(Login or register-free of charge- to download)
Jin Woo Moon and Jae D. Chang
Year:
2010
Bibliographic info:
31st AIVC Conference " Low Energy and Sustainable Ventilation Technologies for Green Buildings", Seoul, Korea, 26-28 October 2010

This study tested the feasibility of employing artificial neural network (ANN)-based predictive and adaptive control logics to improve thermal comfort and energy efficiency through a decrease in over- and under-shooting of control variables. Three control logics were developed: (1) conventional temperature/humidity control logic, (2) ANN-based temperature/humidity control logic, and (3) ANN-based Predicted Mean Vote (PMV) control logic. Analysis of the thermal chamber tests revealed that the ANN-based predictive temperature/humidity control logic provided greater periods of thermal comfort than that of the conventional logic by 0.3 to 5.1 percentage points for air temperature and 0.2 percentage point for humidity as well as a reduction in over-shoots and under-shoots. In addition, the ANN-based PMV control logic provided significantly better PMV conditions than both temperature and humidity based control logics. In most cases, ANN-based controls demonstrated a reduction in electricity consumption by 11.3% to 14.0% compared to non-ANN-based control logics, resulting in reduced fan usage and air circulation.