Incorporating Virtual Metrology Into Failure Prediction

Kang, Seokho; An, Daewoong; Rim, Jaeyoung

doi:10.1109/tsm.2019.2932377

Cited by 10 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [42], the authors presented a VM model to predict to perform wafer die inspection using ANN with a multi-task learning scheme. Wafers that completed the fabrication process are first tested at the wafer test phase to ensure the wafers meet the required electrical properties at the die level.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Realizable Overlay Virtual Metrology System in Semiconductor Manufacturing: Proposal, Challenges and Future Perspective

Tin

Tan

Yong³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Integrated circuits (IC) are fabricated on a wafer through stacked layers of circuit patterns. To ensure proper functionality, the overlay of each pattern layer must be within the tolerance. Inspecting each wafer's overlay is unrealistic and impractical. Hence, wafers are selectively inspected at metrology stations through sampling strategies. With virtual metrology (VM), the metrology quality of the uninspected wafers can be estimated. Motivated by a real-world production environment of a 200mm semiconductor manufacturing plant (fab), a VM to estimate the overlay of the photolithography process is envisioned. Past researches on overlay VM leveraged fault detection and classification (FDC) data to estimate the overlay errors. As such, for fabs in the progress of completing their FDC development for photolithography equipment, a different modeling approach is required to realize an overlay VM that sustains the production line until FDC data can be leveraged for VM. With practical gaps that must be addressed in real fabs, this paper focuses on realizing an overlay VM for the photolithography process without leveraging FDC data. Therefore, the objectives of this paper are two folds: First, to identify the research challenges towards realizing the overlay VM. Second, to propose the future research perspectives of the envisioned overlay VM. Based on the future research perspectives, a two-steps overlay VM modeling approach utilizing data mining techniques is proposed toward realizing the envisioned overlay VM system. The proposed approach first classifies the process stability at the wafer lot level, and subsequently, performs overlay error estimations for wafers in the wafer lots classified with stable process. Linear regression models are proposed to perform overlay error estimations in this work to augment the interpretability of the overlay VM.

show abstract

Section: Related Workmentioning

confidence: 99%

“…[41] Etching Etch rate • A feature extraction method using deep learning. [42] Final test Wafer die failure • A die failure prediction model utilizing VM in the joint model. Feature extraction over raw data instead of summarized statistically features used conventionally Data characteristics will gradually change over time regardless.…”

mentioning

confidence: 99%

A Realizable Overlay Virtual Metrology System in Semiconductor Manufacturing: Proposal, Challenges and Future Perspective

Tin

Tan

Yong³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In recent years, there has been active research and development of Virtual Metrology (VM), which virtually predicts the properties of finished products by statistical analysis of various data. [10][11][12][13][14][15] The effectiveness of VM has also been demonstrated in mass production. VM typically uses data from Equipment Engineering Systems (EES) such as process temperature, pressure and gas flow rate.…”

Section: Introductionmentioning

confidence: 99%

Chamber in-situ estimation during etching process by SiF₄ monitoring using laser absorption spectroscopy

Hada

Takahashi

Sakaguchi

et al. 2023

Jpn. J. Appl. Phys.

View full text Add to dashboard Cite

The behavior of the partial pressure of SiF4, a byproduct in fluorine-based plasma etching, has been measured in real-time using a method based on Laser　Absorption Spectroscopy (LAS). The partial pressure of SiF4 is highly correlated　with the etch rate of SiO2 (R2 = 0.999). Etch endpoints were clearly observed　from the signal transitions, whose period indicate the etch rate uniformity. In　addition, integrating the partial pressure of SiF4 with respect to time is correlated　with the number of Si atoms etched regardless of the composition of the etched materials. Specifically, Si, SiO2 and Si3N4 were examined in this work. Based on　the strong relationship between the measured SiF4 partial pressure and the　etching profiles, real-time monitoring by LAS is useful for the prediction of etch　profiles.

show abstract

Machine learning-based techniques for fault diagnosis in the semiconductor manufacturing process: a comparative study

et al. 2022

View full text Add to dashboard Cite

Incorporating Virtual Metrology Into Failure Prediction

Cited by 10 publications

References 30 publications

A Realizable Overlay Virtual Metrology System in Semiconductor Manufacturing: Proposal, Challenges and Future Perspective

A Realizable Overlay Virtual Metrology System in Semiconductor Manufacturing: Proposal, Challenges and Future Perspective

Chamber in-situ estimation during etching process by SiF₄ monitoring using laser absorption spectroscopy

Machine learning-based techniques for fault diagnosis in the semiconductor manufacturing process: a comparative study

Contact Info

Product

Resources

About

Incorporating Virtual Metrology Into Failure Prediction

Cited by 10 publications

References 30 publications

A Realizable Overlay Virtual Metrology System in Semiconductor Manufacturing: Proposal, Challenges and Future Perspective

A Realizable Overlay Virtual Metrology System in Semiconductor Manufacturing: Proposal, Challenges and Future Perspective

Chamber in-situ estimation during etching process by SiF4 monitoring using laser absorption spectroscopy

Machine learning-based techniques for fault diagnosis in the semiconductor manufacturing process: a comparative study

Contact Info

Product

Resources

About

Chamber in-situ estimation during etching process by SiF₄ monitoring using laser absorption spectroscopy