A combination of artificial intelligence (AI) and the Internet of Things (IoT) looks set to revolutionise the way ventilation networks for underground mining operations are designed and monitored.
AI offers the capability to discern hidden patterns, adapt to changing conditions and provide forecasts amidst uncertainty when it comes to the continuous supply of fresh air to all below-surface extraction activities.
Although the development of intelligent ventilation is not exactly a new concept, it has gathered momentum in the past decade and, in effect, has collectively become part of a multifaceted international research objective.
With the consumption of mineral resources constantly growing, accompanied by a continual expansion in mining capacity, project proponents are branching out, with underground mining operations increasing their level of harmful emissions.
According to the Mining Institute of the Ural Branch of the Russian Academy of Sciences, complex mine ventilation network analysis relies heavily on analytical tools and software systems, while improving ventilation necessitates numerical simulation to manage airflows and pollutants. Combined, as earlier research has observed, they are intricate, with numerous degrees of freedom.
“Constructing mathematical models for such networks proves challenging due to substantial input data errors from field measurements and unpredictable aerodynamic factors,” the academy’s Mikhail Semin and Denis Komshchikov noted. “This compels engineers and scientists to seek novel approaches to ventilation issues. “AI has emerged as one such approach.
“Mine ventilation, employing AI technologies, plays a crucial role in predicting harmful impurity release and emergency situations like fires. “However, pinpointing emission locations and quantities can be challenging due to geological, geographical and operational factors.”
Semin and Komshchikov said it is known that deterministic methods are more effective in the study of corresponding physical processes, while heuristic and intelligent approaches demonstrate efficiency in tasks where an explicit connection between the studied parameters and phenomena is not readily apparent. “It is in this context that AI technologies are being integrated into mine ventilation systems today,” they noted.
“Physical processes within mine atmospheres are well understood by engineers and scientists and are typically modelled using deterministic approaches, such as solving systems of Kirchhoff equations (which see the absorption of heat as relieving the stress caused by rising temperatures) to determine air distribution and solving differential equations for convective-diffusion transfer of heat and harmful impurities through mine workings.
“However, the mine ventilation network is a complex system with numerous unpredictable and unaccounted factors. “Analysing these factors within deterministic frameworks often proves challenging or leads to failure, making heuristic approaches and machine learning methods more suitable.” One interesting question, Semin and Komshchikov posed, is how many measuring stations are needed to correctly assess air distribution in the entire operation while accurately determining the location of resistance failures in mine airways.
The answer depends on the number of branches in the ventilation network, and topology features such as through-flow and U-tube ventilation layouts should also be considered. A change in the air resistance of mine airways, they pointed out, is not the only unaccounted factor that could lead to alterations in air distribution within a mine ventilation network. Previous research indicates that other possible reasons for observed deviations in measured air velocities at measuring stations could also include thermal and gas depression.
“For example, unaccounted-for heat and gas emissions from mining equipment, as well as gas emissions from rock masses, can also significantly impact mine air distribution,” they said. Another promising area for utilising AI in mine ventilation may be determining the shock losses of mine airways when calculating air distribution. Last year, Semin highlighted the importance of shock loss factors, especially in airways with large cross-sections. Existing approaches to calculating shock losses, however, lack both sufficient accuracy and versatility – particularly in their applicability to various types of mine airway junctions.
“The use of surrogate modelling could facilitate the selection of an approximating function for shock loss factors based on mine airway parameters, potentially providing accurate solutions across a wide range of mine airway junctions,” Semin and Komshchikov said. “We anticipate that the utilisation of intelligent methods for solving mine ventilation problems will increase in the future. “This trend will be propelled by advancements in computing power and the emergence of new, more efficient AI technologies. “Recognising the existing gaps, AI will be progressively deployed across a broader spectrum of mine ventilation challenges.”
In terms of IoT, one innovation is the ZigBee Wireless Sensor Networks (WSN) technology, a system that transmits data over long distances by passing it through a mesh network of intermediate devices to reach more distant ones. Under this regime, sensors are used to capture the environmental variables that in turn are used for data acquisition. These sensor signals are then converted into electrical ones, which receive the sensor-generated information and send it to a wireless network access plant.
Research has indicated that the narrow space of an underground environment significantly enhances the signal intensity and, as a result, ZigBee can have a great advantage in the deep. Evidently – according to research published in 2021 – the application of ZigBee WSN technology is becoming more and more popular for underground mines as it has good information collection capabilities for things like harmful gas concentration and temperature, which in turn can provide signals for intelligent mine ventilation systems.
As a result, in the future, ZigBee WSN technology is likely to become a medium for information transmission in intelligent mine ventilation due to its three characteristics – suitability for underground mines, low energy consumption and good performance when it comes to the collection of information.
