随着现代飞机高机动性的要求和S弯进气道的提出,发动机进气道内流场畸变问题日益突出,如何在地面试车台准确模拟发动机进口气动界面(Aerodynamic interface plane,AIP)的总压畸变面临更大的挑战.本文以美国Arnold工程发展中心提出的一种新型可变开角的铰链式总压畸变模拟器为基础,以单铰链畸变单元为研究对象,采用RANS(Reynolds-averaged Navier-Stokes)数值方法详细分析了铰链主要几何参数和来流马赫数对稳态畸变流场的影响规律,采用精度更高的分离涡模拟(Detached eddy simulation,DES)方法研究了铰链下游漩涡发展和总压脉动特征.通过对原铰链进行锯齿改型,在保证稳态畸变流场基本不变的前提下,加强了尾迹与主流区的掺混,有效降低了下游流场的动态畸变指数,扩大了稳/动态畸变比例的模拟范围.

In order to improve the performance of an air turbine starter and match it with the bleed characteristics of the auxiliary power unit, the aerodynamic performance and flow field details of the air turbine starter are studied by means of numerical simulation and experiment, and the optimal design of the guide and turbine stage blade is completed. After the modification, the mass flow, the efficiency and the power increase by 23.2%, 3.4% and 18.0%, respectively. The comparison between numerical simulation and test results shows that the overall difference of flow is small, the fluctuation range is within ±3%, and the mean value is equal to 0.17%. The maximum power difference is equal to 2.38% and the minimum is equal to 0.1%. The numerical simulation results show that there are common working points between the modified air turbine starter and the bleed characteristic line of the auxiliary power unit, and the working performance of the auxiliary power unit has been significantly improved.

基于现有涡扇发动机,按涡轮冲压组合发动机技术验证要求,开展了基于成熟涡扇发动机改涡轮基的设计研究.根据涡轮基工作性能和技术要求,分析了改型设计的难点,并开展了涡轮基控制计划设计、高空大马赫数起动设计、超声速燃烧设计、低转速接通加力设计、全权限控制系统设计、燃滑油系统设计、高空封严设计和涡轮基与冲压级匹配设计.通过整机试验验证改型后发动机满足验证平台需求,并配装冲压组合发动机平台完成关键技术验证试验.对其他发动机的改型设计具备一定的工程参考价值.

为提高某型空气涡轮起动机的性能,采用数值仿真和试验相结合的方法,开展了某型空气涡轮起动机气动性能和流场仿真的研究,并完成了优化设计.数值仿真结果表明,进气弯管内侧存在明显的流动分离,导致下游流场均匀性恶化,导向器叶片和转子叶片表面均存在一定的附面层分离,排气框架未充分考虑流动的顺畅性,最终造成空气涡轮起动机性能偏低.数值仿真和试验结果的对比表明,数值仿真获得的空气流量比试验低1.90％左右,涡轮功率高1.04％左右.数值仿真和试验符合较好,采用这种数值仿真方法研究空气涡轮起动机具有较高的准确性,对导向器叶片进行了优化设计,显著提升了空气涡轮的性能,优化后功率比原型增加了14.2％.

为了培养我国航空发动机领域的设计人才,结合飞行器动力工程专业培养计划,南京航空航天大学于2011年开设了"航空发动机总体设计"课程.经过多年的教学积累,初步形成了较为完善的教学资源和教学方法.在此基础上,结合我国在航空发动机领域设计人才的需求,进行"航空发动机总体设计"课程教学模式改革.本次改革充分考虑学生的兴趣,提高实践课时比例,增强学生的动手能力和团队合作意识,有利于进一步提升本课程的教学质量,从而为国家培养航空发动机领域自主设计人才,提升我国航空发动机制造业水平.

面向工业界提出的工程技术人才需求,以培养出具有航空发动机工程设计、实践能力和工程创新、合作意识的高素质人才为目标,南京航空航天大学于2011年将"航空发动机总体设计"课程作为专业必修课引入飞行器动力工程专业培养计划,这在国内尚属先例.该课程国内尚无可用中文教材、无可借鉴的教学经验,课程组通过引入国外英文教材,参考国外教学方法和考核方法,经过7年的教学实践探索,目前已基本建成了一套完善的教学课件、大作业题库、辅导资料资源库等教学资源,形成了以课堂讲授、实践设计、过程考核为特点的教学方法,学生一致认为通过对课程学习熟悉了发动机总体设计流程,并提高了团队合作能力和工程实践能力.

