Unmanned Aerial Vehicle Inspection Routing and Scheduling for Engineering Management

Technological advancements in unmanned aerial vehicles(UAVs)have revolutionized various industries,enabling the widespread adoption of UAV-based solutions.In engineering management,UAV-based inspection has emerged as a highly efficient method for identifying hidden risks in high-risk construction environments,surpassing traditional inspection techniques.Building on this foundation,this paper delves into the optimization of UAV inspection routing and scheduling,addressing the complexity introduced by factors such as no-fly zones,monitoring-interval time windows,and multiple monitoring rounds.To tackle this challenging problem,we propose a mixed-integer linear programming(MILP)model that optimizes inspection task assignments,monitoring sequence schedules,and charging decisions.The comprehensive consideration of these factors differentiates our problem from conventional vehicle routing problem(VRP),leading to a mathematically intractable model for commercial solvers in the case of large-scale instances.To overcome this limitation,we design a tailored variable neighborhood search(VNS)metaheuristic,customizing the algorithm to efficiently solve our model.Extensive numerical experiments are conducted to validate the efficacy of our proposed algorithm,demonstrating its scalability for both large-scale and real-scale instances.Sensitivity experiments and a case study based on an actual engineering project are also conducted,providing valuable insights for engineering managers to enhance inspection work efficiency.

Analysis of Safety Assessment and Testing of Heavy Traffic Vehicles on Old Bridges Without Data

This article presents a real-life project that aimed to evaluate the safety of traffic vehicles on old bridges without any prior data.The project involved various safety inspections,including conventional,static,and dynamic load inspections and safety assessments.After conducting these tests,it was concluded that the structure of the old bridge is relatively safe,with only a few bumps.The bridge could function normally following appropriate treatment.The analysis provides valuable insights into the assessment of the quality and safety of such bridges to ensure the safe driving of heavy vehicles.

A two-stage optimization method for unmanned aerial vehicle inspection of an oil and gas pipeline network

Oil and gas pipeline networks are a key link in the coordinated development of oil and gas both upstream and downstream.To improve the reliability and safety of the oil and gas pipeline network, inspections are implemented to minimize the risk of leakage, spill and theft, as well as documenting actual incidents. In recent years, unmanned aerial vehicles have been recognized as a promising option for inspection due to their high efficiency. However, the integrated optimization of unmanned aerial vehicle inspection for oil and gas pipeline networks, including physical feasibility, the performance of mission, cooperation, real-time implementation and three-dimensional(3-D) space, is a strategic problem due to its large-scale,complexity as well as the need for efficiency. In this work, a novel mixed-integer nonlinear programming model is proposed that takes into account the constraints of the mission scenario and the safety performance of unmanned aerial vehicles. To minimize the total length of the inspection path, the model is solved by a two-stage solution method. Finally, a virtual pipeline network and a practical pipeline network are set as two examples to demonstrate the performance of the optimization schemes. Moreover, compared with the traditional genetic algorithm and simulated annealing algorithm, the self-adaptive genetic simulated annealing algorithm proposed in this paper provides strong stability.

Design of motion control of dam safety inspection underwater vehicle

Plenty of dams in China are in danger while there are few effective methods for underwater dam inspections of hidden problems such as conduits,cracks and inanitions.The dam safety inspection remotely operated vehicle(DSIROV) is designed to solve these problems which can be equipped with many advanced sensors such as acoustical,optical and electrical sensors for underwater dam inspection.A least-square parameter estimation method is utilized to estimate the hydrodynamic coefficients of DSIROV,and a four degree-of-freedom(DOF) simulation system is constructed.The architecture of DSIROV's motion control system is introduced,which includes hardware and software structures.The hardware based on PC104 BUS,uses AMD ELAN520 as the controller's embedded CPU and all control modules work in VxWorks real-time operating system.Information flow of the motion system of DSIROV,automatic control of dam scanning and dead-reckoning algorithm for navigation are also discussed.The reliability of DSIROV's control system can be verified and the control system can fulfill the motion control mission because embankment checking can be demonstrated by the lake trials.

