Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kang, Minji, Kim, Seongho, Go, Eunseo, Paek, Donghyeon, Lim, Geon, Kim, Muyoung, Kim, Soyeun, Jang, Sung Kyu, Choi, Min Sup, Kang, Woo Seok, Kim, Jaehyun, Kim, Jaekwang, Kim, Hyeong-U
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.03826
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910929983111168
author Kang, Minji
Kim, Seongho
Go, Eunseo
Paek, Donghyeon
Lim, Geon
Kim, Muyoung
Kim, Soyeun
Jang, Sung Kyu
Choi, Min Sup
Kang, Woo Seok
Kim, Jaehyun
Kim, Jaekwang
Kim, Hyeong-U
author_facet Kang, Minji
Kim, Seongho
Go, Eunseo
Paek, Donghyeon
Lim, Geon
Kim, Muyoung
Kim, Soyeun
Jang, Sung Kyu
Choi, Min Sup
Kang, Woo Seok
Kim, Jaehyun
Kim, Jaekwang
Kim, Hyeong-U
contents Precise monitoring of etch depth and the thickness of insulating materials, such as Silicon dioxide and silicon nitride, is critical to ensuring device performance and yield in semiconductor manufacturing. While conventional ex-situ analysis methods are accurate, they are constrained by time delays and contamination risks. To address these limitations, this study proposes a non-contact, in-situ etch depth prediction framework based on machine learning (ML) techniques. Two scenarios are explored. In the first scenario, an artificial neural network (ANN) is trained to predict average etch depth from process parameters, achieving a significantly lower mean squared error (MSE) compared to a linear baseline model. The approach is then extended to incorporate variability from repeated measurements using a Bayesian Neural Network (BNN) to capture both aleatoric and epistemic uncertainty. Coverage analysis confirms the BNN's capability to provide reliable uncertainty estimates. In the second scenario, we demonstrate the feasibility of using RGB data from digital image colorimetry (DIC) as input for etch depth prediction, achieving strong performance even in the absence of explicit process parameters. These results suggest that the integration of DIC and ML offers a viable, cost-effective alternative for real-time, in-situ, and non-invasive monitoring in plasma etching processes, contributing to enhanced process stability, and manufacturing efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2505_03826
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle In-situ and Non-contact Etch Depth Prediction in Plasma Etching via Machine Learning (ANN & BNN) and Digital Image Colorimetry
Kang, Minji
Kim, Seongho
Go, Eunseo
Paek, Donghyeon
Lim, Geon
Kim, Muyoung
Kim, Soyeun
Jang, Sung Kyu
Choi, Min Sup
Kang, Woo Seok
Kim, Jaehyun
Kim, Jaekwang
Kim, Hyeong-U
Computer Vision and Pattern Recognition
Artificial Intelligence
Precise monitoring of etch depth and the thickness of insulating materials, such as Silicon dioxide and silicon nitride, is critical to ensuring device performance and yield in semiconductor manufacturing. While conventional ex-situ analysis methods are accurate, they are constrained by time delays and contamination risks. To address these limitations, this study proposes a non-contact, in-situ etch depth prediction framework based on machine learning (ML) techniques. Two scenarios are explored. In the first scenario, an artificial neural network (ANN) is trained to predict average etch depth from process parameters, achieving a significantly lower mean squared error (MSE) compared to a linear baseline model. The approach is then extended to incorporate variability from repeated measurements using a Bayesian Neural Network (BNN) to capture both aleatoric and epistemic uncertainty. Coverage analysis confirms the BNN's capability to provide reliable uncertainty estimates. In the second scenario, we demonstrate the feasibility of using RGB data from digital image colorimetry (DIC) as input for etch depth prediction, achieving strong performance even in the absence of explicit process parameters. These results suggest that the integration of DIC and ML offers a viable, cost-effective alternative for real-time, in-situ, and non-invasive monitoring in plasma etching processes, contributing to enhanced process stability, and manufacturing efficiency.
title In-situ and Non-contact Etch Depth Prediction in Plasma Etching via Machine Learning (ANN & BNN) and Digital Image Colorimetry
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2505.03826