LPI Radar Waveform Recognition Based on Features from Multiple Images

Detecting and classifying the modulation type of the intercepted noisy LPI (low probability of intercept) radar signals in real-time is a necessary survival technique in the electronic intelligence systems. Most radar signals have been designed to have LPI properties; therefore, the LPI radar waveform recognition technique (LWRT) has recently gained increasing attention. In this paper, we propose a multiple feature images joint decision (MFIJD) model with two different feature extraction structures that fully extract the pixel feature to obtain the pre-classification results of each feature image for the non-stationary characteristics of most LPI radar signals. The core technology of this model is combining the short-time autocorrelation feature image, double short-time autocorrelation feature image and the original signal time-frequency image (TFI) simultaneously input into the hybrid model classifier, which is suitable for non-stationary signals, and it has higher universality. We demonstrate the performance of MFIJD by simulating 11 types of the signals defined in this paper and generating training sets and test sets. The comparison with the literature shows that the proposed methods not only has a high universality for LPI radar signals, but also better adapts to LPI radar waveform recognition at low SNR (signal to noise ratio) environment. The overall recognition rate of the method reaches 87.7% when the SNR is −6 dB.

Download Full-text

A Radar Signal Recognition Approach via IIF-Net Deep Learning Models

Computational Intelligence and Neuroscience ◽

10.1155/2020/8858588 ◽

2020 ◽

Vol 2020 ◽

pp. 1-8

Author(s):

Ji Li ◽

Huiqiang Zhang ◽

Jianping Ou ◽

Wei Wang

Keyword(s):

Recognition Accuracy ◽

Signal To Noise Ratio ◽

Recognition Rate ◽

Software Radio ◽

Radar Signal ◽

Signal Recognition ◽

Electromagnetic Environment ◽

Time Frequency ◽

Low Snr ◽

Radar Signals

In the increasingly complex electromagnetic environment of modern battlefields, how to quickly and accurately identify radar signals is a hotspot in the field of electronic countermeasures. In this paper, USRP N210, USRP-LW N210, and other general software radio peripherals are used to simulate the transmitting and receiving process of radar signals, and a total of 8 radar signals, namely, Barker, Frank, chaotic, P1, P2, P3, P4, and OFDM, are produced. The signal obtains time-frequency images (TFIs) through the Choi–Williams distribution function (CWD). According to the characteristics of the radar signal TFI, a global feature balance extraction module (GFBE) is designed. Then, a new IIF-Net convolutional neural network with fewer network parameters and less computation cost has been proposed. The signal-to-noise ratio (SNR) range is −10 to 6 dB in the experiments. The experiments show that when the SNR is higher than −2 dB, the signal recognition rate of IIF-Net is as high as 99.74%, and the signal recognition accuracy is still 92.36% when the SNR is −10 dB. Compared with other methods, IIF-Net has higher recognition rate and better robustness under low SNR.

Download Full-text

Radar Emitter Recognition Based on the Energy Cumulant of Short Time Fourier Transform and Reinforced Deep Belief Network

Sensors ◽

10.3390/s18093103 ◽

2018 ◽

Vol 18 (9) ◽

pp. 3103 ◽

Cited By ~ 11

Author(s):

Xuebao Wang ◽

Gaoming Huang ◽

Zhiwen Zhou ◽

Wei Tian ◽

Jialun Yao ◽

...

Keyword(s):

Fourier Transform ◽

Signal To Noise Ratio ◽

Recognition Rate ◽

Deep Belief Network ◽

Short Time Fourier Transform ◽

Belief Network ◽

Time Frequency ◽

Low Snr ◽

Emitter Recognition ◽

Short Time

To cope with the complex electromagnetic environment and varied signal styles, a novel method based on the energy cumulant of short time Fourier transform and reinforced deep belief network is proposed to gain a higher correct recognition rate for radar emitter intra-pulse signals at a low signal-to-noise ratio. The energy cumulant of short time Fourier transform is attained by calculating the accumulations of each frequency sample value with the different time samples. Before this procedure, the time frequency distribution via short time Fourier transform is processed by base noise reduction. The reinforced deep belief network is proposed to employ the input feature vectors for training to achieve the radar emitter recognition and classification. Simulation results manifest that the proposed method is feasible and robust in radar emitter recognition even at a low SNR.

