Two-Stage Neural Network Based Combined Interference Classification and Recognition for a GNSS Receiver

Abstract

Under the complex war environment based on Global Navigation Satellite Systems (GNSS), suppression interference and spoofing interference would be used in combination by enemy. Thus, the difficulty of interference detection and recognition in the receiver could increase significantly due to the uncertain appearance of these two categories of attacking signals. Aiming to this issue, a BP (Back Propagation) neural network based two-stage interference classification and recognition scheme is proposed towards the combined interference scenario with suppression interference and spoofing. Both networks utilize a three-layer fully connected neural network to realize classifying decisions. The first-stage recognition module adopt nine characteristic parameters extracted from time, frequency and power domains of the digital intermediate frequency (IF) signals, which are fed into a BP neural network, to recognize six typical suppression interferences, such as Single Tone Interference (STI), Multi-Tone Interference (MTI), Linear Frequency Modulation Interference (LFMI), Pulse Interference (PI), BPSK Narrowband Interference (BPSKNBI) and BPSK Wideband Interference (BPSK WBI). However, since spoofing interference has the similar structure as the true satellite signal, the second-stage recognition module is introduced to distinguish the spoofing signal from the true satellite signal by using eleven new characteristic parameters extracted from the two-dimensional array output by the acquisition processing of a receiver. The test results show that the proposed scheme can recognize a kind of suppression interference or a spoofing signal appeared randomly more quickly and accurately.