Download or read book Integrating Data Mining and Transient Modeling for Anomaly Detection and Condition Assessment in Water Distribution Systems written by Lu Xing (Ph. D.) and published by . This book was released on 2021 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: The needs for more resilient, sustainable, and intelligent water distribution systems (WDSs) are becoming increasingly urgent, due to the challenges imposed by rapid urbanization, depleting water resources, infrastructure degradation, and climate change. However, the performance of water systems is often difficult to monitor and model due to the size, complexity, underground location, and the large amount of data needed to fully grasp how systems function. Hydraulic transients in WDSs can disturb the steady-state flow conditions by introducing fast flow changes, imposing abrupt internal pressure forces on pipeline systems, and generating pressure waves that propagate rapidly through piped networks. These disturbances have been identified as one of the major contributing factors to pipe deterioration and catastrophic failure. Complementarily, transient-based approaches are promising in fault detection, condition assessment, and pressure management, because a significant amount of information about the water systems can be revealed during a very short period as the transient wave travels quickly through the piped networks. The goal of this dissertation is to leverage transient modeling, data mining, machine learning, and remote sensing to develop physics-based and data-driven models to achieve high-performance modeling and improve the monitoring capabilities in WDSs. In the context of system monitoring, a two-step time series data mining approach is proposed to extract the patterns, intensity, and frequency from high-resolution pressure data. The proposed approach provides a fast and efficient way to discover the hidden information in WDSs by analyzing high-resolution pressure signals from distributed sensors. From the perspective of physics-based modeling, this dissertation contributed the first open-source Python package, TSNet, for transient modeling in WDSs. TSNet exhibits the capabilities of simulating various transient conditions, including background leaks, pipe bursts, and operational changes in valves and pumps. Moreover, this dissertation proposed an approach for utilizing transient modeling to design distributed sensor networks, such that robust network-wide monitoring can be achieved under data and model uncertainties. The proposed sensor placement strategy addresses the challenge of limited budget, as well as data and modeling uncertainties by incorporating robust representation and tolerance analysis into an optimization framework where the objective is to achieve best detection and identification of all possible events. Finally, this dissertation proposes the graph neural network (GNN) models as a learning-based approach for data assimilation and state estimation in WDSs. In addition to the classical supervised training approach, a semi-supervised training scheme is also formulated to provide a novel paradigm where physical laws and measurement data can be incorporated to improve the training of GNN models. The results demonstrate that the GNN model trained with semi-supervised approach is a promising approach for data assimilation and state estimation in WDSs

Download or read book Drinking Water Distribution Systems written by National Research Council and published by National Academies Press. This book was released on 2006-12-22 with total page 404 pages. Available in PDF, EPUB and Kindle. Book excerpt: Protecting and maintaining water distributions systems is crucial to ensuring high quality drinking water. Distribution systems-consisting of pipes, pumps, valves, storage tanks, reservoirs, meters, fittings, and other hydraulic appurtenances-carry drinking water from a centralized treatment plant or well supplies to consumers' taps. Spanning almost 1 million miles in the United States, distribution systems represent the vast majority of physical infrastructure for water supplies, and thus constitute the primary management challenge from both an operational and public health standpoint. Recent data on waterborne disease outbreaks suggest that distribution systems remain a source of contamination that has yet to be fully addressed. This report evaluates approaches for risk characterization and recent data, and it identifies a variety of strategies that could be considered to reduce the risks posed by water-quality deteriorating events in distribution systems. Particular attention is given to backflow events via cross connections, the potential for contamination of the distribution system during construction and repair activities, maintenance of storage facilities, and the role of premise plumbing in public health risk. The report also identifies advances in detection, monitoring and modeling, analytical methods, and research and development opportunities that will enable the water supply industry to further reduce risks associated with drinking water distribution systems.