Download Full-text

Emitter Signal Waveform Classification Based on Autocorrelation and Time-Frequency Analysis

Electronics ◽

10.3390/electronics8121419 ◽

2019 ◽

Vol 8 (12) ◽

pp. 1419 ◽

Cited By ~ 1

Author(s):

Zhiyuan Ma ◽

Zhi Huang ◽

Anni Lin ◽

Guangming Huang

Keyword(s):

Hybrid Model ◽

Signal To Noise Ratio ◽

Recognition Rate ◽

Complete Classification ◽

Construction Technique ◽

Electronic Warfare ◽

Image Construction ◽

Time Frequency ◽

Low Snr ◽

Signal Waveform

Emitter signal waveform recognition and classification are necessary survival techniques in electronic warfare systems. The emitters use various techniques for power management and complex intra-pulse modulations, which can create what looks like a noisy signal to an intercept receiver, so emitter signal waveform recognition at a low signal-to-noise ratio (SNR) has gained increased attention. In this study, we propose an autocorrelation feature image construction technique (ACFICT) combined with a convolutional neural network (CNN) to maintain the unique feature of each signal, and a structure optimization for CNN input layer called hybrid model is designed to achieve image enhancement of the signal autocorrelation, which is different from using a single image combined with CNN to complete classification. We demonstrate the performance of ACFICT by comparing feature images generated by different signal pre-processing algorithms, and the evaluation indicators are signal recognition rate, image stability degree, and image restoration degree. This paper simulates six types of the signals by combining ACFICT with three types of hybrid model, the simulation results compared with the literature show that the proposed methods not only has a high universality, but also better adapts to waveform recognition at low SNR environment. When the SNR is –6 dB, the overall recognition rate of the method reaches 88%.

Download Full-text

Detection of Polyphase Codes Radar Signals in Low SNR

Mathematical Problems in Engineering ◽

10.1155/2016/1382960 ◽

2016 ◽

Vol 2016 ◽

pp. 1-6 ◽

Cited By ~ 2

Author(s):

Runlan Tian ◽

Guoyi Zhang ◽

Rui Zhou ◽

Wei Dong

Keyword(s):

Hough Transform ◽

Signal To Noise Ratio ◽

Superior Performance ◽

Radar Signal ◽

Time Frequency ◽

Low Snr ◽

Radar Signals ◽

Core Idea ◽

Code Type ◽

Electronic Intelligence

A novel effective detection method is proposed for electronic intelligence (ELINT) systems detecting polyphase codes radar signal in the low signal-to-noise ratio (SNR) scenario. The core idea of the proposed method is first to calculate the time-frequency distribution of polyphase codes radar signals via Wigner-Ville distribution (WVD); then the modified Hough transform (HT) is employed to cumulate all the energy of WVD’s ridges effectively to achieve signal detection. Compared with the generalised Wigner Hough transform (GWHT) method, the proposed method has a superior performance in low SNR and is not sensitive to the code type. Simulation results verify the validity of the proposed method.

Download Full-text

LPI Radar Waveform Recognition Based on CNN and TPOT

Symmetry ◽

10.3390/sym11050725 ◽

2019 ◽

Vol 11 (5) ◽

pp. 725 ◽

Cited By ~ 5

Author(s):

Jian Wan ◽

Xin Yu ◽

Qiang Guo

Keyword(s):

