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.

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.

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.

Risk Assessment of Coal Mine Water Hazard Based on Three-Dimensional Model of Geology and Underground Space

Mine safety have top-five disasters,which including the water,gas,fire,dust and geological dynamic disaster.The coal mine water disaster is one of the important factors which restricted the development of China’s coal production.It is showed by statistics that 60%of mine accidents are affected by groundwater,which not only result in the production losses,casualties and a variety of

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.

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.

大截面矩形顶管施工对既有管线影响研究

顶管施工会扰动邻近建筑物,危及工程安全。该文以苏州市城北路综合管廊元和塘段顶管工程为背景,通过ABAQUS有限元分析软件建立三维模型,研究顶管下穿地下管线施工对管周土及既有管线影响,并基于极限分析方法探讨了管线失稳模式。结果表明:大直径矩形顶管顶进方向的影响范围约为2倍顶管宽度,两侧的影响范围约为1倍顶管宽度,地下管线到顶管轴线的水平距离为0.5倍~1倍顶管宽度时,应注意管线受到的水平方向附加荷载是否会导致管线破坏;管线与顶管相对位置对管线破坏影响较为显著,越靠近顶管的管线破坏越严重,滑移线由顶管两侧经由管线向地面发展,破坏部位由管线顶部两侧延伸至底部;除受与顶管相对位置影响外,管线破坏模式还受矩形顶管形状影响,管线顶部及靠近顶管顶角区域破坏风险最大。

基于移动端管线内外业一体化数据采集整理系统研究

在分析地下管线外业数据采集、内业数据整理的工作流程并对其充分理解的基础上,采用基于Android的移动平台规范化采集管线数据,通过数据组织,在外业采集完成阶段就完成管线数据生产的绝大部分工作,省去内业大量展点编绘属性录入和整理的工作,实现管线数据作业效率的提升。

城市地下燃气管线系统定量风险评估

随着快速的城市化进程,地下管线系统越来越复杂,地下管线系统的风险显著增加。中国地下燃气管线事故数量较多,而且其事故造成的伤亡后果远远高于其他地下管线。其他地下管线在运行过程中对地下燃气管线系统造成的风险也受到燃气领域人员的关注。为了对地下管线系统进行定性、定量和系统的风险评估,综合STAMP和BN两种系统分析方法建立STAMP-BN模型,基于STAMP模型识别系统风险和因果因素,基于STAMP结果和安全控制结构,采用BN建模进行定量风险评估。应用建立的STAMP-BN模型进行地下管线系统风险评估,结果表明造成地下燃气管线泄漏的主要中间原因是三方公司的动土作业,并揭示了第三方公司和燃气公司脆弱的根本原因。可见加强第三方公司运营层协调和燃气公司协调安排、事件应急、对其他地下管线造成的慢性危害识别方面的能力是消减风险的关键。

基于改进YOLOv7的管道缺陷检测技术研究

针对城镇地下管网规模巨大、传统的人工检测方法已不能满足现在工程需求的问题,提出采用MobileNetv3-YOLOv7网络模型作为地下管道缺陷目标检测的算法来提升检测的精度和速度。首先,管道图像数据集进行预处理,对输入图像灰度化及重采样,均衡样本的数量;其次,将轻量化网络MobileNetv3和YOLOv7网络框架相结合,增加BiFPN特征金字塔结构以提高精确度;然后,在数据处理方面通过Mosaic数据增强方式提高该模型的鲁棒性;最后,设计YOLOv7网络模型的对比实验验证本模型的可行性。在Pytorch实验框架下,对MobileNetv3-YOLOv7网络模型进行了验证。实验结果表明,该模型可减少参数计算量,并且平均准确率有所提高。

基于Neo4j的城市地下管道信息知识图谱构建研究

为更好地支撑城市地下管道的探测作业,更系统、灵活地管理地下管道知识数据库,以相关国内标准、规范为研究基础,通过实体提取、知识整合等过程,建立城市地下管道信息知识图谱。将知识图谱存储在图数据库Neo4j中,提出基于数据-知识融合的辅助探测决策应用框架,进而提供实时、精准的知识查询接口。研究结果表明:构建的知识图谱可以辅助地下管道开挖工程的探测决策过程,一定程度上为推进地下管道数据-知识融合探测体系建成提供参考。

