Dim target detection using high order correlation method

This work presents a method for clutter rejection and dim target track detection from infrared (IR) satellite data using neural networks. A high-order correlation method which recursively computes the spatio-temporal cross-correlations between data of several consecutive scans is developed. The implementation of this scheme using a connectionist network is presented. Several important properties of the high-order correlation method which indicate that the resultant filtered images capture all the target information are established. The simulation results obtained with this approach show at least 93% clutter rejection. Further improvement in the clutter rejection rate is achieved by modifying the high-order correlation method to incorporate the target motion dynamics. The implementation of this modified high-order correlation using a high-order neural network architecture is demonstrated. The simulation results indicate at least 97% clutter rejection rate for this method. A comparison is also made between the methods developed here and the conventional frequency domain three-dimensional (3-D) filtering scheme, and the simulation results are provided     

Space-time autoregressive filtering for matched subspace STAP

Practical space-time adaptive processing (STAP) implementations rely on reduced-dimension processing, using techniques such as principle components or partially adaptive filters. The dimension reduction not only decreases the computational load, it also reduces the sample support required for estimating the interference statistics. This results because the clutter covariance is implicitly assumed to possess a certain (nonparametric) structure. We demonstrate how imposing a parametric structure on the clutter and jamming can lead to a further reduction in both computation and secondary sample support. Our approach, referred to as space-time autoregressive (STAR) filtering, is applied in two steps: first, a structured subspace orthogonal to that in which the clutter and interference reside is found, and second, a detector matched to this subspace is used to determine whether or not a target is present. Using a realistic simulated data set for circular array STAP, we demonstrate that this approach achieves significantly lower signal-to-interference plus noise ratio (SINR) loss with a computational load that is less than that required by other popular approaches. The STAR algorithm also yields excellent performance with very small secondary sample support, a feature that is particularly attractive for applications involving nonstationary clutter.     

利用神经网络的海杂波幅度分布参数估计方法

海杂波是制约对海雷达探测性能的主要因素之一,掌握其特性,具有十分重要的意义。经典海杂波统计模型在参数估计方法上以传统统计学理论为基础,在样本数较少的情况下,估计结果往往较差,导致建模准确度下降。此外,在复杂非均匀探测背景下,难以实现海杂波模型参数的准确实时估计。针对该问题,文章将深度神经网络模型引入海杂波参数估计领域,通过构建合理的模型,使其具备海杂波幅度分布模型的高精度参数估计能力。该方法采用直方图统计的方法进行数据预处理,合理划分输入数据标签的分组区间,构建数据集训练神经网络,并利用测试数据得到神经网络估计结果。仿真数据和X波段IPIX雷达实测数据验证结果表明,与传统数理统计估计方法相比,该算法明显提升了海杂波统计模型参数估计精度。     

Improving performance in pulse radar detection using neuralnetworks

A new approach using a multilayered feed forward neural network for pulse compression is presented. The 13 element Barker code was used as the signal code. In training this network, the extended Kalman filtering (EKF)-based learning algorithm which has faster convergence speed than the conventional backpropagation (BP) algorithm was used. This approach has yielded output peak signal to sidelobe ratios which are much superior to those obtained with the BP algorithm. Further, for use of this neural network for real time processing, parallel implementation of the EKF-based learning algorithm is indispensable. Therefore, parallel implementation has also been developed     

概率神经网络在识别带有噪声字母中的应用

字符识别是模式识别中的一个应用,通过训练网络可以教会计算机如何识别字符,这在票据处理方面可以大大地提高效率。该文中所建立的神经网络为具有局部响应的高斯函数的三层概率神经网络,它以牢固的插值理论为基础,具有学习速度快,不易陷入局部极小等优点。本文介绍了概率神经网络的学习算法和一个三层概率神经网络对带有噪声的26个英文大写字母的识别。其中利用MATLAB编写仿真程序对概率神经网络进行训练,仿真结果表明,训练的概率神经网络可以对给定的带有噪声的字母作出正确的识别。     

一种基于修正Hough变换的航迹起始算法

为了在重杂波区内检测出运动的目标,提出了一种修正的Hough变换算法用于初始航迹的建立。与传统的算法相比,修正算法充分利用目标的运动学信息,选取了更为合适的变换参量,仅利用较少拍数的量测就可以完成起始,能够在检测概率较高的环境下具有良好的起始性能。计算机仿真结果表明,算法能够克服传统算法的多拍扫描,大大缩短实际的计算量和起始时间,实现对航迹起始的在线改进。     

