Hand-eye-vision based control for an inspection robot's autonomous line grasping

In order to ensure that the off-line arm of a two-arm-wheel combined inspection robot can reliably grasp the line in case of autonomous obstacle crossing,a control method is proposed for line grasping based on hand-eye visual servo.On the basis of the transmission line's geometrical characteristics and the camera's imaging principle,a line recognition and extraction method based on structure constraint is designed.The line's intercept and inclination are defined in an imaging space to represent the robot's change of pose and a law governing the pose decoupling servo control is developed.Under the integrated consideration of the influence of light intensity and background change,noise(from the camera itself and electromagnetic field)as well as the robot's kinetic inertia on the robot's imaging quality in the course of motion and the grasping control precision,a servo controller for grasping the line of the robot's off-line arm is designed with the method of fuzzy control.An experiment is conducted on a 1:1 simulation line using an inspection robot and the robot is put into on-line operation on a real overhead transmission line,where the robot can grasp the line within 18 s in the case of autonomous obstacle-crossing.The robot's autonomous line-grasping function is realized without manual intervention and the robot can grasp the line in a precise,reliable and efficient manner,thus the need of actual operation can be satisfied.

High Precision Ultrasonic Guided Wave Technique for Inspection of Power Transmission Line

Due to the merits of high inspection speed and long detecting distance, Ultrasonic Guided Wave（UGW） method has been commonly applied to the on-line maintenance of power transmission line. However, the guided wave propagation in this structure is very complicated, leading to the unfavorable defect localization accuracy. Aiming at this situation, a high precision UGW technique for inspection of local surface defect in power transmission line is proposed. The technique is realized by adopting a novel segmental piezoelectric ring transducer and transducer mounting scheme, combining with the comprehensive characterization of wave propagation and circumferential defect positioning with multiple piezoelectric elements. Firstly, the propagation path of guided waves in the multi-wires of transmission line under the proposed technique condition is investigated experimentally. Next, the wave velocities are calculated by dispersion curves and experiment test respectively, and from comparing of the two results, the guided wave mode propagated in transmission line is confirmed to be F（1,1） mode. Finally, the axial and circumferential positioning of local defective wires in transmission line are both achieved, by using multiple piezoelectric elements to surround the stands and send elastic waves into every single wire. The proposed research can play a role of guiding the development of highly effective UGW method and detecting system for multi-wire transmission line.

Dynamic Balance Control Based on an Adaptive Gain-scheduled Backstepping Scheme for Power-line Inspection Robots

This paper presents an adaptive gain-scheduled backstepping control(AGSBC) scheme for the balance control of an underactuated mechanical power-line inspection(PLI) robotic system with two degrees of freedom and a single control input.First, a nonlinear dynamic model of the balance adjustment process of the PLI robot is constructed, and then the model is linearized at a nominal equilibrium point to overcome the computational infeasibility of the conventional backstepping technique. Second, to solve generalized stabilization control issue for underactuated systems with multiple equilibrium points,an equilibrium manifold linearized model is developed using a scheduling variable, and then a gain-scheduled backstepping control(GSBC) scheme for expanding the operational area of the controlled system is constructed. Finally, an adaptive mechanism is proposed to counteract the impact of external disturbances. The robust stability of the closed-loop system is ensured by Lyapunov theorem. Simulation results demonstrate the effectiveness and high performance of the proposed scheme compared with other control schemes.

Online application of automatic surface quality inspection system to finishing line of cold rolled strips

An automatic surface quality inspection system installed on a finishing lineof cold rolled strips is introduced. The system is able to detect surface defects on cold rolledstrips, such as scratches, coil breaks, rusts, roll imprints, and so on. Multiple CCD area scancameras were equipped to capture images of strip surface simultaneously. Defects were detectedthrough 'Dark-field illumination' which is generated by LED illuminators. Parallel computationtechnique and fast processing algorithms were developed for real-time data processing. Theapplication to the production line shows that the system is able to detect defects effectively.

Impacts of flexible obstructive working environment on dynamic performances of inspection robot for power transmission line

The rigid-flexible coupling dynamic modeling and simulation of an inspection robot were conducted to study the influences of the flexible obstructive working environment i.e. overhead transmission line on the robot＇s dynamic performance. First, considering the structure of the obstacles and symmetrical mechanism of the robot prototype, four basic subactions were abstracted to fulfill full-path kinematic tasks. Then, a multi-rigid-body dynamic model of the robot was built with Lagrange equation, whil^e a multi-flexible-body dynamic model of a span of lin~ was obtained by combining finite element method （FEM）, modal synthesis method and Lagrange equation. The two subsystem models were coupled under rolling along no-obstacle segment and overcoming obstacle poses, and these simulations of three subactions along different spans of line were performed in ADMAS. The simulation results, including the coupling vibration parameters and driving moment of joint motors, show the dynamic performances of the robot along ftexibile obstructive working path： in flexible obstructive working environment, the robot can fulfill the preset motion goals; it responses slower in more flexible path; the fluctuation of robot as well as driving moment of the corresponding joint in startup and brake region is greater than that in rigid environment; the fluctuation amplitude increases with increasing working environment flexibility.

