Pipe Junctions Research Articles

Leak detection and localization of fluid-filled pipeline using accelerometer pairs and mode separation method

Acoustic methods are commonly used to detect and locate leaks in pipelines, but they often overlook important multimodal characteristics of acoustic waves, limiting their applicability. Based on propagation theories regarding F(1,1) mode signal extraction, a new and easy-to-use method for leak detection and localization in pressurized pipelines is proposed. The F(1,1) mode signals are obtained using accelerometer pairs and mode separation method, which are then used to train detection models and to estimate the time difference of arrival (TDOA) for leak localization. Mode separation empowers the data-driven models with physically meaningful samples, aiming to broaden their applicability. The mode consistency between TDOA and velocity is achieved to ensure accurate leak localization. Experiments in buried water-filled ductile iron pipe (experiment A) and in fuel-filled iron pipe (experiment B) are conducted and the longest test distance reaches 72 m. The results validate that the employment of mode separation notably improves current leak detection and localization methods which primarily rely on original signals. The recognition rates rise about 3 %∼11 %, and the false alarm rates reduce about 1 %∼2 %, even when confronted with pipe junction interferences. Also, the leak localization errors are overall lower, with absolute errors below 2 m and relative errors less than 5 % of the test segment length for most cases.

Numerical simulation of air flow and distribution in the blast system of blast furnace

A three-dimensional geometric model of the blast system of the 5500 m3 blast furnace was established in this study. The velocity distribution of the blast system was calculated by OpenFOAM, and the velocity distribution at cross sections of the round pipe and the branch pipe was analysed. The main conclusions are as follows: (1) When the hot air enters the branch pipe, the air flow speed gradually increases and reaches its maximum value (approximately 266.7 m/s) at the tuyere outlet. (2) When the hot air enters the round pipe from the main pipe, there is momentum loss. When the hot air further reaches the opposite side of the junction between the round pipe and the main (Tuyere 1#), the speed of the hot air in the round pipe decreases to the minimum. (3) The maximum air flow average speed of the tuyere outlet is located at Tuyeres 20# and 21# at the junction of the main pipe and the round pipe, which can reach 264.5 m/s. The minimum air flow average velocity of the tuyere outlet is located at Tuyeres 19# and 22#, approximately 258.5 m/s.

An investigation of the cavitation and vibration phenomena in a cylindrical cyclone

Cylindrical cyclones are a popular choice for oil-water separation and sewage treatment in the petroleum industry. Here, we investigate the cavitation and vibration phenomena in a cylindrical cyclone with a vortex finder by using various cyclone operating parameters and conducting multiphase flow numerical simulations. The lowest point of pressure on the cross section of the main cylinder is defined as the pressure center point and is used to understand the generation of the flow field oscillation, which is shown to exhibit an approximately circular motion. This circular oscillation of the flow field is an important characteristic that influences the overall performance and behavior of the cyclone system. Cavitation analysis results show that an increase in the inlet velocity leads to more intense cavitation and an expansion of the cavitation area. At lower split ratios, cavitation primarily occurs at the junction of the inlet pipe and the main cylinder, while at higher split ratios, the cavitation area gradually extends into the overflow pipe. Additionally, structural response analysis demonstrates that increasing the inlet velocity and overflow split ratio significantly enhances the vibrational degree of the structure, leading to greater stress levels. Adjusting the oil content at the inlet has a relatively minimal impact on the structural response compared with the influence of the inlet velocity and split ratio. Furthermore, dimensional analysis is used to analyze the change of wall pressure, and the wall pressure that induces structural vibration can be calculated using the inlet velocity and the split ratio.

Identifying some regularities of the heat transfer in the welded joint of SUS304 pipe using a numerical approach

In this study, an investigation into the impact of heat transmission in the welded junction of SUS304 pipe has been carried out with the use of a numerical method. An investigation was carried out by employing ANSYS’s static structural tools in conjunction with the software package’s thermal transient analysis. Based on the heat flow on the welding point, where the temperature reaches 507 °C within 200 mm of the end of the welded pipe, an examination into the efficiency of heat transfer has been carried out. This analysis was based on the heat flow on the welding point. As the total heat flux approaches 7.02e6 W∙m–2, studies have been conducted on the topic. There have been three types of directional heat flux measurements made (X, Y, and Z), with the numerical findings indicating that the X direction produces the most variable heat flow readings. These checks were performed in a variety of settings. These were chosen as the correct paths to go since they led directly to the source of the warmth. whereas the Z-axis permits the minimum amount of heat flow throughout the board. The damaged area identified on the trees that were still standing was factored into the calculation. To calculate the amount of residual stress, the Von Mises stress was applied repeatedly during the whole procedure. This tactic ended up being employed. Due to the tension caused by the pipe’s increased bending radius, the piece of pipe located 200 mm from the pipe’s distal end is the most vulnerable. The value was calculated to be 2.49e6 Pa when the temperature was increased to 500 °C.

