KUPS: Knowledge-Based Ubiquitous and Persistent Sensor Networks for Threat Assessment

We propose a knowledge-based ubiquitous and persistent sensor network (KUPS) for threat assessment, in which "sensor" is a broad characterization. It refers to diverse data or information from ubiquitous and persistent sensor sources such as organic sensors and human intelligence sensors. Our KUPS for threat assessment consists of two major steps: situation awareness using fuzzy logic systems (FLSs) and threat parameter estimation using radar sensor networks (RSNs). Our FLSs combine the linguistic knowledge from different intelligent sensors, and our proposed maximum-likelihood (ML) estimation algorithm performs target radar cross section (RCS) parameter estimation. We also show that our ML estimator is unbiased and the variance of parameter estimation matches the Cramer-Rao lower bound (CRLB) if the radar pulses follow the Swerling II model. Simulations further validate our theoretical results.     

Hybrid connectionist systems in research and teaching

There is a tremendous world-wide interest in the development of the theory and application of artificial intelligence (AI) and related techniques both in tertiary institutions and in industry. This paper presents a brief survey of overseas AI teaching programs together with a review of the teaching program in the University of South Australia. In addition, post-graduate projects undertaken by the Knowledge-Engineering Systems Group (KES), and sponsored by the Defence, Science and Technology Organisation (DSTO), are discussed. These involve expert systems, neural networks, fuzzy logic and genetic algorithms. It is shown by using a classical exclusive-OR problem that it is useful to use hybrid techniques which offer fast convergence in optimization problems. Although much of this work is still at an early stage, sufficient progress has been made to demonstrate the merit of using AI and related techniques to help create solutions to these problems     

气动计算软件集成系统中的远程控制

随着我国航空航天技术的飞速发展，气动计算软件集成技术日趋成熟，但用户在并行计算中需要手动输入的操作较多。鉴于此，通过编程开发了基于TCP／IP协议的FTP客户端应用程序，实现了对网格文件的信息采集、过滤并将其和参数、脚本文件等批量自动上传的功能。根据批处理文件中的命令，调用Windows平台自带的客户端Telnet，向远程集群管理节点发出命令，远程启动服务器集群的并行计算任务。最后，在客户端实现了远程控制服务器集群上的计算流体力学软件Fluent进行并行计算。结果表明：使用该远程控制系统能够减少用户输入操作，提高计算效率，保证数据的实时更新。     

Intelligent control of a planning system for astronaut training

This work intends to design, analyze and solve, from the systems control perspective, a complex, dynamic, and multiconstrained planning system for generating training plans for crew members of the NASA-led International Space Station. Various intelligent planning systems have been developed within the framework of artificial intelligence. These planning systems generally lack a rigorous mathematical formalism to allow a reliable and flexible methodology for their design, modeling, and performance analysis in a dynamical, time-critical, and multiconstrained environment. Formulating the planning problem in the domain of discrete-event systems under a unified framework such that it can be modeled, designed, and analyzed as a control system will provide a self-contained theory for such planning systems. This will also provide a means to certify various planning systems for operations in the dynamical and complex environments in space. The work presented here completes the design, development, and analysis of an intricate, large-scale, and representative mathematical formulation for intelligent control of a real planning system for Space Station crew training. This planning system has been tested and used at NASA-Johnson Space Center     

双极值模糊软K-代数

引入双极值模糊软K-代数的概念,讨论关于双极值模糊软集的交,并运算的相关性质以及它在模糊软K-同态下像的性质。通过双极值模糊集的（t,s）-水平截集给出了双极值模糊软K-代数的等价刻画。     

Application of hybrid metaheuristics in sensor management

The capacity of today's sensor systems has rapidly grown beyond the borders of human controllability. The real time (re)scheduling that is needed to manage them can only be done using state of the art planning and scheduling methods. This paper discusses one of the most recent and promising advances in operations research and artificial intelligence planning systems: hybrid metaheuristics. These robust heuristic search techniques efficiently use limited time and computing resources to produce good schedules within short term. Simulations show the use and performance of these techniques in multi-function radar systems.     

