小口径トンネルロボットのニューラル形最適ファジィ変数オートチューニング法

概要

論文の詳細を見る
This paper describes the autotuning method of fuzzy set values for a small tunnelling robot. We have already proposed a fuzzy directional control method using fuzzy rule set which inputs both deviation and angular deviation, output head angle as control input. In this paper, we use a neural network to obtain the optimum fuzzy set values. The input of the neural network is the initial deviation and initial angular deviation. The output of the neural network is fuzzy set values. This neural network learns from deviation error. Total deviation error of simulation using the optimum fuzzy set values obtained by the proposed method was smaller than that of simulation using the optimum values obtained by trial and error. A neural network which can apply to any initial deviation was formed by using plural deviations. Moreover, this method can tune the optimum fuzzy set values 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
1992-09-25