Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Automated machine learning for predictive quality in production

: Krauß, Jonathan; Machado Pacheco, Bruno; Zang, Hanno Maximilian; Schmitt, Robert Heinrich

Fulltext ()

Procedia CIRP 93 (2020), pp.443-448
ISSN: 2212-8271
Conference on Manufacturing Systems (CMS) <53, 2020, Online>
Journal Article, Conference Paper, Electronic Publication
Fraunhofer IPT ()
predictive quality; machine learning; Data Science; Automated ML; AutoML; Benchmarking; artificial intelligence; data integration; data preprocessing; Hyperparameter Tuning

Applications that leverage the benefits of applying machine learning (ML) in production have been successfully realized. A fundamental hurdle to scale ML-based projects is the necessity of expertise from manufacturing and data science. One possible solution lies in automating the ML pipeline: integration, preparation, modeling and model deployment. This paper shows the possibilities and limits of applying AutoML in production, including a benchmarking of available systems. Furthermore, AutoML is compared to manual implementation in a predictive quality use case: AutoML still requires programming knowledge and is outperformed by manual implementation - but sufficient results are available in a shorter timespan.