Predictive Maintenance of Mining Centrifuges Using Machine Learning and Deep Learning Models

This study facilitates the achievement of Sustainable Development Goals (SDG 9: Industry, Innovation, and Infrastructure and SDG 13: Climate Action) using intelligent maintenance solutions. Achieving operational and environmental sustainability in the mining sector poses significant challenges that require innovative solutions to enhance equipment efficiency and minimize unforeseen failures. The current research formulates a predictive maintenance system is utilizing Artificial Intelligence (AI) and Machine Learning (ML) techniques, based on the analysis of sensor data from industrial centrifuges. Deep Neural Networks (DNN), Long Short-Term Memory (LSTM), K-Nearest Neighbors (KNN), Naïve Bayes (NB), Logistic Regression (LR), and XGBoost are evaluated. XGBoost demonstrated exceptional proficiency in managing time-series data, achieving the highest accuracy of 99.80%, followed by LSTM. These results underscore the potential of ML techniques to optimize predictive maintenance, reduce energy and resource consumption, enhance operational efficiency, and promote sustainable industrial practices.