Simultaneous computation of model order and parameter estimation for system identification based on gravitational search algorithm

Abstract

System identification is a technique used to obtain a mathematical model of a system by performing analysis of input-output characteristic of the system. Most significant steps of system identification process are generally summarized into four main stages. The initial stage is collection of experimental data. After that, the model order and structure are selected. The next stage is to approximate the parameters of the model and finally, the mathematical model is validated. In this paper, a technique termed as Simultaneous Model Order and Parameter Estimation (SMOPE), which is specifically based on Gravitational Search Algorithm (GSA) is proposed to combine model order selection and parameter estimation in one process. Both the model order and the parameters of the system are estimated simultaneously to attain the best mathematical model of a system. From the simulation, it is proven that the proposed method can be an alternative technique for solving the system identification problem.