Despite various breakthroughs of machine learning and data analysis techniques for improving smar... more Despite various breakthroughs of machine learning and data analysis techniques for improving smart operation and management of urban water infrastructures, some key limitations obstruct this progress. Among these shortcomings, the absence of freely available data due to data privacy or high costs of data gathering and the nonexistence of adequate rare or extreme events in the available data plays a crucial role. Here, the Generative Adversarial Networks (GANs) can help overcome these challenges. In machine learning, generative models are a class of methods capable of learning data distribution to generate artificial data. In this study, we developed a GAN model to generate synthetic time series to balance our limited recorded time series data and improve the accuracy of a data-driven model for combined sewer flow prediction. We considered the sewer system of a small town in Germany as the test case. Precipitation and inflow to the storage tanks are used for the Data-Driven model development. The aim is to predict the flow using precipitation data and examine the impact of data augmentation using synthetic data in model performance. Results show that GAN can successfully generate synthetic time series from real data distribution, which helps more accurate peak flow prediction. However, the model without data augmentation works better for dry weather prediction. Therefore, an ensemble model is suggested to combine the advantages of both models.
The rapid population growth and urban development have notably influenced the role of water distr... more The rapid population growth and urban development have notably influenced the role of water distribution networks (WDNs) compared to the past. This issue encourages operators to adopt new smart tools to better system management. Such a smart system is expected to play an effective role in both crisis and normal services. For fire extinguishing services, a WDN needs to be well-equipped to supply the fire flow efficiently. In this sense, WDNs are required not only modern fire-fighting equipment but also a systematic program to satisfy the fire demand in the right place at the right time. This paper aims at introducing a pre-processing (not real-time) approach for smart pressure management using the regulation of control valves. The problem is formulated as a mathematical programing in which the reliability measure is maximized and the valve opening positions are decision variables. Using a self-adaptive Genetic Algorithm coupled with EPANET, the problem is solved. The proposed algorithm is applied to a case study from the literature and produces the optimum pattern for regulation of valves. Such results can be an appropriate guide for operators to practically maneuver valves in fire situation. The case study manifests that by applying the model the reliability of system can be increased up to 40.7%.
Allocation is the number-one cause of conflict in water resources, whether betweensovereign natio... more Allocation is the number-one cause of conflict in water resources, whether betweensovereign nations, different user groups or neighboring basins. The inter-basin watertransfer is a remedy to the negative issues of water shortage in drought-stricken regions. Ina water transfer project, the receiving basin always benefits while the donor basin maysuffer. In this work, to define an operating policy, a multi-reservoir multi-purpose system issimulated and optimized for a set of long-term historical records. A multi-objectiveoptimization model is developed based on Non-Dominated Sorting Genetic Algorithm(NSGA-II). The optimization results define the best possible performance set for a twobasinsystem with the objectives of supplied water shortage minimization during droughts.In a multi-objective optimization problem, there is not a single solution that simultaneouslyoptimizes all objectives. However, decision makers are concerned with finding a uniquecompromise solution that balances confl...
Flood impact assessment in a river system is done with the help of flood routing and this process... more Flood impact assessment in a river system is done with the help of flood routing and this process helps to determine the status of sensitive points of the route in terms of flood entry and the resulting risks for urban and rural areas. For flood routing, a hydrodynamic numerical model should be implemented and this model needs upstream and downstream boundaries. In some cases, the upstream boundary, which is usually a hydrograph, is not available due to the lack of facilities and it is necessary to be generated for numerical model implementation. The purpose of this study is to present an integrated method comprising an optimization model and a hydrodynamic numerical model for flood modeling in order to determine the upstream hydrograph using the measured downstream hydrograph along a river. The routing procedure consists of three steps: (1) generating a hypothetical upstream hydrograph using the genetic algorithm method; (2) hydrodynamic modeling using a numerical simulation model ...
This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.
Flood routing in flood forecasting issue, calculation the height of flood bands, determining the ... more Flood routing in flood forecasting issue, calculation the height of flood bands, determining the river boundaries, and estimation of protective facilities for flood –exposed building is applicable. In many cases, due to the lack of measuring stations, the status of the upstream flood generating hydrograph is not known. The purpose of this study is to present an integrated method comprising of an optimization model and a hydrodynamic numerical model for flood modeling to determine the upstream hydrograph using the provided hydrograph at the downstream measuring station of a river. The routing procedure consists of three steps: (1) generating a hypothetical upstream hydrograph using genetic algorithm method; (2) hydrodynamic modeling using a numerical simulation model for flood routing according to the hypothetical hydrograph which is generated in the first step; (3) compare the calculated and observed hydrograph in downstream by using a fitness function. This recommended procedure wa...
