심층 신경망을 이용한 패드 표면 거칠기 기반 CMP 재료 제거율 예측 = Prediction of CMP Material Removal Rate based on Pad Surface Roughness Using Deep Neural Network

다국어 초록 (Multilingual Abstract)

As the digitization of the manufacturing process is accelerating, various data-driven approaches using machine learning are being developed in chemical mechanical polishing (CMP). For a more accurate prediction in contact-based CMP, it is necessary to consider the real-time changing pad surface roughness during polishing. Changes in pad surface roughness result in non-uniformity of the real contact pressure and friction applied to the wafer, which are the main causes of material removal rate variation. In this paper, we predicted the material removal rate based on pressure and surface roughness using a deep neural network (DNN). Reduced peak height (Rpk) and real contact area (RCA) were chosen as the key parameters indicative of the surface roughness of the pad, and 220 data were collected along with the process pressure. The collected data were normalized and separated in a 3 : 1 : 1 ratio to improve the predictive performance of the DNN model. The hyperparameters of the DNN model were optimized through random search techniques and 5 cross-validations. The optimized DNN model predicted the material removal rate with high accuracy in ex-situ CMP. This study is expected to be utilized in data-driven machine learning decision making for cyber-physical CMP systems in the future.

참고문헌 (Reference)

1 최재영 ; 정해도 ; 박기현 ; 김형재 ; 서헌덕, "패드 그루브의 치수가 CMP 연마특성에 미치는 영향" 대한기계학회 29 (29): 432-438, 2005

2 안정언 ; 정재윤, "머신러닝을 이용한 반도체 웨이퍼 평탄화 공정품질 예측 및 해석 모형 개발" 사)한국빅데이터학회 4 (4): 61-71, 2019

3 Kim, S., "The effect of pad-asperity curvature on material removal rate in chemical-mechanical polishing" 14 : 42-47, 2014

4 Lee, H., "Semi-empirical material removal rate distribution model for SiO2 chemical mechanical polishing(CMP)processes" 37 (37): 483-490, 2013

5 Lee, K. B., "Recurrent feature-incorporated convolutional neural network for virtual metrology of the chemical mechanical planarization process" 31 (31): 73-86, 2020

6 Jeong, H., "Prediction of real contact area from microtopography on CMP pad" 6 (6): 113-120, 2012

7 Li, Z., "Prediction of material removal rate for chemical mechanical planarization using decision treebased ensemble learning" 141 (141): 031003-, 2019

8 Park, B., "Pad roughness variation and its effect on material removal profile in ceria-based CMP slurry" 203 (203): 287-292, 2008

9 Jang, J. -H., "Optimization of groove sizing in CMP using CFD" 1522-1527, 2004

10 Park, K., "Investigation of pad surface topography distribution for material removal uniformity in CMP process" 155 (155): H595-, 2008

11 Prasad, Y. N., "Generation of pad debris during oxide CMP process and its role in scratch formation" 158 (158): H394-, 2011

12 Kim, H., "Friction and thermal phenomena in chemical mechanical polishing" 130 : 334-338, 2002

13 Park, K., "Effects of pad properties on material removal in chemical mechanical polishing" 187 : 73-76, 2007

14 Zhang, L., "Dependence of pad performance on its texture in polishing mono-crystalline silicon wafers" 52 (52): 657-662, 2010

15 Jeon, B. J., "Chemical mechanical planarization removal rate estimation with ensemble model" 1398-1402, 2016

16 김형재 ; 권대희 ; 정해도 ; 이응숙 ; 신영재, "CMP 공정에서 발생하는 연마온도 분포에 관한 연구" 한국정밀공학회 20 (20): 223-, 2003

17 Yu, H. -M., "CMP process optimization engineering by machine learning" 34 (34): 280-285, 2021

18 Hyunseop Lee ; Hyoungjae Kim ; Haedo Jeong, "Approaches to Sustainability in Chemical Mechanical Polishing (CMP): A review" 한국정밀공학회 9 (9): 349-367, 2022

19 Wang, P., "A deep learning-based approach to material removal rate prediction in polishing" 66 (66): 429-432, 2017

20 이창석 ; 이호준 ; 정문기 ; 정해도, "A Study on the Correlation between Pad Property and Material Removal Rate in CMP" 한국정밀공학회 12 (12): 917-920, 2011