Machine Learning for Predictive Maintenance in Industry 4.0: A Systematic Review of Algorithms and Implementation Cases (#1804)

Authors

Fernández Salazar, Jessica Karina

Angulo Corcuera, Carlos Antonio

Suysuy Chambergo, Ericka Julissa

Castañeda Gonzales, Jaime Laramie

Izquierdo Espinoza, Julio Roberto

Pérez Najera, Celín

Otero Gonzales, Carlos Alberto

Abstract

The objective of the present study was to characterize the implementations of Machine Learning algorithms in predictive maintenance within the framework of Industry 4.0, with emphasis on its applicability and adaptation to the Latin American context, calculating on empirical evidence documented between 2018 and 2024, it was carried out through a narrative-analytical approach, complemented with a quantitative analysis of performance metrics, this combination allowed identifying best practices and critical success factors, as well as making objective comparisons between approaches and solutions, offering a comprehensive vision of the trends in predictive maintenance, where a gradual and adaptive approach is required, using traditional algorithms to balance complexity and viability in contexts with limited resources, observing a trend towards hybrid systems that facilitate the transition to Industry 4.0, especially for SMEs through continuous training and the development of human capital are key to ensuring the success and sustainability of these technologies.