Open AccessAir conditioning system online control by incorporating low-dimensional linear models and intelligent predictions
Author(s) -
Cuiling Ren,
Shi-Jie Cao
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/609/3/032026
Subject(s) - hvac , ventilation (architecture) , air conditioning , energy consumption , energy recovery ventilation , indoor air quality , computer science , efficient energy use , simulation , automotive engineering , environmental science , engineering , environmental engineering , mechanical engineering , electrical engineering
Development of control techniques for heating, ventilation and air conditioning (HVAC) systems to provide occupancy driven energy and comfort management has been an active area. In this study, we carried out the work on the balance between indoor environmental quality (IEQ) and energy consumption with low-dimensional linear models (LLM), artificial neural network (ANN) and contribution ratio of indoor climate (CRI) to provide support for HVAC control. In general, ventilation (pollutant) and temperature factors were both considered in the CFD simulation. Linear ventilation model (LVM) and linear temperature model (LTM) were employed to expand the CFD database. Then, combined with ANN, CRI and LLM, LLVM (low-dimensional linear ventilation model)-based ANN and LLTM (low-dimensional linear temperature model)-based CRI could rapidly predict the indoor environmental parameters. The evaluation indices were also defined to provide weightings between indoor environment and energy consumption. On this basis, the HVAC energy consumption caused by ventilation and air conditioning loads could be decreased by 50% and 16% respectively. This study will promote an intelligent HVAC control strategy for user comfort and HVAC energy conservation.