Incorporating motion analysis technology into modular arrangement of predetermined time standard (MODAPTS)

Implementing new strategies to achieve higher work efficiency is essential to improve productivity during a monotonous and exhausting work task. The Modular Arrangement of Predetermined Time Standard (MODAPTS) concept is widely used to achieve these goals in the field of human factors. However, MODAPTS is very complicated with regard to assisting engineers in understanding the system because it requires much learning time and even longer hours of effort during coding manual process. To help overcome the deficiency of the traditional method, a modern method for motion analysis, called PCA-based motion analysis, is proposed in this paper. Motion analysis has already been the main approach to analyze human motion in sports science and biometrics, but it is still unfamiliar for human factors analysts. This paper discusses a potential connection between motion analysis technology and MODAPTS analysis, which would help make MODAPTS more efficient and reliable. In the experiment, fifteen participants were asked to watch a motion sequence and then analyze the motion sequence using MODAPTS. Meanwhile, the motion-captured data were carefully segmented into motion elements with the PCA approach. A comparison of the motion segmentation contrast was made between MODAPTS analysis and automatic motion element segmentation using PCA. The accuracy rate of segmentation by the PCA approach was 80.08%, and the primitive frames of the two methods indicated that the segmentation is acceptable. In addition, the PCA-based motion analysis showed a substantial time-saving difference in the processing time, which was only approximately 3 min for motion analysis versus over 1 h for MODAPTS. Motion analysis provides high efficiency and reliability for motion segmentation and sufficient precision compared to the results using MODAPTS. Moreover, assessment of the operations’ rationality and optimization of the production line design instead of repetitive work on motion segmentation is the focus. Integrating motion analysis technology into traditional MODAPTS is a useful advancement that permits significant progress for human factors analysis. In the future, the accuracy of the automatic segmentation techniques should be improved.Relevance to industryIn recent years, motion analysis technology has become increasingly popular in various fields but not in the field of human factors. The automatic method presented in this paper may allow industrial workers to optimize unreasonable motion, remove unnecessary operations and formulate the standard working time more conveniently and accurately.     

基于图像伺服的接触网绝缘子自动水冲洗车

目前铁路绝缘子维护领域内还没有自动水冲洗设备,本文提出了捕获跟踪与瞄准系统对绝缘子进行自动冲洗维护。在绝缘子识别的基础上,进一步设计出基于图像的视觉伺服系统(IBVS,Image-Based Visual Servoing)控制方法,调整冲洗水炮炮管及摄像机姿态对绝缘子进行瞄准,来完成绝缘子冲洗工作。该方法主要思路为写出特征函数的差并使其最小,特征函数是通过两个雅可比矩阵及其伪逆矩阵建立起图像与冲洗装置控制量之间的关系,最后达到控制目的。本文使用Matlab对IBVS控制方法进行验证,该方法控制双自由度冲洗装置精确性达到要求,可实现绝缘子冲洗瞄准。     

基于周期性结构特征的绝缘子掉片检测算法

由于受强电场、机械应力、污秽、温度以及湿度等影响,绝缘子经常出现内部裂缝、表面破损、绝缘阻抗降低及污闪等现象,进而造成电网停电事故,自动地检测绝缘子缺陷对保障电力网络的安全运行具有重要的意义。本文根据绝缘子相邻伞裙间距的不变性特点,提出一种绝缘子的掉片检测算法,首先,采用基于直方图的自适应分割方法,提取绝缘子区域图像,并进行水平倾斜校正,然后,利用灰度归一化相关匹配方法,估计绝缘子几何结构的周期性参数,最后,利用灰度归一化相关匹配方法,检测绝缘子掉片位置。针对无人机巡检的809张缺陷绝缘子数据集,绝缘子掉片检测的准确率和召回率分别达到95.8%和91.9%。与现有的方法相比,其优点是不需要事先利用大样本进行统计学习,对尺度、旋转、光照、背景以及绝缘子种类的变化均具有很强的适应性。     

Monitoring and optimizing the state of pollution of high voltage insulators using wireless sensor network based convolutional neural network

