Intelligent control using destabilized and stabilized controllers for a swung up and inverted 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. This study deals with a nonlinear control problem. In the control, an NN-based nonlinear switching hyperplane is designed based on the dynamical energy principle. The proposed integrated CNN is applied to a control problem of a swung up and inverted double pendulum mounted on a cart for the case of arbitrary initial condition of pendulum angle. In order to verify the performance of the integrated CNN, computer simulations and experiments on a real apparatus were carried out for the cases of parameter variation and sensor failure. As a result, it was demonstrated that the integrated CNN can stand up the double pendulum without touching the cart position limit in abnormal situations. Then, the robustness and the fault-tolerance of the integrated CNN were verified compared with the linear quadratic control techniques.