Secondary flow and thermal field dynamics in a T-junction with an upstream elbow: A POD-aided, eddy-sensitized Reynolds-stress modeling study

The thermal mixing of the flow-crossing streams in a T-shaped pipe junction configuration with the main branch inflow forming an elbow is presently simulated by applying a RANS-based eddy-resolving model of turbulence. The low-temperature main stream enters the T-junction with a Reynolds number of Rem=107893 after passing through a 90o-turned elbow located upstream. The high temperature branch stream is injected perpendicularly into the main stream at a Reynolds number of Rem=5422. A significant difference between the flow velocities of the two streams leads to the formation of a characteristic mixing process resembling a reattached jet configuration. Of particular interest is the interference of the branch flow with the main flow characterized by secondary vortices – the so – called Dean vortices, that are convected from the curved main inlet generating a low-rank mixing structures in its wake. The reference LES-based (Large-Eddy Simulation) database is provided by Tunstall et al. (2016). The computational framework relying on the scale-adaptive turbulence modeling approach, introduced principally by Menter and Egorov (2010), is used to simulate the dynamics of large-scale turbulent structures with moderate spatial and temporal resolution requirements. The motion of unresolved subscale structures is described by an appropriately sensitized differential near-wall Reynolds stress model according to Jakirlić and Maduta (2015). In addition, Proper-Orthogonal Decomposition (POD) is used to analyze the prevailing flow and thermal field mechanisms. The results obtained show a reasonable level of agreement with the LES reference, both from the standpoint of first-order statistics and spectral reproduction of the dynamics of coherent structures.

Kirchhoff–Love shell representation and analysis using triangle configuration B-splines

This paper presents the application of triangle configuration B-splines (TCB-splines) for representing and analyzing the Kirchhoff–Love shell in the context of isogeometric analysis (IGA). TCB-splines offer flexibility in modeling complex geometries with C1 continuity, making them naturally fit into the Kirchhoff–Love shell formulation with complex geometries. We first propose a linear least-squares-based framework to reparametrize the mid-surface of a thin shell, which consists of multiple (trimmed) NURBS patches and is topologically equivalent to an open disk with a finite number of holes, into a single TCB-surface defined over a carefully computed parametric domain. We then utilize TCB-splines for geometric representation and solution approximation in shell analysis. We verify the accuracy and robustness of our method by applying it to linear and nonlinear benchmark shell problems. The applicability of the proposed approach to shell analysis is further exemplified by performing geometrically nonlinear Kirchhoff–Love shell simulations of a pipe junction and a front bumper represented by a single patch of TCB-splines.

A Transient-Based Analysis of a Leak in a Junction of a Series Pipe System: Mathematical Development and Numerical Modeling

In this paper, a numerical model is proposed to simulate the effect of a leak occurring at a pipe junction. The developed model, based on the method of characteristics, considers both hydraulic singularities, the leak and the junction, as superposed boundary conditions located in the same section. Obtained results representing the temporal evolution of pressure signals have allowed for locating the leak through the separation of its effect from that of the junction. For testing purposes, the transient was created by a sudden closure of a downstream valve in a reservoir-two series pipe-valve system. The novel proposed approach has proven its usefulness on locating and sizing the leak through detailed test cases. In sizing the leak, better accuracy is obtained when using the maximum pressure head reached by the incident wave before encountering the leaky junction instead of that of the transmitted wave through the leak. On the other hand, for the localization of the leak, rather than looking for an equivalent characteristic period of the two-pipe system, it was shown that the characteristic period of the pipe connected to the reservoir, once incorporated into the localization formula, leads to precise results with minimal uncertainty. For the piping system, two cases of configuration, viz. expansion and shrinkage (narrowing), were tested. In general, using the proposed approach, the maximum uncertainty values for the sizing and localization of a leak in the junction are 0.1513% and 1.09%, respectively. Additionally, the friction effect on the localization and sizing of the leak at the junction was investigated to conclude that the friction does not significantly affect the precision of the numerically obtained results for the sizing and localization of the leak at the junction.

