Nonlinear dynamic system identification with a cooperative population-based algorithm featuring a restart metaheuristic

Abstract

Dynamic system identification is commonly reduced to an optimization problem which is complex and multimodal. To find a global optimum of this problem, evolutionary algorithms are often applied. However, as it was shown in many studies, conventional evolution-based algorithms do not demonstrate the acceptable performance for this class of problems, therefore, some effective modifications have been proposed so far. In our study, we combine two approaches which were previously used in linear dynamic system identification and allowed their accurate identification. More specifically, we present a cooperative evolutionary algorithm with a restart metaheuristic and apply it for the parameter identification of a nonlinear cascaded system. The experimental results prove the effectiveness of the proposed evolution-based identification compared to other known solutions of this problem.

Identification of Differential Equations Systems With Various Input Effects

“…A lot of methods have been developed to simulate dynamic processes. These methods belong to the analytical and numerical, parametric and nonparametric classes (Brester et al, 2020;Ovcharenko, 2020;Roehrl et al, 2020). The study of various systems' behavior often leads to analysis and solution of equations that include characteristics such as a rate of change of system parameters.…”