Real time endpoint detection in plasma etching using Real-Time Decision Making Algorithm

Noh, Ho-Taek; Kim, Dong-Il; Han, Seung-Soo

doi:10.1109/cstic.2015.7153380

Cited by 7 publications

(6 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although there may be limitations in measuring the exact electron temperature and electron density of plasma using OES, the line ratio method was used to extract variables related to electron temperature and electron density. By leveraging the chemical species information obtained through OES with machine learning and deep learning technologies, hidden patterns and correlations can be uncovered to enable efficient process diagnosis [6][7][8]. Moreover, a thorough understanding of OES and plasma principles makes it possible to extract valuable plasma information (PI) parameters, such as electron temperature, electron density, and chemical species density [9].…”

Section: Introductionmentioning

confidence: 99%

Explainable artificial intelligence-based evidential inferencing on process faults in plasma etching

Choi,

An,

Lee

et al. 2024

J. Phys. D: Appl. Phys.

View full text Add to dashboard Cite

The fault detection and classification (FDC) modeling proposed in this study is a research approach that is intended to improve the performance of plasma process models by leveraging optical emission spectroscopy (OES) data containing plasma information (PI) and enhancing model interpretability using explainable artificial intelligence (XAI) algorithms. Status variable identification data that included normal and abnormal states of bias power, pressure, SF6 gas flow, and O2 gas flow were collected during a silicon etching process with SF6, O2 gas plasma. Additional variables were derived from the OES data and included additional PI, such as O and F radicals, which were computed using actinometry, and electron temperature and electron density computed using the line ratio method. By building a high-performance FDC model and interpreting its results using XAI algorithms, we propose solutions to the limitations of the FDC model in semiconductor plasma processes.

show abstract

Section: Introductionmentioning

confidence: 99%

Explainable artificial intelligence-based evidential inferencing on process faults in plasma etching

Choi,

An,

Lee

et al. 2024

J. Phys. D: Appl. Phys.

View full text Add to dashboard Cite

show abstract

“…[15][16][17][18] Researchers have attempted to improve sensitivity using whole spectra by adopting various machinelearning techniques that utilize the signals from thousands of optical channels in a short time. [19][20][21][22][23][24][25][26][27][28][29][30][31][32] Dimension reduction methods, such as principal component analysis (PCA) [20][21][22] and non-negative matrix factorization (NMF), [23] have been developed to reduce the OES dataset dimensionality and extract patterns from the endpoint. Classification methods, such as the support vector machine (SVM), [24][25][26][27] hidden Markov model (HMM), [28,29] and convolutional neural network (CNN), [30] have been developed for EPD to classify the state of etching processes before and after the endpoint.…”

Section: Introductionmentioning

confidence: 99%

“…[19][20][21][22][23][24][25][26][27][28][29][30][31][32] Dimension reduction methods, such as principal component analysis (PCA) [20][21][22] and non-negative matrix factorization (NMF), [23] have been developed to reduce the OES dataset dimensionality and extract patterns from the endpoint. Classification methods, such as the support vector machine (SVM), [24][25][26][27] hidden Markov model (HMM), [28,29] and convolutional neural network (CNN), [30] have been developed for EPD to classify the state of etching processes before and after the endpoint. Both dimension reduction and classification methods require training for real-time EPD, and the trained models are limited to specific target materials and process conditions.…”

Section: Introductionmentioning

confidence: 99%

Spectral clustering algorithm for real‐time endpoint detection of silicon nitride plasma etching

Lee

Choi

Kim

et al. 2023

Plasma Processes & Polymers

View full text Add to dashboard Cite

The spectral clustering algorithm (SCA) is developed for endpoint detection (EPD) of Si 3 N 4 plasma etching using optical emission spectroscopy (OES). OES signals are collected in real-time and filtered using discrete wavelet transform (DWT).The SCA using 3648 full-spectrum wavelengths with DWT filtering improves signal-to-noise ratio (SNR) by 2.78 times compared to single-wavelength related to N 2 molecule in 1.0% relative area etching. The wavelengths

show abstract

“…Such various length signals could be expected for the data coming out of different channels recorded by dry etch tool, which naturally happens, for example, due to some lot-to-lot thickness variation. The outcome is typically controlled by introducing endpoint (EndPT) algorithms, 9,10) which implies slight variations in the process step duration from run to run.…”

Section: Introductionmentioning

confidence: 99%

Assessment of STI dry etch process variability by means of dynamic time warping technique

Milenin¹,

Chan²,

Lazzarino³

2023

Jpn. J. Appl. Phys.

View full text Add to dashboard Cite

Numerical data of two in-situ optical acquisition systems were used in machine learning algorithm to evaluate an shallow trench isolation dry etch process in a dataset of more than 200 etched wafers processed during a year. Though overall recipe performance was according to specifications, the observed parameter fluctuations were characterized to check for correlation patterns in processing data by means of machine learning. Thus, dynamic time wrapping was used to analyze time series datasets to get characteristics of minimum distance’s path between signals coming of each individual wafer. Such metrics of distances could help clustering groups of wafers that appear to be in proximity. Out of eight analyzed channels, we observed the largest distance variability was in the Si main etch for spectral reflectometer dataset, which we compared to optical emission spectroscopy channels. Based on correlation assessment of distances to the etch depth uniformity data, we showed that the selected approach is a good means to analyze time series datasets of e.g. dry etch processes for monitoring process stability.

show abstract

Real time endpoint detection in plasma etching using Real-Time Decision Making Algorithm

Cited by 7 publications

References 1 publication

Explainable artificial intelligence-based evidential inferencing on process faults in plasma etching

Explainable artificial intelligence-based evidential inferencing on process faults in plasma etching

Spectral clustering algorithm for real‐time endpoint detection of silicon nitride plasma etching

Assessment of STI dry etch process variability by means of dynamic time warping technique

Contact Info

Product

Resources

About