Data-enabled Bayesian inference for strategic maintenance decisions in industrial operations

• Published in: Data in brief 2024-12, Vol.57, p.111058, Article 111058
• Main Authors: Torres-Sainz, Raúl, Lorente-Leyva, Leandro L., Arbella-Feliciano, Yorley, Trinchet-Varela, Carlos Alberto, Pérez-Vallejo, Lidia María, Pérez-Rodríguez, Roberto
• Format: Article
• Language: English
• Subjects: Intelligent predictive maintenance; Maintenance management; Maintenance strategy selection; Monte Carlo simulation
• ISSN: 2352-3409; 2352-3409
• DOI: 10.1016/j.dib.2024.111058

Efficient management of industrial assets and equipment depends heavily on the selection of appropriate maintenance strategies. This research presents a dataset generated through Monte Carlo simulations to evaluate 12 key criteria relevant to maintenance strategy selection. The dataset covers a wide range of potential maintenance scenarios, providing comprehensive data for researchers to explore various strategies in industrial settings. The data were normalized and structured in a way that facilitates their use for further modeling or analysis. The dataset offers an opportunity for researchers to reproduce the data collection process, enabling comparisons with their own studies. By providing this dataset, we aim to support the development of new models for maintenance strategy selection and encourage further exploration of data-driven approaches in industrial maintenance. Additionally, the dataset can serve educational purposes, assisting in the teaching of decision-making in the context of maintenance operations.