The radar's high-resolution range profile (HRRP) data structure is complex, and extracting stable and reliable features from it is crucial for HRRP target recognition. In this paper, we propose to use the convolution module to extract local spatial features of HRRP and use the positional encoding to embed the position information to generate new temporal features, and then capture the long-term dependency within the distance unit of HRRP through the multi-head new self-attention mechanism of the Transformer encoder, to construct a reliable feature extraction method for the HRRP target. Finally, a new deep learning model CNN-TEAN (CNN TransEncoder-Attention Network), based on one-dimensional residual convolution, Transformer encoder, and attention mechanism, is formed using the attention mechanism, fully connected layer, and softmax for classification. Using six simulated ship target data types for experimental validation, the CNN-TEAN model proposed in this paper can achieve a higher recognition rate than RNN, LSTM, and SVM models.

The High Resolution Range Profile (HRRP) contains rich target information and is commonly utilized in the field of radar automatic target recognition. Most of the key targets of concern in practical applications are non-cooperative, making it challenging to acquire data for such targets. This often results in an imbalance in target categories within datasets, thereby impacting the classification performance of models. To address these issues, this paper proposes the Weighted-SMOTE (Synthetic Minority Over-sampling Technique) algorithm. The algorithm assigns different weights to the number of synthetic new samples for each sample based on the Euclidean distance between minority class samples and the remaining samples. Furthermore, it utilizes the MCNN-TEAN (Multi-scale Convolutional Neural Network – TransEncoder Attention Network) model to extract multi-level features and capture long-term dependencies between feature dimensions, thereby improving the classification accuracy of targets.

针对现有辐射源识别方法难以适应时变信道的问题,提出一种信道自适应的特定辐射源训练与识别方法.利用分布差异的数据,在经过预训练的网络模型上开展无监督训练,并在训练中对数据特征加以约束,使失配的特征在高维空间中逐渐对齐,从而提升模型对于变化场景的鲁棒性.实例证实该方法的有效性.

针对舷外有源诱饵干扰性能评估的问题,提出了一种基于区间层次分析-模糊综合评判的舷外有源诱饵干扰性能评估方法.该方法以模糊数学理论为基础,借鉴已建立评价指标的模糊综合评判因素集,采用 1-9 标度法和区间数打分,基于层次分析法和熵值法主客观组合赋权确定评价指标权重,通过隶属函数建立评判矩阵,计算模糊综合评断结果,并按照隶属度的大小确定舷外有源诱饵干扰能力级别.经实例验证,该方法降低了评估结果主观性的影响.

为便于与射频集成电路差分输出端口集成设计,提供了一种平面结构的椭圆形宽带差分天线的设计方案.利用椭圆形辐射贴片边缘与椭圆形地平面边缘的渐变形状可以实现天线的宽带辐射,利用辐射单元的对称设计和差分微带线进行馈电,采用反射板结构,以牺牲天线工作带宽为代价,可以实现波束的单侧辐射,提高天线增益.仿真结果表明,无反射板时,天线工作带宽为5.2GHz～12GHz,增益约为2dB～5dB;有反射板时,天线工作带宽为7.9GHz～12GHz,增益约为5dB～8dB.

A multi-UAV and multi-target assignment method based on observation equalization optimization is proposed for fixed-wing UAV standoff tracking with heterogeneous sensors. The mechanical circle scanning sensor is changed to observe only partial targets by sector scanning to improve the observation performance. A novel performance function is proposed to balance observation with current and prior FIM for each target. Then, the configuration and observability of heterogeneous sensors are considered to divide groups of UAVs and targets. Finally, the multi-target assignment with heterogeneous sensors is solved by linear programming and replanning online in time. The simulation results present some intuitive cooperative track patterns and verify the effectiveness of the proposed sector scanning mode and online replanning method, which can reduce the deviation of the observation performance for targets by 7.6% and 15.4%, respectively.

The angular resolution of radar is of crucial significance to its tracking performance. In this paper, a super-resolution parameter estimation algorithm based on wide-narrowband joint processing is proposed to improve the angular resolution of wideband monopulse radar. The range cells containing resolvable scattering points are detected in the wideband mode, and these range cells are adopted to estimate part of the target parameters by algorithms of low computational requirement. Then, the likelihood function of the echo is constructed in the narrow-band mode to estimate the rest of the parameters, and the parameters estimated in the wideband mode are employed to reduce computation and enhance estimation accuracy. Simulation results demonstrate that the proposed algorithm has higher estimation accuracy and lower computational complexity than the current algorithm and can avoid the risk of model mismatch.

针对雷达目标全极化高分辨距离像(high resolution range profile,HRRP)提取可分性特征时,利用全部距离单元作为度量尺度无法保留各距离单元具体特征的问题,在综合利用4个极化通道的舰船目标HRRP信息时选择单个距离单元作为度量尺度.在此基础上,提出基于Pauli分解,H、α、A、α分解和结构相似性参数的特征提取方法对目标极化散射矩阵进行特征提取,并将提取得到的特征与基于卷积神经网络(convolutional neu-ral network,CNN)的舰船目标HRRP识别方法结合,利用改进残差结构CNN从极化特征中进一步提取深层可分性特征进行目标识别.实验结果表明,所提方法能够保留目标全极化HRRP更多特征,提高目标识别的准确率.

舷外有源诱饵是对抗反舰导弹的一种有效的方式.论文对舷外有源诱饵的质心式干扰机理进行分析,建立了舷外有源诱饵等效雷达截面积模型、导弹跟踪模型等一系列数学模型,对反舰导弹的突防过程进行了仿真,对影响舷外有源诱饵干扰效果的因素进行了定量的分析,得到舷外有源诱饵干扰有效性的使用要求.研究结果可为舷外有源诱饵的战术使用提供参考,也可为水面舰艇规避反舰导弹攻击提供借鉴.

