Inverse neural MIMO NARX model identification of nonlinear system optimized with PSO

Abstract

In this paper, a neural Inverse Dynamic MIMO NARX (Neural IDMN) model is applied for modelling and identifying simultaneously both of joints of the prototype 2-axes PAM robot arm. The contact force variations and highly nonlinear coupling features of both links of the 2-axes PAM system are modelled thoroughly through an Inverse Neural MIMO NARX Model-based identification process using experiment input-output training data. For the first time, the parameters of dynamic Inverse neural MIMO NARX Model of the 2-axes PAM robot arm has been identified and optimized with Particle Swarm optimisation (PSO) algorithm. The results show that the neural IDMN Model trained by PSO algorithm yields outstanding performance and perfect accuracy. © 2010 IEEE.