Using deep learning to value free-form text data for predictive maintenance
Juan Pablo Usuga-Cadavid,
Samir Lamouri,
Bernard Grabot and
Arnaud Fortin
International Journal of Production Research, 2022, vol. 60, issue 14, 4548-4575
Abstract:
Past maintenance logs may encapsulate meaningful data for predicting the duration of machine breakdowns, the potential causes of a problem, or the necessity to stop production to perform repair activities. These insights may be accessed using machine learning (ML). However, maintenance logs tend to have imbalanced distributions and rely on noisy unstructured text data provided by operators. Additionally, the limited interpretability of ML models results in human reluctance when accepting model predictions. Hence, this study explored the use of two recent deep learning models (CamemBERT and FlauBERT) for natural language processing (NLP) to harness unstructured data from maintenance logs. The class imbalance effect was mitigated using data-level and algorithm-level approaches. To improve interpretability, a technique called LIME was employed to interpret single predictions and to propose a method for insight extraction from several maintenance reports. Results suggest three key points: CamemBERT and FlauBERT can achieve excellent results with minimum text pre-processing and hyperparameter tuning. Second, random oversampling (ROS) generally mitigates the effect of class imbalance. However, ROS was observed to be unnecessary when performing pertinent data pre-processing. Finally, at the maintenance level, the proposed insight extraction method can provide valuable information from a set of poorly structured maintenance reports.
Date: 2022
References: Add references at CitEc
Citations:
Downloads: (external link)
http://hdl.handle.net/10.1080/00207543.2021.1951868 (text/html)
Access to full text is restricted to subscribers.
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:taf:tprsxx:v:60:y:2022:i:14:p:4548-4575
Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/TPRS20
DOI: 10.1080/00207543.2021.1951868
Access Statistics for this article
International Journal of Production Research is currently edited by Professor A. Dolgui
More articles in International Journal of Production Research from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().