Machine learning models for estimating the consumed and remaining useful life of haul trucks in an open-pit mine in Peru

Authors

• Marco Cotrina, Design and planning of mine – DIPLAMIN research team, National University of Trujillo, Trujillo, PeruFollow
• Jairo Marquina, Design and planning of mine – DIPLAMIN research team, National University of Trujillo, Trujillo, Peru
• Mario Sandoval, Design and planning of mine – DIPLAMIN research team, National University of Trujillo, Trujillo, Peru
• Jose Mamani, National University of the Altiplano, Faculty of Chemical Engineering, Peru
• Johnny Ccatamayo, Department of Mining Engineering, Universidad Nacional San Cristóbal de Huamanga, Ayacucho, Peru

Author ORCID Identifier

Marco Antonio Cotrina-Teatino: 0000-0003-3801-0370

Jairo Jhonatan Marquina-Araujo: 0000-0002-5880-8227

Mario David Sandoval-Carranza: 0000-0002-9965-2820

Jose Nestor Mamani-Quispe: 0000-0001-7803-7936

Johnny Henrry Ccatamayo-Barrios: 0000-0002-5798-4851

Abstract

The purpose of this study was to develop a machine learning-based model to predict the consumed useful life and estimate the remaining useful life of haul trucks in an open-pit mining operation in Peru. A comparative analysis of multiple machine learning models was conducted, including multiple linear regression (MLR), random forest + PSO, support vector regression (SVR), gradient boosting machine (GBM), decision tree + PSO, and artificial neural networks (ANN-MLP). The models were evaluated using performance metrics such as R², RMSE, and MAE, selecting the optimal model to estimate the remaining useful life based on a theoretical lifespan of 25,000 hours. The SVR model was the most accurate, achieving R² = 0.92 in validation, with an RMSE of 1.36 and an MAE of 0.97. The estimated remaining useful life revealed that haul truck V_2205 had the highest operational availability (3 years and 11 months), while V_2202 had the lowest (11 months). These findings highlight not only the importance of predictive maintenance, but also the novelty of modeling daily UL as an intermediate target to improve the realism and interpretability of RUL estimation in mining operations

Recommended Citation

Cotrina, Marco; Marquina, Jairo; Sandoval, Mario; Mamani, Jose; and Ccatamayo, Johnny (2026) "Machine learning models for estimating the consumed and remaining useful life of haul trucks in an open-pit mine in Peru," Journal of Sustainable Mining: Vol. 25 : Iss. 3 , Article 11.
Available at: https://doi.org/10.46873/2300-3960.1513

Creative Commons License

This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.