This paper introduces a methodology for soil slope stability analysis based on optimization, limi... more This paper introduces a methodology for soil slope stability analysis based on optimization, limit equilibrium principles and method of slices. In this study, the slope stability analysis problem is transformed into a constrained nonlinear optimization problem. To solve that, a Self-Adaptive Genetic Algorithm (GA) is utilized. In this study, the slope stability safety factors are the objective functions, slip surface parameters are the decision variables and, the equilibrium equations are the problem constraints. The proposed model satisfies all conditions of the equilibrium completely. It is also applicable to problems with different soil layers, variable soil properties and including pore water pressure. The model is applied against a benchmark example and the results are compared with previous studies. Accordingly, it is found computationally efficient and reliable.
Forecasting precipitation is a crucial input to hydrological models and hydrological event manage... more Forecasting precipitation is a crucial input to hydrological models and hydrological event management. Accurate forecasts minimize the impact of extreme events on communities and infrastructure by providing timely and reliable information. In this study, six artificial intelligent hybrid models are developed to predict daily rainfall in urban areas by combining the firefly optimization algorithm (FA), invasive weed optimization algorithm (IWO), genetic particle swarm optimization algorithm (GAPSO), neural network (ANN), group method of data handling (GMDH), and wavelet transformation. Optimization algorithms increase forecasting accuracy by controlling all stages. A variety of criteria are used for validating the models, including correlation coefficient (R), root-mean-square error (RMSE), mean absolute error (MAE), critical success index (CSI), probability of detection (POD), and false alarm ratio (FAR). The proposed models are also evaluated in an urban area in Ahvaz, Iran. The GA...
Journal of Water Supply: Research and Technology - Aqua, 2017
Transient protection is an important issue in pipeline design. As protective devices impose a hug... more Transient protection is an important issue in pipeline design. As protective devices impose a huge cost on the project, it is better and more efficient to use optimization models for determination of their position and type with the aim of cost reduction. Except for the cost, the other important issue in obtaining the number and locating of protective devices is the consideration of important operational parameters during the utilization of the pipelines. This paper introduces a new objective function called 'serviceability factor' for achieving the best layout for protection devices by considering five main operational parameters. A double-objective model has been used to optimize the protective devices to obtain the minimum of cost and the most appropriate level of operational parameters. The presented model utilizes the non-dominated sorting genetic algorithm (NSGAII) simultaneously with transient analysis through the method of characteristics. A real pipeline has been optimized using this model and the results are presented in the form of Pareto optimal solutions.
Journal of Water Resources Planning and Management, 2021
This study aims to introduce a generic solution in the context of a multicriteria decision making... more This study aims to introduce a generic solution in the context of a multicriteria decision making (MCDM) platform to (1) facilitate the optimization of hybrid (de)centralized urban drainage infrastructures with many decisions and often conflicting objectives (reliability, resilience, sustainability, and construction costs); (2) investigate the trade-offs between performance indicators and system configuration; and (3) avoid conflicts between optimization analysts and decision makers by involving the latter in different stages of planning. For this purpose, first, all optimum design scenarios of hybrid urban drainage systems (UDSs) are generated through multiobjective optimization (MOO). Then a platform based on MCDM is presented to comprehensively analyze the solutions found by MOO and to rank the solutions. For the sake of demonstration, the proposed framework is applied to a real case study. The results confirm the ability of the proposed framework in handling many decisions, objectives, and indicators for solving a complex optimization problem in a reasonable time by delivering realistic solutions. In addition, the results demonstrate the important role of the degree of (de)centralization (DC) and the layout configuration in obtaining optimal solutions.
Today, pipe systems are the most common facilities to convey various fluids from one place to ano... more Today, pipe systems are the most common facilities to convey various fluids from one place to another. In such facilities faults like leaks lead to advert consequences such as economic losses and social health threats. The fact that early detection of leaks can play a prominent role in reducing the amount of these undesired impacts has absorbed noticeable attention from researchers to this field of study. This paper presents a literature review on major aspects of hydraulic transient-based leak detection in pipe systems over the past three decades. The value of the present study is that an extensive database of peer-reviewed publications is brought together under a meticulous survey. It describes the trends, status and pinpoints the areas with a need for further investigation in the future. Uniquely, it contains information for over 95 publications in a tabular form, presenting domain type, analysis approach, optimization technique, topographic complexity of the case study, leak unk...
