Please wait a minute...
浙江大学学报(工学版)  2017, Vol. 51 Issue (11): 2222-2231    DOI: 10.3785/j.issn.1008-973X.2017.11.017
土木与交通工程     
数据驱动的城市供水管网异常事件侦测方法
徐哲, 熊晓锋, 洪嘉鸣, 何必仕, 陈云
杭州电子科技大学自动化学院, 浙江 杭州 310018
Data-driven abnormal event detection method for urban water supply network
XU Zhe, XIONG Xiao-feng, HONG Jia-ming, HE Bi-shi, CHEN Yun
Automation college of Hangzhou Dianzi University, Hangzhou Zhejiang, 310018, China
 全文: PDF(3327 KB)   HTML
摘要:

针对供水管网爆管等监控问题,提出数据驱动的供水管网异常事件侦测方法.在某市供水管网独立计量区域(DMA)内,采用打开消防栓方式进行模拟爆管实验,在对实测数据进行小波降噪等预处理的基础上,分别采用基于VARX模型的差异分析方法和统计过程控制(SPC)方法进行异常侦测,再使用贝叶斯网络综合推理.通过引入信噪比分析,降低了综合推理后的误报次数.实验结果表明,该异常侦测方法可以达到较高的准确性.

Abstract:

A data driven method for abnormal event detection of water supply network was proposed in order to solve the pipe burst monitoring problem. Pipe burst experiments were conducted by opening fire hydrant in a district metering area (DMA) of an urban water supply network. Based on the measured data of wavelet de-noising preprocessing, the difference analysis method of VARX model and statistical process control (SPC) methods for abnormal event detection were used. Then Bayesian network was used for comprehensive inference, and false alarm after comprehensive inference was reduced with signal-noise ratio analysis. The experimental results show that the data driven method can achieve higher accuracy.

收稿日期: 2016-10-24 出版日期: 2017-11-13
CLC:  TU991.33  
基金资助:

国家自然科学基金重点资助项目(61233004);国家自然科学浙江联合基金资助项目(U1509205).

作者简介: 徐哲(1967-),男,教授,从事智慧水务建模与控制等研究.ORCID:0000-0001-6506-1021.E_mail:xuzhe@hdu.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  

引用本文:

徐哲, 熊晓锋, 洪嘉鸣, 何必仕, 陈云. 数据驱动的城市供水管网异常事件侦测方法[J]. 浙江大学学报(工学版), 2017, 51(11): 2222-2231.

XU Zhe, XIONG Xiao-feng, HONG Jia-ming, HE Bi-shi, CHEN Yun. Data-driven abnormal event detection method for urban water supply network. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(11): 2222-2231.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2017.11.017        http://www.zjujournals.com/eng/CN/Y2017/V51/I11/2222

