Underground mining, essential for global raw material supply, and here especially for the majority of critical raw materials, faces significant challenges, including worker safety, operational efficiency and environmental sustainability, Christel Füllenbach and Professor Helmut Mischo*, write.
Traditionally, maintenance strategies in this sector relied heavily on manual inspections and time-based preventive maintenance schedules. However, these conventional approaches have often proven labour-intensive, costly and insufficient in predicting or preventing equipment failures effectively. Recent advancements in digitalisation and automation – specifically through condition monitoring, predictive maintenance and automated inspections – are now offering transformative potential for maintenance strategies in underground mining, addressing core industry challenges.
Limitations of traditional maintenance in mining
For decades, underground mining maintenance depended on manual inspections and predetermined maintenance schedules, with equipment servicing occurring at fixed intervals regardless of its actual condition. While useful, these time-based preventive measures are inherently limited, often leading to unnecessary maintenance tasks or, conversely, to unexpected equipment failures. For example, skilled personnel conduct regular checks based on experience and judgment, which can lead to inconsistencies and the potential for missed early warnings of equipment issues (Kruczek, P., et al., 2019, p. 459 ff.). Moreover, traditional maintenance is resource-intensive, involving substantial manual labour in hazardous underground environments, which increases safety risks and operational costs (Salami, O., B., et al., 2023, p. 617 ff.).
Digitalisation and automation: Transforming maintenance strategies
During the last 15 years, the continuous shift toward digitalised and automated solutions in maintenance marks a fundamental evolution in underground mining. Condition monitoring, predictive maintenance and automated inspection systems each bring specific advantages in enhancing operational efficiency and reliability.
The implementation of condition monitoring enables real-time data collection on equipment parameters, including temperature, vibration and pressure, via sensor networks. By analyzsng this data, mining operators can determine the precise maintenance needs of machinery, rather than relying on inflexible schedules. Case studies indicate that condition monitoring reduces unexpected downtime significantly; for instance, in one South African underground mine, implementing this approach led to a 30% reduction in downtime, offering clear benefits for reliable, uninterrupted operations (Aqueveque, P. et al., 2021, p. 17365 ff.; Rihi, A., et al., p. 2483 ff.).
Building on this, predictive maintenance applies advanced machine-learning algorithms to forecast machinery failures before they occur, effectively shifting maintenance from a reactive to a proactive stance. By anticipating equipment issues, predictive maintenance reduces the need for emergency repairs and limits personnel exposure in high-risk zones. Studies have shown that predictive maintenance can reduce machinery downtime by up to 20%, while also improving safety standards (Putha, S., 2022, p. 160 ff.). In one notable instance, a mining operation utilising predictive maintenance algorithms experienced a significant drop in operational disruptions, illustrating the potential of data-driven maintenance in high-stakes environments like underground mining (Dayo-Olupona, O., 2023, p. 12 ff.).
As one of the most recent developments, automated inspection systems, including drones and robotics, offer further advancements by conducting inspections in hazardous or hard-to-reach areas without requiring direct human involvement. Drones, equipped with high-resolution cameras and other sensors, perform routine inspections with exceptional speed and accuracy, contributing to reduced inspection times and enhanced data precision. A mining company, for instance, achieved a 50% reduction in inspection time after deploying drones for regular equipment checks, thus underscoring both the efficiency and safety improvements achievable with automation (Weyers, E., 2021, S. 55 ff.).
Benefits and sustainability of digitalised maintenance strategies
The implementation of digitalised and automated maintenance strategies offer distinct advantages across safety, efficiency and sustainability metrics. Enhanced safety is one of the primary outcomes, as digital and automated tools reduce the need for personnel to conduct inspections in hazardous areas, lowering accident rates associated with traditional manual checks. Efficiency gains are equally significant; with precise maintenance scheduling enabled by data analytics, companies minimise unnecessary downtime and maximise machinery lifespan. Furthermore, this approach contributes to cost reductions, as predictive and condition-based maintenance reduce both emergency repair costs and the long-term expenses of equipment replacement (Jasiulewicz-Kaczmarek, M., 2019, p. 91 ff.).
From a sustainability perspective, automated and predictive maintenance models contribute directly to resource conservation. The reduction in maintenance frequency and improved operational efficiency lower energy consumption and material waste, aligning with circular economy principles. Automated inspections and predictive models foster an eco-friendlier mining operation by reducing carbon emissions and minimising waste outputs, which is increasingly critical for an industry under pressure to meet stringent environmental standards (Firoozi, A., et al., 2024, p. 2 ff.).
Current R&D and outlook
Current research in underground mining maintenance is focused on refining digital and automated solutions to enhance predictive accuracy and operational efficiency. Advances in machine learning are boosting predictive maintenance models, allowing improved anticipation of equipment failures by analysing large, complex data sets, such as vibration and acoustic signals (Chimunhu, P., et al., 2024, p. 30 ff.). Additionally, IoT-enabled sensors are becoming more resilient and effective in extreme underground conditions, facilitating real-time equipment monitoring and environmental data collection (Wu, Y., et al., 2019, p. 9 ff..).
