Data fusion system engineering

The paper reports on methods for the cost-effective development and integration of multi-sensor fusion technology. The methods presented extend the Project Correlation Data Fusion Engineering Guidelines with significant evolution. The key new insight is in formulating the system engineering process as a resource management problem; allowing the application of the Bowman's model of the duality between data fusion and resource management     

基于遗传算法的被动式滚转控制系统设计

根据随机规划理论，建立了小尺寸，细长旋转体再入飞行器被动式滚转控制系统的机会约束规划模型，并运用基于随机模拟的遗传算法来求解，给出了能够确保飞行器在不确定再入环境下具有鲁棒可行性的弹道倾角γE和质心系数x↑cg的最优设计值，通过工程实例计算表明，在选用适当的运行参数情况下，本文所提供的方法能够比较有效地为再入飞行器的设计服务。     

Data fusion algorithm based on state and attribute parameter

Ａｑｕｅｓｔｉｏｎｔｈａｔｈａｓｂｅｅｎｃｏｎｃｅｒｎｅｄｆｏｒｍａｎｙｙｅａｒｓｉｎｔｈｅｍｕｌｔｉｔａｒｇｅｔｔｒａｃｋｉｎｇｆｉｅｌｄｉｓｈｏｗｔｏｒｅｄｕｃｅｔｈｅｃｏｍｐｕｔａｔｉｏｎａｌｃｏｍｐｌｅｘｉｔｙｏｆｄａｔａａｓｓｏｃｉａｔｉｏ...     

基于信息融合遗传算法的航空发动机气路故障诊断

针对航空发动机由传统定期维修向视情维修转变的发展趋势,研究了遗传算法在气路性能参数估计中的应用,提出了改进的基于信息融合的遗传算法,将多源信息融合到遗传算法中,用以减小遗传算法的搜索范围.仿真结果表明:通过融合多源信息,有效克服遗传算法在寻优过程中陷入局部最优的情况,从而提高了气路性能参数的估计精度,能将估计误差控制在5%以内.      

基于多目标遗传算法的再入飞行器气动布局优化

本文采用多目标遗传算法来确定再入飞行器气动布局优化问题的Pareto最优解集，并和传统的多目标优化方法（加权和方法、约束法）进行比较。通过计算表明，多目标遗传算法能够在一次运行中搜索到优化问题的近似Pareto最优解集，这为飞行器设计得进行目标折衷决策提供了充分的依据。     

基于多目标遗传算法的多级轴流压气机优化设计

建立了一种多级轴流压气机的多目标优化设计方法。采用流线曲率法计算压气机气动性能，结合多目标遗传算法来进行性能参数优化。针对一台两级轴流压气机，选定优化设计的目标是最大的总压比和最高的总绝热效率。将转子尾缘的稠度和相对气流角以及静子尾缘的稠度和气流角作为设计变量。通过优化设计得到一组在两个目标上均优于初始设计的Pareto最优解，对典型的Pareto最优解和初始设计进行分析、比较，证明了该优化设计方法的有效性。     

基于改进遗传算法的燃气轮机自适应建模

综合运用了一种改进的遗传算法和自适应建模技术对燃气轮机的精确特性进行寻优获取.引入自适应机制优化交叉和变异算子,同时引入模拟退火算法,使改进遗传算法能很快接近最优解,并能跳出局部最优的陷阱,在保证解的质量的同时提高了收敛的速度.针对以往自适应模型中未考虑测量参数间的线性相关性和不同的传感器测量精度对目标函数的影响等问题,采用加权方法建立了较为完备的燃气轮机自适应数学模型,应用改进遗传算法获取燃气轮机部件的精确特性,实例计算结果表明:模拟退化改进遗传算法进行的自适应建模效果更好.      

