Dingo is to introduce practical machine learning models built using real customer data and targeted at specific industry problems from January, the company has announced.

“Dingo has spent the last 12 months developing and refining machine learning models, in collaboration with Queensland University of Technology, to detect anomalies in condition monitoring data in Dingo’s OEM-independent global asset health database,” the company said.

These models highlight anomalous behaviour in the data and will be available to users of Trakka®. As more quality component failure data is added to the data set, the accuracy of the anomaly detection models will improve, according to Dingo.

“By detecting anomalies automatically, it will allow our users to:

• “Detect developing issues well before traditional engineering limits are reached;
• “Find slight changes in data trends, not discernable to a human analyst;
• “Act faster to correct abnormalities and restore equipment to normal operating condition.”

Dingo says Trakka is a powerful, cloud-based predictive maintenance software system designed to house all of asset health data under one roof. The solution provides operations with the tools, insights, and decision-support to run a best-in-class asset health programme, according to the company.

Further to this announcement, Dingo is also developing sophisticated predictive analytics models aimed at forecasting the remaining useful life of assets. Due for release in June 2019, Trakka users will have access to valuable analytical information about the Probability of Failure and Degradation Indexes, the company said.

“These models are built by Dingo subject matter experts for common asset specific failure modes, eg Engine piston ring wear. They are designed with scalability in mind and can be easily retrained to work with a broad range of asset/failure mode problems experienced by real mining operations, making them highly reusable without further development,” Dingo said.

“By creating an accurate Remaining Useful Life model, it will allow our users to:

• “More confidently plan component replacements;
• “Optimise repair costs when components are nearing end of life;
• “Improve related processes such as budgeting and supply chain logistics and management.”