Indoor pollution control based on surrogate model for residential buildings

Area of Science:

• Environmental Science
• Building Science
• Computational Fluid Dynamics

Background:

• Humans spend most of their lives indoors, making indoor air quality (IAQ) critical for health.
• Current HVAC systems cannot effectively predict or optimize IAQ in real-time, especially near individuals.
• Monitoring IAQ parameters in personal breathing zones presents a significant challenge to effective regulation.

Purpose of the Study:

• To acquire indoor pollutant distribution and precise environmental data.
• To develop an efficient method for forecasting and enhancing indoor air quality.
• To enable intelligent control techniques for indoor atmospheric ventilation.

Main Methods:

• Utilized computational fluid dynamics (CFD) for accurate environmental simulations.
• Developed a Kriging surrogate model for rapid IAQ prediction.
• Integrated surrogate models with CFD data for real-time environmental forecasting.

Main Results:

• The Kriging surrogate model demonstrated rapid IAQ prediction capabilities.
• The model efficiently forecasts indoor environmental conditions using CFD simulation data.
• Optimization algorithms were employed to achieve desired indoor air conditions.

Conclusions:

• The developed surrogate model offers a highly effective approach to IAQ management.
• This method provides intelligent control for indoor ventilation systems.
• Accurate IAQ prediction and enhancement are achievable through advanced modeling techniques.