Abstract: Aiming at the problem that the particle swarm optimization (PSO) algorithm tends to precocious convergence, a new algorithm of celestial system particle swarm optimization (CSPSO) is presented. With reference to the celestial system model in astronomy, the CSPSO algorithm divides the population into multiple independent celestial systems of which each and every one orbits in space in accordance with its own rules. The chaotic optimization is introduced in the later half of the algorithm to get the globe optimum solution. The CSPSO algorithm was applied to the identification of induction motor parameters, and the simulation results showed that it has higher identifiability parameters than GA and PSO algorithms.