基于两层POD和BPNN的翼型反设计方法

翼型优化过程需要大量的 CFD 分析,计算量大、耗时长。本文发展基于本征正交分解（POD）和反向传播神经网络（BPNN）的翼型反设计方法,该方法的优化过程如下：首先,通过 Hicks-Henne 参数化,在设计空间中构造翼型外形的样本库,并利用 Xfoil/Fluent 对样本翼型的流场进行求解;然后,对翼面压力系数和几何外形分别建立 POD 模型,即两层 POD 模型,并得到对应的基模态系数;最后,使用 BPNN 建立从压力系数的基模态系数到几何外形的基模态系数的映射,实现在给定压力系数下对几何外形的快速预测。通过算例分析,结果表明：在亚/跨声速状态,基于 200 个样本训练所得的两层 POD+BPNN 模型可以实现对具有目标压力系数分布的翼型的预测,其精度满足翼型反设计要求。     

改进型Gappy POD翼型反设计方法

 为了提高基本Gappy本征正交分解(POD)翼型反设计方法的精度,在原始方法快照采样过程中,调整参数化方法,并用已产生翼型中压力分布最接近目标压力分布的翼型替换基础扰动翼型,形成最优快照替换采样法。在迭代求解阶段,根据迭代产生的压力分布与迭代产生的翼型实际压力分布之间的误差,引入校正快照,并据此调整目标压力分布,形成校正迭代法。实际算例表明,最优快照替换采样法所采集快照张成的空间较原始采样法更接近设计目标。而校正迭代法较原始迭代法能明显提高反设计精度。但最佳模态数量的选择对于Gappy POD翼型反设计方法仍然是一个难点。     

Pressure distribution feature-oriented sampling for statistical analysis of supercritical airfoil aerodynamics

In the field of supercritical wing design, various principles and rules have been summarized through theoretical and experimental analyses. Compared with black-box relationships between geometry parameters and performances, quantitative physical laws about pressure distributions and performances are clearer and more beneficial to designers. With the advancement of computational fluid dynamics and computational intelligence, discovering new rules through statistical analysis on computers has beco...     

高负荷风扇转子叶片反问题设计

为改进高负荷风扇转子性能,采用了一种工程适用的叶片反问题设计方法。该方法使用粘性CFD与数值优化相结合,适合具有高进口马赫数、高逆压梯度流动特征的高效叶型设计,并应用二维叶型反问题加三维积叠的叶片设计思路,充分继承了已有的基元叶型积叠准则,极大地缩短了计算时间。利用发展的反问题设计平台,完成了叶片的反问题设计。三维数值模拟结果表明:反问题设计的转子叶片能较好地控制转子尖部激波结构,减小激波损失,提高效率,增大稳定裕度。     

基于深度学习的混合翼型前缘压力分布预测

提出了一种基于深度学习的混合翼型前缘压力分布预测方法，通过对翼型几何特征提取、压力分布曲线的参数化，建立了卷积神经网络模型（CNN），并利用计算流体力学（CFD）的计算结果作为其训练样本，实现对混合翼型前缘压力分布的预测。结果表明:两种方法计算结果的拟合优度大于0.98，基于深度学习的计算方法耗时1.7 s，CFD方法耗时大于50 s，计算时间大大缩短。该方法能够在满足计算精度的条件下提高计算效率并可应用于其他的翼型设计过程。      

超临界翼型稳健型优化设计研究

基于标准遗传算法、RBF神经网络以及类函数/型函数变形技术建立了翼型气动优化设计系统,在选取3次CST方法即分别对翼型上下表面采用4个设计变量进行参数化,对某型客机基本翼型在给定设计指标下进行优化设计,分别研究了巡航状态下的气动优化,以及结合蒙特卡洛分析方法马赫数随机平均分布下的翼型稳健型优化设计。结果显示,优化后的翼型的气动特性有着显著提高。     

Robust Design of Supercritical Wing Aerodynamic Optimization Considering Fuselage Interfering

