Abstract
Abstract
The traditional CSO algorithm is easy to fall into local extremum in optimization. In this paper, a CSO algorithm based on weight coefficient is proposed. In the CSO algorithm, the inertia weight coefficient is introduced into the hen position formula, and the learning factor influenced by the rooster is added to the chick position formula. Finally, using the idea of heredity, individuals with excellent fitness value are selected for crossover and mutation with a certain probability. Through the simulation comparison of five typical test functions, the simulation results show that the improved CSO algorithm can avoid local optimization, strengthen the global extreme value search ability, and improve the convergence speed and accuracy range of the algorithm.
Subject
General Physics and Astronomy
Reference7 articles.
1. A Multiswarm Intelligence Algorithm for Expensive Bound Constrained Optimization Problems[J];Mashwani;Complexity,2021
2. An adaptive location-aware swarm intelligence optimization algorithm[J];Jiang;International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems,2021
3. Projection pursuit model for evaluation of flood and drought disasters based on chicken swarm optimization algorithm[J];Cui,2016
4. EXTRACTING DESIGN RECOMMENDATIONS FROM INTERACTIVE GENETIC ALGORITHM EXPERIMENTS: APPLICATION TO THE DESIGN OF SOUNDS FOR ELECTRIC VEHICLES[J];Souaille,2021