Abstract
Semiconductor manufacturing is a highly innovative branch of industry, where a high degree of automation has already been achieved. For example, devices tested to be outside of their specifications in electrical wafer test are automatically scrapped. In this paper, we go one step further and analyze test data of devices still within the limits of the specification, by exploiting the information contained in the analog wafermaps. To that end, we propose two feature extraction approaches with the aim to detect patterns in the wafer test dataset. Such patterns might indicate the onset of critical deviations in the production process. The studied approaches are: 1) classical image processing and restoration techniques in combination with sophisticated feature engineering and 2) a data-driven deep generative model. The two approaches are evaluated on both a synthetic and a real-world dataset. The synthetic dataset has been modeled based on real-world patterns and characteristics. We found both approaches to provide similar overall evaluation metrics. Our in-depth analysis helps to choose one approach over the other depending on data availability as a major aspect, as well as on available computing power and required interpretability of the results.
Originalsprache | englisch |
---|---|
Aufsatznummer | 8689102 |
Seiten (von - bis) | 190-198 |
Seitenumfang | 9 |
Fachzeitschrift | IEEE transactions on semiconductor manufacturing |
Jahrgang | 32 |
Ausgabenummer | 2 |
DOIs | |
Publikationsstatus | Veröffentlicht - Mai 2019 |
Fingerprint
Schlagwörter
ASJC Scopus subject areas
- !!Electronic, Optical and Magnetic Materials
- !!Condensed Matter Physics
- !!Electrical and Electronic Engineering
- !!Industrial and Manufacturing Engineering
Dies zitieren
Feature Extraction From Analog Wafermaps: A Comparison of Classical Image Processing and a Deep Generative Model. / Teixeira dos Santos, Tiago Filipe; Schrunner, Stefan; Geiger, Bernhard; Pfeiler, Olivia; Zernig, Anja; Kaestner, Andre; Kern, Roman.
in: IEEE transactions on semiconductor manufacturing, Jahrgang 32, Nr. 2, 8689102, 05.2019, S. 190-198.Publikation: Beitrag in einer Fachzeitschrift › Artikel › Forschung › Begutachtung
}
TY - JOUR
T1 - Feature Extraction From Analog Wafermaps: A Comparison of Classical Image Processing and a Deep Generative Model
AU - Teixeira dos Santos, Tiago Filipe
AU - Schrunner, Stefan
AU - Geiger, Bernhard
AU - Pfeiler, Olivia
AU - Zernig, Anja
AU - Kaestner, Andre
AU - Kern, Roman
PY - 2019/5
Y1 - 2019/5
N2 - Semiconductor manufacturing is a highly innovative branch of industry, where a high degree of automation has already been achieved. For example, devices tested to be outside of their specifications in electrical wafer test are automatically scrapped. In this paper, we go one step further and analyze test data of devices still within the limits of the specification, by exploiting the information contained in the analog wafermaps. To that end, we propose two feature extraction approaches with the aim to detect patterns in the wafer test dataset. Such patterns might indicate the onset of critical deviations in the production process. The studied approaches are: 1) classical image processing and restoration techniques in combination with sophisticated feature engineering and 2) a data-driven deep generative model. The two approaches are evaluated on both a synthetic and a real-world dataset. The synthetic dataset has been modeled based on real-world patterns and characteristics. We found both approaches to provide similar overall evaluation metrics. Our in-depth analysis helps to choose one approach over the other depending on data availability as a major aspect, as well as on available computing power and required interpretability of the results.
AB - Semiconductor manufacturing is a highly innovative branch of industry, where a high degree of automation has already been achieved. For example, devices tested to be outside of their specifications in electrical wafer test are automatically scrapped. In this paper, we go one step further and analyze test data of devices still within the limits of the specification, by exploiting the information contained in the analog wafermaps. To that end, we propose two feature extraction approaches with the aim to detect patterns in the wafer test dataset. Such patterns might indicate the onset of critical deviations in the production process. The studied approaches are: 1) classical image processing and restoration techniques in combination with sophisticated feature engineering and 2) a data-driven deep generative model. The two approaches are evaluated on both a synthetic and a real-world dataset. The synthetic dataset has been modeled based on real-world patterns and characteristics. We found both approaches to provide similar overall evaluation metrics. Our in-depth analysis helps to choose one approach over the other depending on data availability as a major aspect, as well as on available computing power and required interpretability of the results.
KW - Automation
KW - data processing
KW - feature extraction
KW - unsupervised learning
UR - http://www.scopus.com/inward/record.url?scp=85065391683&partnerID=8YFLogxK
U2 - 10.1109/TSM.2019.2911061
DO - 10.1109/TSM.2019.2911061
M3 - Article
VL - 32
SP - 190
EP - 198
JO - IEEE transactions on semiconductor manufacturing
JF - IEEE transactions on semiconductor manufacturing
SN - 0894-6507
IS - 2
M1 - 8689102
ER -