基于视觉的机器人智能化焊接技术现状与发展

针对机器人自动焊接技术快速发展的现状,结合机器视觉技术、智能控制技术和信息技术在焊接技术领域应用的特点,归纳综合了弧焊视觉传感技术、激光接缝跟踪技术、熔池视觉形态特征传感与提取技术、熔透与熔深智能控制技术、缺陷监测及控制技术和基于网络的数字化焊接技术的研究现状,分析了激光跟踪传感器结构、熔池与接缝计算机图像处理方法、熔池视觉几何特征提取方法、熔深熔透视觉传感与判断技术、基于网络的焊接信息远程传输与品质评价技术,给出了弧焊机器人智能化和数字化焊接技术优质、高效、柔性、快速、适应性强的特点,探讨了的智能化、数字化焊接技术的主要发展方向。     

基于PSO-SVR的15-5PH合金粉末激光熔覆层稀释率预测方法

为了预测15-5PH合金粉末激光熔覆层稀释率进而改善熔覆层性能,提出一种基于粒子群算法(PSO)优化支持向量回归(SVR)的15-5PH激光熔覆层稀释率预测方法。以15-5PH为熔覆材料,45钢为基体进行激光熔覆实验;基于实验结果建立了工艺参数与15-5PH熔覆层稀释率间的SVR模型;优选SVR模型的核函数并运用PSO优化SVR模型的参数。结果表明：PSO-SVR模型选择高斯核函数时预测性能最好;与SVR模型和BP神经网络模型的预测结果相比,PSO-SVR模型对15-5PH熔覆层稀释率的预测结果更准确,模型的决定系数为0.964 7,均方误差为0.000 3,平均相对误差为3.6%。     

曲轴轴颈损伤表面的激光熔覆再制造修复研究

要对发动机曲轴的激光熔覆进行再制造修复,可以在曲轴材料钢样板表面制备铁基激光熔覆层方面应用激光熔覆技术,结合熔覆层自身的性能,通过光学显微镜和显微硬度计实施熔覆层金相组织观察和硬度测试工作。相关试验结果表明,熔覆层和基体之间结合性能极佳,熔覆层硬度是基体硬度的3倍左右。同时,要使曲轴基于绕主轴径旋转现状下实施多拐曲轴连杆轴径激光熔覆作业,需要掌握好连杆轴径表面获取连续均匀熔覆层应当符合的基本要点,在满足基本要求的同时,提出激光束和转动轴径的运动轨迹以及相对速度之间的关系模型,并采取试验方式验证轨迹模型的可行性。     

碳化硼及硅铁稀土激光熔覆层摩擦学性能研究

为考查稀土镧元素对硼的催渗作用及对激光熔覆层性能的影响，用铁粉、碳化硼、硅铁稀土等物质，在45^#钢试块表面熔覆一层高镧高硼激光熔覆层，并在摩擦磨损试验机上考察了熔覆层的摩擦学性能。通过熔覆层表面组织XPS(X射线光电子能谱仪)分析，探讨了在稀土镧元素作用下，熔覆层的组织性能变化及对摩擦副摩擦学性能的影响。试验结果表明：稀土元素加入改善了表层组织结构，避免了熔覆层表面开裂现象的发生，表层硬度及耐磨性能得到了显著改善，硅铁稀土加入量为5％～6％时熔覆层耐磨性能最佳。     

基于等温线分布的熔透控制系统模型及系统仿真分析

建立了基于等温线分布的熔透闭环控制系统模型，对控制系统进行了仿真分析，获得了控制器参数的优化值，试验表明控制系统具有较好的适应性。     

电子束焊熔深神经网络模糊控制系统建模与仿真

研究钛合金电子束焊熔深控制系统建模问题。在分析电子束焊接特点的基础上,设计三因素五水平正交试验,通过试验得到不同焊接参数下熔宽和熔深的值,将熔宽和熔深的值作为训练样本对神经网络进行训练,建立以熔宽为输入,以熔深为输出的误差反向传播(Error back propagation,BP)神经网络模型,该模型由一个S型函数隐含层加上一个线性输出层组成。针对熔深数学模型难以获得的情况,设计以熔深的偏差和偏差变化率为输入变量,焊接电流的变化量为输出变量的模糊控制器,该控制器有9条模糊控制规则。将BP神经网络模型和模糊控制器结合起来建立钛合金电子束焊熔深控制系统模型,并且采用单位阶跃信号对该模型进行仿真试验,试验结果表明所设计的控制系统动态性能和稳态性能良好。     

