Matthew Krugh

Papers

Total Citations

H-Index

About

Matthew Krugh is a researcher specializing in predictive maintenance, machine learning applications in manufacturing, and intelligent condition monitoring systems. His work sits at the intersection of industrial automation and data-driven analytics, addressing one of modern manufacturing's most pressing challenges: minimizing unexpected equipment downtime while optimizing maintenance scheduling. Krugh's notable contributions include pioneering the application of random forest regression to collaborative robot (cobot) systems, demonstrating how purposeful failure data can train accurate anomaly detection models for UR10 cobot end-effectors — a practical and innovative approach to generating training datasets in environments where failure data is scarce. His 2021 paper on this topic has garnered 12 citations, reflecting its relevance to the growing cobot industry. Equally significant is his work on unsupervised learning for vibration analysis, also accumulating 12 citations, which addresses a critical gap in manufacturing analytics: enabling meaningful insights from sensor data even when labeled training examples are unavailable. This research empowers manufacturers to proactively track machine health without extensive manual annotation. Together, Krugh's contributions advance the practical deployment of artificial intelligence in smart manufacturing environments, making predictive maintenance more accessible and reliable for modern production facilities.