一种直升机避障电力线检测方法

电力线是一类形状细长、特征稀疏、随着视角的变化容易混淆在大量背景信息中的特殊障碍物，常规电力线检测识别算法得到的目标框对电力线所在位置的估计不够准确。为此，提出了一种相对角度估计方法，基于常规电力线目标检测与识别算法，并结合电力线相对角度估计，从而提高电力线的检测识别过程中所在位置的精度。相比电力线绝对角度回归的方法，提出的相对角度估计方法容易训练易收敛，计算量小，适用于实时性要求较高的应用场合。     

基于人工神经网络的智能化架空线路应变快速解调方法北大核心

为了提高智能化光纤复合架空线路态势感知的实时性,将人工神经网络方法应用于光纤沿线应变解调,确定了神经网络的结构。编程实现了基于洛伦兹模型的最小二乘谱拟合方法和神经网络方法,采用不同信噪比和布里渊频移的布里渊谱训练神经网络,将它们应用于某光纤复合架空线路沿线光纤应变的测量,从不同角度比较了两种方法的计算结果。计算结果表明,神经网络方法能有效获得光纤沿线的布里渊频移进而获得应变,具有与谱拟合方法相似的准确性,但应变解调时间仅约为谱拟合方法的1/20000。研究结果为提高智能光纤复合架空线路态势感知的实时性提供了参考。     

Optical design of the Lyman alpha based beam emission spectroscopy(LAB)diagnostic on the HL-2A tokamak

In this article, we present the optical design of a novel diagnostic on the HL-2 A tokamak, i.e. the20-channel edge Lyman-alpha beam emission spectroscopy, which is a promising solution for edge density turbulence research on tokamaks, as it offers the possibility of density fluctuation measurement with a 3.3 mm spatial resolution while maintains a high temporal resolution of1 μs. The optical path, including the reflective collection optics, the high-dispersion spectrometer, and the linear detector array, is carefully optimized to obtain a good image quality and a high throughput. The maximum root mean square radius of the collection optics is 64 μm.The detected photon flux is estimated to be about 10~(11) photons/s/channel.     

Transmission line detection in aerial images: An instance segmentation approach based on multitask neural networks

Camera-based transmission line detection (TLD) is a fundamental and crucial task for automatically patrolling powerlines by aircraft. Motivated by instance segmentation, a TLD algorithm is proposed in this paper with a novel deep neural network, i.e., CableNet. The network structure is designed based on fully convolutional networks (FCNs) with two major improvements, considering the specific appearance characteristics of transmission lines. First, overlaying dilated convolutional layers and spatial convolutional layers are configured to better represent continuous long and thin cable shapes. Second, two branches of outputs are arranged to generate multidimensional feature maps for instance segmentation. Thus, cable pixels can be detected and assigned cable IDs simultaneously. Multiple experiments are conducted on aerial images, and the results show that the proposed algorithm obtains reliable detection performance and is superior to traditional TLD methods. Meanwhile, segmented pixels can be accurately identified as cable instances, contributing to line fitting for further applications.     

Microwave bandpass filter by feedback interference topology

This paper proposes a signal feedback interference topology to control the characteristics of a coupled line bandpass filter. Control is carried out by varying the ratio of the transmission line parameters of the forward and the feedback couplers. The topology produces a compact filter that does not require a complicated design or fabrication. The results of the insertion and return losses show that the feedback‐controlled design has desirable features in terms of the design frequency, fractional bandwidth, stopband rejection level, roll‐off rate and insertion loss. The test results of the fabricated prototype achieved good agreement with the simulation results of the ideal transmission line design model. Several microwave, modern wireless and mobile/satellite communication systems may benefit from such a filter design due to its compactness and flexibility.     

Smart control of the assembly process with a fuzzy control system in the context of Industry 4.0

