Nonlinear system identification and control using state transition algorithm

TL;DR

This paper introduces the state transition algorithm (STA), a novel optimization method for nonlinear system identification and control, demonstrating superior performance over existing algorithms in accuracy, speed, and stability.

Contribution

The paper presents the STA as a new optimization approach for nonlinear system identification and control, with applications to parameter estimation and PID controller design.

Findings

STA achieves faster convergence than other algorithms.

STA provides more accurate system parameter estimation.

Experimental results confirm STA's stability and effectiveness.

Abstract

By transforming identification and control for nonlinear system into optimization problems, a novel optimization method named state transition algorithm (STA) is introduced to solve the problems. In the proposed STA, a solution to a optimization problem is considered as a state, and the updating of a solution equates to a state transition, which makes it easy to understand and convenient to implement. First, the STA is applied to identify the optimal parameters of the estimated system with previously known structure. With the accurate estimated model, an off-line PID controller is then designed optimally by using the STA as well. Experimental results have demonstrated the validity of the methodology, and comparisons to STA with other optimization algorithms have testified that STA is a promising alternative method for system identification and control due to its stronger search ability, faster convergence rate and more stable performance.