Artificial intelligence for the modeling of water pipes deterioration mechanisms

Abstract Water pipes deterioration modeling has been a prevalent research topic in the last two decades due to high water break incidents and contamination rates. Failure processes are de facto very intricate to be diagnosed since there is a time lag between the failure incidence and consequences. Artificial intelligence (A.I.) techniques have gained much momentum during the last two decades, specifically for the deterioration modeling and assessment of water distribution networks. However, a comprehensive critical review on water infrastructure modeling via artificial intelligence and machine learning techniques is missing in the literature. This paper aims to bridge the gap in the body of knowledge and address the aforementioned limitations. The intellectual contributions of this paper are twofold. First, a comprehensive literature review method is presented through sequential steps that systematize and synthesize the literature in a scientific way. The state-of-the-art of AI-based deterioration modeling for urban water systems is revealed along with models' methodologies, contributions, drawbacks, comparisons, and critiques. Second, future research directions and challenges are recommended to assist the construction automation research community in setting a vibrant agenda for the upcoming years.

[1]  Agathoklis Agathokleous,et al.  Risk-based asset management of water piping networks using neurofuzzy systems , 2009, Comput. Environ. Urban Syst..

[2]  Shaoqing Ge,et al.  Failure Analysis, Condition Assessment Technologies, and Performance Prediction of Prestressed-Concrete Cylinder Pipe: State-of-the-Art Literature Review , 2014 .

[3]  Tarek Zayed,et al.  Integrated performance assessment model for water distribution networks , 2016 .

[4]  Stewart Burn,et al.  LEAK DETECTION IN SIMULATED WATER PIPE NETWORKS USING SVM , 2012, Appl. Artif. Intell..

[5]  Dragan Savic,et al.  Assessing pipe failure rate and mechanical reliability of water distribution networks using data-driven modeling , 2009 .

[6]  Resul Kara,et al.  Leakage detection and localization on water transportation pipelines: a multi-label classification approach , 2017, Neural Computing and Applications.

[7]  Richard Mounce,et al.  Novelty detection for time series data analysis in water distribution systems using support vector machines , 2011 .

[8]  Osama Moselhi,et al.  Assessment of Remaining Useful Life of Pipelines Using Different Artificial Neural Networks Models , 2016 .

[9]  Do-Hyeun Kim,et al.  Underground Risk Index Assessment and Prediction Using a Simplified Hierarchical Fuzzy Logic Model and Kalman Filter , 2018 .

[10]  J. Klein,et al.  Survival Analysis: Techniques for Censored and Truncated Data , 1997 .

[11]  S. Yannopoulos,et al.  Water Distribution System Reliability Based on Minimum Cut – Set Approach and the Hydraulic Availability , 2013, Water Resources Management.

[12]  Lotfi A. Zadeh,et al.  Soft computing and fuzzy logic , 1994, IEEE Software.

[13]  Osama Moselhi,et al.  Forecasting the Remaining Useful Life of Cast Iron Water Mains , 2009 .

[14]  Zong Woo Geem,et al.  A New Heuristic Optimization Algorithm: Harmony Search , 2001, Simul..

[15]  Rehan Sadiq,et al.  Modeling failure risk in buried pipes using fuzzy Markov deterioration process , 2019 .

[16]  Balvant Rajani,et al.  Comprehensive review of structural deterioration of water mains: statistical models , 2001 .

[17]  Tarek Zayed,et al.  Condition Rating Model for Underground Infrastructure Sustainable Water Mains , 2006 .

[18]  Tarek Zayed,et al.  Computer Vision-Based Model for Moisture Marks Detection and Recognition in Subway Networks , 2018, J. Comput. Civ. Eng..

[19]  Balvant Rajani,et al.  Comprehensive review of structural deterioration of water mains: physically based models , 2001 .

[20]  Zheng Liu,et al.  State of the art review of inspection technologies for condition assessment of water pipes , 2013 .

[21]  Homayoun Najjaran,et al.  Leakage detection and location in water distribution systems using a fuzzy-based methodology , 2011 .

[22]  Christos Makropoulos,et al.  A neurofuzzy spatial decision support system for pipe replacement prioritisation , 2005 .

[23]  Massoud Tabesh,et al.  A comparison between performance of support vector regression and artificial neural network in prediction of pipe burst rate in water distribution networks , 2014, KSCE Journal of Civil Engineering.

