Confronting the coexisting safety risks of overloaded operation and aging infrastructure in urban pipeline networks, and in response to the national “Two Major Initiatives” and “Two New Drivers” policy, the development of efficient and intelligent pipeline leak monitoring and precise prevention technologies is currently a focal point in academic research and engineering practice. Existing pipeline leak detection methods were summarized and categorized into hardware-based and software-based dimensions, involving multiple disciplines such as acoustics and optics. Current primary leak detection technologies were systematically investigated from the two directions of sensor measurement and simulation modeling, with their advantages and disadvantages studied. Challenges faced by current detection technologies were analyzed, and future development trends were outlooked. This review aims to provide a reference for research and practice in related fields.
在管道泄漏检测的多种技术路径中,基于仿真建模的方法因其能够从本质机理上复现管网系统的动态运行特性,长期以来被视为实现精准定位与定量分析的核心技术路线。该方法的核心在于构建与真实管网高度契合的仿真模型,通过集成流体力学、热力学以及管网拓扑结构等先验知识,建立以流体运动方程(如能量方程、连续性方程)为基础的精确机理模型。在理想状态下,该模型能够实时模拟无泄漏工况下的压力、流量等关键参数,并通过与现场实测数据进行持续比对,一旦发现显著偏差,即可判定泄漏发生,并依据偏差的时空分布特征反演计算出泄漏点位置与泄漏量。其技术路线可分为四个阶段:第一阶段为构建高精度的管网机理模型;第二阶段为实时数据同化与模型动态校准;第三阶段为泄漏检测、定位与定量;第四阶段为诊断反馈与模型自学习。此外,要捕捉泄漏引发的微小波动,必须建立精细模型,并将其与数据采集与监控(supervisory control and data acquisition,SCADA)系统紧密结合,实现从静态模拟到动态分析的转变。
管道泄漏源的精确定位是泄漏防控工作的核心目标,其精度直接关系到能否及时处置泄漏故障,从而避免重大安全事故的发生并有效控制经济损失。目前管道泄漏检测的定位方法根据检测原理不同,可分为4种:基于时延估计的泄漏定位方法(time difference of arrival,TDOA)、基于声波衰减的泄漏定位方法、基于特征参数的管道泄漏定位方法、基于信息融合的管道泄漏定位方法[66],其中最常用的定位方法还是基于时延估计的泄漏定位方法。
CaiChangxin, YiKang, LiaoRuiquan. Research progress of leak detection and localization technology for long-distance oil pipelines[J]. Science Technology and Engineering, 2023, 23(24): 10177-10189.
WangDazhi, ZhangChuanwei, ZhangJingxiang. Analysis of leakage causes and detection methods for long-distance oil and gas pipelines[J]. China Chemical Trade, 2025(25): 121-123.
BaiYe, ZhangYunpeng, PengShuo, et al. Research progress in pipeline leak detection technology and safety assessment[J]. Nondestructive Testing, 2025, 47(2): 59-67.
GaoLin, CaoJianguo. A review of pipeline leak detection methods[J]. Modern Manufacturing Engineering, 2022(2): 154-162.
[9]
SekhavatiJ, HashemabadiS H, SoroushM. Computational methods for pipeline leakage detection and localization: a review and comparative study[J]. Journal of Loss Prevention in the Process Industries, 2022, 77: 104771.
[10]
IslamM R, AzamS, ShanmugamB, et al. A review on current technologies and future direction of water leakage detection in water distribution network[J]. IEEE Access, 2022, 10: 107177-107201.
[11]
赵泽生, 袁宏永. 城市供热安全工程[M]. 北京: 中国建筑工业出版社, 2025.
[12]
ZhaoZesheng, YuanHongyong. Urban heating safety engineering[M]. Beijing: China Architecture and Building Press, 2025.
ZhaoYali. Research on distributed optical fiber pipeline leak monitoring system based on ϕ-OTDR[J]. Mechanical and Electrical Information, 2022(5): 34-36.
[15]
ZhanY G, LiuL R, WangZ Y, et al. Pipeline leakage identification method based on DPR-net and distributed optical fiber acoustic sensing technology[J]. Optics Communications, 2025, 574: 131096.
