簡易檢索 / 詳目顯示

回結果列表
研究生： 裴光雅
QUANG-NHA BUI
論文名稱： Leak Detection in Water Distribution System based on Bayesian Network Learning and Hybrid Multivariate Regression Particle Swarm Optimization Approach
Leak Detection in Water Distribution System based on Bayesian Network Learning and Hybrid Multivariate Regression Particle Swarm Optimization Approach
指導教授： 呂守陞
Sou-Sen Leu
口試委員: 楊亦東
I-Tung Yang
楊德良
Der-Liang Young
黃榮堯
Rong-Yao Huang
潘乃欣
Nai-Hsin Pan
學位類別： 博士
Doctor
系所名稱： 工程學院 - 營建工程系
Department of Civil and Construction Engineering
論文出版年： 2016
畢業學年度： 104
語文別： 英文
論文頁數： 120
中文關鍵詞： Water distribution system 、Water leakage 、Bayesian network 、Leak detection 、PSO
外文關鍵詞： Water distribution system, Water leakage, Bayesian network, Leak detection, PSO
相關次數： 點閱：428  下載：1 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • Leaks in the water distribution systems (WDSs) not only cause waste of resource and energy, but also potential health risk due to polluted water ingress through cracks. Thus, leakage control in the water distribution systems become a compelling but challenging issue in water conservation. This research proposes two models to deal with water leakage problems: The first model called expert structural expectation-maximization (ExSEM) for predicting water leakage in WDSs, and the second one for dealing with leak detection problem by coupling a hybrid multivariate linear regression particle swam optimization (MLR-PSO) with a data-driven optimal sensor placement (DOSP) algorithm. The first model can take into account the uncertainty of leakage-related factors and balance the contribution of monitoring data and prior information in a Bayesian learning process to maximize leakage prediction accuracy, while the combination of two sub-models in the second model help overcome the drawbacks of traditional leak detection methods by significantly reducing the computation time and maintaining robust leak detection capability. The optimal sensor placement strategy bases on exploiting historical data to maximize the leak detectability of the second model. The results of this study could benefit water utilities by aiding them in establishing an effective active leakage control plan to minimize the risk of water leakage. Case studies are presented to demonstrate the robustness and effectiveness of the proposed methods.

    Leaks in the water distribution systems (WDSs) not only cause waste of resource and energy, but also potential health risk due to polluted water ingress through cracks. Thus, leakage control in the water distribution systems become a compelling but challenging issue in water conservation. This research proposes two models to deal with water leakage problems: The first model called expert structural expectation-maximization (ExSEM) for predicting water leakage in WDSs, and the second one for dealing with leak detection problem by coupling a hybrid multivariate linear regression particle swam optimization (MLR-PSO) with a data-driven optimal sensor placement (DOSP) algorithm. The first model can take into account the uncertainty of leakage-related factors and balance the contribution of monitoring data and prior information in a Bayesian learning process to maximize leakage prediction accuracy, while the combination of two sub-models in the second model help overcome the drawbacks of traditional leak detection methods by significantly reducing the computation time and maintaining robust leak detection capability. The optimal sensor placement strategy bases on exploiting historical data to maximize the leak detectability of the second model. The results of this study could benefit water utilities by aiding them in establishing an effective active leakage control plan to minimize the risk of water leakage. Case studies are presented to demonstrate the robustness and effectiveness of the proposed methods.

