Multi-function Radar Behavior State Detection Algorithm based on Bayesian Criterion

Abstract

An iterative detection algorithm, based on fixed length sliding window, is proposed for multi-function phased array radar (MPAR) behavior recognition. First, characteristic parameters such as frequency, pulse width, pulse amplitude, pulse repetition interval and beam orientation were extracted. Then the pulse sequence is divided by sliding the appropriate fixed-length window. Finally, the conditional probability is calculated step by step based on Bayesian criterion, and the probability result is compared with the previous probability to determine whether it is a change point. This approach can be applied to radar behavior recognition without prior knowledge. The effectiveness of the proposed approach is demonstrated by simulation results.