Exploring digital twin systems in mining operations: A review
Pouya Nobahar, Chaoshui Xu, Peter A. Dowd, Roohollah Shirani Faradonbeh
Abstract
Constant attempts have been made throughout human history to find solutions to complex issues. These attempts resulted in industrial revolutions and the transition from manual labor to machines and new technologies. The latest advancements in artificial intelligence (AI) are revolutionary. The use of these smart technologies in mining can lead to increased profitability, enhanced performance, improved safety, and better adherence to environmental regulations. In this paper, the applications of AI and digital twin systems in mining operations are reviewed, covering various components, including mineral exploration, drilling, blasting, loading, hauling, mineral processing, and environmental issues. Critical data inputs for each component are identified, and relevant tools and methods are discussed. These will facilitate the development of digital twin models with learning, simulation, prediction, and optimization capabilities. This study provides valuable insights into fully integrated digital twin mining systems, which will significantly improve mining efficiency and sustainability. Although innovative technologies, such as the Internet of Things (IoT) and other intelligent tools, are increasingly being used in the mining sector, many mining processes still depend on human oversight to deal with challenges, such as remote operations, geological variability, high investment costs, and a skills gap. There is, therefore, significant potential to enhance the use of sensors and IoT devices to support data collection for more integrated and powerful digital twin systems to drive further innovation and operational improvements across the mining value chain.