Wireless Transmission System for Vehicle Inspection Data

Based on general packet radio service(GPRS) and TCP/IP protocol,a wireless transmission system of vehicle inspection data is designed. Basic structure and work theory are expounded. SIM300 designed by SIMCOM is used for client GPRS communication module. Using Winsock control of visual basic(VB),the client and server communication has been accomplished. By means of a client and server communications software,the remote wireless transmission of vehicle inspection data has been accomplished also. The server management software has been developed by using Microsoft SQL Server 2000 and VB6.0. Functions of software include import,inquiry,export and maintenance of test data.

Manipulator-based autonomous inspections at road checkpoints:Application of faster YOLO for detecting large objects

With the increasing number of vehicles,manual security inspections are becoming more laborious at road checkpoints.To address it,a specialized Road Checkpoints Robot(RCRo)system is proposed,incorporated with enhanced You Only Look Once(YOLO)and a 6-degree-of-freedom(DOF)manipulator,for autonomous identity verification and vehicle inspection.The modified YOLO is characterized by large objects’sensitivity and faster detection speed,named“LF-YOLO”.The better sensitivity of large objects and the faster detection speed are achieved by means of the Dense module-based backbone network connecting two-scale detecting network,for object detection tasks,along with optimized anchor boxes and improved loss function.During the manipulator motion,Octree-aided motion control scheme is adopted for collision-free motion through Robot Operating System(ROS).The proposed LF-YOLO which utilizes continuous optimization strategy and residual technique provides a promising detector design,which has been found to be more effective during actual object detection,in terms of decreased average detection time by 68.25%and 60.60%,and increased average Intersection over Union(Io U)by 20.74%and6.79%compared to YOLOv3 and YOLOv4 through experiments.The comprehensive functional tests of RCRo system demonstrate the feasibility and competency of the multiple unmanned inspections in practice.

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。

基于改进PSO的无人机精细化自主巡检航迹布设优化

提出基于改进PSO的无人机精细化自主巡检航迹布设优化。结合波束法测量地面像控点坐标,通过结构矩阵描述平面误差细化值,完成像控点的布设。采用改进PSO算法计算航迹子路径的变更代价,得到新的路径点,由此实现无人机精细化自主巡检航迹布设优化。实验结果表明,所提方法的无人机精细化自主巡检航迹布设时间仅为39.4 min,说明所提方法能够有效提高无人机精细化自主巡检航迹布设效率,精细化自主巡检航迹布设优化效果更好。

基于无人机巡检与深度学习的河道整治施工进度图像识别

长线性小流域治理工程中的河道衬砌、生态护岸等距离长、范围广、布置分散,且工区交通不便,人工巡检费时费力,难以及时掌握工程的整体施工进度形象面貌。提出了基于无人机巡检与深度学习的河道整治施工进度智能图像识别方法,通过定位施工节点(施工区域起点和终点)的位置计算施工进度。首先,建立了施工区域目标检测模型,针对无人机航拍影像进行河道衬砌护岸施工区域的识别以及施工节点的定位;然后,利用尺度不变特征变换(scale-invariant feature transform,SIFT)算法对不同视频帧中的施工节点进行匹配,并基于单目视觉的运动视差法,计算施工节点的实际工区坐标;最后,计算当前衬砌护岸施工进度,并分析进度偏差。结果表明:该方法得到的施工节点定位平均误差为1.026 m,平均相对误差为0.74%,该方法能够较为准确地从航拍图像中识别得到当前衬砌护岸的施工进程,从而实现长线性工区快速巡检,及时掌控现场施工进度,提高工程管理的智能化水平。

基于连续可微采样的无人机多向视点规划

无人机在各种工业基础设施的自主巡检中,需要为大型复杂待巡检对象设计大量的数据采集航点,以获取高质量的全覆盖影像数据。逐点飞行作业能耗高采集效率低,限制了无人机大规模的工业应用。为了优化飞行作业模式,有效提升巡检效率,针对已知待巡检复杂设备结构提出一种全新的多向视点规划算法——连续可微采样的无人机多向视点规划算法(MD-VPP)。该方法在满足全面覆盖巡视目标以及数据采集质量要求的前提下,大幅减少航点数量。首先,将云台俯仰角、偏航角和相机成像面积作为约束条件,构建视点采集连续可微的视图质量目标函数,优化求解候选视点集;然后利用贪心算法求解全覆盖待巡检对象的航点位姿。通过实验对比分析了针对不同巡检对象的航点数量和航点数减少率,相比领域内其他优秀方法,所提方法在确保全覆盖的前提下航点数量至少降低77%,极大地提升了无人机单次作业的数据采集效率。

