Useful Life Prediction of Bearings in Abrasive Environments through FEM Modeling, IoT Validation, and Visual Training Using Machine Learning

Torres Hinostroza A.; Julian Daga R.; Poma Tintaya E.; Del Aguila Ramos J.; Huari Huaman O. · Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology (2026) · DOI: 10.18687/laccei2026.1.1.2394

Resumen

The reliability of rolling bearings in mining machinery is essential for maintaining operational continuity in extreme environments such as Cerro de Pasco, Peru, where abrasive particles, humidity, and cyclic loads accelerate mechanical degradation. To overcome the limitations of conventional maintenance approaches, this study proposes a hybrid methodology for predicting the Remaining Useful Life (RUL) of industrial bearings by integrating Finite Element Modeling (FEM), IoT-based monitoring, and machine learning techniques. The analysis focuses on the SKF 22244 CC/W33 spherical roller bearing used in crushers and grinding mills. FEM simulations identified stress concentration zones under realistic loads, while vibration, temperature, and pressure data acquired through IoT sensors were used to train XGBoost and Random Forest models for RUL prediction. Additionally, a Convolutional Neural Network (CNN) classified wear severity from bearing images with accuracy above 93%. Results indicate that actual bearing lifespan in abrasive environments may decrease by up to 15% compared with ISO 281 theoretical predictions, highlighting the importance of predictive models adapted to real operating conditions. Cross-validation between simulations, sensor data, and intelligent algorithms confirmed the robustness of the proposed approach for early fault detection, maintenance optimization, and reliability improvement in mining systems.

Instituciones: Universidad Continental