本論文主要是以倒傳遞類神經網路、基因演算法及模糊理論結合倒傳遞類神經網路為基礎的控制器應用在離心式擺鎚吸震器的主動式控制，藉由所提出的控制器來調整離心式擺鎚吸震器的擺鎚扭矩參數，使得系統的反共振頻率(anti-resonance frequency)偏移，來降低轉盤的震動量。經由推導主動式擺鎚吸震器的動態數學模式，繪出擺鎚扭矩參數變化與轉盤震動及擺鎚最大振幅的頻率響應圖。當系統的擾動頻率改變時，可藉由所提出的控制器找出最佳的擺鎚扭矩參數值，使系統的轉盤震動達到最小值。由系統的模擬結果可以看出所提出的控制器在擾動頻率改變時能有效的使旋轉震動降低到所期望的值。 In this study, the back-propagation (BP) neural network algorithm, genetic algorithms (GAs) and fuzzy back-propagation neural network are proposed for active control of a centrifugal pendulum vibration absorber (CPVA). The proposed algorithms are applied in this case to regulate the anti-resonance frequency in an active pendulum vibration absorber (APVA), by suppressing vibration of the carrier. The dynamic model of the APVA was developed and simulated using MATLAB. In the simulation results, when the variations of the excitation frequency, the controllers will find the optimal variables to determine an appropriate value such that the vibration amplitude of the carrier is minimized. A comparison of the carrier vibration results for the BP neural network algorithm, the genetic algorithm and fuzzy back-propagation neural network are performed. The simulation results demonstrate the effectiveness of the proposed APVA for reducing the carrier vibrations.
