Advancing understanding of indoor conditions using artificial intelligence methods

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