An Application of Clustering and Cluster Update Methods to Boiler Sensor Prediction and Case-Based-Reasoning to Boiler Repair

Abstract

Driven by demand from both consumers and manufacturers alike, Internet of Things (IoT) capabilities are being built into more products. Consumers want more control and access to their devices, while manufacturers can find data gathered from IoT-capable products invaluable. In this thesis, we use data from a growing fleet of IoT-connected boilers in the residential, lightcommercial, and medium-commercial ranges to demonstrate a framework for cluster initialization and updating. We compare two methods of dynamically updating clusters: a sequential method inspired by sequential K-means clustering and a cohesion-based method called DYNC. A predictive artificial neural network system demonstrates the effectiveness of the clustering methods. In a secondary topic, a multi-tiered case-based reasoning system (CBR) is created based on boiler problem and repair support cases. Word embeddings are extracted from case comments and used to predict potential solutions to problems and problem categories using user selection and input. The primary tier uses information about actions taken involving specific parts, along with comments fed through the word embedding model, to predict the correct next step. The secondary tier uses only case comments to provide categories of likely symptoms and solutions. The third tier is a pure probability fall-back model.