SUMMARY
Over the last several years, distributed computing has enabled sensor data acquisition on an unprecedented scale. Using wireless networking, the Internet of Things has dramatically changed the landscape of how devices are monitored. In some areas, such change remains to be manifested. Specifically, significant advancements remain to be made in the way data are captured and utilized in the manufacturing sector. Several challenges inhibit growth in this research area. First, the nature of manufacturing can require the analysis of a large variety of machine tools with unique mechanical characteristics. These various tools also utilize a number of unique communication protocols and can have non-intuitive, nonstandard syntax. Additionally, the proprietary nature of the machine controllers can inhibit access to the more informative machine parameters. This thesis will advance the state-of-the-art in data acquisition and utilization for machine health and process monitoring of advanced manufacturing systems. Specifically, this work proposes an integrated architecture for standardized data acquisition, storage, and analysis with the objective of characterizing and tracking the health and utilization of manufacturing equipment. Special considerations are made for developing an interpretable analytics engine in edge computing devices. By using this approach, storage, bandwidth, and centralized computing needs can be dramatically reduced compared alternative approaches.