[24]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[25]  Ahmed Osama,et al.  Fuzzy-Based Methodology for Integrated Infrastructure Asset Management , 2017, Int. J. Comput. Intell. Syst..

[26]  Do-Hyeun Kim,et al.  A Blended Risk Index Modeling and Visualization Based on Hierarchical Fuzzy Logic for Water Supply Pipelines Assessment and Management , 2018 .

[27]  Zheng Yi Wu,et al.  Leakage Zone Identification in Large-Scale Water Distribution Systems Using Multiclass Support Vector Machines , 2016 .

[28]  Symeon E. Christodoulou,et al.  A Risk Analysis Framework for Evaluating Structural Degradation of Water Mains in Urban Settings, Using Neurofuzzy Systems and Statistical Modeling Techniques , 2003 .

[29]  Tarek Zayed,et al.  Infrastructure Management : Integrated AHP/ANN Model to Evaluate Municipal Water Mains' Performance , 2008 .

[30]  Eslam Mohammed Abdelkader,et al.  An accelerometer-based leak detection system , 2018 .

[31]  Marc Parizeau,et al.  Multiobjective Approach for Pipe Replacement Based on Bayesian Inference of Break Model Parameters , 2009 .

[32]  Stewart Burn,et al.  An Approach to Leak Detection in Pipe Networks Using Analysis of Monitored Pressure Values by Support Vector Machine , 2009, 2009 Third International Conference on Network and System Security.

[33]  Małgorzata Kutyłowska,et al.  Comparison of Two Types of Artificial Neural Networks for Predicting Failure Frequency of Water Conduits , 2016 .

[34]  Emad Elwakil,et al.  Water pipe failure prediction and risk models: state-of-the-art review , 2020 .

[35]  Zhigang Tian,et al.  A review on pipeline integrity management utilizing in-line inspection data , 2018, Engineering Failure Analysis.

[36]  Małgorzata Kutyłowska,et al.  Neural network approach for failure rate prediction , 2015 .

[37]  Agnieszka Malinowska,et al.  Fuzzy inference-based approach to the mining-induced pipeline failure estimation , 2017, Natural Hazards.

[38]  Yi Zhang,et al.  Fuzzy-Based Robustness Assessment of Buried Pipelines , 2018 .

[39]  Ömer Faruk Ertuğrul,et al.  A Detailed Analysis on Extreme Learning Machine and Novel Approaches Based on ELM , 2015 .

[40]  Ahmad Asnaashari,et al.  Forecasting watermain failure using artificial neural network modelling , 2013 .

[41]  Andrew J. Day,et al.  Sensor-fusion of hydraulic data for burst detection and location in a treated water distribution system , 2003, Inf. Fusion.

[42]  Mohammad Karamouz,et al.  Pressure Management Model for Urban Water Distribution Networks , 2010 .

[43]  Karim Salahshoor,et al.  Multiphase Pipeline Leak Detection Based on Fuzzy Classification , 2009 .

[44]  H. Najjaran,et al.  A fuzzy expert system for deterioration modeling of buried metallic pipes , 2004, IEEE Annual Meeting of the Fuzzy Information, 2004. Processing NAFIPS '04..

[45]  T. Dawood,et al.  A Contamination Risk Model for Water Distribution Networks , 2019 .

[46]  Mahmut Firat,et al.  Estimation of Failure Rate in Water Distribution Network Using Fuzzy Clustering and LS-SVM Methods , 2015, Water Resources Management.

[47]  Alison M. St. Clair,et al.  State-of-the-technology review on water pipe condition, deterioration and failure rate prediction models! , 2012 .

[48]  H. C. W. Lau,et al.  A fuzzy-based decision support model for engineering asset condition monitoring - A case study of examination of water pipelines , 2011, Expert Syst. Appl..

[49]  Tarek Zayed,et al.  Hierarchical Fuzzy Expert System for Risk of Failure of Water Mains , 2010 .

[50]  Homayoun Najjaran,et al.  Condition assessment of water mains using fuzzy evidential reasoning , 2005, 2005 IEEE International Conference on Systems, Man and Cybernetics.

[51]  Isam Shahrour,et al.  Application of Artificial Neural Networks (ANN) to model the failure of urban water mains , 2010, Math. Comput. Model..