Download or read book Integrated Multiple sensor Methodology for Condition Assessment of Water Mains written by Mohamed Fahmy and published by . This book was released on 2009 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: Considerable capital investment has been made in civil infrastructure systems across the globe including water mains. Currently, existing failure detection and location methods do not allow for quick reaction to failures. In addition, no unified standards are followed in condition assessment of water mains. Moreover, the decision by which water mains are inspected is currently carried out based on approximation and experience of decision-makers, which might be limited and may lead to overlooking suitable evaluation methods that might save time, effort and cost. This research presents a methodology that contributes to different phases in the asset management of water mains. It enhances current practice in condition assessment of water mains and assists in setting up rehabilitation priorities. The methodology implemented is based on intensive literature review, evaluation of current methods, field investigation and experiments, and interviews with experts. The methodology considered augments two approaches currently used in condition assessment of water mains, which are proactive and reactive methods. The developed methodology calls for designing a new decision support system (DSS) for selection of most suitable non-destructive evaluation (NDE) method(s). It consists of two components: 1) A Database management system (DBMS), and 2) an evaluation and ranking module (ERM). These NDE methods are used for either detecting suspected leaks or measuring pipe wall thickness, the latter is employed to predict remaining service life of pipe being considered. In case of suspected leaks, this study presents a newly designed automated system for detection of water leaks in underground pipelines and identifying their respective locations. The development of this system is based on using Thermography infrared (IR) camera in order to detect thermal contrast at the pavement surface due to water leaks at the most suitable time. The data obtained is analyzed in order to establish the relationship between the detected leakage area and the approximate location of leak. Prototype software developed in Visual C# environment is implemented in order to determine the location of leaks automatically. Two deterioration models were designed and developed for estimating remaining useful life of water mains, and predicting annual breakage rate of water mains. The development of the two models is based on the analysis of real data collected from 16 municipalities in Canada and the US. The two models were developed considering two approaches, multiple regression analysis and Artificial Neural Networks (ANNs) based on the most suitable subsets of selected factors. The final model was selected due to its reliability and better performance in comparison to other models. The outputs of the deterioration models developed in this research were used, in addition to other deterioration factors that were not considered in existing models in order to develop a Decision Support System (DSS) for generating condition rating scale of water main being considered, and for prioritizing rehabilitation/ maintenance actions. The system is hierarchal in structure, and the condition-rating index is generated using Multi Attributes Utility Theory (MAUT). System validation was carried out by comparing its outcome with real case studies. A prototype software application of the model presented in this research is implemented as a proof of concept to demonstrate the capabilities and essential features of the developed models.

Download or read book Integrated Reliability Assessment of Water Distribution Networks written by Azhar Uddin Mohammed and published by . This book was released on 2016 with total page 183 pages. Available in PDF, EPUB and Kindle. Book excerpt: The condition of current water infrastructure in North America is alarming due to deterioration of old water mains indicating the incompetence of existing water distribution to cope with increasing demands. ASCE (2013) report card graded the drinking water networks a score of D, representing ?poor condition?. In contrast, the Canadian drinking water infrastructure scored better, indicating ?Good: adequate for now?. Despite this, 15.4% of the water distributions are graded ?fair? to ?very poor? with a replacement value of CAD 25.9 billion. Delaying the investment can result in degrading water service, increasing service disruptions, and increasing expenditures for emergency repairs. Taking into account the deterioration severity and investment gap, water utilities need an asset management tool that can effectively prioritize the rehabilitation works. This research is aiming at developing an integrated reliability assessment model that can identify the crucial water main segments and prioritize their renewal at all hierarchical levels of the network. In this regard, the proposed research framework encompasses modeling aspects of mechanical and hydraulic condition of a WDN. The first model analyzes the mechanical condition of a WDN at the component, segment and network levels. This model utilizes reliability theory for assessing component and segment reliabilities, whereas minimum cut set approach is pursued for assessing mechanical reliability of a network. To facilitate this tedious process, it has been coded in MATLAB R2013b programming environment along with the utilization of Wolfram Mathematica 10.2 and Microsoft Excel 2013. The second model analyzes the hydraulic performance of a WDN in terms of hydraulic reliability. It involves the hydraulic simulation of a WDN in normal and failure conditions, which aid in obtaining the required as well as actual pressure head at demand nodes. The model is then formulated with pressure conditions to evaluate the available demand at demand nodes which in contrast to the required demand aids in predicting the hydraulic reliability of the network. Finally, an integrated reliability assessment model is presented to conclude the research methodology by determining the overall sub-network reliability. The developed methodology is worked out on two case studies from the cities of London, Ontario and Doha, Qatar. Also, it is implemented on two different sub-networks from the City of London (north phase and south phase) for drawing comparisons, which concluded that the mechanical reliability of a network encompassed by newer components with less number of failures is greater than that of other networks. Additionally, the results of model implementation revealed that structure/configuration of the network also played an important role in affecting the overall network reliability. It was found 0.82 for the north phase sub-network and 0.84 for the south phase indicating that the south phase sub-network is more reliable. Therefore, the north phase sub-network takes the priority when scheduling the rehabilitation. The resulting reliability indices of a WDN, helps the municipalities to effectively prioritize the rehabilitation works at respective hierarchical levels. Moreover, the outcomes of this research also aid in identifying the most critical water main segments that need to be monitored constantly in order to prevent the network failure.

