abstract
- This article focuses on designing a neural identifier for non-linear systems using an Integral Sliding Mode (ISM) approach. A Differential Neural Network (DNN) structure identifies a non-linear system; meanwhile, the learning laws for stabilizing the identification error are obtained from the Lyapunov Stability analysis. An integral sliding surface is proposed to provide the convergence of the system identifier weights to the ideals to approximate the non-linear system. The results for identifying the Van Der Poll Oscillator and the Inverted Pendulum show better identification error reduction performance than a traditional DNN.