• Electronics Technology •

### Parity recognition of blade number and manoeuvre intention classification algorithm of rotor target based on micro-Doppler features using CNN

Wantian WANG(), Ziyue TANG(), Yichang CHEN*(), Yongjian SUN()

• Received:2019-07-05 Online:2020-10-30 Published:2020-10-30
• Contact: Yichang CHEN E-mail:laodifang0120@126.com;tang_zi_yue@163.com;cyc_2007@163.com;bmdsun@126.com
• About author:WANG Wantian was born in 1992. He received his B.E. and M.S. degrees in radar engineering and information and communication engineering from Air Force Early Warning Academy in 2015 and 2017, respectively. He is currently pursuing his Ph.D. degree in Air Force Early Warning Academy. His current research interests include radar signal processing and target classification and recognition. E-mail: laodifang0120@126.com|TANG Ziyue was born in 1966. He received his M.S. and Ph.D. degrees from Air Force Early Warning Academy and Naval Engineering University, Wuhan, China in 1990 and 2000, respectively. He is currently a professor of Air Force Early Warning Academy. His current research interests include radarsignal processing, anti-interference, target detection and imaging, and radar automatic target recognition. E-mail: tang_zi_yue@163.com|CHEN Yichang was born in 1988. He received his M.S. and Ph.D. degrees in electronic engineering from the Institute of Information and Navigation, Air Force Engineering University, Xi'an, China in 2013 and 2017, respectively. From 2014 to 2017, he was a visiting scholar at Tsinghua University, Beijing, China. Since 2018, he has been with the faculty of Air Force Early Warning Academy, China, where he is currently a lecturer. His current research interests include radar imaging, compressed sensing and radar automatic target recognition. E-mail: cyc_2007@163.com|SUN Yongjian was born in 1976. He received his Ph.D. degree in the Second Academy of China Aerospace Science and Industry Co. Ltd., Beijing, China, in 2014. He is currently an instructor in Air Force Early Warning Academy. His current research interests include compressive sensing, radar signal processing and AI based automatic target recognition. E-mail: bmdsun@126.com
• Supported by:
the National Natural Science Foundation of China(61901514);the Young Talent Program of Air Force Early Warning Academy(TJRC425311G11);This work was supported by the National Natural Science Foundation of China (61901514) and the Young Talent Program of Air Force Early Warning Academy (TJRC425311G11)

Abstract:

This paper proposes a parity recognition of blade number and manoeuvre intention classification algorithm of rotor target based on the convolutional neural network (CNN) using micro Doppler features. Firstly, the time-frequency spectrograms are acquired from the radar echo by the short-time Fourier transform. Secondly, based on the obtained spectrograms, a seven-layer CNN architecture is built to recognize the blade-number parity and classify the manoeuvre intention of the rotor target. The constructed architecture contains a leaky rectified linear unit and a dropout layer to accelerate the convergence of the architecture and avoid over-fitting. Finally, the spectrograms of the datasets are divided into three different ratios, i.e., 20%, 33% and 50%, and the cross validation is used to verify the effectiveness of the constructed CNN architecture. Simulation results show that, on the one hand, as the ratio of training data increases, the recognition accuracy of parity and manoeuvre intention is improved at the same signal-to-noise ratio (SNR); on the other hand, the proposed algorithm also has a strong robustness: the accuracy can still reach 90.72% with an SNR of – 6 dB.