空间非合作目标惯性参数的Adaline网络辨识方法

空间在轨操作中,航天器在对空间非合作目标的抓捕行动常常导致航天器本体的姿态和空间轨迹发生变化。为克服空间非合作目标对航天器本体动力学、运动学的影响,使控制系统做出精准及时的姿控策略调整,确保航天器正常在轨工作和轨迹姿态的高精度,需对抓捕的非合作目标的惯性参数进行辨识。针对传统辨识方法依赖广义逆求解导致的辨识过程运算量大,且数值容易产生剧烈振荡,造成辨识结果不稳定等不足,采用基于归一化最小均方（NLMS）准则的Adaline神经网络方法进行空间非合作目标惯性参数的辨识。首先,基于动量守恒理论建立抓捕后的航天器-机械臂-空间非合作目标系统模型;然后将辨识方程的系数矩阵作为网络的输入和输出,空间非合作目标的惯性参数作为神经网络的训练权重,基于迭代步长可变的NLMS准则实现对目标惯量参数的快速、准确辨识;最后,在构造的ADAMS/MATLAB联合仿真平台上进行了验证。仿真结果表明,基于NLMS准则的Adaline神经网络是一种快速、准确辨识目标惯量参数的有效方法。     

Multiple target detection using modified high order correlations

This work is concerned with the problem of multiple target track detection in heavy clutter. Using the “modified high order correlation” (HOC) process and a track scoring mechanism a new method is developed to perform data association and track identification in the presence of heavy clutter. Using this new scheme any number of very close, crossing or splitting target tracks can be resolved without increasing the computational complexity of the algorithm. The applicability of the method for continuous detection of target tracks that can originate and terminate at any scan is also demonstrated, In addition, the operating characteristics as a function of the clutter density are also provided. Simulation results on all the cases are presented     

飞行器神经元控制系统的研究与设计

提出了一种基于神经元网络的飞行控制系统设计方法 ,该方法设计的神经元飞行控制器具有良好的鲁棒性 ,使飞行器在整个飞行包络内都能保持某种最优的操纵品质。给出的计算机仿真结果显示出神经元网络作为飞行控制器在处理飞行器参数大范围变化的非线性特性方面具有潜在的优良品质     

Sensor registration using neural networks

One of the major problems in multiple sensor surveillance systems is inadequate sensor registration. We propose a new approach to sensor registration based on layered neural networks. The nonparametric nature of this approach enables many different kinds of sensor biases to be solved. As part of the implementation we develop some modifications to the common network training algorithm to tackle the inherent randomness in all components of the training set     

非线性MIMO系统神经网络自适应方法及其在飞控中的应用

提出了一种非线性系统的对角自回归神经网络模型。为了实现MIMO系统自适应控制,采用自回归辨识网络对未知非线性系统进行辨识,并将被控对象的误差灵敏度信息用于对角自回归控制网络训练。辨识网络和控制网络都用动态BP算法训练。实际某型飞机纵向模型的仿真结果表明,运用这种控制结构可得到较好的控制效果。     

基于神经网络和人工势场的协同博弈路径规划

协同博弈路径规划是空战自主决策、机器人体育比赛等应用场景中的重要问题，其难点在于对环境对抗性反馈的实时自适应和多智能体的相互配合。提出一种基于神经网络和人工势场的协同博弈路径规划方法，使用反向传播（BP）神经网络自适应调整人工势场函数系数，并将人工势场作为神经网络输出端的特征提取。为解决真实样本质量和数量不足的问题，基于遗传算法仿真生成样本数据用于神经网络训练，并通过滚动时域的思路面向动态博弈优化样本性能。从样本数据中提炼出距离差与航向差以反映协同和博弈特性，利用神经网络的黑盒特性和学习能力解决协同博弈问题。应用于二对一反隐身超视距空战路径规划，比经典人工势场法有明显性能提升，且计算开销可接受，计算复杂度分析表明该方法可以较好扩展到多机对抗场景。     

基于量测一致性的分布式多传感器多目标跟踪算法

针对无线传感器网络跟踪多目标过程中传感器能搭载的计算负荷有限,不宜采用复杂算法实现数据处理的问题,提出了一种基于量测一致性的分布式多传感器多目标跟踪算法。算法采用计算相对简易的最近邻域法处理多目标跟踪中的数据互联问题,针对最近邻域法容易受杂波干扰的情况,通过量测的平均一致性迭代来改进算法的性能。仿真结果证明,算法具备有效抑制因误判产生的错误量测对跟踪过程干扰的性能,实现了良好的传感器网络跟踪精度和估计信息一致性。     

基于改进的BP网络的水机温度模型建立

传统的水电仿真系统中的温度模型的构建方法存在模型可移植性比较差、推导过程必须有水电专家的参与、推导过程复杂度大、模型精确度不高等不足,这些都对水电仿真的进一步发展和准确性产生了一定影响。因此需要一种更新的方法来适应水电仿真的发展。为此提出了一种改进的BP网络神经元网络学习算法,通过改进训练算法以提高神经网络的训练效率以及准确度。将这种算法应用于吉林丰满水电厂水电仿真系统的水机温度模型的建立实验中,并与原有的神经网络方法进行比较,比较结果表明,该方法能提高分类准确率和训练速度。     

