小口径トンネルロボットのニューラル形最適ゲインオートチューニング

概要

論文の詳細を見る
This paper describes the autotuning of feedback gain for a small tunnelling robot. We have already proposed a directional control method in that the head angle of the control input is the sum of the deviation multiplied by feedback gain K_p and the angular deviation multiplied by feedback gain K_a. In this paper, we use a neural network to obtain feedback gains K_p and K_a. The input of the neural network is the initial deviation and initial angular deviation. The output of the neural network is the feedback gains K_p and K_a. This neural network learns from deviation error. The optimum gains obtained by the proposed method agreed with the optimum gain obtained by trial and error. The neural network which can apply to any initial deviation was formed by using plural deviations. Moreover, this method can tune the optimum gains to any design line. These results showed the validity of this method.
社団法人日本機械学会の論文
1992-02-25