کالیبراسیون پارامترهای با اثرات دینامیکی در مدلسازی شبکههای خطوط لوله با تحلیل معکوس جریان گذرا در حوزه فرکانس
بروز جریانهای گذرا بهدلیل شرایط بهرهبرداری در شبکههای آبرسانی امری اجتناب ناپذیر است. بنابرای... more بروز جریانهای گذرا بهدلیل شرایط بهرهبرداری در شبکههای آبرسانی امری اجتناب ناپذیر است. بنابراین تحلیل شبکههای آبرسانی برای جریان گذرا، جهت افزایش اعتمادپذیری سیستم امری ضروری است. از طرفی، دقت یک تحلیل به میزان زیادی وابسته به پارامترهای مختلف ورودی بهمدل از قبیل زبری جدار لولهها، اثرات نوسانی ضریب افت غیرماندگار و سرعت موج در لولهها است. از آنجا که تعیین قطعی این پارامترها در عمل امکانپذیر نیست، این مسئله معمولا از طریق کالیبراسیون سیستم مورد مطالعه و عمدتا با روشهای سعی و خطا و قضاوت مهندسی انجام میشود. خطوط لوله دارای پیچیدگیهای ذاتی در تحلیل هیدرولیکی هستند. از سوی دیگر تعداد و اثرگذاری متقابل پارامترهای دینامیکی در این شبکهها قابل توجه بوده و تشخیص صریح نقش هر یک در پاسخهای سیستم بسیار دشوار بهنظر میرسد. از این رو برای کالیبراسیون شبکههای خطوط لوله تحت فشار تحت جریانهای گذرا نیاز به استفاده از روشها و مدلهای سیستماتیکتر است. در این تحقیق با استفاده از تحلیل معکوس جریان گذرا در حوزه فرکانس، به چگونگی تخمین این پارامترها پرداخته شد. روش حل مسئله کالیبراسیون ب...
Intelligent Optimization of Wastewater Collection Networks
Design of a wastewater collection network is consisting of (1) generating the network’s layout an... more Design of a wastewater collection network is consisting of (1) generating the network’s layout and (2) sizing its hydraulic components. These two sub-problems are nonlinear and discrete in nature and include many complex constraints from hydraulics, technical criteria and regional limitations. This chapter introduces a comprehensive sewer design model possible to be coupled to a variety of intelligent optimization models. For this purpose, two self-adaptive design algorithms are developed for generating the layout and sizing of sewers. Through these algorithms, all constraints of the problem are systematically met and hence, there is no need for any constraint handling strategy into the applied optimization solvers. For optimum design of the network four metaheuristic methods of Genetic Algorithm (GA), Simulate Annealing (SA), Particle Swarm Optimization (PSO) and Tabu Search (TS) are introduced.
Inverse Transient Analysis (ITA) is a powerful approach for leak detection of pipelines. When the... more Inverse Transient Analysis (ITA) is a powerful approach for leak detection of pipelines. When the pipe transient flow is analyzed in frequency domain the ITA is called Inverse Frequency Response Analysis (IFRA). To implement an IFRA for leak detection, a transient state is initiated in the pipe by fast closure of the downstream end valve. Then, the pressure time history at the valve location is measured. Using the Fast Fourier Transform (FFT) the measured signal is transferred into the frequency domain. Besides, using the transfer matrix method, a frequency response analysis model for the pipeline is developed as a function of the leak parameters including the number, location and size of leaks. This model predicts the frequency responses of the pipe in return for any random set of leak parameters. Then, a nonlinear inverse problem is defined to minimize the discrepancies between the observed and predicted responses at the valve location. To find the pipeline leaks the method of Par...
