SDH-FCOS:An Efficient Neural Network for Defect Detection in Urban Underground Pipelines

Urban underground pipelines are an important infrastructure in cities,and timely investigation of problems in underground pipelines can help ensure the normal operation of cities.Owing to the growing demand for defect detection in urban underground pipelines,this study developed an improved defect detection method for urban underground pipelines based on fully convolutional one-stage object detector(FCOS),called spatial pyramid pooling-fast(SPPF)feature fusion and dual detection heads based on FCOS(SDH-FCOS)model.This study improved the feature fusion component of the model network based on FCOS,introduced an SPPF network structure behind the last output feature layer of the backbone network,fused the local and global features,added a top-down path to accelerate the circulation of shallowinformation,and enriched the semantic information acquired by shallow features.The ability of the model to detect objects with multiple morphologies was strengthened by introducing dual detection heads.The experimental results using an open dataset of underground pipes show that the proposed SDH-FCOS model can recognize underground pipe defects more accurately;the average accuracy was improved by 2.7% compared with the original FCOS model,reducing the leakage rate to a large extent and achieving real-time detection.Also,our model achieved a good trade-off between accuracy and speed compared with other mainstream methods.This proved the effectiveness of the proposed model.

Building Information Modeling-Based Secondary Development System for 3D Modeling of Underground Pipelines

Underground pipeline networks constitute a major component of urban infrastructure,and thus,it is imperative to have an efficient mechanism to manage them.This study introduces a secondary development system to efficiently model underground pipeline networks,using the building information modeling(BIM)-based software Revit.The system comprises separate pipe point and tubulation models.Using a Revit application programming interface(API),the spatial position and attribute data of the pipe points are extracted from a pipeline database,and the corresponding tubulation data are extracted from a tubulation database.Using the Family class in Revit API,the cluster in the self-built library of pipe point is inserted into the spatial location and the attribute data is added;in the same way,all pipeline instances in the pipeline system are created.The extension and localization of the model accelerated the modeling speed.The system was then used in a real construction project.The expansion of the model database and rapid modeling made the application of BIM technology in three-dimensional visualization of underground pipeline networks more convenient.Furthermore,it has applications in pipeline engineering construction and management.

Discussion on applying an analytical method to optimize the anti-freeze design parameters for underground water pipelines in seasonally frozen areas

Adopting the quasi-three-dimensional （Quasi-3D） numerical method to optimize the anti-freeze design parameters of an underground pipeline usually involves heavy numerical calculations. Here, the fitting formulae between the safe con-veyance distance （SCD） of a water pipeline and six influencing factors are established based on the lowest water temper-ature （LWT） along the pipeline axis direction. With reference to the current widely used anti-freeze design approaches for underground pipelines in seasonally frozen areas, this paper first analyzes the feasibility of applying the maximum frozen penetration （MFP） instead of the mean annual ground surface temperature （MAGST） and soil water content （SWC） to calculate the SCD. The results show that the SCD depends on the buried depth if the MFP is fixed and the variation of the MAGST and SWC combination does not significantly change the SCD. A comprehensive formula for the SCD is estab-lished based on the relationships between the SCD and several primary influencing factors and the interaction among them. This formula involves five easy-to-access parameters： the MFP, buried depth, pipeline diameter, flow velocity, and inlet water temperature. A comparison between the analytical method and the numerical results based on the Quasi-3D method indicates that the two methods are in good agreement overall. The analytic method can be used to optimize the anti-freeze design parameters of underground water pipelines in seasonally frozen areas under the condition of a 1.5 safety coefficient.

Electromagnetic Fields and Induced Voltages on Underground Pipeline in the Vicinity of AC Traction System

Various regulations, aimed at the protection of human beings and electrical equipment against possible adverse effects resulting from exposure to electromagnetic fields, have been issued in many countries. Most of them are based on safety guidelines published by international expert groups. In this paper, electric and magnetic fields are calculated in the vicinity of 25 kV traction line supplying railway traction systems. Calculation results are compared to exposure limits specified by safety guidelines and regulations. Possible countermeasures for reduction of electromagnetic fields are proposed. Also, this paper presents a method for calculation of the induced voltages to an underground gas pipeline from a neighbouring 25 kV electric traction overhead line in case of short circuit. Calculations are performed with EMTP-ATP software. Possible countermeasures for reduction of induced voltages are proposed.

