Abstract: This paper studies on the classification issue of turbojet, propeller and helicopter targets by using the conventional radar system. Based on the micro-Doppler effect, the echo signal model for the rotating parts of aircrafts is analyzed theoretically via the multi-scattering center model firstly. Then according to the differences between the frequency modulation properties of the three kinds of airplanes in the Doppler domain, a new feature extraction method is proposed based on the Empirical Mode Decomposition (EMD) algorithm. Finally, the experimental results with the simulated training data, the measured test data and the Support Vector Machine (SVM) show the proposed method can achieve good classification performance under the test condition of relatively high Signal-to-Noise Ratio (SNR).