模糊邏輯的研究及應用

Study and Application of Fuzzy Logic

廖展義(Chan-I Liao)

指導教授 ： 廖炯州

共同指導教授 ： 葉雲奇(Yun-Chi Yeh)

健行科技大學/電資學院/電子工程系碩士班/碩士(2020年)

摘要

本篇論文所提出的『模糊邏輯的研究及應用』，是以模糊邏輯(Fuzzy Logic)為理論基礎，並將它應用於辨識『歷屆畢業校友對本系之核心能力在就業技能及本系所設計課程內容之間的相關性調查』的為範例說明。本篇論文提出的模糊邏輯演算法，它是由如下的四個歩驟所組成，分別是：歩驟1：模糊化(fuzzification)；歩驟2：模糊規則庫的建立(fuzzy rule base establishment)，歩驟3：模糊推論工場的設計(fuzzy inference engine design)，及歩驟4：解模糊化(defuzzification)。辨識過程，說明如下：(1)首先將『就業所需』及『課程內容』兩者之間的相關性，區分成如下的五種程度表示，分別是『極為相關』、『高度相關』、『中度相關』、『低度相關』、及『少有相關』等；(2)接著依此相關性的程度，以模糊邏輯演算法，判定課程的授課內容是否需要再作調整。本文將授課內容是否需要再作調整，分成如下的5種不同程度，它們分別是：(a)符合；(b)不足；(c)缺乏；(d)不實用；及(e)無用。在本篇論文中，模糊邏輯演算法是以MATLAB程式語言實現，原因是MATLAB程式語言具有語法簡單、及演算法較容易實現等優點；(3)最後本文是顯示『就業所需』與『課程內容』相關性的辨識結果。綜合如上的過程，結論是本篇論文所提出之模糊邏輯演算法及其應用，可說是ㄧ個簡單有效的辨識方法。

關鍵字

模糊邏輯 ； 教學評量 ； MATLAB

並列摘要

The proposed "Study and Application of Fuzzy Logic" is based on fuzzy logic and identifies " A survey of the correlation between graduates' core competencies in employment skills and the content of courses designed by the department" as an example. The fuzzy logic algorithm proposed in this paper is composed of the following four steps: Step 1: fuzzification, Sep 2: fuzzy rule base establishment, Step 3: fuzzy inference engine design, and Step 4: defuzzification. The identification process is explained as follows: (1) First, the correlation between "need for employment" and "course content" is classified into the following five levels: "extremely correlation", "highly correlation", "Moderate correlation", "low correlation", and "rare correlation"; (2) Secondly, according to the degree of correlation, use fuzzy logic algorithms to determine whether the content of the course needs to be adjusted. Whether the content of the course needs to be adjusted again is divided into the following five different levels: (a) conform; (b) insufficient; (c) lack; (d) not practical; and (e) useless. In this study, fuzzy logic algorithms are realized with the MATLAB programming language, because MATLAB has the advantages of simple syntax and easy implementation for the proposed algorithms; (3) Finally, this study shows the recognition results on "employment requirements" and "course contents". The proposed fuzzy logic algorithm is a simple and effective identification method for identification of "employment requirements" and "course contents".

並列關鍵字

Fuzzy Logic ； Teaching evaluation ； MATLAB

參考文獻

參考文獻

[1] L.A. Zadeh. Fuzzy sets, Information and control, vol. 8, pp. 338–353, 1965.

[2] L.A. Zadeh, Fuzzy sets as a basis for a theory of possibility, Fuzzy Sets and Systems, 1978.

[3] M.J. Er, B.H. Kee, and C.C. Tan, Design and development of an intelligent controller for a pole-balancing robot, Microprocessors and Microsystems, vol.26, pp. 433-448, 2002.

[4] C.H. Huang, W.J. Wang, and C.H. Chiu, Design and implementation of fuzzy control on a two-wheel inverted pendulum, IEEE Transactions on Industrial Electronics, vol. 58, pp.1-14, 2011.