数据融合技术与潜艇指控系统的发展

就潜艇指控系统的现状和发展,综述了数据融合技术在潜艇指控系统中的应用前景。     

基于加权动态规划和航迹关联的小目标检测技术

低信噪比下运动小目标的检测一直是成像目标检测中的一个热点问题。提出了一种新的小目标检测算法,采用方向加权的动态规划算法和二值航迹关联,克服了低信噪比下目标机动和传感器的不稳定对小目标检测的影响,实现了对深空背景下运动方式任意、速度最大达1像素/帧的弱小运动目标的有效检测。     

基于PMC模型的神经网络

在计算机系统中有许多诊断算法,其中针对PMC模型有0-1规划的诊断算法,这个诊断算法是NP完全的,是在多项式时间内不可解的。然而利用神经网络的高度并行性这个特点,就可以在很短的时间内解出结果。主要分析了系统诊断模型PMC的症候特征,得到其充要条件,提出了新的算法,该算法具有高度的并行性,神经网络的发展为此提供了用模拟电路来实现算法的可能性,并进行了模拟验证。     

一种高超声速飞行器在线反馈滤波算法

高超声速飞行器是近年来各国大力发展的新概念飞行器,针对其飞行运动轨迹难以进行高精度跟踪这一问题,结合神经网络强大的自适应和自学习能力,提出了一种高超声速飞行器在线反馈滤波算法.其核心是在当前统计模型的基础上,利用BP神经网络与卡尔曼滤波相结合进行滤波器设计,实现对高超声速飞行器高精度跟踪.最后通过仿真试验进行比较,验证...     

逐步Ⅰ型混合截尾试验下Burr部件的可靠性分析

在逐步Ⅰ型混合截尾试验下,研究了Burr部件寿命参数及可靠性指标的极大似然估计和Bayes估计.利用简单迭代方法,给出了寿命参数和可靠性指标的极大似然估计的数值解.然后利用Lindely Bayes近似算法得到了平方损失下寿命参数以及可靠性指标的Bayes估计.最后,运用Monte-Carlo方法对各估计结果作了模拟比较,结果表明Bayes估计较极大似然估计的误差小.     

目标区域局部特征和局部图像质量相结合的激光干扰效果评估

为客观描述光电成像系统激光干扰效果,提出目标区域局部特征和图像质量相结合的干扰效果评估算法。图像的局部特征用特征点描述,图像质量用结构相似度指数描述。该算法利用特征点匹配算法确定场景图像中的目标区域,计算干扰前后目标区域内特征点数量的变化、干扰后目标区域内未饱和面积所占的比重以及目标区域内图像的结构相似度指数,并将上述各参数相乘得到最终的评价指标。利用该方法对典型激光干扰图像进行评估,结果表明:在不同入射功率和不同光斑位置情况下,所提评估指标比单独使用结构相似度的评估指标具有更大的取值范围和更明显的非线性变化特征。这说明:该指标能够反映光电成像系统激光干扰过程的丰富细节,更加适合激光干扰效果的评估。     

基于卷积神经网络的卫星网络协调态势评估方法

为充分发掘利用海量卫星网络数据,提高决策效率,加强空间频轨资源获取与储备的分析手段,尤其是对地球静止轨道资源的协调获取问题,提出基于机器学习算法的卫星网络态势评估策略。通过对卫星网络协调因素进行特征分析,选择卷积神经网络(Convolution Neural Network, CNN)为目标算法模型,并建立算法模型的训练数据集及Label规则,采用分裂信息增益度量方法对数据进行降维处理,建立CNN评估模型,并进行了验证分析。结果表明,CNN模型对卫星网络协调态势评估问题测试的正确率高达80%以上,具有较高的评估效能。随着数据量的增多,CNN评估效果逐步提升,是一种在卫星网络协调态势分析、资源储备的有效评估方法。     

Research and development of training pistols for laser shooting simulation system

