Implementation method of Metropolis-Hastings variation particle swarm resampling particle filter

Abstract

The invention relates to an implementation method of a particle swarm resampling particle filter based on Metropolis-Hastings variation. The invention provides the implementation method of the particle swarm resampling particle filter based on the Metropolis-Hastings variation so as to solve the problem that estimated accuracy of a particle filter is not high when the number of particles is small. The implementation method enables Metropolis-Hastings (MH) movement to be used as a variation operator of particle swarm optimization, an MH variation rule is combined with a speed-position search process of a particle swarm, a resampled particle swarm is more approximate to a real posterior probability density distribution, the problem that a common variation particle swarm algorithm diverges easily is effectively solved, a convergence speed of the particle filter in a sequential estimation process is accelerated, and estimation accuracy of the particle filter is improved. Proved by a simulation test, the particle swarm optimization particle filter based on the Metropolis-Hastings variation can effectively overcome the phenomenon of particle depletion and improve tracking and estimating effects of a nonlinear system.

Description

technical field [0001] The invention belongs to the field of digital signal processing, more specifically relates to the field of nonlinear filtering, and provides a particle filter resampling and a method for realizing the particle filter. Background technique [0002] Particle filters are widely used in non-Gaussian and nonlinear system state estimation, especially in navigation guidance, target tracking, financial analysis, artificial intelligence, blind signal processing and other fields. However, an unavoidable problem in the particle filter is the phenomenon of particle degeneration (Particle Degeneracy), that is, after several iterations of the particle set, except for a few particles, most of the particles have only tiny weights (a small particle weight means The contribution to the posterior probability density is small), and the particles with small weights also need to participate in subsequent iterative calculations, which increases the amount of useless calculat...

AI Technical Summary

Problems solved by technology

However, the research of Kennedy.J (1995) shows that the standard particle swarm optimization algorithm has premature convergence phenomenon, and it is easy to fall into the local optimal solution

In response to this problem, Lu Zhensu (2004), Wang Haifeng (2009), and Chen Jianchao (2009) proposed the improvement of ordinary mutation particle swarm optimization, which enhanced the ability of particle swarm to jump out of the local optimal solution, but they did not consider The probability density distribution of the state, which in turn increases the risk of divergence after mutation

Images