IBM, Theiss use big data to predict mining gear failure
IBM and Australian contract mining group Theiss have teamed up to use big data to improve mining operational productivity and machine availability.
The collaboration will aim to use predictive analytics and modelling technologies to improve efficiency and asset management, with an initial focus on Theiss's mining trucks and excavators.
Announcing the deal, the companies said many natural resource industries have been slow to invest in operational IT systems and are still relying too heavily on a fix-it-when-it-breaks or a time-based approach to machine maintenance. This can result in premature part replacements, unnecessary downtime and extra expense.
But the sector is starting to recognise how IT can help them with their core exploration and extraction operations.
IBM Research and Theiss have been focused on integrating machine sensor data, maintenance history and operational and environmental factors to optimise the maintenance process.
Using a technique the companies call predictive machine management, Theiss aims to be able to use even minor anomaly and malfunction patterns to predict the likelihood of a component failure.
The companies' comments support the recent assertion by Deloitte that the mining sector is taking the lead in terms of big data adoption in Australia.
Theiss is a wholly owned subsidiary of Leighton Holdings.
The hidden legal risk in your AI workflow
Australia's new privacy tort just made your AI workflow a legal liability.
Secure by Design: vital in an evolving threat landscape
By embedding security into the fabric of development, Australian business can not only comply...
Keeping IT teams resilient by reducing complexity
Architectural diversity, API sprawl and fragmented tooling make it difficult for IT teams to see...