Using Enhanced Adaptive Grey Model for solving the Pilot Run Forecasting Problem in Copper Pillar Assembly Process / 使用強化型適應性灰預測模型求解銅柱凸塊封裝之試產預測問題

碩士 / 國立成功大學 / 工業與資訊管理學系碩博士班 / 100 / In new product build up, SPC data that gather by insufficient prior run samples is not complete enough to offer production performance for engineering’s study and evaluation,especially for semi-conductor technology progress.
As multiple and thin function chip development,fine pitch design we called copper pillar is capable to achieve high density layout requirement.By this solution,bump diameter that may influence chip function and efficiency takes the most important role to fulfill this technology development. In order to evaluate and simulate production performance, we are using box plot and fuzzy theory that consider dynamic tendency and grey model for learning short-term time series production data,to improve the short term time series prediction performance of traditional Gray Model (1,1).
According to simulation result,this dynamic tendency grey model provided the best prediction accuracy for the research case and the other public testing data,than the rest gray model.

Identiferoai:union.ndltd.org:TW/100NCKU5041051
Date January 2012
CreatorsYi-HsiangHuang, 黃湙翔
ContributorsDer-Chiang Li, 利德江
Source SetsNational Digital Library of Theses and Dissertations in Taiwan
Languagezh-TW
Detected LanguageEnglish
Type學位論文 ; thesis
Format66

Page generated in 0.0014 seconds