The Implementation of a Smart Sampling Scheme C2O Utilizing Virtual Metrology in Semiconductor Manufacturing

Tin, Tze Chiang; Tan, Saw Chin; Yong, Hing; Kim, Jimmy Ook Hyun; Teo, Eric Ken Yong; Wong, Joanne Ching Yee; Lee, Ching Kwang; Than, Peter; Tan, Angela Pei San; Phang, Siew Chee

doi:10.1109/access.2021.3103235

Cited by 3 publications

(15 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While two prediction tasks are present in the methodology, this work will only focus on the prediction accuracy of the regression task. The baseline of this work will be based on the results published in [13].…”

Section: Methodsmentioning

confidence: 99%

“…Certain process and wafer qualification criteria are placed to ensure the reliability of such modelling, such as the selection of only fabrication process with at least process capability index, greater than 1.33, and only wafers of mass production products with non-rework conditions. A joint-modelling approach that first perform novelty detection, followed by the regression estimation of the overlay metrology values, the authors presented the experimental results in [13]. The experimental results obtained were significant enough for the authors to pursue the enhancement further in the proposed future works.…”

Section: A Research Backgroundmentioning

confidence: 99%

“…Feature selection is a crucial step to identify features that potentially that can augment the prediction accuracy of the conjecture models. The works [6] and [13] have identified stepwise feature selection has the feature selection method that gave the best predictors to the prediction models. In order to maintain consistency with the methodology of [13], this work employs stepwise feature selection method as feature selection method.…”

Section: Features Selectionmentioning

confidence: 99%

“…The next metric employed is the mean absolute scaled error (MASE). MASE was used by both [6] and [13] as one of the metrics to evaluate the performance of the regression models because MASE allows prediction performance of a VM model to be measured based on the error tolerance of the targeted metrology. The error tolerance of a metrology quality is the permitted metrology error boundary that would not result in significant defects on a wafer die.…”

Section: Performance Metricsmentioning

confidence: 99%

“…The data use for this work were acquired from a real fab. This work applied the same setting as in [13] that targets a list of photolithography processes of stepper type photolithography equipment with > 1.33. Data for 2000 wafers over a period of 7 months, with January 2019 being the start month.…”

Section: A Experimental Designmentioning

confidence: 99%

See 4 more Smart Citations

Virtual Metrology in Semiconductor Fabrication Foundry Using Deep Learning Neural Networks

2022

Self Cite

View full text Add to dashboard Cite

Physical metrology inspections are crucial in semiconductor fabrication foundry to ensure wafers are fabricated within the production specification limits and prevent faulty wafers from being shipped and installed in customers' devices. However, it is not possible to examine every wafer as such inspection would incur impractical cost on manpower, finances, and production cycle time (CT) of fabrication foundries (fabs). Virtual metrology (VM) presents an alternate approach to perform metrology inspection without incurring high costs by using machine learning (ML) models. By leveraging historical equipment and process data, ML models can be calibrated to estimate the targeted metrology variables to estimate the quality of wafers, thereby performing virtual inspection on wafers. Recently, VM researchers begin introducing deep learning (DL) into VM research works to examine its capability. Specifically, the VM researchers experimented on the convolutional neural network (CNN). The targeted metrologies are metrologies of plasma-based processes in both etching and chemical vapor deposition. Initial success has been reported by the VM researchers. While various CNN-based VM models have been proposed plasma-based fabrication processes, it has yet to be experimented in photolithography process. Motivated by the initial successes of CNN in plasma-based processes, this work is an initiative to experiment CNN's performance in predicting the overlay errors of photolithography process. Using data from a real fab, this work first establishes a baseline using the methodology of a prior work. Then, the prediction results of the proposed CNN model are compared with the baseline. The results showed that CNN is able to further reduce the prediction errors.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: A Research Backgroundmentioning

confidence: 99%