    ACKNOWLEDGEMENTS iii Abstract v Dedication vii Table of Contents ix List of Figures xiii List of Tables xv List of notations and abbreviations xvii Chapter 1 INTRODUCTION 1 1.1 Research Background 1 1.2 Research Objectives 5 1.3 Research Scope 6 1.4 Dissertation Structure 7 Chapter 2 LITERATURE REVIEW 9 2.1 Overview of leakage management: 9 2.1.1 Economic level of leakage 10 2.1.2 Leak run time (leak break duration) 11 2.1.3 Active leakage detection 12 2.2 Review of Leakage Detection Methods 12 2.2.1 Leak prior assessment methods 12 2.2.2 Leak location detection methods (leak localization) 15 2.2.3 Leak pinpointing methods 20 2.2.4 Leak prediction methods 23 2.3 Review of Sensor Placement Methods 24 Chapter 3 RESEARCH METHODOLOGY 27 3.1 Bayesian Network: From construction to application 27 3.1.1 Bayesian Network 27 3.1.2 BN from construction to application 30 3.2 Structural Expectation Maximization algorithm 33 3.3 Scoring functions for BN structure learning 35 3.3.1 Bayesian scoring function: 35 3.3.2 Information theoretic scoring function: 37 3.4 Hydraulic simulation of water network 38 3.5 Generalized simulation-based optimization approach for water leak detection 44 3.6 Optimal sensor placement algorithm 46 Chapter 4 LEAK PREDICTION BASED ON EXPERT STRUCTURAL EXPECTATION MAXIMIZATION 49 4.1 Identification of leakage factors 49 4.2 Data collection and preprocessing 51 4.2.1 Observation data 51 4.2.2 Initial Bayesian network 52 4.2.3 Bayesian network by experts 52 4.3 Model construction 53 4.3.1 Water leakage control system 53 4.3.2 Expert Bayesian information criterion score 55 4.3.3 Expert structural expectation–maximisation algorithm for predicting water pipe leakage 57 4.4 Application to case study 58 4.4.1 Input data and experimental setup 58 4.4.2 Bayesian learning results 61 4.4.3 Leakage prediction results and comparison 64 4.5 Analysis of effects of leakage-related factors 65 Chapter 5 WATER LEAKS DETECTION BY A HYBRID MLR-PSO COUPLING WITH DOSP 69 5.1 Data-driven optimal sensor placement 69 5.1.1 Pipe leakage probability exploited from data 70 5.1.2 Data-driven optimal sensor placement algorithm 70 5.2 MVR-PSO algorithm 72 5.2.1 Leak sensitivity matrix by multivariate linear regression analysis 73 5.2.2 Particle swam optimization (PSO) 75 5.3 Application to case study 78 5.3.1 Experiment 1: simple network 78 5.3.2 Experiment 2: DMA network 84 Chapter 6 CONCLUSION 89 6.1 Conclusion 89 6.2 Future research direction 90 References 93 Appendix A : DMA information 102 Xin-Yi DMA 102 DMA information 103 Appendix B : Inflow data observation 104 Appendix C : Data for Leak prediction 105

    Akhtar, M. J. and I. B. Utne (2014). "Human fatigue’s effect on the risk of maritime groundings – A Bayesian Network modeling approach." Safety Science 62(0): 427-440.
    Alkasseh, J. A., M. Adlan, I. Abustan, H. Aziz and A. Hanif (2013). "Applying Minimum Night Flow to Estimate Water Loss Using Statistical Modeling: A Case Study in Kinta Valley, Malaysia." Water Resources Management 27(5): 1439-1455.
    Araujo, L. S., H. Ramos and S. T. Coelho (2006). "Pressure Control for Leakage Minimisation in Water Distribution Systems Management." Water Resources Management 20(1): 133-149.
    Babbitt, H. E., F. C. Amsbary and D. R. Gwinn (1920). "THE DETECTION OF LEAKS IN UNDERGROUND PIPES [with DISCUSSION]." Journal (American Water Works Association) 7(4): 589-595.
    Barbieri, R., N. Barbieri and K. F. de Lima (2015). "Some applications of the PSO for optimization of acoustic filters." Applied Acoustics 89: 62-70.
    Besner, M.-C., M. Prévost and S. Regli (2011). "Assessing the public health risk of microbial intrusion events in distribution systems: Conceptual model, available data, and challenges." Water Research 45(3): 961-979.
    Blesa, J., F. Nejjari and R. Sarrate (2014). "Robustness Analysis of Sensor Placement for Leak Detection and Location under Uncertain Operating Conditions." Procedia Engineering 89(0): 1553-1560.
    Casillas, M., V. Puig, L. Garza-Castañón and A. Rosich (2013). "Optimal Sensor Placement for Leak Location in Water Distribution Networks Using Genetic Algorithms." Sensors 13(11): 14984.
    Cataldo, A., G. Cannazza, E. D. Benedetto and N. Giaquinto (2012). "A TDR-based system for the localization of leaks in newly installed, underground pipes made of any material." Measurement Science and Technology 23(10): 105010.
    Colombo, A. F., P. Lee and B. W. Karney (2009). "A selective literature review of transient-based leak detection methods." Journal of Hydro-environment Research 2(4): 212-227.
    Cooper, G. F. and E. Herskovits (1992). "A Bayesian method for the induction of probabilistic networks from data." Machine Learning 9(4): 309-347.
