To improve PSO, differential evolution (DEA) and ant colony strategy are involved into PSO algorithm, and new PSO(DAPSO) is presented. Handling the current optimal positions of particles with differential evolution, the detecting and exploitation ability of both PSO and DEA are utilized effectively, and some potential evolution directions are constructed for each particle in PSO, at the same time a strategy is presented to choose which one may be the local best for PSO evolution process just like pheromone table in ant colony algorithm. It is shown by tested with well-known benchmark functions that DAPSO algorithm is better than PSO algorithm with linearly decreasing weight and differential evolution algorithm.