Radar Signal Intra-Pulse Modulation Recognition Based on Convolutional Neural Network and Deep Q-Learning Network
Intra-pulse modulation recognition of radar signals is an important part of modern electronic intelligence reconnaissance and electronic support systems. With the increasing density of radar signals, the analysis and processing of multi-component radar signals have become an urgent problem in the cu...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9033991/ |
| _version_ | 1818921188713299968 |
|---|---|
| author | Zhiyu Qu Chenfan Hou Changbo Hou Wenyang Wang |
| author_facet | Zhiyu Qu Chenfan Hou Changbo Hou Wenyang Wang |
| author_sort | Zhiyu Qu |
| collection | DOAJ |
| description | Intra-pulse modulation recognition of radar signals is an important part of modern electronic intelligence reconnaissance and electronic support systems. With the increasing density of radar signals, the analysis and processing of multi-component radar signals have become an urgent problem in the current radar reconnaissance system. In this paper, an intra-pulse modulation recognition approach for single-component and dual-component radar signals is proposed. First, in order to adapt to the time-frequency energy distribution characteristics of various radar signals, we propose to extract the time-frequency images (TFIs) of received signals by Cohen class time-frequency distribution (CTFD) with multiple kernel functions. Besides, the image processing methods are used to suppress noise and adjust the size and amplitude of the TFIs. Second, we design and pre-train a TFI feature extraction network for radar signals based on a convolutional neural network (CNN). Finally, to improve the probability of successful recognition (PSR) of the recognition system in the pulse overlapping environment, a multi-label classification network based on a deep Q-learning network (DQN) is explored. Besides, two sub-networks take TFIs based on special kernel functions as input and re-judge the recognition results of some specific signals to further enhance the recognition effect of the recognition system. The proposed approach can identify 8 kinds of random overlapping radar signals. The simulation results show that the overall PSR of dual-component radar signals and single-component radar signals can reach 94.83% and 94.43%, respectively, when the signal-to-noise ratio (SNR) is -6 dB. |
| first_indexed | 2024-12-20T01:33:41Z |
| format | Article |
| id | doaj.art-1f0cdc9fff2f4a3cb47a67b3b1002ac8 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T01:33:41Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1f0cdc9fff2f4a3cb47a67b3b1002ac82022-12-21T19:58:04ZengIEEEIEEE Access2169-35362020-01-018491254913610.1109/ACCESS.2020.29803639033991Radar Signal Intra-Pulse Modulation Recognition Based on Convolutional Neural Network and Deep Q-Learning NetworkZhiyu Qu0https://orcid.org/0000-0002-4823-0396Chenfan Hou1https://orcid.org/0000-0003-1602-0674Changbo Hou2https://orcid.org/0000-0002-6421-3481Wenyang Wang3https://orcid.org/0000-0003-4744-0268College of Information and Communication Engineering, Harbin Engineering University, Harbin, ChinaCollege of Information and Communication Engineering, Harbin Engineering University, Harbin, ChinaCollege of Information and Communication Engineering, Harbin Engineering University, Harbin, ChinaCollege of Information and Communication Engineering, Harbin Engineering University, Harbin, ChinaIntra-pulse modulation recognition of radar signals is an important part of modern electronic intelligence reconnaissance and electronic support systems. With the increasing density of radar signals, the analysis and processing of multi-component radar signals have become an urgent problem in the current radar reconnaissance system. In this paper, an intra-pulse modulation recognition approach for single-component and dual-component radar signals is proposed. First, in order to adapt to the time-frequency energy distribution characteristics of various radar signals, we propose to extract the time-frequency images (TFIs) of received signals by Cohen class time-frequency distribution (CTFD) with multiple kernel functions. Besides, the image processing methods are used to suppress noise and adjust the size and amplitude of the TFIs. Second, we design and pre-train a TFI feature extraction network for radar signals based on a convolutional neural network (CNN). Finally, to improve the probability of successful recognition (PSR) of the recognition system in the pulse overlapping environment, a multi-label classification network based on a deep Q-learning network (DQN) is explored. Besides, two sub-networks take TFIs based on special kernel functions as input and re-judge the recognition results of some specific signals to further enhance the recognition effect of the recognition system. The proposed approach can identify 8 kinds of random overlapping radar signals. The simulation results show that the overall PSR of dual-component radar signals and single-component radar signals can reach 94.83% and 94.43%, respectively, when the signal-to-noise ratio (SNR) is -6 dB.https://ieeexplore.ieee.org/document/9033991/Radar signal recognitionCohen class time-frequency distributionconvolutional neural networkdeep Q-learning network |
| spellingShingle | Zhiyu Qu Chenfan Hou Changbo Hou Wenyang Wang Radar Signal Intra-Pulse Modulation Recognition Based on Convolutional Neural Network and Deep Q-Learning Network IEEE Access Radar signal recognition Cohen class time-frequency distribution convolutional neural network deep Q-learning network |
| title | Radar Signal Intra-Pulse Modulation Recognition Based on Convolutional Neural Network and Deep Q-Learning Network |
| title_full | Radar Signal Intra-Pulse Modulation Recognition Based on Convolutional Neural Network and Deep Q-Learning Network |
| title_fullStr | Radar Signal Intra-Pulse Modulation Recognition Based on Convolutional Neural Network and Deep Q-Learning Network |
| title_full_unstemmed | Radar Signal Intra-Pulse Modulation Recognition Based on Convolutional Neural Network and Deep Q-Learning Network |
| title_short | Radar Signal Intra-Pulse Modulation Recognition Based on Convolutional Neural Network and Deep Q-Learning Network |
| title_sort | radar signal intra pulse modulation recognition based on convolutional neural network and deep q learning network |
| topic | Radar signal recognition Cohen class time-frequency distribution convolutional neural network deep Q-learning network |
| url | https://ieeexplore.ieee.org/document/9033991/ |
| work_keys_str_mv | AT zhiyuqu radarsignalintrapulsemodulationrecognitionbasedonconvolutionalneuralnetworkanddeepqlearningnetwork AT chenfanhou radarsignalintrapulsemodulationrecognitionbasedonconvolutionalneuralnetworkanddeepqlearningnetwork AT changbohou radarsignalintrapulsemodulationrecognitionbasedonconvolutionalneuralnetworkanddeepqlearningnetwork AT wenyangwang radarsignalintrapulsemodulationrecognitionbasedonconvolutionalneuralnetworkanddeepqlearningnetwork |