A distortion generator equipped with a motor-activated movable flat baffle was installed just upstream of a rectangular plenum entrance to investigate the effects of inlet total pressure distortion on the stability and performance of an auxiliary power unit (APU). Experiments and numerical simulations on a direct connect scale inlet model of the APU were carried out to obtain a quantitative relationship between the insertion depth of the flat baffle in the flow stream and the total pressure distortion intensity and region. In the experiments, the blocking coefficient and total pressure distortion coefficient were controlled by adjusting the insertion depth of the flat baffle and the mass flow. In the simulations, detailed flow field was analyzed based on the detached-eddy simulation (DES) method. The results show that the pressure distribution of the distorted flow on the aerodynamic interface plane (AIP) can be divided into a high-pressure region, a transition region, and a low-pressure region. The area affected by the distorted flow was larger than the inserting area of the flat baffle. That area was more related to the relative blocking coefficient, and less affected by the mass flow. The total pressure distortion coefficient had a linear relationship with the mass flow rate and is positively correlated with the relative blocking coefficient. As the relative blocking coefficient increased to a certain value, an exponential growth in the total pressure distortion coefficient occurred, and consequently, the flow field distortion was intensified. In the flow field, a pair of corner vortices were formed at the corner between the flat baffle and the bottom wall of the inlet pipe, and a large separation zone was formed behind the flat baffle and exhibits certain unsteady characteristics.

使用数值模拟研究了静叶锯齿尾缘改型对3.5级压气机性能的影响,分析了锯齿形状、布置位置等对压气机转速特性的影响.结果表明,在进口导向叶片尾缘上全叶高开齿能够拓宽90％转速的压气机稳定工作范围,且对压比、效率的影响很小,而对100％转速特性影响不大;相对于本文开展的锯齿改型而言,齿宽小的结构优于齿宽大的锯齿,全叶高锯齿扩稳胜于部分叶高(叶尖)锯齿.这些研究加深了锯齿尾缘叶片对压气机性能影响的认识,为压气机扩稳研究提供了借鉴.

Abstract Sleep staging is an important basis for diagnosing sleep-related problems. In this paper, an attention based convolutional network for automatic sleep staging is proposed. The network takes time-frequency image as input and predict sleep stage for each 30-s epoch as output. For each CNN feature maps, our model generate attention maps along two separate dimensions, time and filter, and then multiplied to form the final attention map. Residual-like fusion structure is used to append the attention map to the input feature map for adaptive feature refinement. In addition, to get the global feature representation with less information loss, the generalized mean pooling is introduced. To prove the efficacy of the proposed method, we have compared with two baseline method on sleep-EDF data set with different setting of the framework and input channel type, the experimental results show that the paper model has achieved significant improvements in terms of overall accuracy, Cohen’s kappa, MF1, sensitivity and specificity. The performance of the proposed network is compared with that of the state-of-the-art algorithms with an overall accuracy of 83.4%, a macro F1-score of 77.3%, κ = 0.77, sensitivity = 77.1% and specificity = 95.4%, respectively. The experimental results demonstrate the superiority of the proposed network.

以某离心压气机为研究对象,数值计算离心压气机风车工作流动特点,分析了工作叶轮叶片受力情况、探讨了APU风车点火转速存在上限值的成因.研究表明,采用等转速特性线插值获得风车状态的流量、压比和温比的精度和置信度是可取的;后弯叶片是冲击气流吹转离心压气机的主要受力面,工作叶轮在5％设计转速(Nd)以下对外输出力矩,辅助涡轮部件提升APU转子转速;转速达15％Nd后,工作叶轮恢复对气流做功,发挥泵气增压功能,气流流量、压力得到提升;出口流量相对值随飞行条件和压气机转速变化规律有助于APU空中点火转速存在上限值的理解.

针对微型燃气轮执行机构故障,提出了一种基于改进帝国竞争算法的自适应容错控制方法,实现了对故障的有效抑制.本文建立了微型燃气轮发电系统部件级一体化模型,实现了部件级模型与发电系统的联合仿真,提出了一种自适应改革概率的方法对帝国竞争算法进行改进.设计了基于改进帝国竞争算法的自适应模糊逻辑保护控制器.最后进行了改进算法性能测试以及微型燃气轮发电系统在孤岛模式下的仿真实验.结果表明:本文所提出的改进方法可以提高帝国竞争算法的寻优性能,设计的容错器可以明显改善故障发生时的动态性能,确保发电系统的稳定工作.

IPU是APU和EPU高度融合的产物.在EPU模式下,为了不使离心压气机空转导致温度过高,离心压气机处于正转逆流工况.为了满足EPU模式下压气机流量、功耗的要求,采用数值模拟方法,分析流动现象,完成扩压器出口挡板的设计.结果表明:正转逆流工况下离心压气机先对逆流气体做功,之后逆流气体对压气机做功;扩压器出口挡板缝隙存在临界面积,出口挡板缝隙面积大于临界面积时,压气机正转逆流功耗和流量不随挡板缝隙面积变化而变化;扩压器出口挡板缝隙为条形缝隙,缝隙面积占出口总面积的2.6％～1.9％,高压气源压力选择450～800 kPa.

因经济性需求使得发动机涵道比不断增大,导致风扇的转速不断下降,风扇与增压级和低压涡轮之间的转速不匹配问题越来越突出.基于桨尖喷气旋翼的原理提出了一种新型的喷气自驱动风扇发动机,从核心机中引出高温高压气体至风扇叶尖区域,通过高速喷射获得反作用力驱动风扇旋转.利用C++程序对带喷气自驱动风扇的发动机进行了总体性能仿真,与常规发动机相比,采用该方案后发动机在基本不改变原有推力和耗油率的条件下,进一步提升了发动机的推重比.

