Analyzing heating equipment's operations based on measured data.

A heating (or cooling) equipment's operation is consisted of cycles. In each cycle, the equipment operates to generate heat to raise the room temperature and shuts down when the desired temperature is reached. This research studies the cyclic characteristics of typical gas burning furnaces. Each cycle is divided into runtime and idle states. The runtime process is further decomposed into three phases: startup, stable operation and shutdown. The measured data shows that the length of runtime in each cycle remains constant but idle time varies from cycle to cycle responding to outdoor environmental conditions. Four Data Mining Algorithms (DMAs) including k-Nearest Neighbors (KNN), Naive Bayes (NB), Support Vector Machines (SVM) and Artificial Neural Networks (ANN) are used to analyze the relationship between cycle idle time and weather conditions based on actual minute-by-minute electricity usage data of two furnaces in a residential house and weather data from the near-by weather station for a period of four months (January to April 2011). The obtained results show that SVM and ANN provide more accurate predictions of idle time. Parametric correlation analysis indicates that indoor–outdoor temperature difference and wind speed are two key parameters affecting cycle idle time. The obtained results on the cyclic characteristics of a heating equipment provide essential information for estimate heating energy demand according to weather conditions, determining the equipment's energy efficiency, and diagnosing potential faults in its operation. [ABSTRACT FROM AUTHOR]