1.School of Automobile and Traffic Engineering, Wuhan University of Science and Technology;2.School of Logistics Engineering，Wuhan University of Technology
To solve the contradiction between population diversity and convergence in Particle Swarm Optimization, an improved particle swarm optimization which called dynamic multi-population particle swarm optimization algorithm with recombined learning and hybrid mutation was proposed. In the proposed algorithm, a population was divided dynamically and a new particle was reconstructed as a guiding factor. It retained the spatial information of the excellent particles while increasing population diversity. During the execution of the algorithm, a hybrid mutation strategy was applied to adjust the optimal solution. A opposition-based learning and a neighborhood-disturbance operations were implemented based on a time-varying probability. It helped the particles jump out of the local dilemma quickly, and strengthened good searching in the nearby areas. The effectiveness and superposition effects of several proposed improvement operations compared with several improved particle swarm algorithms based on a set of 14 multi-type benchmark functions were verified. In order to further explore the sensitivity of probability-based hybrid mutation strategy, a large number of simulation experiments were carried out to analyze the mutation mode and parameter settings. The results showed that the disturbed extreme strategy had significant advantages. Controlling the learning intensity reasonably can make the opposition-based learning show better performances, furthermore, a suggersted value range was given. Finally, experimental results indicated that the proposed algorithm can get a better balance betweetn the exploitation and exploration for the swarm searching and improve the solution accuracy and convergence performance.