Automated deep learning system for power line inspection image analysis and processing: architecture and design issues

The continuous growth in the scale of unmanned aerial vehicle (UAV) applications in transmission line inspection has resulted in a corresponding increase in the demand for UAV inspection image processing. Owing to its excellent performance in computer vision, deep learning has been applied to UAV inspection image processing tasks such as power line identification and insulator defect detection. Despite their excellent performance, electric power UAV inspection image processing models based on deep learning face several problems such as a small application scope, the need for constant retraining and optimization, and high R&D monetary and time costs due to the black-box and scene data-driven characteristics of deep learning. In this study, an automated deep learning system for electric power UAV inspection image analysis and processing is proposed as a solution to the aforementioned problems. This system design is based on the three critical design principles of generalizability, extensibility, and automation. Pre-trained models, fine-tuning (downstream task adaptation), and automated machine learning, which are closely related to these design principles, are reviewed. In addition, an automated deep learning system architecture for electric power UAV inspection image analysis and processing is presented. A prototype system was constructed and experiments were conducted on the two electric power UAV inspection image analysis and processing tasks of insulator self-detonation and bird nest recognition. The models constructed using the prototype system achieved 91.36% and 86.13% mAP for insulator self-detonation and bird nest recognition, respectively. This demonstrates that the system design concept is reasonable and the system architecture feasible .

Three-axis magnetic flux leakage in-line inspection simulation based on finite-element analysis

With the increase of pipelines, corrosion leakage accidents happen frequently. Therefore, nondestructive testing technology is important for ensuring the safe operation of the pipelines and energy mining. In this paper, the structure and principle of magnetic flux leakage （MFL） in-line inspection system is introduced first. Besides, a mathematic model of the system according to the ampere circuit rule, flux continuity theorem, and column coordinate transform is built, and the magnetic flux density in every point of space is calculated based on the theory of finite element analysis. Then we analyze and design the disposition of measurement section probes and sensors combining both three-axis MFL in-line inspection and multi-sensor fusion technology. Its advantage is that the three-axis changes of magnetic flux leakage field are measured by the multi-probes at the same time, so we can determine various defects accurately. Finally, the theory of finite element analysis is used to build a finite element simulation model, and the relationship between defects and MFL inspection signals is studied. Simulation and experiment results verify that the method not only enhances the detection ability to different types of defects but also improves the precision and reliability of the inspection system.

Prototype Line Crawler for Power Line Inspection

In South Africa, electricity is supplied through thousands-of-kilometers of overhead power cables, which is owned by Eskom the national energy supplier. Currently monitoring of these overhead power cables are done by means of helicopter inspection flights and foot patrols, which are infrequent and expensive. In this paper, the authors present the design of a prototype power line crawler （inspection robot） for the monitoring of these overhead power lines in South Africa. The designed prototype power line crawler is capable of driving on the wire, balancing on the wire and is capable of maneuvering past certain obstacles found on the overhead power cables. The prototype power line crawler is designed to host a monitoring system that monitors the power line as the inspection robot drives on it. Various experimental tests were performed and are presented in this paper, showing the capability of performing these tasks. This prototype inspection robot ensures a platform for future development in this area.

Safety Distance Determination for 500 kV AC Transmission Line’s Helicopter Inspection

As an efficient and advanced line inspection method, helicopter line patrol is gradually more and more used in transmission lines inspection, promoting the elaborate operation of transmission lines and reducing the management cost. However, as a 'floating-potential conductor' near to a high-voltage transmission line, the helicopter would be at a high electric field region;and bring security risk to equipment and operating personnel. In this paper, the electric field strength near the cabin at locations of different distance from transmission lines is investigated by calculation, and the field in the helicopter cabin is also calculated with finite element method (FEM). The result indicates that the potential difference becomes higher with the decrease of the distance between the helicopter and transmission line. Considering the discharge energy and the guarantee of the persons’ safety, the safety distance is determined as d≥15 m.

