Forecast-Based Decision Framework for Replacement of Ros and Onboard Components in Autonomous Loaders: A Case Study at GBC Mine PT Freeport Indonesia
Downloads
The mining industry plays a critical role in global economic activities, particularly in supporting the supply of essential raw materials. In Indonesia, PT Freeport Indonesia operates the Grasberg Block Cave (GBC) underground mine, which utilizes autonomous loaders integrated with the Remote Operating System (ROS). The reliability of ROS and its onboard components is essential to ensure continuous production and operational efficiency in a complex underground environment. This study aims to develop a forecast-based decision framework to determine the optimal timing for component replacement in autonomous loaders. A quantitative approach was employed using time-series forecasting based on historical downtime and component replacement data from 2023 to 2025. The Autoregressive Integrated Moving Average (ARIMA) model was applied to identify failure patterns and predict future degradation trends. The results indicate that component failures, particularly in joystick and other critical onboard systems, follow a non-random and progressive degradation pattern influenced by environmental and operational factors such as vibration, dust, humidity, and intensive usage. The ARIMA (1,0,1) model demonstrates adequate performance in capturing temporal failure behavior and supporting maintenance planning. The proposed decision framework integrates forecasting outputs, degradation trends, and operational risk considerations to support proactive maintenance strategies. The implementation of this framework is estimated to reduce downtime-related production loss by approximately 62.5%, equivalent to around 5,750 tons per month. These findings highlight the practical value of integrating forecasting models into maintenance decision-making processes. This study contributes to predictive maintenance practices by bridging the gap between failure prediction and operational decision-making in autonomous mining systems.
Adelakun, B. O. (2023). AI-driven financial forecasting: Innovations and implications for accounting practices. International Journal of Advanced Economics.
Ahern, M. (2022). Development of a framework to aid the transition from reactive to proactive maintenance approaches to enable energy reduction. Applied Sciences.
Ampaw-Asiedu, D., Avickson, E. K., & Nyonyoh, N. (2024). Financial forecasting and planning: Predictive models that support agile financial planning by adjusting forecasts based on emerging trends and macroeconomic factors. Journal Homepage, 7421.
Benhaifia, A. (2025). Systematic review of predictive maintenance practices in the manufacturing sector. Intelligent Systems with Applications.
Bouazizi, S., & Ltifi, H. (2024). Enhancing accuracy and interpretability in EEG-based medical decision making using an explainable ensemble learning framework: Application for stroke prediction. Decision Support Systems, 178, Article 114126.
Chen, L. (2023). Machine learning methods in weather and climate applications: A survey. Applied Sciences.
Cristofaro, M. (2025). Growth hacking: A scientific approach for data-driven decision making. Journal of Business Research.
Dayo-Olupona, O. (2023). Adoptable approaches to predictive maintenance in mining industry: An overview. Resources Policy.
Di, J. (2025). Comparative analysis of time-series forecasting models for Eloran systems: Exploring the effectiveness of dynamic weighting. Sensors.
Fatima, S. S. (2024). A review of time-series forecasting algorithms for industrial manufacturing systems. Machines.
Ficili, I. (2025). From sensors to data intelligence: Leveraging IoT, cloud, and edge computing with AI. Sensors.
Goli, M. (2025). A literature review-based evaluation framework for maintenance strategy selection in heavy vehicles. Results in Engineering.
Hossain, M. N., & Mita, T. A. B. (2024). An empirical study of big data-enabled predictive analytics and their impact on financial forecasting and market decision-making. Review of Applied Science and Technology, 3(1), 143–182.
Loboichenko, V. (2025). Review of advances in fire extinguishing based on computer vision applications: Methods, challenges, and future directions. Sensors.
Misra, K. B. (2008). Reliability engineering: A perspective.
Owen, A. (2024). Predictive analytics for demand forecasting in manufacturing. ResearchGate.
Ozpinar, A., & Soofastaei, A. (2025). Harnessing the convergence of information technology and operational technology for digital transformation: An integrated framework for effective project management, skill development, team coordination, and collaboration in manufacturing industry. In Advanced analytics for Industry 4.0 (pp. 117–193). CRC Press.
Ptfi. (2025). PTFI. Retrieved from https://ptfi.co.id
Rahman, S. M. T., & Hye, A. (2022). Data driven business intelligence tools in agribusiness: A framework for evidence-based marketing decisions. International Journal of Business and Economics Insights, 2(1), 35–72.
Souza, G. A. (2026). Data storytelling in intelligent analytics systems: From visualization to decision intelligence. Journal International Review of Research Studies, 1(3), 1–90.
Urrea, C. (2025). Semantic priority navigation for energy-aware mining robots. Systems.
Vudugula, S. (2023). Integrating artificial intelligence in strategic business decision-making: A systematic review of predictive models. International Journal of Scientific Interdisciplinary Research.
Copyright (c) 2026 Paskah Handikardo Benjamin Nainggolan, Nur Budi Mulyono
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
