Optimal location and performance prediction of portable air cleaner in composite room shapes using convolutional neural network

Abstract

Portable air cleaners are commonly used to eliminate hazardous indoor air pollutants such as particulate matters and infectious viruses. The effectiveness of portable air cleaners heavily relies on their installation location, which affects the patterns of airflow carrying the pollutants. Herein, we propose a methodology for optimizing the portable air cleaner placement to maximize its effectiveness using artificial intelligence technology. To build an artificial intelligence model, we obtained the data on airflow patterns for different room shapes and locations of the portable air cleaner through numerical simulations. We utilized floor-plan image data to simplify the handling of complex geometric information related to portable air cleaner placements. The artificial intelligence model extracted geometric features from the floor plan and predicted the effectiveness of the portable air cleaner. The predicted results revealed that the model recommended the location with the highest effectiveness as optimal. The artificial intelligence model achieved a high prediction accuracy of 91.2% and precisely determined the optimal location in rooms with varying shapes. This approach can elucidate the complex relationship between geometric placements and airflow characteristics. Furthermore, the artificial intelligence model can be used as a powerful decision-making tool for indoor air quality management in the building environment.