# A New Structure for Particle Swarm Optimization (nPSO) Applicable to Single Objective and Multiobjective Problems

Zhang, Qian and Mahfouf, Mahdi (2006) A New Structure for Particle Swarm Optimization (nPSO) Applicable to Single Objective and Multiobjective Problems. In: 2006 3rd International IEEE Conference Intelligent Systems. IEEE, pp. 176-181. ISBN 1-4244-0195-X. (doi:10.1109/IS.2006.348413) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided) (KAR id:50555)

 The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided. Official URLhttp://doi.org/10.1109/IS.2006.348413

## Abstract

This paper presents a new optimization algorithm based on particle swarm optimization (PSO). The new contribution relates to the introduction of a new momentum term' which is known to influence the convergence properties of the original PSO algorithm. It is shown that the new algorithm structure, named nPSO, can solve the problem of premature convergence, widely experienced in the original PSO algorithm, and also can make the particles' optimal search process truly' adaptive. The proposed algorithm is validated via well-known challenging functions and is found to be more efficient than the original PSO algorithm. Furthermore, the algorithm is extended to include the multiobjective case via dynamic weighted aggregation (DWA) and the maintaining of an archive to preserve the Pareto optimal solutions. The new algorithm, named new multiobjective PSO (nMPSO), it also compared to well-known evolutionary multiobjective algorithms based on a series of challenging benchmark multiobjective functions. Results obtained hitherto suggest that nMPSO can locate the Pareto-optimal front and performs better than other salient optimization algorithms.

Item Type: Book section 10.1109/IS.2006.348413 particle swarm optimization; convergence; intelligent systems; intelligent structures; evolutionary computation; computational modeling; animals; birds; systems engineering and theory; equations Q Science > Q Science (General) > Q335 Artificial intelligenceT Technology > TA Engineering (General). Civil engineering (General) > TA168 Systems engineeringT Technology > TA Engineering (General). Civil engineering (General) > TA401 Materials engineering and construction Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Engineering and Digital Arts Qian Zhang 18 Sep 2015 16:40 UTC 16 Nov 2021 10:21 UTC https://kar.kent.ac.uk/id/eprint/50555 (The current URI for this page, for reference purposes)