Drogue detection for autonomous aerial refueling based on convolutional neural networks

Drogue detection is a fundamental issue during the close docking phase of autonomous aerial refueling(AAR). To cope with this issue, a novel and effective method based on deep learning with convolutional neural networks(CNNs) is proposed. In order to ensure its robustness and wide application, a deep learning dataset of images was prepared by utilizing real data of ‘‘Probe and Drogue" aerial refueling, which contains diverse drogues in various environmental conditions without artificial features placed on the drogues. By employing deep learning ideas and graphics processing units(GPUs), a model for drogue detection using a Caffe deep learning framework with CNNs was designed to ensure the method's accuracy and real-time performance. Experiments were conducted to demonstrate the effectiveness of the proposed method, and results based on real AAR data compare its performance to other methods, validating the accuracy, speed, and robustness of its drogue detection ability.     

N-fold Bernoulli probability based adaptive fast-tracking algorithm and its application to autonomous aerial refuelling

Recently, deep learning has been widely utilized for object tracking tasks. However, deep learning encounters limits in tasks such as Autonomous Aerial Refueling (AAR), where the target object can vary substantially in size, requiring high-precision real-time performance in embedded systems. This paper presents a novel embedded adaptiveness single-object tracking framework based on an improved YOLOv4 detection approach and an n-fold Bernoulli probability theorem. First, an Asymmetric Convolutional Network (ACNet) and dense blocks are combined with the YOLOv4 architecture to detect small objects with high precision when similar objects are in the background. The prior object information, such as its location in the previous frame and its speed, is utilized to adaptively track objects of various sizes. Moreover, based on the n-fold Bernoulli probability theorem, we develop a filter that uses statistical laws to reduce the false positive rate of object tracking. To evaluate the efficiency of our algorithm, a new AAR dataset is collected, and extensive AAR detection and tracking experiments are performed. The results demonstrate that our improved detection algorithm is better than the original YOLOv4 algorithm on small and similar object detection tasks; the object tracking algorithm is better than state-of-the-art object tracking algorithms on refueling drogue tracking tasks.     

Rotating machinery fault detection and diagnosis based on deep domain adaptation: A survey

In practical mechanical fault detection and diagnosis, it is difficult and expensive to collect enough large-scale supervised data to train deep networks. Transfer learning can reuse the knowledge obtained from the source task to improve the performance of the target task, which performs well on small data and reduces the demand for high computation power. However, the detection performance is significantly reduced by the direct transfer due to the domain difference. Domain adaptation (DA) can transfer the distribution information from the source domain to the target domain and solve a series of problems caused by the distribution difference of data. In this survey, we review various current DA strategies combined with deep learning (DL) and analyze the principles, advantages, and disadvantages of each method. We also summarize the application of DA combined with DL in the field of fault diagnosis. This paper provides a summary of the research results and proposes future work based on analysis of the key technologies.     

基于多特征图像增强深度卷积神经网络的航天用电子元器件分类算法

为了实现航天用电子元器件的全自动及非接触识别,并减少由照明系统造成的图像亮度不均、偏色等问题对检测结果的影响,通过结合局部、区域和总体三个层次特征提升物体检测精度,提出了一种基于多特征图像增强深度卷积神经网络(MFIE-DCNN)的航天用电子元器件分类算法。MFIE-DCNN算法包含多特征学习和深度学习,其学习过程类似于人类视觉系统,能够对形状、方向和颜色特征进行深度挖掘,突出元器件边界信息,抑制背景杂波干扰。实验结果表明,该算法能够区分电路板板载元器件的种类,检测准确度优于传统算法。对比基于稀疏自动编码器的深度神经网络,检测结果提高了近20%。     

建构主义教学模式对大学生学习方式影响研究

建构主义教学模式对大学生学习方式有重要影响,通过实证研究方法,研究了课堂环境下建构主义教学模式与大学生学习方式之间的内在关系。研究结果表明：以互动性、自主性为特征的建构主义教学模式与深层学习方式显著正相关,教学模式中的自主性对深层动机和策略的影响均显著高于互动性,且自主性可以更为有效地促使学生采用深层学习方式。     

基于VBGMM-DCNN的列车卫星定位欺骗干扰检测方法

面向基于全球导航卫星系统的铁路列车定位实施欺骗干扰的主动检测，在卫星定位解算层次，运用深度学习建模学习方法的优势，提出一种基于变分贝叶斯高斯混合模型-深度卷积神经网络（variational Bayesian Gaussian mixture model-deep convolutional neural network, VBGMM-DCNN）的列车卫星定位欺骗干扰检测方法。该方法首先提取能够充分体现欺骗干扰对定位解算过程作用影响的卫星观测特征参数，构建干扰检测特征矢量；然后，采用VBGMM模型拟合经过预处理的特征向量的概率分布，得到二维概率密度图；最后，将概率密度图用于DCNN模型实施欺骗干扰的检测决策。结合现场实验所得运行场景数据，利用实验室搭建的欺骗干扰测试环境实施了干扰注入测试与检验，结果表明,欺骗干扰检测性能随着DCNN网络深度的增加而提升，相对于常规有监督决策方法F1值最高提升44.68%。基于VBGMM-DCNN的欺骗干扰检测能够适应测试验证中运用的列车运行特征及定位观测条件，所达到的检测性能优于对比算法。     

基于深度学习的小目标检测研究进展

随着深度学习方法的快速发展,目标检测作为计算机视觉领域中最基本、最具有挑战性的任务之一,已取得了令人瞩目的进展。现有的算法大多针对于具有一定尺寸或比例的大中型目标,但由于待测目标尺寸小、特征弱等原因,对小目标的检测性能还远远不能令人满意。小目标检测（SOT）作为一种广泛应用于室外远程拍摄和航空遥感场景的技术,近年来受到了广泛的关注,各种方法层出不穷,但是目前对该问题的全面综述较少。从问题定义、算法分析、应用介绍、方向展望等方面对基于深度学习的小目标检测研究进展进行了综述。首先,给出了小目标检测问题的定义,阐述了其技术难点及在实际应用中面临的挑战;接着,从8个不同角度分析了检测器对小目标检测精度较低的主要原因及相应的改进方法,详细归纳总结了小目标检测在各技术方面的研究工作;然后介绍了几个特定场景下小目标检测算法的典型应用;最后,对小目标检测未来的发展趋势进行展望,提出可行的研究方向,期望为该领域的研究工作提供可借鉴和参考的思路。     

基于深度卷积网络的SAR图像目标检测识别

在SAR图像解译应用领域,目标的自动检测与识别一直是该领域的研究重点和热点,也是该领域的研究难点。针对SAR图像的目标检测与识别方法一般由滤波、分割、特征提取和目标识别等多个相互独立的步骤组成。复杂的流程不仅限制了SAR图像目标检测识别的效率,多步骤处理也使模型的整体优化难以进行,进而制约了目标检测识别的精度。采用近几年在计算机视觉领域表现突出的深度学习方法来处理SAR图像的目标检测识别问题,通过使用CNN、Fast RCNN以及Faster RCNN等模型对MSTAR SAR公开数据集进行目标识别及目标检测实验,验证了卷积神经网络在SAR图像目标识别领域的有效性及高效性,为后续该领域的进一步研究应用奠定了基础。     

Full blended blade and endwall design of a compressor cascade

In the current state-of-the-art, high-loss flow in the endwall significantly influences compressor performance. Therefore, the control of endwall corner separation in compressor blade rows is important to consider. Based on the previous research of the Blended Blade and EndWall (BBEW) technique, which can significantly reduce corner separation, in combination with a non-axisymmetric endwall, the full-BBEW technique is proposed in this study to further reduce the separation in endwall region. The principle of the unchanged axial passage area is considered to derive the geometric method for this technique. Three models are further classified based on different geometric characteristics of this technique: the BBEW model, Inclining-Only EndWall (IOEW) model, and full-BBEW model. The most effective design of each model is then found by performing several optimizations at the design point and related numerical investigations over the entire operational conditions. Compared with the prototype, the total pressure loss coefficient decreases by 7%–9% in the optimized full-BBEW at the design point. Moreover, the aerodynamic blockage coefficient over the entire operational range decreases more than the other models, which shows its positive effect for diffusion. This approach has a larger decrease at negative incidence angles where the intersection of the boundary layer plays an important role in corner separation. The analysis shows that the blended blade profile enlarges the dihedral angle and creates a span-wise pressure gradient to move low momentum fluid towards the mainstream. Furthermore, the inclining hub geometry accelerates the accumulated flow in the corner downstream by increasing the pressure gradient. Overall, though losses in the mainstream grow, especially for large incidences, the full-BBEW technique effectively reduces the separation in corners.     

A generative deep learning framework for airfoil flow field prediction with sparse data

Deep learning has been probed for the airfoil performance prediction in recent years.Compared with the expensive CFD simulations and wind tunnel experiments, deep learning models can be leveraged to somewhat mitigate such expenses with proper means. Nevertheless, effective training of the data-driven models in deep learning severely hinges on the data in diversity and quantity. In this paper, we present a novel data augmented Generative Adversarial Network(GAN), da GAN, for rapid and accurate fl...     

间隙变化对压气机静叶叶栅气动性能的影响

利用压气机平面叶栅试验,在大负攻角工况、设计工况和角区失速工况下,研究间隙变化对叶栅气动性能的影响,并分析内部流动变化与气动性能变化的关联。试验结果表明,不同工况下间隙变化对流场结构的影响不同,因而对叶栅性能的影响规律也不同。大负攻角工况下,不同间隙叶栅内在压力面前缘附近都存在一对由端壁向叶展中部发展的分离涡,间隙增大可以使叶栅总损失近似线性减小,并使间隙侧气流折转能力略微提升。设计工况下,无间隙侧吸力面角区存在轻微的角区分离,小间隙（0.2%展长）的引入首先会加剧间隙侧角区分离,当间隙进一步增大时,角区分离消失并形成泄漏涡结构。叶栅总损失随间隙增大呈先增大后减小再增加的趋势,角区分离的消除有助于提高间隙侧气流折转能力。角区失速工况下,间隙的引入可以削弱并移除间隙侧角区失速结构,从而使叶栅总损失下降,并在0.5%展长间隙时达到最小值,同时间隙侧气流折转能力得到增强。当间隙进一步增大时,叶栅损失变化不大。在间隙变化过程中,两侧端部流动结构产生相互影响,使两侧流场性能变化呈相反趋势。通过对比全工况范围内的气动性能,叶栅在选取0.5%展长间隙时整体性能最优。     

Impulse feature extraction method for machinery fault detection using fusion sparse coding and online dictionary learning

Impulse components in vibration signals are important fault features of complex machines. Sparse coding(SC) algorithm has been introduced as an impulse feature extraction method, but it could not guarantee a satisfactory performance in processing vibration signals with heavy background noises. In this paper, a method based on fusion sparse coding(FSC) and online dictionary learning is proposed to extract impulses efficiently. Firstly, fusion scheme of different sparse coding algorithms is presented to ensure higher reconstruction accuracy. Then, an improved online dictionary learning method using FSC scheme is established to obtain redundant dictionary and it can capture specific features of training samples and reconstruct the sparse approximation of vibration signals. Simulation shows that this method has a good performance in solving sparse coefficients and training redundant dictionary compared with other methods. Lastly, the proposed method is further applied to processing aircraft engine rotor vibration signals. Compared with other feature extraction approaches, our method can extract impulse features accurately and efficiently from heavy noisy vibration signal, which has significant supports for machinery fault detection and diagnosis.     

基于深度图推理的卫星背板部件检测方法

在轨加注是一种典型的在轨服务操作,它对于降低空间运输成本和任务风险起着重要的作用,视觉感知系统可以感知操作任务周围环境并提供给控制系统。目前在轨加注依赖于人,在人员监控下完成或通过遥操作完成,缺乏自主性。本文围绕未来高自主性的基于深度强化学习的在轨加注方法,对基于深度学习的视觉感知方法展开了研究,针对基于深度学习的方法对相似实例的检测存在精确率低、对光照变化敏感等缺点,提出了基于深度图推理的卫星背板部件检测方法。提出的方法可以有效地检测复杂形状的目标,不依赖于手工设计的特征;提高了复杂光照环境下部件的检测正确率;可以有效区分外形相似的不同部件;其有效性在数学仿真和物理仿真中均得到了验证。     

空间机器人深度学习识别捕获部位的应用探讨

针对空间机器人对捕获部位识别方法的普适性、实时性和准确性等要求,提出了采用深度学习方法对空间机器人捕获目标的特征部位进行识别。通过比较分析方法、数据驱动方法等传统识别方法和深度学习方法的优缺点,发现深度学习方法对于解决空间机器人捕获部位识别问题具有显著优势。进一步分析了应用深度学习方法解决捕获部位识别问题的几个关键技术问题,为后续空间机器人在轨捕获目标的研究与实践提供了新的思路。     

