Intelligent 6G Wireless Network with Multi-Dimensional Information Perception

Intelligence and perception are two operative technologies in 6G scenarios.The intelligent wireless network and information perception require a deep fusion of artificial intelligence(AI)and wireless communications in 6G systems.Therefore,fusion is becoming a typical feature and key challenge of 6G wireless communication systems.In this paper,we focus on the critical issues and propose three application scenarios in 6G wireless systems.Specifically,we first discuss the fusion of AI and 6G networks for the enhancement of 5G-advanced technology and future wireless communication systems.Then,we introduce the wireless AI technology architecture with 6G multidimensional information perception,which includes the physical layer technology of multi-dimensional feature information perception,full spectrum fusion technology,and intelligent wireless resource management.The discussion of key technologies for intelligent 6G wireless network networks is expected to provide a guideline for future research.

A Privacy-Preserving Federated Learning Algorithm for Intelligent Inspection in Pumped Storage Power Station

As a distributed machine learning architecture,Federated Learning(FL)can train a global model by exchanging users’model parameters without their local data.However,with the evolution of eavesdropping techniques,attackers can infer information related to users’local data with the intercepted model parameters,resulting in privacy leakage and hindering the application of FL in smart factories.To meet the privacy protection needs of the intelligent inspection task in pumped storage power stations,in this paper we propose a novel privacy-preserving FL algorithm based on multi-key Fully Homomorphic Encryption(FHE),called MFHE-PPFL.Specifically,to reduce communication costs caused by deploying the FHE algorithm,we propose a self-adaptive threshold-based model parameter compression(SATMPC)method.It can reduce the amount of encrypted data with an adaptive thresholds-enabled user selection mechanism that only enables eligible devices to communicate with the FL server.Moreover,to protect model parameter privacy during transmission,we develop a secret sharing-based multi-key RNS-CKKS(SSMR)method that encrypts the device’s uploaded parameter increments and supports decryption in device dropout scenarios.Security analyses and simulation results show that our algorithm can prevent four typical threat models and outperforms the state-of-the-art in communication costs with guaranteed accuracy.

Application of Mobile Intelligent Inspection System in Substation Equipment Management

Intelligent inspection is more and more widely applied in all walks of life. This paper introduces the application of the intelligent inspection system in substation equipment management based on mobile phone terminal. It can make the power supply enterprise have more effective means to ensure the safe operation of equipment, improve equipment management level, and improve the economic benefits of power supply.

Intelligent Camera for Surface Defect Inspection

An intelligent camera for surface defect inspection is presented which can pre-process the surface image of a rolled strip and pick defective areas out at a spead of 1 600 meters per minute. The camera is made up of a high speed line CCD, a 60 Mb/s CCD digitizer with correlated double sampling function, and a field programmable gate array(FPGA), which can quickly distinguish defective areas using a perceptron embedded in FPGA thus the data to be further processed would dramatically be reduced. Some experiments show that the camera can meet high producing speed, and reduce cost and complexity of automation surface inspection systems.

Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring

Computer vision techniques, in conjunction with acquisition through remote cameras and unmanned aerial vehicles (UAVs), offer promising non-contact solutions to civil infrastructure condition assessment. The ultimate goal of such a system is to automatically and robustly convert the image or video data into actionable information. This paper provides an overview of recent advances in computer vision techniques as they apply to the problem of civil infrastructure condition assessment. In particular, relevant research in the fields of computer vision, machine learning, and structural engineering is presented. The work reviewed is classified into two types: inspection applications and monitoring applications. The inspection applications reviewed include identifying context such as structural components, characterizing local and global visible damage, and detecting changes from a reference image. The monitoring applications discussed include static measurement of strain and displacement, as well as dynamic measurement of displacement for modal analysis. Subsequently, some of the key challenges that persist toward the goal of automated vision-based civil infrastructure and monitoring are presented. The paper concludes with ongoing work aimed at addressing some of these stated challenges.

The Design of VLC-PLC System for Substation Inspection

A kind of integrated network architecture visible light communication (VLC) and power line communication (PLC) is put forward. This architecture is low cost and easy to implement which overcomes the shortcoming of the traditional network architecture. Furthermore, the VLC-PLC integration technology is applied to typical power grid business scene, which is substation intelligent inspection. The business process of master station platform is analyzed. During the intelligent inspection, the VLC-PLC system provides voice communication for on-site inspection personnel and management personnel, and position service. The system can ensure the safety and security of power production.