    Covas, D. and H. Ramos (2010). "Case Studies of Leak Detection and Location in Water Pipe Systems by Inverse Transient Analysis." Journal of Water Resources Planning and Management 136(2): 248-257.
    Delgado-Galván, X., R. Pérez-García, J. Izquierdo and J. Mora-Rodríguez (2010). "An analytic hierarchy process for assessing externalities in water leakage management." Mathematical and Computer Modelling 52(7–8): 1194-1202.
    Demirci, S., E. Yigit, I. H. Eskidemir and C. Ozdemir (2012). "Ground penetrating radar imaging of water leaks from buried pipes based on back-projection method." NDT and E International 47: 35-42.
    Diamantidis, N. A., D. Karlis and E. A. Giakoumakis (2000). "Unsupervised stratification of cross-validation for accuracy estimation." Artificial Intelligence 116(1-2): 1-16.
    EC (2015). EU Reference document Good Practices on Leakage Management WFD CIS WG PoM, European Commission.
    EPA (2007). Leakage Management Technologies. U.S.A, Awwa Research Foundation.
    Farley, M. and S. Trow (2003). Losses in Water Distribution Networks: A Practitioner's Guide to Assessment, Monitoring and Control IWA publishing.
    Feelders, A. and L. C. van der Gaag (2006). "Learning Bayesian network parameters under order constraints." International Journal of Approximate Reasoning 42(1-2): 37-53.
    Fletcher, R. and M. Chandrasekaran (2008). SmartBall™: A New Approach in Pipeline Leak Detection. 2008 7th International Pipeline Conference. Calgary, Alberta, Canada. 2.
    Francis, R. A., S. D. Guikema and L. Henneman (2014). "Bayesian Belief Networks for predicting drinking water distribution system pipe breaks." Reliability Engineering & System Safety 130(0): 1-11.
    Friedman, N. (1998). The Bayesian structural EM algorithm. In UAI.
    Gámez, J., J. Mateo and J. Puerta (2011). "Learning Bayesian networks by hill climbing: efficient methods based on progressive restriction of the neighborhood." Data Mining and Knowledge Discovery 22(1): 106-148.
    Giustolisi, O., Z. Kapelan and D. Savic A Hydraulic Simulation Model for Pipe Networks with Leakage Outflows and Pressure-Driven Demands. World Environmental and Water Resources Congress 2007: 1-15.
    Goulet, J.-A., S. Coutu and I. F. C. Smith (2013). "Model falsification diagnosis and sensor placement for leak detection in pressurized pipe networks." Advanced Engineering Informatics 27(2): 261-269.
    Granian, H., S. H. Tabatabaei, H. H. Asadi and E. J. M. Carranza (2015). "Multivariate regression analysis of lithogeochemical data to model subsurface mineralization: a case study from the Sari Gunay epithermal gold deposit, NW Iran." Journal of Geochemical Exploration 148: 249-258.
    Haghighi, A. and H. M. Ramos (2012). "Detection of Leakage Freshwater and Friction Factor Calibration in Drinking Networks Using Central Force Optimization." Water Resources Management 26(8): 2347-2363.
    Heckerman, D. (2008). A Tutorial on Learning with Bayesian Networks: 33-82.
    Heckerman, D., D. Geiger and D. M. Chickering (1995). "Learning Bayesian networks: The combination of knowledge and statistical data." Machine Learning 20(3): 197-243.
    Henrion, M. (1987). Practical Issues in Constructing a Bayes' Belief Network. Proceedings of the Proceedings of the Third Conference Annual Conference on Uncertainty in Artificial Intelligence-UAI-87, New York, NY, Elsevier Science.
    Ho, C.-I., M.-D. Lin and S.-L. Lo (2010). "Use of a GIS-based hybrid artificial neural network to prioritize the order of pipe replacement in a water distribution network." Environmental Monitoring and Assessment 166(1-4): 177-189.
    Hunaidi, O., W. T. Chu, A. Wang and W. Guan (1999). Leak detection methods for plastic water distribution pipes
    AWWA research foundation and American Water Works Association.
    IWSA (1991). Statistics on impact factors of water leakage. IWA Statistics. London, UK: IWSA, International Water Service Association.
    Jasper, M. N., G. K. Mahinthakumar, S. R. Ranjithan and E. D. Brill (2013). A sensitivity analysis of data measurement types for leak detection in water distribution systems. World Environmental and Water Resources Congress 2013: Showcasing the Future, May 19, 2013 - May 23, 2013, Cincinnati, OH, United states, American Society of Civil Engineers (ASCE).
