自监督注意力方法 GREP 用于 CMP 材料去除率预测的虚拟量测
Self-Supervised Attention-Based Virtual Metrology for CMP MRR Prediction
AI 导读
研究者提出自监督注意力框架 GREP（Global Regression Pretraining），通过全局代理目标回归从无标签传感器信号学习时序表征，再经监督微调预测 CMP（化学机械平坦化）材料去除率（MRR）。
正文 · 原文
Abstract:Chemical mechanical planarization (CMP) is a critical semiconductor manufacturing process where material removal rate (MRR) is a key metric for process monitoring and advanced process control (APC). Virtual metrology enables MRR estimation from process time series signals, supporting run-to-run(R2R) control and process optimization while reducing reliance on physical metrology. Existing approaches typically rely on simplified linear assumptions or require handcrafted feature engineering. In this paper, we propose Global Regression Pretraining(GREP), a self-supervised, attention-based framework for CMP MRR prediction. GREP learns temporal representations from unlabeled sensor signals through global proxy-target regression, followed by supervised fine-tuning for MRR estimation. The framework is evaluated against a feature-engineered supervised baseline under three conditions: limited labeled data, sensor noise, and temporal process drift. Experiments on the PHM 2016 CMP dataset demonstrate competitive performance under limited labeled-data conditions, with improvements in selected cases and performance largely comparable to the baseline across different labeled-data fractions. Both models exhibit relatively small changes in prediction error with increasing noise, while GREP achieves a 17.0% RMSE reduction in the final temporal interval.
| Comments: | Submitted to the IEEE International Symposium on Semiconductor Manufacturing (ISSM 2026) |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.16172 [cs.LG] |
| (or arXiv:2611.16172v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.16172 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jonathan Adam Rico [view email]
[v1]
Thu, 12 Nov 2026 02:01:24 UTC (879 KB)
来源：arXiv cs.AI · arxiv.org