Recent Research Advances in the Risk Assessment Method of an Underground Pressure Pipeline

This paper reviews the risk assessment method of an underground pressure pipeline, introduces the risk assessment method of expert grading, fuzzy integrative assessment, probabilistic risk assessment and extenics assessment in an underground pressure pipeline. Moreover, it puts forward the developing orientation of risk assessment.

Response of underground pipeline through fault fracture zone to random ground motion

It is assumed that a pipeline is laid through a vertical fault fracture zone, and is excited by seismic ground motion modelled as stationary stochastic process. For horizontal incidence of waves, the cross-PSD （Power Spectral Density） function is developed using wave propagation theory, while for vertical incidence of waves the cross-PSD function is composed by auto-PSD model, coherence model and site response model. As the seismic input, the eross-PSD function is used to calculate the the axial and lateral seismic responses of underground pipeline through the fracture zone. The results show that the incident directions of seismic waves, width and soil property of the fracture zone have great influence on underground pipeline. It is suggested that the flexible joints with appropriate stiffness should be added into the pipeline near the interfaces between the fracture zone and the surrounded media.

Incident analyses of frost heaving failure of municipal underground gas pipelines in cold regions of northern China

In the cold regions of northern China, incidents of municipal underground gas pipeline rupture and leakage occur quite fi-equently, aaost often in winter. To prevent harm to citizen safety and property, analysis of the causes of such cracking and leakage is therefore valuable. Two incident analyses are discussed here and the reasons why most of these types of cases occur dttring winter are clarified. Fhe effects of vehicle loadings above buried pipelines are calculated and compared with the effects and calculations of frost heaving forces. We demonstrate thtit when the soil layer above a pipeline freezes rapidly, the soil generates repeated frost heaving, which exerts heaving forces on the pipeline that can result in fatigue crack propagation and ultimate pipeline failure. Therefore, the incident induced 9y frost heaving is one of the primary reasons of gas pipeline failure. Based on these analyses, we present some recommendations pertaining to the proper design, construction, and management of gas pipelines.

Design of Underground Pipelines under Arbitrary Seismic Loading

On the basis of Hamilton-Ostrogradskiy variation principle a system of equations of linear pipeline vibrations interacting with surrounding soil is derived with appropriate boundary and initial conditions under arbitrary direction of seismic effect. Dynamic problem of underground pipeline is solved by finite difference method of the second order of accuracy with different combinations of boundary conditions under the effect of seismic load on a given law with arbitrary direction. Numerical implementation of the problem is realized.

Research of Risk Identification and Prevention of Underground Pressure Pipelines Damage Caused by External Disturbance

External disturbance is an important cause of underground pressure pipeline damage,which leads to accidents,and it is crucial to study the risk of damage caused by external disturbance and come up with proper prevention and control measures.We reviewed literature on risk identification of underground pressure pipelines damage due to external disturbance was conducted,and a list of risk factors was formed.Based on the list of risk factors,fault tree analysis was carried out on underground pressure pipelines damage caused by external disturbances,and risk prevention and control measures were proposed through the calculation of minimum cut sets,minimum path sets,and structural importance,in hopes of providing reference for the normal operation of underground pressure pipelines.

基于FCC-Deeplabv3+的城市地下管道缺陷语义分割方法

城市地下管道图像缺陷具有种类多、背景复杂、噪声多、缺陷尺度变化大等特点,导致目前城市地下管道缺陷分割算法精度不够高.本研究提出了一种基于Deeplabv3+的改进分割模型FCC-Deeplabv3+,并将该模型首次应用到城市地下管道缺陷分割.结合十字交叉注意力机制,使模型在预测时获取更丰富的上下文信息;提出了改进的解码器上采样策略,引入多尺度信息,减少中间层信息的丢失;使用基于增强的对比学习策略监督模型,提升了模型分割能力.此外,针对目前城市地下管道缺陷分割领域没有公开数据集的情况,基于Sewer-ML公开数据集,进行数据标注工作,构建了包含900张用于缺陷分割任务的数据集.通过实验验证了提出的缺陷分割模型的有效性及实时性,对比原始Deeplabv3+模型,mIoU提升了3.73%,mPA也提升了1.67%,并且相比其他基于深度学习的语义分割算法,也具有一定优势.

