Deep Reinforcement Learning based real-time open-pit mining truck dispatching system

Open-pit mines are highly dynamic and uncertain environments with complex interactions between haulage and loading equipment on a shared road network. Truck fleet management systems play a crucial role in providing real-time assignments of trucks for bulk material transportation in mining operations to ensure the efficient utilization of the mine equipment assets and achieve different mining and ore processing targets. This research proposes developing a Deep Reinforcement Learning (DRL) based truck dispatching system for open-pit operations using a Double Deep Q-Learning algorithm. A discrete event simulation model of the open-pit truck and shovel environment is developed to capture uncertainties throughout the equipment operating cycle and train the DRL truck dispatching system to learn a Q-value, expected cumulative return, function to guide the dispatching decisions to meet proposed mining quantity and quality targets. A case study is presented in an iron ore deposit where the trained agent learns a robust dispatching policy to achieve the ore and waste mining targets and maintain the metal concentration of the ore feed to the processing plants within a desired range.

• Record URL:
  • https://doi.org/10.1016/j.cor.2024.106815
• Record URL:
  • http://www.sciencedirect.com/science/article/pii/S0305054824002879
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/1793974
• Supplemental Notes:
  • © 2024 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies. Abstract reprinted with permission of Elsevier.
• Authors:
  • Noriega, Roberto
  • Pourrahimian, Yashar
  • Askari-Nasab, Hooman
• Publication Date: 2025-1

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: 106815
• Serial:
  • Computers & Operations Research
  • Volume: 173
  • Issue Number: 0
  • Publisher: Elsevier
  • ISSN: 0305-0548
  • Serial URL: https://www.sciencedirect.com/journal/computers-and-operations-research

Subject/Index Terms

• TRT Terms: Dispatching; Fleet management; Machine learning; Mines; Trucks
• Subject Areas: Data and Information Technology; Freight Transportation; Operations and Traffic Management; Planning and Forecasting;

Filing Info

• Accession Number: 01932899
• Record Type: Publication
• Files: TRIS
• Created Date: Oct 7 2024 4:55PM