SUMMARY

The past decade has seen an explosion in the capabilities of distributed computing, the Internet of Things, and open source software and hardware. As a result, internet connectivity has become ubiquitous across nearly all industries. Within the manufacturing sector, machine controllers now support protocols which make very detailed utilization information accessible. In addition, advances in embedded computing enable distributed, low-cost sensor deployment on an unprecedented scale. Leveraging these advances in data availability, this work presents a methodology for machine health monitoring in an Internet of Things architecture. Using modern messaging protocols, bidirectional communication between machine controllers and external sensors enables contextual data acquisition for tracking health trends in manufacturing equipment. Using modern machine learning tools and embedded computing, a low-cost, integrated data acquisition platform is proposed in this work. Built on modern, open-source hardware and software, this platform enables high-quality sensor data acquisition and edge-based computation to facilitate machine health monitoring in an IoT framework. By leveraging proposed protocols for edge-based feature extraction, large sensor samples are reduced in size to facilitate health monitoring and near real-time inference. This proposed methodology compares favorably to cloud-based solutions. A case study in tool wear analysis shows that CNC controller data may be used to contextualize accelerometer measurements, and in turn facilitate training novelty detection and classification algorithms. These algorithms are then deployed to the edge device for near-real time inference.