Temporal Clustering Based Thermal Condition Monitoring in Building

Abstract

Recurrent or non-recurrent temperature and humidity variations trigger various damages on the inside and outside surfaces of buildings, which eventually lead to poor insulation, additional energy consumption, and expensive repairing plan. Formal thermal inspection by professionals is expensive, often inconclusive and inconvenient for continuous or frequent monitoring. Thermal condition monitoring with sensors provides data-driven knowledge of thermal properties of built environments to residents and also helps in accelerating the process of thermal inspection by the professionals. In this work, we introduce a thermal condition monitoring framework which simultaneously learns temporal feature representations of thermal condition (i.e., temperature, humidity, etc.) from inside and outside of built environment, and performs cluster assignments on the unlabeled data using deep neural network. We install thermo-hygrometers in three different homes for at least 40 days. Temporal clustering on the latent features of thermal data provides the pattern of indoor thermal conditions during different outside weather conditions. We demonstrate how indoor thermal variables respond to the outdoor thermal condition for each of the cluster patterns. Our proposed new algorithm for temporal clustering is evaluated on the collected thermal dataset from three buildings and compared with other temporal clustering algorithms, such as k-shape, deep temporal clustering (DTC), self-organizing map (SOM) from recent studies. Our framework achieves better clustering metrics and provides a non-intrusive data-driven approach to monitor indoor thermal response which saves time and resources for visual inspection by professionals. This also keeps the residents informed about the thermal condition of home with no knowledge on structural properties of buildings.