Gradient-based Iterative Identification Method for Non-uniformly Sampled Input-nonlinear Systems
Abstract
This paper proposes an identification method of an input-nonlinear system withsaturation and dead-zone nonlinearity using the asynchronous input-output data spaced bynon-uniform intervals. The piecewise expression of the nonlinear part is simplified asan analytic function with an available switching function. By extending the traditionalcontinuous linear time-invariant processes to non-uniformly sampled input-nonlinearsystems, a concise input-output representation model is derived. Based on the key termseparation principle and the auxiliary model identification idea, a gradient-basediterative identification algorithm is developed for simultaneously estimating allparameters of the derived model. Through a numerical example, the proposed algorithmshows its superior estimation accuracy compared to the auxiliary model-based forgettingfactor stochastic gradient algorithm. Finally, the application to a two-tank systemindicates the effectiveness of the proposed method.
DOI: 10.61416/ceai.v25i4.8446