Cone-Shaped Space Target Inertia Characteristics Identification by Deep Learning with Compressed Dataset

Abstract

An effective method for identifying inertia characteristics of cone-shaped space target based on deep learning is proposed. The inertia ratio is determined by the time-varying scattering fields from the cone-shaped targets. The multistatic method is introduced to reduce the evaluation time of time-varying scattering fields. The micro-Doppler spectrogram (MDS) dataset is constructed by time-frequency analysis with numerical simulation method, point scattering model, and experimental tests. The compressed dataset is further achieved by truncated singular value decomposition (SVD). Finally, the micro-motion parameter identification model is constructed to identify the inertia ratio for the cone-shaped space target. The interaction loss function and the feed-forward denoising convolutional neural networks (DnCNNs) are employed to improve the identification accuracy. Parameters identification of the precession frequency, precession angle, spin frequency, and inertia ratio with both simulation and experiment datasets demonstrate the validity of the proposed method.