一种基于证据距离的多分类器差异性度量

 多分类器系统因其能够显著提升分类精度而引发了广泛关注。多分类器系统中各子分类器间的差异性是提升融合分类精度的先决条件。提出了一种基于证据距离的分类器系统差异性度量,同时基于该度量提出一种多分类器系统构造方法。综合了既有差异性度量、所提新差异性度量以及在训练样本集上的分类性能等多个指标,实现了多分类器系统的有效构造。实验结果表明,所提差异性度量及多分类器系统构造方法是合理的,能有效提升融合分类精度。     

Optimal Utilization of Satellite Communication Systems through Supervisory Control

Users of satellite communication systems being designed are charcterized by diversity. System designers now have the capability of serving thousands of simultaneous users; the users need not all follow the same system parameters. Diversity and characteristics are shown, and an attempt is made to list all the parameters desired by users. Usage of satellite communications systems is projected to serve a maximum of 200 000 users by means of 10 multipurpose satellites. It is shown that a supervisory control system is necessary to achieve optimal utilization of the existing resources.     

Improved NSGA-Ⅱ Multi-objective Genetic Algorithm Based on Hybridization-encouraged Mechanism

To improve performances of multi-objective optimization algorithms,such as convergence and diversity,a hybridization-encour-aged mechanism is proposed and realized in elitist nondominated sorting genetic algorithm (NSGA-Ⅱ).This mechanism uses the nor-malized distance to evaluate the difference among genes in a population.Three possible modes of crossover operators-"Max Distance","Min-Max Distance",and "Neighboring-Max"-are suggested and analyzed.The mode of "Neighboring-Max",which not only takes advantage of hybridization but also improves the distribution of the population near Pareto optimal front,is chosen and used in NSGA-II on the basis of hybridization-encouraged mechanism (short for HEM-based NSGA-Ⅱ).To prove the HEM-based algorithm,several problems are studied by using standard NSGA-II and the presented method.Different evaluation criteria are also used to judge these algorithms in terms of distribution of solutions,convergence,diversity,and quality of solutions.The numerical results indicate that the application of hybridization-encouraged mechanism could effectively improve the performances of genetic algorithm.Finally,as an example in engineering practices,the presented method is used to design a longitudinal flight control system,which demonstrates the obtainability of a reasonable and correct Pareto front.     

飞机飞行控制系统参数多目标优化设计研究

针对传统飞行控制律参数单目标优化设计不能同时满足多控制指标要求,且与飞行品质要求缺乏相关性,物理意义不明确等缺点,提出了一种基于改进粒子群算法的飞行控制律多目标优化设计方法。算法模拟鸟类捕食过程,使得种群随着"食物"的发现和消耗,聚集为数量和构成动态调整多个子群,且子群粒子速度也随之进行自适应变异,从而有利于维持种群的多样性,有效抑制早熟收敛现象发生。最后,使用改进的粒子群优化算法对某型飞机纵向控制律设计进行数值仿真,结果显示,算法有效提高控制律优化调参效率,结果满足期望的飞行品质要求。     

基于改进PSO的飞行控制律参数多目标优化方法

针对传统飞行控制律参数单目标优化设计不能同时满足多控制指标要求,且与飞行品质要求缺乏相关性,以及物理意义不明确等缺点,提出了一种基于改进粒子群算法的飞行控制律多目标优化设计方法。该算法模拟鸟类捕食过程,使得种群随着"食物"的发现和消耗,聚集为数量和构成动态调整多个子群,且子群粒子速度也随之进行自适应变异。从而,有利于维持种群的多样性,有效抑制早熟收敛现象发生。最后,还使用改进的粒子群优化算法对某型飞机横侧向控制律设计进行了数值仿真,结果显示该算法有效提高控制律优化调参效率,可满足期望的飞行品质要求。     

Improved NSGA-II Multi-objective Genetic Algorithm Based on Hybridization-encouraged Mechanism

To improve performances of multi-objective optimization algorithms, such as convergence and diversity, a hybridization- encouraged mechanism is proposed and realized in elitist nondominated sorting genetic algorithm （NSGA-Ⅱ）. This mechanism uses the normalized distance to evaluate the difference among genes in a population. Three possible modes of crossover operators--＂Max Distance＂, ＂Min-Max Distance＂, and ＂Neighboring-Max＂--are suggested and analyzed. The mode of ＂Neighboring-Max＂, which not only takes advantage of hybridization but also improves the distribution of the population near Pareto optimal front, is chosen and used in NSGA-Ⅱ on the basis of hybridization-encouraged mechanism （short for HEM-based NSGA-Ⅱ）. To prove the HEM-based algorithm, several problems are studied by using standard NSGA-Ⅱ and the presented method. Different evaluation criteria are also used to judge these algorithms in terms of distribution of solutions, convergence, diversity, and quality of solutions. The numerical results indicate that the application of hybridization-encouraged mechanism could effectively improve the performances of genetic algorithm. Finally, as an example in engineering practices, the presented method is used to design a longitudinal flight control system, which demonstrates the obtainability of a reasonable and correct Pareto front.     

