Schäfer F, Schwulera E, Otten H, Franke J (2019)
Publication Language: English
Publication Type: Conference contribution, Conference Contribution
Publication year: 2019
Event location: Laguna Hills, California
URI: https://ieeexplore.ieee.org/document/9027777
DOI: 10.1109/AI4I46381.2019.00017
Ongoing changes in the field of information technology and increasing data availability in combination with open source software for data mining and machine learning algorithms require companies to rethink their process improvement strategy. For the zero defect goal within production lines, new optimization potentials arise that need to be raised. This also comprises to think ahead of already existing and well-established methods for process improvement like Six Sigma from descriptive to predictive. This paper addresses the progress of improving processes not only with descriptive analytics in retrospect, but also forward-looking predictive algorithms. We state the similarities and differences of both approaches and how to bridge the gap. Two practical use cases within the field of electronics production underline this approach and point out important steps and challenges.
APA:
Schäfer, F., Schwulera, E., Otten, H., & Franke, J. (2019). From Descriptive to Predictive Six Sigma: Machine Learning for Predictive Maintenance. In Proceedings of the IEEE Artificial Intelligence for Industries. Laguna Hills, California.
MLA:
Schäfer, Franziska, et al. "From Descriptive to Predictive Six Sigma: Machine Learning for Predictive Maintenance." Proceedings of the IEEE Artificial Intelligence for Industries, Laguna Hills, California 2019.
BibTeX: Download