Development for Improving Eco-Friendly and Energy Efficient Indoor Environment Control Algorithms Based on Building Users

Purpose: This study examines the effectiveness of an optimized, occupant-centric supply air thermal control strategy engineered to enhance the operational performance of a management office. The research focuses on establishing a control paradigm capable of resolving the classic trade-off between minimizing building energy consumption and maintaining desired indoor thermal comfort levels. Method: A straightforward thermal energy balance of the facility was formulated to quantify dynamic temperature variations over time. The thermal comfort index was implemented as the core ergonomic metric to track indoor comfort deviations. An adaptive control loop featuring step-by-step air supply adjustment logic was developed and utilized to train an artificial neural network structured. The combined the adaptive control loop and the network algorithm were subsequently integrated into a unified simulation block framework. Results: The adaptive control model demonstrated high statistical accuracy for both mass flow rate and supply air temperature. Multi-seasonal simulation results revealed that the adaptive model successfully mitigates the severe temperature fluctuations and overshooting typical of traditional dead-band thermostats. During peak summer demands, the proposed model achieved about 20% increase in energy efficiency alongside a massive 46% improvement in thermal comfort tracking precision. Annually, the framework sustained about 6% reduction in overall energy footprint and about 38% increase in comfort homeostasis, respectively.