民用飞机生产体系需求定义过程研究

建立高效灵活的民用飞机生产体系是民机项目研制成功的重中之重,也是民机制造商面对变化多端的民机市场必须解决的关键所在。民机产品的复杂性与多样性,决定了民机生产体系的复杂性与多样性。借助系统工程方法探索以需求为牵引对生产体系开展正向设计的方法,在充分研究民机产品与生产体系关系的前提下,借鉴目前广泛用于飞机产品需求定义的思路,本文对生产体系需求定义过程进行了研究,提出了利益攸关方模型和基础功能模型,将风险分析引入生产需求定义过程以提升目标系统的安全性,描述了从利益攸关方需要到需求和从风险应对需要到需求这两类需求捕获方法,提供了生产体系需求的分类方式并阐述了分类的目的,给出的典型生产体系需求来源可作为相关实践的模板。     

推力矢量飞机自适应控制系统仿真平台研究

研究了具有自修复功能的推力矢量飞机自适应控制系统的结构功能特点,研究了RHO优化控制算法实现在线控制器设计,利用MSLS辨识算法实现在线飞行参数辨识和等价空间算法、传感器信息融合技术和概率统计理论实现FDI算法。并且根据系统各个部分的算法,采用面向对象技术语言VC 6.0和三维图形语言OpenGL开发了仿真平台,利用仿真平台实时演示了飞机存在舵面故障情况下的飞行控制系统运行仿真,解决了飞机飞行过程中存在舵面损伤和气动参数变化的问题,该仿真平台可以根据需求进行飞机故障加载,具备完备的推力矢量飞机自适应控制系统仿真功能。     

Variable Structure Control of Catastrophic Course in Airdropping Heavy Cargo

The mathematical model of a transport aircraft would be subjected to a sudden change when heavy cargo is dropped off in airdropping, which exerts serious influences upon the safety of the aircraft. A variable structure controller is specially designed for handling the airdrop process. The nonlinear system is linearized by input-output feedback linearization using differential geometry theories. On this basis, an inner loop system for velocity and attitude tracking control is designed by using the exponentially approaching rule of the variable structure theory. The whole flight control system is integrated with the outer loop flight altitude control. Digital simulation evidences the applicability of the system to potentially catastrophic course in airdropping heavy cargo and provides robustness against system parameter perturbation.     

Improvement of Automatic Landing Through the Use of a Space Diversity ILS Receiving System

A space diversity method of receiving and processing ILS localizer information has been developed and flight tested. Multiple lateral ly separated antennas are used which sense the ILS signal on and around the approach path. Combining these signals suppresses ILS beam distortion produced by multipath signal interference and provides much improved guidance information to the landing aircraft control system.     

System of simulation training for unmanned aircraft

For proficiently operating an unmanned aircraft, the aircrew must be thoroughly trained. However, using practical equipment to train the aircrew is work of high cost and risk. In this paper, a system of simulation training for unmanned aircraft is introduced. Its function and composition are explained in detail. In practice, the system not only decreases training cost and risk, but also strengthens training effectiveness and diversity     

直接升力控制律的逆乃奎斯特阵列法设计

采用直接力控制可弥补常规飞机在轨迹操纵方面的不足,并产生某些新的运动模式 对飞机直接升力控制可的三种基本运动模式进行讨论,从中归纳出直接升力控制 设计就是输出解控制系统的设计问题。并以单纯直接升力控制方式为例,用逆乃奎斯特列方法设计了某飞机的直接升力系统,仿真结果表明ＩＮＡ方法是解决多变量解耦问题的有效方法。     

现代飞机自动地形跟随系统控制律的研究

自动地形跟随系统是现代飞机低空突防系统的一个重要组成部分,在利用地形遮蔽以提高飞机生存能力的军事领域具有重要的意义.本文以飞机纵向地形跟随控制系统为研究对象,应用适应角法设计了飞机纵向地形跟随控制律,并建立了相应的结构图和仿真验证模型.结果表明,设计的控制系统得到了良好的地形跟随效果.     

