CMP 패드 컨디셔닝에서 딥러닝을 활용한 컨디셔너 스윙에 따른 패드 마모 프로파일에 관한 연구
Study on the Pad Wear Profile Based on the Conditioner Swing Using Deep Learning for CMP Pad Conditioning
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Chemical mechanical planarization (CMP) is an essential process for ensuring high integration when manufacturing semiconductor devices. CMP mainly requires the use of polyurethane-based polishing pads as an ultraprecise process to achieve mechanical material removal and the required chemical reactions. A diamond disk performs pad conditioning to remove processing residues on the pad surface and maintain sufficient surface roughness during CMP. However, the diamond grits attached to the disk cause uneven wear of the pad, leading to the poor uniformity of material removal during CMP. This study investigates the pad wear rate profile according to the swing motion of the conditioner during swing-arm-type CMP conditioning using deep learning. During conditioning, the motion of the swing arm is independently controlled in eight zones of the same pad radius. The experiment includes six swing-motion conditions to obtain actual data on the pad wear rate profile, and deep learning learns the pad wear rate profile obtained in the experiment. The absolute average error rate between the experimental values and learning results is 0.01%. This finding confirms that the experimental results can be well represented by learning. Pad wear rate profile prediction using the learning results reveals good agreement between the predicted and experimental values.
Abstract
Chemical mechanical planarization (CMP) is an essential process for ensuring high integration when manufacturing semiconductor devices. CMP mainly requires the use of polyurethane-based polishing pads as an ultraprecise process to achieve mechanical material removal and the required chemical reactions. A diamond disk performs pad conditioning to remove processing residues on the pad surface and maintain sufficient surface roughness during CMP. However, the diamond grits attached to the disk cause uneven wear of the pad, leading to the poor uniformity of material removal during CMP. This study investigates the pad wear rate profile according to the swing motion of the conditioner during swing-arm-type CMP conditioning using deep learning. During conditioning, the motion of the swing arm is independently controlled in eight zones of the same pad radius. The experiment includes six swing-motion conditions to obtain actual data on the pad wear rate profile, and deep learning learns the pad wear rate profile obtained in the experiment. The absolute average error rate between the experimental values and learning results is 0.01%. This finding confirms that the experimental results can be well represented by learning. Pad wear rate profile prediction using the learning results reveals good agreement between the predicted and experimental values.
참고문헌 (8)
- Lee, H., "Approaches to Sustainability in Chemical Mechanical Polishing (CMP): A Review", Int. J. Precis. Eng. Manufact. -Green Technology (2022)[DOI]
- Lee, H., "Mechanical aspects of the chemical mechanical polishing process : A review", Int. J. Precis. Eng. Manufact (2016)[DOI]
- Lee, D., "Slurry components in metal chemical mechanical planarization (CMP) process: A Review", Int. J. Precis. Eng. Manufact (2016)[DOI]
- Borucki, L. J., "Theory of pad conditioning for chemical–mechanical polishing", J. Eng. Math. (2004)[DOI]
- Zhou, Y. Y., "Variation of polish pad shape during pad dressing", Mater. Sci. Eng. (1999)[DOI]
- Lee, H., "Investigation of pad wear in CMP with swing-arm conditioning and uniformity of material removal", Precis. Eng (2017)[DOI]
- Park, B., "Design Variables of Chemical-Mechanical Polishing Conditioning System to Improve Pad Wear Uniformity", Tribol. Lubr (2022)[DOI]
- Park, B., "Nonuniformity of Conditioning Density According to CMP Conditioning System Design Variables Using Artificial Neural Network", Tribol. Lubr (2022)[DOI]