Semi-Supervised Deep Kernel Active Learning for Material Removal Rate Prediction in Chemical Mechanical Planarization

• Main Authors: Huang, J. (Author), Lv, C. (Author), Wang, H. (Author), Zhang, M. (Author), Zhang, T. (Author)
• Format: Article
• Language: English
• Published: MDPI 2023
• Subjects: active learning; Active Learning; algorithm; article; Chemical-mechanical planarization process; Clustering algorithms; controlled study; deep kernel learning; Deep kernel learning; Deep learning; E-learning; feature extraction; Gaussian distribution; Gaussian noise (electronic); Information use; Kernel learning; learning; Learning algorithms; Learning systems; Material removal rate; Mean square error; mean squared error; phase match; Phase match; Phase matching; phase partition; Phase partition; physics; prediction; Principal component analysis; Regression analysis; regression model; Semi-supervised; semi-supervised regression; Semi-supervised regression; virtual metrology; Virtual metrology
• Online Access: View Fulltext in Publisher; View in Scopus
• ISBN: 14248220 (ISSN)
• DOI: 10.3390/s23094392

The material removal rate (MRR) is an important variable but difficult to measure in the chemical–mechanical planarization (CMP) process. Most data-based virtual metrology (VM) methods ignore the large number of unlabeled samples, resulting in a waste of information. In this paper, the semi-supervised deep kernel active learning (SSDKAL) model is proposed. Clustering-based phase partition and phase-matching algorithms are used for the initial feature extraction, and a deep network is used to replace the kernel of Gaussian process regression so as to extract hidden deep features. Semi-supervised regression and active learning sample selection strategies are applied to make full use of information on the unlabeled samples. The experimental results of the CMP process dataset validate the effectiveness of the proposed method. Compared with supervised regression and co-training-based semi-supervised regression algorithms, the proposed model has a lower mean square error with different labeled sample proportions. Compared with other frameworks proposed in the literature, such as physics-based VM models, Gaussian-process-based regression models, and stacking models, the proposed method achieves better prediction results without using all the labeled samples. © 2023 by the authors.