DDBN的无人机决策推理模型参数学习

针对复杂战场环境下的无人机决策推理模型参数学习的问题,提出基于遗传算法的离散动态贝叶斯网络参数学习算法。该算法将模型网络参数的最大似然估计函数作为遗传算法的适应度函数,在全局进行并行优化搜索,得到最优的网络参数,从而提高了决策推理模型对复杂环境的快速适应。仿真结果表明,该算法可以获得准确的离散动态贝叶斯网络参数,能够有效地解决复杂战场环境下无人机威胁评估问题,为无人机的自主任务决策提供有效的参数保障。     

一种基于数据辅助的PSK信噪比估计新方法

针对复高斯信道中的PSK系统,文章提出了一种新的简便的信噪比估计算法。与传统的基于数据辅助的信噪比算法比较表明,新算法在保持较好的估计性能的同时,能够有效的降低计算复杂度,适合硬件实现。     

Multi-scale traffic vehicle detection based on faster R-CNN with NAS optimization and feature enrichment

It well known that vehicle detection is an important component of the field of object detection. However, the environment of vehicle detection is particularly sophisticated in practical processes. It is compara-tively difficult to detect vehicles of various scales in traffic scene images, because the vehicles partially obscured by green belts, roadblocks or other vehicles, as well as influence of some low illumination weather. In this paper, we present a model based on Faster R-CNN with NAS optimization and feature enrichment to realize the effective detection of multi-scale vehicle targets in traffic scenes. First, we proposed a Retinex-based image adaptive correction algorithm (RIAC) to enhance the traffic images in the dataset to reduce the influence of shadow and illumination, and improve the image quality. Second, in order to improve the feature expression of the backbone network, we conducted Neural Architecture Search (NAS) on the backbone network used for feature extraction of Faster R-CNN to generate the optimal cross-layer connection to extract multi-layer features more effectively. Third, we used the object Feature Enrichment that combines the multi-layer feature information and the context information of the last layer after cross-layer connection to enrich the information of vehicle targets, and improve the robustness of the model for challenging targets such as small scale and severe occlusion. In the imple-mentation of the model, K-means clustering algorithm was used to select the suitable anchor size for our dataset to improve the convergence speed of the model. Our model has been trained and tested on the UN-DETRAC dataset, and the obtained results indicate that our method has art-of-state detection performance.     

Transverse relaxation characteristic and stress relaxation model considering molecular chains of HTPB coating based on pre-strained thermal aging

In order to accurately describe the transverse relaxation characteristic and stress relaxation modulus of HTPB coating during pre-strain thermal aging process, a one month thermal aging test was carried out at 70 C with pre-strain of 0％, 3％, 6％ and 9％, respectively. The low-field 1H NMR and stress relaxation modulus tests were carried out for HTPB coating at different aging stages. The stress relaxation model considering the molecular chains was proposed according to the changes of crosslinking chain and dangling chain of HTPB coating during pre-strain aging. The results showed that with the increase of aging time, the decay rate of transverse relaxation curve became faster, the transverse relaxation time decreased, the value of combined parameter qMrl increased, the proportion of crosslinking chain decreased, while the proportion of dangling chain increased. Moreover, the stress relaxation modulus increased, the crosslinking network structure of HTPB coating became denser and the degree of cross-linking increased. At the initial aging stage, the pre-strain will destroy the crosslinking network structure of HTPB coating to a certain extent. With the increase of aging time, the effect of pre-strain will gradually weaken and the influence of aging on materials will gradually increase. The correlations between the stress relaxation model considering the molecular chains and the test results were more than 0.9950, which can accurately describe the stress relaxation modulus of HTPB coating during the pre-strain thermal aging process.     

基于D-S证据推理的多传感器信息融合技术在战场目标识别中的应用

近年来,多传感器信息融合技术已经在许多领域得到了广泛的应用,该技术也可以用于战场目标识别.在简单介绍了多传感器信息融合技术的概念和方法之后,详细阐明了D-S证据推理的原理及其应用于战场目标识别的方法,并进行了仿真处理.仿真结果说明,基于D-S证据推理的多传感器信息融合技术,是解决目标识别问题的一种有效方法.     

论赤壁之战敌对双方战争指导的优劣得失

发生在建安十三年(公元208年)的赤壁之战以其深远独特的影响、丰富多样的作战形式在三国乃至整个中国军事史上占据着不可替代的地位。它是一场典型的以弱胜强、以少胜多的战争,是一场囊括了野战、攻城、追击、遭遇、火攻、退却、水战等多种作战形式的战争,是中国历史上第一次在长江流域进行的大规模江河作战,同时又是中国历史上第一次企图通过江河作战而谋求实现统一而最终失败的战争。无论从大战略的高度来看,还是从军事战略的角度来分析,赤壁之战都是一场具有多种典型价值的战争。今天,我们分析战争敌对双方曹军与孙刘联军战争指导的优劣得失,仍能获得历史的经验与有益的启示。     

紧跟中国特色军事变革走向加速培养复合型军事指挥人才

中国特色军事变革的走向,决定着我军人才队伍建设的方向.复合型军事指挥人才培养,是我军面对的一个崭新课题.要科学解析复合型军事指挥人才内涵特征和主导地位;加速构建复合型军事指挥人才培养的主体格局;积极推动复合型军事指挥人才培养良性发展.     

坚持用科学发展观指导部队建设

坚持用科学发展观指导部队建设,就是要深入学习,切实强化运用科学发展观指导实践的自觉性和坚定性;理清思路,不断增强指导部队建设的科学性和前瞻性;改进作风,真正确立与科学发展观相适应的领导方式和工作方法;改革创新,努力提高部队建设科学发展的新起点。     

弱拓扑下集值最优化问题的通有稳定性

用函数的上图象之间的Hausdoff距离定义最优化问题目标函数间的距离。在此弱拓扑下研究定义在紧距离空间上具有普遍意义的最优化问题的稳定性;指出在Baire分类意义下大多数这类问题的解是通有稳定的。     

基于微分求积法的高超声速机翼蒙皮颤振研究

机翼蒙皮在高超声速气流中会发生颤振等气动弹性问题,破坏结构.引入微分求积方法,可以有效地分析机翼蒙皮的颤振问题.将机翼蒙皮等效成薄板,基于一阶活塞理论,根据克希霍夫假设及弹性理论建立蒙皮的气动弹性偏微分方程,采用微分求积法将偏微分方程离散为常微分方程,并根据频率重合理论对颤振问题进行求解.得到的颤振速度与有限元方法计算结果进行比较,误差为0 58％,验证了微分求积法在求解颤振偏微分方程时的有效性.分析了蒙皮面积、厚度、纵横比等不同参数对蒙皮颤振速度的影响.结果表明,颤振速度随蒙皮面积的增大而减小,随纵横比、厚度的增大而增大.