306 3. CONCLUSION This paper presents an adaptive machine learning–based Automatic Operator Guidance System (AOGS) designed to optimize haul truck productivity in open-pit coal mining operations. The study integrates real-time telematics, GPS, and operational data to model the relationship between operator behavior, road conditions, and haulage performance. A physics-informed adaptive learning framework is developed to generate optimal speed recommendations and predict cycle times under dynamic operational conditions. The system incorporates a rulebased guidance engine that translates model outputs into real-time, actionable feedback for operators, improving driving consistency and safety. Field validation demonstrates significant operational benefits, including reduced fuel consumption, decreased braking events, and improved cycle-time stability. The implementation resulted in an overall productivity increase of approximately 6%, highlighting the effectiveness of personalized, data-driven operator guidance. The findings confirm that adaptive machine learning integrated with fleet management systems provides a scalable and practical solution for enhancing efficiency, safety, and decisionmaking in large-scale mining operations. REFERENCES [1] Najor J and Hagan P 2004 Mine Production Scheduling within Capacity Constraints (Sydney: The University of New South Wales) [2] Komatsu 2009 Specifications and Application Handbook (Japan: Komatsu Ltd) [3] Chaowasakoo P et al 2017 Digitalization of mine operations: Scenarios to benefit in real-time truck dispatching International Journal of Mining Science and Technology 27 229–236 [4] Smith, J., “Machine Learning in Mining Operations,” Mining Engineering Journal, 2022. [5] Stevenson W J and Ozgur C 2007 Chapter 13. Waiting-line models. Introduction to management science with spreadsheets. (London: McGraw-Hill Irwin) [6] Gross D and Harris C M 1998 Fundamentals of Queueing Theory (New York: John Wiley & Sons, Inc) [7] Giffin W C 1978 Queueing: Basic Theory and Applications (Columbus, Ohio: Grid, Inc) [8] Caterpillar, Haul Road Design Guidelines, CAT Global Mining, 2019 [9] Bishop, C. M., Pattern Recognition and Machine Learning, Springer, 2006.
RkJQdWJsaXNoZXIy MTM0Mzk2