管线穿越对既有地铁隧道的变形影响分析

依托北京市东城区某会馆外部市政工程穿越地铁8号线某区间项目,利用Midas GTS软件和实地监测方法分别分析了地下管线穿越对既有地铁隧道的变形影响,得到以下结论:地下管线上穿会导致既有地铁隧道的上浮,最大竖向变形位置位于施工轴线下方,既有地铁隧道的竖向位移和水平位移值随监测点距施工中心轴线距离的增加而逐渐减小;多管线分步穿越施工,由此引起的变形量随步序施工基本呈线性增加;管线上穿施工对既有地铁隧道的影响相对较小。

Location monitoring approach of underground pipelines using time-sequential images

The location monitoring of underground pipelines is of utmost significance as it helps the effective management and maintenance of the pipelines,and facilitates the planning of nearby projects,preventing damage to the pipelines.However,currently there is a serious lack of data on the locations of underground pipelines.This paper proposes an image-based approach for monitoring the locations of underground pipelines by combing deep learning and visual-based reconstruction.The proposed approach can build the monitoring model for underground pipelines and characterize their locations through their centroid curve.Its advantages are:(1)simplicity:it only requires time-sequential images of the inner walls of underground pipelines;(2)clarity:the location model and the location curve of underground pipelines can be provided quickly;(3)robustness:it can cope with some existing problems in underground pipelines,such as light variations and small viewing angles.A lightweight approach for monitoring the locations of underground pipelines is achieved.The proposed approach’s effectiveness has been validated through laboratory simulation experiments,demonstrating accuracy at the millimeter level.

复杂条件背景下城市地下管线探测技术的应用

为了解决复杂地下环境、多样管线类型以及老化管线设施背景下,传统的单一管线探测技术无法满足实际需求的问题,本文在对多种探测技术进行简单介绍后,提出采用地质雷达探测技术进行地下管线探测,并分析其在城市基础设施管理中的实际应用情况。本研究对复杂的地下管线探测具有一定的借鉴意义。

基于增强现实技术的地下管线智慧化管理研究——以北京城市副中心应用系统为例

随着我国城市化的快速发展,作为“城市生命线”的地下管线建设规模迅速扩张,管线管理已成为韧性城市的重要环节,采用智慧化手段提升地下管线管理效能势在必行。该文从数据可视化、数据发布与共享等方面介绍增强现实技术在地下管线智慧化管理系统中的应用,提出突破原有传统的单一数据管理功能,实现风险识别、预测预警、智能分析,切实推动管线运营、安全管理、隐患治理能力为目标的智慧化管理系统建设发展,为全面推进韧性城市建设提供技术支撑。

北京市地下管线智慧化管理实践研究

该文对北京市地下管线智慧化管理实践进行研究。通过文献查阅与实地调研,调查通州地下管线三维数字化管理平台、怀柔韧性城市应用场景技术迭代平台、北京市管线防护系统的基本情况、运行成效,报告3个案例的现状,从数据管理、感知体系建设、协同共治等方面提出推进地下管线智慧化管理的对策建议,为建设地下管线“一网统管”体系,提升地下管线管理科学化、精细化、智能化水平提供参考。

基于云计算智慧城市地下管线综合管理平台建设探讨

随着城市化进程飞速发展,地下管线作为城市基础设施关键部分,其合理规划和高效管理至关重要。为做好地下管线综合管理工作,文章研究了基于云计算智慧城市地下管线综合管理平台的建设路径,在掌握地下管线管理信息化需求的基础上,阐述应用云计算、人工智能等新一代信息技术建设智慧管网平台,助推城市管理智能化发展进程。同时,强调了系统建设的技术选型、平台架构设计,以及介绍了建设智慧城市地下管线综合管理平台采用的多源数据三维一体化集成展示、三维管线自动化建模、图库联动和管线三维分析等关键技术措施。