Data fusion and tracking using HMMs in a distributed sensor network

This work deals with the problem of multiple target tracking, from the measurements made on a field of passive sonars activated by an active sonar (multistatic network). The difficulties encountered then are of two kinds: each sensor alone does not provide full observability of a target, and multiple, possibly maneuvering targets moving in a cluttered environment must be dealt with. The algorithm presented here is based on a discrete Markovian modelization of the targets evolution in time. It starts with a fusion of the detections obtained at each measurement time. Tracking and target motion analysis (TMA) are next achieved thanks to dynamic programming (DP). This approach leads to multiple and maneuvering target tracking, with few assumptions; for instance, the use of deterministic target state models are avoided. Simulation results are presented and discussed.     

应用遗传算法研究典型冲件级进模排样设计

利用VB语言面向对象，智能化轻松设计界面的特点，建立典型冲件的级进模排样专家系统。实现了用遗传算法进行辅助排样设计决策分析，确定最优排样方案的设计路线。     

Flight control system design and optimisation with a genetic algorithm

A design procedure for a flight control system is here presented. An optimisation process, based on a genetic algorithm, is used to meet the frequency domain handling qualities requirements for the longitudinal plane. The parameters are implemented as fitness functions related to the expected magnitude of bandwidth and delay. The impact of the parametric shaping of the fitness functions on the search and optimisation process is also evaluated. The dynamic response of the augmented aircraft is obtained for a realistic simulation case, validated after comparison with reference test data. The bandwidth and the delay of the longitudinal short term attitude response are estimated before and after the inclusion of the flight control system in the simulation model, and the parameters are compared with the expected handling qualities levels. The feasibility of the design process is demonstrated and the overall performance of the generation process is analyzed.     

基于遗传算法的双层发散冷却优化

描述了基于遗传算法的双层多孔介质骨架发散冷却的优化方法.冷却剂在固定压差(Be数)与多孔介质特征尺寸的条件下被注入固体骨架,通过改变多孔介质的材料、孔隙率和厚度比例,在满足固体骨架的质量和成本等约束条件下,以最低热端表面温度为优化目标,利用遗传算法找出可行的最优冷却结构设计.计算结果表明,靠近冷端的第一层多孔介质孔隙率应当尽可能的大以提高冷却剂流量,但是其组成材料对热端表面温度影响很小,而第二层靠近热端的多孔介质的组成材料对热端表面温度有很重要的影响,它的孔隙率取决与其对有效导热系数、冷却剂流量和内部热交换系数三方面影响的平衡.      

Data fusion in biometrics

Any biometric system has drawbacks and cannot warranty 100% identification rates, nor 0% false acceptance and rejection ratios. One way to overcome the limitations is through a combination of different biometric systems. In addition, a multimodal biometric recognition is more difficult to fool than a single, biometric system, because it is more unlikely to defeat two or three biometric systems than one. This paper summarizes the different data fusion levels, and how it must be performed in order to improve the results of each combined system on its own     

基于遗传算法的旋翼翼型综合气动优化设计

结合直升机飞行特性及旋翼工作气动环境,提出了适用于中型运输直升机旋翼翼型优化设计的目标函数及约束条件.在此基础上采用遗传算法,以"黑鹰"(UH-60A)直升机旋翼翼型SC1095为基础翼型,进行多目标、多状态以及多约束条件下的旋翼翼型优化设计.优化翼型同SC1095翼型相比弯度稍大,最大厚度略有增加.结果表明:优化翼型气动力特性在满足约束条件的情况下,零升力矩系数减小了57.2%,最大升力系数增加了3.7%,阻力系数减小了7.5%.同时,非定常动态失速状态下的气动特性也有一定的改善,阻力系数和力矩系数的发散范围均有明显的减小.此外,悬停状态计算结果表明:采用优化翼型构成的旋翼与SC1095旋翼相比,具有更高的悬停效率及更低的力矩系数.      

