本文關(guān)鍵詞： 高頻地波雷達(dá) 機(jī)器學(xué)習(xí) 特征提取 特征篩選 卷積神經(jīng)網(wǎng)絡(luò)　出處：《哈爾濱工業(yè)大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：高頻地波雷達(dá)(High Frequency Surface Wave Radar,簡(jiǎn)稱HFSWR),基于高頻(3MHz-30MHz)垂直極化波與海面的相互作用,能探測(cè)超出地球曲率的遠(yuǎn)處目標(biāo),對(duì)于國(guó)家安全、航海安全以及環(huán)境檢測(cè)具有至關(guān)重要的意義。然而返回的電磁波受到如海雜波、電離層雜波、大氣噪聲、流星余跡、電臺(tái)干擾等多種因素影響,極大影響了HFSWR的目標(biāo)檢測(cè)。如今主流的雜波抑制方法,如空時(shí)、時(shí)頻、圖像、建模分析等,都有其針對(duì)性處理的雜波以及適應(yīng)性應(yīng)用的條件。若將高頻地波雷達(dá)回波距離多普勒譜(Range-dopper,簡(jiǎn)稱RD譜)自適應(yīng)的區(qū)分成不同類型的雜波,不僅可以自適應(yīng)的將不同類型的雜波送入不同的抑制方法模塊里,后續(xù)的目標(biāo)檢測(cè)策略還可根據(jù)雜波的類型作出相應(yīng)調(diào)整,實(shí)現(xiàn)更智能的雷達(dá)處理模式。本文的最終目的是能很好的區(qū)分高頻地波雷達(dá)背景中的不同雜波。由于實(shí)測(cè)HFSWR回波RD譜中各類雜波的邊界是未知的,本文首先利用海雜波產(chǎn)生的原理、雷達(dá)方程、地波衰減原理以及電離層雜波的統(tǒng)計(jì)特性對(duì)HFSWR模擬仿真。本文將介紹相關(guān)的原理,制作不同海態(tài)環(huán)境下關(guān)于雜波的仿真環(huán)境以及仿真數(shù)據(jù)的雜波類別標(biāo)簽。對(duì)雜波的認(rèn)知和抑制一直是研究的重點(diǎn)。本文先針對(duì)現(xiàn)有對(duì)雜波認(rèn)知的方法,建立雜波特征庫,相繼提取了雜波的功率譜幅值、無維分流參數(shù)、小波多尺度參數(shù)、Gabor方向性參數(shù)、統(tǒng)計(jì)擬合參數(shù)、Bragg峰理論位置信息、雜噪比以及聯(lián)合參數(shù)作為雜波獨(dú)特的特征向量。并基于特征統(tǒng)計(jì)、信息理論以及分類效果對(duì)特征分析和篩選,選取最優(yōu)的特征組合進(jìn)行基于支持向量機(jī)的雜波分類,得到了滿意的分類效果。本文提出了一種基于卷積神經(jīng)網(wǎng)絡(luò)(Convolutional neural network,簡(jiǎn)稱CNN)的雜波分類方法。介紹了對(duì)仿真RD譜的預(yù)處理以及送入CNN的子圖像,經(jīng)CNN訓(xùn)練學(xué)習(xí)后,將訓(xùn)練好的網(wǎng)絡(luò)效果與特征篩選算法對(duì)比分析。這種方法同樣具有比較滿意的分類效果,為雜波的背景分類提供了一種新方法。最后,本文將上述方法應(yīng)用在實(shí)測(cè)數(shù)據(jù)中,提出了一種自動(dòng)分類算法來對(duì)實(shí)測(cè)數(shù)據(jù)定量評(píng)價(jià),并提供了GUI(Graphical User Interface)界面便于自動(dòng)提取算法的進(jìn)一步完善。本文提出的方法在實(shí)測(cè)數(shù)據(jù)中也具有可行性。
[Abstract]:High Frequency Surface Wave radar (HFSWR), based on the interaction of high frequency 3MHz-30MHz waves with the sea surface, can detect distant targets beyond the curvature of the earth. Safety of navigation and environmental detection are of vital importance. However, returned electromagnetic waves are affected by many factors, such as sea clutter, ionospheric clutter, atmospheric noise, meteor trace, radio interference, etc. It has greatly affected the target detection of HFSWR. Nowadays, the mainstream clutter suppression methods, such as space-time, time-frequency, image, modeling and analysis, etc. If the echo range Doppler spectrum of HF ground wave radar is adaptively divided into different types of clutter, Not only can different types of clutter be adaptively sent into different suppression methods, but the subsequent target detection strategies can also be adjusted accordingly according to the type of clutter. The final purpose of this paper is to distinguish the different clutter in the background of high frequency ground wave radar. The boundary of all kinds of clutter in the measured HFSWR echo Rd spectrum is unknown. This paper first uses the principle of sea clutter generation, radar equation, ground wave attenuation principle and statistical characteristics of ionospheric clutter to simulate HFSWR. The simulation environment of clutter and the label of clutter category of simulation data in different sea environment are made. The recognition and suppression of clutter is always the focus of the research. Firstly, aiming at the existing methods of recognition of clutter, the clutter signature library is established in this paper. The power spectrum amplitude, dimensionless shunt parameters, wavelet multiscale parameters and Gabor directional parameters of clutter are extracted successively, and the theoretical position information of Bragg peak is obtained by statistical fitting parameters. Based on feature statistics, information theory and classification effect, the best feature combination is selected to classify clutter based on support vector machine. In this paper, a clutter classification method based on convolution neural network Convolutional neural Network (CNNs) is proposed. The preprocessing of simulated Rd spectrum and the sub-images sent to CNN are introduced. After training and learning by CNN, this paper proposes a new method of clutter classification based on Convolutional neural Network (CNNs). The trained network effect is compared with the feature selection algorithm. This method also has a satisfactory classification effect, which provides a new method for background classification of clutter. Finally, the above method is applied to the measured data. An automatic classification algorithm is proposed to quantitatively evaluate the measured data, and the GUI(Graphical User interface is provided to further improve the automatic extraction algorithm. The method proposed in this paper is also feasible in the field data.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TN959;TP181