基于时域有限差分的地下管线探测数值模拟

探地雷达作为一种无损检测手段广泛应用于地下管线探测,能快速探测到地下管线的位置、埋深及管径情况,给工程施工带来极大便利。然而高频雷达波波长短、介质吸收强烈,使得探测剖面较为复杂,探地雷达对地下管线的探测效果也因管线材质和天线频率而不同。为了提高探测的效果和解释的准确性,采用基于时域有限差分的gprMax开源代码对地下管线探测进行数值模拟。在天线频率400 MHz,圆管埋深0.9 m工况下,对不同管线材质进行仿真,结果显示,金属圆管反射电场强度是PVC圆管反射的两倍。说明当管线材质与周围介质介电常数差异大时,反射波能量强,雷达剖面结构更清晰。分别对400、900和1500 MHz天线频率进行仿真,结果表明雷达图的分辨力随着天线频率增加而提升。最后对管内介质分别为空气和水的工况进行仿真,在天线频率400 MHz工况下,管内介质为水的雷达图呈现3个明显的双曲线,管内介质为空气的雷达图值呈现1个明显的双曲线,说明电磁波在水中的能量衰减比空气中少。

TNT当量法在地下窨井空间天然气管道泄漏爆炸破坏研究

城市地下天然气管道在日常运行中存在泄漏爆炸风险,爆炸伤害波及范围作为评价爆炸影响效应、确定安全距离的关键指标,是城市天然气管道设计的重要参考依据。为准确推算泄漏燃气扩散至地下窨井空间后燃气爆炸所产生的破坏范围,通过TNT当量法建立数学模型,根据天然气泄漏到燃气检查井、水网窨井等密闭空间的天然气体积值,研究了燃气爆炸后的破坏范围。研究表明:以某城市生命线项目地下天然气管道节点数据为背景,对爆炸预测分析模型进行测试和验证,得出了天然气管道窨井、水网窨井爆炸的死亡半径、重伤半径、轻伤半径以及财产损失半径,研究结果为地下窨井空间天然气管道泄漏爆炸事故应急预案制定和应急处置方案实施提供重要的参考依据。

上盖开发的地下停车场室外综合管线设计优化

市域铁路车辆基地占地面积大,且城市用地紧张,地下车辆基地进行上盖开发形成趋势。地下车辆基地采用混凝土和整体钢板结构形式,一方面地下车辆基地结构立柱密集繁多,且由于消防要求导致顶板悬挂管线空间受限,对管线的布置带来巨大的挑战;另一方面混凝土一旦浇筑完成,再进行二次开挖返工困难重重。该文主要通过介绍地下停车场底板和顶板室外管线布置特点,包括管沟敷设形式、管沟布置原则和管线接口等在实际工程中的应用,再利用三维建模可视化(BIM)进行关键交叉节点的检查,最终合理完成室外管线优化设计。

改进YOLOv5的探地雷达常见地下管线识别

针对当前探地雷达(Ground Penetrating Radar,GPR)图像识别准确率低,且小目标识别困难等问题,本文将YOLOv5(You Only Look Once)和ConvNeXt网络相结合,提出一种适用于GPR图像的常见地下管线识别网络ConvNeXt-YOLOv5,显著提高了雷达图像中小目标的识别精度.同时,为了解决因地下管线原始信息不足而导致的模型训练精度低的问题,使用实测GPR图像、时域有限差分法(Finite-Difference Time-Domain,FDTD)与混类增强算法Mixup模拟图像构建数据集.然后,在此数据集上验证了本文所提方法对常见地下管线的识别效果,并用识别后的二维GPR B-scan图像还原出地下管线的三维图像.实验结果表明,对镀锌输水钢管、PVC管、电缆线和含水塑料瓶等常见地下管线进行识别时,ConvNeXt-YOLOv5表现出优良的识别性能.尤其是对PVC管的识别精度提升明显.与YOLOv4、YOLOv5、YOLOv7和Faster R-CNN模型相比,其平均精度均值分别提高了3.83%、2.82%、1.9%和3.72%.同时,三维探地雷达图像更直观的还原了地下管线信息.