Download or read book Failure Rate Prediction Models of Water Distribution Networks written by Seyed Farzad Karimian and published by . This book was released on 2016 with total page 148 pages. Available in PDF, EPUB and Kindle. Book excerpt: The economic, social and environmental impacts of water main failures impose a great pressure on utility managers and municipalities to develop reliable rehabilitation/replacement plans. The Canadian Infrastructure Report Card 2012 stated that 15.4% of Canadian water distribution systems was in a ?fair? to ?very poor? condition with a replacement cost of CAD 25.9 billion. The ?fair?, ?poor? and ?very poor? conditions represent the beginning of deterioration, nearing the end of useful life and no residual life expectancy, respectively. The majority of municipalities in Canada do not possess complete dataset of water distribution networks. The annual number of breaks or breakage rate of each pipe segment is known as one of the most important criteria in condition assessment of water pipelines. The main objective of this research is to develop a research framework that circumvent the limitations of existing studies by: 1) identifying the most critical factors affecting water pipe failure rates, 2) determining the best mathematical expression for predicting water pipeline failure rate 3) developing deterioration curves, and 4) deploying sensitivity analysis to recognize the effect of each input change on the breakage rate. The proposed research framework utilizes Best Subset regression to recognize the most effective factors on water pipelines. Best-Subset Algorithm is a procedure to find the best combination of variables to predict the water pipe failure rate among all possible candidates. Once the process of critical factor selection is performed, selected variables are employed to predict the number of breaks of water pipes using Evolutionary Polynomial Regression (EPR). The EPR is an intuitive data mining technique performed in two stages: 1) the search for the best model using Multi-Objective Genetic Algorithm (MOGA), and 2) the parameter estimation for the model using Least Square Method. The predicted number of breaks, computed by EPR, is utilized to develop deterioration curves by applying Weibull distribution function. Finally, sensitivity analysis is performed to: 1) recognize the effect of changing each input on the failure rate, and 2) study the relationship between the selected inputs and the output. The developed research framework is applied into two case studies to test its effectiveness. The case considers the water distribution networks in the City of Montréal, Canada and the City of Doha, Qatar. Physical factors, such as age, length, diameter and pipe material were identified as the most critical factors to affect the failure rate of pipes. The results indicate that the developed models successfully estimated the number of breaks for the City of Montreal and City of Doha with a maximum R-Squared of 89.35% and 96.27%, respectively. Also, it is tested by using 20% of each dataset and promising results were generated with a maximum R-Squared of 84.86% and 74.39% for dataset of Montreal and Doha respectively. This demonstrates the accuracy and robustness of the developed models in assessing and analyzing water distribution networks. The developed model is useful for municipalities and decision makers to prioritize the maintenance, repair, rehabilitation, and budget allocation of water distribution networks.

Download or read book Data driven modeling based Sensor Placement for the Detection and Identification of Failures in Cyber Physical Water Distribution Networks written by Utsav Parajuli and published by . This book was released on 2023 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: The advance in Information and Communication Technology (ICT) has led to the transition of conventional water supply systems into water cyber-physical systems (CPSs). The water CPSs consist of the Supervisory Control and data acquisition (SCADA) system, making it vulnerable to various cyber-physical intrusions. In addition, water CPSs routinely experience anomalies from other conventional physical and operational failures. Although several data-driven methods have been created and validated for detecting a specific, single failure type, a comprehensive framework to distinguish and identify the failure type from other various types of possible failures is needed. In this context, this thesis addresses the following questions: 1) can the existing data-driven machine learning models contribute to the descriptive classification of failure types?; 2) is a sensor placement created for identifying a certain failure type also effective in identifying other failure types?; 3) does the sensor placement that is selected optimally for a particular failure type provide good performance for real world data under the data noise?. To find the answers and test the corresponding hypotheses, this study presents sensor placement with an integrated framework of unsupervised and supervised data-driven models for failure detection and identification. The integrated framework is applied to C-town WDN. As the first part, the integrated framework is designed as the combination of a deep learning autoencoder (AE) model and supervised multiclass classification models - Support Vector Machine (SVM), Random Forest (RF), and Artificial Neural Networks (ANN). The AE model is used for training the normal dataset with continuous SCADA features to detect unknown failures based on the threshold of the reconstruction error. This AE model showed acceptable performance to detect anomalies occurring from a certain failure event among various types. In identifying and differentiating the failure event among various types, SVM model demonstrated the best performance among three supervised failure identification models- SVM, RF, and ANN. As the second part, this study proposed a feature selection approach for the integrated failure detection/identification framework in the first part, which suggests the best sensor placement strategy for classification-based failure identification in a water CPS. The approach adopts a wrapper-based feature selection method that employs recursive feature elimination (RFE) with an RF classifier for feature selection. The performance of sensor placement options in failure detection and identification is evaluated using deep learning (AE) feature extraction followed by a RF model. The primary finding indicated that the best sensor option targeting a certain, single failure type shows a little bit lower performance in differentiating a failure event from various types. This provides useful insights to engineer water CPSs' sensor placement strategies to detect, identify, and differentiate a failure event from various possible failure events. Also, the findings suggested that the performance of the integrated framework for failure identification has better performance under data noise when the embedded data-driven models are trained by realistic failure datasets including data noise.