BiLingyue, WangQiang, WuYuhang. DTS-based leak detection and localization in syngas pipelines using an adaptive variance threshold algorithm[J]. Science Technology and Engineering, 2025, 25(12): 5037-5044.
[18]
GanW B, ZhangY J, JiaS K, et al. UWFBG array vibration sensing technology for gas pipeline leakage detection and location[J]. Optics Communications, 2024, 560: 130414.
[19]
LiH J, ZhuH H, TanD Y, et al. Detecting pipeline leakage using active distributed temperature sensing: theoretical modeling and experimental verification[J]. Tunnelling and Underground Space Technology, 2023, 135: 105065.
[20]
VollmerE, RuckJ, VolkR, et al. Detecting district heating leaks in thermal imagery: comparison of anomaly detection methods[J]. Automation in Construction, 2024, 168: 105709.
[21]
YangH T, TongY N, CaoZ Q, et al. Infrared image enhancement algorithm based on improved wavelet threshold function and weighted guided filtering[J]. Journal of Physics: Conference Series, 2023, 2525(1): 012017.
[22]
JiaH L, FengY, QiW J. Research on infrared image denoising and enhancement algorithm[C]//7th International Conference on Artificial Intelligence and Pattern Recognition. New York: Association for Computing Machinery, 2025: 466-471.
[23]
GuanH, XiaoT, LuoW, et al. Automatic fault diagnosis algorithm for hot water pipes based on infrared thermal images[J]. Building and Environment, 2022, 218: 109111.
ChenQiuyan, ZhangXinyan, HeMin, et al. Leakage identification in pipeline thermal images based on deep learning[J]. Infrared Technology, 2024, 46(5): 522-531.
[26]
ShiY, ChangJ Q, LiL, et al. Improved object detection network for pipeline leakage localization in the pneumatic system based on thermal images[J]. Measurement: Journal of the International Measurement Confederation, 2025, 242: 116225.
[27]
谢陈龙. 基于声发射信号的供水管网泄漏识别技术研究[D]. 哈尔滨: 哈尔滨工业大学, 2024.
[28]
XieChenlong. Research on leak identification technology in water supply networks based on acoustic emission signals[D]. Harbin: Harbin Institute of Technology, 2024.
HeLixin, ZhangHongyang, ZhangZheng, et al. Comparative study of machine learning models for water supply network leakage identification based on Mel-frequency cepstral coefficients[J]. Water and Wastewater Engineering, 2024, 60(8): 137-143.
[31]
YangX, FangH Y, YuX, et al. Study on the mechanism of vibration signal generation in water supply pipeline leaks[J]. Measurement, 2024, 229: 114415.
[32]
ScusselO, MichaelJ B, JenniferM M, et al. An investigation into the physical mechanisms of leak noise propagation in buried plastic water pipes: a wave dynamic stiffness approach[J]. Acoustics, 2024, 6(1): 157-176.
GuoShuaijie, ZhangLishen, LiCheng, et al. Leak detection and localization in directly buried hot-water heating pipelines using acoustic method[J]. Science Technology and Engineering, 2023, 23(11): 4765-4772.
SunShaojie, QiaoLei, LiYong, et al. Simulation and experiment on acoustic source characteristics of heating pipeline leakage[J]. Mechanical and Electrical Engineering Technology, 2023, 52(7): 111-114.
ChenYiming, WangBo, LiuHongda, et al. Numerical simulation of leakage in buried gas transmission pipelines based on acoustic analogy method[J]. Journal of Xi'an Shiyou University (Natural Science Edition), 2023, 38(5): 85-91.
[39]
YanD, WangG, WangJ J, et al. Pipeline multi-point leakage identification based on temporal convolutional network[J]. Flow Measurement and Instrumentation, 2025, 106: 102992.
ZhouJie. Nondestructive testing method for pipelines based on CUSUM algorithm using negative pressure wave[J]. Science and Technology Innovation and Productivity, 2024, 45(3): 105-107.
[42]
LiuW, FuQ, GaoH. Pipeline leak detection and localization based on the flow balance and negative pressure wave methods[J]. AIP Advances, 2024, 14(11): 115203.