In this paper, a wireless sensor network (WSN) is combined with Convolutional Neural Network (CNN) forming a hybrid framework to detect the pollution state in high voltage insulators. The WSN is formed by the collection of sensor readings from each high voltage insulator over the transmission tower. The collected sensor readings from the sensor network is sent to the processing unit or detection unit, where CNN is used for the purpose of detecting the partial discharged high voltage insulator. The CNN is used with partial discharge diagnosis model to detect the dischargers in high voltage insulators. The extraction of relevant features from the CNN helps to improve the detection. The experimental validation are conducted on the proposed model with collected training datasets and real time testing datasets. The proposed method is compared with existing models to test the partial discharges in high voltage insulators, namely Artificial Neural Network, Fuzzy and Ant Colony Optimization. The result shows that the proposed method is effective in detecting the partial discharges than the existing methods in terms of False Acceptance Rate and Missing Detection Rate.     

基于先验知识的航拍绝缘子检测方法

在架空输电线路中对带电状态的绝缘子进行检测和故障定位,对保证电网可靠运行具有重大意义。基于无人机平台提出一种复杂背景条件下的绝缘子检测算法。在检测算法的特征提取层引入注意力机制模块以获取更多的绝缘子特征信息,同时利用航拍图像中绝缘子的先验知识,结合K均值聚类算法改进目标候选框的生成模式。在此基础上,通过将中心损失引入绝缘子检测目标函数以增强训练过程中绝缘子类内特征的内聚性。实验结果表明,相对Faster R-CNN检测算法,在绝缘子检测数据集上Faster R-CNN改进算法检测精度提高4%以上。     

面向改进尺度缩放网络的绝缘子识别

目的 在电力系统中，准确地识别绝缘子目标是保障输电线路正常运行的重要前提。针对传统方法无法自动提取绝缘子特征，以及深度学习网络提取绝缘子语义信息不足的问题，提出了一种基于改进多尺度网络的绝缘子识别模型，同时满足自动识别和增强语义信息的要求。方法 改进工作主要分为3部分，首先，采用特征融合的方法，增强特征提取网络生成的特征图的语义信息；其次，特征提取后，为了避免经过多次卷积、池化操作，较小尺度绝缘子语义信息损失严重，因此，扩大网络中的小尺度特征图，进一步丰富较小尺度绝缘子的语义信息；最后，为了更好地识别尺度差异较大的绝缘子，改进锚点框的参数。完成改进工作后，通过边框回归得到绝缘子的准确位置信息，最终识别出绝缘子。结果 实验数据集由复合、玻璃和陶瓷3种材质的绝缘子构成，共有4 350幅图像。在实验数据集上进行识别，实验结果与3种不同结构的多尺度网络模型相比，模型结构最优，识别准确率为96.28%，与传统的Faster RCNN（faster region convolutional neural network）、改进的Faster RCNN等方法相比，识别准确率提高了1.98%~11.99%不等。结论 本文提出的改进模型使绝缘子识别准确率显著提高，为之后的输电线路检测工作夯实基础。     

基于PLS分析的高压绝缘子污秽等级判定

针对污秽绝缘子红外热像特征数据具有多重相关性的特点,提出基于PLS(Partial Least Squares, PLS)回归分析的高压绝缘子污秽等级判定方法。在最大限度保留原有数据信息的前提下,建立起高压绝缘子污秽特征量与污秽等级之间的PLS回归模型方程,通过对回归模型方程进行变量投影重要性指标分析,可以得到各个特征量对污秽等级判定结果的影响程度。此方法有效解决了自变量之间的多重相关性问题,量化了污秽特征量与污秽等级之间的关系。测试结果表明,将PLS回归分析应用于高压绝缘子污秽等级的判定,科学可靠,准确率高,具有较强的实用性。     

使用改进Yolov5的变电站绝缘子串检测方法

针对变电站绝缘子串水冲洗机器人在复杂光照环境下无法准确识别绝缘子的问题,提出了一种基于改进Yolov5的绝缘子检测方法。首先针对逆光环境下图像质量差导致算法失效的问题,提出了一种模拟过曝增强算法,并应用到数据增强过程中;此外,针对变电站绝缘子检测任务,对网络的Neck进行了优化裁剪,使推理速度获得了提升;最后,使用注意力机制改善了裁剪后网络检测精度下降的问题。实验表明,改进后的Yolov5在检测精度基本不变的情况下推理速度提高了25%,并且对于逆光下图像的检测精度获得了大幅提升。     

