AI-Driven Predictive Maintenance in Mining: A Systematic Literature Review on Fault Detection, Digital Twins, and Intelligent Asset Management

Abstract

The mining industry faces increasing challenges in maintaining high production levels while minimizing unplanned failures and operational costs. Critical assets, such as crushers, conveyor belts, mills, and ventilation systems, operate under extreme conditions, leading to accelerated wear and failure risks. Traditional maintenance strategies often fail to prevent unexpected downtimes, safety hazards, and economic losses. As a response, industries are integrating predictive monitoring technologies, including machine learning, the Internet of Things, and digital twins, to enhance early fault detection and optimize maintenance strategies. This Systematic Literature Review analyzes 166 high-impact studies from Scopus and Web of Science, identifying key trends in fault detection algorithms, hybrid AI models, and real-time monitoring techniques. The findings highlight the increasing adoption of deep learning, reinforcement learning, and digital twins for anomaly detection and process optimization. Additionally, AI-driven methods are improving sensor-based data acquisition and asset management, extending equipment lifecycles while reducing failures. Despite these advancements, challenges such as data standardization, model scalability, and system interoperability persist, requiring further research. Future work should focus on real-time AI applications, explainable models, and academia-industry collaboration to accelerate the implementation of intelligent maintenance solutions, ensuring greater reliability, efficiency, and sustainability in mining operations.