Efficient Double-Tee Junction Mixing Assessment by Machine Learning

Grbčić, Luka; Kranjčević, Lado; Družeta, Siniša; Lučin, Ivana

doi:10.3390/w12010238

Cited by 11 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And with the increase of outlet pipe length, the outlet concentration variance is remarkably declined, which means the mixing process is much better and more efficient. Grbčić et al [10] did similar research about the mixing assessment of a double-tee junction. The result shows that the concentration was less stratified than the one near the junction, which is in line with our result.…”

Section: Length Of the Tube At Outlet Cmentioning

confidence: 96%

A research on the converging process in a T-shape tube

Xi¹,

Yu²,

Yuan³

2023

HSET

View full text Add to dashboard Cite

A T-shape tube is an important structure in chemical engineering and other fields. This article utilizes the CFD method on python with a simplified Navier-Stokes equation to stimulate the converging process of different fluids and studies the influence of inflow speed, viscosity, density, diffusion coefficient, the diameter of the tube and the length of the tube on the transmission characteristics like pressure and flow field. The results indicate that the ratio of the velocity of the main tube to that of the branch, the diameter of tube AC and tube B is inversely related with mixing efficiency and that the increase of pipe length at outlet tube and the diffusion coefficient of fluid is positive to the well-distributed concentration of outflow. However, the density and viscosity of inflow seem to have little impact on the mixing process.

show abstract

Section: Length Of the Tube At Outlet Cmentioning

confidence: 96%

A research on the converging process in a T-shape tube

Xi¹,

Yu²,

Yuan³

2023

HSET

View full text Add to dashboard Cite

show abstract

“…Therefore, EPANET extension EPANET-BAM [3] was proposed which uses experimentally calibrated mixing model parameter to more accurately model mixing in network junctions. A number of studies investigated mixing behavior for different conditions, both experimentally and numerically, to further enhance these simpler 1D numerical models [4][5][6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

Machine-Learning Classification of a Number of Contaminant Sources in an Urban Water Network

Lučin

Grbčić

Čarija

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

In the case of a contamination event in water distribution networks, several studies have considered different methods to determine contamination scenario information. It would be greatly beneficial to know the exact number of contaminant injection locations since some methods can only be applied in the case of a single injection location and others have greater efficiency. In this work, the Neural Network and Random Forest classifying algorithms are used to predict the number of contaminant injection locations. The prediction model is trained with data obtained from simulated contamination event scenarios with random injection starting time, duration, concentration value, and the number of injection locations which varies from 1 to 4. Classification is made to determine if single or multiple injection locations occurred, and to predict the exact number of injection locations. Data was obtained for two different benchmark networks, medium-sized network Net3 and large-sized Richmond network. Additionally, an investigation of sensor layouts, demand uncertainty, and fuzzy sensors on model accuracy is conducted. The proposed approach shows excellent accuracy in predicting if single or multiple contaminant injections in a water supply network occurred and good accuracy for the exact number of injection locations.

show abstract