Abstract
This paper presents a novel modified particle swarm optimization algorithm (MPSO) for both offline and online parametric identification of dynamic models. The MPSO is applied for identifying a suspension system introduced by a quarter-car model. A novel mutation mechanism is employed in MPSO to enhance global search ability and increase convergence speed of basic PSO (BPSO) algorithm. MPSO optimization is used to find the optimum values of parameters by minimizing the sum of squares error. The performance of the MPSO is compared with other optimization methods including BPSO and Genetic Algorithm (GA) in offline parameter identification. The simulating results show that this algorithm not only has advantage of convergence property over BPSO and GA, but also can avoid the premature convergence problem effectively. The MPSO algorithm is also improved to detect and determine the variation of parameters. This novel algorithm is successfully applied for online parameter identification of suspension system.
Highlights
A mathematical model can be provided to describe the behavior of a system based on obtained data for its inputs and outputs by system identification
This paper presents a novel modified particle swarm optimization algorithm (MPSO) for both offline and online parametric identification of dynamic models
In order to show the effectiveness of the proposed MPSO in offline identification, it has been compared with Genetic Algorithm (GA) and basic PSO (BPSO)
Summary
A mathematical model can be provided to describe the behavior of a system based on obtained data for its inputs and outputs by system identification. Many traditional techniques for parameter identification have been studied such as the recursive least square [2], recursive prediction error [3], maximum likelihood [4], and orthogonal least square estimation [5] Despite their success in system identification, traditional optimization techniques have some fundamental problems including their dependence on unrealistic assumptions such as unimodal performance landscapes and differentiability of the performance function, and trapping in local minima [6]. Evolutionary algorithms (EAs) and swarm intelligence (SI) techniques seem to be promising alternatives as compared with traditional techniques They do not rely on any assumptions such as differentiability, continuity, or unimodality. The MPSO is compared to GA and BPSO in offline parameter identification of suspension system.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