Accurately Measuring Inspection Time with Computers

Accurately measuring inspection time (IT) with computers requires several considerations. They are: 1) Screen redraw period;2) Synchronous and timely image presentation;3) Stimulus duration timing;4) Image scale invariance;5) Stan dardized presentation format (of which image scale invariance is a part). The first consideration dictates a minimum duration available for measuring IT. The second and third are necessary for accurate stimulus duration. The fourth is necessary to provide scale invariant images, that is, images with the same visual angle at a given viewing distance on any computer. And the fifth ensures that participants everywhere respond to the same task. Our computer program em bodies these elements and we make it freely available to any interested party. Data to establish validity and reliability are presented, and normative data on 2518 participants aged 6 to 92 years are available.

Multi-dimensional and Multi-threshold Airframe Damage Region Division Method Based on Correlation Optimization

In order to obtain the image of airframe damage region and provide the input data for aircraft intelligent maintenance,a multi-dimensional and multi-threshold airframe damage region division method based on correlation optimization is proposed.On the basis of airframe damage feature analysis,the multi-dimensional feature entropy is defined to realize the full fusion of multiple feature information of the image,and the division method is extended to multi-threshold to refine the damage division and reduce the impact of the damage adjacent region’s morphological changes on the division.Through the correlation parameter optimization algorithm,the problem of low efficiency of multi-dimensional multi-threshold division method is solved.Finally,the proposed method is compared and verified by instances of airframe damage image.The results show that compared with the traditional threshold division method,the damage region divided by the proposed method is complete and accurate,and the boundary is clear and coherent,which can effectively reduce the interference of many factors such as uneven luminance,chromaticity deviation,dirt attachment,image compression,and so on.The correlation optimization algorithm has high efficiency and stable convergence,and can meet the requirements of aircraft intelligent maintenance.

Design of Low-power Inspection Instrument Based on RF Technology

A design for low power consumption inspection instrument, in which the ATMega32L is used as the control core, is presented. The reader with wireless identification based on RF technology is researched and the low-cost power is studied particularly. This instrument can be used in industry fields to measure temperature, humidity, gas concentration and other specifications, so it has wide applications and is worth to be extended.

The Development of a Smart Mobile App for Building Façade Defects Inspections

The manual visual inspections of façade building defects are posing a high and increasing cost for building asset managers,particularly when inspections delay projects or require asset outages,visits to decommissioned sites or work within hazardous environments.This paper reports on the development,testing and delivery of a working mobile app prototype to facilitate the inspections and documentation of building facade condition monitoring.The work presented builds upon the development of an online platform for remote building inspection based on the integration of methodologies and tools,including VR(virtual reality),and digital photogrammetry to collect real-time data that support automated decision making.The mobile app:(i)allows the user to import 3D models and 2D building plans;(ii)provides the means of first-person exploration of models via a VR headset;and(iii)captures,records and catalogues images of façade defect types,and the date and time.An inspection case study was used to demonstrate and evaluate the mobile app prototype.The Building Inspector app allows building professionals to manage inspections and to track past and ongoing monitoring of the condition of building façades.

电力巡检机器人路径规划方法综述

随着电力系统规模和复杂性的不断增加,传统的人工巡检方式已很难满足当下电力巡检要求。巡检机器人因具有安全性、可靠性和智能性已被逐步应用到电力巡检中。机器人在运行过程中通过提前预测、自主决策或智能导航的方式完成全局遍历与避障。电力巡检的核心任务是规划出一条安全且最优的运行轨迹。系统地分析和梳理了巡检机器人巡检过程中的各类方法;阐述了在变电站和输电线路等不同场景中算法的应用;综述了各类路径规划算法的研究现状和改进方法。在此基础上,对未来电力巡检机器人路径规划的研究和发展方向做出了展望。

迈向智能监察:人工智能赋能国家监察的逻辑与进路

新一代人工智能的兴起为国家治理注入新动能,为国家监察工作的数字化、智能化指明方向。人工智能赋能国家监察具有以“数据全覆盖”实现“监察全覆盖”、从人力监督到智能监督等现实价值。受限于国家监察的初创性与人工智能的局限性,国家监察智能化呈现阶段性特征。国家监察的智能化发展围绕数据、算法、算力三大核心要素,实现监察“块数据”构建、面向国家监察的语言模型嵌入及算力资源的优化供给。针对人工智能存在的数据隐私、数据安全等技术性风险,可从人工智能政府采购的制度化与规范化、建构监察对象数据隐私与安全保护机制和人工智能监察应用的纠错与救济机制等方面予以防范和化解。

桁架式机器人视觉巡检系统设计

针对当前智能制造装备存在传感器监测盲区且人工点检效率低、易出错的现状,设计一套桁架式移动机器人视觉巡检系统,实现自动监测生产线设备上电气、机械关键部位易松动易错位等问题。该系统安装在生产线上方,具有可达范围广、无拍照死角、适用场景广和不影响生产线设备动作等优点,解决传统地面移动巡检机器人占用生产线空间、拍照角度受限、无法进入复杂生产线内部点检等缺点。在智能制造技术升级的背景下,该系统具有较高的实用价值及推广意义。

