High-frequency radar aircraft detection method based on neural networks and time-frequency algorithm

Aircraft detection is an important application of Wuhan Ionosonde Sounding System (WISS), which recently has been developed by the Ionospheric Laboratory of Wuhan University. Since the ionosphere varies temporally and spatially, severe multipath effects are produced, which jeopardise the characteristic quantities extracting of targets from the recorded data. To solve the above problems and further identify the targets from the fuzzy signals, this study presents a neural networks and time-frequency-based algorithm. By neural networks, the characteristic quantities of targets are extracted from the recorded data, and then, the Doppler spectrum of target signals is computed to determine the radial velocity of targets. Moreover, with the help of time-frequency analysis, the radial velocity variability in time domain can be identified, which finally leads to the identification of the type of the targets. Simulations using the recorded data of the WISS show that the type of the targets is aircraft and 90.9% accurate recognition of aircraft targets can be achieved.