Drinking water is one of our most important re- sources, so the ability to reliably monitor harmful contaminations in our water distribution network is vital. In order to minimize false alarms for water monitoring, while keeping a high sensitivity, a machine learning approach was evaluated in this project. Measurement data captured with a new kind of sensor, an electronic tongue, was provided by Linköping university. The solution was an artificial neural network, in the structure of an Autoencoder, which could learn the dynamic behaviour of natural deviations and with a false alarm rate of approximately one false alarm per week. This was done by evaluating the data and assembling an input structure to account for daily cyclic phenomena, which then was used to train the neural network. The solution could detect anomalies as small as 1.5% by comparing the input with the reconstructed vector, and raise an alarm. In conclusion, an Autoencoder is a viable method for detecting anomalies in water quality. / Drickvatten är en av våra mest värdefulla tillgångar, det är därför mycket viktigt att det finns sätt att pålitligt övervaka om dricksvattennätet blivit förorenat. För att kunna minimera antalet falsklarm och samtidigt ha hög känslighet mot dessa föroreningar undersöktes och implementerades en lösning med maskininlärningsalgoritmer. Mätdata tillhandahölls av Linköpings universitet och kom från en ny sensor kallad elektronisk tunga. Lösningen var ett artificiellt neuralt nätverk i form av en Autoencoder, som kunde lära sig det dynamiska beteende som ofarliga avvikelser utgjorde. Detta gav en lösning som i medel gav ett falsklarm per sju dagar. Detta gjordes genom att utvärdera rådata och konstruera en struktur på indata som tar hänsyn till dygnsbunda naturliga fenomen. Denna struktur användes sedan för att träna det neurala nätverket. Lösningen kunde upptäcka fel ner till 1.5% genom att jämföra indata med den rekonstruerade vektorn, och på så sätt ge ett alarm. / Kandidatexjobb i elektroteknik 2020, KTH, Stockholm

Management and supply of water in an urban water distribution system is a complex process, which include various complexities like pressure variations across the network depending on topography, demand variations depending on customers’ requirement and unaccounted water etc. Applying automatic control methods to water distribution systems is a way to improve the management of water distribution. There have been some attempts in recent years to develop optimal control algorithms to assist in the operation of complex water distribution systems. The difficulties involved by these hydraulic systems such as non-linearity, and diurnal demand patterns make the choice of a suitable automatic control method a challenge. For this purpose, this study intends to investigate the applicability of different controllers which would be able to meet the targets as quickly as possible and without creating undue transients. As a first step towards application of different controllers, PD and PID linear controllers have been designed for pump control and valve control in water distribution systems. Then a Dynamic Inversion based nonlinear controller has been designed by considering the non-linearities in the system. Here, different cases considering the effects of initial conditions used, linearization methods used, time step used for integration and selection of gains etc., have been studied before arriving at best controller. These controllers have been designed for both the flow control problems and level control problems. It is found that Dynamic Inversion-based nonlinear controller outperforms other controllers. It is well known that the performance of controllers is much dependent on the tuning of the gains (parameters). Thus in this study various alternative techniques such as Ziegler--Nichols rules (ZNPID), Genetic algorithms (GAPID) and fuzzy algorithms (FZPID) have been studied and a comparative study has been made Although with all the three gain tuning methods, required states have reached their target values, but the responses vary much in reaching to final targets. The self-tuned FZPID controller outperforms other two controllers, especially with regard to overshoots and the time taken to tune the gains for each problem. Further, an optimal DI controller is developed for the over determined case with more controls and less targets. Energy loss is considered as an objective function and normal DI controller equations are considered as constraints. Hence, an attempt is made to reduce the energy minimization in water distribution system by formulating an optimal control problem using optimal Dynamic Inversion concept. Finally, leakage reduction model is developed based on excessive pressure minimization problem by locating valves optimally as well as by setting valves optimally. For this purpose, optimization problem is solved using Pattern search algorithms and hydraulic analysis is carried out using EPANET program.

