Intelligent failure-proof control using cubic neural network (application to a control problem of swung up and stabilized double pendulum)

This study aims at establishing a robust intelligent control method with higher control performance and wider applicable region by extending the Cubic Neural Network (CNN) intelligent control method. In particular, this study deals with a nonlinear and failure-proof control problem for an intelligent control method of integrated CNN. The proposed CNN is applied to a control problem of a swung up and inverted double pendulum mounted on a cart. In this study, the dynamical energy principle is embedded into the integrator of CNN that consists of multilevel parallel processing on different degrees of abstraction. In order to confirm the effectiveness of the integrated CNN controller, we carried out computational simulations and experiments using a real apparatus. As a result, it was demonstrated that the integrated CNN controllers can stand up the double pendulum taking into account the cart position limit for the case of arbitrary initial condition of the pendulum angle.