Beam-on-spring modeling of buried MDPE pipes in sand subjected to lateral loads at a pipe junction

Buried pipelines in landslide areas may experience excessive stresses or strains that depend on a complex soil-pipe interaction. The simplified beam-on-spring analysis is recommended in current pipe design guidelines to assess buried pipes subjected to ground movements. The recommended method was developed based on observations of buried steel pipes. The applicability of the methods was not evaluated for Medium-Density Polyethylene (MDPE) pipes that are widely used in gas distribution systems. This paper evaluates the applicability of the beam-on-spring modeling technique for MDPE pipes experiencing relative ground movements observed in laboratory tests. Finite element analysis was performed, modeling the pipes as beams and the soil reactions using the pipe-soil-interaction (PSI) elements in Abaqus, representing springs. The study reveals that while the beam-on-spring analysis can simulate the pipe responses, the spring parameters recommended in the design guidelines are not applicable to buried MDPE pipes. The required magnitudes of peak axial and lateral spring forces and the yield displacements for MDPE pipes are larger than those recommended in the design guidelines. Based on the simulation of experimentally measured pipe responses, modifications to the recommendations of existing design guidelines for estimating the spring parameters are proposed for application to the MDPE pipe assessment.

Prediction of chlorine concentration of flows exiting pipe in cross junctions: experimental and numerical study

Abstract This paper aims to develop and validate an analytical equation to predict the concentration of residual chlorine exiting a typical pipe junction. In order to investigate the trend of the incoming flow rates before leaving the junction, experiments with inflow rates (North and West) ranging from 0.18 to 2.17 L/s, Reynolds numbers ranging from 14,324 to 110,780, and free chlorine concentrations ranging from 0.5 to 1.80 mg/L were performed. The results showed that flows tend to bifurcate rather than mix completely, and the bifurcation and mixing depend mainly on the relative flow rates entering the cross junction. Based on the experimental results, a dimensionless concentration (R) was estimated, allowing for predicting chlorine at the East outlet. Then, a solute mass balance was also performed within the cross junction to predict chlorine concentration at the South outlet. Finally, an adjustment of the R-value was performed by using 3D computational fluid dynamics (CFD), and the analytical equations were also validated with simulations. The standard k–ε turbulence model with enhanced wall treatment for modeling turbulence and near-wall effects, respectively, were used. More mixing models will improve water quality simulations to ensure proper control of chlorine and possible contaminants in water distribution systems.

Shape optimization of pipeline components

AbstractWhen it comes to shape optimization of processes and equipment in an industrial environment, adjoint methods together with computational fluid dynamics have been a great solution. The success of these methods is due to the total cost of obtaining the sensitivity derivatives once it is independent of the number of shape parameters. However, few developments for multiphase flows have been proposed, as there are still fundamental limitations in adjoint models that might prevent their common use. The adjoint theory is not applicable, for example, to the Lagrangian formulation, which has been the workhorse in particle‐induced erosion simulations. Despite these circumstances, it is intuitively possible to think that the optimization of the carrier flow is also expected to ‘optimize’ the particle flow. For instance, reducing total losses in a pipe junction will lead to a more streamlined design. This, in turn, will prevent sudden changes in fluid motion and, consequently, in particle path. As a direct outcome, erosion is expected to be mitigated, as it is mostly influenced by the particle velocity. Given the lack of rigorous mathematical proof of that, the present work investigates how the optimization of single‐phase flow can also mitigate erosion. The erosive wear problem was tackled in three different bend pipes, and the correlation with Stokes number was further explored. As general results, substantial reductions in peak erosion have been found as a consequence of minimizing total losses for all addressed cases. Accordingly, these pipeline components may have an increase in their service life.