[1] CHEN H, YE H, CHEN L V, et al.. Application of support vector machine learning to leak detection and location in pipelines[C]//Instrumentation and Measurement Technology Conference. Como,Italy:Proceedings of the IEEE, 2004:2273-2277.
[2] STEPHENS M L, LAMBERT M F,SIMPSON A R. Determining the Internal wall condition of a water pipeline in the field using an inverse transient[J]. Journal of Hydraulic Engineering, 2013,139(3):310-324.
[3] GONG J,SIMPSON A R,LAMBERT M F, et al. Detection of distributed deterioration in single pipes using transient reflections[J]. Journal of Pipeline Systems Engineering & Practice,2013, 4(1):32-40.
[4] 郭新蕾,杨开林.管道泄漏检测的水力瞬变全频域数学模型[J].水利学报,2008,39(10):1264-1271. GUO Xin-lei, YANG Kai-lin. Hydraulic transient model in frequency domain for leak detection in pipeline systems[J]. Journal of Hydraulic Engineering, 2008, 39(10).
[5] WU Z Y, BURROWS R, MOORCROFT J, et al. Pressure-dependent leakage detection method compared with conventional techniques[C]//Conference on Water Distribution Systems Analysis.[S. l.]:[s. n.] 2011:1083-1092.
[6] 刘书明,王欢欢,徐锦华,等.基于智能优化算法的供水管网漏水点定位[J].同济大学学报:自然科学版,2014,42(5):740-744. LIU Shu-ming, WANG Huan-huan, XU Jin-hua, et al. Identification of leakage location based on modern optimization algorithms[J]. Journal of TONGJI University:Natural Science,2014, 42(5):740-744.
[7] 程伟平,赵丹丹,许刚,等.供水管网爆管水力学模型与爆管定位[J].浙江大学学报:工学版,2013,47(6):1057-1062. CHENG Wei-ping, ZHAO Dan-dan, XU Gang, et al. Pipe burst hydraulic model of water distribution system and pipe burst location[J]. Journal of Zhejiang University:Engineering Science,2013,47(6):1057-1062.
[8] 李稳,崔建国,毛立波.供水管网压力异常工况下的趋势面分析模型及应用[J].节水灌溉,2011(8):47-50. LI Wen, CUI Jiun-guo, MAO Li-bo. Study on trend-surface analysis model under abnormal pressure condition in water-supply pipe network and its application[J]. Water Saving Irrigation, 2011(8):47-50.
[9] YE G, FENNER R A. Kalman Filtering of hydraulic measurements for burst detection in water distribution systems[J]. Journal of Pipeline Systems Engineering & Practice,2011,2(1):14-22.
[10] JUNG D, LANSEY K. Water Distribution System burst detection using a nonlinear kalman filter[J].Journal of water resources planning and management.2014,141(5):1-13.
[11] MOUNCE S R,BOXALL J B,MACHELL J. Development and verification of an online artificial intelligence system for burst detection in water distribution systems[J].Journal of Water Resources Planning & Management,2010,136(3):309-318.
[12] 黄廷林,曹梅花,张卉.基于SCADA系统给水管网实时检测爆管位置方法的研究[J].给水排水,2007,33(5):104-108. HUANG Ting-lin, CAO Mei-hua, ZHANG Hui. Study on SCADA based real-time detection of pipe bursts location of water supply network[J]. Water & Wastewater Engineering, 2007, 33(5):104-108.
[13] PALAU C V, ARREGUI F J, CARLOS M. Burst detection in water networks using principal component analysis[J].Journal of Water Resources Planning & Management, 2011, 138(1):47-54.
[14] ROMANO M, KAPELAN Z, SAVIC D A. Automated detection of pipe bursts and other events in water distribution systems[J]. Journal of Water Resources Planning & Management,2012,140(4):456-467.
[15] ROMANO M. Near real-time detection and approximate location of pipe bursts and other events in water distribution systems[J].University of Exeter, 2012.
[16] 李楠楠,郄志红,古田均.供水管网爆管故障诊断的PSO-SVM方法[J].系统工程理论与实践,2012,32(9):2104-2110. LI Nan-nan, QIE Zhi-hong, GU Tian-jun. PSO-SVM model for pipe bursting diagnosis of water supply network[J]. Systems Engineering-Theory & Practice, 2012,32(9):2104-2110.
[17] BOGNER K,PAPPENBERGER F. Multiscale error analysis,correction, and predictive uncertainty estimation in a flood forecasting system[J].Water Resources Research,2011,47(7):1772-1780.
[18] DONOHO D L, JOHNSTONE I M. Adapting to unknown smoothness via wavelet shrinkage[J]. Journal of the American Statistical Association, 1995,90(432):1200-1224.
[19] 齐培艳,段西发,田铮.基于小波的非参数回归模型均值变点的Bootstrap监测[J].系统工程理论与实践,2014(10):2650-2655. QI Pei-yan, DUAN Xi-fu,TIAN Zheng. Bootstrap monitoring for mean change of nonparametric regression models by wavelets[J]. Systems Engineering-Theory & Practice,2014, 34(10):2650-2655.
[20] SOUTO M, MOREIRA A, VEIGA A, et al. A high-dimensional VARX model to simulate monthly renewable energy supply[C]//Power Systems Computation Conference. Wroclaw Poland:IEEE, 2015:1-7.
[21] DAN K,KING K. Methods for evaluating water distribution network early warning systems[J]. Journal(American Water Works Association), 2010, 102(1):79-89.
[22] PANGULURI S, GRAYMAN W M, CLARK R M. Water distribution system and analysis:field studies,modeling and management[EB/OL]. http://www.uky.edu/WDST/PDFs/[53] %20Water%20Distribution%20Systems%20Analysis%20-%20Field%20Studies%20Modeling%20and%20Management.pdf.2005-12-01/2016-09-16.

[1] 吴众华, 张土乔, 黄亚东, 等. 基于可靠性的给水管网传感器多目标选址[J]. J4, 2009, 43(6): 1060-1064.