Fuzzy Neural Network algorithm based on the delay compensation force/position control structure of a redundant actuation parallel robot

Abstract

In this paper, a novel control method of the redundant force branch based on the force/position hybrid control structure of Smith predictor compensation is proposed. A fuzzy PI controller is designed based on Smith predictor compensation structure and it is included in the redundant force branch. This method can obtain good tracking and dynamic performance. However, fuzzy control doesn't have self-learning and adaptive ability, so fuzzy neural network (FNN) controller is used in the redundant force branch. The simulation results show that the proposed FNN algorithm based on delay compensation force/position hybrid control structure can improve the adaptability and the control accuracy of driving force of redundant branch.