Leakage discharge analysis model based on FastICA algorithm
ZHENG Cheng zhi, GAO Jin liang, HE Wen jie
1. School of Municipal and Environmental Engineering, Harbin Institute of Technology, Harbin 150090, China;
2. Tianjin Water Works Group Co. Ltd, Tianjin 300040, China
A new leakage discharge analysis model based on fast independent component analysis (FastICA) algorithm was established in order to solve the problems of the traditional leakage discharge analysis models, such as low simulation accuracy, incapability of reflecting the uncertain relationship between leakage discharge and presssure head and so on. The model divided total water supply flow into actual consumed water flow and leakage discharge and considered them as two source signals. In the model, the total water supply flow and pressure head at the entrance were considered as two input parameters. The waveform information of two flows were obtained by separating source signals. The order of the source signals was determined by comparing the correlation coefficients. The real amplitude of leakage discharge was solved out according to the flow balance equation. Therefore, the leakage discharge was simulated in time series. For this model, the input parameters are easily getparms. It can effectively avoid the complexity of the relationship between leakage discharge and head pressure. Thus the simulation accuracy is high in the water distribution system with one entrance only. The model has been preferably applied in the node demand distribution of one water distribution network’s hydraulic model.
ZHENG Cheng zhi, GAO Jin liang, HE Wen jie. Leakage discharge analysis model based on FastICA algorithm. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2016, 50(6): 1031-1039.
［1］ THORNTON J, LAMBERT A. Progress in practical prediction of pressure: leakage, pressure: burst frequency and pressure: consumption relationships ［C］∥ Proceedings of IWA Special ConferenceLeakage, Halifax: ［s. n.］, 2005: 12-14.
［2］ FERRANTE M, MASSARI C, BRUNONE B, et al. Experimental evidence of hysteresis in the headdischarge relationship for a leak in a polyethylene pipe ［J］. Journal of Hydraulic Engineering, 2010, 137(7):775-780.
［3］ CASSA A M, VAN ZYL J E, LAUBSCHER R F. A numerical investigation into the effect of pressure on holes and cracks in water supply pipes ［J］. Urban Water Journal, 2010, 7(2): 109-120.
［4］ CASSA A M, VAN ZYL J E. Predicting the headarea slopes and leakage exponents of cracks in pipes ［C］∥ Urban Water Management: Challenges and Oppurtunities11th International Conference on Computing and Control for the Water Industry, CCWI. Exeter: CCWI, 2011: 2.
［5］ PAOLA F D, GIUGNI M. Leakages and pressure relations: an experimental research ［J］. Drinking Water Engineering and Science Discussions, 2012, 5(1): 403-419.
［6］ FERRANTE M. Experimental investigation of the effects of pipe material on the leak headdischarge relationship ［J］. Journal of Hydraulic Engineering, 2012, 138(8): 736-743.
［7］ JAUMOUILL E, PILLER O, VAN ZYL J E. Advantages of a hydraulic saintvenant type model with pressuredependent leakage ［C］∥ Proceedings of the 10th Annual Water Distribution Systems Analysis Conference, WDSA. Kruger National Park: WDSA, 2009: 814-823.
［8］ WU Z Y, BURROWS R, MOORCROFT J, et al. Pressuredependent leakage detection method compared with conventional techniques ［J］. Water Distribution System Analysis, 2010: 1083-1092.
［9］ WALSKI T, BEZTS W, POSLUSZNY E T, et al. Modeling leakage reduction through pressure control ［J］. Journal of American Water Works Association, 2006, 98(4): 147-155.
［10］ VAN ZYL J E, CLAYTON C R I. The effect of pressure on leakage in water distribution systems ［J］. Proceedings of the Institution of Civil Engineers: Water Management, 2007, 160(2): 109-114.
［11］ MENICONI S, BRUNONE B, FERRANTE M, et al. Numerical and experimental investigation of leaks in viscoelastic pressurized pipe flow ［J］. Drinking Water Engineering and Science, 2013, 6(1): 1116.
［12］ TABESH M, YEKTA A H A, BURROWS R. An integrated model to evaluate losses in water distribution systems ［J］. Water Resources Management, 2009,23(3): 477-492.
