本文關(guān)鍵詞： 雷達(dá)目標(biāo)識(shí)別 高分辨距離像 流形學(xué)習(xí) 幾何結(jié)構(gòu)特征 譜包絡(luò) 信息融合　出處：《電子科技大學(xué)》2016年博士論文　論文類型：學(xué)位論文

【摘要】：探測(cè)與測(cè)距是早期雷達(dá)的基本功能,這已經(jīng)遠(yuǎn)遠(yuǎn)不能滿足現(xiàn)代雷達(dá)需要獲取越來越多的目標(biāo)信息的需求。在軍用和民用的很多應(yīng)用中,不但需要探測(cè)到目標(biāo),還要識(shí)別出是什么目標(biāo),即雷達(dá)目標(biāo)識(shí)別。目標(biāo)識(shí)別自然成為現(xiàn)代雷達(dá)信息處理中非常重要的研究方向之一。雷達(dá)信號(hào)帶寬的提高使得雷達(dá)具有距離向高分辨能力,可對(duì)目標(biāo)進(jìn)行高分辨成像。高分辨距離像(HRRP)能夠較好的表征觀測(cè)目標(biāo)等效多散射中心沿距離向的分布結(jié)構(gòu),且易于獲取和處理,為我們提供了一種非常有潛力的雷達(dá)目標(biāo)識(shí)別手段。以高分辨距離像為研究對(duì)象,圍繞著穩(wěn)健特征提取、多特征綜合、多特征信息融合、系統(tǒng)構(gòu)架等關(guān)鍵問題,對(duì)雷達(dá)目標(biāo)高分辨距離像識(shí)別中所涉及的相關(guān)理論和關(guān)鍵技術(shù)開展了深入的理論研究和實(shí)驗(yàn)驗(yàn)證。論文主要工作和創(chuàng)新之處概況如下:(1)對(duì)兩種典型的流形學(xué)習(xí)算法——鄰域保持投影(NPP)和局部切空間排列(LTSA)進(jìn)行研究,分析了算法具備松弛HRRP的姿態(tài)敏感性的優(yōu)良特性。針對(duì)HRRP雷達(dá)目標(biāo)識(shí)別,分別提出了增強(qiáng)的鄰域保持投影(ENPP)算法和增強(qiáng)核鄰域保持投影(EKNPP)算法,以及線性鑒別局部切空間排列(LDLTSA)算法和核鑒別局部切空間排列(KDLTSA)算法。實(shí)驗(yàn)結(jié)果驗(yàn)證了所提算法的有效性以及相較于現(xiàn)有的同類算法所表現(xiàn)出來的性能優(yōu)勢(shì)。(2)針對(duì)雷達(dá)HRRP目標(biāo)識(shí)別中由于訓(xùn)練樣本非常有限導(dǎo)致傳統(tǒng)的子空間算法學(xué)習(xí)性能下降的問題,對(duì)基于點(diǎn)到空間距離測(cè)度的子空間學(xué)習(xí)算法進(jìn)行分析和研究,提出了兩種新的基于點(diǎn)到空間距離測(cè)度的學(xué)習(xí)算法:鄰域特征空間鑒別分析I(NFSDA-I)和鄰域特征空間鑒別分析II(NFSDA-II)。實(shí)驗(yàn)結(jié)果表明,相對(duì)于其它已有的點(diǎn)到空間類的學(xué)習(xí)算法,NFSDA-I和NFSDA-II算法的子空間具有更高的多目標(biāo)鑒別能力,目標(biāo)識(shí)別性能較優(yōu)。(3)對(duì)HRRP時(shí)域回波中潛在的目標(biāo)幾何結(jié)構(gòu)特征進(jìn)行分析,采用統(tǒng)計(jì)的方法,從HRRP時(shí)域回波中提取出8個(gè)從不同角度反映目標(biāo)幾何結(jié)構(gòu)信息的特征量,并采用多特征綜合的研究思路,選擇多個(gè)特征組合起來得到8個(gè)綜合特征。實(shí)驗(yàn)結(jié)果表明了其中一些幾何結(jié)構(gòu)特征的有效性,如:熵和不規(guī)則度特征,以及多特征綜合識(shí)別所具有的性能優(yōu)勢(shì)。(4)首次將語音識(shí)別領(lǐng)域里有關(guān)譜包絡(luò)的研究成果引入到HRRP雷達(dá)目標(biāo)識(shí)別中,從HRRP的頻域特性中提取出9個(gè)典型的譜包絡(luò)特征,并組合構(gòu)建了21個(gè)綜合特征,用于目標(biāo)分類。實(shí)驗(yàn)結(jié)果表明,所提取的譜包絡(luò)特征對(duì)于HRRP雷達(dá)目標(biāo)識(shí)別是有效的,且具有一定的潛力。此外,采用多個(gè)譜包絡(luò)特征綜合識(shí)別的效果良好。(5)研究了基于多特征融合的雷達(dá)目標(biāo)識(shí)別技術(shù)。對(duì)基于信息融合的雷達(dá)目標(biāo)識(shí)別系統(tǒng)框架和相關(guān)的融合算法進(jìn)行了研究,在此基礎(chǔ)上,給出了一個(gè)基于Dempster-Shafer理論多特征融合的HRRP雷達(dá)目標(biāo)識(shí)別方案,分別提取四種不同特征、采用兩種分類器進(jìn)行分類,并在決策層上基于Dempster-Shafer理論進(jìn)行融合判決。實(shí)驗(yàn)表明了該融合識(shí)別方案的有效性。(6)對(duì)寬帶數(shù)字陣列雷達(dá)目標(biāo)識(shí)別系統(tǒng)進(jìn)行研究。以S波段16陣元線陣的寬帶數(shù)字陣?yán)走_(dá)系統(tǒng)為基礎(chǔ),構(gòu)建了基于OpenVPX的信號(hào)與信息處理系統(tǒng),并建立了適用于串行高速總線的目標(biāo)識(shí)別開放式軟件架構(gòu)。
[Abstract]:Is the basic function of early detection and ranging radar, which can not meet the needs of modern radar to get more information of the target in the military and civilian needs. In many applications, not only need to detect the target, but also identify what goal, namely the radar target recognition. Target recognition has become one of very important research direction of information in the processing of modern radar. The radar signal because of the increasing bandwidth of radar has high range resolution ability to target high resolution imaging. High resolution range profile (HRRP) to the distribution characterization of the target equivalent better scattering center along the range direction, and is easy to acquire and process, provides a very the potential of the radar target recognition method for us in HRRP as the research object, around the robust feature extraction, multi feature and multi feature information fusion system. The key problem of structure, on the radar target HRRP recognition in the related theory and key technology to carry out in-depth theoretical and experimental research. The main work and innovations of the paper are as follows: (1) survey of two typical manifold learning algorithm, neighborhood preserving projection (NPP) and local tangent space alignment (LTSA) research, analysis of the excellent properties of