A Lightweight Chip-Scale Chemical Mechanical Polishing Model Based on Polynomial Network

IF 2.3 3区工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

IEEE Transactions on Semiconductor Manufacturing Pub Date : 2024-02-26 DOI:10.1109/TSM.2024.3370175

Ruian Ji;Rong Chen;Lan Chen

{"title":"A Lightweight Chip-Scale Chemical Mechanical Polishing Model Based on Polynomial Network","authors":"Ruian Ji;Rong Chen;Lan Chen","doi":"10.1109/TSM.2024.3370175","DOIUrl":null,"url":null,"abstract":"Chemical mechanical polishing/planarization (CMP) combines physical grinding and chemical reactions to planarize the wafer surface. The complex mechanism of CMP brings great challenges to the mechanism-based modeling process. The data-driven CMP modeling process is limited by insufficient datasets. At the same time, these two types of models generally have high computational complexity. In this paper, we introduce the group method of data handling (GMDH)-type polynomial network to build the CMP model to address the above challenges. We designed and manufactured the test chip using a 28nm process. The measurement data from the test chip shows that compared with the mechanism-based CMP model, the trained CMP model based on GMDH-type polynomial network has higher accuracy and lower computational complexity, with the average simulation speed being 115x faster. Experiments based on silicon data show that this modeling method has a small demand for data, and 20 randomly selected sets of data can meet the needs for modeling the current CMP process.","PeriodicalId":451,"journal":{"name":"IEEE Transactions on Semiconductor Manufacturing","volume":"37 2","pages":"139-145"},"PeriodicalIF":2.3000,"publicationDate":"2024-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Semiconductor Manufacturing","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10445485/","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 0

Abstract

Chemical mechanical polishing/planarization (CMP) combines physical grinding and chemical reactions to planarize the wafer surface. The complex mechanism of CMP brings great challenges to the mechanism-based modeling process. The data-driven CMP modeling process is limited by insufficient datasets. At the same time, these two types of models generally have high computational complexity. In this paper, we introduce the group method of data handling (GMDH)-type polynomial network to build the CMP model to address the above challenges. We designed and manufactured the test chip using a 28nm process. The measurement data from the test chip shows that compared with the mechanism-based CMP model, the trained CMP model based on GMDH-type polynomial network has higher accuracy and lower computational complexity, with the average simulation speed being 115x faster. Experiments based on silicon data show that this modeling method has a small demand for data, and 20 randomly selected sets of data can meet the needs for modeling the current CMP process.

查看原文本刊更多论文

基于多项式网络的轻量级芯片级化学机械抛光模型

化学机械抛光/平面化（CMP）结合了物理研磨和化学反应，使晶片表面平面化。CMP 的复杂机理给基于机理的建模过程带来了巨大挑战。数据驱动的 CMP 建模过程受到数据集不足的限制。同时，这两类模型的计算复杂度普遍较高。本文引入数据处理组法（GMDH）型多项式网络来构建 CMP 模型，以解决上述难题。我们采用 28 纳米工艺设计并制造了测试芯片。测试芯片的测量数据表明，与基于机制的 CMP 模型相比，基于 GMDH 型多项式网络训练的 CMP 模型具有更高的精度和更低的计算复杂度，平均仿真速度提高了 115 倍。基于硅片数据的实验表明，这种建模方法对数据的需求较小，随机选取 20 组数据即可满足当前 CMP 过程建模的需要。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Transactions on Semiconductor Manufacturing 工程技术-工程：电子与电气

CiteScore

5.20

自引率

11.10%

发文量

101

审稿时长

3.3 months

期刊介绍： The IEEE Transactions on Semiconductor Manufacturing addresses the challenging problems of manufacturing complex microelectronic components, especially very large scale integrated circuits (VLSI). Manufacturing these products requires precision micropatterning, precise control of materials properties, ultraclean work environments, and complex interactions of chemical, physical, electrical and mechanical processes.