Firepower combat is a fundamental form of modern warfare and a key research area for enhancing the bat-tlefield operational capabilities of the Chinese military.In response to the traditional particle swarm optimization algorithm's applicability to continuous solution spaces and its tendency to fall into local optima,this paper proposes a hybrid particle swarm optimization algorithm that integrates the genetic algorithm.The crossover and mutation opera-tors are modified to fully utilize both the individual's current optimal values and the overall optimal values of the parti-cle swarm.In addition,the proposed algorithm incorporates the concept of simulated annealing and accepts inferior particles after crossover and mutation with a certain probability.It retains the rapid local search advantage of the par-ticle swarm optimization algorithm while possessing the global optimization performance of the genetic algorithm.The simulation results show that the hybrid particle swarm optimization algorithm has superior performance in firepower al-location of multi-platform and multi-weapon air and missile defense systems compared to the genetic algorithm.
air and missile defensemulti-platform and multi-weapon firepower allocationhybrid particle swarm optimization algorithm
NETL
NSTL
万方数据
