Adaptive neural model optimized by modified differential evolution for identifying 5-DOF robot manipulator dynamic system

This paper proposes an adaptive neural network (ANN) model for modeling the nonlinear dynamic of a robot manipulator based on experimental input-output data from the system. The ANN model is created by combining the multilayer perceptron neural network structure and the nonlinear auto-regressive with eXogenous input model and is trained by the modified differential evolution (MDE) algorithm. The effectiveness of the proposed method is evaluated and compared with other algorithms such as the back-propagation algorithm, the traditional differential evolution and the hybrid differential evolution-back-propagation algorithm. The results prove that the proposed ANN model optimized by the MDE algorithm for the 5-DOF robot manipulator dynamic is successfully modeled and performed well.