Le but de cette thèse est de modéliser la propagation d’un contaminant au sein d’un réseau d’eau potable muni de capteurs temps réel. Elle comporte les trois axes de développement suivant: la résolution des équations de transport, celle du problème d’identification des sources de contamination et le placement des capteurs.Le transport d’un produit chimique est modélisé dans un réseau d’eau potable par l’équation de transport réaction 1-D avec l’hypothèse de mélange parfait aux noeuds. Il est proposé d’améliorer sa prédiction par l’ajout d’un modèle de mélange imparfait aux jonctions double T et d’un modèle de dispersion prenant en compte un profil de vitesse 3-D et la diffusion radiale. Le premier modèle est créé à l’aide d’un plan d’expériences avec triangulation de Delaunay, de simulations CFD, et de la méthode d’interpolation krigeage. Le second utilise les équations adjointes du problème de transport avec l’ajout de particules évoluant à l’aide d’une marche aléatoire, cette dernière modélisant la diffusion radiale dans la surface droite du tuyau.Le problème d’identification des sources consiste, à l’aide de réponses positives ou négatives à la contamination des noeuds capteurs, à trouver l’origine, le temps d’injection et la durée de la contamination. La résolution de ce problème inverse est faite par la résolution des équations de transport adjointes par formulation backtracking. La méthode donne la liste des sources potentielles ainsi que le classement de celles-ci selon leur probabilité d’être la vraie source de contamination. Elle s’exprime en fonction de combien, en pourcentage, cette source potentielle peut expliquer les réponses positives aux capteurs.Le placement des capteurs est optimisé pour l’identification des sources. L’objectif est la maximisation du potentiel de détection de la véritable source de contamination. Deux résolutions sont testées. La première utilise un algorithme glouton combiné à une méthode de Monte Carlo.La seconde utilise une méthode de recherche locale sur graphe.Finalement les méthodes sont appliquées à un cas test réel avec dans l’ordre : le placement des capteurs, l’identification de la source de contamination et l’estimation de sa propagation. / The aim of this thesis is to model the propagation of a contaminant inside a water distribution network equipped with real time sensors. There are three research directions: the solving of the transport equations, the source identification and the sensor placement. Classical model for transport of a chemical product in a water distribution network isusing 1D-advection-reaction equations with the hypothesis of perfect mixing at junctions. It isproposed to improve the predictions by adding a model of imperfect mixing at double T-junctions and by considering dispersion effect in pipes which takes into account a 3-D velocity profile. The first enhancement is created with the help of a design of experiment based on the Delaunay triangulation, CFD simulations and the interpolation method Kriging. The second one uses the adjoint formulation of the transport equations applied with an algorithm of particle backtracking and a random walk, which models the radial diffusion in the cross-section of a pipe.The source identification problem consists in finding the contamination origin, itsinjection time and its duration from positive and negative responses given by the sensors. The solution to this inverse problem is computed by solving the adjoint transport equations with a backtracking formulation. The method gives a list of potential sources and the ranking of thosemore likely to be the real sources of contamination. It is function of how much, in percentage, they can explain the positive responses of the sensors.The sensor placement is chosen in order to maximize the ranking of the real source of contamination among the potential sources. Two solutions are proposed. The first one uses agreedy algorithm combined with a Monte Carlo method. The second one uses a local search method on graphs. Finally the methods are applied to a real test case in the following order: the sensor placement, the source identification and the estimation of the contamination propagation.

