輔助模糊控制/決策之支援系統

機構典藏 > College of Business and Management > Graduate Institute & Department of Information Management > Proceeding > Item 987654321/23168

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/23168

Title:	輔助模糊控制/決策之支援系統
Authors:	周志強;李鴻璋
Contributors:	淡江大學資訊管理學系
Date:	1994-05
Issue Date:	2009-11-30 14:35:31 (UTC+8)
Publisher:	臺北縣淡水鎮 : 淡江大學
Abstract:	舉凡世事，只要有人的介入，必使其包含或多或少的不確定性(Uncertainty)，傳統二值邏輯(Two-value Logic)已不再能真實的描繪出模糊的意念(Semantics)。故提出一個輔助模糊控制/決策之支援系統(FCDS)，其擁有使用宜人的(User Friendly)圖形使用者介面(Graphic User Interfaces) 、多選擇性的推論運算。(lmplication Functions) 方式與反模糊(Defuzzification)方法，且結合規則的自動學習產生與更近似人類思考模式的二階層結則(Two-level Meta-rule) 控制規則。在FCDS 中發展二階層結則的「倒車入庫」與傳統單層模糊規則系統、類神經網路(Neural Network)作一比較;並討論規則學習中利用最大原則(Maximum Principle) 與頻率原則(Frequncy Principle) 產生規則之效能(Performance)作一比較﹒最後再以「財務流通性的決策評估」一例，驗證此系統確實可正確無誤的完成模糊控制/決策系統。 For most real-world control problems can involve more or less uncertainty. Two-value logic cannot describe fuzzy semantic actually, so we propose a developing support system in fuzzy control/decision - FCDS. FCDS include many advantages, such as user friendly, graphic user interface, multi-choice fuzzy implication functions, and defuzzifical strategies. It also combines generating rules automatically and two-level thinking of meta-rule. Applications to truck backer-upper used meta-rule and to assess the problem of financial liquidity are presented. For the truck control problem, we propose two types. Type one, inference using meta-rule is compared with a neural network controller and a pure limited-rule fuzzy controller; the new method shows the best performance. Type two, the maximum principle is compared with the frequency principle. As a result, frequency principle is better. For diagnoising financial liquidity, we want to prove the FCDS can complete the problem of control I decision.
Relation:	1994國際資訊管理研討會論文集=Proceedings of the 5th International Conference on Information Management，頁37-45
Appears in Collections:	[Graduate Institute & Department of Information Management] Proceeding

Files in This Item:

File	Size	Format
index.html	0Kb	HTML	295	View/Open

Loading...