Application of Deep Learning on Gage R&R for Anomaly Detection

Abstract

This research examines the use of deep learning techniques, particularly autoencoders, to improve Gage Repeatability and Reproducibility (Gage R&R) assessments within quality engineering. Gage R&R serves as a crucial aspect of Measurement System Analysis (MSA), designed to evaluate the variation within measurement systems. The focus of the study lies on the use of unsupervised deep learning models to detect anomalies in measurement systems, thus improving reliability and efficiency in quality control processes. This study integrates theoretical foundations, literature reviews, and empirical analyses to present a comprehensive understanding of the subject.

Start Time

16-4-2025 1:30 PM

End Time

16-4-2025 4:00 PM

Presentation Type

Poster

Presentation Category

Science, Technology and Engineering

Student Type

Graduate Student - Masters

Faculty Mentor

Jeff Knisley

Faculty Department

Mathematics and Statistics

This document is currently not available here.

Share

COinS
 
Apr 16th, 1:30 PM Apr 16th, 4:00 PM

Application of Deep Learning on Gage R&R for Anomaly Detection

This research examines the use of deep learning techniques, particularly autoencoders, to improve Gage Repeatability and Reproducibility (Gage R&R) assessments within quality engineering. Gage R&R serves as a crucial aspect of Measurement System Analysis (MSA), designed to evaluate the variation within measurement systems. The focus of the study lies on the use of unsupervised deep learning models to detect anomalies in measurement systems, thus improving reliability and efficiency in quality control processes. This study integrates theoretical foundations, literature reviews, and empirical analyses to present a comprehensive understanding of the subject.