ON-LINE INSPECTION TECHNIQUES OF MANUFACTURING QUALITY OF ROLLED-STEEL SHEET

On-line measurement of manufaturing quality of rolled steel needs the performances of noncontact, high-responds, high-resolution and high aceuracy. The reccntly developed hardware makes it possible. This paper gives a review of the development of this techniques and introduces four kinds of developed measurement systems. And the future development trends in this field was also discussed.

Prototype Monitoring System for Power Line Inspection by Means of a PandaBoard

The national energy supplier （Eskom in South Africa） supplies electricity through thousands-of-kilometers of overhead power lines. The current methods of inspection of these overhead power lines are infrequent and expensive. In this paper, the authors present the development of a prototype monitoring system for power line inspection in South Africa. The developed prototype monitoring system collects data （information） from the overhead power lines, is remotely accessible and fits into a power line robot. The prototype monitoring system makes use ofa PandaBoard （SBC） with GPS receiver and 5 MP camera to collect data. Hardware fatigue is the biggest problem faced on the overhead power lines and is captured by means of the 5 MP camera and is displayed on a website hosted by the PandaBoard via Wi-Fi. The monitoring system has low power consumption, is light weight, compact and easily collects data. The data obtained from the prototype monitoring system was satisfactory and provides an improved solution for monitoring power lines for Eskom in South Africa.

Inspection and Monitoring Techniques for Power Lines

Structural assessment is prerequisite for proper maintenance of civil infrastructure.In the begining of this paper,modern inspection and monitoring methods are briefly reviewed.Experiences in applying image-based methods for highway bridge inspection are described shortly afterward.Studies are then extended to explore technologies for power delivery infrastructure evaluation.Typical power line components are first introduced. Structural analyses show complicated coupling phenomena in the power line system;and its vulnerability is intensified by extreme environment or human induced events.As a main interest,the state-of-art of power line inspection is summarized.Both visual observations and inspections assisted with novel techniques are presented.Real time monitoring of the power line is also investigated in this paper.Technologies that have potentials for monitoring power cables,insulators,and support structures are identified.A conceptual integrated design is proposed by the authors through combining innovative inspection with promising monitoring methods to ensure a sustainable,smart power line.

EDLine与改进光流法线路异物智能检测

为提高无人机电力故障巡检效率,提出一种结合边缘绘制线(edge drawing line,EDLine)特征提取算法与改进光流法的输电线路异物智能检测方法。鉴于背景纹理对航拍图像的影响,研究一种基于矩阵的线段融合算法以解决EDLine线段检测的断续问题,根据多特征约束提取输电线路区域。为有效识别异物,利用动量因子改进光流算法迭代收敛速度,根据光流信息检测异物故障。对无人机巡检图像的测试结果表明,该方法在复杂背景或异物不明显时均可有效检测出异物。提出检测算法准确度高、鲁棒性强,保证巡检的时效性。

Assembly-Line Health Check up in Digitalized Hospital

The health check up flow of digital hospital can be consulted with the assem bly line of industry factory.Because they have the following same features:highly specialized workstation, closeness and continuance,rhythm,balanced production,continuous production.The essential prerequisites are as the follows:The inspecting item s and methods should be stable;advanced product mix and stable production design;standardized raw m aterial,consumption,procedure, inspection method;there are lots of request for health inspection;the customers move at the least unit;the space arrangement should be reasonable;the time arrangement should be proportion. With the com puter net,the digital inspection can achieves the raw material controlling accurately. The basis of check up line concerns about equipm ent,net and software,data collection,and per- sonnel.The group technology is used in the health inspection flow design of the digital hospital in the field of items custom ers and zone redivided.The digital assembly linem ic health inspect has the following stages:m ember registering,notice,check in,arrange order,tim e control,report,feed- back and analysis. The assem bly linemic has following advantages:increasing the productivity, the space utility,satisfaction of customer,fund returning,lowering the cost and ensuring the quality.

Multi-Equipment Detection Method for Distribution Lines Based on Improved YOLOx-s

