The core of the tunnel boring machine is a metal structure at its front, responsible for the destruction of rock, retraction of the excavation, and the forward movement of the machine. This shield structure is composed of numerous elements such as cutters, spheres, and wheels. These components are vital for the machine's functionality but are also consumables that wear out and need timely replacement. Failure to replace these parts promptly can lead to machine breakdowns, project delays, and increased operational costs.

To address this challenge, a software solution was developed to automate the process of monitoring and controlling the timeliness of component replacement. This system visualizes the TBM with all its components and allows the entry of manual inspection results regarding the technical condition of these parts. The software's standout feature is its predictive algorithm, which estimates the wear of components based on the history of technical works, enabling proactive maintenance.

The developed predictive maintenance system leverages a sophisticated algorithm that analyzes historical data on component usage and maintenance records. By studying patterns and trends in this data, the system can forecast when a component is likely to wear out and needs replacement.

This approach provided several advantages over traditional maintenance methods, which rely on fixed schedules or reactive repairs after a failure occurs. With predictive maintenance, maintenance tasks started to be performed just in time, reducing unnecessary replacements and minimizing downtime.

The predictive maintenance strategy aims to minimize unplanned downtime by accurately forecasting potential breakdowns. Companies must avoid such occurrences, as the repercussions can severely harm their reputation and financial health. Unplanned downtime can significantly delay project implementation, resulting in catastrophic financial losses, as demonstrated by an incident in the US in 2013*.

• Increased efficiency and Reduced downtime: By predicting wear and scheduling maintenance proactively, the system ensures that the TBM operates with minimal interruptions.
• Enhanced safety: Regular and timely maintenance reduces the risk of equipment failure, ensuring a safer working environment for operators and technicians.
• Cost savings: Avoiding emergency repairs and extending the life of components results in significant cost savings.
• Improved planning and Resource allocation: Maintenance activities are now better planned and resources allocated more efficiently, leading to smoother project execution.

A real-life case study demonstrated the system's success. In a major tunneling project, the predictive maintenance system significantly reduced downtime and maintenance costs, while improving overall efficiency. Users reported high satisfaction with the system’s ability to predict component wear accurately and schedule maintenance proactively.

The future of predictive maintenance for tunneling equipment looks promising, with potential advancements including:

1. Integration with IoT: Enhanced data collection and real-time monitoring using IoT devices.
2. Machine learning enhancements: Improved predictive algorithms through machine learning, increasing accuracy and reliability.
3. Automated maintenance robots: Deployment of robots to perform maintenance tasks based on predictions, further reducing human intervention and risk.

Predictive maintenance offers a transformative approach to maintaining tunneling equipment, addressing the challenges of wear and tear on critical components. The software solution discussed provides a robust framework for ensuring the timely replacement of consumable parts, enhancing efficiency, safety, and cost-effectiveness in tunneling projects. Companies looking to adopt predictive maintenance solutions can benefit greatly from these advancements.

If you find yourself with lingering questions or are navigating similar challenges in adopting predictive maintenance solutions for tunneling equipment, we are here to assist you. Our expertise in integrating IoT, advancing machine learning algorithms, and implementing automated maintenance solutions can provide clarity and guidance.

Embracing these innovations ensures not only enhanced operational efficiency and safety but also positions your projects at the forefront of technological advancement in tunneling. Feel free to reach out for further insights or to discuss how these strategies can be tailored to meet your specific needs.


Sources:
[1] Lindblom, M. (2019, April 30). Contractor ordered to pay state over tunnel-boring machine Bertha’s big stall. The Seattle Times. Retrieved from https://www.seattletimes.com/seattle-news/transportation/contractor-ordered-to-pay-state-over-tunnel-boring-machine-berthas-big-stall/.
[2] Market Research Future. (n.d.). Tunnel Boring Machine Market Size was valued at USD 6.75 Billion in 2022 and is projected to grow from 7.5 Billion in 2024 to 9.25 Billion by 2030. Market Research Future. Retrieved from https://www.marketresearchfuture.com/reports/tunnel-boring-machine-market-10218