基于机器学习的单孔绝热气膜冷却效率分布预测研究

为了研究利用机器学习技术对绝热冷却效率进行直接预测的方法及特点,搭建了基于上采样卷积神经网络的机器学习模型,生成了用于训练以及验证的数值模拟数据集,使用了监督式学习的方法对模型进行了训练.训练使用反向传播算法和基于随机梯度下降的Adam优化算法,输入模型的参数包括吹风比、主流湍流强度、喷射角、孔形状、孔尺寸,模型输出为...     

通信卫星技术综述

本文对通信卫星技术进行综述,叙述通信卫星设计过程中的限制条件;描述有效载荷、姿态和轨道控制、电源、测控、结构及热控等星上分系统的主要设计技术特征。     

Optimization of communication network topology for navigation sharing among distributed satellites

Navigation sharing among distributed satellites is quite important for coordinated motion and collision avoidance. This paper proposes optimization methods of the communication network topology to achieve navigation sharing. The whole communication network constructing by inter-satellite links are considered as a topology graph. The aim of this paper is to find the communication network topology with minimum communication connections’ number (MCCN) in different conditions. It has found that the communication capacity and the number of channels are two key parameters affecting the results. The model of MCCN topology for navigation sharing is established and corresponding method is designed. Two main scenarios, viz., homogeneous case and heterogeneous case, are considered. For the homogeneous case where each member has the same communication capacity, it designs a construction method (Algorithm 1) to find the MCCN topology. For the heterogeneous case, it introduces a modified genetic algorithm (Algorithm 2) to find the MCCN topology. When considering the fact that the number of channels is limited, the Algorithm 2 is further modified by adding a penalized term in the fitness function. The effectiveness of these algorithms is all proved in theoretical. Three examples are further tested to illustrate the methods developed in this paper.     

基于特征识别的整体壁板快速编程推理算法

航天器整体壁板的编程效率已成为型号研制过程中的主要瓶颈之一.本文首先阐述特征识别技术在数控编程中的应用和发展现状.与传统编程过程先总体规划,再逐条编程的总-分方法不同,特征编程采取先生成单个特征的刀轨,再完成整个零件程序的分-总方法,易于覆盖从毛坯向模型最终状态全过程.在此基础上,提出了单特征和多特征数控推理算法,完成了整体壁板快速编程系统的开发.实践证明,使用该方法能够初步实现整体壁板数控加工程序的自动生成.     

Advances and challenges on springback control for creep age forming of aluminum alloy

Creep age forming(CAF) is an advanced forming technology that combines creep deformation and age hardening processes. When compared with the conventional forming technologies including roll bending and shot-peen forming, CAF has many advantages of low residual stress,excellent dimensional stability, good service performance and short production cycle. It is an optimal technique for precise manufacturing for shape and properties of large-scale complicated thinwalled components of light-weight and...     

Space time clock: An on-chip clock with 10-12 instability

High precision and stable clock is extremely important in communication and navigation. The miniaturization of the clocks is considered to be the trend to satisfy the demand for5G and the next generation communications. Based on the concept of meter bar and the principle of the constancy of light velocity, we designed a micro clock, Space Time Clock(STC), with the size smaller than 1 mm × 1 mm and the power dissipation less than 2 m W. Designed in integrated circuit of 0.18 μm technology, the in...     

A spanwise loss model for axial compressor stator based on machine learning

In the early stage of aircraft engine design, the through-flow method is an important tool for designers. The accuracy of the through-flow method depends heavily on the accuracy of the loss model. However, most existing models cannot(or cannot well) provide the spanwise loss distribution. To construct an effective spanwise loss model, both turbomachinery knowledge and machine learning skills were used in this paper. A large number of numerical simulations were carried out to build a database con...     

A review of friction stir joining of SiCp/Al composites

SiCp/Al composites have excellent comprehensive properties and have been widely used in aerospace, automotive industry and other fields. Due to the huge difference in performance between SiC particles and matrix alloys, traditional fusion welding methods are difficult to meet the join requirements of SiCp/Al composites. Friction stir joining (friction stir welding), as a solid phase joining process, has been proved to be a new technology with fine prospect in joining SiCp/Al composites compared with fusion welding process. Although some progress has been made in recent years, there are still full of challenges. In this paper, the research status of friction stir joining of SiCp/Al composites in recent years is expatiated, including the weldability of SiCp/Al composites, the macrostructure and the microstructure of joints, mechanical properties of joints, and tool wear and monitoring. Furthermore, the existing challenges of friction stir joining of SiCp/Al composites are summarized and the future development directions are prospected.     

基于浮空器的新型应急通信监测系统

介绍了一种新型的机动式空中应急通信监测系统,该系统以机动式系留气球和小型遥控飞艇为空中平台,搭载各种通信、侦察、监测等电子设备,具有快速灵活、机动性强、费用低廉等特点,能够适应复杂环境,面对突发事件时可以快速布置到任何需要的地方。     

基于SVM算法的虚假航迹识别

针对云雨杂波和主被动干扰导致多雷达传感器产生虚假目标航迹的问题,利用支持向量机(SVM)算法的自主学习能力,通过构建基于数据驱动的判别模型进行虚假航迹识别。针对航迹起始得到的目标潜在航迹,利用人工智能数据驱动、自学习的特点,设计了SVM算法。通过对已标记真假的目标航迹样本进行离线学习,形成虚假航迹识别的SVM分类器,实现了基于数据驱动的判别模型代替先验知识规则约束的固定模型,并在工程应用中,利用SVM分类器在线识别虚假航迹,完成实时剔除。通过实测雷达数据实验验证,该算法的目标虚假航迹准确率高达95%以上,完全满足实际的工程应用需求。相比基于阈值或规则进行硬性判断的传统虚假航迹识别方法,所提出的算法不仅提高了准确率,还具有较高的实时性,能够适应复杂多变的杂波环境,在实际应用中具有更强的适应性和实用性。因此,提出的基于SVM算法的虚假航迹识别方法对于密集杂波场景下的虚假航迹剔除问题具有显著的实际应用价值。