Stap using knowledge-aided covariance estimation and the fracta algorithm

In the airborne space-time adaptive processing (STAP) setting, a priori information via knowledge-aided covariance estimation (KACE) is employed in order to reduce the required sample support for application to heterogeneous clutter scenarios. The enhanced FRACTA (FRACTA.E) algorithm with KACE as well as Doppler-sensitive adaptive coherence estimation (DS-ACE) is applied to the KASSPER I & II data sets where it is shown via simulation that near-clairvoyant detection performance is maintained with as little as 1/3 of the normally required number of training data samples. The KASSPER I & II data sets are simulated high-fidelity heterogeneous clutter scenarios which possess several groups of dense targets. KACE provides a priori information about the clutter covariance matrix by exploiting approximately known operating parameters about the radar platform such as pulse repetition frequency (PRF), crab angle, and platform velocity. In addition, the DS-ACE detector is presented which provides greater robustness for low sample support by mitigating false alarms from undernulled clutter near the clutter ridge while maintaining sufficient sensitivity away from the clutter ridge to enable effective target detection performance     

基于强化学习的多无人机避碰计算制导方法

针对大量固定翼无人机在有限空域内的协同避碰问题,提出了一种基于多智能体深度强化学习的计算制导方法。首先,将避碰制导过程抽象为序列决策问题,通过马尔可夫博弈理论对其进行数学描述。然后提出了一种基于深度神经网络技术的自主避碰制导决策方法,该网络使用改进的Actor-Critic模型进行训练,设计了实现该方法的机器学习架构,并给出了相关神经网络结构和机间协调机制。最后建立了一个实体数量可变的飞行场景模拟器,在其中进行"集中训练"和"分布执行"。为了验证算法的性能,在高航路密度场景中进行了仿真实验。仿真结果表明,提出的在线计算制导方法能够有效地降低多无人机在飞行过程中的碰撞概率,且对高航路密度场景具有很好的适应性。     

修正的概率数据互联算法

阐明了概率数据互联(PDA)算法能很好地解决密集环境下的目标跟踪问题,在该算法基础上,人们又提出了联合概率数据互联(JPDA)算法和一些基于 PDA 的修正算法。在概率数据互联算法中,有一个很重要的参数就是杂波数密度(或波门内虚假量测期望数)。然而在许多实际情况中,这个参数是很难获取的。针对这一问题,文中提出了一种修正的概率数据互联算法,该算法通过实时地调整这一参数来获得对目标较为准确的估计结果。最后,给出了算法的仿真分析。     

SPRI: simulator of polarimetric radar images

Simulator of polarimetric radar images (SPRI) consists of a suite of image processing programs for producing realistic millimeter-wave (MMW) radar images artificially on a workstation. The heart of the simulation approach is a polarimetric Rayleigh clutter simulator coupled to a clutter database. The simulator produces high resolution single-look polarimetric images. Hard targets can then be embedded into this clutter map, and the resultant image can be degraded in resolution, number of looks, polarization, etc. to match that which would be observed by a real sensor. Examples of simulated images, and comparisons of these simulations to actual images, are presented. The MMW Clutter Database is the most comprehensive to-date database of over 3500 Mueller matrices for many kinds of terrestrial clutter measured at 35 and 95 GHz, many of which are at incidence angles close to grazing. The database can be accessed via a World Wide Web flexible interface that enables data to be combined in new and unique ways specified by the user, and displayed in either tabular or graphical format. The structure and access procedure to the database are described     

密集杂波环境下的数据关联快速算法

基于联合概率数据互联（JPDA）的思想,提出了一种新的数据关联快速算法（Fast Al-gorithm for Data Association,简称FAFDA算法）.该方法不需象在最优JPDA算法中那样生成所有可能的联合互联假设,因而具有计算量小,易于工程实现的特点。仿真结果表明,与最优JPDA算法相比,FAFDA算法的跟踪性能令人满意,并且在密集杂波环境下可实时、有效地跟踪100批次以上的目标。     

Neural solution to the multitarget tracking data associationproblem

The problem of tracking multiple targets in the presence of clutter is addressed. The joint probabilistic data association (JPDA) algorithm has been previously reported to be suitable for this problem in that it makes few assumptions and can handle many targets as long as the clutter density is not very high. However, the complexity of this algorithm increases rapidly with the number of targets and returns. An approximation of the JPDA that uses an analog computational network to solve the data association problem is suggested. The problem is viewed as that of optimizing a suitably chosen energy function. Simple neural-network structures for the approximate minimization of such functions have been proposed by other researchers. The analog network used offers a significant degree of parallelism and thus can compute the association probabilities more rapidly. Computer simulations indicate the ability of the algorithm to track many targets simultaneously in the presence of moderately dense clutter