DeepVision based detection for energy-efficiency and indoor air quality enhancement in highly polluted spaces

Abstract

Cooking can generate substantial heat from cooking equipment, potentially resulting in reduced thermal comfort levels if this excess heat is not adequately dissipated. Additionally, it can significantly affect indoor air quality (IAQ), not only in kitchen spaces but also in adjacent areas lacking sufficient ventilation. To ensure a healthy and comfortable indoor environment while avoiding unnecessary energy use, this research proposes an approach for detecting equipment usage. Utilizing deep learning and computer vision techniques (referred to as DeepVision), this method aids the operation of demand-driven ventilation systems in highly polluted spaces. A Faster RCNN model was employed and trained to detect kitchen equipment usage in real-time. The ventilation rate for the kitchen space was adjusted based on this real-time detection. Experimental tests were carried out in a case study kitchen and results showed that the detection model achieved an overall F1 score of 0.9142. Overall, the model achieved good performance in real-time detection, accurately identifying appliances in use, such as stoves, ovens, and toasters. Field experimental results showed the advantages of combining mechanical ventilation methods, such as extractor fans and cooker hoods, to mitigate IAQ issues while also achieving energy savings. Moreover, the energy simulations demonstrate its potential to reduce energy consumption by dynamically adjusting ventilation rates in response to real-time equipment usage. When the fan speed was varied according to the real-time detection method, the PM2.5 concentration in the cooking period was 16.5 % lower, with only a 3.7 % rise in fan power and a 0.8 % rise in daily heating demand, compared to using a constant fan speed.