Correlated Bayesian Co-Training for Virtual Metrology

Page view(s)
19
Checked on Oct 15, 2024
Correlated Bayesian Co-Training for Virtual Metrology
Title:
Correlated Bayesian Co-Training for Virtual Metrology
Journal Title:
IEEE Transactions on Semiconductor Manufacturing
Keywords:
Publication Date:
03 November 2022
Citation:
Nguyen, C., Li, X., Blanton, S., & Li, X. (2023). Correlated Bayesian Co-Training for Virtual Metrology. IEEE Transactions on Semiconductor Manufacturing, 36(1), 28–36. https://doi.org/10.1109/tsm.2022.3217350
Abstract:
A rising challenge in manufacturing data analysis is training robust regression models using limited labeled data. In this work, we investigate a semi-supervised regression scenario, where a manufacturing process operates on multiple mutually correlated states. We exploit this inter-state correlation to improve regression accuracy by developing a novel co-training method, namely Correlated Bayesian Co-training (CBCT). CBCT adopts a block Sparse Bayesian Learning framework to enhance multiple individual regression models which share the same support. Additionally, CBCT casts a unified prior distribution on both the coefficient magnitude and the inter-state correlation. The model parameters are estimated using maximum-a-posteriori estimation (MAP), while hyper-parameters are estimated using the expectation-maximization (EM) algorithm. Experimental results from two industrial examples shows that CBCT successfully leverages inter-state correlation to reduce the modeling error by up to 79.40%, compared to other conventional approaches. This suggests that CBCT is of great value to multi-state manufacturing applications.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - Project U15-E-011SV
Grant Reference no. : U15-E-011SV
Description:
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
1558-2345
0894-6507
Files uploaded: