인공신경망을 활용한 CMP 컨디셔닝 시스템 설계 변수에 따른 컨디셔닝 밀도의 불균일도 분석
Nonuniformity of Conditioning Density According to CMP Conditioning System Design Variables Using Artificial Neural Network
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Chemical mechanical planarization (CMP) is a technology that planarizes the surfaces of semiconductor devices using chemical reaction and mechanical material removal, and it is an essential process in manufacturing highly integrated semiconductors. In the CMP process, a conditioning process using a diamond conditioner is applied to remove by-products generated during processing and ensure the surface roughness of the CMP pad. In previous studies, prediction of pad wear by CMP conditioning has depended on numerical analysis studies based on mathematical simulation. In this study, using an artificial neural network, the ratio of conditioner coverage to the distance between centers in the conditioning system is input, and the average conditioning density, standard deviation, nonuniformity (NU), and conditioning density distribution are trained as targets. The result of training seems to predict the target data well, although the average conditioning density, standard deviation, and NU in the contact area of wafer and pad and all areas of the pad have some errors. In addition, in the case of NU, the prediction calculated from the training results of the average conditioning density and standard deviation can reduce the error of training compared with the results predicted through training. The results of training on the conditioning density profile generally follow the target data well, confirming that the shape of the conditioning density profile can be predicted.
Abstract
Chemical mechanical planarization (CMP) is a technology that planarizes the surfaces of semiconductor devices using chemical reaction and mechanical material removal, and it is an essential process in manufacturing highly integrated semiconductors. In the CMP process, a conditioning process using a diamond conditioner is applied to remove by-products generated during processing and ensure the surface roughness of the CMP pad. In previous studies, prediction of pad wear by CMP conditioning has depended on numerical analysis studies based on mathematical simulation. In this study, using an artificial neural network, the ratio of conditioner coverage to the distance between centers in the conditioning system is input, and the average conditioning density, standard deviation, nonuniformity (NU), and conditioning density distribution are trained as targets. The result of training seems to predict the target data well, although the average conditioning density, standard deviation, and NU in the contact area of wafer and pad and all areas of the pad have some errors. In addition, in the case of NU, the prediction calculated from the training results of the average conditioning density and standard deviation can reduce the error of training compared with the results predicted through training. The results of training on the conditioning density profile generally follow the target data well, confirming that the shape of the conditioning density profile can be predicted.
참고문헌 (13)
- Hyunseop Lee, "Approaches to Sustainability in Chemical Mechanical Polishing (CMP): A review", International Journal of Precision Engineering and Manufacturing-Green Technology, 9(1), pp.349~367 (2022), 한국정밀공학회[DOI]
- Zhao, D, "Chemical Mechanical Polishing: Theory and experiment", Friction, 1(Issue4), pp.306~326 (2013)[DOI]
- 이현섭, "Mechanical Aspects of the Chemical Mechanical Polishing Process: A Review", International Journal of Precision Engineering and Manufacturing, 17(4), pp.525~536 (2016), 한국정밀공학회
- Son, J, "Contact-Area-Changeable CMP Conditioning for Enhancing Pad Lifetime", Appl. Sci, 11, pp.3521~2021 (2021)[DOI]
- Li, Z. C, "Diamond disc pad conditioning in chemical mechanical planarization(CMP) : A surface element method to predict pad surface shape", Precis. Eng, 36, pp.356~363 (2012)[DOI]
- Zhou, Y. -Y, "Variation of polish pad shape during pad dressing", Mater. Sci. Eng. B, 6(Issue2), pp.91~98 (1999)[DOI]
- Chang, O, "Mathematical modeling of CMP conditioning process", Micronelectron. Eng, 84(Issue4), pp.577~583 (2007)[DOI]
- Lee, S, "Kinematical modeling of pad profile variation during conditioning in chemical mechanical polishing", Jpn. J.. Appl. Phys, 48(12R), pp.126502~ (2009)[DOI]
- Lee, H, "Investigation of pad wear in CMP with swing-arm conditioning and uniformity of material removal", Precis. Eng, 49, pp.85~91 (2017)[DOI]
- 박병훈, "패드 마모 균일성 향상을 위한 CMP 컨디셔닝 시스템설계 변수 연구", 한국트라이볼로지학회지, 38(1), pp.1~7 (2022), 한국트라이볼로지학회[DOI]
- Marquardt, D. W, "An Algorithm for Least-Squares Estimation of Nonlinear Parameters", J. Soc. Indust., Appl. Math, 11(2), pp.431~441 (1963)[DOI]
- Lv, C, "Levenberg-Marquardt Backpropagation Training of Multilayer Neural Networks for State Estimation of A Safety Critical Cyber-Physical System", IEEE Trans. Industr. Infrm, 14(Issue8), pp.3436~3446 (2017)[DOI]
- Li, K, "The Application of BP Neural Network in Students’ Evaluation", Topics in Chem. Mater. Eng, 1(1), pp.463~465 (2018)[DOI]