Download or read book Transient Response Analysis for Fault Detection and Pipeline Wall Condition Assessment in Field Water Transmission and Distribution Pipelines and Networks written by Mark Leslie Stephens and published by . This book was released on 2008 with total page 716 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Modeling and Optimization of Transients in Water Distribution Networks with Intermittent Supply written by Anna Marie Lieb and published by . This book was released on 2016 with total page 133 pages. Available in PDF, EPUB and Kindle. Book excerpt: Much of the world's rapidly growing urban population relies upon water distribution systems to provide treated water through networks of pipes. Rather than continuously supplying water to users, many of these distribution systems operate intermittently, with parts of the network frequently losing pressure or emptying altogether. Such intermittent water supply deleteriously impacts water availability, infrastructure, and water quality for hundreds of millions of people around the world. In this work I introduce the problem of intermittent water supply through the lens of applied mathematics. I first introduce a simple descriptive mathematical model that captures some hydraulic features of intermittency not accounted for by existing water distribution system software packages. I then consider the potential uses of such a model in a variety of optimization examples motivated by real-world applications. In simple test networks, I show how to reduce pressure gradients while the network fills by changing either the inflow patterns or the elevation profile. I also show test examples of using measured data to potentially recover unknown information such as initial conditions or boundary outflows. I then use sensitivity analysis to better understand how various parameters control model output, with an eye to figuring out which parameters are worth measuring most carefully in field applications, and also which parameters may be useful in an optimization setting. I lastly demonstrate some progress in descriptively modeling a real network, both through the introduced mathematical model and through a fluid-mechanics-based method for identifying data where the model is most useful.

Download or read book Spatial Data Analysis of Networked Infrastructure Failure Data written by Daniel Pinho de Oliveira and published by . This book was released on 2010 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Failure Monitoring and Asset Condition Assessment in Water Supply Systems written by Dalius Misiunas and published by . This book was released on 2005 with total page 331 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Leak Detection written by Stuart Hamilton and published by IWA Publishing. This book was released on 2013-06-30 with total page 106 pages. Available in PDF, EPUB and Kindle. Book excerpt: Ageing infrastructure and declining water resources are major concerns with a growing global population. Controlling water loss has therefore become a priority for water utilities around the world. In order to improve efficiencies, water utilities need to apply good practices in leak detection. Leak Detection: Technology and Implementation assists water utilities with the development and implementation of leak detection programs. Leak detection and repair is one of the components of controlling water loss. In addition, techniques are discussed within this book and relevant case studies are presented. This book provides useful and practical information on leakage issues.

Download or read book Losses in Water Distribution Networks written by M. Farley and published by IWA Publishing. This book was released on 2003-03-31 with total page 297 pages. Available in PDF, EPUB and Kindle. Book excerpt: This is a best practice manual for addressing water losses in water distribution networks worldwide. Systems and methodologies are presented for improving water loss and leakage management in a range of networks, from systems with a well-developed infrastructure to those in developing countries where the network may need to be upgraded. The key feature of the manual is a diagnostic approach to develop a water loss strategy - using the appropriate tools to find the right solutions - which can be applied to any network. The methods of assessing the scale and volume of water loss are outlined, together with the procedures for setting up leakage monitoring and detection systems. As well as real losses (leakage) procedures for addressing apparent losses, by introducing regulatory and customer metering policies are explained. Suggestions are made for demand management and water conservation programmes, to complement the water loss strategy. Recommendations are made for training workshops and operation and maintenance programmes to ensure skills transfer and sustainability. The manual is illustrated throughout with case studies. Losses in Water Distribution Networks will appeal to a wide range of practitioners responsible for designing and managing a water loss strategy. These include consultants, operations managers, engineers, technicians and operational staff. It will also be a valuable reference for senior managers and decision makers, who may require an overview of the principles and procedures for controlling losses. The book will also be suitable as a source document for courses in Water Engineering, Resource Management and Environmental Management.

