As the electromagnetic environment becomes more and more complex and changeable,it brings great challenges to electronic countermeasures.The traditional pulse description and signal recognition methods cannot meet the requirements of the battlefield.Aiming at the problem of accurate identification of radiation sources in complex electromagnetic environments,the phased array radar emitter is moded based on its microscopic features such as envelope and phase noise characteristics.A method for individual identification of radar radiation sources based on radar IF data and one-dimensional convolutional neural networks is proposed in combination with convolutional neural networks.A one-dimensional convolutional neural network is trained to learn and identify the effective features of radar radiation source signals.The recognition simulation experiments are conducted under different signal-to-noise ratio conditions with high recognition correct rates,which proves the effectiveness and feasibility of the method.