In this paper, we describe our solution to the Google Landmark Recognition 2019 Challenge held on Kaggle. Due to the large number of classes, noisy data, imbalanced class sizes, and the presence of a significant amount of distractors in the test set, our method is based mainly on retrieval techniques with both global and local CNN approaches. Our full pipeline, after ensembling the models and applying several steps of re-ranking strategies, scores 0.37606 GAP on the private leaderboard which won the 1st place in the competition.

Instance-level image retrieval is a long-standing and challenging problem in multimedia. Recently, fine-tuning Convolutional Neural Networks (CNNs) has become a promising direction, and a number of successful strategies based on global CNN descriptors have been proposed. However, it is difficult to make direct comparisons and draw conclusions due to different settings and/or datasets. The goal of this paper is two-fold. Firstly, we present a unified implementation of modern global-CNN-based retrieval systems, break such a system into six major components, and investigate each part individually as well as globally when considering different configurations. We conduct a systematic series of experiments on a component-by-component basis and find an optimal solution in designing such a system. Secondly, we introduce a novel joint loss function with learnable parameter for fine-tuning for retrieval tasks and show, with extensive experiments, significant improvement over previous works. On the new and challenging large-scale Google-Landmarks-Dataset, we set a baseline for future research and comparisons, while on traditional retrieval benchmarks such as Oxford5k and Paris6k, as well as their recent revised versions ROxford5k and RParis6k, we achieve state-of-the-art performance under all three (Easy, Medium, and Hard) evaluation protocals by a large margin compared to competing methods.

离心压气机正转逆流是综合动力装置在应急动力模式下避免离心压气机温度过高而不得不采取的措施.为了改善正转逆流时离心压气机的功耗,本文提出了角度大幅可调的扩压器叶片组合,并结合三维数值模拟技术,研究了扩压器叶片安装角大幅调节对离心压气机反向流动的影响.分析表明:扩压器叶片安装角调整对扩压器叶片通道和工作叶轮流动通道的影响很大,调整后流动分离区减少、减弱甚至消除了激波,流动更为顺畅;在气源压力和缝隙面积一定时,流量明显增加,但离心压气机的功耗反而变小.同样的反向气流流量下,调整扩压器叶片安装角能显著降低离心压气机的功耗,从而提高综合动力装置的功率输出.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

To efficiently improve the effects of image Super Resolution (SR),a multi-stage cascade residual convolution neural network model was proposed.Firstly,two-stage SR image reconstruction method was used to reconstruct the 2-times SR image and then reconstruct the 4-times SR image;secondly,residual layer and jump layer were used to predict the texture information of the high resolution space in the first and second stages,and deconvolution layer was used to reconstruct 2-times and 4-times SR images.Finally,two multi-task loss functions were constructed respectively by the results of two stages.And the loss of the first stage guided that of the second one,which accelerated the network training and enhanced the supervision and guidance of the network learning.The experimental results show that compared with bilinear algorithm,bicubic algorithm,Super Resolution using Convolutional Neural Network (SRCNN) algorithm and Fast Super Resolution Convolutional Neural Network (FSRCNN) algorithm,the proposed model can better construct the details and texture of images,which avoids the image over smoothing after iterating,and achieves higher Peak Signal-to-Noise Ratio (PSNR) and Mean Structural SIMilarity (MSSIM).

To solve the low detection accuracy of SSD for the small size object, this paper proposed an improved algorithm of SSD object detection based on the feature pyramid (FP-SSD). In the deep convolutional neural network, the high-level features contain well semantic information but are not sensitive to the translations. The low-level features have high resolutions but could not represent the features well. The feature pyramid structure contains multi-scale features. To combine the high and low-level features of the pyramid, the algorithm of this paper applied the deconvolution network to the high-level features of the feature pyramid to get the semantic information, dilated convolution network to learn the position information of the low-level features and used convolution for the middle level features to reduce the feature channels, then used convolution to fuse the features. After using the algorithm, a multi-scale detection structure is constructed. FP-SSD achieves a mean accuracy of 79% on PASCAL VOC2007, and 47% on MSCOCO, which has a great improve compared with SSD. We compared the detection accuracy and results with all kinds of scales by experiments, compared with SSD, the accuracy of FP-SSD is higher, which has more accurate location and higher recognition confidence.

采用分离涡模拟的方法研究了锯齿尾缘对压气机叶栅的影响.在保持来流Ma为0.3的情况下,对比了基准叶栅和锯齿叶栅3个攻角下的流场和气动参数.研究结果表明:正攻角下,锯齿使分离涡被切割进而破碎,围绕齿尖形成发卡涡;负攻角下,可能通过势干扰影响叶盆分离涡的强度和脱落频率.进一步研究表明,尖齿整体效果优于宽齿,锯齿对尾迹亏损的作用效果与叶栅进气攻角以及锯齿对流场涡系发展的作用机理紧密联系.