The interbasin water transfer is a remedy to mitigate the negative issues of water shortage in ar... more The interbasin water transfer is a remedy to mitigate the negative issues of water shortage in arid and semi-arid regions. In a water transfer project the receiving basin always benefits while, the sending basin may suffer. In this study, the project of interbasin water transfer from Dez water resources system in south-west of Iran to the central part of the contrary is investigated during a drought period. To this end, a multi-objective optimization model is developed based on the Non Dominated Sorting Genetic Algorithm (NSGA-II). The optimum trade-off between the water supply benefits into and out of the Dez River basin as well as energy production is derived. Formulating the problem as a multi-objective optimization provides a better insight into the gains and losses of a water transfer project. Analyzing the case study, revealed that to reach an acceptable level of reliability for meeting the water demands it is no longer possible to generate hydropower energy with high levels o...
This paper introduces a methodology for considering the uncertainties in stability analysis of gr... more This paper introduces a methodology for considering the uncertainties in stability analysis of gravity dams. For this purpose, a conceptual model based on the fuzzy set theory and Genetic Algorithm (GA) optimization is developed to be coupled to a gravity dam analysis model. The uncertainties are represented by the fuzzy numbers and the GA is used to estimate in what extent the input uncertainties affect the dam safety factors. An example gravity dam is analyzed using the proposed approach. The results show that the crisp safety factors might be highly affected by the input uncertainties. For instance, ±10% uncertainty in the design parameters could result in about −346 to + 146 % uncertainty in the stability safety factors and −59 to + 134 % in the stress safety factor of the example dam.
The accuracy of leak detection and calibration of pipe networks by means of the inverse transient... more The accuracy of leak detection and calibration of pipe networks by means of the inverse transient analysis (ITA) is highly affected by the number and location of the measurement sites. This study introduces a conceptual decision-making model, the Decision Table Method (DTM), for the measurement site design of pipe networks with the aim of inverse transient analysis. Through the Decision Table Method, near optimum measurement sites are decided based on two criteria of the maximum sensitivity of measurement sites and the maximum diversity of sensitivity with respect to unknown parameters of leak areas and friction factors. The main advantage of DTM is that even in case of large networks, calculation of the Hessian matrix and the utilization of any optimization algorithm is not required. To evaluate the efficiency and applicability of the method, it is applied on two pipe networks of small and large size from the literature and the results are compared with the previous methods. Accord...
In recent years, the concept of a centralized drainage system that connect an entire city to one ... more In recent years, the concept of a centralized drainage system that connect an entire city to one single treatment plant is increasingly being questioned in terms of the costs, reliability, and environmental impacts. This study introduces an optimization approach based on decentralization in order to develop a cost-effective and sustainable sewage collection system. For this purpose, a new algorithm based on the growing spanning tree algorithm is developed for decentralized layout generation and treatment plant allocation. The trade-off between construction and operation costs, resilience, and the degree of centralization is a multiobjective problem that consists of two subproblems: the layout of the networks and the hydraulic design. The innovative characteristics of the proposed framework are that layout and hydraulic designs are solved simultaneously, three objectives are optimized together, and the entire problem solving process is self-adaptive. The model is then applied to a re...
Structural resilience describes urban drainage systems’ (UDSs) ability to minimize the frequency ... more Structural resilience describes urban drainage systems’ (UDSs) ability to minimize the frequency and magnitude of failure due to common structural issues such as pipe clogging and cracking or pump failure. Structural resilience is often neglected in the design of UDSs. The current literature supports structural decentralization as a way to introduce structural resilience into UDSs. Although there are promising methods in the literature for generating and optimizing decentralized separate stormwater collection systems, incorporating hydraulic simulations in unsteady flow, these approaches sometimes require high computational effort, especially for flat areas. This may hamper their integration into ordinary commercially designed UDS software due to their predominantly scientific purposes. As a response, this paper introduces simplified cost and structural resilience indices that can be used as heuristic parameters for optimizing the UDS layout. These indices only use graph connectivit...
This paper presents some developments in the optimization effectiveness for the dynamic design of... more This paper presents some developments in the optimization effectiveness for the dynamic design of water distribution networks (WDNs), tackled employing multi-objective genetic algorithms. Unlike the traditional single-phase design, the dynamic multi-phase design operates on planning WDN upgrades on short time intervals, also called phases or stages, while fitting them into a long-term planning horizon, thus requiring bespoke research efforts for the improvement of the optimization effectiveness. A modified version of dynamic NSGA-II optimization is introduced here, including: no penalty on the objective functions for infeasible solutions, adoption of engineering judgments in the construction of optimization individuals, restricting the number of parallel pipes at each site. This results in the improvement of convergence speed and solution quality in two case studies with different complexities.
Uploads
Papers by Ali Haghighi