地下管线BIM模型快速构建及教学应用

在职业技术技能教学中,城市地下管线测绘一直是教学的难点。地下管线位于地面以下,在地表往往只能看到窨井盖等管线附属设施,在实际的地下管线测绘技能教学过程中无法完全展现地下管线的真实形态,不利于学生知识技能的掌握。基于城市地下市政基础设施普查数据库,二次开发Revit软件插件,快速构建地下管线及附属设施的三维BIM模型,进行虚拟仿真教学,对学生了解地下管线形态、掌握地下管线测绘方法有重要作用,有助于提高课堂效率,增强学生技能水平。

考虑管线老化和破损时基坑开挖对邻近管线纵向变形的影响

基于影像源法,结合Pasternak地基模型,提出了一种考虑管线老化和破损的邻近地下管线纵向变形计算方法。收集4个工程案例数据进行对比验证,并对基坑围护结构变形控制参数、管线轴线埋深、管线轴线到基坑围护结构的水平距离、老化和破损程度这5个影响因素进行了分析。研究结果表明:随着基坑围护结构变形增大,其对管线纵向变形影响及影响范围也随之增大,管线最大沉降与围护结构变形呈正相关关系;基坑侧壁与管线轴线距离增加,管线的纵向变形非线性减小;管线沉降与其埋深呈非线性减小关系;管线老化会导致管线整体变形增大,而管线破损则会导致破损位置产生较大变形。基坑施工前有必要对邻近的地下管线使用年限以及破损程度进行调查。

南昌地铁地下多管线近邻地铁人行通道的施工影响分区

针对地下地铁人行通道暗挖施工对近邻多管线扰动影响问题,依托南昌地铁3号线邓埠站1号出入口人行通道暗挖工程,采用数值计算与理论分析相结合的方法,系统研究了通道暗挖施工扰动作用下近邻多管线的力学特性,总结关键因素对管线力学行为的影响规律,提出了通道暗挖下近邻密集管线影响分区计算方法与控制措施。结果表明:结合Peck曲线分布规律确定出以控制值的60%与20%作为强影响分区、弱影响分区、无影响分区的阈值;采用多元非线性函数进行拟合得出的线竖向位移与多因素的关系函数,对影响分区划分效果较好;建立的地铁隧道暗挖对近邻密集管线强弱影响分区方法,可通过有效的措施将密集管线强影响区转变为弱影响区和无影响区,进而保障施工安全。

南方某城市地下综合管廊应急排水设计思考

城市综合管廊已成为城市基础设施建设重要的一部分,然而对其应急排水设计目前仍缺乏充分思考。研究以南方某城市地下深埋综合管廊为例,综合考虑管廊开口处进水、管廊结构缝处渗漏水、管廊接出口渗漏水、管廊内冲洗排水、检修放空排水、供水管道渗漏水和供水管道爆管排水7种排水;针对不同规模的供水爆管漏失面积,提出相应的应急排水措施,包括提高日常排水泵流量,设置应急排水泵,调动移动抽水车;最后,研究建立管廊内给水管爆漏应急预案,提出爆管突发事件的监测要求和应急处置流程,以期最大限度地减少突发性爆管造成的影响。研究成果对综合管廊供水管道安全运行及应急排水设计具有重要的指导意义。

地下管线损伤与变形的两阶段预警方法研究

为有效预警地下管线安全问题,满足现场对易观察的安全指标的需要,分析地下管线的损伤变形特征,基于现有的地下管线安全预警评价指标,结合管线的大变形和小变形特征,总结各常见损伤对管线安全影响较大的因素,提出针对地下管线的两阶段预警方法与地下管线变形过程安全预警三色图,并以地下管线下方出现空洞并逐渐扩大为例进行说明。结果表明:该方法能够直观、方便地判断管线在变形过程中的安全状态,为地下管线事故和隐患的决策提供参考信息,以便于决策方和施工方能够快速直观地判断管线安全。