光传感器中劣化绝缘子非接触式检测技术研究

传统的检测技术在检测光传感器中的劣化绝缘子时,检测范围小,成本高,且工作人员必须要直接接触传感器。为了解决上述问题,提出了一种新的光传感器中劣化绝缘子检测技术。利用驱动控制电机、LD光源、调节电路、光学传感头和电源设定检测通道,通过光纤自动判断绝缘子串的空间分布特性,将分析数据与数据库中的标准数据进行对比,得到检测结果。为验证所提检测技术的工作效果,与传统技术进行实验对比,结果表明,运用所提技术对劣化绝缘子进行检测时,检测成本远低于传统方法,说明该技术能够实现非接触式检测,检测范围广,成本低,对于保障电网安全运行有重要的意义。     

Efficient design sensitivity analysis of incompressible fluids using SPH projection method

Using the direct differentiation method, a design sensitivity analysis method for time-dependent incompressible fluids is developed. The fluid behavior is described as the motion of particles involved by the SPH method. In the SPH projection method, instead of changing the fluid density, incompressibility is enforced by the pressure Poisson equation derived from pressure projection, which enable to use larger time steps. In spite of the additional pressure Poisson equation, the computational cost for the design sensitivity is not expensive since the factorized system matrix of pressure Poisson equation can be utilized. Aforementioned computational efficiency is very beneficial for the design sensitivity computation required for every time step in explicit time integration and updated Lagrangian schemes, for which an update scheme of design velocity field is developed using the velocity sensitivity. Through demonstrative numerical examples, the developed DSA method turns out to be efficient and shows excellent agreement with finite differencing.     

磁致伸缩液位传感器中高分辨力时间量检测

高分辨力时间量检测是磁致伸缩液位传感器实现高准确度测量的关键技术之一.针对磁致伸缩液位传感器的国产化开发研制中的时间量检测问题,提出采用复杂可编程逻辑器件(CPLD)实现高分辨力时间量检测的方案.通过理论分析和实践证明:该方案可以满足磁致伸缩液位传感器对时间量检测的功能要求.该方案所用器件少、电路简单,可供有关国产化开发研制的技术人员参考.     

接触网绝缘子泄漏电流在线监测装置设计

为有效地预测接触网绝缘子污秽水平,提高接触网运行安全可靠性,设计了一种基于ARM的接触网绝缘子泄露电流在线监测装置。通过传感器采集泄露电流和环境湿度预测绝缘子污秽水平,从而判断绝缘子是否应该进行清洗。选取了FQBJ—25/8—760P复合绝缘子为研究对象,在饱和空气湿度下,利用在线监测装置进行人工污秽实验。利用实验数据拟合污秽水平与泄漏电流的关系曲线,为确定接触网绝缘子泄漏电流在线监测装置的预警值提供指导。基于污闪发展三区段思想,提出接触网绝缘子安全运行区、污秽清理区及危险区。     

Adaptive Dynamic Surface Control with Guaranteed L∞ Tracking Performance for a Class of Uncertain Nonlinear Systems with Unknown Time Delays

This paper is aimed at exploring dynamic surface control (DSC) for a class of uncertain nonlinear systems in strict‐feedback form with time delays. Combining the Finite Covering Lemma (Heine‐Borel Theorem) with neural networks, a novel method is proposed to approximate time delay terms, which leads to the abandonment of traditional Lyapunov‐Krasovskii functionals. Then, a surface error modification and an initialization technique are proposed to guarantee the tracking performance. Moreover, by applying a newly‐developed neural network based adaptive control technique, it is shown that the update law for the proposed DSC scheme is needed only at the last design step with only one parameter being estimated online, which significantly reduces the computational burden, compared with current DSC schemes. Simulation results are presented to illustrate the efficiency of the proposed scheme.     

