您现在的位置: 首页> 研究主题> 广义似然比

广义似然比

广义似然比的相关文献在1999年到2022年内共计81篇,主要集中在无线电电子学、电信技术、自动化技术、计算机技术、水路运输 等领域,其中期刊论文60篇、会议论文1篇、专利文献2539篇;相关期刊44种,包括系统工程与电子技术、哈尔滨工程大学学报、电子学报等; 相关会议1种,包括2008年全国博士生学术论坛(航空宇航科学与技术)等;广义似然比的相关文献由218位作者贡献,包括时艳玲、林毓峰、刘维建等。

广义似然比—发文量

期刊论文>

论文:60 占比:2.31%

会议论文>

论文:1 占比:0.04%

专利文献>

论文:2539 占比:97.65%

总计:2600篇

广义似然比—发文趋势图

广义似然比

-研究学者

  • 时艳玲
  • 林毓峰
  • 刘维建
  • 水鹏朗
  • 王永良
  • 许述文
  • 余作奔
  • 俞卞章
  • 刘晓佳
  • 刘锡祥
  • 期刊论文
  • 会议论文
  • 专利文献

搜索

排序:

年份

    • 刘祥; 黄天耀; 刘一民
    • 摘要: 本文研究频率捷变雷达的扩展目标检测问题。当频率捷变雷达的合成带宽较大时,雷达目标会变成扩展目标,导致雷达无法直接应用传统的恒虚警检测算法。针对这一问题,本文建立了频率捷变雷达的扩展目标检测模型,推导了基于广义似然比的检验统计量,并且通过数值仿真展示了相应的检测概率和虚警概率。为了提升雷达的抗干扰能力和频谱利用率,本文考虑了雷达只使用一部分发射频点的场景。数值结果表明,在高信噪比下,频率捷变雷达使用的发射频点越多、合成带宽越大时,扩展目标检测的性能越好。
    • 翟树芬; 苏宇楠; 魏传华
    • 摘要: 本文研究固定效应变系数空间自回归面板数据模型的空间效应检验问题,利用基于局部线性方法的pro le似然估计技术,构造了广义似然比检验统计量,并提出利用一类基于残差的bootstrap方法求取检验p值,最后数值模拟表明所提方法在有限样本下有较好表现.
    • 李海鹏; 孙大军; 郑翠娥
    • 摘要: 水声定位系统是现代深海作业必备的高精度水下定位装备,精确的时延估计是实现高精度水声定位的基础,但由于信号远距离传输以及强干扰的影响,水声定位系统时延估计精度较低.针对此问题该文提出一种基于子空间理论的宽带强干扰抑制方法,首先通过贝叶斯信息量准则估计子空间维度,然后推导了不同信号假设下的概率密度函数,求解未知参数的最大似然估计,构造广义似然比并通过最优匹配广义似然比检测法估计与期望信号最匹配的子空间,然后以此构造空间投影算子对接收数据进行线性投影,最终抑制干扰和噪声,提高时延估计精度.仿真结果表明该方法能够有效抑制干扰和噪声的影响,提高定位系统时延估计精度.
    • 刘浩
    • 摘要: 文章研究了两种海面目标检测算法.由于海杂波的非高斯、非平稳和非均匀特性,传统的分布模型不能对海杂波进行有效的拟合,海杂波的概率密度函数会产生严重的拖尾现象.海杂波的非平稳性主要体现在纹理上,通过对纹理进行逆高斯建模,并估计纹理的最大后验值和最小均方误差值,对非平稳纹理进行归一化处理,实现海杂波协方差矩阵的平稳化.在广义似然比检测模型的基础上,提出了最大后验逆高斯广义似然比检测器(MAP-IGD-GLRT)和最小均方误差逆高斯广义似然比检测器(MMSE-IGD-GLRT).经过仿真和实测数据实验验证,该文所提两种检测器均优于对比算法.
    • 许述文; 石星宇; 水鹏朗
    • 摘要: 随着雷达分辨率的提高及擦地角的减小,海杂波幅度分布明显偏离瑞利分布,表现出很强的非高斯特性,复合高斯模型得到广泛应用。因此该文以复合高斯杂波为背景,研究当信号发生失配时的雷达目标检测问题。该文基于两步广义似然比(GLRT)检验,设计了复合高斯杂波下对失配信号具有选择性的自适应检测器。为了设计选择性检测器,在零假设下引入虚假干扰以修正原始二元假设,并假设该虚假干扰与实际目标信号在白化空间正交。该文提出的检测器对海杂波纹理分量及协方差矩阵恒虚警(CFAR)。最后利用仿真及实测海杂波数据,通过蒙特卡洛实验验证该检测器的有效性。实验表明,该文所提检测器有效提高了对失配信号的选择性,同时对距离扩展目标匹配信号的检测性能也有1~3 dB的提升。%Because of the improvement in radar resolution and decrease in grazing angle, the amplitude distribution of sea clutter obviously deviates from the Rayleigh distribution and presents a significant non-Gaussian feature. In this case, the compound Gaussian model is widely used. This study investigates the problem of detecting a target when signal mismatches occur in compound Gaussian clutter and proposes a selective detector to reject mismatched signals embedded in compound Gaussian clutter based on the so-called two-step Generalized Likelihood Ratio Test (GLRT). To design the selective detector, we modified the original hypothesis test by injecting a fictitious interference under the null hypothesis. These unwanted signals are assumed to be orthogonal to the nominal steering vector in the whitened subspace. The proposed detector has a Constant False Alarm Rate (CFAR) with respect to the statistics of the texture and covariance matrix. Finally, to demonstrate the effectiveness of the proposed detector, a Monte Carlo simulation is conducted to assess its performance based on the simulated and measured sea clutter data. The experimental results show that the proposed detector effectively improves the selectivity of the mismatched signals together with the detection of matched signals in a range spread target of 1~3 dB.
    • 张云雷; 汤俊; 王力
    • 摘要: 分辨率是雷达系统的重要性能指标之一,传统采用模糊函数(AF)来分析波形的距离和多普勒分辨能力。该文提出以下观点:第一,传统的模糊函数分析方法的基本出发点是首先采用匹配滤波来处理回波信号,而从机理上来说,匹配滤波是在白噪声和点目标前提下使得输出信噪比(SNR)最大,对检测来说最优,但不适用于多个目标的分辨问题;第二,模糊函数分析方法并不能反映出噪声、目标起伏等随机因素,以及近距多目标波形相互干扰等因素的影响;第三,模糊函数只适用于两相同信噪比目标分辨,不适用于实际中经常存在的不同信噪比的多个目标的分辨。该文基于原始回波数据,采用统计学中的假设检验理论来研究雷达近邻目标距离分辨的问题,在给出统计意义上的正确分辨概率和虚判概率定义基础上,推导近邻目标距离统计分辨限(SRL)的表达式。仿真表明,统计分辨限可以突破瑞利限。当设定虚判概率和分辨概率分别为0.001和0.5时,对幅度不相关0 dB的线性调频信号,距离统计分辨下限可达0.3倍瑞利限。%Resolution performance is an important performance criteria of the radar systems. Typically, the Ambiguity Function (AF) of signals is used to define the range and Doppler limits. In this study Some new opinions are proposed—First, the AF is based on the signals processed with matched filter, which can guarantee the maximization of the output of the Signal-to-Noise Ratio (SNR). Thus, the AF is optimal for target detection. However, the AF is unsuitable for the resolution of multiple targets. Second, the AF cannot reflect the effect of random factors, such as noise, target fluctuation, and mutual interference of close targets. Third, the AF can only handle two equal-powered targets and provide the conclusion of the limits. However, the AF fails to distinguish multiple unequal-powered targets, which is often the case in reality. Therefore, the hypothesis testing theory is applied to resolve the range resolution of two closely spaced targets for radars, and our study is based on the original echoes of the signals. With the definition of the correct resolution and false alarm rates in the statistical standpoint, we derive the expression of the range Statistical Resolution Limit (SRL). The simulation results indicate that the SRL can exceed the Rayleigh limit. With the false alarm and correct resolution rates being 0.001 and 0.5, respectively, for the two uncorrelated-amplitude linear-frequency-modulated signals, the range SRL can be as low as 0.3 times of the Rayleigh limit.
    • 程建华; 孙湘钰; 牟宏杰; 范晓亮