Water distribution systems convey drinking water from treatment plant and make available to consumers’ taps. It consists of essential components like pipes, valves, pumps, tanks and reservoirs etc. The main concern in the working of a water distribution system is to assure customer demands under a choice of quantity and quality throughout the complete life span for the probable loading situations. However, in some cases, the existing infrastructure may not be adequate to meet the customer’s requirements. In such cases, system modeling plays an important role in proper management of water supply systems. In present scenario, modeling plays a significant task in appropriate execution of water distribution system. From the angle of taking management decisions valve throttling control and pumps speed control are very important. These operational problems can be addressed by manual control or by automatic control. The problem is the use of manual controls that slow down the effectiveness of the system. It reduces the efficiency of operation of valve or pump. To improve the efficiency of such water distribution systems, an automatic control based technology has been developed that links the operation of the variable speed pump control or valve throttling control. By employing an automatic control, the pump can adjust its speed at all times to meet the actual flow requirements of each load served. In case of real system design Simulink is the most widely used tool. Commercial software package Matlab/Simulink used for creation of WDS model. The goal was to produce a model that could numerically analyze the dynamic performance of a water distribution system. A Comparison of single platform methodology (Simulink based control) and double platform methodology (Matlab and EPANET based control) has been done. Nonlinear Dynamic Inversion (DI) Control system model is developed for WDS model in Matlab/Simulink environment. Controller gain parameters are the very important value in control prospective. If the controller gain parameters are chosen incorrectly, the controlled process input can be unstable, i.e. its output diverges, with or without oscillation Tuning is the adjustment of control parameters (gains) to the optimum values for the desired control response. There are several methods for tuning controller like manual tuning (Trial and error procedure), Ziegler-Nichols method, Output Constraint Tuning (OCT) etc. Establishment of a pump operational policy by which all the reservoirs can be fed simultaneously to meet their requirements without creating undue transients. Tune the gain of DI controllers by different tuning methods and evaluate the best tuning method on the basis of controller performance. Development of meaningful additional objective is search of lower bound pump speed on the basis of control time or settling time. To bring the pump speeds in feasible range, application of constraint in pumps speed is introduced. The magnitude of constraints can be found using Monte Carlo methods. Monte Carlo methods are frequently used in simulating physical and mathematical systems. This method may be the most commonly applied statistical method in engineering and science disciplines. Another benefit is providing increased confidence that a model is robust using Monte Carlo testing. Model development for generalized control system for water distribution network provides the simplification needed for the simulation of large systems. Model development is based on the study of symmetric and non symmetric small, irregular networks, as well as large, regular and open bifurcating water distribution system. The problem considered in this section is that of flow dynamics in simple to complex, regular network which bifurcates in the form of a branching tree. In addition the control application of the flow network is investigated using valves as the manipulated variables to control branch flow rates. Communication between the network hydraulics coming from EPANET and control algorithm develop on Matlab (Programming Language) can be generalized with the help of development of general purpose control algorithm model.

Drinking water companies have the technology and responsibility to deliver safe and high-quality drinking water to the water distribution systems network (WDN). However, many events within the WDN, such as cross-connections and backflow, might degrade water quality and pose public health risks to consumers. Cross-connection and backflow events may occur if there is physical contact between the external non-potable water source and the drinking water. When the pressure in the external source is greater than in the WDN, and when there are inadequate cross-connections controls, cross-connections and backflows may occur. This project aimed to investigate the circumstances that influence cross-connection and backflow events and estimate the health risk of infection. The method used for this study included hydraulic and water quality modeling EPANET to simulate the fate and transport of pathogens in the WDN during the outbreak. Besides, the quantitative microbial risk assessment QMRA was used to evaluate the health risks associated with cross-connections and backflow events due to ingestion of contaminated water. The modeled events included four reference pathogens (viruses: Norovirus and Rotavirus, bacteria: Campylobacter, and protozoa: Cryptosporidium) from four water types (wastewater, greywater, treated wastewater, and treated greywater). The simulation considered three potential pathogen load risk levels entering WDN: extreme, evaluated, and endemic. The results indicate that the factors that influence pathogen intrusion and