The winning Digi-MIN team consisting of three Gekko representatives (graduate process engineer Eliza Craig, graduate metallurgist Barry Tuncks and mechanical designer Matt Kurtze) and Monash University student Daniel Bechaz.
By Elizabeth Fabri
GEKKO Systems has partnered with Rockwell Automation to develop a metallurgical software program that will account for metal content at various stages of ore processing and provide miners with analytic capabilities to audit and improve performance.
In late February the two companies signed a Memorandum of Understanding (MoU), and had now progressed to the development and pilot stage of the project.
Gekko global mining and processing services manager Renaldo Maras said the company was pleased to be collaborating with Rockwell Automation; a company it had worked with at length over the last 15 years.
“It is exciting for Gekko Systems to be associated with Rockwell Automation in what we believe to be a significant opportunity to assist the mining industry to make sense from valuable data that is often lost or not easily accessible for analysis.” Mr Maras said.
Rockwell Automation Gekko account manager Steve Simpkin said he was “delighted to have the opportunity to help co-develop this Connected Mine software solution with Gekko Systems”.
“This is the culmination of our ongoing 15 plus year relationship and the exploitation of technology and industry trends towards the Industrial Internet of Things.
“This is a solution that ultimately will help benefit our respective clients.”
In late March the Gekko team won the 2017 Melbourne Unearthed Hackathon, a 54-hour open innovation event which gathered software developers, engineers and designers into teams to develop prototype technologies to solve one of four challenges provided by Newcrest Mining.
The winning Digi-MIN team consisting of three Gekko representatives and a Monash University student tackled unplanned downtime and rate interruption events within its Newcrest’s concentrators at Cadia.
“We developed a tool that flags small variations in the correlation between two related variables,” graduate process engineer Eliza Craig said.
“We demonstrated that the correlation between two variables in the HPGR changed several times before a single downtime event and our algorithm was able to flag this more than 24 hours in advance.
“The algorithm is robust enough that it can easily be applied to any two related variables across any piece of equipment or site.
“By flagging small changes in the correlation in real time, equipment can be inspected and downtime can be planned. This can drastically reduce the cost and impact of unplanned downtime on site.”
