遞迴式小波類神經模糊網路之動態系統判別

Identification of Dynamical System using Recurrent Wavelet Neuro-Fuzzy network

10.6989/JN.201012.0141

黃元瑞(Yuan-Ruey Huang)；童景賢(Jing-Syan Torng)

小波 ； 類神經模糊網路 ； 遞迴式類神經網路 ； wavelet ； neuro-fuzzy network ； recurrent neural network

南亞學報

30期（2010 / 12 / 01）

141 - 156

繁體中文

本文提出遞迴小波類神經模糊網路（Recurrent Wavelet Neuro-Fuzzy network）模式方法，該法係以遞迴小波類神經網路為推論機構。遞迴式類神經網路具備前饋和迴授兩種的網路特性，使得遞迴式類神經網路的輸出包含以前所輸出的資料，因此遞迴式類神經網路具有動態行為以及資料貯存的特性。並且遞迴式類神經網路是一種動態的映射結構，所以，對於未知模式的動態系統、系統參數的變化和外來負載的干擾等均能有效的鑑別。本研究以滾珠螺桿系統為非線性摩擦力之動態系統，經驗證顯示遞迴小波類神經模糊網路模式有良好之鑑別非線性系統之功能。

In this study, Recurrent Wavelet Neuro-Fuzzy Network (RWNFN) is proposed. RWNFN uses Recurrent Wavelet Neural networks as inferring mechanisms. Recurrent Wavelet Neural networks has two characters: feed forward and feedback. Therefore, the outputs of Recurrent Wavelet Neural network have the previous outputs of its own which make it as a dynamical mapping mechanism. Hence, RWNFN with dynamical mapping functions can identify nonlinear dynamical system effectively. In this paper, the ball-screw-driving system is used as a nonlinear frictional dynamic system. According to the modeling results, RWNFN can identify nonlinear dynamical system effectively.