基于混合引导策略的高精度萤火虫优化粒子滤波算法

Firefly Algorithm with High Precision Mixed Strategy Optimized Particle Filter

针对现有群智能优化粒子滤波算法精度较低和收敛速度较慢的问题,提出了一种基于混合引导策略的萤火虫优化粒子滤波算法(MSFA-PF).通过在萤火虫寻优过程中加入混沌扰动搜索策略,以权衡粒子的寻优能力与开发能力;提出一种动态视觉搜索策略,以提高粒子向高似然区域移动的寻优利用率;根据粒子滤波机制设计了新的荧光亮度计算公式,以扩展观测信息,从而提高了粒子质量.仿真结果表明,所提出的MSFA-PF算法能够有效提高智能优化粒子滤波对非线性系统状态估计的精度和速度.

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.