注塑参数优化方法研究

对参数优化方法在注塑研究中的应用进行综述,阐述了各方法的基本原理和主要特点,着重讨论优化方法所适用的优化问题的类型和其对注塑翘曲、收缩、熔接缝及强度的预测能力以及模拟软件的应用,探讨了不同优化方法相结合对搜索效率和优化结果的影响。强调了基于知识的参数优化方法在注塑研究中的重要性。     

熔敷金属力学性能人工神经网络模型的研究

在试验的基础上,采用人工神经网络方法建立了基于BP算法的熔敷金属力学性能的预测模型,该模型训练结果与试验值之间有很好的对应关系,说明该模型能准确反映合金元素与熔敷金属力学性能之间复杂的非线性关系。用该模型研究了合金元素对熔敷金属低温韧性的影响,分析得出了与试验一致的结果。     

纯Cr粉末激光熔覆技术研究

利用激光在PCrNi3Mo钢上熔覆纯Cr粉末，采用多道搭接技术实现了大面积激光熔覆，利用预热技术有效地消除熔覆层的裂纹。试验结果表明，获得了激光熔覆的最佳工艺参数，激光熔覆层均匀连续，无宏观气孔和裂纹，激光熔覆层与基体发生了冶金结合。熔覆层组织紧密，细化了晶粒和组织结构，硬度和耐磨损性能较高。     

基于卷积神经网络的GTAW熔透预测

焊接熔池信息能反映熔透状态,但建立熔池与熔透状态的关系十分困难。针对该问题,提出一种基于卷积神经网络(Convolution neural networks,CNN)的GTAW背面熔透预测模型。通过基于被动视觉的熔池二维图像采集,建立了用于CNN网络训练和测试的训练集和测试集。其次建立了CNN背面熔透预测模型,优化了学习率、batch-size、迭代次数等网络参数。研究发现:第一层卷积核尺寸为9×9,最后一层含有64个卷积核使模型在预测准确率和训练时间上综合表现达到最佳。使用训练集数据训练模型,将训练完成的模型在测试集上对背面熔透进行预测,取得了高于96%的预测准确率。通过对预测模型的特征映射进行可视化分析,模型是通过熔池边缘,反光点位置和熔池尾部等特征来预测背面熔透情况。     

基于MPI电脑面板注塑模优化设计

运用流动模拟分析软件MPI(Moldflow Plastics Insight)对电脑面板的注射成型工艺和填充过程进行计算机模拟,分析了模具不同浇口设置对注塑工艺造成的影响.主要通过填充过程工艺参数、熔接痕、气穴等对比分析,以保持注塑过程工艺参数合理和产品质量最好为目的,优化设计了电脑面板模具的浇注系统.     

注射填充过程的计算机模拟

以Ｈｅｌｅ－Ｓｈａｗ 流动为基础,建立了塑料熔体充模流动的数学模型。采用ＭＯＬＤＦＬＯＷ 充模模块,对轿车发电机散热罩的充模流动过程进行了动态模拟。分析并解决了影响制品质量的主要原因和问题。     

注射填充过程的计算机模拟

以Hele-Shaw 流动为基础,建立了塑料熔体充模流动的数学模型。采用MOLDFLOW 充模模块,对轿车发电机散热罩的充模流动过程进行了动态模拟。分析并解决了影响制品质量的主要原因和问题。     

Sensing characteristics of contact-type transducer for flexural waves

For the purpose of understanding and improving the stress wave factor technique and the travelling wave control method, the sensing characteristics of contact-type transducers for flexural waves are investigated in this paper. Two kinds of frequency response functions (FRF) are presented to characterize the transducer sensing results: one is for any harmonic plane wave, and the other for any point source disturbance. The two FRF are both expressed in the form of explicit physical interpretations which distinguish the influences from the transducer itself and from the tested structure. Based on this, three characteristic lines about the FRF are presented: one is a scattering line which means the FRF is dominated by the nature of wave scattering or wave reflection, the other two are transducer’s mass and spring lines which imply the transducers properties dominate the FRF. Using these three lines, the difference between general ultrasonic transducers and general vibration transducers can be clearly identified. Finally using the fast Fourier transform (FFT) technique, some typical time domain numerical results of the transducer output are also presented to show some important sensing characteristics.     