Analysis Of Water Distribution Networks In A Supply System Drinking Water In STL Ulu Terawas Districts Musi Rawas District

AbstractClean water is a vital need of living things, especially for human beings who live spread throughout the earth's surface both in urban and rural areas. This study aims to determine the discharge and the condition of the existing water sources used by SPAM, STL Ulu Terawas Sub-district, to find out the elevation of each pipe junction of the STL Ulu Terawas SPAM pipe. Provide the most efficient alternative network in meeting the needs of the community. The method of analyzing the water distribution network in the drinking water supply system in STL Ulu Terawas District, Kabupaten Musi Rawas using EPANET 2.0 software. The EPANET simulation results show that the water discharge value at the SPAM STL Ulu Terawas Musi Rawas Regency is getting lower as the water pressure decreases at junction 4 (four) the water discharge is 30 liters/second until junction 13 (thirteen) the water discharge is 15 liters/second. The EPANET simulation results show that the elevation conditions at the SPAM STL Ulu Terawas Musi Rawas Regency are too high from the water source, such as at junction 2 (two) the elevation is 51 meters, while the elevation at junction 10 (ten) elevation is 62 meters. That's what causes the water discharge to get further and lower its speed. The EPANET simulation results show that the water distribution network of SPAM STL Ulu Terawas has failed, such as at junction 4 (four) the water discharge is 30 liters/second while junction 13 (thirteen) water discharge is 15 liters/second, which means it can be explained that the water distribution network At SPAM STL Ulu Terawas Kabupatn Musi Rawas, the water has not been able to drain properly.

The Influence of Temperature on Degradation of Oil and Gas Tubing Made of L80-1 Steel

Corrosion in the oil and gas industry is very common due to the simultaneous action of a chemically active environment, temperature, and other non-chemical factors, for example, mechanical erosion by friction, and for these reasons corrosion is a very complex process. Corrosion at higher temperatures is an important aspect when extracting natural gas from a field with high temperatures (120 °C in the Lubiatow deposit and 180 °C in the gas well in Kutno). Water in the reservoir is often in the form of steam, with a pressure of about 25 MPa; as a result of its extraction, it cools down, which causes condensation. Condensed water in contact with the acid components of the gas causes corrosion, especially in the presence of aggressive gases, such as CO2 and H2S. Therefore, the aim of the work was to conduct research on the influence of water condensation, as a result of temperature changes in gasses containing CO2 and H2S on the corrosion of L80-1 steel at the junction of extraction pipes with casing pipes. The tests are carried out at temperatures of 65–95 °C, under a pressure of 7.5 MPa, so in quite aggressive conditions. The duration of the studies was 720 h (within a month). The results of the research allowed an answer to be provided for the question of what influence temperature, gas components, and pressure have on the corrosion of the well construction material. Moreover, the results clearly showed the selection of the material for the well, in order to prevent corrosion in aggressive environments.

CFD simulation and statistical experimental design analysis of core annular flow in T-junction and Y-junction for oil-water system

One of the big challenges in transporting heavy oils through the pipelines is the high pressure drop due to the effect of viscosity and shear-thinning fluid behaviour of oil. Core annular technique has been applied in industry for transporting heavy oil via pipelines to considerably reduce pressure drop. Several studies have been conducted related to oil-water core annular flow (CAF) within pipelines. However, limited works are found in cases of CAF in widely used T and Y-shaped junction pipes which have important roles for dividing or combining the flow. In this study, a computational fluid dynamic (CFD) approach was applied to simulate the high viscous oil-water CAF through T and Y-shaped junction pipe configurations. The 2k factorial statistical experimental design was applied to investigate the effect of pipe diameter and junction angle on the flow performance through T and Y-shaped junction pipes. Eight cases were run with different junction pipe configuration combinations. By applying the factorial designs method, all possible combinations of factors were able to be investigated with lowest numbers of simulation run. The selected response variables of the flow system were the average values of oil hold up and pressure gradient as well as the standard deviation of pressure from inlet to outlets of pipes. It was observed that the stability of CAF was not achieved at the downstream region. The flow transformed into stratified and slug flow. The most attractive design was measured by the small average of pressure gradient and standard deviation of pressure but with a high value of oil holdup. The T-shaped pipe with smaller inlet diameter combined with larger outlet diameter showed the most considerable effect for a better flow performance.