consequently the risk of infection were the duration and intensity of the low-pressure event, the location of the cross-connection, and the pathogen concentration in water sources. The estimated daily risk of infection from cross-connection and backflow events generally exceeded the acceptable target level of 10−6 per person per day for all reference pathogens and modeled events. The exception was for the endemic risk level during the cross-connections with treated wastewater and greywater, where the risk was 10−7 and 10−10. Several measures can be implemented to manage and mitigate the risk of cross-connections, such as demanding plumbing installation procedures and backflow prevention devices and developing an early detection system to predict the cross-connection earlier before the outbreak happens to the system, for instance, by applying a machine learning system. / Vattenreningsindustrin har tekniken och ansvaret för att leverera säkert och högkvalitativt dricksvatten till nätverket för vattendistributionssystem (WDN). Däremot många händelser inom WDN, såsom korskopplingar och återflöde, kan försämra vattenkvaliteten och utgöra folkhälsorisker för konsumenterna. Korskoppling och återflödeshändelser kan inträffa om det finns fysisk kontakt mellanden externa vattenkällan för icke dricksvatten och dricksvattnet. När trycket i den externa källan är högre än i WDN, och när det finns otillräckliga korskopplingskontroller, kan korskopplingar och återflöden inträffa. Syftet med detta projekt var att undersöka omständigheterna som påverkar korskopplings- och återflödeshändelser samt uppskatta hälsorisken för infektion. Metoden som användes för denna studie inkluderade hydraulisk och vattenkvalitetsmodellering med EPANET för att simulera transporten och förekomsten av patogener i WDN under utbrottet. Dessutom användes kvantitativ mikrobiell riskbedömning (QMRA) för att utvärdera hälsoriskerna i samband medkorskopplingar och återflödeshändelser på grund av intag av förorenat vatten. De modelleradehändelserna inkluderade fyra referenspatogener (virus: Norovirus och Rotavirus; bakterier:Campylobacter; och protozoer: Cryptosporidium) från fyra vattentyper (avloppsvatten, gråvatten, renatavloppsvatten och renat gråvatten). Simuleringen beaktade tre potentiella patogenbelastningsrisknivåer som kommer in i WDN: extrem, utvärderad och endemisk. Resultaten tyder på att de faktorer som påverkar patogenavbrott och följaktligen risken för infektionvar lågtryckshändelsens varaktighet och omfattning, platsen för korskopplingen och patogenkoncentrationen i vattenkällor. Den uppskattade dagliga risken för infektion från korskopplingoch återflödeshändelser översteg i allmänhet den acceptabla målnivån på 10e6 per person och dag föralla referenspatogener och modellerade händelser. Undantaget var den endemiska risknivån vidkorskopplingarna med renat avloppsvatten och gråvatten, där risken var 10e7 och 10e10. Flera åtgärder kan implementeras för att hantera och minska risken för korskopplingar, såsom atttillämpa krav på installationsprocedurer för VVS och anordningar för att förhindra återflöde samt attutveckla ett system för tidig upptäckt för att förutsäga korskopplingen tidigare innan utbrottet inträffarmed systemet, till exempel genom att tillämpa ett maskininlärningssystem.

Drinking water systems aim to remove, reduce, and prevent microbial contamination in water by usingmultiple barriers from catchments to consumers. Water distribution networks are vulnerable tocontamination from external sources if they lose their physical or hydraulic integrity. The leading causeof intrusion is losing hydraulic integrity due to low pressure in the water distribution networks. Eventsthat lead to low pressure in the water distribution networks can result in transient or sustained lowpressure lasting from milliseconds in a transient to hours and days in sustained low-pressure events.This study studied two sustained low-pressure events with durations of one to five hours, leading tointrusion in the water distribution network. The first event was the pump shut down, and the secondwas the pipe repair. Different durations, start times, and locations were simulated for the pumpshutdown and pipe repair events. Hydraulic and water quality modelling using EPANET 2.2 was usedto simulate low-pressure events and intrusion of microbial contamination in the drinking waterdistribution networks. Quantitative microbial risk assessment (QMRA) was used to estimate potentialpublic health risks using the Swedish QMRA tool. Campylobacter, Norovirus, and Cryptosporidiumwere selected as reference pathogens for simulating intrusion transport within the drinking waternetwork based on their health problem severity, persistence in water supplies, and resistance to chlorinecompound disinfectants. The study area was taken from the virtual network files generated usingHydroGen. This study showed that the volume of intrusion depended on the magnitude but mainly onthe duration of pressure drop. Also, the length of the pipes experiencing pressure drop and the numberof intrusion nodes affected the volume of intrusion. The location and magnitude of maximum nodalpathogen concentration changed significantly by changing the pump shutdown's start time and locationof pipe repair. Generally, the pump shutdown event affected extended areas with low pressure in thewater distribution network than the pipe repair. The QMRA results showed a considerable infection riskin all studied pump shutdown scenarios. The pipe repair duration was crucial in increasing or decreasingthe infection probability. The findings of hydraulic modelling and QMRA could benefit the watermanagers in deciding mitigation strategies.