Robust optimization approach for aerodynamic design has been developed and applied to supercritical wing aerodynamic design. The aerodynamic robust optimization design system consists of genetic optimization algorithm, improved back propagation (BP) neural network and deformation grid technology. In this article, the BP neural network has been improved in two major aspects to enhance the training speed and precision. Uniformity sampling is adopted to generate samples which will be used to establish surrogate model. The testing results show that the prediction precision of the improved BP neural network is reliable. On the assumption that the law of Mach number obeys normal distribution, supercritical wing configuration considering fuselage interfering of a certain aerobus has been taken as a typical example, and five design sections and twist angles have been optimized. The results show that the optimized wing, which considers robust design, has better aerodynamic characteristics. What's more, the intensity of shock wave has been reduced.     

高高空长航时无人机翼型优化设计研究

针对高高空长航时无人机的特点和使用要求,开展了高高空长航时无人机翼型的优化设计研究.为了提高采用遗传算法的气动优化设计的效率,将分布式计算与遗传算法相结合,形成了基于遗传算法和分布式计算的气动优化设计方法,并将该方法与基于反设计概念的工程方法相结合进行了高高空长航时无人机翼型的气动优化设计.设计实践表明,该方法是可行的,设计出的翼型是能够满足工程需要的.     

基于分布估计算法的翼型稳健设计(英文)

A transonic airfoil designed by means of classical point-optimization may result in its dramatically inferior performance under off-design conditions. To overcome this shortcoming, robust design is proposed to find out the optimal profile of an airfoil to maintain its performance in an uncertain environment. The robust airfoil optimization is aimed to minimize mean values and variances of drag coefficients while satisfying the lift and thickness constraints over a range of Mach numbers. A multi-objective estimation of distribution algorithm is applied to the robust airfoil optimization on the base of the RAE2822 benchmark airfoil. The shape of the airfoil is obtained through superposing ten Hick-Henne shape functions upon the benchmark airfoil. A set of design points is selected according to a uniform design table for aerodynamic evaluation. A Kriging model of drag coefficient is constructed with those points to reduce computing costs. Over the Mach range from 0.7 to 0.8, the airfoil generated by the robust optimization has a configuration characterized by supercritical airfoil with low drag coefficients. The small fluctuation in its drag coefficients means that the performance of the robust airfoil is insensitive to variation of Mach number.     

Few-shot electromagnetic signal classification: A data union augmentation method

Deep learning has been fully verified and accepted in the field of electromagnetic signal classification. However, in many specific scenarios, such as radio resource management for aircraft communications, labeled data are difficult to obtain, which makes the best deep learning methods at present seem almost powerless, because these methods need a large amount of labeled data for training. When the training dataset is small, it is highly possible to fall into overfitting, which causes performance degradation of the deep neural network. For few-shot electromagnetic signal classification, data augmentation is one of the most intuitive countermeasures. In this work, a generative adversarial network based on the data augmentation method is proposed to achieve better classification performance for electromagnetic signals. Based on the similarity principle, a screening mechanism is established to obtain high-quality generated signals. Then, a data union augmentation algorithm is designed by introducing spatiotemporally flipped shapes of the signal. To verify the effectiveness of the proposed data augmentation algorithm, experiments are conducted on the RADIOML 2016.04C dataset and real-world ACARS dataset. The experimental results show that the proposed method significantly improves the performance of few-shot electromagnetic signal classification.     

