本論文以模糊控制器為基本架構，發現大多數模糊控制器之模糊規則庫均具有反對稱的性質，所以我們根據此特性設計一個單數入模糊控制器，比較可得傳統雙輸入模糊控制器與單輸入模糊控制器之響應圖近似，但是單輸入模糊規則數卻大大地減少，因此更加利於修改。接著，我們應用基因演算法來調整比例因子，經由此方法可使的上升時間和最大超越量均有所改善。此外，我們又另外提出模糊基底函數與其它連續型基底函數做比較，因而發現模糊基底函數的性能相較於其他連續型基底函數更加優越。 We find that rule tables of most fuzzy logic controllers have skew-symmetry property. In this thesis, we will propose a new variable, which is a sole fuzzy input variable. The single-input fuzzy logic controller can greatly reduce the total number of rules. Hence, generations and the adjustment of control rules are easier. Control performance is nearly the same as that of conventional fuzzy logic controllers. In order to improve the performance of the transient state and the steady state of single-input fuzzy logic controller, we develop a method to tune the scaling factors based on genetic algorithms. The simulations of this new method show the better performance in the response. Next, we will discuss the fuzzy basis function and other continuous basis functions. Then, it is seen that the fuzzy basis function has the better performance than other continuous basis functions.