基于视觉检测的智能桥梁检查车设计与分析

针对公路变截面梁的特点,提出了一种基于视觉检测的智能检查车。该智能检查车由车体平台和视觉检测平台组成,既能无人智能快速检测,又能人工定点维修,有效地提高了桥梁养护效率及检查工作的安全性。介绍了车体平台的具体结构设计和视觉检测平台的具体组成,并对智能检测和人工检查做了对比试验分析,结果表明智能检测比人工检查具有更好的病害检测完整性和更高的检测效率。

船舶检验水下机器人结构设计与仿真

针对传统人工检验船舶水下部分工作中,存在的低效率和安全隐患等问题,结合船舶检验应用场景和水下机器人技术,研究设计一种船舶检验水下机器人,用其代替工作人员进行船舶水下检测。对该船舶检验水下机器人采用框架式结构设计,极大地提升其抗水流能力;设计导管螺旋桨作为推进结构,提高其水下作业的灵敏度。对该机器人结构进行流体仿真,仿真结果显示其在水下运行时所受阻力较小,灵敏度较高。试验结果表明:该机器人能在船舶航行之前对船舶水下部分进行外观检测,不仅能降低船舶检验的难度,而且能提高船舶检验效率。

改进CBBA算法的风电场无人机群巡检任务分配

提出一种基于改进的共识捆绑算法(CBBA)的多无人机风电场巡检任务分配方法。首先,根据风电机组基础信息,采用K-均值算法确定无人机数量和安放位置,并构建风电机组巡检价值评估函数,更为合理地评估各风电机组的巡检收益;然后,针对无人机的归巢返程问题,提出一种基于CBBA算法的任务包双向构建策略;最后,为克服传统CBBA算法中存在的因个体“贪婪”导致的整体效益下降问题,设计一种基于类别的奖励制度,以提高任务分配的合理性。试验表明,所提方法可根据风速、风向的变化制定相应的巡检任务分配方案,可为无人机群自主巡检风电场的任务分配提供可参考的方案。

基于YOLOv8目标检测模型的工地车辆清洁度识别

为缓解建筑工地车辆未经过清洗离开工地带来的城市道路污染和卫生问题,采用计算机视觉领域的目标检测方法即YOLOv8技术设计了一种车辆清洁度检测算法。该算法首先根据工地实际视频数据构建目标检测标签与清洁度标签,然后利用构建好的工地车辆清洗数据集训练YOLOv8目标检测模型,接着调用该模型用于实时检测目标车辆与清洗装置出水情况,最后根据检测效果实时计算最终清洗状况。针对清洗装置有时喷水面积较小的情况,在网络架构中额外引入一个专门用于小尺寸目标的检测层,并采用Focus层技术对输入图像执行分块处理,验证指标包括精确率、召回率、平均精度均值、帧率和清洁度(平均交并比)。结果显示该算法对车辆清洗情况的判断准确率达97.6%,表明所提出的改进模型很好地解决了工地车辆清洁度识别问题。

带上盖开发地铁车辆基地运用检修库房净空高度设计

[目的]城市轨道交通车辆基地的上盖物业开发已成为上海、北京等诸多城市的车辆基地设计基本要求,为了有效解决上盖物业开发对盖下库房的影响,需对运用检修库房的净空高度进行研究。[方法]以车辆基地的运用库和联合车库作为研究对象,分析上盖开发车辆基地库房净空高度的主要影响因素,梳理运用检修库房净空高度设计流程;提出架空接触网制式和接触轨制式下的库房净空计算方法。[结果及结论]采用接触网制式时,需考虑接触网导线高度及安全距离、起重机走行轨轨顶标高及起重机高度、架空管线层高度、结构主梁高度等因素,停车列检库首层盖板的最小高度为7.5 m;检修库(除停车列检库、临修库外)首层盖板高度统一为8.5 m;临修库首层盖板的最小高度为13.5 m。采用接触轨制式时,影响因素除接触网导线高度外,其余均与接触网制式一致,停车列检库、周月检库房首层盖板高度分别为7.5 m和8.5 m。

基于构架运动状态的轨道几何形位检测方法研究与应用

轨道几何状态检测对保证行车安全至关重要,列车上搭载检测系统检测线路,成本低且及时高效,但多采用基于加速度的惯性基准法解算轨道几何形位,适用于轨道质量较好线路,不适用于线形复杂、基础设施差的重载铁路.提出一种基于构架运动状态的轨道几何形位检测方法,利用构架姿态角及位移解算轨道几何形位.基于该方法研制了搭载式轨道动态检查仪,设备结构简单且成本低.在某重载铁路试验,系统运行稳定,解算结果经重复性分析并与轨检车检测结果对比,检测结果可靠且满足线路日常巡检需要.

