A Novel ANN-ARMA Scheme Enhanced by Metaheuristic Algorithms for Dynamical Systems and Time Series Modeling and Identification

This paper presents a new scheme for dynamical systems and time series modeling and identification.It is based on artificial neural networks (ANN) and metaheuristic algorithms.This scheme combines the strength of ANN with the dexterity of metaheuristic algorithms.This fusion is renowned for its ability to detect complex patterns, which considerably improves accuracy, computational efficiency, and robustness.The proposed scheme deals with the curve fitting and addresses ANN's local minima problem.This approach introduces the identification concept using a fresh novel identification element, referred to as the error model.The proposed framework encompasses a parallel interconnection of two models.The principal sub-model is the elementary model, characterized by standard specifications and a lower resolution, designed for the data being examined.In order to address the resolution limitation and achieve heightened precision, a second sub-model, named the error model, is introduced.This error model captures the disparities between the primary model and considered data.The parameters of the proposed scheme are adjusted using metaheuristic algorithms.This technique is tested across many benchmark data sets to determine its efficacy.A comparative study along with benchmark approaches will be provided.Extensive computer studies show that the suggested strategy considerably increases convergence and resolution.