［13］ BURNELL D, RACE J. Water distribution systemsanalysis: patterns in supplypipe leakage ［C］∥ Joint Conference on Water Resource Engineering and Water Resources Planning and Management 2000: Building Partnerships. Minneapolis: American Society of Civil Engineers, 2004: 104.
［14］ WU Z Y, FARLEY M, TURTLE D, et al. Water Loss Reduction ［M］. Pennsylvania: Bentley Institute Press, 2011: 32-57.
［15］ 朱世泰. 城市供水管网模型校核参数的研究［D］. 广州:华南理工大学, 2014: 5-11.
ZHU Shitai. Study on calibrated parameters of urban water distribution system model ［D］. Guangzhou: South China University of Technology, 2014: 5-11.
［16］ CHEUNG P B, GIROL G V, ABE N, et al. Night flow analysis and modeling for leakage estimation in a water distribution system ［C］∥ Integrating Water SystemsProceedings of the 10th International on Computing and Control for the Water Industry, CCWI 2009. Sheffield: CCWI, 2010: 509-513.
［17］ 张冬,李淑慧,张俊杰.优化管网压力以降低管网漏损的研究［J］. 中国给水排水, 2014, 30(3): 59-61.
ZHANG Dong, LI Shuhui, ZHANG Junjie. Optimization of water distribution network pressure for educing leakage ［J］. China Water and Wastewater, 2014, 30(3): 59-61.
［18］ ALMANDOZ J, CABRERA E, ARREGUI F, et al. Leakage assessment through water distribution network simulation ［J］. Journal of Water Resources Planning And Management, 2005, 131(6): 458-466.
［19］ YUAN X, WANG C, JI F, et al. A magnetic flux leakage analysis model based on finite element neural network ［J］. InsightNonDestructive Testing and Condition Monitoring, 2011, 53(9): 482-486.
［20］ MASSARI C, FERRANTE M, BRUNONE B, et al. Is the leak headdischarge relationship in polyethylene pipes a bijective function？ ［J］. Journal of Hydraulic Research, 2012, 50(4): 409-417.
［21］ 于先川, 胡丹. 盲源分离理论与应用［M］. 北京: 科学出版社, 2011: 17-52.
［22］ 金羽晔, 李式巨, 王彦波, 等. CDMA 盲自适应独立分量多用户检测器［J］. 浙江大学学报: 工学版, 2008, 42(10): 1745-1750.
JIN Yute, LI Shiju, WANG Tanbo, et al. Independent component analysis based blind adaptive multiuserdetector for CDMA ［J］. Journal of Zhejiang University: Engineering Science, 2008, 42(10): 1745-1750.
［23］ 周晓峰, 杨世锡.基于负熵最大化的机械振源半盲分离方法［J］. 浙江大学学报: 工学版, 2011, 45(5): 846-850.
ZHOU Xiaofeng, YANG Shixi. Semiblind sources separation of mechanical vibrations base on maximization of negentropy ［J］. Journal of Zhejiang University: Engineering Science, 2011, 45(5): 846-850.
［24］ ALMANDOZ J, CABRERA E, ARREGUI F, et al. Leakage assessment through water distribution network simulation ［J］. Journal of Water Resources Planning and Management, 2005, 131(6): 458-466.
［25］ TABESH M, TANYIMBOH T T, BURROWS R. Headdriven simulation of water supply networks ［J］. International Journal of Engineering, 2002, 15(1): 11-22.
［26］ 顾军,胡显丹.基于FastICA 算法的敌我识别信号分选方法研究［J］.舰船电子对抗, 2009, 32(5): 41-44.
HU Jun, HU Xiandan. Research into the sorting method of IFF signals based on fastICA algorithm ［J］. Shipboard Electronic Countermeasure, 2009, 32(5):41-44.
［27］ 蒋夕平, 吴凤凰, 蒋昱, 等. 基于 FastICA 算法的高光谱矿物丰度反演［J］. 吉林大学学报:地球科学版, 2013, 43(5): 1681-1686.
JIANG Xiping, WU Fenghuang, JIANG Yu, et al. Hyperspectral mineral abundance inversion based on FastICA algorithm ［J］. Journal of Jilin University: Earth Science Edition, 2013, 43(5): 1681-1686.
