Water utilities are challenged to reduce their water losses through detecting, localizing, and repairing leaks as quickly possible in aging distribution systems. In this work, we solve challenging problem by detecting multiple simultaneously a network for the Battle of Leak Detection Isolation Methods. The performance leak detection localization depends on how well system roughness demand calibrated. addition, existing affect diagnosis unless they identified explicitly represented model. To...

Losses in water distribution systems can be between several percent well maintained up to more than 50 developing countries. Most of the losses originate from leaks. Therefore, a fast detection and localization leaks is crucial for effectively reducing this networks. Model-based leak has become increasingly popular recent years. Certainly, performance these methods linked 1) measurement locations system 2) uncertainties at locations. This paper provides methodology that incorporates...

Abstract Global mean sea-level rise (SLR) has accelerated since 1900 from less than 2 mm yr −1 during most of the century to more 3 1993. Decision-makers in coastal countries, however, require information on SLR at regional scale, where detection an acceleration is difficult, because long-term signal obscured by large inter-annual variations with multi-year trends that are easily one order magnitude larger global values. Here, we developed a time series approach determine whether...

Short-term fecal pollution events are a major challenge for managing microbial safety at recreational waters. Long turn-over times of current laboratory methods analyzing indicator bacteria (FIB) delay water quality assessments. Data-driven models have been shown to be valuable approaches enable fast However, barrier towards the wider use such is prevalent data scarcity existing bathing waters, which questions representativeness and thus usefulness datasets model training. The present study...

Abstract Metamodels accurately reproduce the output of physics-based hydraulic models with a significant reduction in simulation times. They are widely employed water distribution system (WDS) analysis since they enable computationally expensive applications design, control, and optimisation networks. Recent machine-learning-based metamodels grant improved fidelity speed; however, only applicable to network were trained on. To address this issue, we investigate graph neural networks (GNNs)...

Several attempts of the past aimed to convert EPANET into a bigger open-source project by rewriting in an object-oriented way. We introduce Python based (OOPNET) with purpose address water engineers that might be not so familiar complex programming languages like C++ or Java. input files are translated object oriented structure OOPNET and manipulated simulated EPANET's command-line interface through Python. The replacement hydraulic solver is still ongoing has provide solution completely...

Nowadays, modern utilities have installed a variety of measurement devices like pressure sensors, flow meters, noise loggers, water quality sensors for different intentions. In this paper we introduce an experimental distribution system (EWDS-TUG) that serves as example implementing smart network solution. The used EWDS-TUG states highly determined supply system. Artificial customers are and can be controlled automatically by magnetic valves. We present how collect sensor data control valves...

Outworn water distribution infrastructures require real-time monitoring and management of pressure flow, together with accurate leak detection localization techniques. Smart networks based on wireless sensors offer a huge potential in this domain, but their deployment maintenance is often costly labor-intensive. In paper, we present Adige: an efficient smart network architecture long-range technology that improves the scalability robustness systems. We developed sensor node prototype using...

In this paper the impact of different distance metrics as well sortings parameter space on shape objective function for model-based leakage localization is investigated. Leakage formulated an optimization problem solved with a differential evolution algorithm. Distance and are evaluated through convergence speed algorithm quality results in terms topological from leak found by to real leak. The tested hydraulic model real-world network has shown that Cuthill-McKee ordering search together...

The calculation of outflow from pipe bursts is interest for water utilities, as the discharged may cause large amounts damage to adjacent infrastructure. Therefore, crack type specific relationship between leakage and pressure interest. Recent findings offer new opportunities burst calculations with hydraulic models. In this paper, we compare two approaches according uncertainties caused by input parameters give recommendations applicability methods. Simulations in a case study area have...

Socioeconomic characteristics are influencing the temporal and spatial variability of water demand, which biggest source uncertainties within distribution system modeling. Improving current knowledge these influences can be utilized to decrease demand uncertainties. This paper aims link smart meter data socioeconomic user by applying a novel clustering algorithm that uses dynamic time warping metric on daily patterns. The approach is tested simulated measured single-family home sets. It...

Sensors used for wastewater flow measurements need to be robust and are, consequently, expensive pieces of hardware that must maintained regularly function correctly in the hazardous environment sewers. Remote sensing can remedy these issues, as lack direct contact between sensor sewage reduces demands maintenance. This paper utilizes off-the-shelf cameras machine learning algorithms estimate discharge open sewer channels. We use convolutional neural networks extract water level surface...

In this paper we compare 6 algorithms for optimal pressure sensor placement by applying them to a real world system. The targets of these comparisons were a) see how robust positions are in terms different mathematical approaches b) derive the purpose small leakage localisation case study distribution Therefore, created artificial scenarios system opening fire hydrants at flow rates. Pressure was measured all that found be an ideal position any applied methods. Based on measurements,...

The hydraulic verification of combined sewer systems as well the assessment overflows (CSOs) can be conducted using a hydrodynamic model. Unfortunately, long-term simulations with models for CSOs cause unacceptably long computation times. Using only series storm events instead precipitation continuum reduce this time and enables parallel simulation single events. We introduce method to select method's parameters have been optimized replicate overflow volume continuous minimize overall time....

In this work a Genetic Algorithm is used to obtain optimal planar UHF RFID tag antenna topologies. The presented design method automated and solely requires very little human intervention. Different requirements like dimension, conductive dielectric materials, frequency range, etc. can be adjusted. This enables the of tailored antennas for different requirements. Due complex behavior numerical electromagnetic field simulation essential. Simulation carried out with aid ANSYS HFSS DESIGNER....

Leakages in water distribution systems are one of the most emerging topics field supply. Therefore, understanding leak hydraulics is high interest. This paper outlines an experimental laboratory network. The main purpose this system to gain knowledge and experience for two tasks. First, verification hydraulic modeling approaches concerning leakage outflow. Second, practically performance evaluation algorithms localization developed at our institute. chosen setup allows multiple leakages,...

Emerging contaminants (ECs) are natural or manufactured chemical compounds that hard to remove through water treatment; hence, they accumulate in the environment. Such have already been detected wastewater, aquatic environments, and distribution systems (WDSs). Consequently, researchers developing sensors tailored explicitly new contaminants. By combining those with real-time simulation models, digital twins within reach assess system-wide quality. In future, such will build cornerstone for...

This paper aims to investigate the effect of distance metrics on fitness landscape for model-based leakage localization and its impact performance differential evolution optimization algorithm applied a theoretical water distribution network from literature.