Robustness and Fault-Tolerance of Cubic Neural Network Intelligent Control Method: Comparison with Sliding Mode Control

This study aims at establishing a robust intelligent control method with higher control performance and wider application region. In particular, this study deals with a nonlinear and failure-proof control problem. In this study, the dynamical energy principle is embedded into the integrator of Cubic Neural Network (CNN) that consists of multilevel parallel processing on different degrees of abstraction. The proposed CNN is applied to a control problem of a swung up and inverted pendulum. In order to confirm the effectiveness of the integrated CNN controllers, we carried out simulations and experiments with parameter variation and sensor failure. As a result of simulation and experiment, it was demonstrated that the integrated CNN controllers can stand up the pendulum taking into account the cart position limit at abnormal situations. Then, the robustness and the faulttolerance of the proposed CNN controllers is confirmed by comparing sliding mode control techniques.