本論文將探討傳統滑動模式控制跟類神經網路的相互結合，並實際應用在一個倒三角體的非線性不穩定系統上。在傳統的滑動模式控制必須了解系統的動態方程式及其參數，才可針對所需要求做設計，但實際上系統的動態方程式及參數並不是很容易求得的。因此我們便設計了兩個平行處理的神經網路，其輸出分別去取代滑動控制的等量控制及誤差控制，並利用了最陡梯度法去調整神經網路的權重值。最後可發現在傳統滑動模式控制中最容易產生的抖動現象及誤差皆可以消除，並且保有滑動模式控制所擁有延著滑動平面趨向平衡點的特性。 In this paper, we will propose a cooperative control approach that is based on combination of Neural Networks and Sliding Mode Control (SMC) methodology. The main purpose is to eliminate the chattering phenomenon. Furthermore, the system performance obtained via the method of SMC can be improved. In the present approach, two parallel Neural Networks are utilized to realize a Neuro-Sliding Mode Control (NSMC). The equivalent control and the corrective control in terms of Sliding Mode Control are the outputs of the Neural Networks. The weights adaptations of Neural Network are determined based on the Sliding Mode Control equations. Then, the gradient descent method is used to minimize the control force so that chattering phenomenon can be eliminated.
