A Study on Radar Emitter Recognition Based on SPDS Neural Network

摘要

With the rapid development of new type radar, it?s more difficult to recognize radar emitter signal. Trying to improve radar emitter recognition rate and reduce the processing time are the core of the research in this area. A new efficient radar emitter recognizer using Single Parameter Dynamic Search (SPDS) algorithm is proposed in this study. The SPDS algorithm is a modified algorithm of BP network and it only permits one of all parameters in the network to change during each epoch of searching step for parameters which guarantees to carry out the exact one-dimensional search. This algorithm can overcome the giant limits of BP algorithm such as local minimum and long training time. The effectiveness of SPDS algorithm is shown in simulation results. Compared with the classical neural network algorithms, the radar emitter signal can be recognized more accurately with the SPDS algorithm and the learning speed is improved greatly. The recognition rate is close to 100% under the condition of enough training times and uncomplicated data.