基于模糊支持向量机的飞机飞行动作识别

传统的支持向量机由两类扩展到多类问题时,出现不可分区域。针对飞行动作识别提出解决这一现象的模糊支持向量机。采用模糊支持向量机对某型飞机飞行动作进行识别。实际飞参数据(6种飞行动作模式)的识别结果表明,模糊支持向量机较传统的多类支持向量分类器在飞机飞行动作识别率上有显著提高。     

JMASS环境下的飞行仿真组件集成研究

简要介绍了联合建模与仿真系统(JMASS)的基本概念,分析了JMASS的结构和组成。进一步以一个飞行仿真组件的集成为实例,阐述了如何进行基于JMASS仿真环境的仿真子系统开发,特别研究了如何给已有仿真组件增加设计专门针对JMASS环境而的接口的技术,使现有组件能够顺利集成到JMASS环境下,并使之正确运行。     

空客A330飞行模拟器ECAMCONTROL面板的适应性改造

由于两种型号的A330飞行模拟器ECAM CONTROL面板备件不通用，在无内部原理图的前提下，依据电路基础知识，合理推测新备件内部原理并搭建测试电路验证，成功实施了改造，使新备件在旧模拟器上获得了正常使用。     

Performance analysis of variable speed tail rotors with Gurney flaps

Gurney Flaps (GFs) are used for improving the performance of variable speed tail rotors. A validated analytical helicopter model able to predict the main and tail rotor power is utilized. The fixed height GF has substantially small influence on the tail rotor power in hover and low to medium speed forward flight, and can obtain significant power reduction in high speed flight. This ability can be enhanced by decreasing the tail rotor speed. With the deployment of GF, the collective pitch of the tail rotor decreases, and the maximum tail rotor thrust increases. The GF can compensate the reduction of the maximum thrust by the decrease in the tail rotor speed. The GF with a height of 5% of the chord length can almost remedy 50% of the thrust reduction introduced by decreasing 10% of the tail rotor speed. With the increase of GF height, the maximum thrust generated by the tail rotor increases. The GF with larger height can cause the increase in the tail rotor power in hover and low to medium speed flight. The retractable GF can obtain more power savings than the fixed height GF. However, the benefit is substantially small even in high speed flight. Considering the side effects introduced by the active GF, the fixed height GF may be more preferable. The mechanism for the retractable GF to generate more tail rotor thrust is to increase the lift in advancing side due to the higher dynamic pressure.     

基于改进GPC的无人直升机动态路径规划

针对小型无人直升机航迹受到风场扰动和导航系统定位误差影响下的航迹最优规划问题,建立了风扰动和导航误差影响下的飞行航迹线性模型。基于混合整数规划思想,采用粒子滤波改进广义模型预测控制算法实时规划航迹,降低了导航定位误差造成的航迹估计偏差,提高了航迹估计精度。仿真结果表明,该算法能够生成三维可行航迹并躲避障碍物,且规划时间和无人机能耗较传统方法显著减少。     

飞机驾驶舱视觉告警信号设计的基本要求分析

飞机驾驶舱告警系统对提高飞行员工作效率和保障飞行安全具有重要的作用。本文主要概述了视觉告警信号的设计标准和信息编码的设计规定,并论述了相关标准中对颜色编码和告警字符的设计规定,为飞机驾驶舱视觉告警信号的设计提供相关设计参考。     

基于LADRC的无人直升机轨迹跟踪

无人直升机轨迹控制系统是对多输入/多输出强耦合非线性系统进行解耦控制的系统。为解决无人直升机轨迹控制效果依赖于直升机物理参数的测量和辨识精度以及外部扰动大小问题,提出了一种基于线性自抗扰控制(LADRC)的多回路无人直升机轨迹控制系统。首先建立无人直升机X-Cell的飞行动力学模型,并引入风切变、大气紊流和突风模型以更加准确模拟真实飞行环境;然后对X-Cell进行配平计算以验证动力学模型和配平算法的准确性,并选取一组配平值作为轨迹控制仿真的初始状态和操纵量;随后根据被控量的动力学方程阶次选取对应的一阶和二阶LADRC基本控制器,并结合时间尺度原理,自内向外依次构建无人直升机的姿态、速度和位置控制回路,将三回路串联从而建立了无人直升机轨迹控制系统;而后进行了稳定性分析,特征根计算结果表明轨迹控制系统镇定了X-Cell开环系统不稳定的动态特性;最后将该控制系统应用于各种扰动下直升机轨迹跟踪仿真,结果表明本文无人直升机轨迹控制系统能很好地实现带爬升率的"8"字形轨迹跟踪,且相比于基于比例积分和微分(PID)控制的轨迹控制系统,该控制系统具有更优的鲁棒性和抗扰性。     

基于遗传算法与评估模型的飞行载荷实测研究

为了得到飞行载荷实测所需的最优载荷方程,建立了可表征载荷方程数学意义和物理意义的评估模型,与遗传算法(GA)结合,以载荷方程评估驱动载荷方程建立,形成一种新的载荷方程建立方法——EMGA。通过建立某机翼根部剪力方程,比较了穷尽搜索(ES)法、传统GA和EMGA所建载荷方程的评估模型参数。最后将3种方法建立的方程用于飞行载荷实测。结果发现:和其他两种方法比较,本文提出的EMGA可得到最优的载荷方程;EMGA测得的飞行载荷分散性小,最优载荷方程的测量结果可作为最终的飞行载荷。     

直升机桨距主动控制对旋翼性能的影响

为摸索直升机桨距主动控制对旋翼性能的影响规律并揭示其机理,首先建立能够考虑2阶谐波桨距控制影响的旋翼气动力模型,进一步建立相应的直升机飞行动力学模型,将旋翼需用功率作为性能评估的依据,在全机配平状态下开展2阶谐波桨距控制对旋翼性能的影响研究.对于样例直升机,前进比为0.2时,施加任何2阶谐波桨距控制均使旋翼需用功率增加;前进比为0.35时,施加幅值为1.5°、初相位为90°的2阶谐波桨距控制使旋翼需用功率降低约5%.通过分析样例直升机桨盘平面迎角分布和阻力系数分布,总结出利用2阶谐波桨距控制提升旋翼性能的物理本质:当直升机处于高速、大载荷飞行状态时,施加适当的2阶谐波桨距控制可以改善桨盘平面迎角分布,推迟后行边桨叶失速,从而降低旋翼需用功率,有效提升旋翼性能.     

Intelligent modeling and identification of aircraft nonlinear flight

In this paper, a new approach has been proposed to identify and model the dynamics of a highly maneuverable fighter aircraft through artificial neural networks（ANNs）. In general, aircraft flight dynamics is considered as a nonlinear and coupled system whose modeling through ANNs, unlike classical approaches, does not require any aerodynamic or propulsion information and a few flight test data seem sufficient. In this study, for identification and modeling of the aircraft dynamics, two known structures of internal and external recurrent neural networks（RNNs） and a proposed structure called hybrid combined recurrent neural network have been used and compared.In order to improve the training process, an appropriate evolutionary method has been applied to simultaneously train and optimize the parameters of ANNs. In this research, it has been shown that six ANNs each with three inputs and one output, trained by flight test data, can model the dynamic behavior of the highly maneuverable aircraft with acceptable accuracy and without any priori knowledge about the system.