对切割效应下箔条云质心干扰机理进行分析,建立了箔条云切割模型、导弹跟踪模型等一系列数学模型,对反舰导弹的突防过程进行仿真,对影响箔条云干扰效果的因素进行定量的分析,得到箔条云干扰有效性的使用要求.研究结果可为箔条云干扰的战术使用提供参考,也可为水面舰艇规避反舰导弹的威胁提供借鉴依据.

In through-the-wall imaging, the clutter cannot be eliminated completely through traditional algorithms, and seriously affects the subsequent target detection and recognition. To solve the problem, based on robust principal component analysis theory, a joint low-rank and sparse model is established in echo and image domain respectively. The models are solved by smoothing fast alternating linearization method. Then, the target images are dealt with exponentially weighted multiply multi-domain image fusion to obtain the final image. The simulation results indicate that the algorithm has great speed and accuracy with effective improvement on imaging quality of targets.

多功能雷达具有多种工作模式,正确识别雷达工作模式对于提高电子战效能具有重要意义.论文首先介绍了多功能雷达的主要工作模式,通过辐射源描述字进行区分,随后引入K-means聚类算法,梳理了算法步骤,分析了算法适用于雷达工作模式识别问题的合理性.实验结果表明,该算法具有很高的识别准确率,能够有效实现对多功能雷达工作模式的正确划分.

为了解雷达目标更多的详细信息,对基于高分辨距离像(high resolution range profile,HRRP)序列的目标识别方法进行分析.对隐马尔可夫模型(hidden Markov model,HMM)、卷积神经网络(convolutional neural network,CNN)、循环神经网络(recurrent neural network,RNN)和长短期记忆网络(long short-term memory,LSTM)等面向序列识别的分类器进行阐述和讨论,分析不同分类器用于HRRP目标识别的发展历程,指出不同识别方法的优缺点及适用性条件.结果表明,该研究可为不同识别场景下应用合适的分类器提供一些思路.

针对现有的分组交织器识别算法计算复杂高且容错性差缺点,从分组交织后的同步码分布规律出发,提出了一种新的识别算法.首先,利用数据矩阵统计特性,给出了在任意矩阵列数下,同步码和随机业务数据位置上的概率密度分布函数,基于最小错误判决准则,设定了同步码检测门限,同时基于3倍标准差准则,求解出稳健的交织周期识别门限;其次,分析了数据矩阵中每一行与每一列累积量之间的对应关系,提出了一种快速交织周期遍历方法,使得数据矩阵的构建次数大大减少;最后,总结了4个分组交织后同步码分布规律,通过遍历同步码序列,利用同步码之间的位置关系,实现交织同步位置、分组交织列与交织行参数快速识别.仿真结果表明:所提算法具有较强的低信噪比容错性,在信噪比为-6 dB条件下,参数识别率能够达到98％以上,同时与现有的算法相比,其性能提升4～10 dB且计算效率明显提高.

反舰导弹攻击海面舰船目标时,通常根据目标的散射特征数据进行目标类型判定并做出决策.但是在高海况下:如果导弹横浪飞行,海浪对导弹命中目标的影响会变小,基本能保证可靠命中目标;但如果导弹顶浪飞行,则海浪会引起目标雷达反射截面积(Radar Cross Section,RCS)的起伏甚至突变,影响导弹对目标的锁定和判断.文章建立了不同海况和舰船目标的融合模型,并针对融合模型仿真计算了导弹不同突击方向时的RCS,最终根据高海况时舰船横浪或顶浪航行的原则,按照捕捉概率最大的方向确定导弹的攻击方向.

This paper mainly studies the power transform preprocessing of High Resolution Range Profile (HRRP). Power transform can make the HRRP data tend to be normally distributed, improve the recognition effect of common classifiers such as linear discriminant function and k-nearest neighbor (KNN), increase the role of weak scattered points in recognition, and weaken the shielding effect of strong scattered points on weak scattered points, so as to alleviate the attitude sensitivity problem of HRRP. This paper first introduces the statistical properties of HRRP, then introduces the properties of power transform and parameter estimation methods, including parameter estimation based on the skewness and kurtosis normality test and Jarque-Bera normality test. After analyzing and summarizing the shortcomings of the two methods, the parameter estimation method of adaptive Jarque-Bera normality test was proposed. The power transform parameters obtained from the improved parameter estimation method of Jarque-Bera normality test were used to preprocess the measured HRRP. The results were verified by normplot and the measured ship HRRP, which are more close to the normal distribution; In the meantime, the target classification and recognition experiment is carried out by using the measured ship HRRP data after power transform, and the average recognition accuracy is improved by more than 4.8 percent.

介绍了一种基于灰色关联-可拓学雷达导引头抗干扰性能评估方法.该方法以物元模型的可拓集合和关联函数理论为基础,首先确定评价指标等级范围,其次采用区间数打分,基于灰色关联方法确定评价指标权重,最后计算评价指标相对于各评价等级关联度,按照关联度的大小确定雷达导引头抗干扰能力级别.经实例验证,该方法可降低评估结果主观性的影响.

基于四种典型舰船目标高分辨一维距离像,对特征的提取进行了探讨,分别提取了时域和变换域的特征.通过理论分析与仿真实验的方式,利用分类树、朴素贝叶斯和SVM等典型分类器对不同特征进行了识别,验证了不同分类器下使用不同特征进行目标识别的性能,通过选择分类器和基于一维距离像提取的特征,可以有效改善识别性能.