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。     

基于微分进化算法的二自由度PID控制器参数优化

针对二自由度PID控制器参数多、调节困难等问题,提出了一种基于微分进化算法参数调节优化方法。证明了微分进化算法能够收敛到平稳点,并具有概率全局收敛性。研究了二自由度PID控制器参数与抑制特性、跟踪特性的关系,并将微分算法与遗传算法、粒子群算法的参数优化结果进行了比较。仿真验证表明,微分算法能够更好地实现二自由度PID控制器参数的调节,具有优异的跟踪特性和抑制特性。     

基于共轭次梯度算法的磁传感器安装误差校正

随着头盔显示技术的发展,对头盔电磁定位的精度要求越来越高,在现有的加工工艺和机上安装条件下,要提高定位精度,必须对传感器安装误差进行校正。通过坐标转换原理对安装误差进行建模,在此基础上利用最小二乘原则选取目标函数,将校正过程抽象为最优化问题求解。提出一种基于共轭次梯度算法的最优化问题求解方法,实现了传感器安装误差校正。利用MATLAB上对校正算法进行仿真,仿真结果表明,共轭次梯度算法简洁易用、校正精度高、收敛速度快,能够明显提高磁场测量精度。     

保序调整对线性回归影响的试验分析

采用数学试验方法模拟随机变量,考察满足序关系的变量关于自变量的线性回归,研究并对比在这种情况下直接应用最小二乘线性回归与先对观察到的因变量使用PAVA算法进行保序调整再应用最小二乘线性回归的优劣。结果表明实际应用中,首先进行PAVA算法作调整并不一定是好的,尤其当数据量比较大的时候,其并不能提高拟合效果反而增加工作量。当因变量满足序关系时,直接做最小二乘回归,无需对因变量使用PAVA算法作调整。     

A new inversion method of plasma density distribution of plasmasphere in the geomagnetic equatorial plane from IMAGE data

The plasma density distribution of plasmasphere in the geomagnetic equatorial plane can help us study the magnetosphere like plasmasphere, ionosphere and their kinetics. In this paper, we introduce a new inversion method, GE-ART, to calculate the plasma density distribution in the geomagnetic equatorial plane from the Extreme Ultraviolet (EUV) data of IMAGE satellite under the assumption that the plasma density is constant along each geomagnetic field line. The new GE-ART algorithm was derived from the traditional Algebraic Reconstruction Techniques (ART) in Computed Tomography (CT) which was different from the several existing methods. In this new method, each value of the EUV image data was back-projected evenly to the geomagnetic field lines intersected by this EUV sight. A 3-D inversion matrix was produced by the contributions of all the voxels contained in the plasmasphere covered by the EUV sensor. That is, we considered that each value of the EUV image data was relative to the plasma densities of all the voxels passed through by the corresponding EUV radiation, which is the biggest difference to all the existing inversion methods. Finally, the GE-ART algorithm was evaluated by the real EUV data from the IMAGE satellite.     

距离信息对DDFRC算法定位误差的影响与分析

在固定单站无源定位算法中,基于角度(Direct of Arrival)、角度变化率(Direct of Arrival Rate-of-Change)、多普勒频率(Doppler Frequency)和多普勒频率变化率(Doppler Frequency Rate-of-Change)4个观测信息实现定位(即DDFRC定位)算法仅通过单次观测即可实现对目标辐射源的定位。文中通过转移观测的卡尔曼滤波对定位结果进行平滑,较原有算法拥有更好的跟踪效果。同时,对定位误差进行了定量分析,并将距离信息引入算法的仿真分析之中,详细讨论了各个观测量误差在不同距离时对算法定位性能的影响,根据仿真结果,结合定位误差的定量分析对算法性能做出评价。通过仿真分析,得到了定位算法对不同距离下各参数的精度要求,从而为在实际系统中使用该定位算法提供了参考。     

具有星间链路的导航星座重构研究

针对具有星间链路的导航星座在卫星节点或链路失效情况下的重构优化设计问题,提出了一种基于遗传算法的设计方法。首先,根据导航星座的功能需求与设计约束,建立了星座综合重构优化设计模型。其次,提出了基于遗传算法的综合优化设计方法,并根据问题特性对遗传算法的具体操作进行了修改。最后,应用该方法对Walker 24/3/2构型星座及网状星间网络在节点和链路混合故障模式下的重构进行了优化设计。结果表明,基于该方法重构后的星座与网络拓扑性能能够得到一定程度的改善,证明了方法的可行性。     

基于新体制的单基线定位技术研究

结合工程应用,研究单基线利用模糊相位差对地面固定目标的高精度快速定位方案与关键技术,分析自适应随机惯性权值粒子群算法的性能。仿真结果表明,通过优化和改进,基于新体制的该算法能获得较好的定位性能。     

Aerodynamic multi-objective integrated optimization based on principal component analysis

Based on improved multi-objective particle swarm optimization (MOPSO) algorithm with principal component analysis (PCA) methodology,an efficient high-dimension multiobjective optimization method is proposed,which,as the purpose of this paper,aims to improve the convergence of Pareto front in multi-objective optimization design.The mathematical efficiency,the physical reasonableness and the reliability in dealing with redundant objectives of PCA are verified by typical DTLZ5 test function and multi-objective correlation analysis of supercritical airfoil,and the proposed method is integrated into aircraft multi-disciplinary design (AMDEsign) platform,which contains aerodynamics,stealth and structure weight analysis and optimization module.Then the proposed method is used for the multi-point integrated aerodynamic optimization of a wide-body passenger aircraft,in which the redundant objectives identified by PCA are transformed to optimization constraints,and several design methods are compared.The design results illustrate that the strategy used in this paper is sufficient and multi-point design requirements of the passenger aircraft are reached.The visualization level of non-dominant Pareto set is improved by effectively reducing the dimension without losing the primary feature of the problem.     

模糊控制器在全自动洗衣机中的应用

本文介绍了一种全自动洗衣机模糊控制策略，在传统洗衣机基础上，加装了模糊控制器，根据衣质衣量确定用水量，根据衣物的污浊度确定洗涤时间，再根据控制算法编制相应的程序，由模糊控制器控制洗衣机自动完成全部洗衣过程。