Signal To Noise Ratio ◽

Recognition Rate ◽

Recognition System ◽

Radar Signal ◽

Automatic Identification ◽

Identification System ◽

Electronic Warfare ◽

Time Frequency ◽

Barker Codes ◽

Intelligence Support

The electronic reconnaissance system is the operational guarantee and premise of electronic warfare. It is an important tool for intercepting radar signals and providing intelligence support for sensing the battlefield situation. In this paper, a radar waveform automatic identification system for detecting, tracking and locating low probability interception (LPI) radar is studied. The recognition system can recognize 12 different radar waveform: binary phase shift keying (Barker codes modulation), linear frequency modulation (LFM), Costas codes, polytime codes (T1, T2, T3, and T4), and polyphase codes (comprising Frank, P1, P2, P3 and P4). First, the system performs time–frequency transform on the LPI radar signal to obtain a two-dimensional time–frequency image. Then, the time–frequency image is preprocessed (binarization and size conversion). The preprocessed time–frequency image is then sent to the convolutional neural network (CNN) for training. After the training is completed, the features of the fully connected layer are extracted. Finally, the feature is sent to the tree structure-based machine learning process optimization (TPOT) classifier to realize offline training and online recognition. The experimental results show that the overall recognition rate of the system reaches 94.42% when the signal-to-noise ratio (SNR) is −4 dB.

Download Full-text

Robust estimation of instantaneous phase using a time-frequency adaptive filter

Geophysics ◽

10.1190/geo2011-0435.1 ◽

2013 ◽

Vol 78 (1) ◽

pp. O1-O7 ◽

Cited By ~ 5

Author(s):

Wen-kai Lu ◽

Chang-Kai Zhang

Keyword(s):

Adaptive Filter ◽

Signal To Noise Ratio ◽

Amplitude Spectrum ◽

Estimation Method ◽

Frequency Component ◽

Data Sets ◽

Time Frequency ◽

Instantaneous Phase ◽

The Hilbert Transform ◽

Short Time

The instantaneous phase estimated by the Hilbert transform (HT) is susceptible to noise; we propose a robust approach for the estimation of instantaneous phase in noisy situations. The main procedure of the proposed method is applying an adaptive filter in time-frequency domain and calculating the analytic signal. By supposing that one frequency component with higher amplitude has higher signal-to-noise ratio, a zero-phase adaptive filter, which is constructed by using the time-frequency amplitude spectrum, enhances the frequency components with higher amplitudes and suppresses those with lower amplitudes. The estimation of instantaneous frequency, which is defined as the derivative of instantaneous phase, is also improved by the proposed robust instantaneous phase estimation method. Synthetic and field data sets are used to demonstrate the performance of the proposed method for the estimation of instantaneous phase and frequency, compared by the HT and short-time-Fourier-transform methods.

Download Full-text

Separation of Intercepted Multi-Radar Signals Based on Parameterized Time-Frequency Analysis

Frequenz ◽

10.1515/freq-2015-0253 ◽

2016 ◽

Vol 70 (9-10) ◽

Author(s):

W. L. Lu ◽

J. W. Xie ◽

H. M. Wang ◽

C. Sheng

Keyword(s):

Frequency Analysis ◽

Simulated Data ◽

Radar Signal ◽

Electronic Warfare ◽

Time Frequency Analysis ◽

Time Frequency ◽

Frequency Domains ◽

Stationary Signals ◽

Radar Signals ◽

Electronic Intelligence

AbstractModern radars use complex waveforms to obtain high detection performance and low probabilities of interception and identification. Signals intercepted from multiple radars overlap considerably in both the time and frequency domains and are difficult to separate with primary time parameters. Time–frequency analysis (TFA), as a key signal-processing tool, can provide better insight into the signal than conventional methods. In particular, among the various types of TFA, parameterized time-frequency analysis (PTFA) has shown great potential to investigate the time–frequency features of such non-stationary signals. In this paper, we propose a procedure for PTFA to separate overlapped radar signals; it includes five steps: initiation, parameterized time-frequency analysis, demodulating the signal of interest, adaptive filtering and recovering the signal. The effectiveness of the method was verified with simulated data and an intercepted radar signal received in a microwave laboratory. The results show that the proposed method has good performance and has potential in electronic reconnaissance applications, such as electronic intelligence, electronic warfare support measures, and radar warning.