ChenBin, HanXutong, WangLinquan, et al. A heating pipeline leak detection method based on AlexNet convolutional neural network: 202310222531[P]. 2023-07-14.
LiJiangang, QiWeixue, WangJingjing, et al. A method for leak identification and localization in heating pipeline networks: 202310916827[P]. 2023-11-10.
LiJiangang, ShiGuanghui, JiKedan, et al. A method for leak identification and localization in heating pipeline networks based on D-S evidence theory: 202310916425[P]. 2023-09-29.
[49]
VradisG C, SchempfH. Design, construction and field demonstration of explorer: a long-range untethered live gasline inspection robot system: 815463[R]. United States: U.S. Department of Energy, 2002.
MaYunbin, ShangZuyue, ZhengJie, et al. Research progress of oil and gas pipeline robots[J]. Science Technology and Engineering, 2025, 25(8): 3089-3101.
[52]
XuY N, YuZ P, CuiG M, et al. A flexible modular worm-inspired robot for multi-scenario explorations in pipeline[J]. Cell Reports Physical Science, 2026, 7(1): 103038.
MaYinghan, ZhaoHong, YuJiahao, et al. Structural design and optimization of a fluid-driven pipeline inspection robot[J]. Journal of Chongqing University of Technology (Natural Science), 2023, 37(1): 322-329.
[55]
EltwabA A A, SamehA. A modular, multi-sensor crawler robot for adaptive pipeline inspection: design and experimental validation[J]. Scientific Reports, 2026, 16(1): 880.
[56]
JangH, KimT Y, LeeY C, et al. Autonomous navigation of in-pipe inspection robot using contact sensor modules[J]. IEEE/ASME Transactions on Mechatronics, 2022, 27(6): 1-10.
[57]
LiuY X, DaiX L, WangZ, et al. A tensegrity-based inchworm-like robot for crawling in pipes with varying diameters[J]. IEEE Robotics and Automation Letters, 2022, 7(4): 1-8.
[58]
XylemInc. SmartBall technology for inline pipeline leak detection[EB/OL].[2026-05-11]. https://prod.xylem.com/en-me/products--services/pipeline-assessment/smartball-inline-free-swimming-inspection-platform/.
FangWenjun, WangHao, ShenQilu, et al. Leak location detection method for heating pipelines based on intelligent ball and acoustic localization: 202411320208[P]. 2024-10-25.
[61]
XuT S, ChenS L, GuoS X, et al. A small leakage detection approach for oil pipeline using an inner spherical ball[J]. Process Safety and Environmental Protection: Transactions of the Institution of Chemical Engineers Part B, 2019, 124: 279-289.
SongJinzhou, WuTong, ChenDi, et al. Research on real-time model-based pipeline leak monitoring technology using Brunone model[J]. Natural Gas and Oil, 2025, 43(4): 148-154.
WangDongmei, SongNannan, ZhangDan, et al. A digital twin-based pipeline leak identification model using AOA-SVM[J]. Journal of Jilin University (Information Science Edition), 2025, 43(5): 937-943.
[66]
WangJ L, WangH H, NieL T. Hydraulic simulation of water supply network leakage based on EPANET[J]. Journal of Pipeline Systems Engineering and Practice, 2024, 15(1): 1-9.
[67]
GargK, SinghS, RokadeM, et al. Experimental and computational fluid dynamic (CFD) simulation of leak shapes and sizes for gas pipeline[J]. Journal of Loss Prevention in the Process Industries, 2023, 84: 105112.
JiangBaiyi, MuTianwei, LiWeike, et al. Spatiotemporal joint water supply network leakage detection based on a deep learning framework[J]. Water and Wastewater Engineering, 2024, 60(6): 152-158.
ZhaoLinshuo, YeGuoxuan, ShenYonggang, et al. Water supply pipeline leakage detection based on time-frequency convolutional neural network[J]. China Water and Wastewater, 2023, 39(17): 53-58.
TanZhen, GuoXinlei, LiJiazhen, et al. Research on pipeline leak detection model based on multi-scale convolutional neural network[J]. Journal of Hydraulic Engineering, 2023, 54(2): 220-231.
