An Artificial Neural Network Application to Identification of the Satellite Antenna Tracking System

• Main Authors: Chih-Hsuan Kuo, 郭志暄
• Other Authors: Te-Jen Su
• Format: Others
• Language: zh-TW
• Published: 2014
• Online Access: http://ndltd.ncl.edu.tw/handle/qgevrb

碩士 === 國立高雄應用科技大學 === 電子工程系碩士班 === 102 === In this paper, the parameter identification of the Artificial Neural Networks (ANN) is provided for an application to the satellite antenna controller. The high cost of satellite antenna controller is necessary in the tracking system, and the dynamic characteristic of satellite antenna controller is nonlinear. Therefore, the performance of satellite antenna controller is predicted by Artificial Neural Networks. The calculated simulate-outputs in the specific algorithm optimize the performance of the controlled substances. Therefore, the Artificial Neural Networks are employed to simulate the satellite antenna controller design herein. We may obtain the calculated output signals of back propagation Neural Network to elevation and rotation angles. Finally, this paper proves the data of antenna satellite controller with back propagation Neural Network is effective by comparing the data of tracking performance of FORMOSAT-2 satellite.