Exo-atmospheric Discrimination of Infrared Ballistic Space Target Based on the Time-Delay Recurrent Neural Network: Exo-atmospheric Discrimination of Infrared Ballistic Space Target Based on the Time-Delay Recurrent Neural Network

This paper presents a Time-Delay Recurrent Neural Network (TDRNN) for exo-atmospheric ballistic space infrared target discrimination. The TDRNN employs adaptive time delays and recurrences where the adaptive time delays make the network choose the optimal values of time delays for the temporal location of important information in the input sequence, and the recurrences enable the network to have dynamic discrimination function. The IR radiation data of space target considering the sensor effect is simulated, taking into account the synthetic factors of heat parameter and motion, the space environment radiation and the sensor effect. The target discrimination experiment is developed, based on dynamic IR radiation simulated data of four typical ballistic space target. The simulation results show that TDRNN have better discrimination ability.