1994 年 60 巻 573 号 p. 1735-1742
This paper deals with an automatic generation algorithm of a hierarchical fuzzy model using the genetic algorithm and the delta rule. The fuzzy inference can be applied to various problems. However, the determination of the membership functions is a difficult problem because the determination depends on human experts. Auto-tuning methods of the fuzzy model have been proposed to develop the time-consuming operation by human experts. However, a number of fuzzy rules are needed in the case of simple fuzzy inference. Therefore, we propose an auto-tuning method of the hierarchical fuzzy inference. At the same time, the proposed method enables the fuzzy model to construct the optimal and the minimal structures. In this paper, we show the effectiveness of the proposed method by simulation, for the control of the level of water in tanks. This general system can be applied to the control of robot's motion, sensing and recognition problems and so on.