基于卷积神经网络和多项式混沌方法的翼型鲁棒性优化

在常规的翼型优化设计方法中,设计点处最优翼型的气动性能会在非设计点处有所恶化,因此有必要对翼型鲁棒性优化方法进行研究。提出一种基于卷积神经网络和多项式混沌方法的翼型鲁棒性设计方法,首先搭建基于卷积神经网络的气动力预测模型;其次采用多项式混沌方法对马赫数和攻角进行不确定度量化,构建翼型鲁棒性气动优化设计系统;最后对以 RAE2822 翼型为基准翼型的气动优化设计问题进行优化设计验证。结果表明：本文提出的翼型鲁棒性设计方法可行,优化后翼型的气动性能和鲁棒性气动优化设计效率在较宽的设计范围内都有所提升。     

大型民机翼型变弯度气动特性分析与优化设计

为了提高飞机巡航过程中升力系数、马赫数变化后的气动效率,大型民用运输机开始采用机翼变弯度技术。以典型远程宽体客机翼型为例,研究了翼型后缘变弯度对气动性能与压力分布的影响。利用代理模型建立了不同巡航设计工况下,翼型后缘弯度与气动性能的关系。以此为基础,提出了基于代理模型的大型民机翼型变弯度设计优化方法。算例研究表明,在给定巡航升力系数与马赫数下,该方法可以预测出翼型的最佳弯度,从而改善非设计点气动性能。该方法对大型民机机翼变弯度构型设计工作有一定的工程意义。     

高超声速飞行器宽速域翼型/机翼设计与分析

对于现代高超声速飞行器的设计而言,除了需要保证高超声速的性能外,还必须兼顾满足工程需求的亚跨超声速特性。首先,采用雷诺平均Navier-Stokes（RANS）方程流动求解器,结合基于Kriging模型的代理优化算法,开展了高超声速飞行器宽速域翼型的优化设计研究,设计出了一种下表面具有双"S"形特征的新翼型。综合性能评估结果表明,该翼型相比于常规的高超声速翼型,在跨声速和高超声速下具有更加优良的气动特性;其跨声速状态下的升阻比达到78.9,高超声速状态下的升阻比达到5.94,能够实现宽速域内良好的综合气动性能。其次,开展了仿德国"桑格尔号"（SANGER）空天飞机运载机机翼的气动特性研究,对配置宽速域翼型与常规高超声速翼型的机翼进行了气动力特性综合对比分析。结果表明,配置新翼型的机翼在宽速域范围内整体气动性能更优,说明所设计的宽速域翼型在三维机翼上也具有一定的实用价值。     

绕翼型跨音速大扰动对称势流的插值混合差分法

 本文将跨音速定常小扰动势流混合差分法推广到跨音速大扰动定常势流,提出了在局部速度坐标系中求解跨音速精确势流方程的插值混合差分法。作为算例,计算了双圆弧翼型和NACA0015翼型对称问题压力分布,并与已知实验值和双圆弧翼型小扰动混合差分法计算值进行比较,结果接近。试算表明,本文提出的插值混合差分格式是稳定和收敛的。本文解决了M_∞趋近于1的计算难点。     

Robust design of NLF airfoils

 A robust optimization design approach of natural laminar airfoils is developed in this paper. First, the non-uniform rational B-splines (NURBS) free form deformation method based on NURBS basis function is introduced to the airfoil parameterization. Second, aerodynamic characteristics are evaluated by solving Navier-Stokes equations, and the γ-Re_θt transition model coupling with shear-stress transport (SST) turbulent model is introduced to simulate boundary layer transition. A numerical simulation of transition flow around NLF0416 airfoil is conducted to test the code. The comparison between numerical simulation results and wind tunnel test data approves the validity and applicability of the present transition model. Third, the optimization system is set up, which uses the separated particle swarm optimization (SPSO) as search algorithm and combines the Kriging models as surrogate model during optimization. The system is applied to carry out robust design about the uncertainty of lift coefficient and Mach number for NASA NLF-0115 airfoil. The data of optimized airfoil aerodynamic characteristics indicates that the optimized airfoil can maintain laminar flow stably in an uncertain range and has a wider range of low drag.     