First-mode properties of N-story buildings

First-mode properties of N-story buildings determined from a standard computer program possess certain simple relationships which can be displayed graphically by straight lines. Structures investigated include uniform buildings and buildings with reduced first floor stiffness. Some of the results presented are verified analytically from difference equations.     

圆弧类涡旋修正齿型泄漏线的计算

分析了圆弧类涡旋修正齿型的啮合特点及啮合规律，由此提出了适用于所有圆弧类修正齿型的涡旋机械工作腔周向及径向泄漏线动态长度的精确计算方法。并对应用较多的动静盘齿端形状相同的修正齿型，给出了泄漏线的简化计算方法，为涡旋机械工作过程的深入研究提供了理论基础。     

First-mode properties of N-story buildings

First-mode properties of $\text{N-}\text{story}$ buildings determined from a standard computer program possess certain simple relationships which can be displayed graphically by straight lines. Structures investigated include uniform buildings and buildings with reduced first floor stiffness. Some of the results presented are verified analytically from difference equations.     

基于微米压入的延性金属单轴拉伸性能与断裂韧性评价技术研究进展

微米压入技术已可实现延性金属材料力学性能的准无损检测,相对于传统力学性能测试手段,该技术不仅可实现焊接接头、增材修复界面等微尺度复杂结构力学性能的准无损评价,还可用于在役设备关键重要部件力学性能的在线监测,为其安全预警与寿命预测提供依据。系统总结基于微米压入的延性金属单轴拉伸性能及断裂韧性评价技术的研究及应用现状。首先,较完整地阐述各类评价模型的基本原理、技术路线及实际应用现状,深入讨论不同评价模型的优点及局限性,给出领域内规范、标准的制定进展;然后,分别从理论研究和工程应用两个角度论述了基于微米压入力学性能评价方法存在的问题和挑战;最后,对微米压入力学性能检测技术的发展与应用趋势进行了展望。     

Nondestructive Testing of Mechanical Properties of Rolled Steel (Review): 1. Tests of Strength and Plastic Properties

This review considers the creation and development of a nondestructive technique based on coercive-force measurements used to determine strength and plastic properties of industrial rolling products made from Russian-produced low-carbon and low-alloy steels. The operating principle for a coercimeter equipped with a field electromagnet is described briefly. Regression lines of mechanical properties versus coercimeter readings are presented for 20Κ- and 09Γ2-steel sheets produced by Nizhni Tagil Iron and Steel Works. Different methods for considering sheet thickness and tube dimensions are discussed.__________Translated from Defektoskopiya, Vol. 41, No. 5, 2005, pp. 39–52.Original Russian Text Copyright © 2005 by Bida.     

A review of the techniques for the mold manufacturing of micro/nanostructures for precision glass molding

Micro/nanostructured components play an important role in micro-optics and optical engineering, tribology and surface engineering, and biological and biomedical engineering, among other fields. Precision glass molding technology is the most efficient method of manufacturing micro/nanostructured glass components, the premise of which is meld manufacturing with complementary micro/nanostructures. Numerous mold manufacturing methods have been developed to fabricate extremely small and high-quality micro/nanostructures to satisfy the demands of functional micro/nanostructured glass components for various applications. Moreover, the service performance of the mold should also be carefully considered. This paper reviews a variety of technologies for manufacturing micro/nanostructured molds. The authors begin with an introduction of the extreme requirements of mold materials. The following section provides a detailed survey of the existing micro/nanostructured mold manufacturing techniques and their corresponding mold materials, including nonmechanical and mechanical methods. This paper concludes with a detailed discussion of the authors recent research on nickel-phosphorus (Ni-P) mold manufacturing and its service performance.