Spatial batch optimal design based on self-learning gaussian process models for LPCVD processes

Pei Sun; Lei Xie; Junghui Chen

doi:10.1016/j.cjche.2015.11.013

Your Location：

Home >

Browse articles >

Spatial batch optimal design based on self-learning gaussian process models for LPCVD processes

第25届中国过程控制会议专栏 | Updated：2026-01-06

- Spatial batch optimal design based on self-learning gaussian process models for LPCVD processes
- Chinese Journal of Chemical Engineering Vol. 23, Issue 12, Pages: 1958-1964(2015)
- Affiliations：
  
  State Laboratory of Industrial Control Technology, Institute of Cyber-Systems and Control, Zhejiang University,Hangzhou,China,310027
- Author bio：
- Funds：
- DOI：10.1016/j.cjche.2015.11.013
  CLC：
- Published：2015
- Accepted：
Scan QR Code
Pei Sun, Lei Xie, Junghui Chen. Spatial batch optimal design based on self-learning gaussian process models for LPCVD processes[J]. Chin.J.Chem.Eng., 2015, 23(12): 1958-1964.
DOI：

Pei Sun, Lei Xie, Junghui Chen. Spatial batch optimal design based on self-learning gaussian process models for LPCVD processes[J]. Chin.J.Chem.Eng., 2015, 23(12): 1958-1964. DOI： 10.1016/j.cjche.2015.11.013.

摘要

Abstract

Low pressure chemical vapor deposition (LPCVD) is one of themost important processes during semiconductor manufacturing. However

the spatial distribution of internal temperature and extremely few samples makes it hard to build a good-quality model of this batch process. Besides

due to the properties of this process

the reliability of the model must be taken into consideration when optimizing the MVs. In this work

an optimal design strategy based on the self-learning Gaussian processmodel (GPM)is proposed to control this kind of spatial batch process. The GPMis utilized as the internalmodel to predict the thicknesses of thin films on all spatial-distributed wafers using the limited data. Unlike the conventional model based design

the uncertainties of predictions provided by GPM are taken into consideration to guide the optimal design of manipulated variables so that the designing can be more prudent. Besides

the GPM is also actively enhanced using as little data as possible based on the predictive uncertainties. The effectiveness of the proposed strategy is successfully demonstrated in an LPCVD process.

关键词

Keywords

references

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

Dual-metal sulfide/carbon yolk-shell composites for advanced lithium-ion battery anodes

Bayesian optimization of operational and geometric parameters of microchannels for targeted droplet generation

Combined micromixing and coalescence separation for improved oil desulfurization

Ensemble learning-driven multi-objective optimization of the co-pyrolysis process of biomass and coal for high economic and environmental performance

High-throughput and intelligent design of potential GRK2 inhibitor candidates using deep learning and mathematical programming methods

Related Author

He Zhen

Zhao Tongfa

Wei Yuqian

Hou Linpei

Wang Yuxin

Li Bo

Zifeng Li

Xiaoping Guan

Related Institution

Department of Chemical and Materials Engineering, University of Auckland, Private Bag 92019, Auckland 1142, New Zealand

School of Materials Science and Engineering, Jiangsu University of Science and Technology

School of Chemical Engineering, University of Chinese Academy of Sciences

State Key Laboratory of Mesoscience and Engineering, Institute of Process Engineering, Chinese Academy of Sciences

National Engineering Laboratory for Industrial Wastewater Treatment, East China University of Science and Technology

⁰