Application of particle swarm optimization algorithm- based fuzzy BP neural network for target damage assessment

It has proposed a kind of hybrid method based on intuitionistic fuzzy set theory and particle swarm optimization (PSO) algorithm-based neural network (NN). We apply it to the integrative damage effect assessment of battlefield target. Firstly, we improve PSO algorithm, propose the adaptive inertia factor and excellence selection mechanism, introduce inter-partition particle swarm initialization and simulated annealing mutation mechanism. Secondly, we use the improved PSO algorithm to optimize the initial weights and thresholds of neural network to improve the network structure. Thirdly, we carry on the fusion of multiple different neural networks based on intuitionistic fuzzy set theory. The purpose of this study is to determine the weight of different neural networks, and synthesize their assessment result has the final output according to the weight. The effectiveness and reasonableness of algorithm are improved by simulation results.