zur automatisierten Qualitätssicherung in der industriellen Fertigung: Eine Fallstudie zur Klassifizierung von Fehlern in Solarzellen mittels Elektrolumineszenz-Bildern

Abstract: Zusammenfassung Die Qualitätssicherung bei der Produktion von Solarzellen ist ein entscheidender Faktor, um langfristige Leistungsgarantien auf Solarpanels gewähren zu können. Die vorliegende Arbeit leistet hierzu einen Beitrag zur automatisierten Fehlererkennung auf Wafern, indem Elektrolumineszenz-Bilder eines realen Herstellungsszenarios mithilfe von verschiedenen Computer-Vision-Modellen klassifiziert werden. Die Herausforderung besteht hierbei nicht nur darin, defekte Wafer von funktionsfähigen zu separie… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2021
2021
2022
2022

Publication Types

Select...
2
2
1

Relationship

2
3

Authors

Journals

citations
Cited by 5 publications
(3 citation statements)
references
References 20 publications
(16 reference statements)
0
3
0
Order By: Relevance
“…While automated quality control is common in many industries [27][28][29], the PV industry is lacking behind because of complex production environments. Consequently, the PV industry often still relies on manual human controls of PV wafers which is both tedious and costly and therefore offers grand potentials for improvements via automated inspections based on DL models [14,30].…”
Section: Case Descriptionmentioning
confidence: 99%
See 1 more Smart Citation
“…While automated quality control is common in many industries [27][28][29], the PV industry is lacking behind because of complex production environments. Consequently, the PV industry often still relies on manual human controls of PV wafers which is both tedious and costly and therefore offers grand potentials for improvements via automated inspections based on DL models [14,30].…”
Section: Case Descriptionmentioning
confidence: 99%
“…adversarial attacks [13] or induced biases [6]. Similarly, public images usually contain generic objects such as houses, cars, and animals, which rarely reflect the shapes of objects in industrial applications like technical components and surface defects [14]. Beyond that, pre-trained models often consist of several million parameters [15], which limits their application on small devices with limited hardware.…”
Section: Introductionmentioning
confidence: 99%
“…Fuelled by modern sensor technology, broad access to computing power, and the development of userfriendly programming frameworks, the field of computer vision (CV) is currently experiencing a renaissance that results in groundbreaking new applications: cars begin to drive autonomously in real traffic (Grigorescu et al, 2020), medical diagnosis systems support doctors in detecting hard-to-find diseases (McKinney et al, 2020), and intelligent manufacturing plants detect production deficiencies at an early stage (Zschech et al, 2020).…”
Section: Introductionmentioning
confidence: 99%