Download Full-text

The Gearbox Fault Detection of Machine Center by Using Time Frequency Order Spectrum

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.452-453.1329 ◽

2012 ◽

Vol 452-453 ◽

pp. 1329-1333 ◽

Cited By ~ 1

Author(s):

C.C. Wang ◽

Y. Kang ◽

Y.L. Chung

Keyword(s):

Fault Detection ◽

Back Propagation ◽

Machine Center ◽

Rotor Systems ◽

Time Frequency ◽

Order Spectrum ◽

Signal Features ◽

Stationary Signals ◽

Short Time ◽

Frequency Features

Previously, for the case of fixed or steady state rotation rate, spectrum analysis can be used to extract the frequency features as the basis for the gearbox fault detection of machine center. However, the gearbox of machine center for increasingly instant speed variations mostly generate non-stationary signals, and the signal features must be averaged with analysis time which makes it difficult to identify the causes of failures. This study proposes a time frequency order spectrum method combining the short-time Fourier transform (STFT) and speed frequency order method to capture the order features of non-stationary signals. Such signal features do not change with speed, and are thus effective in identifying faults in mechanical components under non-stationary conditions. In this study, back propagation neural networks (BPNN) and time frequency order spectrum methods were used to verify faults diagnosis and obtained superior diagnosis results in non-stationary signals of gear-rotor systems in machine center.

Download Full-text

Selection of window for inter-pulse analysis of simple pulsed radar signal using the short time Fourier transform

International Journal of Engineering & Technology ◽

10.14419/ijet.v4i4.5139 ◽

2015 ◽

Vol 4 (4) ◽

pp. 531 ◽

Cited By ~ 1

Author(s):

Ashraf Adamu Ahmad ◽

Abdullahi Daniyan ◽

David Ocholi Gabriel

Keyword(s):

Fourier Transform ◽

Signal To Noise Ratio ◽

Additive White Gaussian Noise ◽

Side Lobe ◽

Radar Signal ◽

Short Time Fourier Transform ◽

Time Frequency ◽

Window Functions ◽

Pulse Analysis ◽

Short Time

The electronic intelligence (ELINT) system is used by the military to detect, extract information and classify incoming radar signals. This work utilizes short time Fourier transform (STFT) - time frequency distribution (TFD) for inter-pulse analysis of the radar signal in order to estimate basic radar signal time parameters (pulse width and pulse repetition period). Four well-known windows functions of different and unique characteristics were used for the localization of STFT to determine their various effects on the analysis. The window functions are Hamming, Hanning, Bartlett and Blackman window functions. Monte Carlo simulation is carried out to determine the performance of the signal analysis in presence of additive white Gaussian noise (AWGN). Results show that the lower the transition of main lobe width and higher the peak side lobe, the better the performance of the window function irrespective of time parameter being estimated. This is because 100 percent probability of correct estimation is achieved at signal to noise ratio of about -2dB for Bartlett, 4dB for both Hamming and Hanning, and 9dB for Blackman.

Download Full-text

A Study of Parameters Setting of the STADZT

Acta Polytechnica ◽

10.14311/1654 ◽

2012 ◽

Vol 52 (5) ◽

Author(s):

Václav Turoň

Keyword(s):

Spectral Analysis ◽

Fourier Transform ◽

Frequency Resolution ◽

Short Time Fourier Transform ◽

Time Frequency ◽

Stationary Signals ◽

Zolotarev Polynomials ◽

Non Stationary Signal ◽

Short Time ◽

Main Influence

This paper deals with the new time-frequency Short-Time Approximated Discrete Zolotarev Transform (STADZT), which is based on symmetrical Zolotarev polynomials. Due to the special properties of these polynomials, STADZT can be used for spectral analysis of stationary and non-stationary signals with the better time and frequency resolution than the widely used Short-Time Fourier Transform (STFT). This paper describes the parameters of STADZT that have the main influence on its properties and behaviour. The selected parameters include the shape and length of the segmentation window, and the segmentation overlap. Because STADZT is very similar to STFT, the paper includes a comparison of the spectral analysis of a non-stationary signal created by STADZT and by STFT with various settings of the parameters.

Download Full-text