[52]  Dongwoo Jang,et al.  Estimation of Leakage Ratio Using Principal Component Analysis and Artificial Neural Network in Water Distribution Systems , 2018 .

[53]  Kerry J. McManus,et al.  Prediction of Water Pipe Asset Life Using Neural Networks , 2007 .

[54]  Francesco Archetti,et al.  Analytical Leakages Localization in Water Distribution Networks through Spectral Clustering and Support Vector MACHINES. The Icewater Approach , 2014 .

[55]  Bilal Siddiqui,et al.  Measurement error sensitivity analysis for detecting and locating leak in pipeline using ANN and SVM , 2014, 2014 IEEE 11th International Multi-Conference on Systems, Signals & Devices (SSD14).

[56]  Solomon Tesfamariam,et al.  Possibilistic approach for consideration of uncertainties to estimate structural capacity of ageing cast iron water mains , 2006 .

[57]  Shang-Lien Lo,et al.  Use of a GIS-based hybrid artificial neural network to prioritize the order of pipe replacement in a water distribution network , 2010, Environmental monitoring and assessment.

[58]  Rehan Sadiq,et al.  Fuzzy-Based Method to Evaluate Soil Corrosivity for Prediction of Water Main Deterioration , 2004 .

[59]  Juhwan Kim,et al.  Trenchless Water Pipe Condition Assessment Using Artificial Neural Network , 2007 .

[60]  Yves Filion,et al.  State-of-the-art review of water pipe failure prediction models and applicability to large-diameter mains , 2017 .

[61]  Jiheon Kang,et al.  Novel Leakage Detection by Ensemble CNN-SVM and Graph-Based Localization in Water Distribution Systems , 2018, IEEE Transactions on Industrial Electronics.

[62]  Bahram Gharabaghi,et al.  Extreme learning machine model for water network management , 2017, Neural Computing and Applications.

[63]  E. Kaplan,et al.  Nonparametric Estimation from Incomplete Observations , 1958 .

[64]  Tarek Zayed,et al.  Risk Assessment for Water Mains Using Fuzzy Approach , 2009 .

[65]  NishiyamaMichael,et al.  Review of statistical water main break prediction models , 2013 .

[66]  Symeon E. Christodoulou,et al.  A Neurofuzzy Decision Framework for the Management of Water Distribution Networks , 2010 .

[67]  Suzhen Li,et al.  Leak detection of water distribution pipeline subject to failure of socket joint based on acoustic emission and pattern recognition , 2018 .

[68]  Saleh M. Amaitik,et al.  DEVELOPMENT OF PCCP WIRE BREAKS PREDICTION MODEL USING ARTIFICIAL NEURAL NETWORKS , 2008 .

[69]  Bahram Gharabaghi,et al.  Predicting the Timing of Water Main Failure Using Artificial Neural Networks , 2014 .

[70]  Kamil Kamiński,et al.  Application of Artificial Neural Networks to the Technical Condition Assessment of Water Supply Systems , 2017 .

[71]  Emad Elwakil.  Integrating AHP-Fuzzy Model for Assessing Construction Organizations’ Performance , 2016 .

[72]  Jayantha Kodikara,et al.  Prediction of stress concentration factor of corrosion pits on buried pipes by least squares support vector machine , 2015 .

[73]  Zheng Liu,et al.  State-of-the-Art Review of Technologies for Pipe Structural Health Monitoring , 2012, IEEE Sensors Journal.

[74]  Sunil K. Sinha,et al.  Development and the Comparison of a Weighted Factor and Fuzzy Inference Model for Performance Prediction of Metallic Water Pipelines , 2011 .

[75]  Michael Burrow,et al.  Condition assessment of the buried utility service infrastructure , 2012 .

[76]  Symeon E. Christodoulou,et al.  Proactive Risk-Based Integrity Assessment of Water Distribution Networks , 2010 .

[77]  Abdelwahab M. Bubtiena,et al.  Application of Artificial Neural networks in modeling water networks , 2011, 2011 IEEE 7th International Colloquium on Signal Processing and its Applications.

[78]  R. Sadiq,et al.  Water Quality Failures in Distribution Networks—Risk Analysis Using Fuzzy Logic and Evidential Reasoning , 2007, Risk analysis : an official publication of the Society for Risk Analysis.

[79]  Sunil K. Sinha,et al.  Development of a Fuzzy Inference Performance Index for Ferrous Drinking Water Pipelines , 2014 .