Several neural network studies have been carried out to apply both learning and adaptability of the neural networks to servo systems. Genarally, those applications have been carried out for the servo systems, which have rather slow responses, so as to perform a comparative long sampling time interval so as to calculate a learning algorithm of the neural networks.
In this research, the vibratory waveform control method of an electro-hydraulic servo system to reproduce the reference input waveform is discussed. Improvement of the reproducibility of the input signal can be carried out at a comparative high frequency domain by the original control method using two neural networks.
In this control method, in the first place, the signal transfer characteristics of the electro-hydraulic servo system is identified by the neural network which is called the neural network model. Next, the vibratory control input signal is created off-line by using the neural network model as the controlled object, then the control input signal is input into the electro-hydraulic servo system. The output waveform of the piston displacement of the electro-hydraulic servo system is evaluated by performance index J which is defined to evaluate waveform distortion.
This control method applied to the digital simulation to confirm reproducibility of the reference input signal, and the results are as follows :
(1) It is possible to identify the signal transfer characteristics of the electro-hydraulic servo system by the linear neural network using a rectangular input signal and its response output signal, and
(2) It is possible to create a vibratory control input signal by using the neural network model. The digital simulation results show the good performance such that J=4.28% for the rectangular input signal with the fundamental frequency of 1Hz and the frequency characteristics of the controlled system which has a bandwidth of 2Hz.

抄録全体を表示

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.

抄録全体を表示

A pneumatic actuator is not easily applied for accurate positioning tasks due to the compliance characteristic resulting from air compressibility. However, a pneumatic servo system can be considered as a kind of elastic type of body exposed to an external force owing to air compressibility even when positioning control is used. These characteristics have been applied to the conveying-peg-hole insertion tasks. Concretely, a peg is moved above a hole horizontally (not necessary to be accurate) by a long stroke pneumatic cylinder and the peg is inserted vertically to the hole by another pneumatic cylinder. Assuming that either the peg or the hole is chamfered, elastic displacement by a collision reaction force from a chamfering plane can be utilized as an absorption function of a relative positioning error, which allows for the insertion to be made. The possibility of insertion depends on the elastic characteristics (mechanical impedance) of positioning control system set up at the conveying cylinder and such a mechanical impedance is regulated by the pressure response characteristics. Since the position control system used here is based on pressure control, the desired impedance characteristics which are derived to provide for insertion analytically can be adjusted using pressure control. The validity of the proposed method could be confirmed through the carrying out of experiments.

抄録全体を表示

Positive displacement machines are suitable for pumps and motors even for water hydraulic systems. However, based on the properties of working fluids, the film thickness of sliding and sealing parts is thin, then, the formation, stability and power losses must be investigated in detail for high performance.
In the sense, the present report is to investigate theoretically the characteristics of the sliding and sealing part of hydrostatic thrust bearings, carrying eccentric loads, which are a basic model of piston type machines.
Based on a newly developed treatment of solid contact, the characteristics of the sliding and sealing parts are clarified as follows :
1) For the same loading the film thickness with case of oils is thicker than that of a water. Then, water films are more easily in solid contact than oil films.
2) The stability region of oil films is wider than that of water films.
3) The power losses on sliding and sealing parts with case of water are much smaller than these of oils.
4) For case of a stepwise change in loading, the films show good damping characteristics even with case of solid contact.

抄録全体を表示