基于MATLAB的海上目标威胁程度仿真研究

介绍了MATLAB模糊逻辑工具箱的基础知识和基本用法,以及海上目标威胁程度等级计算的基本方法,并在此基础上提出了运用MATLAB模糊逻辑工具箱进行海上目标威胁程度等级的仿真。根据海上目标威胁程度等级计算的基本要求和模糊推理系统的构造方法,确定了系统各变量的隶属度函数,制定了系统的模糊规则。仿真结果表明,运用MATLAB模糊逻辑工具箱进行海上目标威胁程度等级的仿真,建立系统隶属度函数和模糊规则非常快捷、方便,各输入变量对输出变量目标威胁程度等级的影响非常直观。     

面向机载应用的领域专用加速器研究

机载环境下数据处理规模的剧增以及人机混合智能的应用使得传统的以CPU 为核心计算单元的架构 已不能满足计算需求。在满足延时、精度等指标的情况下,选用高能效的处理器或处理器组合来快速准确地处 理这些数据成为机载计算领域面临的重要问题。按照常规处理器、领域专用加速器两大类型对各自主要代表性 处理器的架构特点进行了分析和总结,得出了各类处理器在机载情况下的主要适用场景和应用情况。根据领域 专用的设计思想开发了面向数据关联应用的专用加速器,对数据关联算法中的统计距离计算和分簇处理这两个 计算瓶颈进行了定制化的加速设计,并在基于FPGA 的平台上进行了测试验证,结果表明,加速器对于统计距 离计算的加速效果约为FT2000/4 单核性能的10 倍,对于分簇处理的加速效果约为FT2000/4 单核性能的3 倍, 整体运算速度相比FT2000/4 处理器的单核提升了5 倍。     

模糊逻辑控制在过失速机动飞行中的应用

首先建立了进行过失速机动时飞机的动力学数学模型,并在分析了模糊数学和模糊逻辑控制特点的基础上,设计了模糊逻辑控制器 ( FLC)应用于 2种典型的过失速机动 ( 70°迎角定常飞行和眼镜蛇机动 )的数字仿真。结果表明,采用模糊逻辑控制器,调整模糊控制器中有关参数或采用带修正因子的模糊控制器,能够使得飞机在更短的时间内完成过失速机动,同时改善了飞机的动态品质。     

AI techniques in uninhabited aerial vehicle flight

This describes the development of an application of artificial intelligence (AI) for unmanned aerial vehicle (UAV) control. The project was part of the requirements for a class in AI at NOVA Southeastern University and a beginning project at NASA Wallops Flight Facility for a resilient, robust, and intelligent UAV flight control system. A method is outlined which allows a base level application for applying an artificial intelligence method, fuzzy logic, to aspects of control logic for UAV flight. One element of UAV flight, automated altitude hold, has been implemented and preliminary results displayed.     

航空人工智能概念与应用发展综述

针对航空人工智能发展的迫切需要,对人工智能定义、智能等级划分两个基本问题进行讨论,指出人工智能近期难以存在公认定义,需辩证看待人工智能航空应用的不确定性和确定性,对执行特定任务的智能系统进行智能等级划分因不符合当前主流认知规律而没有必要。从总体历史沿革、机载导弹、机载系统及可信等角度阐述航空人工智能应用的发展特点和态势,突出了可信航空人工智能研究作为行业应用前提性条件的重要性。     

基于云平台的飞行试验数据中心架构设计

近年高密度航天发射任务和不断提升的数据采集处理能力使得试验数据规模呈几何级数增长,但目前采用的传统试验数据存储管理和应用服务手段已难以适应任务发展的形势要求.针对航天任务参试系统多、地域跨度广、试验数据采集源多、规模增长迅速、业务应用复杂及用户多样等特征需求,采用云存储和云计算技术,提出了一种基于云平台的分布式数据中心架构,论述了基于两级数据中心的应用服务模式,实现了两级数据中心的整体设计,支持全系统计算资源、存储资源、网络资源和业务资源的统一调度管理,支持计算节点、存储节点和网络节点的动态扩展,能够较好地满足海量飞行试验数据的长期存储管理和高效应用服务需求.     

