The DiG_IT project has reached its conclusion
Author: Valia Iliopoulou
6th May 2025
After 4 and a half years, the DiG_IT project, which aimed at the transition to the Sustainable Digital Mine of the Future, is concluded. The main goal of the project was to address the needs of the mining industry to move forward towards a sustainable use of resources while keeping people and environment at the forefront of their priorities.
To this end, our consortium built an Industrial Internet of Things platform (IIoTp) which collects data from the mining industry (from humans, machines, environment and market) and transforms them into knowledge and actions. The aim of our IIoTp was to improve worker health and safety, making operations more efficient and minimising the environmental impact of mining.
The CORE team had a broad role in the project and contributed to the development of key components of the platform.
Safety Toolbox: Biosignal Analytics and Anomaly Detection
CORE was responsible for designing two out of the three components of the Intelligent safety toolbox that provides insights and supports the prevention of hazardous situations for people’s health in the mining field. The first component is the Biosignal Analytics & Anomaly Detection agent that is part of the Safety monitoring system of the Decision Support System (DSS).
The Biosignal Analytics component is a cloud agent responsible for monitoring and detecting changes in the health state of the individuals that work inside the mines. The system utilises the biometrical data from the smart garments and pairs them with Anomaly Detection models that operate in real-time, to detect any possible alerting states in the health of the miners.
Safety Toolbox: Air-quality smart monitoring and forecasting
The second component of the safety toolbox is the Air-quality smart monitoring and Forecasting agent, that is part of the Environmental and Safety monitoring system of the DSS. The agent is responsible for providing predictions of the air quality KPIs, meaning forecasting how specific air-quality substances are going to progress in the future.
This is useful for safety reasons, like notifying that a section of the mine should be evacuated when a dangerous substance exceeds the accepted limits. The development of the agent is based on Multi-Variate Neural Networks that are trained from data gathered from sensors that are deployed inside the mines.
Examples of actual and forecasted values for NO2
Analysis of target variables per hour
Predictive Operation System I
One of our team’s primary roles was the development of a Predictive Operation System that utilises AI architectures. The system consisted of a forecasting agent that predicts the consumption of an individual asset. The knowledge of anticipated consumption is critical for planning of the field operations and optimising the industrial processes.
Our team relied on COREbeat, our end-to-end predictive maintenance platform, to assist Marini Marmi, a historic marble quarry in the north of italy, with the operation of one of their critical assets. COREbeat was installed on an electrical supplied milling machine utilized for cutting though marble cubes producing marble slices. During the project, the operators received critical warnings from COREbeat. CORE team investigated and indicated the origin of the fault to Marini operators, who decided to halt the machine's operation and placed it in maintenance mode, preventing further damage to the machine.
More information on how COREbeat assisted the staff at Marini can be found here.
Predictive Operation System II
CORE was also primarily responsible for a Predictive Maintenance system that utilises Machine Learning methods and techniques. The system was designed to focus on individual assets, enabling the assessment of their overall health and the prediction of their future states in real-time. The assets selected for predictive maintenance were paired with Anomaly Detection models, specifically designed for the asset type, to maintain input consistency between applications. The goal was to create alerts that can provide early warnings to users about possible failures of the operating equipment.
Anomaly scores and anomaly thresholds of the test set
Commercialisation phase
To ensure successful commercialization, CORE’s dedicated team developed an Innovation Strategy, focusing on clear value propositions and competition mapping. The main findings show that European Economy will need to multiply its production of critical raw materials, due to the increasing digitalisation of the economy and use of renewables. Therefore, AI solutions are obligatory, if mining industry companies want to optimise operations as well as offer environmental protection but also health and safety to their employees.
Additionally, CORE developed business models for two key innovations introduced by the project, the DiG_IT IoT Platform, for mining operations optimisation, online measurements and failure predictions, and the Dig_IT Smart Garment, for improved safety and reduced risk of accidents and injuries, the two innovations with the highest TRL exposed in real conditions.
