MINE SAFETY
Tracking the trends means we are not satisfied with the status quo and we are always working to improve the OAS .”
Meglab ’ s IMAGINE software is able to locate and track different assets from surface ( credit : Meglab / Agnico Eagle )
In the COVID-19 era , safety on mine sites is
front and centre of the minds of mine managers and executive teams . Prevention , diagnosis and self-isolation are the three main areas mining companies are pursuing in order to keep employees and communities safe , and operations running .
As Josh Savit , Product Manager-OAS at Hexagon Mining , says , “ the global pandemic has changed the landscape of the mining industry , increasing the stress in an already stressful environment ”.
This has seen many mines mandate that their employees wear face masks . This includes vehicle operators .
While masks reduce the risk of COVID-19 transmission , they also present a new challenge for safety , especially for fatigue and distraction detection , according to Savit .
In 2019 , Hexagon launched HxGN MineProtect Operator Alertness System Light Vehicle ( OAS-LV ) to address the need for a fatigue and distraction solution for pick-ups , buses , and other vehicles outside of those classified ‘ off-highway ’. This system is based on the same proven technology used in OAS-HV , which protects operators of haul trucks at mine sites .
Both feature the most advanced fatigue and distraction algorithm , according to Savit , an algorithm that is now equipped to deal with the problems some fatigue management and distraction detection systems are experiencing with COVID-19-appropriate face masks .
The advancement of this algorithm stemmed from a client request made during the development of OAS . This client requested the solution identify fatigue and alertness events while the operator wears a dust mask , or other face covering .
Solving this request was far from easy , according to Savit .
“ Most face trackers rely on limited data points ,
requiring the full face to be visible ,” he said in a
Identifying hazards , locating personnel and vehicles , optimising mine rescues , fire suppression and more in this year ’ s annual safety review , compiled by Dan Gleeson
blog post . “ A face mask , therefore , renders face trackers inoperable . The ability to focus is stuck in a continuous loop , trying to establish the needed points . Events generated are false positives because the system can only lock on to a greatly reduced number of data points .”
The OAS 6.1 algorithm , however , uses dynamic tracking , constantly readjusting and mapping the face with every movement , removing the data point requirement , according to Savit .
“ This is possible due to the OAS machinelearning library ,” he said . “ With more than 400,000 images to reference , the algorithm can create millions of unique models . By modelling beyond a standard dust mask to include
everything from turtlenecks to respirators , the library grows . This allows Hexagon ’ s face tracker to adapt and focus on key facial components ; eyes and forehead , for example .” Savit expanded on the system ’ s abilities for
IM : “ The machine-learning algorithm can visualise the face as if the mask is not there . It also uses an increased number of data points
from the upper face to create a dynamic image .”
Enhancements to the algorithm , combined with the continual growth of the machinelearning capabilities , mean operators can wear face masks while still being monitored for signs of fatigue and distraction , Savit says .
“ Subsequently , overall performance of the system has improved ,” he said .
This feature is a differentiator , according to Savit , allowing the operators and operations to trust the alert and know the OAS system is accurately capturing the face .
He concluded : “ In my opinion , it ’ s a given that mask wearing will continue to proliferate in the mining sector . Hexagon ’ s commitment to safety
The next level
In the face of COVID-19 mine shutdowns in South Africa , Booyco Electronics has been advancing testing of its proximity detection systems ( PDS ) to comply with the Level 9 safety standards that will soon enter the law books .
The importance of this testing arises from recent changes in Chapter 8 of the Mine Health and Safety Act , which require mines to take “ reasonably practicable measures ” to prevent collisions between trackless mobile machines ( TMMs ) – as well as between pedestrians and TMMs .
Past measures implemented by mines have included systems that warn pedestrians of their proximity to TMMs ( Level 7 ) and systems that deliver an advisory instruction to TMM operators ( Level 8 ).
“ The Level 9 standard raises the bar significantly , requiring electronic PDS systems to take mechanical control of the TMM and automatically bring it to a stop when a dangerous situation is detected ,” Booyco Electronics CEO , Anton Lourens , said . “ This elevates what is traditionally called a PDS into what is really a collision avoidance – or collision management – system .”
Booyco Electronics says it was the first to begin Level 9 testing in South Africa , which is conducted by the University of Pretoria ’ s Vehicle Dynamics Group . The tests are aligned with the international standard ISO21815 . Regulations regarding Level 9 compliance are expected to be finalised by the end of 2020 .
Lourens says the company ’ s strong relationship with TMM OEMs has allowed it to make good progress in testing Booyco ’ s equipment on their machines in terms of Level 9 standards . “ This ensures that our technology can assist to safely and effectively bring a vehicle to a standstill when required ,” he said .
He highlighted that the parameters of Level 9 control have evolved over the past year or two .
Enhancements to the OAS 6.1 algorithm , combined with the continual growth of the machine-learning capabilities , mean operators can wear face masks while still being monitored for signs of fatigue and distraction , Hexagon says
26 International Mining | OCTOBER 2020