Firearm shooting simulators are effective means for training the personnel in armed forces, police and shooting athletes. Shooter–weapon is a complex biomechanical system, therefore the best training quality is achieved when the process of a weapon shot is reconstructed in a training simulator and its training weapon mimics the (feeling) perception of the real weapon usage. Dynamics of motions of a handgun simulator held in the hand of a shooter by its grip during the shot is analysed theoretically and experimentally. Breech lock mechanism of the simulator is actuated pneumatically by supplying compressed air in pulses from external pressure source. Analysis of the obtained simulation results and experimentally recorded motion parameters of the training weapon body reveals that application of pneumatic drives is a reasonable option to simulate recoil perception of a pistol.     

Gabor-CNN for object detection based on small samples

Object detection models based on convolutional neural networks (CNN) have achieved state-of-the-art performance by heavily rely on large-scale training samples. They are insufficient when used in specific applications, such as the detection of military objects, as in these instances, a large number of samples is hard to obtain. In order to solve this problem, this paper proposes the use of Gabor-CNN for object detection based on a small number of samples. First of all, a feature extraction convolution kernel library composed of multi-shape Gabor and color Gabor is constructed, and the optimal Gabor convolution kernel group is obtained by means of training and screening, which is convolved with the input image to obtain feature information of objects with strong auxiliary function. Then, the k-means clustering algorithm is adopted to construct several different sizes of anchor boxes, which improves the quality of the regional proposals. We call this regional proposal process the Gabor-assisted Region Proposal Network (Gabor-assisted RPN). Finally, the Deeply-Utilized Feature Pyramid Network (DU-FPN) method is proposed to strengthen the feature expression of objects in the image. A bottom-up and a top-down feature pyramid is constructed in ResNet-50 and feature information of objects is deeply utilized through the transverse connection and integration of features at various scales. Experimental results show that the method proposed in this paper achieves better results than the state-of-art contrast models on data sets with small samples in terms of accuracy and recall rate, and thus has a strong application prospect.     

Theoretical calculation and experimental study on the interaction mechanism between TKX-50 and AP

The combination of 5,5′-bistetrazole-1,1′-diolate (TKX-50) and ammonium perchlorate (AP) can make greater use of the chemical energy of TKX-50 based energetic materials. The research on the interaction mechanism between TKX-50 and AP is very important for designing TKX-50-AP compounds and judging the formation feasibility of composite particles, which can lay a theoretical foundation for the preparation of TKX-50-AP mixed crystals and the application of TKX-50 in propellant, propellant and explosive. Herein, in order to research the interaction mechanism between TKX-50 and AP, density-functional theory calculation was applied to optimize three configurations of TKX-50-AP compounds. The geometry structure, electrostatic potential and binding energy of the compounds were predicted, and the electronic density topological analysis was also carried out. Then TKX-50-AP mixed crystals structures were constructed, and the radial distribution function of H–O and H–N in mixed crystals was calculated. Finally, solvent/non-solvent method was applied to prepare TKX-50-AP composites, and the infrared spectroscopy and the non-isothermal decomposition performance of the composites were characterized. Results show that the superposition of positive charges in TKX-50 molecule and negative charges in AP makes the electrostatic potential distributions of TKX-50-AP compounds different from that of TKX-50 and AP. The interaction energies of TKX-50-AP 1, TKX-50-AP 2 and TKX-50-AP 3 are 39.743 kJ/mol, 61.206 kJ/mol and 27.702 kJ/mol, respectively. The interaction between TKX-50 molecules and AP molecules in TKX-50-AP mixed crystals both depends on hydrogen bonds and van der Waals force, and the number and strength of hydrogen bonds are significantly greater than that of van der Waals force. The composition of AP and TKX-50 makes the absorption peak of the five-membered rings and NH₃OH⁺ of TKX-50 shift to low wavenumber in the infrared spectroscopy. In general, TKX-50 interacts with AP via hydrogen bonds and van der Waals force, and the calculated results are in good agreement with the experimental results. The composition of TKX-50 and AP can also prolong the decomposition process.