低速叶型气动反问题设计方法

 低马赫数不可压流动中声速与流速大小差别巨大,采用基于可压缩流动控制方程的计算格式求解流场时,由于数值黏性的污染,解的精度低且收敛性差,通常可使用时间预处理技术来解决这一问题。在基于控制理论的优化方法中,共轭方程的Jacobian矩阵和流动方程的系数矩阵相似,因而在低流动马赫数下,求解共轭方程存在着与求解流动方程相同的数值污染和数值刚性问题。首先推导了带有预处理的Roe格式,然后发展了适合全速度流动的共轭方程求解方法,最后选取翼型和叶栅两个典型算例进行了验证。计算结果表明所发展的方法可很好地用于低马赫数时的气动反问题设计。     

跨音速翼型风洞上下壁干扰及侧壁影响的实验研究

 在西北工业大学跨音速翼型风洞（又名57风洞）中,对弦长分别为50、100、125毫米的三个RAE 104翼型模型进行了压力分布测量。结果表明:当上下壁开闭比选用2％时,风洞的堵塞干扰基本消除。 采用实侧壁、多层网板而不进行抽气及多层网板进行抽气这三种侧壁状态,对RAE 104翼型模型所做实验结果表明:有多层网板而不抽气,使升力系数大大低于无干扰值;在M相似文献   

现代超临界翼型设计及其风洞试验

开展了现代超临界翼型的设计研究,对现役飞机的压力分布形态进行了分析,针对现役飞机在巡航状态和阻力发散点的压力分布进行对比,提取了现役飞机超临界剖面设计的要点。采用类函数/型函数变换(CST)参数化方法、基于二阶震荡及自然选择的随机权重混合粒子群算法(RwSecSelPSO)、雷诺平均Navier-Stokes(RANS)方程、Kriging代理模型结合定期望值型的目标函数建立了优化设计系统。针对提高阻力发散马赫数和降低巡航低头力矩的设计指标,利用优化设计系统通过调整目标期望值设计了一系列满足设计指标但阻力发散马赫数不同的超临界翼型,并选择了其中具有典型特性的翼型进行了对比分析,验证了提高阻力发散马赫数和低速失速特性的设计方法,指出了在阻力发散点形成平顶形压力分布的超临界翼型具有较好的综合性能。对设计的超临界翼型进行了高、低速风洞试验验证,试验结果表明:设计结果达到了设计指标要求,提出的低速改进方案有效,层流对超临界翼型失速特性影响较大。     

基于适当控制翼型演化历程的气动设计方法

本文提出一种翼型设计的新方法,它基于适当控制翼型演化历程,采用求解非定常流动控制方程的方法,实现了翼型反问题的高效求解.同时在笛卡尔坐标系中应用Level-Set函数,避免了贴体动网格的采用,从而大大减少了所需计算工作量.     

物理启发的深度学习模型及其在热端部件散热中的应用

热端部件散热是众多空天设备的关键技术。表面温度分布是散热设计中用到的重要信息,常规的解析建模手段和机器学习方法均无法有效地表达此类高维信息。近年来兴起的图像深度学习算法是解决表面温度信息预测的有效手段。然而,现有的基于大数据的深度学习方法往往对于物理数据和小样本数据不适用,体现为泛化精度差、数据兼容性差、可解释性差。因此,有必要结合传热的先验知识发展物理启发的新型深度学习算法,以增强高自由度、高复杂度散热对象上的设计能力。本文基于卷积算子和有限差分求解方式的类比关系,提出了一种物理启发式的循环卷积神经网络。以横向出流的冲击冷却为例,开展了变计算域大小、变工况、变尺寸的批量数值模拟,获取了冲击冷却关键特征的小样本图像数据。进一步通过神经网络的训练,构建了多参数、大范围内有较好拟合能力的温度、传热系数、压力代理模型。研究结果表明,本文提出的物理启发神经网络模型,对于计算域大小没有限制,可以统一表达不同空间范围内获取的物理数据的共性规律。模型的各类超参设定均具有明确的物理意义,且与经典的微分方程求解理论有一定的类比关系,增强了神经网络调参的方向性。通过传热物理规律与黑箱模型的融合,本文实现了小样本多参数物理数据的共性建模。该方法可以迅速重构热端部件的高维分布信息,可服务于热端部件的快速分析设计以及优化。