Date of Award

December 2019

Degree Type

Thesis

Degree Name

Master of Science

Department

Engineering

First Advisor

Amol D Mali

Committee Members

Chiu Law, Jaejin Jang

Keywords

Boilers, Case-Based Reasoning, Clustering, Machine Learning, Natural Language Processing, Neural Networks

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.

Available for download on Friday, January 07, 2022

Share

COinS