Evaluating Tensile Strength in Butt Fusion and Electrofusion Joints in Nanocomposite HDPE Pipes

In this paper, high-density polyethylene (HDPE) composite pipes, reinforced with glass fibers (GF) and carbon nanotubes (CNTs), are manufactured using a novel extruder and multiple molten reprocessing cycles in a screw cylinder barrel. Moreover, the study investigates the tensile strength of the junction of these composite pipes. The results indicate that the Young’s modulus and the ultimate tensile strength of the fabricated nanocomposite pipes increase by 150 and 163 %, compared to the conventional polyethylene pipes, respectively, using 2 wt% carbon nanotubes and two reprocessing iterations in the cylinder barrel. The effects of adding carbon nanotubes to HDPE and the number of reprocessing cycles on the fracture mechanism of the nanocomposite pipes have been explored based on SEM images and DSC testing. The pipes are joined using the two most common available methods; namely, butt fusion and electrofusion, and their respective tensile strengths are compared. The results demonstrate an 82 % and a 37 % decrease in the tensile strength for the welded pipes, compared to the non-welded pipes, using butt fusion and electrofusion, respectively. However, the tensile strength in the welding of the GFRP nanocomposite pipes can be enhanced by increasing the interconnection between the fibers at the junction. Nevertheless, butt fusion is not recommended for joining FRP composite pipes, while electrofusion can be utilized with some modifications.

Estimation of pulsatile energy dissipation in intersecting pipe junctions using inflow pulsatility indices

This study aims to characterize the effect of inflow pulsatility on the hydrodynamic power loss inside intersecting double-inlet, double-outlet pipe intersection (DIPI) with cross-flow mixing. An extensive set of computational fluid dynamics (CFD) simulations was performed in order to identify the individual effects of flow pulsatility parameters, i.e., amplitude, frequency, and relative phase shift between the inflow waveform oscillations, on power loss. An experimentally validated second order accurate solver is employed in this study. To predict the pulsatile flow performance of any given arbitrary inflow waveforms, we proposed three easy-to-calculate pulsatility indices. The frequency-coupled quasi-steady flow theory is incorporated to identify the functional form of pulsatile power loss as a function of these indices. Our results indicated that the power loss within the inflow branch sections, lumped outflow-junction section, and the whole conduit correlates strongly with the pulsatility of each inflow waveform, the total inflow pulsatility, and inflow frequency content, respectively. The complete CFD simulation matrix provided a unified analytical expression that predicts pulsatile power loss inside a one-degree offset DIPI geometry. The predictive accuracy of this expression is evaluated in comparison to the CFD evaluation of arbitrary multi-harmonic inflow waveforms. These results have important implications on hydrodynamic pipe networks that employ complex junctions as well as in the patient-to-patient comparison of surgically created vascular connections. Coupling the present analytical pulsatile power loss expression with non-dimensional steady power loss formulation provided a valuable predictive tool to estimate the pulsatile energy dissipation for any arbitrary junction geometry with minimum use of the costly CFD computations.

Study of a Noncontact Flow Transducer Using Semicylindrical Capacitive Sensor

The fluid flow rate through a pipeline is a very important process variable in any process plant that is required to be measured accurately. In this article, a new noncontact semicylindrical capacitive flow sensing technique has been developed and studied. The proposed capacitive sensor consists of two semicylindrical curved copper plates mounted on the outside surface of an insulating pipeline near the turbulence region produced at the junction of a larger diameter pipe and a smaller diameter pipe. Here the insulating pipeline section between the copper plates along with the flowing fluid acts as a composite dielectric material of the sensing capacitor. The semicylindrical curved copper plates along with two lead wires are rigidly mounted without any air gap on the larger diameter pipe using a thin layer of araldite. A mathematical relation between the sensor capacitance and flow rate is derived in this article. This capacitance is found to vary nonlinearly with flow rate and is measured using an op-amp-based DeSauty bridge-type transducer circuit where a similar capacitor with the same fluid at zero flow is used as a dummy capacitor. A prototype unit of the proposed transducer is designed, developed and tested experimentally. The static characteristic curves drawn from the experimental results are found to follow the derived mathematical equation to a very good extent with good repeatability.

Corrosion failure analysis of the 45-degree elbow in a natural gas gathering pipeline by experimental and numerical simulation

A bursting incident occurred in a 45-degree elbow of a natural gas gathering pipeline in an oilfield. The failure analysis was performed by means of corrosion morphology observation, corrosion products analysis, and computational fluid dynamics (CFD) simulations. The results showed that a radical change in the fluid state at the 45-degree elbow due to its climbing structure and formation a region of low flow velocity, high pressure and high turbulence kinetic energy, which promoted the condensation of water vapor containing CO2. Then the corrosive water droplets flowed back under the action of gravity and accumulated at the junction between the elbow and horizontal pipeline. In such a corrosive medium, electrochemical corrosion was preferred for 20 steel. In addition, the junction of the horizontal pipe and the inclined pipe exhibits higher structural stress concentration, resulting in increased corrosion thinning. Finally, the failure of the pipeline can be attributed to the synergistic effect of electrochemical corrosion and stress accelerated corrosion.