根据遗传算法的拉深模试冲缺陷智能诊断

总结了拉深模试冲时的缺陷及原因，建立原因表，应用遗传算法技术对拉深模试冲时的缺陷进行智能诊断，探讨了提高拉深模试冲时的缺陷诊断准确率的优化方法，描述了遗传算法的诊断过程。     

适于直升机配平计算的混合遗传算法

结合传统的数值计算如拟牛顿法的局部快速收敛特性,以及遗传算法的全局收敛与群体搜索的优点,发展出一种新的混合遗传算法,使之具备全局快速收敛特性。通过两个算例及某型直升机在前进比为0.2状态下的配平,验证了该算法的可行性及高效性,从而为直升机的配平计算提供了一种新的成功的算法,同时也在传统数值分析方法和现代智能进化算法之间的有效结合做了一次比较成功的尝试。     

Optimization of multiple-impulse minimum-time rendezvous with impulse constraints using a hybrid genetic algorithm

The minimum-time multiple-impulse rendezvous with impulse constraints is investigated in this paper. Based on the Clohessy–Wiltshire (C–W) equations, an optimization model including several different kinds of impulse constraints such as the maximum impulse magnitude, the total velocity change magnitude and the time of imposing impulse for multiple-impulse minimum-time rendezvous is established. A generalized inverse matrix solution for linear equation is applied to avoid handling the terminal equality constraints. In order to obtain the global solution efficiently, a hybrid optimizer combining the advantages of a floating-coded genetic algorithm and simplex method is employed. A low-earth orbit multiple-impulse rendezvous problem is used as an example. The influence of the number of impulses, the optimization variables and the constraints on the solution is analyzed, and the different optimization algorithms are compared. Results indicate our proposed model and approach is effective in designing linearized minimum-time rendezvous trajectory with impulse constraints.     

基于遗传算法提高计算机连续语音识别率的研究

为提高计算机连续语音识别准确率,应用遗传算法人工智能控制技术具有的高效全局启发式搜索特点,探讨了提高计算机连续语音识别准确率的优化方法,通过提取语音特征参数,作为初始语音群体的生成,把语音识别内核程序中语言焦点作为遗传算法中操作算子,以高效全局启发式适配语音类型,连续语音识别准确率提高7％,为实现真正意义上计算机“人一机对话”进行了大胆的尝试。     

Gaussian fitting based optimal design of aircraft mission success space using multi-objective genetic algorithm

In order to obtain the optimized aircraft design concept which meets the increasingly complex operation environment at the conceptual design stage, System-of-systems(So S) engineering must be considered. This paper proposes a novel optimization method for the design of aircraft Mission Success Space(MSS) based on Gaussian fitting and Genetic Algorithm(GA) in the So S area. First, the concepts in the design and evaluation of MSS are summarized to introduce the Contribution to System-of-Systems(CS...     

基于精英保留遗传算法的连续结构多约束拓扑优化

采用遗传算法对应力、位移及结构约束下的连续体结构进行拓扑优化。通过在遗传算法中引入精英保留的进化策略,保证算法的收敛性,改善优化结果。优化过程中,利用精英保留遗传算法进行结构优化,通过基于ANSYS软件的有限元技术进行结构的建模和分析。算例分析表明所提出的方法是合理、有效的。该方法可用于复杂工程结构的初始设计,并能够提供多种初始设计方案。      

一种小波神经网络与遗传算法结合的优化方法

提出一种基于小波神经网络(简称WNN)与Pareto遗传算法相结合的优化方法,并用于内流的数值流场优化计算.小波神经网络由输入层、隐含层和输出层组成.在隐含层用Morlet小波母函数取代了误差反向传播(BP)神经网络中常用的Sigmoid激励函数.Pareto遗传算法具有很好的全局寻优能力和良好的优化效率,在通常情况下它总可以得到均匀分布的Pareto最优解集.典型算例表明:该算法快速、高效,能高精度的完成非线性函数的逼近与映射,其泛化能力很强.