    • 摘要: In this study,to address the inability of the traditional generalized likelihood ratio test for fault detection and isolation to realize the fault detection and isolation of the strapdown, the inertial navigation multi-gyroscope is proposed. This is a multi-fault detection and isolation method based on generalized likelihood ratio fault detection and linear estimation. By considering the redundancy combined inertial navigation multi-gyroscope of the multi-fault six-gyro vertebral body,which is vertically and symmetrically configured as the object, the generalized likelihood ratio method was used to detect the fault of the system,while the linear estimation method was used to predict the gyro output value. The residuals of the predicted and output values were compared to locate the faulty gyroscope, while the fault information was recorded to implement the reconstruction of the system. The simulation and verifica-tion of the measured data demonstrated that the new method could accurately detect and isolate the multi-gyro fault and guarantee the reliability of the strapdown inertial navigation system.%针对传统广义似然比故障检测无法实现捷联惯导多陀螺故障检测和隔离的问题,本文提出基于广义似然比故障检测和线性估计思想相结合的多故障检测与隔离方法.以发生多故障的六陀螺椎体垂向对称配置的冗余捷联惯导为对象,采用广义似然比方法对系统进行故障检测,并引入线性估计思想实现陀螺输出值预测,通过陀螺预测值与输出值的残差比较定位故障陀螺,并记录故障信息,实现系统重构.通过仿真和实测数据验证,证明该方法可以准确实现对多陀螺故障检测与隔离,保障捷联惯导系统可靠性.
    • 袁宇翔; 邹斌
    • 摘要: 针对现有车载捷联惯导系统采用三轴正交安装陀螺配置模式,会出现单个陀螺故障直接导致系统失效的问题,本文提出一种基于正交锥冗余配置的高可靠性车载惯性传感器冗余配置方案.基于可靠性最大化、导航性能最优,以及单个陀螺故障后的导航性能更优的冗余优化准则,设计了五陀螺正交锥配置方案;在此基础上,设计广义似然比故障检测方法与基于线性预测思想的故障隔离方法相结合的故障诊断算法,解决惯导系统多陀螺故障检测和隔离的问题.性能仿真结果表明:惯性传感器冗余配置优化方案能使系统可靠性提升1.35倍,且准确实现对多故障的检测与隔离,对微型化车载捷联惯导方案设计具有重要的实际应用价值.
    • 李月贞; 陈少平
    • 摘要: 针对基于慢变信道假设的认知无线电不适合高速移动场景的问题,提出一种基于广义似然比的OFDM频谱感知算法.利用OFDM信号自身相关性得到OFDM检测统计量,通过研究其统计分布特性得到OFDM广义似然比检测统计量,构建快变信道检测模型进行频谱感知.在原算法的基础上,用检测窗口的宽度近似替代检测统计量的方差,得到广义似然比的改进算法.仿真结果表明,两种感知算法在低信噪比、快变信道环境中都具有很高的认知度,而且改进算法对噪声和干扰还具有很好的鲁棒性.%Since the cognitive radio based on the assumption of a slowly-varying channel is unsuitable for the high-speed mobile scenario,an orthogonal frequency division multiplexing(OFDM)signal's spectrum sensing algorithm based on generalized likelihood ratio is proposed,in which the autocorrelation of OFDM signal is used to get the OFDM detection statistics.Its statistics distribution characteristic is studied to get the OFDM detection statistics of generalized likelihood ratio,and construct the fast-varying channel detection model for spectrum sensing. On the basis of the original algorithm,an improved algorithm of the generalized likelihood ratio is obtained by the approximate replacement of the variance of the detection statistics with the width of the detection window. The simulation results show that the two perception algorithms both have high recognition rate in the low signal-to-noise ratio and fast-varying channel environments,but the improved algorithm has stronger robustness against noise and interference.
  • 查看更多

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号