engleski

Type-2 fuzzy adaptive particle swarm optimization

Aim of this work is to evaluate and model adaptive variant particle swarm optimization, PSO with help of fuzzy logic. Fuzzy logic is used for selection and ranking of particles of sub-swarms of particles and swarm in general (one particle represents one optimization solution). Type-1 fuzzy sets, T1-FS and type-2 fuzzy sets, T2-FS are used respectively. The membership function design of type-1 fuzzy logic system, T1-FLS leads to the difficulty of fuzzy rules database construction when representing linguistic part of knowledge. With type-2 fuzzy logic system, T2-FLS as the extension of T1-FLS, we can effectively improve knowledge representation by using the footprint of uncertainty of the membership functions. Because of this feature T2-FLS shows more flexibility than T1-FLS. For evaluation of the proposed model series of tests are made and results are compared with proven optimization algorithms (genetic algorithm, simulated annealing, particle swarm optimization …) on both single objective optimization problems. Results are shown to be comparative to other observe algorithm.

fuzzy logic; type-2 fuzzy set; adaptation; particle swarm optimization

nije evidentirano