Advancing understanding of indoor conditions using artificial intelligence methods

Physics of Fluids, Journal Year: 2025, Volume and Issue: 37(1)

Published: Jan. 1, 2025

This study presents a novel methodology for optimizing probe placement in indoor air-conditioned environments by integrating computational fluid dynamics simulations with artificial intelligence techniques an unsupervised learning framework. The “Reduce Uncertainty and Increase Confidence” algorithm identified spatially distinct thermal velocity clusters based on temperature magnitude distributions. Optimization of positions within these clusters, guided sequential least squares programing, resulted effective strategy to minimize redundancy while maximizing spatial coverage. highlights the interplay between temperature, relative humidity, velocity, turbulence intensity, revealing critical insights into airflow behavior its implications occupant comfort. findings presented underscore potential targeted provide robust framework advanced climate control.

Language: Английский

The effects of hyperparameters on deep learning of turbulent signals

Physics of Fluids, Journal Year: 2024, Volume and Issue: 36(12)

Published: Dec. 1, 2024

The effect of hyperparameter selection in deep learning (DL) models for fluid dynamics remains an open question the current scientific literature. Many authors report results using models. However, better insight is required to assess models' behavior, particularly complex datasets such as turbulent signals. This study presents a meticulous investigation long short-term memory (LSTM) hyperparameters, focusing specifically on applications involving predicting signals shock boundary layer interaction. Unlike conventional methodologies that utilize automated optimization techniques, this research explores intricacies and impact manual adjustments model. includes number layers, neurons per layer, rate, dropout batch size investigate their model's predictive accuracy computational efficiency. paper details iterative tuning process through series experimental setups, highlighting how each parameter adjustment contributes deeper understanding complex, time-series data. findings emphasize effectiveness precise achieving superior model performance, providing valuable insights researchers practitioners who seek leverage networks intricate temporal data analysis. not only refines predictability specific contexts but also serves guide similar other specialized domains, thereby informing development more effective

Language: Английский

Numerical simulation of high-concentration droplet flow in an idealized mouth–throat airway model in the influence of environmental temperature and humidity

Physics of Fluids, Journal Year: 2024, Volume and Issue: 36(12)

Published: Dec. 1, 2024

The exchange of water vapor between high-concentration droplets and air significantly influences droplet deposition in the upper airway model during nebulizer use. This study employed a two-way coupled Eulerian–Lagrange method to quantify nebulized evaporation relative humidity (RH) variations within an idealized mouth–throat (MT) model, utilizing validated numerical models. interaction inhaled was computed using multiplier based on particle parcel method. Simulations normal saline flow inhalation MT were conducted under two environmental conditions: indoor (26.5 °C, RH = 50%) warm wet (30 75%), with various rates mirroring previous experiments. Droplet fractions (DFs) patterns recorded. results indicated that DF initially decreased then increased rising rates. largest discrepancy predicted measured DFs 10.86%. These findings support theory balance elevated dictates airway. Additionally, simulations revealed conditions affect DF, up 20.78%. hotspot shifted from anterior posterior pharynx.

Language: Английский