人工智能技术在航空发动机孔探检测中的应用进展

孔探是当前航空发动机检修过程中应用最多的无损检测方法,也是孔探图像的唯一获取途径。近年来,深度学习等人工智能方法开始被应用到航空发动机损伤分类、检测中,为实现航空发动机检修智能化提出了一些现行有效的方法,具有重要的工业应用价值。本文概述了航空发动机孔探检测的发展和优缺点,综述了专家系统和机器学习人工智能方法在发动机孔探图像方面的应用进展,总结了基于孔探图像实现航空发动机孔探检测智能化面临的一些挑战。     

ISE: intelligent synthesis environment for future aerospace systems

The Intelligent Synthesis Environment (ISE) being developed by NASA, UVA, and JPL for significantly enhancing the rapid creation of innovative affordable products and missions is described. ISE uses a synergistic combination of leading-edge technologies, including high-performance computing, high-capacity communications and networking, virtual product development, knowledge-based engineering, computational intelligence, human-computer interaction, and product information management. The environment will link scientists, design teams, manufacturers, suppliers, and consultants who participate in the mission synthesis, as well as in the creation and operation of the aerospace system. It will radically advance the process by which complex science missions are synthesized, and high-tech engineering systems are designed, manufactured, and operated. The evolution of engineering design is described along with the shortcomings of current product development techniques. The need for ISE to create high-science payoff missions and aerospace systems at affordable costs is discussed. The five major components critical to ISE and some of their sub-elements are described: namely, human-ISE interaction; infrastructure for distributed collaboration; rapid synthesis and simulation tools; intelligent life-cycle system integration; and cultural change in the creative process. Related government and industry programs are outlined and future impact of ISE on complex missions and aerospace systems is discussed.     

量子计算及其在空气动力学中的应用前景综述

量子计算是最重要的后摩尔计算技术之一，拥有经典计算机无可比拟的超强计算能力，未来能够对各行业应用产生颠覆性的影响。针对量子计算给空气动力学带来的机遇和挑战，详细综述了量子计算机、量子算法、量子底层软件栈等方面的研究进展。结合空气动力学领域常用的基础方法，在综述量子计算线性方程组求解、插值操作、数值积分、优化搜索等最新进展的基础上，结合典型量子算法深入分析了量子计算在空气动力学领域的应用前景，并指出了需要重点关注的研究方向。     

Methodology for cost-effective software fault tolerance formission-critical systems

A computing capabilities continue to advance, there will be a concurrent rise in the number of both hardware and software faults. These will be caused by the greater volume of more complex software, by the increased number of untested software states, and by more incidents of hardware/software interaction faults as a result of increased hardware speed and density. The traditional software implemented fault tolerance: approaches have been successfully utilized in life-critical systems, such as digital flight controls, where their additional costs can be easily justified. Examples include N-Version Programming and Recovery Block approaches. However, there is still a need for dependable computing for mission-critical applications as well. Often, these traditional techniques are avoided for mission-critical systems due to the difficulty in justifying their extra up-front development cost. We provide an alternative for the high “sunk cost” of traditional software fault tolerance techniques. The methodology, called data fusion integrity processes (DFIPs), is a simple, yet effective technique for mission-critical systems. In addition, the approach establishes a framework from which other costlier, more extensive traditional techniques can be added. We present details of the DFIP methodology and a DFIP framework for Ada programs. We also briefly discuss development of a DFIP code generation system which exploits Java that will enable users to quickly build a DFIP framework in Ada, and select reusable DFIP component methods     

What is System Wide Information Management (SWIM)?

