714 耐故障性を有するキュービックニューラルネットワーク知的制御の検証 : 二重振子の振上げ・倒立制御

概要

論文の詳細を見る
This paper discusses an intelligent control method integrating the Cubic Neural Network (CNN) which one of the authors proposed. This study deals with a nonlinear and failure-proof control problem for an intelligent control of an integrated CNN. As an application example, the integrated CNN is applied to the control problem of a swung up and inverted double pendulum. An integrator neural network in which the information on environment is embedded is provided for the integration using the Genetic Algorithm (GA) of both the CNNs for swinging up and inverting controls. As a result of numerical simulation, it is demonstrated that the integrated CNN controllers can stand up the double pendulum for the case of sensor failure of pendulum angle.
一般社団法人日本機械学会の論文
2002-03-14