Dingo’s Trakka® Earns Mining Magazine Award for Best Software
This was originally published by Dingo.
Solution triumphed over stiff competition to win prestigious honour for mining technology advancements
QUEENSLAND, AUSTRALIA – Proving next-generation value innovation is its constant, overarching mission, global predictive maintenance leader Dingo has been awarded the honour of best software development in 2019 from the industry community and editors of top global trade publication Mining Magazine for Trakka® Predictive Analytics.
Development entailed about two years' work and resulted in a final product that marries state-of-the-art machine learning technologies with maintenance expertise to predict impending equipment failures with a high degree of accuracy.
This foresight allows customers to perform corrective maintenance at the optimal time, significantly reducing downtime and optimising the lifespan of the asset.
According to Dingo Director of Product Engineering Colin Donnelly, "Trakka's capabilities equip miners with the knowledge to make maintenance decisions based on a component's current health and what companies themselves determine as most cost and time-efficient."
The Trakka Predictive Analytics solution consists of two distinct but equally important software models: Anomaly Detection and Remaining Useful Life.
The Anomaly Detection system was the culmination of 12 months' worth of joint work by Dingo and Queensland University of Technology. This system detects abnormalities well before equipment's traditional engineering limits are reached, enabling maintenance teams to address issues earlier and quickly restore equipment to normal operating condition.
The Remaining Useful Life model predicts how long assets are likely to remain in operation and provides detailed analytical information through its Probability of Failure and Degradation indices. The result is enhanced ability to confidently plan component replacements, optimise repair costs, and improve related processes, such as budgeting and supply chain management.
Donnelly said Dingo's competitive edge lay in its use of actual failure data to resolve equipment issues for its customers, in addition to its direct integration with enterprise resource planning and computerized maintenance management systems.
"We can more easily translate results generated by models into the next steps companies need to take to maximise the health and life of their equipment with minimal cost and interruption," Donnelly said.
Given Dingo's resolute focus on using real-world data, it is not surprising that Trakka has already returned some concrete results.
Some examples include: determining remaining useful life (RUL) to find wear failures on Caterpillar 789C & D haul truck final drives for a Top 10 global miner's Central America gold operations; collaborations with several North American-based operators on models to address high-frequency failure modes; the detection of con rod-bearing failures in Cummins QSK60 engines for large gold and copper mines in North America; identification of valve failures in Caterpillar 3516 engines for a large North American gold miner; piston liner wear in Caterpillar 3516 engines for a major South American coal mine; and gearbox and pinion bearing failure prediction at milling applications in Australia.
Dingo remains committed to its primary innovation mission: solving real problems for real people.
As noted by Chief Information Officer Gary Fouché, while many systems built by other companies make lofty claims about their predictive analytics capabilities, they are missing the most vital element: practical application.
“There is a big difference between passing data through a generic analytics platform and Dingo's solution. We work with customer failure data to develop models designed to help them gain better insight into the underlying issues so they can address the root cause,” he said.
“Dingo is currently working in collaboration with its customers to prioritise and build more AI models to address a broader range of problems and expand the predictive and prescriptive analytics capability within Trakka,” Fouché said. “We are also extending Trakka’s machine learning capabilities to other areas, including the deployment of AI models to the edge or in the field.”
“By tapping into the power of predictive analytics, miners will be able to anticipate the future and proactively manage equipment maintenance, while reaping huge productivity, planning and safety benefits in the process.”
More information on the Dingo award-winning Trakka Predictive Analytics solution is available at http://www.dingo.com/solutions/predictive-analytics.