02/10/2024 – As part of the Dig_IT project, Task 4.1 led by Tampere University (TAU) has been successfully completed, marking a significant achievement in developing Digital Twins for individual mining assets and a System-of-Systems (SoS) digital twin for entire mining operations. This task plays a crucial role in simulating mining processes to enhance operational efficiency, reliability, and safety in the industry.
The journey to develop these digital twins was a collaborative effort, with Tapojärvi and Titania, two key end users, playing a critical role in shaping the final outcome by offering valuable feedback from real-world mining environments.
What are Digital Twins, and why wre they important?
At its core, a Digital Twin is a digital replica of a physical asset. In the context of Task 4.1, we developed digital twins of several mining machines, simulating the physical phenomena that occur as these machines operate in the mine. These simulations aren’t just theoretical. They rely on real-time measurement data obtained from Gateway devices attached to machine sensors, along with a 3D model of the mine’s terrain. This combination of real-world data and simulated environments allows us to understand exactly what a machine is doing, where it is, and what kind of stress it’s experiencing in the moment.
The results from these simulations, including probabilistic calculations of machine reliability and availability, are aggregated at multiple levels: individual machines, entire fleets, and at the broader System-of-Systems level for the mine. This data, combined with detailed analysis, is then fed into the Decision Support System (DSS), where it’s presented in a clear, actionable format for mining operators.
How does this help mining operations?
Imagine being able to predict when a machine might fail or knowing which areas of the mine are causing the most wear and tear on your equipment. This is exactly what the digital twins allow operators to do. By visualizing the data through heatmaps and statistical overlays on the mine’s map, operators can quickly identify problem areas—whether it’s a bottleneck with high idle times, an area of the mine that’s particularly tough on equipment, or even spots where machines are consuming more energy than expected.
This level of insight not only helps operators make more informed decisions but also ensures that they can take proactive steps to prevent costly breakdowns and optimize performance.
A broader impact on the Dig_IT Project
The work achieved in Task 4.1 doesn’t exist in isolation. The data generated from these digital twins feeds directly into other critical areas of the Dig_IT project. For example, the Predictive Maintenance Agents developed in Task 5.5 rely on this information to anticipate when maintenance is needed. Similarly, the Decision Support System (DSS), developed in Task 5.6, leverages this data to create a comprehensive view of the mine’s operations.
This interconnected approach ensures that the insights from Task 4.1 extend beyond individual machines and become part of a larger system designed to make mining smarter, safer, and more efficient.
The tools behind the twins
Creating these digital twins required a robust set of tools. OpenModelica was used for simulations, while Python libraries like FMPy, Pandas, and Scipy were instrumental in processing the data. These tools allowed us to model complex physical phenomena and generate highly accurate simulations that reflect real-world conditions in the mine.
Looking ahead
With Task 4.1 now completed, the focus is on continuing to integrate these digital twins into the broader Dig_IT framework. This means more detailed simulations, more data, and ultimately, more insight into how to improve mining operations. The next steps will include refining the models and ensuring that the insights gained are fully utilized by all relevant stakeholders.
In the meantime, you can expect to see these digital twins in action, visualized through heatmaps and other interactive tools in the DSS. These are still works in progress, but they are already giving operators a new way to understand and manage their machinery and resources.
About Dig_IT
Dig_IT project aims to develop a human-centered IIoT platform connecting the mining ecosystem of assets, environment, and humans to increase mining efficiency: saving costs using optimized scheduling, increasing uptime using predictive operation and maintenance, and identifying new revenue opportunities using advanced geological interpretation on exploration mining phase. To address industry needs of minimizing accidents, optimizing production processes, and reducing costs, intelligent systems will provide real-time insights for the enterprise at all operational levels.
For more information about the Dig_IT Project and to stay updated on its progress, please visit digit-h2020.eu.
Contact
María García Camprubí
Project Coordinator
ITAINNOVA: Technological Institute of Aragon
info@digit-h2020.eu