A course of action to data-driven Predictive Maintenance

Xenia Klinge, Jens Haupert

In: Hamid R. Arabnia , David de la Fuente , Elena B. Kozerenko , Jose A. Olivas , Fernando G. Tinetti (Hrsg.). ICAI'18. Proceedings of the 2018 International Conference on Artificial Intelligence. International Conference on Artificial Intelligence (ICAI-18) befindet sich 2018 World Congress in Computer Science, Computer Engineering, & Applied Computing (CSCE'18) July 30-August 2 Las Vegas Nevada United States Seiten 71-74 ISBN 1-60132-480-4 CSREA Press United States of America 2018.


Predictive Maintenance is a core component of the modernization efforts of the "Industry 4.0". Its goal is to save costs by predicting machine errors in advance, so that maintenance actions can be taken as soon as, but only when necessary. In the plethora of data science methods, no silver bullet exists for this task. Instead, models have to be tailored to a specific problem by applying the right techniques to leverage the right data. Instead of describing a specific use case in detail, we propose a course of action to introduce Predictive Maintenance to an existing environment: by relying on data-driven techniques, the presented framework is applicable to different scenarios.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence