Data-driven dual-rate cascade control and application to pitch angle control of UAV

A data-driven design method for a cascade control system is proposed. The cascade control system consists of inner and outer loops, where the control interval of the outer loop is an integer multiple of the inner loop; hence, the system is a dual-rate system. In the proposed method, controllers in the inner and outer loops are designed based on one-shot data. In such a dual-rate cascade system, since the controllers are designed using different data-rate signals, the lifting technique is applied to align the dual-rate data. To show its effectiveness, the proposed method is compared with a conventional single-rate cascade control method, and numerical simulations and experiments are presented to examine servo and regulation performance.     

Several Factors Affecting the Inspection of Wind Turbines by UAV

The country strongly supports the development of new energy industries, with the clean energy wind power industry developing rapidly and the market maturing, the scale of wind farms and installed capacity expanding, and the blade length increasing to 60-70m. The increased blade length and weight increase the probability of damage. the manual inspection method is time-consuming and laborious, with a high economic cost, low inspection efficiency, and high safety risks, and cannot meet the current wind turbine fast and efficient inspection requirements. This paper intro-duces the characteristics of the type of UAV, its working status, and mode, and proposes how to determine the best area for UAV inspection according to the factors that can cause interference to the inspection in the actual wind field, to achieve the demand for fast and efficient inspection of the blade surface and improve the accuracy of inspection. It is believed that with the development of UAV technology, UAVs will play a more important role in the field of in-spection.     

一种实时多尺度目标检测识别算法

无人机目标检测与识别任务中,目标随着飞行高度的改变尺寸发生显著变化。常规目标检测模型中,获取的小目标细节信息有限,检测精度较低;而适用于小目标的实时检测模型往往容易丢失大目标的背景信息,降低大目标的检测精度。针对以上多尺度目标检测识别任务难点,提出一种基于改进特征金字塔网络(Feature Pyramid Network, FPN)结构的实时多尺度目标检测识别模型。该模型通过增加特征金字塔层级覆盖更广的目标尺度,获取更为丰富的目标信息;同时,利用跨连接增加不同尺度特征融合的多样性,降低特征传导距离,保留更加完整的尺度特征来提高模型检测识别多尺度目标的性能。通过实验发现,相比于原始网络结构和相同特征层级的四层特征金字塔结构,加入改进特征金字塔结构的多尺度目标检测模型识别性能得到了提升。     

无人机数据链暗室拉距测试方法

无人机数据链的有效通信距离是无人机的一项重要指标,如何准确高效地对有效通信距离进行测试表征,对于无人机安全运行和评估系统正常工作的可靠度具有重要意义。在分析无人机数据链通信链路中传输损耗构成的基础上,从测试环境可控性、测试效率、可重复性、贴近业务应用等方面比较了当前主要测试方法之间的优劣,设计了室内拉距测试方法并完成相应测试,最后根据吞吐量指标对有效通信距离与实际业务应用间的关系进行了讨论。所提出的无人机数据链有效通信距离测试方法简单易行,测试结果准确,具有较强的实用价值。     

孪生网络框架下融合显著性和干扰在线学习的航拍目标跟踪算法

针对一般跟踪算法不能很好地解决航拍视频下目标分辨率低、视场大、视角变化多等特殊难点,该文提出一种融合目标显著性和在线学习干扰因子的无人机(UAV)跟踪算法.通用模型预训练的深层特征无法有效地识别航拍目标,该文跟踪算法能根据反向传播梯度识别每个卷积滤波器的重要性来更好地选择目标显著性特征,以此凸显航拍目标特性.另外充分利用连续视频丰富的上下文信息,通过引导目标外观模型与当前帧尽可能相似地来在线学习动态目标的干扰因子,从而实现可靠的自适应匹配跟踪.实验证明:该算法在跟踪难点更多的UAV123数据集上跟踪成功率和准确率分别比孪生网络基准算法高5.3%和3.6%,同时速度达到平均28.7帧/s,基本满足航拍目标跟踪准确性和实时性需求.     

