Resemblance coefficient based intrapulse feature extraction approach for radar emitter signals

Radar emitter signal recognition plays an important role in electronic intelligence and electronic support measure systems. To enhance accurate recognition rate of advanced radar emitter signals to meet the requirement of modern electronic warfare, Resemblance coefficient (RC) approach is proposed to extract features from radar emitter signals with different intrapulse modulation laws. Definition of RC is given. Properties and advantages of RC are analyzed. Feature extraction algorithm using RC is described in detail. The noise-suppression performances of RC features are also analyzed. Subsequently, neural networks are used to design classifiers. Because RC contains the change and distribution information of amplitude, phase and frequency of radar emitter signals, RC can reflect the intrapulse modulation laws effectively. The results of theoretical analysis and simulation experiments show that RC features have good characteristic of not being sensitive to noise. 9 radar emitter signals are chosen to make the experiment of RC feature extraction and automatic recognition. A large number of experimental results show that good accurate recognition rate can be achieved using the proposed approach. It is proved to be a valid and practical approach.