Keywords

Neural-network metamodels, Inverse mapping from performance goals to decision parameters, Semiconductor test-facility simulation, Simulation-driven parameter tuning, Decision-support automation for production testing

Abstract

A simulation based decision support system is developed for AT&T Microelectronics in Orlando. This system uses simulation modeling to capture the complex nature of semiconductor test operations. Simulation, however, is not a tool for optimization by itself. Numerous executions of the simulation model must generally be performed to narrow in on a set of proper decision parameters. As a means of alleviating this shortcoming, artificial neural networks are used in conjunction with simulation modeling to aid management in the decision making process. The integration of simulation and neural networks in a comprehensive decision support system, in effect, learns the reverse of the simulation process. That is, given a set of goals defined for performance measures, the decision support system suggests proper values for decision parameters to achieve those goals.

Graduation Date

1994

Semester

Spring

Advisor

Mollaghasemi, Mansooreh

Degree

Master of Science (M.S.)

College

College of Engineering

Department

Industrial Engineering and Mangement Systems

Degree Program

Industrial Engineering

Format

PDF

Language

English

Rights

Written permission granted by copyright holder to the University of Central Florida Libraries to digitize and distribute for nonprofit, educational purposes.

Length of Campus-only Access

None

Access Status

Masters Thesis (Open Access)

Identifier

DP0011935

Subjects

Neural networks (Computer science)--Computer simulation; Decision support systems--Computer programs; Decision support systems--Mathematical models; Decision making--Simulation methods; Microelectronics--Simulation methods

Accessibility Status

Searchable text

Share

COinS
 

Accessibility Statement

This item was created or digitized prior to April 24, 2027, or is a reproduction of legacy media created before that date. It is preserved in its original, unmodified state specifically for research, reference, or historical recordkeeping. In accordance with the ADA Title II Final Rule, the University Libraries provides accessible versions of archival materials upon request. To request an accommodation for this item, please submit an accessibility request form.