Developing a selection scheme for dual virtual-metrology outputs

Wei Ming Wu, Fan Tien Cheng, Deng Lin Zeng, Tung Ho Lin, Jyun Fang Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

This paper proposes a selection scheme (S-scheme) between neural-network (NN) and multiple-regression (MR) outputs of a virtual metrology system (VMS). Both NN and MR are applicable algorithms for implementing VM conjecture models. But a MR algorithm may achieve better accuracy only with a stable process, whereas a NN algorithm may has superior accuracy when equipment property drift or shift occurs. To take advantage of the merits of both MR and NN algorithms, the S-scheme is proposed to enhance virtual-metrology (VM) conjecture accuracy. Two illustrative examples in the CVD process of fifth generation TFT-LCD are used to test and compare the conjecture accuracy among solo NN, solo MR, and S-scheme. One-hidden-layered back-propagation neural network (BPNN-I) is adopted for establishing the NN conjecture model. Test results show that the conjecture accuracy of S-scheme can achieve superior accuracy than solo NN and solo MR algorithms.

Original languageEnglish
Title of host publication4th IEEE Conference on Automation Science and Engineering, CASE 2008
Pages230-235
Number of pages6
DOIs
Publication statusPublished - 2008 Nov 3
Event4th IEEE Conference on Automation Science and Engineering, CASE 2008 - Washington, DC, United States
Duration: 2008 Aug 232008 Aug 26

Publication series

Name4th IEEE Conference on Automation Science and Engineering, CASE 2008

Other

Other4th IEEE Conference on Automation Science and Engineering, CASE 2008
Country/TerritoryUnited States
CityWashington, DC
Period08-08-2308-08-26

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Developing a selection scheme for dual virtual-metrology outputs'. Together they form a unique fingerprint.

Cite this