Nonlinear control of triple inverted pendulum based on T-S cloud inference network

Abstract

The triple inverted pendulum is a nonlinear, dynamic and unsteady system. The traditional control methods of triple inverted pendulum have limited control accuracy and slow responding. This kind of pendulum system is difficult to control due to the inherent instability and nonlinear behavior. In this paper, GA-RBF-ARX model is applied to model triple inverted pendulum based on its input/output data. According to the nonlinear identification model, a novel method via T-S cloud inference network controller optimized by genetic algorithm (GA) is proposed. T-S cloud inference network is constituted by T-S fuzzy neural network and the cloud model. Therefore, the rapid of fuzzy logic and the uncertain of cloud model for processing data are both taken into account. What's more, GA possesses global optimization characteristics and good parallel design structure. Compared with the simulation recognition results of T-S fuzzy neural network controller, T-S cloud reference network controller has strong robust and fast calculate speed. So, T-S cloud inference network by GA is an effective method in control.