407 統合化キュービックニューラルネットワーク知的制御手法による倒立振子の振り上げ安定化 : ロバスト性と耐故障性の検証

概要

論文の詳細を見る
This study aims at establishing a robust intelligent control method with high control performance and wide applicable region. In this paper, an integrated Cubic Neural Network (CNN) intelligent control method is applied to swing-up and stabilization of an inverted pendulum on a cart having restricted travel. CNN consists of multilevel parallel processing on different degrees of abstraction. An integrator is employed to decide between a swing-up CNN controller and a stabilizing CNN controller depending on the state of the inverted pendulum system. By comparing the proposed method with a sliding mode control method numerically and experimentally, it was verified that the proposed method has a good robustness with respect to parameter variation and a high tolerance to sensor failure.
2003-10-30