Online learning fuzzy vibration control of smart truss structure

Abstract

This paper deals with the active vibration control of smart truss structure. First, the electro-mechanical coupled dynamic model of the smart structure is constructed. Then, the first-order ordinary differential equation of the control system is presented. After that, an online learning fuzzy control (OLFC) algorithm is proposed to control the structure vibrations. The OLFC algorithm is composed of a reward function, a Q learning algorithm, a rule base generator and a conventional fuzzy controller. The OLFC algorithm learns the rule base by interaction with the plant, and changes rule base generate policy via evaluative reward signal to realize the learning goal. The algorithm only needs little information about the plant to design the reward function. In order to prove the effectiveness of the proposed control algorithm, control responses are presented and compared with conventional fuzzy control method.