Explainable AI in Manufacturing: A Predictive Maintenance Case Study - Advances in Production Management Systems. Towards Smart and Digital Manufacturing Access content directly
Conference Papers Year : 2020

Explainable AI in Manufacturing: A Predictive Maintenance Case Study

Bahrudin Hrnjica
  • Function : Author
  • PersonId : 1132109
Selver Softic
  • Function : Author
  • PersonId : 1132110

Abstract

This paper describes an example of an explainable AI (Artificial Intelligence) (XAI) in a form of Predictive Maintenance (PdM) scenario for manufacturing. Predictive maintenance has the potential of saving a lot of money by reducing and predicting machine breakdown. In this case study we work with generalized data to show how this scenario could look like with real production data. For this purpose, we created and evaluated a machine learning model based on a highly efficient gradient boosting decision tree in order to predict machine errors or tool failures. Although the case study is strictly experimental, we can conclude that explainable AI in form of focused analytic and reliable prediction model can reasonably contribute to prediction of maintenance tasks.
Fichier principal
Vignette du fichier
592-57.pdf (176.93 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03635701 , version 1 (08-04-2022)

Licence

Attribution

Identifiers

Cite

Bahrudin Hrnjica, Selver Softic. Explainable AI in Manufacturing: A Predictive Maintenance Case Study. IFIP International Conference on Advances in Production Management Systems (APMS), Aug 2020, Novi Sad, Serbia. pp.66-73, ⟨10.1007/978-3-030-57997-5_8⟩. ⟨hal-03635701⟩
214 View
762 Download

Altmetric

Share

Gmail Facebook X LinkedIn More