A Track Association Algorithm Combining Particle Swarm Optimization with Grey Theory

Due to the numerous enemy drones engaged in combat, it places a tremendous computing burden on our multi-sensor air information fusion system and causes intelligence delays. The grey analysis approach is used in this article to analyze the correlation between tracks based on the general scenario and similarity of the tracks by combining the particle swarm intelligence optimization algorithm with grey theory. The optimization approach for particle swarm intelligence has the advantage of swiftly solving several models. It optimizes the initial position of the particles and redefines particle velocity, The upgraded particle swarm technique is used to solve the flight path correlation problem in drone swarm combat situations. The grey correlation matrix between flight paths is derived via the grey theory analysis approach and input as a cost function. Following simulation validation, the enhanced particle swarm optimization algorithm significantly speeds up track association while also significantly addressing the drawbacks of the original particle swarm algorithms, such as their propensity for local optima and low track association accuracy when there are numerous targets.