參數不確定系統之相位超前與落後控制器設計:利用模糊類神經網路

Abstract

在本篇論文中我們提出了利用模糊類神經網路之特性，去設計一個不確定系統之相位超前與落後控制器的方法。這個方法有著簡單、快速以及精確度高的特性。面對時域、頻域等各方面的問題，透過模糊類神經網路高效率的數值運算，避開複雜的公式，簡化了問題和有著相同的解決模式。設計的相位超前與落後控制器在系統模型有變動時，仍能滿足變動系統的規格，結果顯示控制器有良好的強健性，驗證了模糊類神經網路廣泛近似與學習的能力，因此模糊類神經網路的確可以有很好的表現。

In the thesis, we present a Phase Lead Phase Lag tuning method for uncertain processes using Fuzzy Neural Network. This method has the property of simplicity、high-speed and high-accuracy. The FNN has the ability of general wide approximation and learning. Using the FNN in the time-domain、frequency-domain problems etc . . , We can avoid solving the complex equations. Therefore the FNN has simplified problems. The designed system controller can still meet the system specifications when the system lightly varies. The simulations show that the system controlled by the Phase Lead Phase Lag controller has the property of robustness. Therefore we can know that the FNN indeed can performance well.