Abstract: Aiming at the problem of the low precision and slow convergence rate of particle filters based on intelligent optimization algorithms, this paper came up with a firefly algorithm with mixed strategy optimized particle filter. The algorithm is applied to the chaotic perturbation search strategy in the firefly optimization mechanism for balancing the particle optimization ability effectively, and proposed dynamic visual search strategy to improve the utilization ratio of particles moving toward high likelihood regions. At the same time, according to the particle filter mechanism, a new fluorescence luminance formula is designed to expand the observation information for improving the particles quality. Experiment results show that the proposed algorithm effectively improves the accuracy and speed of the intelligent optimization particle filter for nonlinear system state estimation.

Key words: particle filter, firefly algorithm, chaotic perturbation, dynamic visual, search strategy