Enabling large-scale dynamic simulations and reducing model complexity of district heating and cooling systems by aggregation

District heating and cooling (DHC) systems are considered cornerstones of a future heat and cold supply due to their ability to integrate renewable and waste heat sources as well as long and short-term storage technologies and their flexibility for integration of other infrastructures. Therefore, DHC systems may represent the central hub of an interlinked overall energy system. These options nevertheless lead to a more complex system if implemented as the number of technical components and potential interactions increase and as the energy demands on the network grow. The transportation of the heat supplied to the consumers through water flow involves both time and temperature-dependent changes based on the mass flow rates and the heat losses to the surrounding from the pipes. The dynamic properties of the consumers and the distribution pipes strongly influence the operation of the district heating systems. Dynamic modeling tools are required to cope with the increasing complexities and to optimize the operation of the DHC systems by using the knowledge of time delay in the heat transport, temperature distribution and flow characteristics. Nevertheless, it is computationally challenging to simulate large-scale DHC networks dynamically. One proposed method for improvement in this context is aggregation, which simplifies the topological complexities of the original network by reducing the number of pipe junctions (branches) and pipes. This paper focuses on the analysis and evaluation of the application of two aggregation methods, the Danish and the German method, in a dynamic modelling environment and comparing the aggregation to the monitoring data of a virtual district heating network with 146 consumers and an existing district heating network with 66 consumers. These evaluations are based on comparison of the simulation results of the aggregated network with fewer consumers than the original network in terms of accuracy, information loss and computational time. The results show that the CPU time in the simulation of this network can speed up approximately more than 95% by aggregating the network down to 3 consumers without significant information loss. We will highlight the current potentials and limitations of both aggregation methods in terms of integrating them in the planning, modelling and operation of DHC systems, including the 4th generation district heating systems.

Numerical schemes based on the stress compensation method framework for creep rupture assessment

Evaluation of creep rupture limit and prediction of creep rupture life are two significant issues for high-temperature devices under the action of cyclic thermo-mechanical loadings. In this paper, the shakedown solution procedure proposed recently by the authors, so-called stress compensation method (SCM), is extended for creep rupture assessment via an extended shakedown theory including creep. Two distinct numerical schemes based on the SCM framework are presented, where Scheme 1 is utilised for evaluation of creep rupture limit and Scheme 2 is utilised for prediction of creep rupture life. Instead of using the detailed creep constitutive equations, the present methods just need to know several material parameters including the creep rupture data. A holed plate is provided as a typical example to validate the reliability of two numerical schemes. Detailed cycle-by-cycle analyses are carried out to illustrate the good accuracy of these calculated creep rupture limits and reveal the failure mechanisms of the structure under different combinations of loads. A numerical study on a pipe junction is also conducted to show the engineering application of the methods. As a result, the two numerical schemes are proved to be effective and reliable for solving practical industrial problems.

Efficient Double-Tee Junction Mixing Assessment by Machine Learning

A new approach in modeling of mixing phenomena in double-Tee pipe junctions based on machine learning is presented in this paper. Machine learning represents a paradigm shift that can be efficiently used to calculate needed mixing parameters. Usually, these parameters are obtained either by experiment or by computational fluid dynamics (CFD) numerical modeling. A machine learning approach is used together with a CFD model. The CFD model was calibrated with experimental data from a previous study and it served as a generator of input data for the machine learning metamodels—Artificial Neural Network (ANN) and Support Vector Regression (SVR). Metamodel input variables are defined as inlet pipe flow ratio, outlet pipe flow ratio, and the distance between the pipe junctions, with the output parameter being the branch pipe outlet to main inlet pipe mixing ratio. A comparison of ANN and SVR models showed that ANN outperforms SVR in accuracy for a given problem. Consequently, ANN proved to be a viable way to model mixing phenomena in double-Tee junctions also because its mixing prediction time is extremely efficient (compared to CFD time). Because of its high computational efficiency, the machine learning metamodel can be directly incorporated into pipe network numerical models in future studies.