In most industrial processing scenarios the value of a product increases over time in the value chain. To avoid unnecessary processing steps, it is of immense importance to detect defects as early as possible in the value creating process. These situations of interest can be distinguished as specified and unspecified situations, dependent on whether the cause-effect relation is known and defined or not. In this article we describe ongoing work on a proactive disruption management system for manufacturing environments, which helps being prepared for the unexpected by applying a combination of unsupervised and supervised machine learning for the identification and prediction of unspecified situations and adopting data mining techniques to derive predictive patterns for specified situations. We also introduce a real-world use case from the field of semiconductor manufacturing and present first preliminary results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.