ニューラルネットワークの油圧サーボ機構への適用に関する基礎的研究 : 系の収束条件と安定問題について

概要

論文の詳細を見る
A hydraulic servo system which has quick-response characteristic, high positioning accuracy and high power by itself is often used in an air plane, a construction machinery and the center of a vibratory testing machine. Several papers for application of Neural Network to servo systems have been reported. Most of them were for systems which have slow speed response characteristic such as pneumatic servo systems. Recently applications to improve the characteristic of a hydraulic servo system, a vibratory waveform control system and so forth are studied. In this study, we applied Neural Network to the hydraulic servomechanism directly and discussed about the basic characteristic such as convergent problem of output waveform for reference input signal and stability problem of the system. The result were as follows: (1) When the Neural Network is applied to the hydraulic servomechanism and learns with the plural number of times in one sampling interval, the theoretical convergent conditional equation could be obtained and confirmed by the simulation and the experiment. (2) In this control system, there are convergent and divergent domains. And we found that the stable and unstable areas existed in the convergent domain.
社団法人日本機械学会の論文
1999-10-25