The antenna scanning period (ASP) of radar is a crucial parameter in electronic warfare (EW) which is used in many applications, such as radar work pattern recognition and emitter recognition. For antennas of radars and EW systems, which perform scanning circularly, the method based on threshold measurement is invalid. To overcome this shortcoming, this study proposes a method using the convolutional neural network (CNN) to recognize the ASP of radar under the condition that antennas of the radar and EW system both scan circularly. A system model is constructed, and factors affecting the received signal power are analyzed. A CNN model for rapid and accurate ASP radar classification is developed. A large number of received signal time–power images of three separate ASPs are used for the training and testing of the developed model under different experimental conditions. Numerical experiment results and performance comparison demonstrate high classification accuracy and effectiveness of the proposed method in the condition that antennas of radar and EW system are circular scan, where the average recognition accuracy for radar ASP is at least 90% when the signal to-noise ratio (SNR) is not less than 30 dB, which is significantly higher than the recognition accuracy of NAC and AFT methods based on adaptive threshold detection.

The antenna scan period is a core technical parameter of radar, and its robust, real-time, and high-precision measurement is of great engineering significance. Based on filed-measured full-pulse radar data, two measurement methods for the antenna scan period are proposed in this paper: the smoothing-fitting method and the smoothing-correlation method. Verified by filed-measured data, the measurement error fluctuation of the smoothing-fitting method is no more than 2 pulse repetition intervals (PRIs), and that of the smoothing-correlation method is no more than 1 PRI, both meeting the requirements of engineering applications. Adopting a point-by-point sliding processing flow without batch fitting, the smoothing-correlation method is more suitable for streaming and real-time data processing compared with the smoothing-fitting method and has a distinct engineering transformation value. Compared with batch processing methods such as the cepstrum method, which need to buffer data of at least one complete scanning period, the smoothing-correlation method avoids full-sequence FFT/IFFT operations. It can significantly reduce memory occupation and processing time and achieve superior real-time performance.