Robotics also continues to improve automated inspection capabilities, with drones and autonomous vehicles now better equipped for navigating hazardous underground areas. Future developments are likely to see fully-autonomous drones that can perform inspections without operator intervention, significantly reducing human risk exposure (Zhang, R., et al-. 2023, p. 2460 ff.).
Looking forward, emerging innovations may lead to self-diagnosing and even self-correcting systems that will enable continuous operation with minimal manual maintenance. Collaboration between mining companies, technology providers and academia is also advancing universal digital standards, supporting broader adoption of automated maintenance technologies worldwide (Suhail A.H., et al., 2024, p. 150 ff.).
The integration of digitalised and automated maintenance strategies represents a critical evolution in underground mining, enhancing safety, operational efficiency and sustainability. These technologies allow mining companies to optimise their maintenance practices, reducing operational risks and improving equipment longevity while minimising environmental impacts. As digital and automated solutions continue to evolve, their transformative impact on underground mining will likely deepen, setting new industry standards for safety, productivity and environmental responsibility.
*Christel Füllenbach is Global Operations Manager at Epiroc; and Professor Helmut Mischo is from TU Bergakademie Freiberg’s Institute of Mining Engineering and Special Civil Engineering
Aqueveque, P., Radrigan, L., Pastene, F., Morales, A. S., & Guerra, E. (2021). Data-Driven Condition Monitoring of Mining Mobile Machinery in Non-Stationary Operations Using Wireless Accelerometer Sensor Modules. IEEE Access, 9, 17365-17381. https://doi.org/10.1109/ACCESS.2021.3051583.
Chimunhu P, Topal E, Asad MWA, Faradonbeh RS, Ajak AD. (2024). The future of underground mine planning in the era of machine learning: Opportunities for engineering robustness and flexibility. Mining Technology.
Dayo-Olupona, O., Genc, B., Celik, T., & Bada, S. (2023). Adoptable approaches to predictive maintenance in mining industry: An overview. Resources Policy, 86(Part A), 104291. ISSN 0301-4207. https://doi.org/10.1016/j.resourpol.2023.104291.
Firoozi, A. A., Tshambane, M., Firoozi, A. A., & Sheikh, S. M. (2024). Strategic load management: Enhancing eco-efficiency in mining operations through automated technologies. Results in Engineering, 24, 102890. ISSN 2590-1230. https://doi.org/10.1016/j.rineng.2024.102890.
Jasiulewicz-Kaczmarek, M., & Gola, A. (2019). Maintenance 4.0 Technologies for Sustainable Manufacturing – an Overview. IFAC-PapersOnLine, 52(10), 91-96. ISSN 2405-8963. https://doi.org/10.1016/j.ifacol.2019.10.005.
Kruczek, P., et al. (2019). Predictive Maintenance of Mining Machines Using Advanced Data Analysis System Based on the Cloud Technology. In Widzyk-Capehart, E., Hekmat, A., & Singhal, R. (eds), Proceedings of the 27th International Symposium on Mine Planning and Equipment Selection – MPES 2018. Springer, Cham. https://doi.org/10.1007/978-3-319-99220-4_38.
Putha, S. (2022). AI-Driven Predictive Maintenance for Smart Manufacturing: Enhancing Equipment Reliability and Reducing Downtime. Journal of Deep Learning in Genomic Data Analysis, 2(1), 160–203. Accessed Nov. 11, 2024. https://thelifescience.org/index.php/jdlgda/.
Rihi, A., Baïna, S., Mhada, F.-Z., Elbachari, E., Tagemouati, H., Guerboub, M., & Benzakour, I. (2022). Predictive maintenance in mining industry: grinding mill case study. Procedia Computer Science, 207, 2483-2492. ISSN 1877-0509. https://doi.org/10.1016/j.procs.2022.09.306.
Salami, O. B., Xu, G., Kumar, A. R., & Pushparaj, R. I. (2023). Underground mining fire hazards and the optimization of emergency evacuation strategies (EES): The issues, existing methodology and limitations, and way forward. Process Safety and Environmental Protection, 177, 617-634. ISSN 0957-5820. https://doi.org/10.1016/j.psep.2023.07.012.
Suhail, A.,H., Guangul, M., Nazeer, A. (2024). Advanced System Diagnostics Tools: Innovations and Applications. IntechOpen. doi: 10.5772/intechopen.114378.
Weyers, E. (2021). The use of drones to improve downtime management on South African mines [University of Johannesburg]. https://ujcontent.uj.ac.za/esploro/outputs/graduate/The-use-of-drones-to-improve/9918409407691#file-0.
Wu, Y., Chen, M., Wang, K., and Fu, G. (2019) “A dynamic information platform for underground coal mine safety based on internet of things,” Safety Science, vol. 113, pp. 9-18, https://doi.org/10.1016/j.ssci.2018.11.003.
Zhang, R., Hao, G., Zhang, K., & Li, Z. (2023). Unmanned aerial vehicle navigation in underground structure inspection: A review. Geological Journal, 58(6), 2454–2472. https://doi.org/10.1002/gj.4763
