Air Entrainment in Drop Shafts: A Novel Approach Based on Machine Learning Algorithms and Hybrid Models

Granata, Francesco; Nunno, Fabio Di

doi:10.3390/fluids7010020

Cited by 8 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where deviation and function flatness depend on the constant C, which is greater than 0 [37]. The effectiveness of SVR depends also on the selection of the kernel function, which defines the feature space, and of its parameters.…”

Section: Support Vector Regression (Svr)mentioning

confidence: 99%

Precipitation Forecasting in Northern Bangladesh Using a Hybrid Machine Learning Model

et al. 2022

Self Cite

View full text Add to dashboard Cite

Precipitation forecasting is essential for the assessment of several hydrological processes. This study shows that based on a machine learning approach, reliable models for precipitation prediction can be developed. The tropical monsoon-climate northern region of Bangladesh, including the Rangpur and Sylhet division, was chosen as the case study. Two machine learning algorithms were used: M5P and support vector regression. Moreover, a novel hybrid model based on the two algorithms was developed. The performance of prediction models was assessed by means of evaluation metrics and graphical representations. A sensitivity analysis was also carried out to assess the prediction accuracy as the number of exogenous inputs reduces and lag times increases. Overall, the hybrid model M5P-SVR led to the best predictions among used models in this study, with R2 values up to 0.87 and 0.92 for the stations of Rangpur and Sylhet, respectively.

show abstract

Section: Support Vector Regression (Svr)mentioning

confidence: 99%

Precipitation Forecasting in Northern Bangladesh Using a Hybrid Machine Learning Model

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is impossible to define straightforward functional relationships between the airflow and the hydrodynamic and geometric variables that it depends on because air entrainment in drop shafts is so complex [56]. However, by employing prediction models built on ML techniques, which may deliver trustworthy tools to handle highly non-linear problems pertaining to experimental hydrodynamics, this issue can be properly addressed.…”

Section: Introductionmentioning

confidence: 99%

Assessment of Machine Learning Algorithms for Predicting Air Entrainment Rates in a Confined Plunging Liquid Jet Reactor

Alazmi,

Al-Anzi

2023

Sustainability

View full text Add to dashboard Cite

A confined plunging liquid jet reactor (CPLJR) is an unconventional efficient and feasible aerator, mixer and brine dispenser that operates under many operating conditions. Such operating conditions could be challenging, and hence, utilizing prediction models built on machine learning (ML) approaches could be very helpful in giving reliable tools to manage highly non-linear problems related to experimental hydrodynamics such as CPLJRs. CPLJRs are vital in protecting the environment through preserving and sustaining the quality of water resources. In the current study, the effects of the main parameters on the air entrainment rate, Qa, were investigated experimentally in a confined plunging liquid jet reactor (CPLJR). Various downcomer diameters (Dc), jet lengths (Lj), liquid volumetric flow rates (Qj), nozzle diameters (dn), and jet velocities (Vj) were used to measure the air entrainment rate, Qa. The non-linear relationship between the air entrainment ratio and confined plunging jet reactor parameters suggests that applying unconventional regression algorithms to predict the air entrainment ratio is appropriate. In addition to the experimental work, machine learning (ML) algorithms were applied to the confined plunging jet reactor parameters to determine the parameter that predicts Qa the best. The results obtained from ML showed that K-Nearest Neighbour (KNN) gave the best prediction abilities, the proportion of variance in the Qa that can be explained by the CPLJR parameter was 90%, the root mean square error (RMSE) = 0.069, and the mean absolute error (MAE) = 0.052. Sensitivity analysis was applied to determine the most effective predictor in predicting Qa. The Qj and Vj were the most influential among all the input variables. The sensitivity analysis shows that the lasso algorithm can create an effective air entrainment rate model with just two of the most crucial variables, Qj and Vj. The coefficient of determination (R2) was 82%. The present findings support using machine learning algorithms to accurately forecast the CPLJR system’s experimental results.

show abstract

“…The pipe offset was set between the 4th and 5th floors. The offset distance was set to 2 m. Studies 9,21,22 have shown that setting the large curvature elbow at the position of the pipe offset can improve the water flow capacity of the drainage system. Thus, the large curvature elbow was employed to connect the drainage stack and offset pipe.…”

Section: Introduction To the Experimental Systemmentioning

confidence: 99%

Overcoming the influence of a 2 metre long pipe offset on water flow capacity of drainage with secondary ventilation in a high-rise building

Yan

Shang

et al. 2022

Building Services Engineering Research and Technology

View full text Add to dashboard Cite

A potential consequence of installing a 2 m long pipe offset on a ventilated drainage system in a high-rise buildings is that the water seal could be damaged when the flowrate exceeds the maximum discharge capacity of a drainage system, thereby threatening the indoor health safety. Some high-rise buildings are designed for commercial and residential use to achieve economic and social benefits, so the whole building use and layout changes in the vertical direction. The drainage stack may be designed with an offset between floors to avoid structural obstacles inside the building. The flow direction change could destroy the water seal of sanitary appliances and threaten the health of residents. To better understand the influence of the form of a pipe offset on the drainage capacity, a full-scale experiment was conducted to study the secondary ventilated system with an antireflux H-tube pipe, which was equipped with two guide plates inside to improve the air-water flow pattern and prevent backflow, installed between floor. This study also considered a kind of offset where the offset distance was 2.0 m rather than the S-shaped offset joint, which is more common in commercial and residential complexes. The influence on the discharge capacity of installing an extra antireflux H-tube pipe was compared with normal 90-degree elbow and only one antireflux H-tube pipe above the offset point. The pressure fluctuation and water seal losses under constant discharge rates were adopted as experimental parameters to determine the maximum discharge capacity according to Standard for Capacity Test of Vertical Pipe of the Domestic Residential Drainage System. Results show that the installation of an extra antireflux H-tube pipe can release the air accumulation caused by pipe offset, and the combined installation of a large curvature elbow and an extra antireflux H-tube pipe can effectively improve the discharge capacity. Practical Application: 2 metre long offsets are not unusual in ventilated drainage systems in high-rise buildings, however, designers and builders do not pay sufficient attention to the adverse consequences of the pipe offset. An extra antireflux H-tube pipe can be installed above the offset joint to optimise the drainage system to perform as it would without the offset. In a system with 2 m long pipe offset, installing a large curvature elbow together with an extra antireflux H-tube pipe together provides a better effect.

show abstract

Air Entrainment in Drop Shafts: A Novel Approach Based on Machine Learning Algorithms and Hybrid Models

Cited by 8 publications

References 29 publications

Precipitation Forecasting in Northern Bangladesh Using a Hybrid Machine Learning Model

Precipitation Forecasting in Northern Bangladesh Using a Hybrid Machine Learning Model

Assessment of Machine Learning Algorithms for Predicting Air Entrainment Rates in a Confined Plunging Liquid Jet Reactor

Overcoming the influence of a 2 metre long pipe offset on water flow capacity of drainage with secondary ventilation in a high-rise building

Contact Info

Product

Resources

About