Download or read book Analysis of Water Distribution Networks written by Pramod R. Bhave and published by Alpha Science Int'l Ltd.. This book was released on 2006 with total page 548 pages. Available in PDF, EPUB and Kindle. Book excerpt: Analysis of a Water Distribution Network may be necessary to know its behaviour under normal and deficient conditions and the design of a new network. Various methods such as Hardy Cross, Newton-Raphson, Linear Theory, and Gradient for static and time-dependent (extended period) analyses are described with small illustrative examples. The book also covers analysis considering withdrawal along links, head-dependent and performance-based analyses, calibration of existing networks, water quality modeling, analysis considering uncertainty of parameters, and reliability analysis of water distribution networks. Brief description of available computer softwares is also given.

Download or read book Beginning Anomaly Detection Using Python Based Deep Learning written by Sridhar Alla and published by Apress. This book was released on 2019-10-10 with total page 427 pages. Available in PDF, EPUB and Kindle. Book excerpt: Utilize this easy-to-follow beginner's guide to understand how deep learning can be applied to the task of anomaly detection. Using Keras and PyTorch in Python, the book focuses on how various deep learning models can be applied to semi-supervised and unsupervised anomaly detection tasks. This book begins with an explanation of what anomaly detection is, what it is used for, and its importance. After covering statistical and traditional machine learning methods for anomaly detection using Scikit-Learn in Python, the book then provides an introduction to deep learning with details on how to build and train a deep learning model in both Keras and PyTorch before shifting the focus to applications of the following deep learning models to anomaly detection: various types of Autoencoders, Restricted Boltzmann Machines, RNNs & LSTMs, and Temporal Convolutional Networks. The book explores unsupervised and semi-supervised anomaly detection along with the basics of time series-based anomaly detection. By the end of the book you will have a thorough understanding of the basic task of anomaly detection as well as an assortment of methods to approach anomaly detection, ranging from traditional methods to deep learning. Additionally, you are introduced to Scikit-Learn and are able to create deep learning models in Keras and PyTorch. What You Will LearnUnderstand what anomaly detection is and why it is important in today's world Become familiar with statistical and traditional machine learning approaches to anomaly detection using Scikit-Learn Know the basics of deep learning in Python using Keras and PyTorch Be aware of basic data science concepts for measuring a model's performance: understand what AUC is, what precision and recall mean, and more Apply deep learning to semi-supervised and unsupervised anomaly detection Who This Book Is For Data scientists and machine learning engineers interested in learning the basics of deep learning applications in anomaly detection

Download or read book Data Analytics in Reservoir Engineering written by Sathish Sankaran and published by . This book was released on 2020-10-29 with total page 108 pages. Available in PDF, EPUB and Kindle. Book excerpt: Data Analytics in Reservoir Engineering describes the relevance of data analytics for the oil and gas industry, with particular emphasis on reservoir engineering.

Download or read book AI and Learning Systems written by Konstantinos Kyprianidis and published by BoD – Books on Demand. This book was released on 2021-02-17 with total page 274 pages. Available in PDF, EPUB and Kindle. Book excerpt: Over the last few years, interest in the industrial applications of AI and learning systems has surged. This book covers the recent developments and provides a broad perspective of the key challenges that characterize the field of Industry 4.0 with a focus on applications of AI. The target audience for this book includes engineers involved in automation system design, operational planning, and decision support. Computer science practitioners and industrial automation platform developers will also benefit from the timely and accurate information provided in this work. The book is organized into two main sections comprising 12 chapters overall: •Digital Platforms and Learning Systems •Industrial Applications of AI

Download or read book The Regional Impacts of Climate Change written by Intergovernmental Panel on Climate Change. Working Group II. and published by Cambridge University Press. This book was released on 1998 with total page 532 pages. Available in PDF, EPUB and Kindle. Book excerpt: Cambridge, UK : Cambridge University Press, 1998.