    Jin, Y., W. Yumei and L. Ping (2007). "The genetic-algorithm-enhanced blind system identification for water distribution pipeline leak detection." Measurement Science and Technology 18(7): 2178.
    Karimi-Nasab, M., M. Modarres and S. M. Seyedhoseini (2015). "A self-adaptive PSO for joint lot sizing and job shop scheduling with compressible process times." Applied Soft Computing 27(0): 137-147.
    Katayama, S. and S. Imori (2014). "Lasso penalized model selection criteria for high-dimensional multivariate linear regression analysis." Journal of Multivariate Analysis 132: 138-150.
    Kim, S. and H. Lee (2003). The Leak Detection Method Using GA and HS Algorithm. World Water & Environmental Resources Congress 2003: 1-10.
    Kuo, T. Y. (2014). Taipei water leak statistics. Taipei, Taiwan ROC, Taipei Water Company.
    Kwang, Y. L. and A. E.-S. Mohamed ( 2008). Modern Heuristic Optimization Techniques: Theory and Applications to Power Systems, Wiley-IEEE Press.
    Lee, P. J., M. F. Lambert, A. R. Simpson, J. P. Vítkovsky and D. Misiunas (2007). "Leak location in single pipelines using transient reflections." Australian Journal of Water Resources 11(1): 53-65.
    Leray, P. and O. Francois (2005). Bayesian Network Structural Learning and Incomplete Data. Proceedings of the International and Interdisciplinary Conference on Adaptive Knowledge Representation and Reasoning (AKRR 2005). Espoo, Finland, 2a-ConfInt: 33-40.
    Liang, K.-Y., S. L. Zeger and B. Qaqish (1992). "Multivariate Regression Analyses for Categorical Data." Journal of the Royal Statistical Society. Series B (Methodological) 54(1): 3-40.
    Liang, W., J. Hu, L. Zhang, C. Guo and W. Lin (2012). "Assessing and classifying risk of pipeline third-party interference based on fault tree and SOM." Engineering Applications of Artificial Intelligence 25(3): 594-608.
    Liao, W. and Q. Ji (2009). "Learning Bayesian network parameters under incomplete data with domain knowledge." Pattern Recognition 42(11): 3046-3056.
    Lijuan, W., Z. Hongwei and N. Zhiguang (2012). Leakage Prediction Model Based on RBF Neural Network. Software Engineering and Knowledge Engineering: Theory and Practice. Y. Wu, Springer Berlin Heidelberg. 114: 451-458.
    Mahor, A. and S. Rangnekar (2012). "Short term generation scheduling of cascaded hydro electric system using novel self adaptive inertia weight PSO." International Journal of Electrical Power & Energy Systems 34(1): 1-9.
    Malm, A., F. Moberg, L. Rosén and T. J. R. Pettersson (2015). "Cost-Benefit Analysis and Uncertainty Analysis of Water Loss Reduction Measures: Case Study of the Gothenburg Drinking Water Distribution System." Water Resources Management 29(15): 5451-5468.
    Marsh, W. and G. Bearfield (2008). Representing Parameterised Fault Trees Using Bayesian Networks. Computer Safety, Reliability, and Security: 120-133.
    Montalvo, I., J. Izquierdo, R. Pérez-García and M. Herrera (2010). "Improved performance of PSO with self-adaptive parameters for computing the optimal design of Water Supply Systems." Engineering Applications of Artificial Intelligence 23(5): 727-735.
    Morrison, J., S. Tooms and D. Rogers (2007). District metered areas guidance notes, International Water Association. version 1.
    Mulholland, M., A. Purdon, M. A. Latifi, C. Brouckaert and C. Buckley (2014). "Leak identification in a water distribution network using sparse flow measurements." Computers & Chemical Engineering(0).
    Murphy, K. (2001). "The Bayes Net Toolbox for MATLAB." Computing Science and Statistics 33.
    Nakhkash, M. and M. R. Mahmood-Zadeh (2004). Water leak detection using ground penetrating radar. Proceedings of the Tenth International Conference Ground Penetrating Radar, GPR 2004, June 21, 2004 - June 24, 2004, Delft, Netherlands, Institute of Electrical and Electronics Engineers Inc.
