Radar Emitter Recognition Based on PSO-BP Network

Abstract According to the problem of emitter characteristic parameters are showed by interval and uneasy to identify, an emitter fusion recognition method based on the PSO-BP neural network is proposed. The method train the network by training samples which are reasonable structured according to the distribution in the interval, so as to determine the network structure and confirm the emitter type through the emitter characteristics parameters. At the same time, the BP neural network is optimized by Particle Swarm Optimization (PSO) algorithm. The coding method of the network output, training data size and deviation rate on the influence of the recognition are researched by simulation, and the validity of this method are verified by the results.