【參考文獻(xiàn)】

相關(guān)期刊論文 前4條

1 肖進(jìn)勝;劉恩雨;朱力;雷俊鋒;;改進(jìn)的基于卷積神經(jīng)網(wǎng)絡(luò)的圖像超分辨率算法[J];光學(xué)學(xué)報(bào);2017年03期

2 尚尚;張寧;李楊;;高頻地波雷達(dá)電離層雜波統(tǒng)計(jì)特性研究[J];電波科學(xué)學(xué)報(bào);2011年03期

3 周浩;文必洋;吳世才;;高頻地波雷達(dá)中電離層雜波的時(shí)頻特征[J];電波科學(xué)學(xué)報(bào);2009年03期

4 李旭濤;王首勇;金連文;;應(yīng)用Alpha穩(wěn)定分布對(duì)雷達(dá)雜波的辨識(shí)[J];電子與信息學(xué)報(bào);2008年09期

相關(guān)博士學(xué)位論文 前1條

1 李楊;高頻地波雷達(dá)背景感知與目標(biāo)檢測(cè)技術(shù)研究[D];哈爾濱工業(yè)大學(xué);2010年

相關(guān)碩士學(xué)位論文 前5條

1 蔡文涵;船載HFSWR海雜波截面積方程研究與仿真[D];哈爾濱工業(yè)大學(xué);2015年

2 李思明;基于復(fù)合高斯模型的雜波統(tǒng)計(jì)分析與建模[D];哈爾濱工業(yè)大學(xué);2015年

3 曾文君;基于多維譜特征的電離層雜波檢測(cè)和識(shí)別方法研究[D];哈爾濱工業(yè)大學(xué);2014年

4 白海洋;電離層回波多普勒特性的研究[D];哈爾濱工業(yè)大學(xué);2012年

5 馬宏偉;高頻雷達(dá)海雜波特性研究與仿真分析[D];哈爾濱工業(yè)大學(xué);2011年

，

本文編號(hào)：1512913