Discrete wavelet transform and radial basis neural network for semiconductor wet-etching fabrication flow-rate analysis

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This paper presents research that uses discrete wavelet transform (DWT) and radial basis neural network for automatic classification. The flow rate of a wet-etching fabrication facility for a single wafer can be analyzed automatically. The electrical signal of a flow meter is collected and decomposed by means of DWT. The signal power of the coefficients processed by the DWT is fed into the radial basis neural network for initial classification. A digital filter for post signal processing and a user-defined threshold value are applied; calculations for successful identification rate take place at the final step. The research results are applicable to automatic identification functions for in situ fabrication monitoring.

Original languageEnglish
Article number6125246
Pages (from-to)865-875
Number of pages11
JournalIEEE Transactions on Instrumentation and Measurement
Volume61
Issue number4
DOIs
Publication statusPublished - 2012 Apr 1

Fingerprint

Wet etching
Discrete wavelet transforms
wavelet analysis
flow velocity
Flow rate
etching
Semiconductor materials
Neural networks
Fabrication
fabrication
digital filters
Digital filters
signal processing
Signal processing
wafers
thresholds
Monitoring
coefficients

All Science Journal Classification (ASJC) codes

  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

@article{0459dd405db949f0893f3846983a754d,
title = "Discrete wavelet transform and radial basis neural network for semiconductor wet-etching fabrication flow-rate analysis",
abstract = "This paper presents research that uses discrete wavelet transform (DWT) and radial basis neural network for automatic classification. The flow rate of a wet-etching fabrication facility for a single wafer can be analyzed automatically. The electrical signal of a flow meter is collected and decomposed by means of DWT. The signal power of the coefficients processed by the DWT is fed into the radial basis neural network for initial classification. A digital filter for post signal processing and a user-defined threshold value are applied; calculations for successful identification rate take place at the final step. The research results are applicable to automatic identification functions for in situ fabrication monitoring.",
author = "Yang, {Wen Ren}",
year = "2012",
month = "4",
day = "1",
doi = "10.1109/TIM.2011.2179824",
language = "English",
volume = "61",
pages = "865--875",
journal = "IEEE Transactions on Instrumentation and Measurement",
issn = "0018-9456",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Discrete wavelet transform and radial basis neural network for semiconductor wet-etching fabrication flow-rate analysis

AU - Yang, Wen Ren

PY - 2012/4/1

Y1 - 2012/4/1

N2 - This paper presents research that uses discrete wavelet transform (DWT) and radial basis neural network for automatic classification. The flow rate of a wet-etching fabrication facility for a single wafer can be analyzed automatically. The electrical signal of a flow meter is collected and decomposed by means of DWT. The signal power of the coefficients processed by the DWT is fed into the radial basis neural network for initial classification. A digital filter for post signal processing and a user-defined threshold value are applied; calculations for successful identification rate take place at the final step. The research results are applicable to automatic identification functions for in situ fabrication monitoring.

AB - This paper presents research that uses discrete wavelet transform (DWT) and radial basis neural network for automatic classification. The flow rate of a wet-etching fabrication facility for a single wafer can be analyzed automatically. The electrical signal of a flow meter is collected and decomposed by means of DWT. The signal power of the coefficients processed by the DWT is fed into the radial basis neural network for initial classification. A digital filter for post signal processing and a user-defined threshold value are applied; calculations for successful identification rate take place at the final step. The research results are applicable to automatic identification functions for in situ fabrication monitoring.

UR - http://www.scopus.com/inward/record.url?scp=84858337554&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858337554&partnerID=8YFLogxK

U2 - 10.1109/TIM.2011.2179824

DO - 10.1109/TIM.2011.2179824

M3 - Article

AN - SCOPUS:84858337554

VL - 61

SP - 865

EP - 875

JO - IEEE Transactions on Instrumentation and Measurement

JF - IEEE Transactions on Instrumentation and Measurement

SN - 0018-9456

IS - 4

M1 - 6125246

ER -