Data-Driven Smart Manufacturing Technologies for Prop Shop Systems

Authors

• Zhicheng Xu, Florida Institute of Technology
• Weinan Gao, Florida Institute of Technology
• Zhicun Chen, Florida Institute of Technology
• Rami J. Haddad, Georgia Southern UniversityFollow
• Scot Hudson, LLC
• Ezebuugo Nwaonumah, LLC
• Frank Zahiri, MXSG
• Jeremy Johnson, MXSG

Document Type

Article

Publication Date

5-23-2023

Publication Title

Proceedings - 2023 IEEE/ACIS 21st International Conference on Software Engineering Research, Management and Applications, SERA 2023

DOI

10.1109/SERA57763.2023.10197769

ISBN

9798350345889

Abstract

In this paper, a data-driven framework was designed to predict manufacturing failure. The framework includes an autoregression model with the least mean square algorithm, a linear regression model with prediction intervals for short-Term and long-Term failure detection, and a feature extraction model with empirical mode decomposition. The analytical results validate that the designed data-driven model is a good candidate for failure predictions in smart manufacturing processes.

Comments

Georgia Southern University faculty members, Rami Haddad co-authored "Data-Driven Smart Manufacturing Technologies for Prop Shop Systems."

Recommended Citation

Xu, Zhicheng, Weinan Gao, Zhicun Chen, Rami J. Haddad, Scot Hudson, Ezebuugo Nwaonumah, Frank Zahiri, Jeremy Johnson. 2023. "Data-Driven Smart Manufacturing Technologies for Prop Shop Systems." Proceedings - 2023 IEEE/ACIS 21st International Conference on Software Engineering Research, Management and Applications, SERA 2023: 189-194. doi: 10.1109/SERA57763.2023.10197769 isbn: 9798350345889
https://digitalcommons.georgiasouthern.edu/electrical-eng-facpubs/183

Copyright

See the publisher's copyright and reuse policies.