模型直升机悬停状态下飞行力学模型辨识

 直升机飞行力学模型的准确性对于直升机的控制系统设计具有非常重要的影响。采用常规的建模方法往往很难获得准确的飞行力学模型。为满足飞行控制系统设计的需要,提出了一种直升机飞行力学模型的系统辨识建模方法。该方法将机理建模方法与辨识建模方法相结合,首先利用状态子空间法获得直升机的近似飞行力学模型,再将机理建模提供的先验知识与子空间法辨识得到的模型相融合,限定主要参数,采用误差预报法进一步寻优得到较准确的直升机飞行力学模型。通过飞行试验,成功地辨识得到了悬停状态下模型直升机状态空间方程表达的线化飞行力学模型。所得的辨识结果能够准确预测出模型直升机的响应,可以应用于飞行控制系统设计当中。     

Satellite Tracking Simultaneous-Lobing Monopulse Receiving System with Polarization Diversity Capability

A 136-MHz to 10-GHz simultaneous-lobing monopulse receiving system, utilizing polarization diversity in both coherent (phase-lock) and noncoherent (nonphase-lock) operational modes, has been developed for the National Aeronautics and Space Administration (NASA) Space Tracking and Data Acquisition Network (STADAN). This sum-and-difference monopulse system, called APDAR (Advanced Polarization Diversity Autotrack Receiver), utilizes a maximalratio polarization diversity combining technique that matches the receiving antenna polarization to the incoming variable polarization from a spin-stabilized or tumbling satellite. Autotrack performance becomes independent of the incoming polarization orientation by continuous in-phase addition of the carrier-signal components from orthogonal antenna elements. This technique relies upon the principle that fading does not occur simultaneously on oppositely polarized receiving channels. APDAR results in improved autotrack performance by eliminating adverse effects of severe (over 30-dB) cross-polarization fading. The predetection diversity combining technique employed provides an average 3-dB signal-to-noise (SNR) improvement. This paper describes a series of 136-MHz satellite tracking tests and analyzes a maximal-ratio predetection diversity combiner, a three-loop phase-lock loop system, and a frequency-switched radiometer.     

Application of neural networks for synthesizing flight control algorithms. I neural network inverse dynamics method for aircraft flight control

The application of artificial neural networks for aircraft motion control, in particular, for creation of nonlinear algorithms of the aircraft remote control system (RCS) is considered. Aircraft as a control object is represented as a multidimensional nonlinear dynamic system and nonlinear control methods are used to operate this system. The control loop is constructed using the method of inverse dynamics based on the feedback linearization principle. The nonlinear control law is represented as a neural network being learned (adjusted) by recorded or incoming measurements of motion parameters. Synthesis and testing of neural network control algorithms is performed with the fully nonlinear mathematical model of a maneuverable aircraft for three control channels. Simulation results of the closed system are presented.     

综合容错飞行控制系统的设计与仿真

将主动容错控制与被动容错控制相结合,提出了一种综合容错飞行控制系统的设计方法。首先利用基于凸优化的线性二次型控制器构造可靠控制系统,然后通过故障检测滤波器对执行机构进行故障检测分离,并使用伪逆法重构控制律。仿真结果表明,该方法提高了飞行控制系统的可靠性。     

基于自适应神经网络的非线性飞控系统设计

将动态逆理论、神经网络和自适应控制相结合应用于非线性飞行控制系统设计中，通过动态逆控制律将非线性耦合系统转换为线性解耦系统，采用具有在线学习能力的神经网络来补偿反馈线性化中存在的逆误差，最后利用李亚普诺夫稳定性理论推导了在线网络权值的自适应调整规则。仿真结果表明，这种控制结构具有良好的跟踪能力和极强的鲁棒性。     

基于T-S模糊系统的空天飞行器鲁棒自适应轨迹线性化控制

 基于T-S模糊系统提出了鲁棒自适应轨迹线性化控制(RATLC)方法。利用T-S模糊系统逼近未知干扰和不确定性因素,并采用Lyapunov方法设计了鲁棒自适应控制律。不论系统状态的维数和用于逼近不确定的模糊系统规则数为多少,整个系统仅有两个参数在线调整。理论分析证明了闭环系统所有信号一致最终有界。应用提出的控制方案设计了空天飞行器(ASV)飞行控制系统,并在高超声速飞行条件下进行了仿真验证,仿真结果表明了控制方案的有效性和鲁棒性。     

Feedback linearization and solar pressure satellite attitudecontrol

The question of large angle pitch attitude maneuver of satellites using solar radiation pressure is considered. For pitch axis maneuver, two highly reflective control surfaces are used to generate radiation moment. Based on dynamic feedback linearization, a nonlinear control law is derived for large pitch attitude control. In the closed-loop system, the response characteristics of the pitch angle are governed by a fourth-order linear differential equation. Robustness of control system is obtained by the integral error feedback. Simulation results are presented to show that in the closed-loop system, attitude control of the satellite is accomplished in spite of the parameter uncertainty in the system