Predictive control of HVAC by multiple output GRU - CFD integration approach to manage multiple IAQ for commercial heritage building preservation

Abstract

Excessive and fluctuating indoor air quality (IAQ) leads to destruction of historical buildings. Regenerated commercial historic buildings are generally fitted with heating, ventilation, and air conditioning (HVAC) systems for IAQ improvement. There is a time delay in the HVAC system to control environment within the target range after the settings adjustment because of the time required for air conditioners to cool, heat or exchange fresh air. The lack of timely and effective control of traditional HVAC is insufficient to control IAQ for the preservation of historical buildings. This research proposed a novel Multiple Output Gate Recurrent Unit (GRU) - Computational Fluid Dynamics (CFD) integration method and combined it with the automatic control using digital twin technology to improve the effectiveness and efficiency of multiple IAQ management for the preservation of whole indoor spaces. This method considered visual impacts and minimized the external equipment impact. The sequencing order of multiple IAQ enhancements by adjusting HVAC control was investigated based on the priority of multiple IAQ parameters on historic building preservation. The proposed Multiple Output GRU prediction reduced the time by at least 1/3 for training and validation. As heritage buildings restrict the installation of sensors, CFD was used to identify the maximum value and location based on sensed IAQ data for adjustment triggers. The combined method contributed to identifying the predicted maximum value to trigger the 10 min pre-regulation of the HVAC system for dealing with the time delay to maintain multiple IAQ in standard ranges for heritage building preservation.