System wide information management (SWIM) has been identified by the FAA as a key enabler for the next generation air traffic system (NGATS). Boeing has been working with the FAA since 2004 to define the role of SWIM within the framework of the existing and envisioned set of national airspace system (NAS) communications systems and air traffic operations. SWIM, as an information management infrastructure, in effect creates a "system of systems" of existing (and new) systems (or software applications, or simply applications) interacting through SWIM services. Describing SWIM in such a context is only fruitful when adopting the point of view of each person based on their role and perspective of airspace operations, be they a user, an application developed, or a SWIM implemented. This paper describes the current vision of SWIM from multiple viewpoints (operational, functional, physical) in an attempt to provide a broad perspective of SWIM to a technical audience of mixed backgrounds     

Computational modeling for multiphase flows with spacecraft application

Many engineering applications involve interactions between solid, gas and liquid phases under normal or micro-gravity conditions. Numerical simulations of such fluid flows need to track the location and the shape of the fluid interface as part of the solution. The merits and basic characteristics of various approaches for numerical computations of interfacial fluid dynamics are reviewed. The computational challenges include: (i) the algorithmic complexity for handling irregularly shaped moving boundaries that can experience merger and break-up; (ii) resolution refinement techniques to maintain desirable resolution of length scales, in accordance with the evolving fluid dynamics; (iii) data structure needed to support identification of the interface and satisfaction of the physical laws in the bulk fluids as well as around the phase boundaries; and (iv) efficient parallel processing techniques required for practical engineering analysis. The present review focuses on these issues related to the Lagrangian–Eulerian approach, utilizing the immersed boundary method with marker-based tracking, as the main framework for interfacial flow computations on Cartesian grids. Specifically, we offer in-depth discussion of the organization and layout of the mesh systems for both fluid and interface representations, local adaptive refinement on two-dimensional/three-dimensional (2D/3D) Cartesian grids, and multi-level domain decomposition method that utilizes Hilbert space filling curves for parallel processing strategy. The effectiveness of individual components and overall algorithm are presented using various tests such as, binary drop-collision computations to highlight grid adaptation and interface tracking algorithms to handle complex interface behavior, and bubble/droplet placed in a vortex field with various density/viscosity ratios across interfaces to address load balancing and scalability aspects of parallel computing. A time-dependent draining flow problem motivated by spacecraft applications is presented to aid spacecraft design efforts.     

基于细菌觅食优化算法的永磁同步电机位置伺服系统模糊控制策略

针对PID控制器参数固定而引起永磁同步电机(PMSM)位置伺服系统控制效果不佳问题,设计了基于细菌觅食优化算法的模糊控制器。该位置控制系统是以空间矢量控制为理论基础,由位置环、速度环、电流环构成的PMSM三闭环控制系统。在MATLAB/Simulink环境中将模糊控制器应用在系统位置环上。对比仿真结果发现,参数优化后的模糊控制器在系统位置环的作用更加优越,完全克服了传统PID控制器的缺点,能有效提高电机位置控制的快速性和准确性。     

Detection of small objects in clutter using a GA-RBF neural network

Detection of small objects in a radar or satellite image is an important problem with many applications. Due to a recent discovery that sea clutter, the electromagnetic wave backscatter from a sea surface, is chaotic rather than purely random, computational intelligence techniques such as neural networks have been applied to reconstruct the chaotic dynamic of sea clutter. The reconstructed sea clutter dynamical system which usually takes the form of a nonlinear predictor does not only provide a model of the sea scattering phenomenon, but it can also be used to detect the existence of small targets such as fishing boats and small fragments of icebergs by observing abrupt changes in the prediction error. We applied a genetic algorithm (GA) to obtain an optimal reconstruction of sea clutter dynamic based on a radial basis function (RBF) neural network. This GA-RBF uses a hybrid approach that employes a GA to search for the optimum values of the following RBF parameters: centers, variance, and number of hidden nodes, and uses the least square method to determine the weights. It is shown here that if the functional form of an unknown nonlinear dynamical system can be represented exactly using an RBF net (i.e., no approximation error), this GA-RBF approach can reconstruct the exact dynamic from its time series measurements. In addition to the improved accuracy in modeling sea clutter dynamic, the GA-RBF is also shown to enhance the detectability of small objects embedded in the sea. Using real-life radar data that are collected in the east coast of Canada by two different radar systems: a ground-based radar and a satellite equipped with synthetic aperture radar (SAR), we show that the GA-RBF network is a reliable detector for small surface targets in various sea conditions and is practical for real-life search and rescue, navigation, and surveillance applications