Inverse model identification of 2-axes pneumatic artificial muscle (PAM) robot arm using double NARX Fuzzy Model and genetic algorithm

In this paper, a novel inverse double NARX fuzzy model is used for modeling and identifying simultaneously both of joints of the prototype 2-axes PAM robot armpsilas inverse dynamic model. The highly nonlinear coupling features of both of links of the 2-axes PAM robot arm is modeled thoroughly through an inverse double NARX fuzzy Model-based identification process using experiment input-output training data. The evaluation of different nonlinear inverse double NARX fuzzy models of the 2-axes PAM robot arm with various ARX model structure will be discussed. For first time, the nonlinear inverse double NARX fuzzy model scheme of the prototype 2-axes PAM robot arm has been investigated. The results show that the nonlinear inverse double NARX fuzzy model trained by genetic algorithm yields more performance and higher accuracy than the traditional inverse fuzzy model.