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

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.

author list (cited authors)

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

citation count

  • 9

publication date

  • January 2019