ニューラルネットワークの油圧サーボ系への適用に関する研究

第2報 系の信号伝達特性の同定と振動波形制御入力の創成…実験による検討

抄録

In the first report, the vibratory waveform control method of an electro-hydraulic servo system to reproduce the reference input waveform was discussed using a digital simulation.
In this report, the control method applied to the experimental apparatus to confirm reproducibility of the reference input signal was confirmed that improvements of the reproducibility of the reference input signal could be performed in a comparative high frequency domain using a control method.The results, which were obtained by the experiment, are as follows.
(1) It is possible to identify the signal transfer characteristics of the electro-hydraulic servo system by a linear neural network using a rectangular input signal and its response the output signal.
(2) It is possible to create the vibratory control input signal by using a neural network model. The experimental results show performance such that J=4.79% and 14.23% for the rectangular input signals with the fundamental frequency of 1 and 10Hz.
(3) It is possible to create the control input signal for the controlled object, which contains a nonlinear element such as a current limiter of the servo amplifier, by this control method.