带有关节权重的DTW 动作识别算法研究

大多数动作仅包含部分关节的运动,现有方法未对运动剧烈的关节与几乎不参与运 动的关节进行区分,一定程度上降低了动作识别精度。针对这个问题,提出一种自适应关节权重 计算方法。结合动态时间规整(DTW)方法,利用获得的关节权重进行动作识别。首先对分类动作 序列进行分段,每段动作序列中运动较剧烈的关节选择分配更高权重,其余关节平均分配权重; 然后提取特征向量,计算两段动作序列的DTW 距离;最后采用K 近邻方法进行动作识别。实验 结果表明,该算法的总体分类识别准确率较高,且对于较相似的动作也能获得较好的识别结果。     

Subjective estimates of times for assembly work

Research by Chan and Hoffmann (2013, 2016) showed that people can estimate task times with reasonable accuracy. That work included experiments on Fitts’ task, a double component movement task, pin-to-hole assembly and ballistic movement tasks. In each case, a linear relationship was found relating subjective estimates of task time and actual task times. In this research, the work has been extended to two industrial assembly tasks: assembly of a U-bolt from components and the more complex task of assembling a hacksaw. These tasks were done in an ergonomically designed work space, with components placed within the Normal Work Area and using jigs for convenience of using two-handed assembly. Actual and estimated component times were obtained from video and voice recordings. Results showed that estimated times were lower than actual assembly times, but higher than times predicted using the MODAPTS predetermined motion time system. Participants appeared to have most difficulty estimating times for task components involving fine manipulation, such as inserting and tightening screws.     

A maintenance time estimation method based on virtual simulation and improved modular arrangement of predetermined time standards

In the early stage of product design, it is important for maintainability design to evaluate accurate and efficient maintenance time by using the virtual simulation technology. However, the difference between the virtual world and reality results in inaccurate estimation of the maintenance time. Besides, few characteristics of the maintenance tasks and actions are considered, leading to a large estimation error. To solve these problems, this paper presents a maintenance time estimation methodology considering the maintenance action elements (MAEs) and modular arrangement of predetermined time standards (MODAPTS) based on the virtual simulation. To consider fully the features of the maintenance operations, a MAE system is designed and integrated with the MODAPTS to decompose the maintenance task into different basic units for the preliminary time estimation. Meanwhile, to bridge the gap caused by the virtual environment, the association relationship of the MAEs and maintainability is analysed to compensate the extra time spent in the interaction among the humans, machines and environment. Through a case study of an auxiliary power unit starter of a Boeing 737, the proposed method is validated to be capable to describe the difficulty in the practical maintenance process and perform an accurate, efficient and stable maintenance time prediction.     

基于声发射技术的绝缘子在线监测对比

为了深入了解声发射技术在绝缘子在线监测方面的应用,在充分了解声发射检测技术原理的基础上采用声发射技术对陶瓷绝缘子和复合绝缘子的污秽放电进行了对比研究。实验结果表明：两种绝缘子虽然实验电压存在高低差异,但在不同污秽度和实验电压下的污秽放电发出的声信号具有基本相同的特性,进一步证明了声发射技术在绝缘子污秽放电中是可行的。另外,在污秽实验中提取实际的声发射信号的特征量,采用模糊推理方法对实际数据进行处理,结果表明模糊推理可以正确判断污秽放电的强弱以及它对绝缘子的威胁程度。     

基于多源信息融合的手势智能交互系统

利用表面肌电信号（surface ElectroMyoGraphy， sEMG）设计了一个提高分类准确性和快速性的识别系统，用于捕获手势动作并进行人机交互.首先，基于无线肌电测量系统和飞行器自主搭建了智能交互平台；接着，采用滑动时间窗的方法对原始sEMG信号设计短时能量阈值进行信号活动段始末点的确定，从而抑制了动作刚执行时趋势段对识别结果的影响；然后，利用时域统计分析对sEMG信号进行特征分析，并提出了一种融合加速度特征信息和sEMG信号的方法来建立5种手势的分类模型.与仅使用sEMG信息源的方式相比，此方法提高了识别准确率.最后，手势控制飞行器运动的实验证明了本方法的可行性和有效性.