Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/121754
Title: MODELING SURFACE PROFILES USING GAUSSIAN PROCESSES WITH ENGINEERING APPLICATIONS
Authors: ZHANG LINMIAO
Keywords: Gaussian process, Surface profi le, Profi le monitoring, Process evaluation, Robust estimation, Quality control
Issue Date: 31-Jul-2015
Citation: ZHANG LINMIAO (2015-07-31). MODELING SURFACE PROFILES USING GAUSSIAN PROCESSES WITH ENGINEERING APPLICATIONS. ScholarBank@NUS Repository.
Abstract: THIS THESIS PROPOSES SEVERAL GAUSSIAN PROCESS EXTENSIONS TO MODEL SURFACE PROFILES. THESE MODELS HAVE WIDE ENGINEERING APPLICATIONS. WE FIRST PROPOSE AN ADDITIVE GAUSSIAN PROCESS (AGP) MODEL TO APPROXIMATE THE STANDARD WAFER PROFILE WHILE QUANTIFYING THE PROCESS VARIATION. BASED ON THE AGP MODEL, STATISTICAL TESTS ARE PROPOSED TO MONITOR THE QUALITY OF NEWLY PRODUCED UNITS. WHEN WAFERS ARE FABRICATED IN BATCHES, WE FURTHER INTRODUCE A MIXED-EFFECTS GAUSSIAN PROCESS MODEL TO CHARACTERIZE THE PROFILES WITH NESTED RANDOM EFFECTS. WE PROPOSE AN EM ALGORITHM TO ESTIMATE THE MODEL PARAMETERS WHICH ARE USED TO EVALUATE THE PROCESS CAPABILITY. THIRDLY, WE CONSIDER THE SCENARIO WHEN SURFACES ARE MEASURED WITH COORDINATES ERROR. WE PROPOSE AN ERROR-ADJUSTMENT APPROACH BASED ON REPEATED MEASUREMENTS TO PROVIDE A ROBUST PREDICTION OF THE SURFACE. WE CONDUCT EXTENSIVE SIMULATION STUDIES TO VALIDATE THESE MODELS. WE ALSO PROVIDE CASE STUDIES TO DEMONSTRATE THAT OUR METHODS ARE APPLICABLE AND EFFE
URI: http://scholarbank.nus.edu.sg/handle/10635/121754
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
ZhangL.pdf4.38 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

107
checked on Nov 2, 2018

Download(s)

31
checked on Nov 2, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.