    Nixon, W., M. S. Ghidaoui and A. A. Kolyshkin (2006). Range of Validity of the Transient Damping Leakage Detection Method, ASCE.
    Nixon, W., M. S. Ghidaoui and A. A. Kolyshkin (2006). "Range of Validity of the Transient Damping Leakage Detection Method." Journal of Hydraulic Engineering 132(9): 944-957.
    Oliver, J. (1984). "RECENT DEVELOPMENTS IN LEAK NOISE CORRELATION TECHNIQUES." Water Services 88(1066): 512-513.
    Pearl, J. (1988). Probabilistic reasoning in intelligent systems: networks of plausible inference, Morgan Kaufmann Publishers Inc.
    Pérez, R., J. Blesa, J. Cugueró and R. Sarrate (2014). Network Monitoring: Sensor Placement, Mass Balance and Water Quality, Effinet.
    Pérez, R., V. Puig, J. Pascual, J. Quevedo, E. Landeros and A. Peralta (2011). "Methodology for leakage isolation using pressure sensitivity analysis in water distribution networks." Control Engineering Practice 19(10): 1157-1167.
    Pilcher, R. (2003). "Leak detection practices and techniques: A practical approach." Water 21(DEC.): 44-45.
    Pudar, R. S. and J. A. Liggett (1992). "Leaks in Pipe Networks." Journal of Hydraulic Engineering 118(7): 1031-1046.
    Puust, R., Z. Kapelan, D. Savic and T. Koppel (2006). Probabilistic Leak Detection in Pipe Networks Using the SCEM-UA Algorithm. Water Distribution Systems Analysis Symposium 2006: 1-12.
    Puust, R., Z. Kapelan, D. A. Savic and T. Koppel (2010). "A review of methods for leakage management in pipe networks." Urban Water Journal 7(1): 25-45.
    Romano, N., G. D'Urso, G. Severino, G. B. Chirico, M. Palladino, B. Brunone, M. Ferrante, S. Meniconi and C. Massari (2013). "Four Decades of Progress in Monitoring and Modeling of Processes in the Soil-Plant-Atmosphere System: Applications and ChallengesEffectiveness Assessment of Pipe Systems by Means of Transient Test-based Techniques." Procedia Environmental Sciences 19: 814-822.
    Rosich, A., R. Sarrate and F. Nejjari (2012). "Optimal Sensor Placement for Leakage Detection and Isolation in Water Distribution Networks*." IFAC Proceedings Volumes 45(20): 776-781.
    Rossman, L. A. (2000). EPANET 2 user's manual. National Risk Management Research Laboratory, USEPA, Cincinnati,OH.
    Sarrate, R., J. Blesa and F. Nejjari (2014). Clustering techniques applied to sensor placement for leak detection and location in water distribution networks. Control and Automation (MED), 2014 22nd Mediterranean Conference of.
    Stephens, M., M. Lambert, A. Simpson, J. Vítkovský and J. Nixon Field Tests for Leakage, Air Pocket, and Discrete Blockage Detection Using Inverse Transient Analysis in Water Distribution Pipes. Critical Transitions in Water and Environmental Resources Management: 1-10.
    Tungadio, D. H., B. P. Numbi, M. W. Siti and A. A. Jimoh (2015). "Particle swarm optimization for power system state estimation." Neurocomputing 148: 175-180.
    TWC (2011). Taiwan water corporation report.
    Wai, L. (1998). "Bayesian network refinement via machine learning approach." Pattern Analysis and Machine Intelligence, IEEE Transactions on 20(3): 240-251.
    Weber, P., G. Medina-Oliva, C. Simon and B. Iung (2012). "Overview on Bayesian networks applications for dependability, risk analysis and maintenance areas." Engineering Applications of Artificial Intelligence(0).
    Wu, Z., P. Sage and D. Turtle (2010). "Pressure-Dependent Leak Detection Model and Its Application to a District Water System." Journal of Water Resources Planning and Management 136(1): 116-128.
    Yang, I. T. and Y.-H. Hsieh (2011). "Reliability-based design optimization with discrete design variables and non-smooth performance functions: AB-PSO algorithm." Automation in Construction 20(5): 610-619.

    無法下載圖示 全文公開日期 2021/08/19 (校內網路)
    全文公開日期 本全文未授權公開 (校外網路)
    全文公開日期 本全文未授權公開 (國家圖書館：臺灣博碩士論文系統)
    QR CODE