PengYanli, LiuJunhong, TaoXiubin, et al. Water supply network leakage prediction based on PSO-GA model[J]. Journal of Shenyang Jianzhu University (Natural Science), 2025, 41(1): 121-129.
WangTong, JinZhaogui, YangRuihu, et al. Pipeline network leakage signal identification based on PSO-LSSVM time series prediction model[J]. Water Resources and Power, 2022, 40(2): 132-135, 181.
[78]
Lay-EkuakilleA, TrottaA, VendraminG. FFT- based spectral response for smaller pipeline leak detection[C]//2009 IEEE Instrumentation and Measurement Technology Conference. Piscataway: IEEE, 2009: 1642-1646.
YangHongying, HuaKe, YeHao, et al. Research on leak diagnosis method for gas transmission pipelines based on in-pipe acoustic waves[J]. Computers and Applied Chemistry, 2010(8): 1009-1012.
GaoRuxia. Research on heating pipeline leak localization based on improved variational mode decomposition with reconstruction denoising[D]. Beijing: Beijing University of Civil Engineering and Architecture, 2024.
[83]
MaY B, ShangZ Y, ZhengJ, et al. Research on leak detection and localization algorithm for oil and gas pipelines using wavelet denoising integrated with long short-term memory (LSTM)-Transformer models[J]. Sensors (Basel, Switzerland), 2025, 25(8): 2411.
[84]
LiuZ M, TangJ C, LiB G, et al. Research on denoising methods for infrasound leakage signals using improved wavelet threshold algorithm[J]. Machines, 2025, 13(11): 1062.
[85]
WangJ H, ZhengC Z, QiuJ, et al. An optimized VMD-wavelet denoising method for leakage detection in water supply networks from acoustic emission signals[J]. International Journal of Pressure Vessels and Piping, 2025, 217: 105535.
[86]
XuZ Q, LiC, MuL B, et al. Leakage detection method of underground heating pipeline based on improved wavelet threshold function[J]. Energy, 2024, 295: 131051.
[87]
HuangN E, ShenZ, LongS R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, 1998, 454(1971): 903-995.
[88]
DragomiretskiyK, ZossoD. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.
QiWeixue, JiKedan, WangJingjing, et al. Heating pipeline leak detection and localization based on VMD-BiGRU[J]. China Measurement and Testing, 2025, 41(12): 148-157.
ShiBaojun, LiZhengxin, LaiGuangjin, et al. Acoustic detection device and method for gas pipeline leakage based on CPO-VMD and multi-feature extraction: 202510196722[P]. 2025-05-02.
[93]
LangX M, YuanL, LiS Y, et al. Pipeline multipoint leakage detection method based on KKL-MSCNN[J]. IEEE Sensors Journal, 2024, 24(7): 11438-11449.
[94]
LiuG, ChenX, ZhangY, et al. Spectral denoising approach using enhanced wavelet packet-optimized EEMD algorithm[J]. Vibrational Spectroscopy, 2025, 140: 103844.
CaoZhimin, HuBin, LiZhinong, et al. Research status of acoustic recognition and localization methods for gas transmission pipeline leakage[J]. Nondestructive Testing, 2023, 45(3): 49-57.
LiuXiaosong, XuZaixiang, ShanZebiao, et al. Time delay estimation method based on quadratic fractional lower-order covariance[J]. Journal of Electronic Measurement and Instrumentation, 2024, 38(2): 112-119.
[103]
LiuH J, FangH Y, YuX, et al. Adaptive leak signal extraction based on EMD-CC for water pipeline leak location[J]. Structures, 2023, 56: 104884.
ShiLiang, JiangZhu, XieJunyi. Denoising method for water supply pipeline leakage signals combining variational mode decomposition and Hilbert transform[J]. China Rural Water and Hydropower, 2025(4): 52-57, 64.
[108]
ZhangX Q, ShiJ H, YangM, et al. Real-time pipeline leak detection and localization using an Attention-based LSTM approach[J]. Process Safety and Environmental Protection, 2023, 174: 460-472.
[109]
YangG, XingD H, WangH. Leak localization in district heating networks integrating physical model-based and data driven-based methods: impact of dataset construction on model performance[J]. Energy, 2024, 308: 132839.