A Comparative Study Between Thermostat/Hygrometer-Based Conventional and Artificial Neural Network-Based Predictive/Adaptive Thermal Controls in Residential Buildings

作者：Moon Jin Woo; Han Seung Hoon^*

来源：Journal of Asian Architecture and Building Engineering, 2012, 11(1): 169-176.

DOI：10.3130/jaabe.11.169

• artificial neural network
• predictive controls
• adaptive controls
• thermal comfort
• PMV control

This study aimed at testing 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 overshoots and undershoots 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. Performance tests were conducted in a thermal chamber for non-application of setback and application of setback of thermal factors. Analysis revealed that the ANN-based predictive temperature/humidity control logic generally provided greater periods of thermal comfort than that of the conventional logic, as well as a reduction in overshoots and undershoots. In addition, the ANN-based PMV control logic provided significantly better PMV conditions than both temperature/humidity based control logics. In more cases, ANN-based control logic demonstrated a reduction in electricity consumption, compared to non-ANN-based control logic, especially for a system with a large time-lag effect such as a radiant water heating system.

• 出版日期2012