• Journal of the Semiconductor & Display Technology
• /
• v.18 no.2
• /
• pp.48-52
• /
• 2019

Virtual metrology, which is one of APC techniques, is a method to predict characteristics of manufactured films using machine learning with saving time and resources. As the photoresist is no longer a mask material for use in high aspect ratios as the CD is reduced, hard mask is introduced to solve such problems. Among many types of hard mask materials, amorphous carbon layer(ACL) is widely investigated due to its advantages of high etch selectivity than conventional photoresist, high optical transmittance, easy deposition process, and removability by oxygen plasma. In this study, VM using different machine learning algorithms is applied to predict the thickness of ACL and trained models are evaluated which model shows best prediction performance. ACL specimens are deposited by plasma enhanced chemical vapor deposition(PECVD) with four different process parameters(Pressure, RF power, $C_3H_6$ gas flow, $N_2$ gas flow). Gradient boosting regression(GBR) algorithm, random forest regression(RFR) algorithm, and neural network(NN) are selected for modeling. The model using gradient boosting algorithm shows most proper performance with higher R-squared value. A model for predicting the thickness of the ACL film within the abovementioned conditions has been successfully constructed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.477-480
• /
• 2022

반도체 성능 향상으로 신호를 전달하는 회로의 단위가 마이크로 미터에서 나노미터로 미세화되어 선폭(linewidth)이 점점 좁아지고 있다. 이러한 변화는 검출해야 할 불량의 크기가 작아지고, 정상 공정상태와 비정상 공정상태의 차이도 상대적으로 감소되어, 공정오차 및 공정조건의 허용범위가 축소되었음을 의미한다. 따라서 검출해야 할 이상징후 탐지가 더욱 어렵게 되어, 높은 정밀도와 해상도를 갖는 검사공정이 요구되고 있다. 이러한 이유로, 미세 공정변화를 파악할 수 있는 신규 검사 및 계측 공정이 추가되어 TAT(Turn-around Time)가 증가하게 되었고, 웨이퍼가 가공되어 완제품까지 도달하는데 필요한 공정시간이 증가하여 제조원가 상승의 원인으로 작용한다. 본 논문에서는 웨이퍼의 검계측 데이터가 아닌, 제조공정 과정에서 발생하는 다양한 센서 및 장비 데이터를 기반으로 웨이퍼 제조 결과가 양품인지 그렇지 않으면 불량인지 구별할 수 있는 가상계측 모델을 제안한다. 기계학습의 여러 알고리즘 중에서 다양한 장점을 갖는 XGBoost 알고리즘을 이용하여 예측모델을 구축하였고, 데이터 전처리(data-preprocessing), 주요변수 추출(feature selection), 모델 구축(model design), 모델 평가(model evaluation)의 순서로 연구를 수행하였다. 결과적으로 약 94% 이상의 정확성을 갖는 모형을 구축하는데 성공하였으나 더욱 높은 정확성을 확보하기 위해서는 반도체 공정과 관련된 Domain Knowledge 를 반영한 모델구축과 같은 추가적인 연구가 필요하다.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.4
• /
• pp.7-12
• /
• 2023

The edge ring placed on the outside of the electrostatic chuck (ESC) is a key component for protecting the ESC and controlling the etching uniformity of the edge of the wafer. Therefore, it is very important to understand the etching phenomenon of edge rings for edge ring management and equipment homeostasis. In this study, a specimen with SiO₂ hard mask and underlying Si mold was installed on the edge ring surface and the etching results were measured by varying the edge ring 2MHz RF power. By developing PI-VM model with high prediction accuracy and analyzing the roles of key parameters in the model, we were able to evaluate the effect of plasma and sheath characteristics around the edge ring on edge ring erosion. This analysis method provided information necessary for edge ring maintenance and operation.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.9
• /
• pp.875-880
• /
• 2015

Traditional semiconductor process control has been performed through statistical process control techniques in a constant process-recipe conditions. However, the complexity of the interior of the etching apparatus plasma physics, quantitative modeling of process conditions due to the many difficult features constraints apply simple SISO control scheme. The introduction of the Advanced Process Control (APC) as a way to overcome the limits has been using the APC process control methodology run-to-run, wafer-to-wafer, or the yield of the semiconductor manufacturing process to the real-time process control, performance, it is possible to improve production. In addition, it is possible to establish a hierarchical structure of the process control made by the process control unit and associated algorithms and etching apparatus, the process unit, the overall process. In this study, the research focused on the methodology and monitoring improvements in performance needed to consider the process management of future developments in the semiconductor manufacturing process in accordance with the age of the APC analysis in real applications of the semiconductor manufacturing process and process fault diagnosis and control techniques in progress.

• Journal of the Ergonomics Society of Korea
• /
• v.32 no.6
• /
• pp.481-487
• /
• 2013

Objective: The present study aims to evaluate the visual reactions of users when they are playing games of different flow levels, and to explore the visual variables that can sensitively reflect the different flow levels. Background: The flow is defined as a psychological state where interface users feel their actions in a virtual setting identical to those in real environment. To measure the flow states of users, the questionnaire-based FSS(Flow State Scale) has mostly been used. However, this method is a qualitative test that has limits in terms of the accuracy of users' flow experiences. Therefore, more accurate methods to measure users' flow experiences are required. Method: Ten subjects participated in the experiment, where the independent variables were three games with different flow levels(puzzle games, dot drawing and coloring) and the time frame(the first and last 10 seconds in game playing), whereas the dependent variables included the pupil size and the frequency and duration of eye blinking. This study was a within-subject design. Each participant performed three types of games with different flow levels 3 times for each for 10 minutes, and their visual reactions to each game were measured. Results: The higher the flow cause the bigger pupil size(p<0.01) and the lower eye blinking frequency(p<0.1), indicating that different types of games lead to different flow levels. The pupil size during the last 10 seconds when the flow level was higher was bigger by 2.1% compared with that during the first 10 seconds in game playing(p<0.1), and the eye blinking frequency decreased by 12%(p<0.01). Conclusion: It was found out that the pupil size and the frequency and duration of eye blinking were psychophysiological indices for evaluating users' flow experiences, which could quantify the flow states users go through. The psychophysiological variables capable of measuring diverse aspects of the flow need diversifying to be applicable to precise measurement of the flow. Application: These studies are warranted for both quantitative analysis of flow levels and qualitative improvement of cyber leisure in line with development of healthy games.