双向多尺度特征融合的高效遥感图像车辆检测

针对遥感图像中车辆检测面临的背景复杂、多尺度差异和小目标难以检测等挑战,提出了一种基于双向多尺度特征融合的检测方法GEM_YOLO。该方法包括三个主要部分:设计了全局高效注意力模块作为特征提取器,实现轻量化和高效率的特征提取,以解决复杂背景下的目标检测问题;提出了双向多尺度特征融合网络作为特征融合器,采用自顶向下和自底向上的特征融合策略,有效促进不同层次特征之间的信息交互;应用基于注意力的动态检测头作为预测器,增强了对不同尺度、空间位置和任务的感知,进一步提升了目标检测的精度和鲁棒性。在公开数据集DIOR和DOTA上进行相关实验,该方法的平均精度均值达到92.4%和81.4%,显著优于其他主流检测方法,同时具有更少的参数量和计算量,为遥感图像检测领域中的车辆检测提供了一种高效解决方案。

基于卷积神经网络的红外弱小车辆目标检测方法

传统方法无法获得理想的红外弱小车辆目标检测结果,导致检测误差大,无法满足实际应用要求,为了解决传统红外弱小车辆目标检测方法存在的局限性,及时检测红外图像中的弱小车辆,提高车辆检测精度,设计了基于卷积神经网络的红外弱小车辆目标检测方法。首先对弱小车辆目标检测需要的红外图像进行采集,并对红外图像噪声进行处理,消除噪声对弱小车辆目标检测的干扰,然后采用卷积神经网络建立弱小车辆目标检测模型,最后通过具体仿真实验测试弱小车辆目标检测方法的性能。结果表明,该方法的弱小车辆目标检测精度超过了90%,大幅度减少了弱小车辆目标的误检率,同时弱小车辆目标检测时间控制在5 s内,可以满足弱小车辆目标检测的实时性要求,具有较高的实际应用价值。

面向海底管道巡检的AUV三维自适应路径跟踪

针对面向海底管道巡检任务的欠驱动自主水下航行器(AUV)三维路径跟踪控制问题进行研究。首先,在固定坐标系和机体坐标系下建立AUV的运动学模型,为设计适宜运动控制的三维路径跟踪控制器,建立流体坐标系,并在Serret-Frenet坐标系下建立AUV的路径跟踪误差模型;其次,将可变前视距离引入传统视线(LOS)制导策略,提出一种自适应LOS制导策略以提高制导精度,并基于此设计面向海底管道巡检的AUV三维路径跟踪控制器,使得AUV可有效跟踪设定的参数化路径;最后,基于李雅普诺夫稳定性理论证明了闭环系统的稳定性。仿真结果验证了所提面向海底管道巡检的三维路径跟踪控制器的有效性。研究成果能够改善AUV的操纵性,可为面向海底管道巡检的无人水下航行器路径跟踪控制方法提供参考。

基于YOLOv5s改进的无人机航拍图像车辆检测模型

针对无人机航拍图像车辆检测任务中存在车辆遮挡严重、小尺度目标多、背景信息复杂、误检漏检情况严重等问题,提出一种基于YOLOv5改进的车辆目标检测模型。首先,增加一个小目标特征检测层,增强对浅层特征图中有效位置特征信息的复提取,从而缓解因深层卷积导致密集小目标特征信息的缺失问题。其次,在Neck中使用GSConv卷积和VOVGSCSP模块,对模型进行轻量化同时提高检测精度。再次,使用Mish作为全局激活函数,提高特征信息在深层网络中的传播和表达能力。然后,为了模型对检测目标的定位精度,使用EIoU作为回归框定位损失。最后,在Backbone中引入Transformer模块,增强模型感受野,提高对关键点信息的提取能力,增强模型抗干扰能力。实验结果表明,最终改进模型的平均检测精度(mAP)达到了83.8%,比原始YOLOv5s模型提高了5.5%,对小目标检测精度明显得到提升。