The YOLOx-s network does not sufficiently meet the accuracy demand of equipment detection in the autonomous inspection of distribution lines by Unmanned Aerial Vehicle(UAV)due to the complex background of distribution lines,variable morphology of equipment,and large differences in equipment sizes.Therefore,aiming at the difficult detection of power equipment in UAV inspection images,we propose a multi-equipment detection method for inspection of distribution lines based on the YOLOx-s.Based on the YOLOx-s network,we make the following improvements:1)The Receptive Field Block(RFB)module is added after the shallow feature layer of the backbone network to expand the receptive field of the network.2)The Coordinate Attention(CA)module is added to obtain the spatial direction information of the targets and improve the accuracy of target localization.3)After the first fusion of features in the Path Aggregation Network(PANet),the Adaptively Spatial Feature Fusion(ASFF)module is added to achieve efficient re-fusion of multi-scale deep and shallow feature maps by assigning adaptive weight parameters to features at different scales.4)The loss function Binary Cross Entropy(BCE)Loss in YOLOx-s is replaced by Focal Loss to alleviate the difficulty of network convergence caused by the imbalance between positive and negative samples of small-sized targets.The experiments take a private dataset consisting of four types of power equipment:Transformers,Isolators,Drop Fuses,and Lightning Arrestors.On average,the mean Average Precision(mAP)of the proposed method can reach 93.64%,an increase of 3.27%.The experimental results show that the proposed method can better identify multiple types of power equipment of different scales at the same time,which helps to improve the intelligence of UAV autonomous inspection in distribution lines.

基于Skyline的输电线路巡检数据可视化系统研究

随着电力建设的迅速发展,输电线路巡检工作逐步采用无人机开展实施,提高了巡检效率,产生了大量非结构化数据,导致不能快速实现多源海量数据的融合、可视化展示。针对传统电力GIS系统无法对非结构化数据融合、展示不足的问题,笔者提出了一种基于Skyline的输电线路巡检数据三维可视化方法。最后,通过原型系统的实现验证了系统设计既能初步解决非结构化机巡数据统一化管理的问题,又能提供三维可视化环境,消除了非结构化数据可视化的短板,在实际工作中具有重要的意义。

Long Range Unmanned Aircraft System for Power Line nspection of Brazilian Electrical System

Power line inspection is an essential procedure in the power lines maintenance area, especially thinking about service availability and energy efficiency. Aerial inspection of electric power transmission lines is typically performed using human-piloted helicopters, which is a procedure that is both expensive and prone to accidents taking risks to human beings＇ lives. The work presents a solution based on UAS （unmanned aircraft system） for inspecting power lines. In this context a R ＆ D project of an unmanned aircraft system to be used for performing complete aerial inspection of overhead power lines is being executed by ITA （Instituto Tecnol6gico de Aeron^utica） （Technological Institute of Aeronautics） in Brazil. Special attention is dedicated to the communication system conception in order to comply with Remotely Piloted Aircraft System definition in the context of long endurance operations of the system. It presents a solution based on LTA （lighter than air） platform in order to extend the communication range beyond line of sight.

基于图像感知的输电线路智能巡检综述

输电线路是电网建设的重要组成部分,定期巡检对于确保输电线路的稳定运行至关重要。文中围绕输电线路智能巡检需求,首先梳理了输电线路不同的巡检方法,介绍了智能巡检中所需的系统框架设备以及智能算法;重点总结了基于传统图像处理和深度学习的智能巡检方法;其次针对输电线路中存在的各种不同故障总结了相关的智能巡检方法,并且通过评价指标进行了对比分析;最后梳理了研究难点,对基于深度学习方法的输电线路巡检发展趋势进行了展望,所提出和总结的输电线路智能巡检方法具有多方面的指导意义。

基于多重注意力和特征对齐的销钉缺陷检测方法

电网规模的快速扩张对输电线路的检测维护提出更高的要求,智能高效的自动化电力巡检图像识别算法作为提高检测维护的手段,已经成为目前研究的重要方向之一。为实现巡检图像中销钉缺陷目标的准确识别,文章提出一种基于多重注意力和特征对齐的销钉缺陷检测方法。首先,构建基于可变形注意力的可变形检测变压器(deformable detection transformer,Deformable-DETR)框架,解决现有识别算法中无法通过卷积神经网络进行像素点轮廓-环境关系建模的问题;之后,提出区域注意力特征提取模块,解决由可变形注意力带来的特征粒度不足的问题;为丰富目标物体特征质量,提出基于注意力的候选框特征对齐模块和约束函数;最后,选取华中地区某电力公司的航拍图像数据验证算法性能。结果表明,所提算法总体性能相比于现有的卷积算法提升5.4%,总体平均检测精度达到90.5%。

Image Correction Method of Color Line-Scan System

As the development of machine vision technology, the color line-scan system is widely applied in the on-line inspection. Due to the non-uniform gray scale and color distortion of the image acquired by the system, the image correction is needed to reduce the problem of image processing and the stability system. Based on reasons mentioned above, a method that using polynomial fitting to correct the image is presented to solve the problem in this paper. The method has been used in the automatic optical inspection of PCB, and has been proved to be effective. So this method will have a potential application to the development of the color line-scan machine vision system.