sensitivity of HRRP relaxation algorithm with the attitude. The HRRP radar target recognition, are put forward to enhance the neighborhood preserving projection (ENPP) algorithm and the enhanced kernel neighborhood preserving projection (EKNPP) algorithm, and the identification of linear local tangent space alignment (LDLTSA) algorithm and kernel discriminant local tangent space alignment (KDLTSA) algorithm. The experimental results verify the performance advantage of the effectiveness of the proposed algorithm and compared with the existing similar algorithms is shown. (2) for radar target recognition by HRRP In the training sample is very limited in the traditional learning subspace algorithm for the problem of declining performance, based on the point to the spatial distance measure subspace learning algorithm analysis and research, put forward two new points to the space based on the distance measure learning algorithm: the neighborhood feature space I discriminant analysis (NFSDA-I) feature space and neighborhood identification analysis of II (NFSDA-II). The experimental results show that compared with other existing learning algorithms to space, NFSDA-I and NFSDA-II algorithm with subspace multi target identification ability is higher, the performance of target recognition is better. (3) the target geometry features of potential HRRP echo was analyzed by using the statistical methods to extract 8 reflect the target geometry information from different angles of the features from the HRRP echo, and the research ideas of integrated multi features, select multiple features combination up To the 8 features. The experimental results show that the effectiveness of some geometric features such as entropy and irregular features, and comprehensive recognition of the characteristics of performance advantages. (4) for the first time on the spectral envelope research results in the field of speech recognition is introduced to the HRRP radar target recognition, from the frequency characteristics of HRRP extracted from 9 typical spectral envelope features, and established 21 comprehensive features, used for target classification. The experimental results show that the spectral envelope of the extracted features are effective for HRRP radar target recognition, and has a certain potential. In addition, the multi spectral envelope feature recognition the effect is good. (5) studied the technology of radar target recognition based on multi feature fusion of radar target recognition system framework and related fusion algorithm based on information fusion is studied, on this basis, based on a given De The theory of mpster-Shafer multi feature fusion HRRP radar target recognition scheme, were extracted from four different characteristics, using two kinds of classifier and decision level fusion based on the Dempster-Shafer theory of judgment. Experimental results show the validity of the fusion scheme. (6) research on wideband digital array radar target recognition system. S band 16 element linear array of wideband digital array radar system based on OpenVPX is constructed based on signal and information processing system, and the establishment of a suitable for high-speed serial bus target recognition of open software architecture.

【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：TN957.51

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 胡衛(wèi)東;;雷達(dá)目標(biāo)識(shí)別技術(shù)的再認(rèn)識(shí)[J];現(xiàn)代雷達(dá);2012年08期

2 叢瑜;肖懷鐵;付強(qiáng);;基于核主分量分析的高分辨雷達(dá)目標(biāo)特征提取與識(shí)別[J];電光與控制;2008年02期

3 莊釗文,黎湘,劉永祥;智能化武器系統(tǒng)發(fā)展的關(guān)鍵技術(shù)——雷達(dá)自動(dòng)目標(biāo)識(shí)別技術(shù)[J];科技導(dǎo)報(bào);2005年08期

相關(guān)博士學(xué)位論文 前1條

1 馮德軍;彈道中段目標(biāo)雷達(dá)識(shí)別與評(píng)估研究[D];國防科學(xué)技術(shù)大學(xué);2006年

，

本文編號(hào)：1535325