Machine learning and AI for long-term fault prognosis in complex manufacturing systems Academic Article

abstract

• 2019 Recent advances in sensors and other streaming data sources of plant floor automation and information systems open an exciting possibility to predict the risks of faults and breakdowns across a manufacturing plant over much longer time horizons than what is conceivable today. This paper introduces a Manufacturing System-wide Balanced Random Survival Forest (MBRSF), a nonparametric machine learning approach that can fuse complex dynamic dependencies underlying these data streams to provide a long-term prognosis of machine breakdowns. Experimental investigations with a 20 machine automotive manufacturing line suggest that MBRSF reduces prediction errors (Brier scores) by over 90% compared to other methods tested.

authors

• Bukkapatnam, Satish

published proceedings

• CIRP ANNALS-MANUFACTURING TECHNOLOGY

author list (cited authors)

• Bukkapatnam, S., Afrin, K., Dave, D., & Kumara, S.

citation count

• 22

complete list of authors

• Bukkapatnam, Satish TS||Afrin, Kahkashan||Dave, Darpit||Kumara, Soundar RT

publication date

• January 2019

publisher

• Elsevier  Publisher

published in

• n0007-8506ISSN  Journal

keywords

• Artificial Intelligence
• Manufacturing System
• Performance

Digital Object Identifier (DOI)

• 10.1016/j.cirp.2019.04.104

start page

• 459

end page

• 462

volume

• 68

issue

• 1

URL

• http://dx.doi.org/10.1016/j.cirp.2019.04.104