Adaptive neuro-fuzzy inference systems (ANFIS) application to investigate potential use of natural ventilation in new building designs in Turkey

• Published in: Energy conversion and management Vol. 48; no. 5; pp. 1472 - 1479
• Main Authors: Ayata, Tahir, Çam, Ertuğrul, Yıldız, Osman
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.05.2007; Elsevier
• Subjects: Air conditioning. Ventilation; ANFIS; Applied sciences; Energy; Energy. Thermal use of fuels; Exact sciences and technology; FLUENT; Heating, air conditioning and ventilation; Natural ventilation; Thermal comfort; Turkey; Ventilation; Wind speed; Asia; Turkey; Thermal comfort; Turkey; ANFIS; Wind speed; FLUENT; Natural ventilation; Temperature; Buildings; Passive system; Finite element method; Fuzzy control; New building; Cooling system; Numerical simulation
• ISSN: 0196-8904; 1879-2227
• DOI: 10.1016/j.enconman.2006.12.008

Natural ventilation in living and working places provides both circulation of clear air and a decrease of indoor temperature, especially during hot summer days. In addition to openings, the dimension ratio and position of buildings play a significant role to obtain a uniform indoor air velocity distribution. In this study, the potential use of natural ventilation as a passive cooling system in new building designs in Kayseri, a midsize city in Turkey, was investigated. First, indoor air velocity distributions with respect to changing wind direction and magnitude were simulated by the FLUENT package program, which employs finite element methods. Then, an adaptive neuro-fuzzy inference systems (ANFIS) model was employed to predict indoor average and maximum air velocities using the simulated data by FLUENT. The simulation results suggest that natural ventilation can be used to provide a thermally comfortable indoor environment during the summer season in the study area. Also, the ANFIS model can be proposed for estimation of indoor air velocity values in such studies.