基于深度学习的发动机叶片故障检测技术

为了解决航空发动机叶片故障检测中存在的检测精度欠佳、检测效率不高的问题,提出了一种基于深度学习的目标检测方法。针对小样本数据集检测精度低、模型训练速度慢等问题,对Faster R-CNN目标检测算法进行结构优化,引入Res2Net结构,通过分割串联的策略强化残差模块的卷积学习能力,搭建了细粒级的多尺度残差模型Res2Net-50,以提升模型的特征提取能力。同时,在网络的训练过程中,采用多次余弦退火衰减法对学习率进行调整,以加快模型的训练速度,提升模型的训练质量。针对航空发动机叶片裂纹和缺损2种故障类型进行网络训练与检测试验,试验结果表明：优化后的模型识别准确率提高了0.7%,模型的平均检测精度提高了1.8%,训练时间缩短了5.56%,取得了比较好的检测效果。     

端壁抽吸位置对压气机叶栅角区分离控制的影响

以某高负荷压气机叶栅为研究对象,应用数值模拟方法探索了叶栅端壁不同抽吸位置对角区流动结构、通道漩涡发展过程以及叶栅性能的影响规律,寻求控制角区分离的可行方法。研究结果表明:在叶栅前缘上游5%C(弦长)位置实施抽吸,延缓了通道涡的形成,但导致叶栅来流攻角发生改变,在角区形成角区分离涡,并且该漩涡与通道涡相互促进,进一步恶化叶栅流场,导致叶栅落后角增大,损失增加;在叶栅通道激波后25%C端壁抽吸,吸除了上游端壁积累的高熵低能气流,制约了通道涡的迅速发展,改善了叶栅通道的流场结构,降低了流动损失,但并未对上游流场产生较大影响,是一种可行的方案。然而25%C处抽吸后,未能完全消除分离,在端部与叶栅通道主流之间存在较高损失区域。     

基于深度学习的无人机航拍目标检测研究综述

目标检测是提高无人机（UAV）感知能力的关键技术之一,其研究对于无人机的应用有着重要意义。与基于手工特征的传统方法相比,基于卷积神经网络的深度学习方法具有强大的特征学习和表达能力,成为目前目标检测任务的主流算法。近年来,目标检测技术已经在自然场景图像上取得了一系列突破性进展,在无人机领域的研究也逐渐成为热点。首先系统阐述了基于深度学习的目标检测算法的研究进展,并总结了相关算法的优缺点。对常见的航空影像数据集进行了梳理并介绍了迁移学习的方法;从无人机影像背景复杂、目标较小、视场大、目标具有旋转性的特点出发,对无人机目标检测在近期的研究进行了归纳和分析。最后讨论了存在的问题和未来可能的发展方向。     

Detection and diagnosis of sensor and actuator failures using IMMestimator

An approach to detection and diagnosis of multiple failures in a dynamic system is proposed. It is based on the interacting multiple-model (IMM) estimation algorithm, which is one of the most cost-effective adaptive estimation techniques for systems involving structural as well as parametric changes. The proposed approach provides an integrated framework for fault detection, diagnosis, and state estimation. It is able to detect and isolate multiple faults substantially more quickly and more reliably than many existing approaches. Its superiority is illustrated in two aircraft examples for single and double faults of both sensors and actuators, in the forms of “total”, “partial”, and simultaneous failures. Both deterministic and random fault scenarios are designed and used for testing and comparing the performance fairly. Some new performance indices are presented. The robustness of the proposed approach to the design of model transition probabilities, fault modeling errors, and the uncertainties of noise statistics are also evaluated     

基于改进YOLOv4的航空发动机小目标损伤检测研究

智能化的航空发动机损伤检测是飞机故障诊断重要的研究方向,针对现有目标检测模型对航空发动机的小目标损伤检测效果差的问题,提出了一种改进的基于You Only Look Once version 4(YOLOv4)的多尺度目标检测方法。在路径聚合网络（PANet）中构建低层次的特征融合层,将更浅层的特征与深层特征融合,提高网络对小目标损伤的检测性能。为减少网络中的冗余参数,在颈部结构中引入了深度可分离卷积,将标准卷积重构为深度可分离卷积的形式。实验表明：改进后的YOLOv4对小目标损伤的检测精度提升了3.43%,模型大小降低了54.06 MB,同时检测速度提高了31.03%。研究结果表明改进的YOLOv4模型对小目标损伤具有更好的检测性能。