基于无人机影像的电网绝缘子自爆识别

电网因其在电能传输方面的关键性作用,在我国民生项目建设领域一直扮演着至关重要的角色。电网杆塔上的绝缘子一旦发生自爆(也称“缺陷”),绝缘子会自动剥落,输电线路就会产生安全隐患,严重时会降低输电线路的运行寿命,甚至会引发供电中断,发生大范围的停电事故,造成巨大的财产损失。目前,主流的巡检方法为人工巡检,该方法不仅耗时耗力,而且也存在一定主观出错率,已不适用于目前电路巡检的实际情况。本设计采用YOLO V5网络模型,对无人机航拍影像中绝缘子串及绝缘子自爆进行自动识别。首先通过平移、翻转、裁剪等,对航拍绝缘子影像数据集进行数据增广,并对增广后的数据集在LabelImg中进行标注,然后利用YOLO V5网络模型对绝缘子串及绝缘子自爆进行识别,最后采用PyQt5框架在PyCharm中设计了绝缘子自爆识别的系统界面,对模型进行调用,实现了绝缘子串及绝缘子自爆识别。本设计采用从网络上下载、国家电网提供、数据增广所得到的500张无人机航拍影像作为数据集,对所得数据集进行人工标注,再使用YOLO V5网络模型进行训练和测试,结果表明YOLO V5网络模型对绝缘子串具有较高的识别精度,最高识别精度为90.2%,对绝缘子自爆的最高检测精度为80.8%。这说明了YOLO V5网络模型在绝缘子串识别方面有较好的表现,但是由于训练集中绝缘子自爆的样本影像数量有限,所以该网络模型对绝缘子的自爆识别存在一定局限性,本实验能够部分代替人力实现电网绝缘子智能巡检,提高了检测效率。     

无人机载PolInSAR城区散射机制初步分析

极化干涉合成孔径雷达（PolInSAR）在城市遥感领域中扮演着重要角色。它能够提高图像的相干性并提高反演结果的精度,所以对于其散射机制的解释往往受到许多研究人员的关注。相关的研究多从极化分解的角度考虑,却少有人从散射中心高度方面进行分析。本文使用Ku波段无人机载极化干涉SAR系统,实现了使用无人机SAR系统对地面进行成像,比较了极化干涉最优分解与Pauli分解作用在不同人造目标时散射中心的关系。我们初步分析了极化干涉SAR的物理意义,并使用C波段的机载极化干涉SAR系统对结论进行验证。     

三维重建技术在拆除爆破中的应用

随着工程爆破行业迈向精细爆破时代,工程技术融合发展极大地推动了爆破技术的数字化、标准化、可视化。影像获取方式的多元化发展,推动了爆破技术的进步。以武汉市原新能酒店爆破拆除工程为案例,采用无人机等载体搭载相关测量设备,对爆破区域进行影像数据扫描,获取区间的影像数据,并通过三维重建软件进行后处理,快速获取爆破区域内的三维影像信息。实践证明:三维重建技术能够在爆破前为爆破工程的设计、施工和安全防护等方案确定提供必要的信息支撑;在爆破后,数字化重现爆破效果,实现对爆堆各项参数的定量分析,从而多角度、全方位地评估爆破质量。采集的影像数据经过适当处理后还可作为档案长期保存,为后续相关爆破工程提供有效参考。     

Additive Manufacturing of Porous Structures for Unmanned Aerial Vehicles Applications

Unmanned aerial vehicles (UAVs) have shown promising benefits in many applications. This has been enabled by the emergence of additive manufacturing (AM), which give the designers a large amount of geometrical freedom. In this paper, a novel design process of fused deposition modeling (FDM) combining both topology and infill optimization is introduced for AM of high performance porous structures. Tensile testing of FDM printed samples is first carried out to study the effect of the build orientation on the mechanical properties of acrylonitrile butadiene styrene (ABS) samples. It is found that samples built perpendicular to the load axis are the weakest with a tensile strength of 29 MPa and Young's modulus of 1960 MPa. The materials properties are fed to the finite elements analysis (FEA) for geometrical topology optimization, aiming to maximize stiffness and reduce weight of those parts. Afterwards, an infill optimization is carried out on the topology optimized parts using different mesostructures such as honeycomb, triangular, and rectangular to achieve high structural performance. The results showed that triangular pattern with 50% infill density had the lowest developed stresses, less mass, and strain energy when compared to other structures. Optimum UAVs parts of a quadcopter are successfully manufactured, assembled, and tested.

     

无人机飞控系统故障诊断专家系统设计

针对无人机飞控系统的特点和维护要求,本文介绍了MBIT故障诊断专家系统的设计思路和实现方法,构建了无人机飞控系统故障诊断专家系统的体系结构,深入研究了如何建立故障知识库,制定推理机制,组建综合数据库和故障解释等问题。并结合某型号给出了具体的示例。在工程实际应用过程中,可以利用本系统对无人机飞控系统进行有效维护。