侯東旭952221E224054

侯東旭952221E224054

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
運用模糊決策樹與 NSGA- Ⅱ演算法探勘多品質特性之製程參數調控法則 95-2221-E-224-054 ( 結案報告 ) 中文摘要 應用濕式 研磨 設備生產 奈米 微粒 材料,近來已朝向 快速化、大量生產與須維持高品 質發展。設備開發製造商或現場工程師,已面臨必須對製程參數進行連續的監控,當製 程上出現偏差或故障時,能快速進行參數調整,排除故障以維持產品品質的迫切需要。 此外,製程的資料中隱藏著許多有價值與重要的調控法則,如能萃取出這些法則,便能 有效的調控及改善製程的生產效率與品質。因此,如何發展出一套調控奈米機械研磨製 程參數之規則庫,以供參數調控之參考,是一項重要的課題。 基於此,本研究擬整合自組織映射網路 (Adaptive Resonance Theory, ART-2) 、資料探 勘之模糊決策樹分類技術 (Fuzzy Decision Tree) 、多目標基因演算法 (Multi-Objective Genetic Algorithm, MOGA) 與柏拉非支配解的概念,來進行重要參數調控規則之萃取, 發展出一套調控奈米機械研磨製程參數之規則庫,以供 機械研磨 設備開發製造商或現場 工程師使用。研究結果顯示,本研究所提出的方法確實可以萃取出隱藏在製程中的重要 調控法則。這些規則可以被用來發展及建立調控奈米機械研磨製程參數之規則庫,以供 當製程上出現偏差或故障時,能快速進行參數調整,有效的改善製程的生產效率與品質。 關鍵詞:奈米研磨製程、模糊理論、決策樹、粗集理論、資料探勘、多目標基因演算法
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Mining Control Rules for a Nano-Particle Milling Process Parameters by Using Fuzzy Decision Tree and Multi-Objective Evolutionary Algorithms Abstract Using mechanical milling process to make nano-particles is a popular method because of its simplicity and the applicability to all classes of materials. The smaller grain size the nano-particle is, the higher performance of surface area the nano-particle has. Therefore, the required qualities of the milling process are that the mean of nano-particle grain size and the variance of grain size must be kept small. However, many process parameters and corresponding quality measures are stored in a huge database and remain unknown. This database certainly contains many useful know-how rules that can be extracted by using data mining techniques to set and tune the process parameters and to improve the efficiency and quality in a nano-particle milling process. In this research, the data mining techniques, variable precision rough set (VPRS) and decision tree C5.0 algorithm, are respectively integrated with fuzzy set theory to extract the useful rules from a history quantitative database and to set the parameters for the corresponding multiple quality criteria in a nano-particle milling process. First of all, the adaptive resonance theory (ART-2) neural networks is used to cluster the history data of
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 11/27/2009 for the course IM MA420 taught by Professor Mar,lee during the Spring '09 term at National Taiwan University.

Page1 / 10

侯東旭952221E224054

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online