数字孪生水利工程建设动态智能监测系统研发与应用

依托大型水利枢纽工程建设,结合项目进度、质量、安全等管理要求,提出数字孪生水利工程动态智能监测系统研发思路。通过研究水下定位和水陆一体化定位,建立水下机器人与无人机智能巡检的统一定位体系;研究海量影像数据存储管理,研究图像识别和机器学习技术自动找出异常点,从而实现施工现场的智慧监控等关键技术。建成集空、天、地、水一体化的监控系统,对各项感知信息进行融合集成和综合利用,对不同时期的数据进行比较分析;建立大数据平台,为大型水利工程设计、工程移民、水土保持、施工安全与质量管理、工程形象展示、水下建筑物安全监测等方面的数字孪生水利工程建设和动态监测提供技术支持,实现大型水利枢纽工程建设过程的智能巡检、智能监测和科学监管。

基于改进YOLOv5算法的无人机巡检图像智能识别方法

提出一种基于改进YOLOv5算法的无人机巡检图像智能识别方法。该方法构建无人机巡检图像的相邻图像独立坐标系,并利用相对定向法确定图像中共同目标的位置关系。将巡检目标统一转换至同一坐标系下,采用先进的分割技术提取目标纹理特征向量,为后续的图像识别提供了有力支持。在改进YOLOv5算法的过程中,特别注重多尺度网络的选择与融合激活函数及损失函数的优化组合。采用大疆无人机获取建筑裂缝巡检图像进行实验。结果表明,该方法能够在高效率下实现不同类型建筑裂缝的高精度识别,展现出优异的稳定性能。这一研究成果为无人机巡检图像的智能识别提供了新的思路和方法,具有广泛的应用前景和实际价值。

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。

智能机器人在大港油田西二联站库巡检中的应用与实践

长期以来,油田站库主要以传统人工运维方式进行管理,该种管理方式暴露出巡检效率低下、巡检工作不到位及生产管理落后等问题,造成站库安全隐患不能及时发现并处置。为了进一步优化站库巡检制度、简化工作流程,在大港油田西二联站库搭建了站库智能机器人巡检系统,该系统代替了传统系统工作效率低、成本高、效果差的人工巡检模式。智能机器人巡检系统的应用降低了员工劳动强度、提升了站库工作效率、保障了站库安全生产,有效地提高了油田安全生产的管理水平,为油田智能化生产管理开辟了新的技术路线。

基于数字孪生的套筒智能检测生产线虚拟调试技术

针对套筒智能检测生产线调试过程中存在调试周期长、试错成本高等问题,设计了基于数字孪生(DT)和虚拟调试(VC)技术,构建了套筒智能检测生产线VC系统。基于DT五维模型的套筒智能检测生产线和VC系统结构模型,明确套筒智能检测生产线的工作原理;阐述VC系统中智能检测生产线的数字空间搭建、控制系统设计、数据同步和交互、实时状态监测、故障模拟与恢复等关键技术。通过实验,证明了该方法的可行性与有效性,并为智能检测生产线的设计提供了参考。

基于微型激光雷达的无人机智能化电力线路巡检技术研究

介绍了一种利用激光探测和测距(LiDAR)进行实时电力线检测的算法,并且对微型激光雷达无人机进行电力线路巡检抽象建模。通过使用平面分析法对巡检现场进行距离的比较来分割点云,并提取一组电力线候选点,这些点被拟合到线段上,线段根据它们的共线性质进一步分组比较。该方法可利用图像的共线特性完成特征检验,并在光线条件差以及线路背景复杂的环境下仍可获得较为可靠的巡检结果。案例中电力线路垂直平均误差最大为0.49 m,其他所有直线的估计平均误差都小于0.07 m,水平拟合时,所有平均误差都在0.14 m以内。验证了所提出基于微型激光雷达的无人机技术进行电力线路智能化巡检方法的有效性与可行性。

数字孪生技术在地铁场段列检车间智能管控平台中的研究与应用

地铁场段列检车间智能化管控水平决定车辆基地高效运转的程度。以BIM+数字孪生技术为基础,建立了列检车间数字孪生体系,搭建了车间智能管控平台,分析了智能列检车间关键技术,构建了管控平台的硬件系统、静态模型和软件平台。某地铁场段列检车间数字孪生典型应用实践证明,该平台能有效整合车间内所有生产要素,基于车间动态、安全预警、作业回溯、安全教育等为生产运维和安全管控快速提供决策。