Assembly line balancing is important for the efficiency of the assembly process, however, a wide range of disruptions can break the current workload balance. Some researchers explored the task assignment plan for the assembly line balancing problem with the assumption that the assembly process is smooth with no disruption. Other researchers considered the impacts of disruptions, but they only explored the task re-assignment solutions for the assembly line re-balancing problem with the assumption that the re-balancing decision has been made already. There is limited literature exploring on-line adjustment solutions (layout adjustment and production rate adjustment) for an assembly line in a dynamic environment. This is because real-time monitoring of an assembly process was impossible in the past, and it is difficult to incorporate uncertainty factors into the balancing process because of the randomness and non-linearity of these factors. However, Industry 4.0 breaks the information barriers between different parts of an assembly line, since smart, connected products, which are enabled by advanced information and communication technology, can intelligently interact and communicate with each other and collect, process and produce information. Smart control of an assembly line becomes possible with the large amounts of real-time production data in the era of Industry 4.0, but there is little literature considering this new context. In this study, a fuzzy control system is developed to analyze the real-time information of an assembly line, with two types of fuzzy controllers in the fuzzy system. Type 1 fuzzy controller is used to determine whether the assembly line should be re-balanced to satisfy the demand, and type 2 fuzzy controller is used to adjust the production rate of each workstation in time to eliminate blockage and starvation, and increase the utilization of machines. Compared with three assembly lines without the proposed fuzzy control system, the assembly line with the fuzzy control system performs better, in terms of blockage ratio, starvation ratio and buffer level. Additionally, with the improvement of information transparency, the performance of an assembly line will be better. The research findings shed light on the smart control of the assembly process, and provide insights into the impacts of Industry 4.0 on assembly line balancing.     

直缝埋弧焊钢管焊缝点状缺陷原因分析及改进

为了解决壁厚23 mm直缝埋弧焊管出现的焊缝点状缺陷问题，通过超声波探伤和宏观金相检测对实际生产过程中出现的焊缝点状缺陷不合格试样进行了分析，对铣边坡口形状、焊接工艺参数、焊接材料、焊接设备及焊件清理等方面给出了相应的优化改进措施。现场应用效果表明:这些措施的实施有效控制了此类直缝埋弧焊管焊缝中的点状缺陷，保证了直缝埋弧焊管焊缝形貌及各项力学性能指标，提高了焊接质量。     

混炼方式对螺旋纳米碳纤维增强天然橡胶复合材料力学性能的影响

采用干法和湿法两种混炼工艺制备了螺旋纳米碳纤维(HCNFs)/炭黑(CB)/天然橡胶(NR)复合材料,通过扫描电镜、拉伸试验机和应变扫描仪分别对所制备复合材料的界面形貌、力学性能和Payne效应进行了测试分析,考察了混炼方式对复合材料宏观力学性能及Payne效应的影响。结果表明,与纯CB填料相比,在干湿两种混炼方式下,添加适量的HCNFs(1～6份)能提高HCNFs/CB/NR复合材料的300%定伸应力、扯断伸长率、拉伸强度和硬度。与干法混炼相比,湿法混炼能明显增强HCNFs/CB/NR复合材料的Payne效应,并提升在HCNFs高添加量(2～6份)条件下的拉伸强度和扯断伸长率,这主要源于湿法混炼能够有效改善HCNFs在橡胶基质中的分散性。     

基于RGV轨导柔性线环境离散型零件生产过程管理与实践

为满足航空中小型结构件快速交付的需要,以提升航空中小型结构件制造高精度、自动化和高效率为目标,通过对航空中小型结构件加工现状进行梳理分析,搭建柔性生产线自动排程与调度平台,实现柔性生产线工艺设计与准备过程管理,简化工艺准备流程,推进快换工装的应用并进行自动化程序管理;在柔性生产线加工运行过程中采用可视化管理方法,推动自动化环境下加工过程资源保障集中化管理。最终使该管理方法在某项目中进行成功实践,取得了良好的经济效益。     

低渗透油藏中不同压裂注采井网非稳态产量计算分析

在井网压裂基础上进行注水，可以有效改善流场，增大泄油面积，是开发低渗透油藏的重要手段。快速准确预测低渗透油藏注水开发产量可以为开发优化设计奠定基础，但低渗透油藏注水开发呈现非稳态、非线性渗流特征，基于达西定律形成的油藏工程方法并不适用。本次研究通过流场分析，来划分等效流动单元，并在此基础上考虑了油水两相渗流启动压力梯度，采用流线积分法建立了不同压裂注采井网的水驱非稳态产量解析计算方法。与物理模拟及数值模拟相比，计算方法更简单，计算速度更快，可以为低渗透油藏压裂注采方式优选及注水开发对策制定提供手段。采用本方法计算并剖析了启动压力梯度、压裂注采方式及裂缝长度对油井生产动态的影响，结果表明：启动压力梯度增大了渗流阻力，与不考虑启动压力梯度相比，油井产量更低；受流动单元控制，不同压裂注采方式的增产效果及见水时间完全不同，同时压裂注采方式的增产效果最好，能够增产3.1倍，但见水时间仅为24个月；随着压裂缝长增加，油井产量越高，但当缝长超过最佳长度，增油效果不明显。