Work Mode Identification of Phased Array Radar with Denoising Auto-encoder

Authors

Haodong Liu, School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China;
Weidong Jin, School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China;
Chunli Chen, School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China;
Cai Jian, School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China;

Abstract

Abstract: A new method to recognize phased array radar in different work modes was proposed based on multi-level modeling combined with Marginalized Stacked Denoising Auto-encoder. In order to analyze the change law of pulses intercepted by surveillance radar, multi-level modeling was proposed to model the pulses at pulse level, pulse group level and work mode level. Marginalized stacked denoising auto-encoder was trained to extract amplitude characteristics at the work mode level. SVM (Support Vector Machine) was added to the top of deep network to realize work mode identification of phased array radar. Qualitative experiments show that the new method is able to extract essential characteristics of the input with its accuracy over 95%, which provides a new idea for mode identification of phased array radar.

Recommended Citation

Liu, Haodong; Jin, Weidong; Chen, Chunli; and Jian, Cai (2020) "Work Mode Identification of Phased Array Radar with Denoising Auto-encoder," Journal of System Simulation: Vol. 29: Iss. 9, Article 12.
DOI: 10.16182/j.issn1004731x.joss.201709012
Available at: https://dc-china-simulation.researchcommons.org/journal/vol29/iss9/12

First Page

1960

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.201709012

Last Page

1967

CLC

TP183

Recommended Citation

Liu Haodong, Jin Weidong, Chen Chunli, Cai Jian. Work Mode Identification of Phased Array Radar with Denoising Auto-encoder[J]. Journal of System Simulation, 2017, 29(9): 1960-1967.

DOI

10.16182/j.issn1004731x.joss.201709012